diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..38dfff0f16e89369f5f3a7712ebe4988ce478c6f 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-879/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9633d8f0130799d996b640335cd6d3846c495f5b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,209 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+
+
+
+
+## Model Details
+
+### Model Description
+
+
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+
+
+### Direct Use
+
+
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+
+
+[More Information Needed]
+
+### Recommendations
+
+
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+
+
+[More Information Needed]
+
+### Training Procedure
+
+
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed]
+
+#### Speeds, Sizes, Times [optional]
+
+
+
+[More Information Needed]
+
+## Evaluation
+
+
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+
+
+[More Information Needed]
+
+#### Factors
+
+
+
+[More Information Needed]
+
+#### Metrics
+
+
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+
+
+[More Information Needed]
+
+## Environmental Impact
+
+
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0
\ No newline at end of file
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..45edbb77201d4198da4bf26b8a7258da2bca8d90
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,50 @@
+{
+ "alora_invocation_tokens": null,
+ "alpha_pattern": {},
+ "arrow_config": null,
+ "auto_mapping": null,
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+ "bias": "none",
+ "corda_config": null,
+ "ensure_weight_tying": false,
+ "eva_config": null,
+ "exclude_modules": null,
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 32,
+ "lora_bias": false,
+ "lora_dropout": 0.05,
+ "lora_ga_config": null,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "monteclora_config": null,
+ "peft_type": "LORA",
+ "peft_version": "0.20.0",
+ "qalora_group_size": 16,
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_proj",
+ "k_proj",
+ "down_proj",
+ "up_proj",
+ "gate_proj",
+ "o_proj"
+ ],
+ "target_parameters": null,
+ "task_type": "CAUSAL_LM",
+ "trainable_token_indices": null,
+ "use_bdlora": null,
+ "use_dora": false,
+ "use_qalora": false,
+ "use_rslora": false,
+ "velora_config": null
+}
\ No newline at end of file
diff --git a/adapter_model.safetensors b/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ae6703c0a7630f91d92d75ebbdd48a896758d3dc
--- /dev/null
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac73482dab07a18e9416036be9875bd9965b5fbb11900b7e33bf7618fb628c6
+size 167832240
diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9633d8f0130799d996b640335cd6d3846c495f5b
--- /dev/null
+++ b/checkpoint-200/README.md
@@ -0,0 +1,209 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+
+
+
+
+## Model Details
+
+### Model Description
+
+
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+
+
+### Direct Use
+
+
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+
+
+[More Information Needed]
+
+### Recommendations
+
+
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+
+
+[More Information Needed]
+
+### Training Procedure
+
+
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed]
+
+#### Speeds, Sizes, Times [optional]
+
+
+
+[More Information Needed]
+
+## Evaluation
+
+
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+
+
+[More Information Needed]
+
+#### Factors
+
+
+
+[More Information Needed]
+
+#### Metrics
+
+
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+
+
+[More Information Needed]
+
+## Environmental Impact
+
+
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0
\ No newline at end of file
diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..45edbb77201d4198da4bf26b8a7258da2bca8d90
--- /dev/null
+++ b/checkpoint-200/adapter_config.json
@@ -0,0 +1,50 @@
+{
+ "alora_invocation_tokens": null,
+ "alpha_pattern": {},
+ "arrow_config": null,
+ "auto_mapping": null,
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+ "bias": "none",
+ "corda_config": null,
+ "ensure_weight_tying": false,
+ "eva_config": null,
+ "exclude_modules": null,
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 32,
+ "lora_bias": false,
+ "lora_dropout": 0.05,
+ "lora_ga_config": null,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "monteclora_config": null,
+ "peft_type": "LORA",
+ "peft_version": "0.20.0",
+ "qalora_group_size": 16,
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_proj",
+ "k_proj",
+ "down_proj",
+ "up_proj",
+ "gate_proj",
+ "o_proj"
+ ],
+ "target_parameters": null,
+ "task_type": "CAUSAL_LM",
+ "trainable_token_indices": null,
+ "use_bdlora": null,
+ "use_dora": false,
+ "use_qalora": false,
+ "use_rslora": false,
+ "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-200/adapter_model.safetensors b/checkpoint-200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..16c21e557c2a4531fff980e26e7e706ad9822cda
--- /dev/null
+++ b/checkpoint-200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d405e3ae88fa2813a3ee78b66a7a0c5e03e899611495ab2506fa1f7ed9dfea
+size 167832240
diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..56179d16e4e1b8f46bc237af50706ddd11116760
--- /dev/null
+++ b/checkpoint-200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa64d2cf898f55baeac5c8c3c99474f4a91c6c937ef8817baf4e9eadbb6b45e
+size 85727828
diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4e7a1892d00a5a9101796f82cee69650623de0cf
--- /dev/null
+++ b/checkpoint-200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39589146f58675d323c28a7637c2b197c2470f377bdc1b580174509beea1240
+size 14244
diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a6934d389a6b865ef182c29e9a1f1fd268a8bdf8
--- /dev/null
+++ b/checkpoint-200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0a841d0fa965ade7dbf3a34a1021756a215f73311c59e711208417d012e806
+size 1064
diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fed0491bb0ae0c4f0752f54ffddf7d69269daed
--- /dev/null
+++ b/checkpoint-200/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+ "bos_token": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|im_end|>"
+}
diff --git a/checkpoint-200/tokenizer.json b/checkpoint-200/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b
--- /dev/null
+++ b/checkpoint-200/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
+size 17209403
diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1dbecde59340b33dcf97ef6087584a5a01208ab5
--- /dev/null
+++ b/checkpoint-200/tokenizer_config.json
@@ -0,0 +1,2072 @@
+{
+ "added_tokens_decoder": {
+ "128000": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128001": {
+ "content": "<|end_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128002": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128003": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128004": {
+ "content": "<|finetune_right_pad_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128005": {
+ "content": "<|reserved_special_token_2|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128006": {
+ "content": "<|start_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128007": {
+ "content": "<|end_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128008": {
+ "content": "<|eom_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128009": {
+ "content": "<|eot_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128010": {
+ "content": "<|python_tag|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128011": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128012": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128013": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128014": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128015": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128016": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128017": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128018": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128019": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128020": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128021": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128022": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128023": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128024": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128025": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128026": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128027": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128028": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128029": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128030": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128031": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128032": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128033": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128034": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128035": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128036": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128037": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128038": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128039": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128040": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128041": {
+ "content": "<|reserved_special_token_33|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128042": {
+ "content": "<|reserved_special_token_34|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128043": {
+ "content": "<|reserved_special_token_35|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128044": {
+ "content": "<|reserved_special_token_36|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128045": {
+ "content": "<|reserved_special_token_37|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128046": {
+ "content": "<|reserved_special_token_38|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128047": {
+ "content": "<|reserved_special_token_39|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128048": {
+ "content": "<|reserved_special_token_40|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128049": {
+ "content": "<|reserved_special_token_41|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128050": {
+ "content": "<|reserved_special_token_42|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128051": {
+ "content": "<|reserved_special_token_43|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128052": {
+ "content": "<|reserved_special_token_44|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128053": {
+ "content": "<|reserved_special_token_45|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128054": {
+ "content": "<|reserved_special_token_46|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128055": {
+ "content": "<|reserved_special_token_47|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128056": {
+ "content": "<|reserved_special_token_48|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128057": {
+ "content": "<|reserved_special_token_49|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128058": {
+ "content": "<|reserved_special_token_50|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128059": {
+ "content": "<|reserved_special_token_51|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128060": {
+ "content": "<|reserved_special_token_52|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128061": {
+ "content": "<|reserved_special_token_53|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128062": {
+ "content": "<|reserved_special_token_54|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128063": {
+ "content": "<|reserved_special_token_55|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128064": {
+ "content": "<|reserved_special_token_56|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128065": {
+ "content": "<|reserved_special_token_57|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128066": {
+ "content": "<|reserved_special_token_58|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128067": {
+ "content": "<|reserved_special_token_59|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128068": {
+ "content": "<|reserved_special_token_60|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128069": {
+ "content": "<|reserved_special_token_61|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128070": {
+ "content": "<|reserved_special_token_62|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128071": {
+ "content": "<|reserved_special_token_63|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128072": {
+ "content": "<|reserved_special_token_64|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128073": {
+ "content": "<|reserved_special_token_65|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128074": {
+ "content": "<|reserved_special_token_66|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128075": {
+ "content": "<|reserved_special_token_67|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128076": {
+ "content": "<|reserved_special_token_68|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128077": {
+ "content": "<|reserved_special_token_69|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128078": {
+ "content": "<|reserved_special_token_70|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128079": {
+ "content": "<|reserved_special_token_71|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128080": {
+ "content": "<|reserved_special_token_72|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128081": {
+ "content": "<|reserved_special_token_73|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128082": {
+ "content": "<|reserved_special_token_74|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128083": {
+ "content": "<|reserved_special_token_75|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128084": {
+ "content": "<|reserved_special_token_76|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128085": {
+ "content": "<|reserved_special_token_77|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128086": {
+ "content": "<|reserved_special_token_78|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128087": {
+ "content": "<|reserved_special_token_79|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128088": {
+ "content": "<|reserved_special_token_80|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128089": {
+ "content": "<|reserved_special_token_81|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128090": {
+ "content": "<|reserved_special_token_82|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128091": {
+ "content": "<|reserved_special_token_83|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128092": {
+ "content": "<|reserved_special_token_84|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128093": {
+ "content": "<|reserved_special_token_85|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128094": {
+ "content": "<|reserved_special_token_86|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128095": {
+ "content": "<|reserved_special_token_87|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128096": {
+ "content": "<|reserved_special_token_88|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128097": {
+ "content": "<|reserved_special_token_89|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128098": {
+ "content": "<|reserved_special_token_90|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128099": {
+ "content": "<|reserved_special_token_91|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128100": {
+ "content": "<|reserved_special_token_92|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128101": {
+ "content": "<|reserved_special_token_93|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128102": {
+ "content": "<|reserved_special_token_94|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128103": {
+ "content": "<|reserved_special_token_95|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128104": {
+ "content": "<|reserved_special_token_96|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128105": {
+ "content": "<|reserved_special_token_97|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128106": {
+ "content": "<|reserved_special_token_98|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128107": {
+ "content": "<|reserved_special_token_99|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128108": {
+ "content": "<|reserved_special_token_100|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128109": {
+ "content": "<|reserved_special_token_101|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128110": {
+ "content": "<|reserved_special_token_102|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128111": {
+ "content": "<|reserved_special_token_103|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128112": {
+ "content": "<|reserved_special_token_104|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128113": {
+ "content": "<|reserved_special_token_105|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128114": {
+ "content": "<|reserved_special_token_106|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128115": {
+ "content": "<|reserved_special_token_107|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128116": {
+ "content": "<|reserved_special_token_108|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128117": {
+ "content": "<|reserved_special_token_109|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128118": {
+ "content": "<|reserved_special_token_110|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128119": {
+ "content": "<|reserved_special_token_111|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128120": {
+ "content": "<|reserved_special_token_112|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128121": {
+ "content": "<|reserved_special_token_113|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128122": {
+ "content": "<|reserved_special_token_114|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128123": {
+ "content": "<|reserved_special_token_115|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128124": {
+ "content": "<|reserved_special_token_116|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128125": {
+ "content": "<|reserved_special_token_117|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128126": {
+ "content": "<|reserved_special_token_118|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128127": {
+ "content": "<|reserved_special_token_119|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128128": {
+ "content": "<|reserved_special_token_120|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128129": {
+ "content": "<|reserved_special_token_121|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128130": {
+ "content": "<|reserved_special_token_122|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128131": {
+ "content": "<|reserved_special_token_123|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128132": {
+ "content": "<|reserved_special_token_124|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128133": {
+ "content": "<|reserved_special_token_125|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128134": {
+ "content": "<|reserved_special_token_126|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128135": {
+ "content": "<|reserved_special_token_127|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128136": {
+ "content": "<|reserved_special_token_128|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128137": {
+ "content": "<|reserved_special_token_129|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128138": {
+ "content": "<|reserved_special_token_130|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128139": {
+ "content": "<|reserved_special_token_131|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128140": {
+ "content": "<|reserved_special_token_132|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128141": {
+ "content": "<|reserved_special_token_133|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128142": {
+ "content": "<|reserved_special_token_134|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128143": {
+ "content": "<|reserved_special_token_135|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128144": {
+ "content": "<|reserved_special_token_136|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128145": {
+ "content": "<|reserved_special_token_137|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128146": {
+ "content": "<|reserved_special_token_138|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128147": {
+ "content": "<|reserved_special_token_139|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128148": {
+ "content": "<|reserved_special_token_140|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128149": {
+ "content": "<|reserved_special_token_141|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128150": {
+ "content": "<|reserved_special_token_142|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128151": {
+ "content": "<|reserved_special_token_143|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128152": {
+ "content": "<|reserved_special_token_144|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128153": {
+ "content": "<|reserved_special_token_145|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128154": {
+ "content": "<|reserved_special_token_146|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128155": {
+ "content": "<|reserved_special_token_147|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128156": {
+ "content": "<|reserved_special_token_148|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128157": {
+ "content": "<|reserved_special_token_149|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128158": {
+ "content": "<|reserved_special_token_150|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128159": {
+ "content": "<|reserved_special_token_151|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128160": {
+ "content": "<|reserved_special_token_152|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128161": {
+ "content": "<|reserved_special_token_153|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128162": {
+ "content": "<|reserved_special_token_154|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128163": {
+ "content": "<|reserved_special_token_155|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128164": {
+ "content": "<|reserved_special_token_156|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128165": {
+ "content": "<|reserved_special_token_157|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128166": {
+ "content": "<|reserved_special_token_158|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128167": {
+ "content": "<|reserved_special_token_159|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128168": {
+ "content": "<|reserved_special_token_160|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128169": {
+ "content": "<|reserved_special_token_161|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128170": {
+ "content": "<|reserved_special_token_162|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128171": {
+ "content": "<|reserved_special_token_163|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128172": {
+ "content": "<|reserved_special_token_164|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128173": {
+ "content": "<|reserved_special_token_165|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128174": {
+ "content": "<|reserved_special_token_166|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128175": {
+ "content": "<|reserved_special_token_167|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128176": {
+ "content": "<|reserved_special_token_168|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128177": {
+ "content": "<|reserved_special_token_169|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128178": {
+ "content": "<|reserved_special_token_170|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128179": {
+ "content": "<|reserved_special_token_171|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128180": {
+ "content": "<|reserved_special_token_172|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128181": {
+ "content": "<|reserved_special_token_173|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128182": {
+ "content": "<|reserved_special_token_174|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128183": {
+ "content": "<|reserved_special_token_175|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128184": {
+ "content": "<|reserved_special_token_176|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128185": {
+ "content": "<|reserved_special_token_177|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128186": {
+ "content": "<|reserved_special_token_178|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128187": {
+ "content": "<|reserved_special_token_179|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128188": {
+ "content": "<|reserved_special_token_180|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128189": {
+ "content": "<|reserved_special_token_181|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128190": {
+ "content": "<|reserved_special_token_182|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128191": {
+ "content": "<|reserved_special_token_183|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128192": {
+ "content": "<|reserved_special_token_184|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128193": {
+ "content": "<|reserved_special_token_185|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128194": {
+ "content": "<|reserved_special_token_186|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128195": {
+ "content": "<|reserved_special_token_187|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128196": {
+ "content": "<|reserved_special_token_188|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128197": {
+ "content": "<|reserved_special_token_189|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128198": {
+ "content": "<|reserved_special_token_190|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128199": {
+ "content": "<|reserved_special_token_191|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128200": {
+ "content": "<|reserved_special_token_192|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128201": {
+ "content": "<|reserved_special_token_193|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128202": {
+ "content": "<|reserved_special_token_194|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128203": {
+ "content": "<|reserved_special_token_195|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128204": {
+ "content": "<|reserved_special_token_196|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128205": {
+ "content": "<|reserved_special_token_197|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128206": {
+ "content": "<|reserved_special_token_198|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128207": {
+ "content": "<|reserved_special_token_199|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128208": {
+ "content": "<|reserved_special_token_200|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128209": {
+ "content": "<|reserved_special_token_201|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128210": {
+ "content": "<|reserved_special_token_202|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128211": {
+ "content": "<|reserved_special_token_203|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128212": {
+ "content": "<|reserved_special_token_204|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128213": {
+ "content": "<|reserved_special_token_205|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128214": {
+ "content": "<|reserved_special_token_206|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128215": {
+ "content": "<|reserved_special_token_207|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128216": {
+ "content": "<|reserved_special_token_208|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128217": {
+ "content": "<|reserved_special_token_209|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128218": {
+ "content": "<|reserved_special_token_210|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128219": {
+ "content": "<|reserved_special_token_211|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128220": {
+ "content": "<|reserved_special_token_212|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128221": {
+ "content": "<|reserved_special_token_213|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128222": {
+ "content": "<|reserved_special_token_214|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128223": {
+ "content": "<|reserved_special_token_215|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128224": {
+ "content": "<|reserved_special_token_216|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128225": {
+ "content": "<|reserved_special_token_217|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128226": {
+ "content": "<|reserved_special_token_218|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128227": {
+ "content": "<|reserved_special_token_219|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128228": {
+ "content": "<|reserved_special_token_220|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128229": {
+ "content": "<|reserved_special_token_221|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128230": {
+ "content": "<|reserved_special_token_222|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128231": {
+ "content": "<|reserved_special_token_223|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128232": {
+ "content": "<|reserved_special_token_224|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128233": {
+ "content": "<|reserved_special_token_225|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128234": {
+ "content": "<|reserved_special_token_226|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128235": {
+ "content": "<|reserved_special_token_227|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128236": {
+ "content": "<|reserved_special_token_228|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128237": {
+ "content": "<|reserved_special_token_229|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128238": {
+ "content": "<|reserved_special_token_230|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128239": {
+ "content": "<|reserved_special_token_231|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128240": {
+ "content": "<|reserved_special_token_232|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128241": {
+ "content": "<|reserved_special_token_233|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128242": {
+ "content": "<|reserved_special_token_234|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128243": {
+ "content": "<|reserved_special_token_235|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128244": {
+ "content": "<|reserved_special_token_236|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128245": {
+ "content": "<|reserved_special_token_237|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128246": {
+ "content": "<|reserved_special_token_238|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128247": {
+ "content": "<|reserved_special_token_239|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128248": {
+ "content": "<|reserved_special_token_240|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128249": {
+ "content": "<|reserved_special_token_241|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128250": {
+ "content": "<|reserved_special_token_242|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128251": {
+ "content": "<|reserved_special_token_243|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128252": {
+ "content": "<|reserved_special_token_244|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128253": {
+ "content": "<|reserved_special_token_245|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128254": {
+ "content": "<|reserved_special_token_246|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128255": {
+ "content": "<|reserved_special_token_247|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|begin_of_text|>",
+ "chat_template": [
+ {
+ "name": "default",
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+ },
+ {
+ "name": "tool_use",
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" \" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within XML tags as follows:\n\" }}\n{{- \"\n\" }}\n{{- '{\"name\": , \"arguments\": }\n' }}\n{{- '<|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- else %}\n {{- '\n' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+ }
+ ],
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|im_end|>",
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 131072,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..aef65bf78a9b21a82c7f2386a5b8cb507cde7ed4
--- /dev/null
+++ b/checkpoint-200/trainer_state.json
@@ -0,0 +1,393 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 0.6811409110259685,
+ "eval_steps": 500,
+ "global_step": 200,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.017028522775649212,
+ "grad_norm": 6.522716999053955,
+ "learning_rate": 0.0001988623435722412,
+ "loss": 2.7211,
+ "mean_token_accuracy": 0.5789041496813297,
+ "num_tokens": 4727.0,
+ "step": 5
+ },
+ {
+ "epoch": 0.034057045551298425,
+ "grad_norm": 1.0070050954818726,
+ "learning_rate": 0.00019772468714448238,
+ "loss": 0.9998,
+ "mean_token_accuracy": 0.8499793156981468,
+ "num_tokens": 9471.0,
+ "step": 10
+ },
+ {
+ "epoch": 0.05108556832694764,
+ "grad_norm": 0.7373425960540771,
+ "learning_rate": 0.00019658703071672356,
+ "loss": 0.8303,
+ "mean_token_accuracy": 0.8681916877627373,
+ "num_tokens": 14013.0,
+ "step": 15
+ },
+ {
+ "epoch": 0.06811409110259685,
+ "grad_norm": 0.8468236327171326,
+ "learning_rate": 0.00019544937428896475,
+ "loss": 0.8404,
+ "mean_token_accuracy": 0.8622620105743408,
+ "num_tokens": 18725.0,
+ "step": 20
+ },
+ {
+ "epoch": 0.08514261387824607,
+ "grad_norm": 0.8178804516792297,
+ "learning_rate": 0.00019431171786120593,
+ "loss": 0.9073,
+ "mean_token_accuracy": 0.8524447843432427,
+ "num_tokens": 23497.0,
+ "step": 25
+ },
+ {
+ "epoch": 0.10217113665389528,
+ "grad_norm": 0.890177309513092,
+ "learning_rate": 0.00019317406143344712,
+ "loss": 0.8029,
+ "mean_token_accuracy": 0.8642359614372254,
+ "num_tokens": 28192.0,
+ "step": 30
+ },
+ {
+ "epoch": 0.11919965942954448,
+ "grad_norm": 1.0545469522476196,
+ "learning_rate": 0.0001920364050056883,
+ "loss": 0.7458,
+ "mean_token_accuracy": 0.8732351213693619,
+ "num_tokens": 32805.0,
+ "step": 35
+ },
+ {
+ "epoch": 0.1362281822051937,
+ "grad_norm": 1.0384492874145508,
+ "learning_rate": 0.00019089874857792946,
+ "loss": 0.9235,
+ "mean_token_accuracy": 0.8408558666706085,
+ "num_tokens": 37714.0,
+ "step": 40
+ },
+ {
+ "epoch": 0.1532567049808429,
+ "grad_norm": 0.6860374808311462,
+ "learning_rate": 0.00018976109215017067,
+ "loss": 0.7623,
+ "mean_token_accuracy": 0.8656536340713501,
+ "num_tokens": 42429.0,
+ "step": 45
+ },
+ {
+ "epoch": 0.17028522775649213,
+ "grad_norm": 0.7284501791000366,
+ "learning_rate": 0.00018862343572241183,
+ "loss": 0.7588,
+ "mean_token_accuracy": 0.8688850715756417,
+ "num_tokens": 47099.0,
+ "step": 50
+ },
+ {
+ "epoch": 0.18731375053214133,
+ "grad_norm": 0.8899862170219421,
+ "learning_rate": 0.00018748577929465302,
+ "loss": 0.7065,
+ "mean_token_accuracy": 0.8717748820781708,
+ "num_tokens": 51795.0,
+ "step": 55
+ },
+ {
+ "epoch": 0.20434227330779056,
+ "grad_norm": 0.5350505709648132,
+ "learning_rate": 0.0001863481228668942,
+ "loss": 0.6696,
+ "mean_token_accuracy": 0.8851396456360817,
+ "num_tokens": 56369.0,
+ "step": 60
+ },
+ {
+ "epoch": 0.22137079608343976,
+ "grad_norm": 0.6087013483047485,
+ "learning_rate": 0.0001852104664391354,
+ "loss": 0.7204,
+ "mean_token_accuracy": 0.8682332798838616,
+ "num_tokens": 61018.0,
+ "step": 65
+ },
+ {
+ "epoch": 0.23839931885908897,
+ "grad_norm": 0.7879019379615784,
+ "learning_rate": 0.00018407281001137657,
+ "loss": 0.7692,
+ "mean_token_accuracy": 0.8653983056545258,
+ "num_tokens": 65741.0,
+ "step": 70
+ },
+ {
+ "epoch": 0.2554278416347382,
+ "grad_norm": 0.6546444296836853,
+ "learning_rate": 0.00018293515358361776,
+ "loss": 0.7119,
+ "mean_token_accuracy": 0.8726310178637504,
+ "num_tokens": 70425.0,
+ "step": 75
+ },
+ {
+ "epoch": 0.2724563644103874,
+ "grad_norm": 0.770902156829834,
+ "learning_rate": 0.00018179749715585894,
+ "loss": 0.7035,
+ "mean_token_accuracy": 0.8711811751127243,
+ "num_tokens": 75101.0,
+ "step": 80
+ },
+ {
+ "epoch": 0.2894848871860366,
+ "grad_norm": 0.8873187899589539,
+ "learning_rate": 0.00018065984072810013,
+ "loss": 0.7419,
+ "mean_token_accuracy": 0.8616803497076034,
+ "num_tokens": 79888.0,
+ "step": 85
+ },
+ {
+ "epoch": 0.3065134099616858,
+ "grad_norm": 0.7061370015144348,
+ "learning_rate": 0.0001795221843003413,
+ "loss": 0.66,
+ "mean_token_accuracy": 0.8744896531105042,
+ "num_tokens": 84562.0,
+ "step": 90
+ },
+ {
+ "epoch": 0.32354193273733506,
+ "grad_norm": 0.8232033252716064,
+ "learning_rate": 0.0001783845278725825,
+ "loss": 0.7403,
+ "mean_token_accuracy": 0.8659066379070282,
+ "num_tokens": 89238.0,
+ "step": 95
+ },
+ {
+ "epoch": 0.34057045551298426,
+ "grad_norm": 0.7313310503959656,
+ "learning_rate": 0.00017724687144482368,
+ "loss": 0.7157,
+ "mean_token_accuracy": 0.8661555901169777,
+ "num_tokens": 93987.0,
+ "step": 100
+ },
+ {
+ "epoch": 0.35759897828863346,
+ "grad_norm": 0.7119390964508057,
+ "learning_rate": 0.00017610921501706487,
+ "loss": 0.7016,
+ "mean_token_accuracy": 0.8678551658987999,
+ "num_tokens": 98722.0,
+ "step": 105
+ },
+ {
+ "epoch": 0.37462750106428266,
+ "grad_norm": 0.7126006484031677,
+ "learning_rate": 0.00017497155858930602,
+ "loss": 0.7009,
+ "mean_token_accuracy": 0.867291408777237,
+ "num_tokens": 103439.0,
+ "step": 110
+ },
+ {
+ "epoch": 0.39165602383993187,
+ "grad_norm": 0.6158230304718018,
+ "learning_rate": 0.00017383390216154724,
+ "loss": 0.7236,
+ "mean_token_accuracy": 0.8636128515005111,
+ "num_tokens": 108209.0,
+ "step": 115
+ },
+ {
+ "epoch": 0.4086845466155811,
+ "grad_norm": 0.6498322486877441,
+ "learning_rate": 0.0001726962457337884,
+ "loss": 0.6813,
+ "mean_token_accuracy": 0.8757071048021317,
+ "num_tokens": 112855.0,
+ "step": 120
+ },
+ {
+ "epoch": 0.4257130693912303,
+ "grad_norm": 0.6594287157058716,
+ "learning_rate": 0.0001715585893060296,
+ "loss": 0.7062,
+ "mean_token_accuracy": 0.8650311172008515,
+ "num_tokens": 117653.0,
+ "step": 125
+ },
+ {
+ "epoch": 0.4427415921668795,
+ "grad_norm": 0.7375237941741943,
+ "learning_rate": 0.00017042093287827076,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8733970731496811,
+ "num_tokens": 122397.0,
+ "step": 130
+ },
+ {
+ "epoch": 0.45977011494252873,
+ "grad_norm": 0.5958442687988281,
+ "learning_rate": 0.00016928327645051198,
+ "loss": 0.691,
+ "mean_token_accuracy": 0.8681387722492218,
+ "num_tokens": 127136.0,
+ "step": 135
+ },
+ {
+ "epoch": 0.47679863771817793,
+ "grad_norm": 0.7407785654067993,
+ "learning_rate": 0.00016814562002275313,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8752307429909706,
+ "num_tokens": 131833.0,
+ "step": 140
+ },
+ {
+ "epoch": 0.49382716049382713,
+ "grad_norm": 0.8190199732780457,
+ "learning_rate": 0.00016700796359499432,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8762851104140281,
+ "num_tokens": 136441.0,
+ "step": 145
+ },
+ {
+ "epoch": 0.5108556832694764,
+ "grad_norm": 0.7571837306022644,
+ "learning_rate": 0.0001658703071672355,
+ "loss": 0.673,
+ "mean_token_accuracy": 0.8691665843129158,
+ "num_tokens": 141186.0,
+ "step": 150
+ },
+ {
+ "epoch": 0.5278842060451255,
+ "grad_norm": 0.6653426885604858,
+ "learning_rate": 0.0001647326507394767,
+ "loss": 0.7126,
+ "mean_token_accuracy": 0.8647830635309219,
+ "num_tokens": 145971.0,
+ "step": 155
+ },
+ {
+ "epoch": 0.5449127288207748,
+ "grad_norm": 0.7333567142486572,
+ "learning_rate": 0.00016359499431171787,
+ "loss": 0.6287,
+ "mean_token_accuracy": 0.878324082493782,
+ "num_tokens": 150669.0,
+ "step": 160
+ },
+ {
+ "epoch": 0.561941251596424,
+ "grad_norm": 0.8214460015296936,
+ "learning_rate": 0.00016245733788395906,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8729922890663147,
+ "num_tokens": 155374.0,
+ "step": 165
+ },
+ {
+ "epoch": 0.5789697743720732,
+ "grad_norm": 0.6251844167709351,
+ "learning_rate": 0.00016131968145620024,
+ "loss": 0.6556,
+ "mean_token_accuracy": 0.8770609870553017,
+ "num_tokens": 160068.0,
+ "step": 170
+ },
+ {
+ "epoch": 0.5959982971477225,
+ "grad_norm": 0.804166853427887,
+ "learning_rate": 0.00016018202502844143,
+ "loss": 0.6366,
+ "mean_token_accuracy": 0.8760894432663917,
+ "num_tokens": 164696.0,
+ "step": 175
+ },
+ {
+ "epoch": 0.6130268199233716,
+ "grad_norm": 0.7013877034187317,
+ "learning_rate": 0.0001590443686006826,
+ "loss": 0.6328,
+ "mean_token_accuracy": 0.8779815405607223,
+ "num_tokens": 169356.0,
+ "step": 180
+ },
+ {
+ "epoch": 0.6300553426990209,
+ "grad_norm": 1.0623070001602173,
+ "learning_rate": 0.0001579067121729238,
+ "loss": 0.6734,
+ "mean_token_accuracy": 0.8710577815771103,
+ "num_tokens": 174041.0,
+ "step": 185
+ },
+ {
+ "epoch": 0.6470838654746701,
+ "grad_norm": 0.7858535647392273,
+ "learning_rate": 0.00015676905574516496,
+ "loss": 0.6775,
+ "mean_token_accuracy": 0.8692880481481552,
+ "num_tokens": 178858.0,
+ "step": 190
+ },
+ {
+ "epoch": 0.6641123882503193,
+ "grad_norm": 0.8943309187889099,
+ "learning_rate": 0.00015563139931740617,
+ "loss": 0.6874,
+ "mean_token_accuracy": 0.868885512650013,
+ "num_tokens": 183669.0,
+ "step": 195
+ },
+ {
+ "epoch": 0.6811409110259685,
+ "grad_norm": 0.5898745656013489,
+ "learning_rate": 0.00015449374288964733,
+ "loss": 0.6907,
+ "mean_token_accuracy": 0.8661940798163414,
+ "num_tokens": 188473.0,
+ "step": 200
+ }
+ ],
+ "logging_steps": 5,
+ "max_steps": 879,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 200,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 8534284789702656.0,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d77eaa0f69f97b2b9813f53e641e4a6232bfa34d
--- /dev/null
+++ b/checkpoint-200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
+size 5624
diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9633d8f0130799d996b640335cd6d3846c495f5b
--- /dev/null
+++ b/checkpoint-400/README.md
@@ -0,0 +1,209 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+
+
+
+
+## Model Details
+
+### Model Description
+
+
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+
+
+### Direct Use
+
+
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+
+
+[More Information Needed]
+
+### Recommendations
+
+
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+
+
+[More Information Needed]
+
+### Training Procedure
+
+
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed]
+
+#### Speeds, Sizes, Times [optional]
+
+
+
+[More Information Needed]
+
+## Evaluation
+
+
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+
+
+[More Information Needed]
+
+#### Factors
+
+
+
+[More Information Needed]
+
+#### Metrics
+
+
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+
+
+[More Information Needed]
+
+## Environmental Impact
+
+
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0
\ No newline at end of file
diff --git a/checkpoint-400/adapter_config.json b/checkpoint-400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..45edbb77201d4198da4bf26b8a7258da2bca8d90
--- /dev/null
+++ b/checkpoint-400/adapter_config.json
@@ -0,0 +1,50 @@
+{
+ "alora_invocation_tokens": null,
+ "alpha_pattern": {},
+ "arrow_config": null,
+ "auto_mapping": null,
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+ "bias": "none",
+ "corda_config": null,
+ "ensure_weight_tying": false,
+ "eva_config": null,
+ "exclude_modules": null,
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 32,
+ "lora_bias": false,
+ "lora_dropout": 0.05,
+ "lora_ga_config": null,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "monteclora_config": null,
+ "peft_type": "LORA",
+ "peft_version": "0.20.0",
+ "qalora_group_size": 16,
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_proj",
+ "k_proj",
+ "down_proj",
+ "up_proj",
+ "gate_proj",
+ "o_proj"
+ ],
+ "target_parameters": null,
+ "task_type": "CAUSAL_LM",
+ "trainable_token_indices": null,
+ "use_bdlora": null,
+ "use_dora": false,
+ "use_qalora": false,
+ "use_rslora": false,
+ "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-400/adapter_model.safetensors b/checkpoint-400/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..86c7e3f6e7b1144a09e9c1b035a7758b11fa6af3
--- /dev/null
+++ b/checkpoint-400/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8ac362c6bd18e2a2c20a4f44f1882f568e0f879c22cab4e217443450541c89
+size 167832240
diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e9cc6a2d21d03ec12f0392ff95cb1012f3783450
--- /dev/null
+++ b/checkpoint-400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78446832e6777e949471c8a7423ef18a9785aa589bd11dc1011a7552cc2050c7
+size 85728276
diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dc670e9aaa90033204696438954bcba8f9b48227
--- /dev/null
+++ b/checkpoint-400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d5f2e1daf718d7f4b153fb015cfb1eab12c9439e2a47cb1a9d7e57dbe69344
+size 14244
diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5705e146302954aa7419a1f92c128f22f55c90bb
--- /dev/null
+++ b/checkpoint-400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbaa767a1867f6f8022ea209ef1a03a369e44768800ec83f2966bcd9939650bb
+size 1064
diff --git a/checkpoint-400/special_tokens_map.json b/checkpoint-400/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fed0491bb0ae0c4f0752f54ffddf7d69269daed
--- /dev/null
+++ b/checkpoint-400/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+ "bos_token": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|im_end|>"
+}
diff --git a/checkpoint-400/tokenizer.json b/checkpoint-400/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b
--- /dev/null
+++ b/checkpoint-400/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
+size 17209403
diff --git a/checkpoint-400/tokenizer_config.json b/checkpoint-400/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1dbecde59340b33dcf97ef6087584a5a01208ab5
--- /dev/null
+++ b/checkpoint-400/tokenizer_config.json
@@ -0,0 +1,2072 @@
+{
+ "added_tokens_decoder": {
+ "128000": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128001": {
+ "content": "<|end_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128002": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128003": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128004": {
+ "content": "<|finetune_right_pad_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128005": {
+ "content": "<|reserved_special_token_2|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128006": {
+ "content": "<|start_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128007": {
+ "content": "<|end_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128008": {
+ "content": "<|eom_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128009": {
+ "content": "<|eot_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128010": {
+ "content": "<|python_tag|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128011": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128012": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128013": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128014": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128015": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128016": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128017": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128018": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128019": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128020": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128021": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128022": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128023": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128024": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128025": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128026": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128027": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128028": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128029": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128030": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128031": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128032": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128033": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128034": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128035": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128036": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128037": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128038": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128039": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128040": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128041": {
+ "content": "<|reserved_special_token_33|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128042": {
+ "content": "<|reserved_special_token_34|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128043": {
+ "content": "<|reserved_special_token_35|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128044": {
+ "content": "<|reserved_special_token_36|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128045": {
+ "content": "<|reserved_special_token_37|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128046": {
+ "content": "<|reserved_special_token_38|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128047": {
+ "content": "<|reserved_special_token_39|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128048": {
+ "content": "<|reserved_special_token_40|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128049": {
+ "content": "<|reserved_special_token_41|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128050": {
+ "content": "<|reserved_special_token_42|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128051": {
+ "content": "<|reserved_special_token_43|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128052": {
+ "content": "<|reserved_special_token_44|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128053": {
+ "content": "<|reserved_special_token_45|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128054": {
+ "content": "<|reserved_special_token_46|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128055": {
+ "content": "<|reserved_special_token_47|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128056": {
+ "content": "<|reserved_special_token_48|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128057": {
+ "content": "<|reserved_special_token_49|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128058": {
+ "content": "<|reserved_special_token_50|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128059": {
+ "content": "<|reserved_special_token_51|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128060": {
+ "content": "<|reserved_special_token_52|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128061": {
+ "content": "<|reserved_special_token_53|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128062": {
+ "content": "<|reserved_special_token_54|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128063": {
+ "content": "<|reserved_special_token_55|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128064": {
+ "content": "<|reserved_special_token_56|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128065": {
+ "content": "<|reserved_special_token_57|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128066": {
+ "content": "<|reserved_special_token_58|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128067": {
+ "content": "<|reserved_special_token_59|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128068": {
+ "content": "<|reserved_special_token_60|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128069": {
+ "content": "<|reserved_special_token_61|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128070": {
+ "content": "<|reserved_special_token_62|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128071": {
+ "content": "<|reserved_special_token_63|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128072": {
+ "content": "<|reserved_special_token_64|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128073": {
+ "content": "<|reserved_special_token_65|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128074": {
+ "content": "<|reserved_special_token_66|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128075": {
+ "content": "<|reserved_special_token_67|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128076": {
+ "content": "<|reserved_special_token_68|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128077": {
+ "content": "<|reserved_special_token_69|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128078": {
+ "content": "<|reserved_special_token_70|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128079": {
+ "content": "<|reserved_special_token_71|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128080": {
+ "content": "<|reserved_special_token_72|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128081": {
+ "content": "<|reserved_special_token_73|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128082": {
+ "content": "<|reserved_special_token_74|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128083": {
+ "content": "<|reserved_special_token_75|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128084": {
+ "content": "<|reserved_special_token_76|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128085": {
+ "content": "<|reserved_special_token_77|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128086": {
+ "content": "<|reserved_special_token_78|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128087": {
+ "content": "<|reserved_special_token_79|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128088": {
+ "content": "<|reserved_special_token_80|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128089": {
+ "content": "<|reserved_special_token_81|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128090": {
+ "content": "<|reserved_special_token_82|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128091": {
+ "content": "<|reserved_special_token_83|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128092": {
+ "content": "<|reserved_special_token_84|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128093": {
+ "content": "<|reserved_special_token_85|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128094": {
+ "content": "<|reserved_special_token_86|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128095": {
+ "content": "<|reserved_special_token_87|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128096": {
+ "content": "<|reserved_special_token_88|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128097": {
+ "content": "<|reserved_special_token_89|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128098": {
+ "content": "<|reserved_special_token_90|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128099": {
+ "content": "<|reserved_special_token_91|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128100": {
+ "content": "<|reserved_special_token_92|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128101": {
+ "content": "<|reserved_special_token_93|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128102": {
+ "content": "<|reserved_special_token_94|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128103": {
+ "content": "<|reserved_special_token_95|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128104": {
+ "content": "<|reserved_special_token_96|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128105": {
+ "content": "<|reserved_special_token_97|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128106": {
+ "content": "<|reserved_special_token_98|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128107": {
+ "content": "<|reserved_special_token_99|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128108": {
+ "content": "<|reserved_special_token_100|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128109": {
+ "content": "<|reserved_special_token_101|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128110": {
+ "content": "<|reserved_special_token_102|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128111": {
+ "content": "<|reserved_special_token_103|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128112": {
+ "content": "<|reserved_special_token_104|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128113": {
+ "content": "<|reserved_special_token_105|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128114": {
+ "content": "<|reserved_special_token_106|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128115": {
+ "content": "<|reserved_special_token_107|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128116": {
+ "content": "<|reserved_special_token_108|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128117": {
+ "content": "<|reserved_special_token_109|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128118": {
+ "content": "<|reserved_special_token_110|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128119": {
+ "content": "<|reserved_special_token_111|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128120": {
+ "content": "<|reserved_special_token_112|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128121": {
+ "content": "<|reserved_special_token_113|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128122": {
+ "content": "<|reserved_special_token_114|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128123": {
+ "content": "<|reserved_special_token_115|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128124": {
+ "content": "<|reserved_special_token_116|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128125": {
+ "content": "<|reserved_special_token_117|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128126": {
+ "content": "<|reserved_special_token_118|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128127": {
+ "content": "<|reserved_special_token_119|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128128": {
+ "content": "<|reserved_special_token_120|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128129": {
+ "content": "<|reserved_special_token_121|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128130": {
+ "content": "<|reserved_special_token_122|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128131": {
+ "content": "<|reserved_special_token_123|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128132": {
+ "content": "<|reserved_special_token_124|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128133": {
+ "content": "<|reserved_special_token_125|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128134": {
+ "content": "<|reserved_special_token_126|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128135": {
+ "content": "<|reserved_special_token_127|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128136": {
+ "content": "<|reserved_special_token_128|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128137": {
+ "content": "<|reserved_special_token_129|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128138": {
+ "content": "<|reserved_special_token_130|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128139": {
+ "content": "<|reserved_special_token_131|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128140": {
+ "content": "<|reserved_special_token_132|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128141": {
+ "content": "<|reserved_special_token_133|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128142": {
+ "content": "<|reserved_special_token_134|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128143": {
+ "content": "<|reserved_special_token_135|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128144": {
+ "content": "<|reserved_special_token_136|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128145": {
+ "content": "<|reserved_special_token_137|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128146": {
+ "content": "<|reserved_special_token_138|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128147": {
+ "content": "<|reserved_special_token_139|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128148": {
+ "content": "<|reserved_special_token_140|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128149": {
+ "content": "<|reserved_special_token_141|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128150": {
+ "content": "<|reserved_special_token_142|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128151": {
+ "content": "<|reserved_special_token_143|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128152": {
+ "content": "<|reserved_special_token_144|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128153": {
+ "content": "<|reserved_special_token_145|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128154": {
+ "content": "<|reserved_special_token_146|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128155": {
+ "content": "<|reserved_special_token_147|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128156": {
+ "content": "<|reserved_special_token_148|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128157": {
+ "content": "<|reserved_special_token_149|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128158": {
+ "content": "<|reserved_special_token_150|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128159": {
+ "content": "<|reserved_special_token_151|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128160": {
+ "content": "<|reserved_special_token_152|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128161": {
+ "content": "<|reserved_special_token_153|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128162": {
+ "content": "<|reserved_special_token_154|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128163": {
+ "content": "<|reserved_special_token_155|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128164": {
+ "content": "<|reserved_special_token_156|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128165": {
+ "content": "<|reserved_special_token_157|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128166": {
+ "content": "<|reserved_special_token_158|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128167": {
+ "content": "<|reserved_special_token_159|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128168": {
+ "content": "<|reserved_special_token_160|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128169": {
+ "content": "<|reserved_special_token_161|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128170": {
+ "content": "<|reserved_special_token_162|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128171": {
+ "content": "<|reserved_special_token_163|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128172": {
+ "content": "<|reserved_special_token_164|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128173": {
+ "content": "<|reserved_special_token_165|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128174": {
+ "content": "<|reserved_special_token_166|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128175": {
+ "content": "<|reserved_special_token_167|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128176": {
+ "content": "<|reserved_special_token_168|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128177": {
+ "content": "<|reserved_special_token_169|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128178": {
+ "content": "<|reserved_special_token_170|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128179": {
+ "content": "<|reserved_special_token_171|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128180": {
+ "content": "<|reserved_special_token_172|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128181": {
+ "content": "<|reserved_special_token_173|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128182": {
+ "content": "<|reserved_special_token_174|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128183": {
+ "content": "<|reserved_special_token_175|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128184": {
+ "content": "<|reserved_special_token_176|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128185": {
+ "content": "<|reserved_special_token_177|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128186": {
+ "content": "<|reserved_special_token_178|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128187": {
+ "content": "<|reserved_special_token_179|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128188": {
+ "content": "<|reserved_special_token_180|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128189": {
+ "content": "<|reserved_special_token_181|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128190": {
+ "content": "<|reserved_special_token_182|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128191": {
+ "content": "<|reserved_special_token_183|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128192": {
+ "content": "<|reserved_special_token_184|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128193": {
+ "content": "<|reserved_special_token_185|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128194": {
+ "content": "<|reserved_special_token_186|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128195": {
+ "content": "<|reserved_special_token_187|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128196": {
+ "content": "<|reserved_special_token_188|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128197": {
+ "content": "<|reserved_special_token_189|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128198": {
+ "content": "<|reserved_special_token_190|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128199": {
+ "content": "<|reserved_special_token_191|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128200": {
+ "content": "<|reserved_special_token_192|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128201": {
+ "content": "<|reserved_special_token_193|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128202": {
+ "content": "<|reserved_special_token_194|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128203": {
+ "content": "<|reserved_special_token_195|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128204": {
+ "content": "<|reserved_special_token_196|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128205": {
+ "content": "<|reserved_special_token_197|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128206": {
+ "content": "<|reserved_special_token_198|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128207": {
+ "content": "<|reserved_special_token_199|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128208": {
+ "content": "<|reserved_special_token_200|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128209": {
+ "content": "<|reserved_special_token_201|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128210": {
+ "content": "<|reserved_special_token_202|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128211": {
+ "content": "<|reserved_special_token_203|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128212": {
+ "content": "<|reserved_special_token_204|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128213": {
+ "content": "<|reserved_special_token_205|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128214": {
+ "content": "<|reserved_special_token_206|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128215": {
+ "content": "<|reserved_special_token_207|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128216": {
+ "content": "<|reserved_special_token_208|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128217": {
+ "content": "<|reserved_special_token_209|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128218": {
+ "content": "<|reserved_special_token_210|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128219": {
+ "content": "<|reserved_special_token_211|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128220": {
+ "content": "<|reserved_special_token_212|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128221": {
+ "content": "<|reserved_special_token_213|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128222": {
+ "content": "<|reserved_special_token_214|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128223": {
+ "content": "<|reserved_special_token_215|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128224": {
+ "content": "<|reserved_special_token_216|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128225": {
+ "content": "<|reserved_special_token_217|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128226": {
+ "content": "<|reserved_special_token_218|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128227": {
+ "content": "<|reserved_special_token_219|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128228": {
+ "content": "<|reserved_special_token_220|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128229": {
+ "content": "<|reserved_special_token_221|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128230": {
+ "content": "<|reserved_special_token_222|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128231": {
+ "content": "<|reserved_special_token_223|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128232": {
+ "content": "<|reserved_special_token_224|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128233": {
+ "content": "<|reserved_special_token_225|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128234": {
+ "content": "<|reserved_special_token_226|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128235": {
+ "content": "<|reserved_special_token_227|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128236": {
+ "content": "<|reserved_special_token_228|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128237": {
+ "content": "<|reserved_special_token_229|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128238": {
+ "content": "<|reserved_special_token_230|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128239": {
+ "content": "<|reserved_special_token_231|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128240": {
+ "content": "<|reserved_special_token_232|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128241": {
+ "content": "<|reserved_special_token_233|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128242": {
+ "content": "<|reserved_special_token_234|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128243": {
+ "content": "<|reserved_special_token_235|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128244": {
+ "content": "<|reserved_special_token_236|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128245": {
+ "content": "<|reserved_special_token_237|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128246": {
+ "content": "<|reserved_special_token_238|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128247": {
+ "content": "<|reserved_special_token_239|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128248": {
+ "content": "<|reserved_special_token_240|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128249": {
+ "content": "<|reserved_special_token_241|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128250": {
+ "content": "<|reserved_special_token_242|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128251": {
+ "content": "<|reserved_special_token_243|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128252": {
+ "content": "<|reserved_special_token_244|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128253": {
+ "content": "<|reserved_special_token_245|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128254": {
+ "content": "<|reserved_special_token_246|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128255": {
+ "content": "<|reserved_special_token_247|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|begin_of_text|>",
+ "chat_template": [
+ {
+ "name": "default",
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+ },
+ {
+ "name": "tool_use",
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" \" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within XML tags as follows:\n\" }}\n{{- \"\n\" }}\n{{- '{\"name\": , \"arguments\": }\n' }}\n{{- '<|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- else %}\n {{- '\n' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+ }
+ ],
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|im_end|>",
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 131072,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97b9577b7e731393b26483965dda3fd1410f21d
--- /dev/null
+++ b/checkpoint-400/trainer_state.json
@@ -0,0 +1,753 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 1.362281822051937,
+ "eval_steps": 500,
+ "global_step": 400,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.017028522775649212,
+ "grad_norm": 6.522716999053955,
+ "learning_rate": 0.0001988623435722412,
+ "loss": 2.7211,
+ "mean_token_accuracy": 0.5789041496813297,
+ "num_tokens": 4727.0,
+ "step": 5
+ },
+ {
+ "epoch": 0.034057045551298425,
+ "grad_norm": 1.0070050954818726,
+ "learning_rate": 0.00019772468714448238,
+ "loss": 0.9998,
+ "mean_token_accuracy": 0.8499793156981468,
+ "num_tokens": 9471.0,
+ "step": 10
+ },
+ {
+ "epoch": 0.05108556832694764,
+ "grad_norm": 0.7373425960540771,
+ "learning_rate": 0.00019658703071672356,
+ "loss": 0.8303,
+ "mean_token_accuracy": 0.8681916877627373,
+ "num_tokens": 14013.0,
+ "step": 15
+ },
+ {
+ "epoch": 0.06811409110259685,
+ "grad_norm": 0.8468236327171326,
+ "learning_rate": 0.00019544937428896475,
+ "loss": 0.8404,
+ "mean_token_accuracy": 0.8622620105743408,
+ "num_tokens": 18725.0,
+ "step": 20
+ },
+ {
+ "epoch": 0.08514261387824607,
+ "grad_norm": 0.8178804516792297,
+ "learning_rate": 0.00019431171786120593,
+ "loss": 0.9073,
+ "mean_token_accuracy": 0.8524447843432427,
+ "num_tokens": 23497.0,
+ "step": 25
+ },
+ {
+ "epoch": 0.10217113665389528,
+ "grad_norm": 0.890177309513092,
+ "learning_rate": 0.00019317406143344712,
+ "loss": 0.8029,
+ "mean_token_accuracy": 0.8642359614372254,
+ "num_tokens": 28192.0,
+ "step": 30
+ },
+ {
+ "epoch": 0.11919965942954448,
+ "grad_norm": 1.0545469522476196,
+ "learning_rate": 0.0001920364050056883,
+ "loss": 0.7458,
+ "mean_token_accuracy": 0.8732351213693619,
+ "num_tokens": 32805.0,
+ "step": 35
+ },
+ {
+ "epoch": 0.1362281822051937,
+ "grad_norm": 1.0384492874145508,
+ "learning_rate": 0.00019089874857792946,
+ "loss": 0.9235,
+ "mean_token_accuracy": 0.8408558666706085,
+ "num_tokens": 37714.0,
+ "step": 40
+ },
+ {
+ "epoch": 0.1532567049808429,
+ "grad_norm": 0.6860374808311462,
+ "learning_rate": 0.00018976109215017067,
+ "loss": 0.7623,
+ "mean_token_accuracy": 0.8656536340713501,
+ "num_tokens": 42429.0,
+ "step": 45
+ },
+ {
+ "epoch": 0.17028522775649213,
+ "grad_norm": 0.7284501791000366,
+ "learning_rate": 0.00018862343572241183,
+ "loss": 0.7588,
+ "mean_token_accuracy": 0.8688850715756417,
+ "num_tokens": 47099.0,
+ "step": 50
+ },
+ {
+ "epoch": 0.18731375053214133,
+ "grad_norm": 0.8899862170219421,
+ "learning_rate": 0.00018748577929465302,
+ "loss": 0.7065,
+ "mean_token_accuracy": 0.8717748820781708,
+ "num_tokens": 51795.0,
+ "step": 55
+ },
+ {
+ "epoch": 0.20434227330779056,
+ "grad_norm": 0.5350505709648132,
+ "learning_rate": 0.0001863481228668942,
+ "loss": 0.6696,
+ "mean_token_accuracy": 0.8851396456360817,
+ "num_tokens": 56369.0,
+ "step": 60
+ },
+ {
+ "epoch": 0.22137079608343976,
+ "grad_norm": 0.6087013483047485,
+ "learning_rate": 0.0001852104664391354,
+ "loss": 0.7204,
+ "mean_token_accuracy": 0.8682332798838616,
+ "num_tokens": 61018.0,
+ "step": 65
+ },
+ {
+ "epoch": 0.23839931885908897,
+ "grad_norm": 0.7879019379615784,
+ "learning_rate": 0.00018407281001137657,
+ "loss": 0.7692,
+ "mean_token_accuracy": 0.8653983056545258,
+ "num_tokens": 65741.0,
+ "step": 70
+ },
+ {
+ "epoch": 0.2554278416347382,
+ "grad_norm": 0.6546444296836853,
+ "learning_rate": 0.00018293515358361776,
+ "loss": 0.7119,
+ "mean_token_accuracy": 0.8726310178637504,
+ "num_tokens": 70425.0,
+ "step": 75
+ },
+ {
+ "epoch": 0.2724563644103874,
+ "grad_norm": 0.770902156829834,
+ "learning_rate": 0.00018179749715585894,
+ "loss": 0.7035,
+ "mean_token_accuracy": 0.8711811751127243,
+ "num_tokens": 75101.0,
+ "step": 80
+ },
+ {
+ "epoch": 0.2894848871860366,
+ "grad_norm": 0.8873187899589539,
+ "learning_rate": 0.00018065984072810013,
+ "loss": 0.7419,
+ "mean_token_accuracy": 0.8616803497076034,
+ "num_tokens": 79888.0,
+ "step": 85
+ },
+ {
+ "epoch": 0.3065134099616858,
+ "grad_norm": 0.7061370015144348,
+ "learning_rate": 0.0001795221843003413,
+ "loss": 0.66,
+ "mean_token_accuracy": 0.8744896531105042,
+ "num_tokens": 84562.0,
+ "step": 90
+ },
+ {
+ "epoch": 0.32354193273733506,
+ "grad_norm": 0.8232033252716064,
+ "learning_rate": 0.0001783845278725825,
+ "loss": 0.7403,
+ "mean_token_accuracy": 0.8659066379070282,
+ "num_tokens": 89238.0,
+ "step": 95
+ },
+ {
+ "epoch": 0.34057045551298426,
+ "grad_norm": 0.7313310503959656,
+ "learning_rate": 0.00017724687144482368,
+ "loss": 0.7157,
+ "mean_token_accuracy": 0.8661555901169777,
+ "num_tokens": 93987.0,
+ "step": 100
+ },
+ {
+ "epoch": 0.35759897828863346,
+ "grad_norm": 0.7119390964508057,
+ "learning_rate": 0.00017610921501706487,
+ "loss": 0.7016,
+ "mean_token_accuracy": 0.8678551658987999,
+ "num_tokens": 98722.0,
+ "step": 105
+ },
+ {
+ "epoch": 0.37462750106428266,
+ "grad_norm": 0.7126006484031677,
+ "learning_rate": 0.00017497155858930602,
+ "loss": 0.7009,
+ "mean_token_accuracy": 0.867291408777237,
+ "num_tokens": 103439.0,
+ "step": 110
+ },
+ {
+ "epoch": 0.39165602383993187,
+ "grad_norm": 0.6158230304718018,
+ "learning_rate": 0.00017383390216154724,
+ "loss": 0.7236,
+ "mean_token_accuracy": 0.8636128515005111,
+ "num_tokens": 108209.0,
+ "step": 115
+ },
+ {
+ "epoch": 0.4086845466155811,
+ "grad_norm": 0.6498322486877441,
+ "learning_rate": 0.0001726962457337884,
+ "loss": 0.6813,
+ "mean_token_accuracy": 0.8757071048021317,
+ "num_tokens": 112855.0,
+ "step": 120
+ },
+ {
+ "epoch": 0.4257130693912303,
+ "grad_norm": 0.6594287157058716,
+ "learning_rate": 0.0001715585893060296,
+ "loss": 0.7062,
+ "mean_token_accuracy": 0.8650311172008515,
+ "num_tokens": 117653.0,
+ "step": 125
+ },
+ {
+ "epoch": 0.4427415921668795,
+ "grad_norm": 0.7375237941741943,
+ "learning_rate": 0.00017042093287827076,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8733970731496811,
+ "num_tokens": 122397.0,
+ "step": 130
+ },
+ {
+ "epoch": 0.45977011494252873,
+ "grad_norm": 0.5958442687988281,
+ "learning_rate": 0.00016928327645051198,
+ "loss": 0.691,
+ "mean_token_accuracy": 0.8681387722492218,
+ "num_tokens": 127136.0,
+ "step": 135
+ },
+ {
+ "epoch": 0.47679863771817793,
+ "grad_norm": 0.7407785654067993,
+ "learning_rate": 0.00016814562002275313,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8752307429909706,
+ "num_tokens": 131833.0,
+ "step": 140
+ },
+ {
+ "epoch": 0.49382716049382713,
+ "grad_norm": 0.8190199732780457,
+ "learning_rate": 0.00016700796359499432,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8762851104140281,
+ "num_tokens": 136441.0,
+ "step": 145
+ },
+ {
+ "epoch": 0.5108556832694764,
+ "grad_norm": 0.7571837306022644,
+ "learning_rate": 0.0001658703071672355,
+ "loss": 0.673,
+ "mean_token_accuracy": 0.8691665843129158,
+ "num_tokens": 141186.0,
+ "step": 150
+ },
+ {
+ "epoch": 0.5278842060451255,
+ "grad_norm": 0.6653426885604858,
+ "learning_rate": 0.0001647326507394767,
+ "loss": 0.7126,
+ "mean_token_accuracy": 0.8647830635309219,
+ "num_tokens": 145971.0,
+ "step": 155
+ },
+ {
+ "epoch": 0.5449127288207748,
+ "grad_norm": 0.7333567142486572,
+ "learning_rate": 0.00016359499431171787,
+ "loss": 0.6287,
+ "mean_token_accuracy": 0.878324082493782,
+ "num_tokens": 150669.0,
+ "step": 160
+ },
+ {
+ "epoch": 0.561941251596424,
+ "grad_norm": 0.8214460015296936,
+ "learning_rate": 0.00016245733788395906,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8729922890663147,
+ "num_tokens": 155374.0,
+ "step": 165
+ },
+ {
+ "epoch": 0.5789697743720732,
+ "grad_norm": 0.6251844167709351,
+ "learning_rate": 0.00016131968145620024,
+ "loss": 0.6556,
+ "mean_token_accuracy": 0.8770609870553017,
+ "num_tokens": 160068.0,
+ "step": 170
+ },
+ {
+ "epoch": 0.5959982971477225,
+ "grad_norm": 0.804166853427887,
+ "learning_rate": 0.00016018202502844143,
+ "loss": 0.6366,
+ "mean_token_accuracy": 0.8760894432663917,
+ "num_tokens": 164696.0,
+ "step": 175
+ },
+ {
+ "epoch": 0.6130268199233716,
+ "grad_norm": 0.7013877034187317,
+ "learning_rate": 0.0001590443686006826,
+ "loss": 0.6328,
+ "mean_token_accuracy": 0.8779815405607223,
+ "num_tokens": 169356.0,
+ "step": 180
+ },
+ {
+ "epoch": 0.6300553426990209,
+ "grad_norm": 1.0623070001602173,
+ "learning_rate": 0.0001579067121729238,
+ "loss": 0.6734,
+ "mean_token_accuracy": 0.8710577815771103,
+ "num_tokens": 174041.0,
+ "step": 185
+ },
+ {
+ "epoch": 0.6470838654746701,
+ "grad_norm": 0.7858535647392273,
+ "learning_rate": 0.00015676905574516496,
+ "loss": 0.6775,
+ "mean_token_accuracy": 0.8692880481481552,
+ "num_tokens": 178858.0,
+ "step": 190
+ },
+ {
+ "epoch": 0.6641123882503193,
+ "grad_norm": 0.8943309187889099,
+ "learning_rate": 0.00015563139931740617,
+ "loss": 0.6874,
+ "mean_token_accuracy": 0.868885512650013,
+ "num_tokens": 183669.0,
+ "step": 195
+ },
+ {
+ "epoch": 0.6811409110259685,
+ "grad_norm": 0.5898745656013489,
+ "learning_rate": 0.00015449374288964733,
+ "loss": 0.6907,
+ "mean_token_accuracy": 0.8661940798163414,
+ "num_tokens": 188473.0,
+ "step": 200
+ },
+ {
+ "epoch": 0.6981694338016177,
+ "grad_norm": 0.6333857774734497,
+ "learning_rate": 0.00015335608646188854,
+ "loss": 0.6129,
+ "mean_token_accuracy": 0.8817986205220223,
+ "num_tokens": 193171.0,
+ "step": 205
+ },
+ {
+ "epoch": 0.7151979565772669,
+ "grad_norm": 0.5913947820663452,
+ "learning_rate": 0.0001522184300341297,
+ "loss": 0.5896,
+ "mean_token_accuracy": 0.8822762459516525,
+ "num_tokens": 197817.0,
+ "step": 210
+ },
+ {
+ "epoch": 0.7322264793529162,
+ "grad_norm": 0.6990242004394531,
+ "learning_rate": 0.00015108077360637088,
+ "loss": 0.6512,
+ "mean_token_accuracy": 0.8739180400967598,
+ "num_tokens": 202556.0,
+ "step": 215
+ },
+ {
+ "epoch": 0.7492550021285653,
+ "grad_norm": 0.6869048476219177,
+ "learning_rate": 0.00014994311717861207,
+ "loss": 0.7025,
+ "mean_token_accuracy": 0.8662877783179284,
+ "num_tokens": 207294.0,
+ "step": 220
+ },
+ {
+ "epoch": 0.7662835249042146,
+ "grad_norm": 0.5135166049003601,
+ "learning_rate": 0.00014880546075085325,
+ "loss": 0.6382,
+ "mean_token_accuracy": 0.8849207311868668,
+ "num_tokens": 211927.0,
+ "step": 225
+ },
+ {
+ "epoch": 0.7833120476798637,
+ "grad_norm": 0.6304216980934143,
+ "learning_rate": 0.00014766780432309444,
+ "loss": 0.6834,
+ "mean_token_accuracy": 0.8688049465417862,
+ "num_tokens": 216626.0,
+ "step": 230
+ },
+ {
+ "epoch": 0.800340570455513,
+ "grad_norm": 0.6879922151565552,
+ "learning_rate": 0.00014653014789533562,
+ "loss": 0.6902,
+ "mean_token_accuracy": 0.8655798360705376,
+ "num_tokens": 221432.0,
+ "step": 235
+ },
+ {
+ "epoch": 0.8173690932311622,
+ "grad_norm": 0.6433548331260681,
+ "learning_rate": 0.0001453924914675768,
+ "loss": 0.6129,
+ "mean_token_accuracy": 0.8795880794525146,
+ "num_tokens": 226022.0,
+ "step": 240
+ },
+ {
+ "epoch": 0.8343976160068114,
+ "grad_norm": 0.7876724600791931,
+ "learning_rate": 0.000144254835039818,
+ "loss": 0.6441,
+ "mean_token_accuracy": 0.8729524433612823,
+ "num_tokens": 230692.0,
+ "step": 245
+ },
+ {
+ "epoch": 0.8514261387824607,
+ "grad_norm": 0.6494749188423157,
+ "learning_rate": 0.00014311717861205915,
+ "loss": 0.7033,
+ "mean_token_accuracy": 0.8632469072937965,
+ "num_tokens": 235400.0,
+ "step": 250
+ },
+ {
+ "epoch": 0.8684546615581098,
+ "grad_norm": 0.6332300305366516,
+ "learning_rate": 0.00014197952218430036,
+ "loss": 0.5947,
+ "mean_token_accuracy": 0.8860528379678726,
+ "num_tokens": 239997.0,
+ "step": 255
+ },
+ {
+ "epoch": 0.885483184333759,
+ "grad_norm": 0.7144895195960999,
+ "learning_rate": 0.00014084186575654152,
+ "loss": 0.649,
+ "mean_token_accuracy": 0.8745664536952973,
+ "num_tokens": 244704.0,
+ "step": 260
+ },
+ {
+ "epoch": 0.9025117071094083,
+ "grad_norm": 0.5460124015808105,
+ "learning_rate": 0.00013970420932878273,
+ "loss": 0.6622,
+ "mean_token_accuracy": 0.8692788198590279,
+ "num_tokens": 249428.0,
+ "step": 265
+ },
+ {
+ "epoch": 0.9195402298850575,
+ "grad_norm": 0.65619295835495,
+ "learning_rate": 0.0001385665529010239,
+ "loss": 0.657,
+ "mean_token_accuracy": 0.8737826406955719,
+ "num_tokens": 254150.0,
+ "step": 270
+ },
+ {
+ "epoch": 0.9365687526607067,
+ "grad_norm": 0.8474870324134827,
+ "learning_rate": 0.0001374288964732651,
+ "loss": 0.6607,
+ "mean_token_accuracy": 0.8756056800484657,
+ "num_tokens": 258826.0,
+ "step": 275
+ },
+ {
+ "epoch": 0.9535972754363559,
+ "grad_norm": 0.6054229736328125,
+ "learning_rate": 0.00013629124004550626,
+ "loss": 0.6526,
+ "mean_token_accuracy": 0.8718441724777222,
+ "num_tokens": 263524.0,
+ "step": 280
+ },
+ {
+ "epoch": 0.9706257982120051,
+ "grad_norm": 0.6568702459335327,
+ "learning_rate": 0.00013515358361774744,
+ "loss": 0.6174,
+ "mean_token_accuracy": 0.881709736585617,
+ "num_tokens": 268179.0,
+ "step": 285
+ },
+ {
+ "epoch": 0.9876543209876543,
+ "grad_norm": 0.7518045902252197,
+ "learning_rate": 0.00013401592718998863,
+ "loss": 0.5896,
+ "mean_token_accuracy": 0.885109031200409,
+ "num_tokens": 272803.0,
+ "step": 290
+ },
+ {
+ "epoch": 1.0046828437633035,
+ "grad_norm": 0.5392197370529175,
+ "learning_rate": 0.00013287827076222981,
+ "loss": 0.6753,
+ "mean_token_accuracy": 0.8788385137915611,
+ "num_tokens": 277527.0,
+ "step": 295
+ },
+ {
+ "epoch": 1.0217113665389528,
+ "grad_norm": 0.5845906734466553,
+ "learning_rate": 0.000131740614334471,
+ "loss": 0.5237,
+ "mean_token_accuracy": 0.8938747227191925,
+ "num_tokens": 282199.0,
+ "step": 300
+ },
+ {
+ "epoch": 1.038739889314602,
+ "grad_norm": 0.6392928957939148,
+ "learning_rate": 0.00013060295790671218,
+ "loss": 0.4973,
+ "mean_token_accuracy": 0.8982622623443604,
+ "num_tokens": 286951.0,
+ "step": 305
+ },
+ {
+ "epoch": 1.055768412090251,
+ "grad_norm": 0.5399300456047058,
+ "learning_rate": 0.00012946530147895337,
+ "loss": 0.5076,
+ "mean_token_accuracy": 0.9008002370595932,
+ "num_tokens": 291569.0,
+ "step": 310
+ },
+ {
+ "epoch": 1.0727969348659003,
+ "grad_norm": 0.6236026883125305,
+ "learning_rate": 0.00012832764505119455,
+ "loss": 0.5084,
+ "mean_token_accuracy": 0.8972577184438706,
+ "num_tokens": 296230.0,
+ "step": 315
+ },
+ {
+ "epoch": 1.0898254576415496,
+ "grad_norm": 0.7385813593864441,
+ "learning_rate": 0.0001271899886234357,
+ "loss": 0.5062,
+ "mean_token_accuracy": 0.8956585437059402,
+ "num_tokens": 301029.0,
+ "step": 320
+ },
+ {
+ "epoch": 1.1068539804171988,
+ "grad_norm": 0.7647150754928589,
+ "learning_rate": 0.00012605233219567692,
+ "loss": 0.5078,
+ "mean_token_accuracy": 0.8982979074120522,
+ "num_tokens": 305696.0,
+ "step": 325
+ },
+ {
+ "epoch": 1.123882503192848,
+ "grad_norm": 0.6433872580528259,
+ "learning_rate": 0.00012491467576791808,
+ "loss": 0.5215,
+ "mean_token_accuracy": 0.8974734947085381,
+ "num_tokens": 310343.0,
+ "step": 330
+ },
+ {
+ "epoch": 1.1409110259684971,
+ "grad_norm": 0.6470033526420593,
+ "learning_rate": 0.0001237770193401593,
+ "loss": 0.5261,
+ "mean_token_accuracy": 0.8938129872083664,
+ "num_tokens": 315097.0,
+ "step": 335
+ },
+ {
+ "epoch": 1.1579395487441464,
+ "grad_norm": 0.6738846302032471,
+ "learning_rate": 0.00012263936291240045,
+ "loss": 0.5277,
+ "mean_token_accuracy": 0.8924461513757705,
+ "num_tokens": 319861.0,
+ "step": 340
+ },
+ {
+ "epoch": 1.1749680715197957,
+ "grad_norm": 0.6639145016670227,
+ "learning_rate": 0.00012150170648464165,
+ "loss": 0.5127,
+ "mean_token_accuracy": 0.8926685571670532,
+ "num_tokens": 324544.0,
+ "step": 345
+ },
+ {
+ "epoch": 1.191996594295445,
+ "grad_norm": 0.7034420371055603,
+ "learning_rate": 0.00012036405005688282,
+ "loss": 0.51,
+ "mean_token_accuracy": 0.8971043467521668,
+ "num_tokens": 329302.0,
+ "step": 350
+ },
+ {
+ "epoch": 1.2090251170710942,
+ "grad_norm": 0.6675500273704529,
+ "learning_rate": 0.000119226393629124,
+ "loss": 0.5738,
+ "mean_token_accuracy": 0.8855719327926636,
+ "num_tokens": 334103.0,
+ "step": 355
+ },
+ {
+ "epoch": 1.2260536398467432,
+ "grad_norm": 0.6019395589828491,
+ "learning_rate": 0.00011808873720136519,
+ "loss": 0.476,
+ "mean_token_accuracy": 0.8989460453391075,
+ "num_tokens": 338666.0,
+ "step": 360
+ },
+ {
+ "epoch": 1.2430821626223925,
+ "grad_norm": 0.6599250435829163,
+ "learning_rate": 0.00011695108077360638,
+ "loss": 0.5178,
+ "mean_token_accuracy": 0.8887226998805999,
+ "num_tokens": 343333.0,
+ "step": 365
+ },
+ {
+ "epoch": 1.2601106853980417,
+ "grad_norm": 0.7334213852882385,
+ "learning_rate": 0.00011581342434584756,
+ "loss": 0.5378,
+ "mean_token_accuracy": 0.8895460113883018,
+ "num_tokens": 348092.0,
+ "step": 370
+ },
+ {
+ "epoch": 1.277139208173691,
+ "grad_norm": 0.7423357963562012,
+ "learning_rate": 0.00011467576791808873,
+ "loss": 0.5012,
+ "mean_token_accuracy": 0.8994292929768563,
+ "num_tokens": 352661.0,
+ "step": 375
+ },
+ {
+ "epoch": 1.29416773094934,
+ "grad_norm": 0.857515811920166,
+ "learning_rate": 0.00011353811149032993,
+ "loss": 0.507,
+ "mean_token_accuracy": 0.8979884222149849,
+ "num_tokens": 357330.0,
+ "step": 380
+ },
+ {
+ "epoch": 1.3111962537249893,
+ "grad_norm": 0.5656803250312805,
+ "learning_rate": 0.0001124004550625711,
+ "loss": 0.5009,
+ "mean_token_accuracy": 0.8934224143624305,
+ "num_tokens": 362020.0,
+ "step": 385
+ },
+ {
+ "epoch": 1.3282247765006385,
+ "grad_norm": 0.6634964942932129,
+ "learning_rate": 0.00011126279863481229,
+ "loss": 0.5414,
+ "mean_token_accuracy": 0.8910330131649971,
+ "num_tokens": 366728.0,
+ "step": 390
+ },
+ {
+ "epoch": 1.3452532992762878,
+ "grad_norm": 0.7004157304763794,
+ "learning_rate": 0.00011012514220705347,
+ "loss": 0.4922,
+ "mean_token_accuracy": 0.8992783546447753,
+ "num_tokens": 371381.0,
+ "step": 395
+ },
+ {
+ "epoch": 1.362281822051937,
+ "grad_norm": 0.6225594282150269,
+ "learning_rate": 0.00010898748577929466,
+ "loss": 0.5084,
+ "mean_token_accuracy": 0.8956901535391808,
+ "num_tokens": 376043.0,
+ "step": 400
+ }
+ ],
+ "logging_steps": 5,
+ "max_steps": 879,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 200,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 1.7027680650141696e+16,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d77eaa0f69f97b2b9813f53e641e4a6232bfa34d
--- /dev/null
+++ b/checkpoint-400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
+size 5624
diff --git a/checkpoint-600/README.md b/checkpoint-600/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9633d8f0130799d996b640335cd6d3846c495f5b
--- /dev/null
+++ b/checkpoint-600/README.md
@@ -0,0 +1,209 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+
+
+
+
+## Model Details
+
+### Model Description
+
+
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+
+
+### Direct Use
+
+
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+
+
+[More Information Needed]
+
+### Recommendations
+
+
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+
+
+[More Information Needed]
+
+### Training Procedure
+
+
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed]
+
+#### Speeds, Sizes, Times [optional]
+
+
+
+[More Information Needed]
+
+## Evaluation
+
+
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+
+
+[More Information Needed]
+
+#### Factors
+
+
+
+[More Information Needed]
+
+#### Metrics
+
+
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+
+
+[More Information Needed]
+
+## Environmental Impact
+
+
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0
\ No newline at end of file
diff --git a/checkpoint-600/adapter_config.json b/checkpoint-600/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..45edbb77201d4198da4bf26b8a7258da2bca8d90
--- /dev/null
+++ b/checkpoint-600/adapter_config.json
@@ -0,0 +1,50 @@
+{
+ "alora_invocation_tokens": null,
+ "alpha_pattern": {},
+ "arrow_config": null,
+ "auto_mapping": null,
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+ "bias": "none",
+ "corda_config": null,
+ "ensure_weight_tying": false,
+ "eva_config": null,
+ "exclude_modules": null,
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 32,
+ "lora_bias": false,
+ "lora_dropout": 0.05,
+ "lora_ga_config": null,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "monteclora_config": null,
+ "peft_type": "LORA",
+ "peft_version": "0.20.0",
+ "qalora_group_size": 16,
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_proj",
+ "k_proj",
+ "down_proj",
+ "up_proj",
+ "gate_proj",
+ "o_proj"
+ ],
+ "target_parameters": null,
+ "task_type": "CAUSAL_LM",
+ "trainable_token_indices": null,
+ "use_bdlora": null,
+ "use_dora": false,
+ "use_qalora": false,
+ "use_rslora": false,
+ "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-600/adapter_model.safetensors b/checkpoint-600/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7c98a90cc346298b21aebdfd77557a5ff33786db
--- /dev/null
+++ b/checkpoint-600/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f507d4abd7010e4a5130e20dd410de849fbd9c5df5116d8c42b121ce6084b10
+size 167832240
diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4f4a2dc4b06bdf86f324d88f25724f0fca372efe
--- /dev/null
+++ b/checkpoint-600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21d3ba4f3589798d054250c59c9e7db0483addbff8261bcb5722b7ba517fc48
+size 85728276
diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4cbe46942fbb2fa0b51b8fcb23268b77805c3f29
--- /dev/null
+++ b/checkpoint-600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c778379c8bd89d29c7155c9f3c8011bb8e7d97afcc65976304bce4dcfefa37
+size 14244
diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..064dc5bcca43e6b1737600721158f608c0ab7bea
--- /dev/null
+++ b/checkpoint-600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd96493eebbb35a30ee240cfe1ad8f98b67771a20ddafde87bd6093f71d27bb
+size 1064
diff --git a/checkpoint-600/special_tokens_map.json b/checkpoint-600/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fed0491bb0ae0c4f0752f54ffddf7d69269daed
--- /dev/null
+++ b/checkpoint-600/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+ "bos_token": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|im_end|>"
+}
diff --git a/checkpoint-600/tokenizer.json b/checkpoint-600/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b
--- /dev/null
+++ b/checkpoint-600/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
+size 17209403
diff --git a/checkpoint-600/tokenizer_config.json b/checkpoint-600/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1dbecde59340b33dcf97ef6087584a5a01208ab5
--- /dev/null
+++ b/checkpoint-600/tokenizer_config.json
@@ -0,0 +1,2072 @@
+{
+ "added_tokens_decoder": {
+ "128000": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128001": {
+ "content": "<|end_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128002": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128003": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128004": {
+ "content": "<|finetune_right_pad_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128005": {
+ "content": "<|reserved_special_token_2|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128006": {
+ "content": "<|start_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128007": {
+ "content": "<|end_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128008": {
+ "content": "<|eom_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128009": {
+ "content": "<|eot_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128010": {
+ "content": "<|python_tag|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128011": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128012": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128013": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128014": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128015": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128016": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128017": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128018": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128019": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128020": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128021": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128022": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128023": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128024": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128025": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128026": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128027": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128028": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128029": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128030": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128031": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128032": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128033": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128034": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128035": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128036": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128037": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128038": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128039": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128040": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128041": {
+ "content": "<|reserved_special_token_33|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128042": {
+ "content": "<|reserved_special_token_34|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128043": {
+ "content": "<|reserved_special_token_35|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128044": {
+ "content": "<|reserved_special_token_36|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128045": {
+ "content": "<|reserved_special_token_37|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128046": {
+ "content": "<|reserved_special_token_38|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128047": {
+ "content": "<|reserved_special_token_39|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128048": {
+ "content": "<|reserved_special_token_40|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128049": {
+ "content": "<|reserved_special_token_41|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128050": {
+ "content": "<|reserved_special_token_42|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128051": {
+ "content": "<|reserved_special_token_43|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128052": {
+ "content": "<|reserved_special_token_44|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128053": {
+ "content": "<|reserved_special_token_45|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128054": {
+ "content": "<|reserved_special_token_46|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128055": {
+ "content": "<|reserved_special_token_47|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128056": {
+ "content": "<|reserved_special_token_48|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128057": {
+ "content": "<|reserved_special_token_49|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128058": {
+ "content": "<|reserved_special_token_50|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128059": {
+ "content": "<|reserved_special_token_51|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128060": {
+ "content": "<|reserved_special_token_52|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128061": {
+ "content": "<|reserved_special_token_53|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128062": {
+ "content": "<|reserved_special_token_54|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128063": {
+ "content": "<|reserved_special_token_55|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128064": {
+ "content": "<|reserved_special_token_56|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128065": {
+ "content": "<|reserved_special_token_57|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128066": {
+ "content": "<|reserved_special_token_58|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128067": {
+ "content": "<|reserved_special_token_59|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128068": {
+ "content": "<|reserved_special_token_60|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128069": {
+ "content": "<|reserved_special_token_61|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128070": {
+ "content": "<|reserved_special_token_62|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128071": {
+ "content": "<|reserved_special_token_63|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128072": {
+ "content": "<|reserved_special_token_64|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128073": {
+ "content": "<|reserved_special_token_65|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128074": {
+ "content": "<|reserved_special_token_66|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128075": {
+ "content": "<|reserved_special_token_67|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128076": {
+ "content": "<|reserved_special_token_68|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128077": {
+ "content": "<|reserved_special_token_69|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128078": {
+ "content": "<|reserved_special_token_70|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128079": {
+ "content": "<|reserved_special_token_71|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128080": {
+ "content": "<|reserved_special_token_72|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128081": {
+ "content": "<|reserved_special_token_73|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128082": {
+ "content": "<|reserved_special_token_74|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128083": {
+ "content": "<|reserved_special_token_75|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128084": {
+ "content": "<|reserved_special_token_76|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128085": {
+ "content": "<|reserved_special_token_77|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128086": {
+ "content": "<|reserved_special_token_78|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128087": {
+ "content": "<|reserved_special_token_79|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128088": {
+ "content": "<|reserved_special_token_80|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128089": {
+ "content": "<|reserved_special_token_81|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128090": {
+ "content": "<|reserved_special_token_82|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128091": {
+ "content": "<|reserved_special_token_83|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128092": {
+ "content": "<|reserved_special_token_84|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128093": {
+ "content": "<|reserved_special_token_85|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128094": {
+ "content": "<|reserved_special_token_86|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128095": {
+ "content": "<|reserved_special_token_87|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128096": {
+ "content": "<|reserved_special_token_88|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128097": {
+ "content": "<|reserved_special_token_89|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128098": {
+ "content": "<|reserved_special_token_90|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128099": {
+ "content": "<|reserved_special_token_91|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128100": {
+ "content": "<|reserved_special_token_92|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128101": {
+ "content": "<|reserved_special_token_93|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128102": {
+ "content": "<|reserved_special_token_94|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128103": {
+ "content": "<|reserved_special_token_95|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128104": {
+ "content": "<|reserved_special_token_96|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128105": {
+ "content": "<|reserved_special_token_97|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128106": {
+ "content": "<|reserved_special_token_98|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128107": {
+ "content": "<|reserved_special_token_99|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128108": {
+ "content": "<|reserved_special_token_100|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128109": {
+ "content": "<|reserved_special_token_101|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128110": {
+ "content": "<|reserved_special_token_102|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128111": {
+ "content": "<|reserved_special_token_103|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128112": {
+ "content": "<|reserved_special_token_104|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128113": {
+ "content": "<|reserved_special_token_105|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128114": {
+ "content": "<|reserved_special_token_106|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128115": {
+ "content": "<|reserved_special_token_107|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128116": {
+ "content": "<|reserved_special_token_108|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128117": {
+ "content": "<|reserved_special_token_109|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128118": {
+ "content": "<|reserved_special_token_110|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128119": {
+ "content": "<|reserved_special_token_111|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128120": {
+ "content": "<|reserved_special_token_112|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128121": {
+ "content": "<|reserved_special_token_113|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128122": {
+ "content": "<|reserved_special_token_114|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128123": {
+ "content": "<|reserved_special_token_115|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128124": {
+ "content": "<|reserved_special_token_116|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128125": {
+ "content": "<|reserved_special_token_117|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128126": {
+ "content": "<|reserved_special_token_118|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128127": {
+ "content": "<|reserved_special_token_119|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128128": {
+ "content": "<|reserved_special_token_120|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128129": {
+ "content": "<|reserved_special_token_121|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128130": {
+ "content": "<|reserved_special_token_122|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128131": {
+ "content": "<|reserved_special_token_123|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128132": {
+ "content": "<|reserved_special_token_124|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128133": {
+ "content": "<|reserved_special_token_125|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128134": {
+ "content": "<|reserved_special_token_126|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128135": {
+ "content": "<|reserved_special_token_127|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128136": {
+ "content": "<|reserved_special_token_128|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128137": {
+ "content": "<|reserved_special_token_129|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128138": {
+ "content": "<|reserved_special_token_130|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128139": {
+ "content": "<|reserved_special_token_131|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128140": {
+ "content": "<|reserved_special_token_132|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128141": {
+ "content": "<|reserved_special_token_133|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128142": {
+ "content": "<|reserved_special_token_134|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128143": {
+ "content": "<|reserved_special_token_135|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128144": {
+ "content": "<|reserved_special_token_136|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128145": {
+ "content": "<|reserved_special_token_137|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128146": {
+ "content": "<|reserved_special_token_138|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128147": {
+ "content": "<|reserved_special_token_139|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128148": {
+ "content": "<|reserved_special_token_140|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128149": {
+ "content": "<|reserved_special_token_141|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128150": {
+ "content": "<|reserved_special_token_142|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128151": {
+ "content": "<|reserved_special_token_143|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128152": {
+ "content": "<|reserved_special_token_144|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128153": {
+ "content": "<|reserved_special_token_145|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128154": {
+ "content": "<|reserved_special_token_146|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128155": {
+ "content": "<|reserved_special_token_147|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128156": {
+ "content": "<|reserved_special_token_148|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128157": {
+ "content": "<|reserved_special_token_149|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128158": {
+ "content": "<|reserved_special_token_150|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128159": {
+ "content": "<|reserved_special_token_151|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128160": {
+ "content": "<|reserved_special_token_152|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128161": {
+ "content": "<|reserved_special_token_153|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128162": {
+ "content": "<|reserved_special_token_154|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128163": {
+ "content": "<|reserved_special_token_155|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128164": {
+ "content": "<|reserved_special_token_156|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128165": {
+ "content": "<|reserved_special_token_157|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128166": {
+ "content": "<|reserved_special_token_158|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128167": {
+ "content": "<|reserved_special_token_159|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128168": {
+ "content": "<|reserved_special_token_160|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128169": {
+ "content": "<|reserved_special_token_161|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128170": {
+ "content": "<|reserved_special_token_162|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128171": {
+ "content": "<|reserved_special_token_163|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128172": {
+ "content": "<|reserved_special_token_164|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128173": {
+ "content": "<|reserved_special_token_165|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128174": {
+ "content": "<|reserved_special_token_166|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128175": {
+ "content": "<|reserved_special_token_167|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128176": {
+ "content": "<|reserved_special_token_168|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128177": {
+ "content": "<|reserved_special_token_169|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128178": {
+ "content": "<|reserved_special_token_170|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128179": {
+ "content": "<|reserved_special_token_171|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128180": {
+ "content": "<|reserved_special_token_172|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128181": {
+ "content": "<|reserved_special_token_173|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128182": {
+ "content": "<|reserved_special_token_174|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128183": {
+ "content": "<|reserved_special_token_175|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128184": {
+ "content": "<|reserved_special_token_176|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128185": {
+ "content": "<|reserved_special_token_177|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128186": {
+ "content": "<|reserved_special_token_178|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128187": {
+ "content": "<|reserved_special_token_179|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128188": {
+ "content": "<|reserved_special_token_180|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128189": {
+ "content": "<|reserved_special_token_181|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128190": {
+ "content": "<|reserved_special_token_182|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128191": {
+ "content": "<|reserved_special_token_183|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128192": {
+ "content": "<|reserved_special_token_184|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128193": {
+ "content": "<|reserved_special_token_185|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128194": {
+ "content": "<|reserved_special_token_186|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128195": {
+ "content": "<|reserved_special_token_187|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128196": {
+ "content": "<|reserved_special_token_188|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128197": {
+ "content": "<|reserved_special_token_189|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128198": {
+ "content": "<|reserved_special_token_190|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128199": {
+ "content": "<|reserved_special_token_191|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128200": {
+ "content": "<|reserved_special_token_192|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128201": {
+ "content": "<|reserved_special_token_193|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128202": {
+ "content": "<|reserved_special_token_194|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128203": {
+ "content": "<|reserved_special_token_195|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128204": {
+ "content": "<|reserved_special_token_196|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128205": {
+ "content": "<|reserved_special_token_197|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128206": {
+ "content": "<|reserved_special_token_198|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128207": {
+ "content": "<|reserved_special_token_199|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128208": {
+ "content": "<|reserved_special_token_200|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128209": {
+ "content": "<|reserved_special_token_201|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128210": {
+ "content": "<|reserved_special_token_202|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128211": {
+ "content": "<|reserved_special_token_203|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128212": {
+ "content": "<|reserved_special_token_204|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128213": {
+ "content": "<|reserved_special_token_205|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128214": {
+ "content": "<|reserved_special_token_206|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128215": {
+ "content": "<|reserved_special_token_207|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128216": {
+ "content": "<|reserved_special_token_208|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128217": {
+ "content": "<|reserved_special_token_209|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128218": {
+ "content": "<|reserved_special_token_210|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128219": {
+ "content": "<|reserved_special_token_211|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128220": {
+ "content": "<|reserved_special_token_212|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128221": {
+ "content": "<|reserved_special_token_213|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128222": {
+ "content": "<|reserved_special_token_214|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128223": {
+ "content": "<|reserved_special_token_215|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128224": {
+ "content": "<|reserved_special_token_216|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128225": {
+ "content": "<|reserved_special_token_217|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128226": {
+ "content": "<|reserved_special_token_218|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128227": {
+ "content": "<|reserved_special_token_219|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128228": {
+ "content": "<|reserved_special_token_220|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128229": {
+ "content": "<|reserved_special_token_221|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128230": {
+ "content": "<|reserved_special_token_222|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128231": {
+ "content": "<|reserved_special_token_223|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128232": {
+ "content": "<|reserved_special_token_224|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128233": {
+ "content": "<|reserved_special_token_225|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128234": {
+ "content": "<|reserved_special_token_226|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128235": {
+ "content": "<|reserved_special_token_227|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128236": {
+ "content": "<|reserved_special_token_228|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128237": {
+ "content": "<|reserved_special_token_229|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128238": {
+ "content": "<|reserved_special_token_230|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128239": {
+ "content": "<|reserved_special_token_231|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128240": {
+ "content": "<|reserved_special_token_232|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128241": {
+ "content": "<|reserved_special_token_233|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128242": {
+ "content": "<|reserved_special_token_234|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128243": {
+ "content": "<|reserved_special_token_235|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128244": {
+ "content": "<|reserved_special_token_236|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128245": {
+ "content": "<|reserved_special_token_237|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128246": {
+ "content": "<|reserved_special_token_238|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128247": {
+ "content": "<|reserved_special_token_239|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128248": {
+ "content": "<|reserved_special_token_240|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128249": {
+ "content": "<|reserved_special_token_241|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128250": {
+ "content": "<|reserved_special_token_242|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128251": {
+ "content": "<|reserved_special_token_243|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128252": {
+ "content": "<|reserved_special_token_244|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128253": {
+ "content": "<|reserved_special_token_245|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128254": {
+ "content": "<|reserved_special_token_246|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128255": {
+ "content": "<|reserved_special_token_247|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|begin_of_text|>",
+ "chat_template": [
+ {
+ "name": "default",
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+ },
+ {
+ "name": "tool_use",
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" \" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within XML tags as follows:\n\" }}\n{{- \"\n\" }}\n{{- '{\"name\": , \"arguments\": }\n' }}\n{{- '<|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- else %}\n {{- '\n' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+ }
+ ],
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|im_end|>",
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 131072,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d163e9e1c67cfe435c82d9f35391ffe5c79b0b6b
--- /dev/null
+++ b/checkpoint-600/trainer_state.json
@@ -0,0 +1,1113 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.0434227330779056,
+ "eval_steps": 500,
+ "global_step": 600,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.017028522775649212,
+ "grad_norm": 6.522716999053955,
+ "learning_rate": 0.0001988623435722412,
+ "loss": 2.7211,
+ "mean_token_accuracy": 0.5789041496813297,
+ "num_tokens": 4727.0,
+ "step": 5
+ },
+ {
+ "epoch": 0.034057045551298425,
+ "grad_norm": 1.0070050954818726,
+ "learning_rate": 0.00019772468714448238,
+ "loss": 0.9998,
+ "mean_token_accuracy": 0.8499793156981468,
+ "num_tokens": 9471.0,
+ "step": 10
+ },
+ {
+ "epoch": 0.05108556832694764,
+ "grad_norm": 0.7373425960540771,
+ "learning_rate": 0.00019658703071672356,
+ "loss": 0.8303,
+ "mean_token_accuracy": 0.8681916877627373,
+ "num_tokens": 14013.0,
+ "step": 15
+ },
+ {
+ "epoch": 0.06811409110259685,
+ "grad_norm": 0.8468236327171326,
+ "learning_rate": 0.00019544937428896475,
+ "loss": 0.8404,
+ "mean_token_accuracy": 0.8622620105743408,
+ "num_tokens": 18725.0,
+ "step": 20
+ },
+ {
+ "epoch": 0.08514261387824607,
+ "grad_norm": 0.8178804516792297,
+ "learning_rate": 0.00019431171786120593,
+ "loss": 0.9073,
+ "mean_token_accuracy": 0.8524447843432427,
+ "num_tokens": 23497.0,
+ "step": 25
+ },
+ {
+ "epoch": 0.10217113665389528,
+ "grad_norm": 0.890177309513092,
+ "learning_rate": 0.00019317406143344712,
+ "loss": 0.8029,
+ "mean_token_accuracy": 0.8642359614372254,
+ "num_tokens": 28192.0,
+ "step": 30
+ },
+ {
+ "epoch": 0.11919965942954448,
+ "grad_norm": 1.0545469522476196,
+ "learning_rate": 0.0001920364050056883,
+ "loss": 0.7458,
+ "mean_token_accuracy": 0.8732351213693619,
+ "num_tokens": 32805.0,
+ "step": 35
+ },
+ {
+ "epoch": 0.1362281822051937,
+ "grad_norm": 1.0384492874145508,
+ "learning_rate": 0.00019089874857792946,
+ "loss": 0.9235,
+ "mean_token_accuracy": 0.8408558666706085,
+ "num_tokens": 37714.0,
+ "step": 40
+ },
+ {
+ "epoch": 0.1532567049808429,
+ "grad_norm": 0.6860374808311462,
+ "learning_rate": 0.00018976109215017067,
+ "loss": 0.7623,
+ "mean_token_accuracy": 0.8656536340713501,
+ "num_tokens": 42429.0,
+ "step": 45
+ },
+ {
+ "epoch": 0.17028522775649213,
+ "grad_norm": 0.7284501791000366,
+ "learning_rate": 0.00018862343572241183,
+ "loss": 0.7588,
+ "mean_token_accuracy": 0.8688850715756417,
+ "num_tokens": 47099.0,
+ "step": 50
+ },
+ {
+ "epoch": 0.18731375053214133,
+ "grad_norm": 0.8899862170219421,
+ "learning_rate": 0.00018748577929465302,
+ "loss": 0.7065,
+ "mean_token_accuracy": 0.8717748820781708,
+ "num_tokens": 51795.0,
+ "step": 55
+ },
+ {
+ "epoch": 0.20434227330779056,
+ "grad_norm": 0.5350505709648132,
+ "learning_rate": 0.0001863481228668942,
+ "loss": 0.6696,
+ "mean_token_accuracy": 0.8851396456360817,
+ "num_tokens": 56369.0,
+ "step": 60
+ },
+ {
+ "epoch": 0.22137079608343976,
+ "grad_norm": 0.6087013483047485,
+ "learning_rate": 0.0001852104664391354,
+ "loss": 0.7204,
+ "mean_token_accuracy": 0.8682332798838616,
+ "num_tokens": 61018.0,
+ "step": 65
+ },
+ {
+ "epoch": 0.23839931885908897,
+ "grad_norm": 0.7879019379615784,
+ "learning_rate": 0.00018407281001137657,
+ "loss": 0.7692,
+ "mean_token_accuracy": 0.8653983056545258,
+ "num_tokens": 65741.0,
+ "step": 70
+ },
+ {
+ "epoch": 0.2554278416347382,
+ "grad_norm": 0.6546444296836853,
+ "learning_rate": 0.00018293515358361776,
+ "loss": 0.7119,
+ "mean_token_accuracy": 0.8726310178637504,
+ "num_tokens": 70425.0,
+ "step": 75
+ },
+ {
+ "epoch": 0.2724563644103874,
+ "grad_norm": 0.770902156829834,
+ "learning_rate": 0.00018179749715585894,
+ "loss": 0.7035,
+ "mean_token_accuracy": 0.8711811751127243,
+ "num_tokens": 75101.0,
+ "step": 80
+ },
+ {
+ "epoch": 0.2894848871860366,
+ "grad_norm": 0.8873187899589539,
+ "learning_rate": 0.00018065984072810013,
+ "loss": 0.7419,
+ "mean_token_accuracy": 0.8616803497076034,
+ "num_tokens": 79888.0,
+ "step": 85
+ },
+ {
+ "epoch": 0.3065134099616858,
+ "grad_norm": 0.7061370015144348,
+ "learning_rate": 0.0001795221843003413,
+ "loss": 0.66,
+ "mean_token_accuracy": 0.8744896531105042,
+ "num_tokens": 84562.0,
+ "step": 90
+ },
+ {
+ "epoch": 0.32354193273733506,
+ "grad_norm": 0.8232033252716064,
+ "learning_rate": 0.0001783845278725825,
+ "loss": 0.7403,
+ "mean_token_accuracy": 0.8659066379070282,
+ "num_tokens": 89238.0,
+ "step": 95
+ },
+ {
+ "epoch": 0.34057045551298426,
+ "grad_norm": 0.7313310503959656,
+ "learning_rate": 0.00017724687144482368,
+ "loss": 0.7157,
+ "mean_token_accuracy": 0.8661555901169777,
+ "num_tokens": 93987.0,
+ "step": 100
+ },
+ {
+ "epoch": 0.35759897828863346,
+ "grad_norm": 0.7119390964508057,
+ "learning_rate": 0.00017610921501706487,
+ "loss": 0.7016,
+ "mean_token_accuracy": 0.8678551658987999,
+ "num_tokens": 98722.0,
+ "step": 105
+ },
+ {
+ "epoch": 0.37462750106428266,
+ "grad_norm": 0.7126006484031677,
+ "learning_rate": 0.00017497155858930602,
+ "loss": 0.7009,
+ "mean_token_accuracy": 0.867291408777237,
+ "num_tokens": 103439.0,
+ "step": 110
+ },
+ {
+ "epoch": 0.39165602383993187,
+ "grad_norm": 0.6158230304718018,
+ "learning_rate": 0.00017383390216154724,
+ "loss": 0.7236,
+ "mean_token_accuracy": 0.8636128515005111,
+ "num_tokens": 108209.0,
+ "step": 115
+ },
+ {
+ "epoch": 0.4086845466155811,
+ "grad_norm": 0.6498322486877441,
+ "learning_rate": 0.0001726962457337884,
+ "loss": 0.6813,
+ "mean_token_accuracy": 0.8757071048021317,
+ "num_tokens": 112855.0,
+ "step": 120
+ },
+ {
+ "epoch": 0.4257130693912303,
+ "grad_norm": 0.6594287157058716,
+ "learning_rate": 0.0001715585893060296,
+ "loss": 0.7062,
+ "mean_token_accuracy": 0.8650311172008515,
+ "num_tokens": 117653.0,
+ "step": 125
+ },
+ {
+ "epoch": 0.4427415921668795,
+ "grad_norm": 0.7375237941741943,
+ "learning_rate": 0.00017042093287827076,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8733970731496811,
+ "num_tokens": 122397.0,
+ "step": 130
+ },
+ {
+ "epoch": 0.45977011494252873,
+ "grad_norm": 0.5958442687988281,
+ "learning_rate": 0.00016928327645051198,
+ "loss": 0.691,
+ "mean_token_accuracy": 0.8681387722492218,
+ "num_tokens": 127136.0,
+ "step": 135
+ },
+ {
+ "epoch": 0.47679863771817793,
+ "grad_norm": 0.7407785654067993,
+ "learning_rate": 0.00016814562002275313,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8752307429909706,
+ "num_tokens": 131833.0,
+ "step": 140
+ },
+ {
+ "epoch": 0.49382716049382713,
+ "grad_norm": 0.8190199732780457,
+ "learning_rate": 0.00016700796359499432,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8762851104140281,
+ "num_tokens": 136441.0,
+ "step": 145
+ },
+ {
+ "epoch": 0.5108556832694764,
+ "grad_norm": 0.7571837306022644,
+ "learning_rate": 0.0001658703071672355,
+ "loss": 0.673,
+ "mean_token_accuracy": 0.8691665843129158,
+ "num_tokens": 141186.0,
+ "step": 150
+ },
+ {
+ "epoch": 0.5278842060451255,
+ "grad_norm": 0.6653426885604858,
+ "learning_rate": 0.0001647326507394767,
+ "loss": 0.7126,
+ "mean_token_accuracy": 0.8647830635309219,
+ "num_tokens": 145971.0,
+ "step": 155
+ },
+ {
+ "epoch": 0.5449127288207748,
+ "grad_norm": 0.7333567142486572,
+ "learning_rate": 0.00016359499431171787,
+ "loss": 0.6287,
+ "mean_token_accuracy": 0.878324082493782,
+ "num_tokens": 150669.0,
+ "step": 160
+ },
+ {
+ "epoch": 0.561941251596424,
+ "grad_norm": 0.8214460015296936,
+ "learning_rate": 0.00016245733788395906,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8729922890663147,
+ "num_tokens": 155374.0,
+ "step": 165
+ },
+ {
+ "epoch": 0.5789697743720732,
+ "grad_norm": 0.6251844167709351,
+ "learning_rate": 0.00016131968145620024,
+ "loss": 0.6556,
+ "mean_token_accuracy": 0.8770609870553017,
+ "num_tokens": 160068.0,
+ "step": 170
+ },
+ {
+ "epoch": 0.5959982971477225,
+ "grad_norm": 0.804166853427887,
+ "learning_rate": 0.00016018202502844143,
+ "loss": 0.6366,
+ "mean_token_accuracy": 0.8760894432663917,
+ "num_tokens": 164696.0,
+ "step": 175
+ },
+ {
+ "epoch": 0.6130268199233716,
+ "grad_norm": 0.7013877034187317,
+ "learning_rate": 0.0001590443686006826,
+ "loss": 0.6328,
+ "mean_token_accuracy": 0.8779815405607223,
+ "num_tokens": 169356.0,
+ "step": 180
+ },
+ {
+ "epoch": 0.6300553426990209,
+ "grad_norm": 1.0623070001602173,
+ "learning_rate": 0.0001579067121729238,
+ "loss": 0.6734,
+ "mean_token_accuracy": 0.8710577815771103,
+ "num_tokens": 174041.0,
+ "step": 185
+ },
+ {
+ "epoch": 0.6470838654746701,
+ "grad_norm": 0.7858535647392273,
+ "learning_rate": 0.00015676905574516496,
+ "loss": 0.6775,
+ "mean_token_accuracy": 0.8692880481481552,
+ "num_tokens": 178858.0,
+ "step": 190
+ },
+ {
+ "epoch": 0.6641123882503193,
+ "grad_norm": 0.8943309187889099,
+ "learning_rate": 0.00015563139931740617,
+ "loss": 0.6874,
+ "mean_token_accuracy": 0.868885512650013,
+ "num_tokens": 183669.0,
+ "step": 195
+ },
+ {
+ "epoch": 0.6811409110259685,
+ "grad_norm": 0.5898745656013489,
+ "learning_rate": 0.00015449374288964733,
+ "loss": 0.6907,
+ "mean_token_accuracy": 0.8661940798163414,
+ "num_tokens": 188473.0,
+ "step": 200
+ },
+ {
+ "epoch": 0.6981694338016177,
+ "grad_norm": 0.6333857774734497,
+ "learning_rate": 0.00015335608646188854,
+ "loss": 0.6129,
+ "mean_token_accuracy": 0.8817986205220223,
+ "num_tokens": 193171.0,
+ "step": 205
+ },
+ {
+ "epoch": 0.7151979565772669,
+ "grad_norm": 0.5913947820663452,
+ "learning_rate": 0.0001522184300341297,
+ "loss": 0.5896,
+ "mean_token_accuracy": 0.8822762459516525,
+ "num_tokens": 197817.0,
+ "step": 210
+ },
+ {
+ "epoch": 0.7322264793529162,
+ "grad_norm": 0.6990242004394531,
+ "learning_rate": 0.00015108077360637088,
+ "loss": 0.6512,
+ "mean_token_accuracy": 0.8739180400967598,
+ "num_tokens": 202556.0,
+ "step": 215
+ },
+ {
+ "epoch": 0.7492550021285653,
+ "grad_norm": 0.6869048476219177,
+ "learning_rate": 0.00014994311717861207,
+ "loss": 0.7025,
+ "mean_token_accuracy": 0.8662877783179284,
+ "num_tokens": 207294.0,
+ "step": 220
+ },
+ {
+ "epoch": 0.7662835249042146,
+ "grad_norm": 0.5135166049003601,
+ "learning_rate": 0.00014880546075085325,
+ "loss": 0.6382,
+ "mean_token_accuracy": 0.8849207311868668,
+ "num_tokens": 211927.0,
+ "step": 225
+ },
+ {
+ "epoch": 0.7833120476798637,
+ "grad_norm": 0.6304216980934143,
+ "learning_rate": 0.00014766780432309444,
+ "loss": 0.6834,
+ "mean_token_accuracy": 0.8688049465417862,
+ "num_tokens": 216626.0,
+ "step": 230
+ },
+ {
+ "epoch": 0.800340570455513,
+ "grad_norm": 0.6879922151565552,
+ "learning_rate": 0.00014653014789533562,
+ "loss": 0.6902,
+ "mean_token_accuracy": 0.8655798360705376,
+ "num_tokens": 221432.0,
+ "step": 235
+ },
+ {
+ "epoch": 0.8173690932311622,
+ "grad_norm": 0.6433548331260681,
+ "learning_rate": 0.0001453924914675768,
+ "loss": 0.6129,
+ "mean_token_accuracy": 0.8795880794525146,
+ "num_tokens": 226022.0,
+ "step": 240
+ },
+ {
+ "epoch": 0.8343976160068114,
+ "grad_norm": 0.7876724600791931,
+ "learning_rate": 0.000144254835039818,
+ "loss": 0.6441,
+ "mean_token_accuracy": 0.8729524433612823,
+ "num_tokens": 230692.0,
+ "step": 245
+ },
+ {
+ "epoch": 0.8514261387824607,
+ "grad_norm": 0.6494749188423157,
+ "learning_rate": 0.00014311717861205915,
+ "loss": 0.7033,
+ "mean_token_accuracy": 0.8632469072937965,
+ "num_tokens": 235400.0,
+ "step": 250
+ },
+ {
+ "epoch": 0.8684546615581098,
+ "grad_norm": 0.6332300305366516,
+ "learning_rate": 0.00014197952218430036,
+ "loss": 0.5947,
+ "mean_token_accuracy": 0.8860528379678726,
+ "num_tokens": 239997.0,
+ "step": 255
+ },
+ {
+ "epoch": 0.885483184333759,
+ "grad_norm": 0.7144895195960999,
+ "learning_rate": 0.00014084186575654152,
+ "loss": 0.649,
+ "mean_token_accuracy": 0.8745664536952973,
+ "num_tokens": 244704.0,
+ "step": 260
+ },
+ {
+ "epoch": 0.9025117071094083,
+ "grad_norm": 0.5460124015808105,
+ "learning_rate": 0.00013970420932878273,
+ "loss": 0.6622,
+ "mean_token_accuracy": 0.8692788198590279,
+ "num_tokens": 249428.0,
+ "step": 265
+ },
+ {
+ "epoch": 0.9195402298850575,
+ "grad_norm": 0.65619295835495,
+ "learning_rate": 0.0001385665529010239,
+ "loss": 0.657,
+ "mean_token_accuracy": 0.8737826406955719,
+ "num_tokens": 254150.0,
+ "step": 270
+ },
+ {
+ "epoch": 0.9365687526607067,
+ "grad_norm": 0.8474870324134827,
+ "learning_rate": 0.0001374288964732651,
+ "loss": 0.6607,
+ "mean_token_accuracy": 0.8756056800484657,
+ "num_tokens": 258826.0,
+ "step": 275
+ },
+ {
+ "epoch": 0.9535972754363559,
+ "grad_norm": 0.6054229736328125,
+ "learning_rate": 0.00013629124004550626,
+ "loss": 0.6526,
+ "mean_token_accuracy": 0.8718441724777222,
+ "num_tokens": 263524.0,
+ "step": 280
+ },
+ {
+ "epoch": 0.9706257982120051,
+ "grad_norm": 0.6568702459335327,
+ "learning_rate": 0.00013515358361774744,
+ "loss": 0.6174,
+ "mean_token_accuracy": 0.881709736585617,
+ "num_tokens": 268179.0,
+ "step": 285
+ },
+ {
+ "epoch": 0.9876543209876543,
+ "grad_norm": 0.7518045902252197,
+ "learning_rate": 0.00013401592718998863,
+ "loss": 0.5896,
+ "mean_token_accuracy": 0.885109031200409,
+ "num_tokens": 272803.0,
+ "step": 290
+ },
+ {
+ "epoch": 1.0046828437633035,
+ "grad_norm": 0.5392197370529175,
+ "learning_rate": 0.00013287827076222981,
+ "loss": 0.6753,
+ "mean_token_accuracy": 0.8788385137915611,
+ "num_tokens": 277527.0,
+ "step": 295
+ },
+ {
+ "epoch": 1.0217113665389528,
+ "grad_norm": 0.5845906734466553,
+ "learning_rate": 0.000131740614334471,
+ "loss": 0.5237,
+ "mean_token_accuracy": 0.8938747227191925,
+ "num_tokens": 282199.0,
+ "step": 300
+ },
+ {
+ "epoch": 1.038739889314602,
+ "grad_norm": 0.6392928957939148,
+ "learning_rate": 0.00013060295790671218,
+ "loss": 0.4973,
+ "mean_token_accuracy": 0.8982622623443604,
+ "num_tokens": 286951.0,
+ "step": 305
+ },
+ {
+ "epoch": 1.055768412090251,
+ "grad_norm": 0.5399300456047058,
+ "learning_rate": 0.00012946530147895337,
+ "loss": 0.5076,
+ "mean_token_accuracy": 0.9008002370595932,
+ "num_tokens": 291569.0,
+ "step": 310
+ },
+ {
+ "epoch": 1.0727969348659003,
+ "grad_norm": 0.6236026883125305,
+ "learning_rate": 0.00012832764505119455,
+ "loss": 0.5084,
+ "mean_token_accuracy": 0.8972577184438706,
+ "num_tokens": 296230.0,
+ "step": 315
+ },
+ {
+ "epoch": 1.0898254576415496,
+ "grad_norm": 0.7385813593864441,
+ "learning_rate": 0.0001271899886234357,
+ "loss": 0.5062,
+ "mean_token_accuracy": 0.8956585437059402,
+ "num_tokens": 301029.0,
+ "step": 320
+ },
+ {
+ "epoch": 1.1068539804171988,
+ "grad_norm": 0.7647150754928589,
+ "learning_rate": 0.00012605233219567692,
+ "loss": 0.5078,
+ "mean_token_accuracy": 0.8982979074120522,
+ "num_tokens": 305696.0,
+ "step": 325
+ },
+ {
+ "epoch": 1.123882503192848,
+ "grad_norm": 0.6433872580528259,
+ "learning_rate": 0.00012491467576791808,
+ "loss": 0.5215,
+ "mean_token_accuracy": 0.8974734947085381,
+ "num_tokens": 310343.0,
+ "step": 330
+ },
+ {
+ "epoch": 1.1409110259684971,
+ "grad_norm": 0.6470033526420593,
+ "learning_rate": 0.0001237770193401593,
+ "loss": 0.5261,
+ "mean_token_accuracy": 0.8938129872083664,
+ "num_tokens": 315097.0,
+ "step": 335
+ },
+ {
+ "epoch": 1.1579395487441464,
+ "grad_norm": 0.6738846302032471,
+ "learning_rate": 0.00012263936291240045,
+ "loss": 0.5277,
+ "mean_token_accuracy": 0.8924461513757705,
+ "num_tokens": 319861.0,
+ "step": 340
+ },
+ {
+ "epoch": 1.1749680715197957,
+ "grad_norm": 0.6639145016670227,
+ "learning_rate": 0.00012150170648464165,
+ "loss": 0.5127,
+ "mean_token_accuracy": 0.8926685571670532,
+ "num_tokens": 324544.0,
+ "step": 345
+ },
+ {
+ "epoch": 1.191996594295445,
+ "grad_norm": 0.7034420371055603,
+ "learning_rate": 0.00012036405005688282,
+ "loss": 0.51,
+ "mean_token_accuracy": 0.8971043467521668,
+ "num_tokens": 329302.0,
+ "step": 350
+ },
+ {
+ "epoch": 1.2090251170710942,
+ "grad_norm": 0.6675500273704529,
+ "learning_rate": 0.000119226393629124,
+ "loss": 0.5738,
+ "mean_token_accuracy": 0.8855719327926636,
+ "num_tokens": 334103.0,
+ "step": 355
+ },
+ {
+ "epoch": 1.2260536398467432,
+ "grad_norm": 0.6019395589828491,
+ "learning_rate": 0.00011808873720136519,
+ "loss": 0.476,
+ "mean_token_accuracy": 0.8989460453391075,
+ "num_tokens": 338666.0,
+ "step": 360
+ },
+ {
+ "epoch": 1.2430821626223925,
+ "grad_norm": 0.6599250435829163,
+ "learning_rate": 0.00011695108077360638,
+ "loss": 0.5178,
+ "mean_token_accuracy": 0.8887226998805999,
+ "num_tokens": 343333.0,
+ "step": 365
+ },
+ {
+ "epoch": 1.2601106853980417,
+ "grad_norm": 0.7334213852882385,
+ "learning_rate": 0.00011581342434584756,
+ "loss": 0.5378,
+ "mean_token_accuracy": 0.8895460113883018,
+ "num_tokens": 348092.0,
+ "step": 370
+ },
+ {
+ "epoch": 1.277139208173691,
+ "grad_norm": 0.7423357963562012,
+ "learning_rate": 0.00011467576791808873,
+ "loss": 0.5012,
+ "mean_token_accuracy": 0.8994292929768563,
+ "num_tokens": 352661.0,
+ "step": 375
+ },
+ {
+ "epoch": 1.29416773094934,
+ "grad_norm": 0.857515811920166,
+ "learning_rate": 0.00011353811149032993,
+ "loss": 0.507,
+ "mean_token_accuracy": 0.8979884222149849,
+ "num_tokens": 357330.0,
+ "step": 380
+ },
+ {
+ "epoch": 1.3111962537249893,
+ "grad_norm": 0.5656803250312805,
+ "learning_rate": 0.0001124004550625711,
+ "loss": 0.5009,
+ "mean_token_accuracy": 0.8934224143624305,
+ "num_tokens": 362020.0,
+ "step": 385
+ },
+ {
+ "epoch": 1.3282247765006385,
+ "grad_norm": 0.6634964942932129,
+ "learning_rate": 0.00011126279863481229,
+ "loss": 0.5414,
+ "mean_token_accuracy": 0.8910330131649971,
+ "num_tokens": 366728.0,
+ "step": 390
+ },
+ {
+ "epoch": 1.3452532992762878,
+ "grad_norm": 0.7004157304763794,
+ "learning_rate": 0.00011012514220705347,
+ "loss": 0.4922,
+ "mean_token_accuracy": 0.8992783546447753,
+ "num_tokens": 371381.0,
+ "step": 395
+ },
+ {
+ "epoch": 1.362281822051937,
+ "grad_norm": 0.6225594282150269,
+ "learning_rate": 0.00010898748577929466,
+ "loss": 0.5084,
+ "mean_token_accuracy": 0.8956901535391808,
+ "num_tokens": 376043.0,
+ "step": 400
+ },
+ {
+ "epoch": 1.3793103448275863,
+ "grad_norm": 0.8019647598266602,
+ "learning_rate": 0.00010784982935153584,
+ "loss": 0.5303,
+ "mean_token_accuracy": 0.8940754950046539,
+ "num_tokens": 380714.0,
+ "step": 405
+ },
+ {
+ "epoch": 1.3963388676032356,
+ "grad_norm": 0.8314201831817627,
+ "learning_rate": 0.00010671217292377703,
+ "loss": 0.5249,
+ "mean_token_accuracy": 0.8924115225672722,
+ "num_tokens": 385498.0,
+ "step": 410
+ },
+ {
+ "epoch": 1.4133673903788846,
+ "grad_norm": 0.6691393256187439,
+ "learning_rate": 0.00010557451649601821,
+ "loss": 0.4817,
+ "mean_token_accuracy": 0.89882483035326,
+ "num_tokens": 390179.0,
+ "step": 415
+ },
+ {
+ "epoch": 1.4303959131545338,
+ "grad_norm": 0.8554338216781616,
+ "learning_rate": 0.00010443686006825938,
+ "loss": 0.5191,
+ "mean_token_accuracy": 0.8876234069466591,
+ "num_tokens": 394930.0,
+ "step": 420
+ },
+ {
+ "epoch": 1.447424435930183,
+ "grad_norm": 0.696018636226654,
+ "learning_rate": 0.00010329920364050057,
+ "loss": 0.5386,
+ "mean_token_accuracy": 0.891503955423832,
+ "num_tokens": 399685.0,
+ "step": 425
+ },
+ {
+ "epoch": 1.4644529587058321,
+ "grad_norm": 0.7389529943466187,
+ "learning_rate": 0.00010216154721274175,
+ "loss": 0.4949,
+ "mean_token_accuracy": 0.9004919424653053,
+ "num_tokens": 404300.0,
+ "step": 430
+ },
+ {
+ "epoch": 1.4814814814814814,
+ "grad_norm": 1.0227491855621338,
+ "learning_rate": 0.00010102389078498294,
+ "loss": 0.54,
+ "mean_token_accuracy": 0.8893611416220665,
+ "num_tokens": 409079.0,
+ "step": 435
+ },
+ {
+ "epoch": 1.4985100042571307,
+ "grad_norm": 0.6526888012886047,
+ "learning_rate": 9.988623435722412e-05,
+ "loss": 0.4917,
+ "mean_token_accuracy": 0.8958082437515259,
+ "num_tokens": 413758.0,
+ "step": 440
+ },
+ {
+ "epoch": 1.51553852703278,
+ "grad_norm": 0.5875766277313232,
+ "learning_rate": 9.874857792946531e-05,
+ "loss": 0.4991,
+ "mean_token_accuracy": 0.8971148490905761,
+ "num_tokens": 418502.0,
+ "step": 445
+ },
+ {
+ "epoch": 1.5325670498084292,
+ "grad_norm": 0.6892980337142944,
+ "learning_rate": 9.761092150170649e-05,
+ "loss": 0.4551,
+ "mean_token_accuracy": 0.9068983420729637,
+ "num_tokens": 423099.0,
+ "step": 450
+ },
+ {
+ "epoch": 1.5495955725840784,
+ "grad_norm": 0.6264586448669434,
+ "learning_rate": 9.647326507394768e-05,
+ "loss": 0.468,
+ "mean_token_accuracy": 0.9043048679828644,
+ "num_tokens": 427701.0,
+ "step": 455
+ },
+ {
+ "epoch": 1.5666240953597277,
+ "grad_norm": 0.5398015379905701,
+ "learning_rate": 9.533560864618886e-05,
+ "loss": 0.4877,
+ "mean_token_accuracy": 0.8986729174852371,
+ "num_tokens": 432430.0,
+ "step": 460
+ },
+ {
+ "epoch": 1.5836526181353767,
+ "grad_norm": 0.827769935131073,
+ "learning_rate": 9.419795221843003e-05,
+ "loss": 0.4951,
+ "mean_token_accuracy": 0.9012611672282219,
+ "num_tokens": 437078.0,
+ "step": 465
+ },
+ {
+ "epoch": 1.600681140911026,
+ "grad_norm": 0.6888080835342407,
+ "learning_rate": 9.306029579067122e-05,
+ "loss": 0.5108,
+ "mean_token_accuracy": 0.8976602256298065,
+ "num_tokens": 441734.0,
+ "step": 470
+ },
+ {
+ "epoch": 1.617709663686675,
+ "grad_norm": 0.837681233882904,
+ "learning_rate": 9.19226393629124e-05,
+ "loss": 0.5377,
+ "mean_token_accuracy": 0.8850761532783509,
+ "num_tokens": 446637.0,
+ "step": 475
+ },
+ {
+ "epoch": 1.6347381864623243,
+ "grad_norm": 0.7211363315582275,
+ "learning_rate": 9.078498293515359e-05,
+ "loss": 0.5001,
+ "mean_token_accuracy": 0.898733913898468,
+ "num_tokens": 451301.0,
+ "step": 480
+ },
+ {
+ "epoch": 1.6517667092379735,
+ "grad_norm": 0.6663438081741333,
+ "learning_rate": 8.964732650739477e-05,
+ "loss": 0.5144,
+ "mean_token_accuracy": 0.8976200923323632,
+ "num_tokens": 455965.0,
+ "step": 485
+ },
+ {
+ "epoch": 1.6687952320136228,
+ "grad_norm": 0.8935639262199402,
+ "learning_rate": 8.850967007963596e-05,
+ "loss": 0.5331,
+ "mean_token_accuracy": 0.8960411131381989,
+ "num_tokens": 460716.0,
+ "step": 490
+ },
+ {
+ "epoch": 1.685823754789272,
+ "grad_norm": 0.7235546708106995,
+ "learning_rate": 8.737201365187714e-05,
+ "loss": 0.4831,
+ "mean_token_accuracy": 0.8972082689404488,
+ "num_tokens": 465370.0,
+ "step": 495
+ },
+ {
+ "epoch": 1.7028522775649213,
+ "grad_norm": 0.774000346660614,
+ "learning_rate": 8.623435722411833e-05,
+ "loss": 0.5186,
+ "mean_token_accuracy": 0.8950631290674209,
+ "num_tokens": 470043.0,
+ "step": 500
+ },
+ {
+ "epoch": 1.7198808003405706,
+ "grad_norm": 0.5213722586631775,
+ "learning_rate": 8.509670079635951e-05,
+ "loss": 0.4567,
+ "mean_token_accuracy": 0.9016156733036041,
+ "num_tokens": 474573.0,
+ "step": 505
+ },
+ {
+ "epoch": 1.7369093231162198,
+ "grad_norm": 0.7278684377670288,
+ "learning_rate": 8.395904436860069e-05,
+ "loss": 0.5545,
+ "mean_token_accuracy": 0.8925162181258202,
+ "num_tokens": 479305.0,
+ "step": 510
+ },
+ {
+ "epoch": 1.7539378458918689,
+ "grad_norm": 0.7252481579780579,
+ "learning_rate": 8.282138794084187e-05,
+ "loss": 0.496,
+ "mean_token_accuracy": 0.8953201442956924,
+ "num_tokens": 484033.0,
+ "step": 515
+ },
+ {
+ "epoch": 1.770966368667518,
+ "grad_norm": 0.727513313293457,
+ "learning_rate": 8.168373151308306e-05,
+ "loss": 0.5033,
+ "mean_token_accuracy": 0.8998701125383377,
+ "num_tokens": 488727.0,
+ "step": 520
+ },
+ {
+ "epoch": 1.7879948914431671,
+ "grad_norm": 0.5375337600708008,
+ "learning_rate": 8.054607508532424e-05,
+ "loss": 0.4903,
+ "mean_token_accuracy": 0.8960629358887673,
+ "num_tokens": 493411.0,
+ "step": 525
+ },
+ {
+ "epoch": 1.8050234142188164,
+ "grad_norm": 0.5851954221725464,
+ "learning_rate": 7.940841865756543e-05,
+ "loss": 0.5139,
+ "mean_token_accuracy": 0.8972602248191833,
+ "num_tokens": 498098.0,
+ "step": 530
+ },
+ {
+ "epoch": 1.8220519369944657,
+ "grad_norm": 0.6942209005355835,
+ "learning_rate": 7.827076222980661e-05,
+ "loss": 0.4728,
+ "mean_token_accuracy": 0.9009919315576553,
+ "num_tokens": 502717.0,
+ "step": 535
+ },
+ {
+ "epoch": 1.839080459770115,
+ "grad_norm": 0.9342221021652222,
+ "learning_rate": 7.71331058020478e-05,
+ "loss": 0.5283,
+ "mean_token_accuracy": 0.8924958631396294,
+ "num_tokens": 507462.0,
+ "step": 540
+ },
+ {
+ "epoch": 1.8561089825457642,
+ "grad_norm": 0.7415278553962708,
+ "learning_rate": 7.599544937428897e-05,
+ "loss": 0.5394,
+ "mean_token_accuracy": 0.8913042590022087,
+ "num_tokens": 512202.0,
+ "step": 545
+ },
+ {
+ "epoch": 1.8731375053214134,
+ "grad_norm": 0.7223448157310486,
+ "learning_rate": 7.485779294653015e-05,
+ "loss": 0.5473,
+ "mean_token_accuracy": 0.8873603999614715,
+ "num_tokens": 517047.0,
+ "step": 550
+ },
+ {
+ "epoch": 1.8901660280970627,
+ "grad_norm": 0.6324387192726135,
+ "learning_rate": 7.372013651877134e-05,
+ "loss": 0.4986,
+ "mean_token_accuracy": 0.9018153563141823,
+ "num_tokens": 521653.0,
+ "step": 555
+ },
+ {
+ "epoch": 1.907194550872712,
+ "grad_norm": 0.6177689433097839,
+ "learning_rate": 7.258248009101252e-05,
+ "loss": 0.5242,
+ "mean_token_accuracy": 0.8907949879765511,
+ "num_tokens": 526387.0,
+ "step": 560
+ },
+ {
+ "epoch": 1.924223073648361,
+ "grad_norm": 0.6327561140060425,
+ "learning_rate": 7.14448236632537e-05,
+ "loss": 0.4725,
+ "mean_token_accuracy": 0.9006670027971267,
+ "num_tokens": 531113.0,
+ "step": 565
+ },
+ {
+ "epoch": 1.9412515964240102,
+ "grad_norm": 0.6829894781112671,
+ "learning_rate": 7.030716723549489e-05,
+ "loss": 0.5255,
+ "mean_token_accuracy": 0.8897917374968529,
+ "num_tokens": 535963.0,
+ "step": 570
+ },
+ {
+ "epoch": 1.9582801191996593,
+ "grad_norm": 0.7764301896095276,
+ "learning_rate": 6.916951080773608e-05,
+ "loss": 0.5636,
+ "mean_token_accuracy": 0.8877105817198754,
+ "num_tokens": 540801.0,
+ "step": 575
+ },
+ {
+ "epoch": 1.9753086419753085,
+ "grad_norm": 0.7201740741729736,
+ "learning_rate": 6.803185437997726e-05,
+ "loss": 0.5279,
+ "mean_token_accuracy": 0.8954470381140709,
+ "num_tokens": 545507.0,
+ "step": 580
+ },
+ {
+ "epoch": 1.9923371647509578,
+ "grad_norm": 0.6038010716438293,
+ "learning_rate": 6.689419795221843e-05,
+ "loss": 0.505,
+ "mean_token_accuracy": 0.8970827981829643,
+ "num_tokens": 550257.0,
+ "step": 585
+ },
+ {
+ "epoch": 2.009365687526607,
+ "grad_norm": 0.5724640488624573,
+ "learning_rate": 6.575654152445962e-05,
+ "loss": 0.5361,
+ "mean_token_accuracy": 0.9015150561928749,
+ "num_tokens": 554990.0,
+ "step": 590
+ },
+ {
+ "epoch": 2.0263942103022563,
+ "grad_norm": 0.5974262952804565,
+ "learning_rate": 6.46188850967008e-05,
+ "loss": 0.3674,
+ "mean_token_accuracy": 0.922430993616581,
+ "num_tokens": 559672.0,
+ "step": 595
+ },
+ {
+ "epoch": 2.0434227330779056,
+ "grad_norm": 0.6744574904441833,
+ "learning_rate": 6.348122866894199e-05,
+ "loss": 0.3751,
+ "mean_token_accuracy": 0.9247258752584457,
+ "num_tokens": 564411.0,
+ "step": 600
+ }
+ ],
+ "logging_steps": 5,
+ "max_steps": 879,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 200,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 2.555721091318579e+16,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d77eaa0f69f97b2b9813f53e641e4a6232bfa34d
--- /dev/null
+++ b/checkpoint-600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
+size 5624
diff --git a/checkpoint-800/README.md b/checkpoint-800/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9633d8f0130799d996b640335cd6d3846c495f5b
--- /dev/null
+++ b/checkpoint-800/README.md
@@ -0,0 +1,209 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+
+
+
+
+## Model Details
+
+### Model Description
+
+
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+
+
+### Direct Use
+
+
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+
+
+[More Information Needed]
+
+### Recommendations
+
+
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+
+
+[More Information Needed]
+
+### Training Procedure
+
+
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed]
+
+#### Speeds, Sizes, Times [optional]
+
+
+
+[More Information Needed]
+
+## Evaluation
+
+
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+
+
+[More Information Needed]
+
+#### Factors
+
+
+
+[More Information Needed]
+
+#### Metrics
+
+
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+
+
+[More Information Needed]
+
+## Environmental Impact
+
+
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0
\ No newline at end of file
diff --git a/checkpoint-800/adapter_config.json b/checkpoint-800/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..45edbb77201d4198da4bf26b8a7258da2bca8d90
--- /dev/null
+++ b/checkpoint-800/adapter_config.json
@@ -0,0 +1,50 @@
+{
+ "alora_invocation_tokens": null,
+ "alpha_pattern": {},
+ "arrow_config": null,
+ "auto_mapping": null,
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+ "bias": "none",
+ "corda_config": null,
+ "ensure_weight_tying": false,
+ "eva_config": null,
+ "exclude_modules": null,
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 32,
+ "lora_bias": false,
+ "lora_dropout": 0.05,
+ "lora_ga_config": null,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "monteclora_config": null,
+ "peft_type": "LORA",
+ "peft_version": "0.20.0",
+ "qalora_group_size": 16,
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_proj",
+ "k_proj",
+ "down_proj",
+ "up_proj",
+ "gate_proj",
+ "o_proj"
+ ],
+ "target_parameters": null,
+ "task_type": "CAUSAL_LM",
+ "trainable_token_indices": null,
+ "use_bdlora": null,
+ "use_dora": false,
+ "use_qalora": false,
+ "use_rslora": false,
+ "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-800/adapter_model.safetensors b/checkpoint-800/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f55433fbe2130d66e78419e7beb8884fa4fe39a7
--- /dev/null
+++ b/checkpoint-800/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604e0297d18f2a6234febc7f5a1bd753c0ad23a1a5b02aefc9ba06deb502ac9d
+size 167832240
diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0fdf9925173cb90a1d7ef3acf8f11f8fbeaba595
--- /dev/null
+++ b/checkpoint-800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2091dee88dd86d212cf9d3247ab597eddbf81bd87cd1514b8e09eb6c9e4e04d
+size 85728276
diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..55749e7a57658495f1bb803ab15124dc0ad896ff
--- /dev/null
+++ b/checkpoint-800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99051acd34ec5b53d2d7f281dab4b9b826e579cc685b1c8c008e4b30c106485f
+size 14244
diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d5f2f02e06ab23f9d7d8ad3ba372f99cc0860116
--- /dev/null
+++ b/checkpoint-800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4225c4e9f1ab7f7ed353e670836f9ef1773c433469b40387b8cbe0244cf93748
+size 1064
diff --git a/checkpoint-800/special_tokens_map.json b/checkpoint-800/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fed0491bb0ae0c4f0752f54ffddf7d69269daed
--- /dev/null
+++ b/checkpoint-800/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+ "bos_token": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|im_end|>"
+}
diff --git a/checkpoint-800/tokenizer.json b/checkpoint-800/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b
--- /dev/null
+++ b/checkpoint-800/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
+size 17209403
diff --git a/checkpoint-800/tokenizer_config.json b/checkpoint-800/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1dbecde59340b33dcf97ef6087584a5a01208ab5
--- /dev/null
+++ b/checkpoint-800/tokenizer_config.json
@@ -0,0 +1,2072 @@
+{
+ "added_tokens_decoder": {
+ "128000": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128001": {
+ "content": "<|end_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128002": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128003": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128004": {
+ "content": "<|finetune_right_pad_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128005": {
+ "content": "<|reserved_special_token_2|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128006": {
+ "content": "<|start_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128007": {
+ "content": "<|end_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128008": {
+ "content": "<|eom_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128009": {
+ "content": "<|eot_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128010": {
+ "content": "<|python_tag|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128011": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128012": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128013": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128014": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128015": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128016": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128017": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128018": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128019": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128020": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128021": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128022": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128023": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128024": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128025": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128026": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128027": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128028": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128029": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128030": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128031": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128032": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128033": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128034": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128035": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128036": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128037": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128038": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128039": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128040": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128041": {
+ "content": "<|reserved_special_token_33|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128042": {
+ "content": "<|reserved_special_token_34|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128043": {
+ "content": "<|reserved_special_token_35|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128044": {
+ "content": "<|reserved_special_token_36|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128045": {
+ "content": "<|reserved_special_token_37|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128046": {
+ "content": "<|reserved_special_token_38|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128047": {
+ "content": "<|reserved_special_token_39|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128048": {
+ "content": "<|reserved_special_token_40|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128049": {
+ "content": "<|reserved_special_token_41|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128050": {
+ "content": "<|reserved_special_token_42|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128051": {
+ "content": "<|reserved_special_token_43|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128052": {
+ "content": "<|reserved_special_token_44|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128053": {
+ "content": "<|reserved_special_token_45|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128054": {
+ "content": "<|reserved_special_token_46|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128055": {
+ "content": "<|reserved_special_token_47|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128056": {
+ "content": "<|reserved_special_token_48|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128057": {
+ "content": "<|reserved_special_token_49|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128058": {
+ "content": "<|reserved_special_token_50|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128059": {
+ "content": "<|reserved_special_token_51|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128060": {
+ "content": "<|reserved_special_token_52|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128061": {
+ "content": "<|reserved_special_token_53|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128062": {
+ "content": "<|reserved_special_token_54|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128063": {
+ "content": "<|reserved_special_token_55|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128064": {
+ "content": "<|reserved_special_token_56|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128065": {
+ "content": "<|reserved_special_token_57|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128066": {
+ "content": "<|reserved_special_token_58|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128067": {
+ "content": "<|reserved_special_token_59|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128068": {
+ "content": "<|reserved_special_token_60|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128069": {
+ "content": "<|reserved_special_token_61|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128070": {
+ "content": "<|reserved_special_token_62|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128071": {
+ "content": "<|reserved_special_token_63|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128072": {
+ "content": "<|reserved_special_token_64|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128073": {
+ "content": "<|reserved_special_token_65|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128074": {
+ "content": "<|reserved_special_token_66|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128075": {
+ "content": "<|reserved_special_token_67|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128076": {
+ "content": "<|reserved_special_token_68|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128077": {
+ "content": "<|reserved_special_token_69|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128078": {
+ "content": "<|reserved_special_token_70|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128079": {
+ "content": "<|reserved_special_token_71|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128080": {
+ "content": "<|reserved_special_token_72|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128081": {
+ "content": "<|reserved_special_token_73|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128082": {
+ "content": "<|reserved_special_token_74|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128083": {
+ "content": "<|reserved_special_token_75|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128084": {
+ "content": "<|reserved_special_token_76|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128085": {
+ "content": "<|reserved_special_token_77|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128086": {
+ "content": "<|reserved_special_token_78|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128087": {
+ "content": "<|reserved_special_token_79|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128088": {
+ "content": "<|reserved_special_token_80|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128089": {
+ "content": "<|reserved_special_token_81|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128090": {
+ "content": "<|reserved_special_token_82|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128091": {
+ "content": "<|reserved_special_token_83|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128092": {
+ "content": "<|reserved_special_token_84|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128093": {
+ "content": "<|reserved_special_token_85|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128094": {
+ "content": "<|reserved_special_token_86|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128095": {
+ "content": "<|reserved_special_token_87|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128096": {
+ "content": "<|reserved_special_token_88|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128097": {
+ "content": "<|reserved_special_token_89|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128098": {
+ "content": "<|reserved_special_token_90|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128099": {
+ "content": "<|reserved_special_token_91|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128100": {
+ "content": "<|reserved_special_token_92|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128101": {
+ "content": "<|reserved_special_token_93|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128102": {
+ "content": "<|reserved_special_token_94|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128103": {
+ "content": "<|reserved_special_token_95|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128104": {
+ "content": "<|reserved_special_token_96|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128105": {
+ "content": "<|reserved_special_token_97|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128106": {
+ "content": "<|reserved_special_token_98|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128107": {
+ "content": "<|reserved_special_token_99|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128108": {
+ "content": "<|reserved_special_token_100|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128109": {
+ "content": "<|reserved_special_token_101|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128110": {
+ "content": "<|reserved_special_token_102|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128111": {
+ "content": "<|reserved_special_token_103|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128112": {
+ "content": "<|reserved_special_token_104|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128113": {
+ "content": "<|reserved_special_token_105|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128114": {
+ "content": "<|reserved_special_token_106|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128115": {
+ "content": "<|reserved_special_token_107|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128116": {
+ "content": "<|reserved_special_token_108|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128117": {
+ "content": "<|reserved_special_token_109|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128118": {
+ "content": "<|reserved_special_token_110|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128119": {
+ "content": "<|reserved_special_token_111|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128120": {
+ "content": "<|reserved_special_token_112|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128121": {
+ "content": "<|reserved_special_token_113|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128122": {
+ "content": "<|reserved_special_token_114|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128123": {
+ "content": "<|reserved_special_token_115|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128124": {
+ "content": "<|reserved_special_token_116|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128125": {
+ "content": "<|reserved_special_token_117|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128126": {
+ "content": "<|reserved_special_token_118|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128127": {
+ "content": "<|reserved_special_token_119|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128128": {
+ "content": "<|reserved_special_token_120|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128129": {
+ "content": "<|reserved_special_token_121|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128130": {
+ "content": "<|reserved_special_token_122|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128131": {
+ "content": "<|reserved_special_token_123|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128132": {
+ "content": "<|reserved_special_token_124|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128133": {
+ "content": "<|reserved_special_token_125|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128134": {
+ "content": "<|reserved_special_token_126|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128135": {
+ "content": "<|reserved_special_token_127|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128136": {
+ "content": "<|reserved_special_token_128|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128137": {
+ "content": "<|reserved_special_token_129|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128138": {
+ "content": "<|reserved_special_token_130|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128139": {
+ "content": "<|reserved_special_token_131|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128140": {
+ "content": "<|reserved_special_token_132|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128141": {
+ "content": "<|reserved_special_token_133|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128142": {
+ "content": "<|reserved_special_token_134|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128143": {
+ "content": "<|reserved_special_token_135|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128144": {
+ "content": "<|reserved_special_token_136|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128145": {
+ "content": "<|reserved_special_token_137|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128146": {
+ "content": "<|reserved_special_token_138|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128147": {
+ "content": "<|reserved_special_token_139|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128148": {
+ "content": "<|reserved_special_token_140|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128149": {
+ "content": "<|reserved_special_token_141|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128150": {
+ "content": "<|reserved_special_token_142|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128151": {
+ "content": "<|reserved_special_token_143|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128152": {
+ "content": "<|reserved_special_token_144|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128153": {
+ "content": "<|reserved_special_token_145|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128154": {
+ "content": "<|reserved_special_token_146|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128155": {
+ "content": "<|reserved_special_token_147|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128156": {
+ "content": "<|reserved_special_token_148|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128157": {
+ "content": "<|reserved_special_token_149|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128158": {
+ "content": "<|reserved_special_token_150|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128159": {
+ "content": "<|reserved_special_token_151|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128160": {
+ "content": "<|reserved_special_token_152|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128161": {
+ "content": "<|reserved_special_token_153|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128162": {
+ "content": "<|reserved_special_token_154|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128163": {
+ "content": "<|reserved_special_token_155|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128164": {
+ "content": "<|reserved_special_token_156|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128165": {
+ "content": "<|reserved_special_token_157|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128166": {
+ "content": "<|reserved_special_token_158|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128167": {
+ "content": "<|reserved_special_token_159|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128168": {
+ "content": "<|reserved_special_token_160|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128169": {
+ "content": "<|reserved_special_token_161|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128170": {
+ "content": "<|reserved_special_token_162|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128171": {
+ "content": "<|reserved_special_token_163|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128172": {
+ "content": "<|reserved_special_token_164|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128173": {
+ "content": "<|reserved_special_token_165|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128174": {
+ "content": "<|reserved_special_token_166|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128175": {
+ "content": "<|reserved_special_token_167|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128176": {
+ "content": "<|reserved_special_token_168|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128177": {
+ "content": "<|reserved_special_token_169|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128178": {
+ "content": "<|reserved_special_token_170|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128179": {
+ "content": "<|reserved_special_token_171|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128180": {
+ "content": "<|reserved_special_token_172|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128181": {
+ "content": "<|reserved_special_token_173|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128182": {
+ "content": "<|reserved_special_token_174|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128183": {
+ "content": "<|reserved_special_token_175|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128184": {
+ "content": "<|reserved_special_token_176|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128185": {
+ "content": "<|reserved_special_token_177|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128186": {
+ "content": "<|reserved_special_token_178|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128187": {
+ "content": "<|reserved_special_token_179|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128188": {
+ "content": "<|reserved_special_token_180|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128189": {
+ "content": "<|reserved_special_token_181|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128190": {
+ "content": "<|reserved_special_token_182|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128191": {
+ "content": "<|reserved_special_token_183|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128192": {
+ "content": "<|reserved_special_token_184|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128193": {
+ "content": "<|reserved_special_token_185|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128194": {
+ "content": "<|reserved_special_token_186|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128195": {
+ "content": "<|reserved_special_token_187|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128196": {
+ "content": "<|reserved_special_token_188|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128197": {
+ "content": "<|reserved_special_token_189|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128198": {
+ "content": "<|reserved_special_token_190|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128199": {
+ "content": "<|reserved_special_token_191|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128200": {
+ "content": "<|reserved_special_token_192|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128201": {
+ "content": "<|reserved_special_token_193|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128202": {
+ "content": "<|reserved_special_token_194|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128203": {
+ "content": "<|reserved_special_token_195|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128204": {
+ "content": "<|reserved_special_token_196|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128205": {
+ "content": "<|reserved_special_token_197|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128206": {
+ "content": "<|reserved_special_token_198|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128207": {
+ "content": "<|reserved_special_token_199|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128208": {
+ "content": "<|reserved_special_token_200|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128209": {
+ "content": "<|reserved_special_token_201|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128210": {
+ "content": "<|reserved_special_token_202|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128211": {
+ "content": "<|reserved_special_token_203|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128212": {
+ "content": "<|reserved_special_token_204|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128213": {
+ "content": "<|reserved_special_token_205|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128214": {
+ "content": "<|reserved_special_token_206|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128215": {
+ "content": "<|reserved_special_token_207|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128216": {
+ "content": "<|reserved_special_token_208|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128217": {
+ "content": "<|reserved_special_token_209|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128218": {
+ "content": "<|reserved_special_token_210|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128219": {
+ "content": "<|reserved_special_token_211|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128220": {
+ "content": "<|reserved_special_token_212|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128221": {
+ "content": "<|reserved_special_token_213|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128222": {
+ "content": "<|reserved_special_token_214|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128223": {
+ "content": "<|reserved_special_token_215|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128224": {
+ "content": "<|reserved_special_token_216|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128225": {
+ "content": "<|reserved_special_token_217|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128226": {
+ "content": "<|reserved_special_token_218|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128227": {
+ "content": "<|reserved_special_token_219|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128228": {
+ "content": "<|reserved_special_token_220|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128229": {
+ "content": "<|reserved_special_token_221|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128230": {
+ "content": "<|reserved_special_token_222|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128231": {
+ "content": "<|reserved_special_token_223|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128232": {
+ "content": "<|reserved_special_token_224|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128233": {
+ "content": "<|reserved_special_token_225|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128234": {
+ "content": "<|reserved_special_token_226|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128235": {
+ "content": "<|reserved_special_token_227|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128236": {
+ "content": "<|reserved_special_token_228|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128237": {
+ "content": "<|reserved_special_token_229|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128238": {
+ "content": "<|reserved_special_token_230|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128239": {
+ "content": "<|reserved_special_token_231|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128240": {
+ "content": "<|reserved_special_token_232|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128241": {
+ "content": "<|reserved_special_token_233|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128242": {
+ "content": "<|reserved_special_token_234|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128243": {
+ "content": "<|reserved_special_token_235|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128244": {
+ "content": "<|reserved_special_token_236|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128245": {
+ "content": "<|reserved_special_token_237|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128246": {
+ "content": "<|reserved_special_token_238|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128247": {
+ "content": "<|reserved_special_token_239|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128248": {
+ "content": "<|reserved_special_token_240|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128249": {
+ "content": "<|reserved_special_token_241|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128250": {
+ "content": "<|reserved_special_token_242|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128251": {
+ "content": "<|reserved_special_token_243|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128252": {
+ "content": "<|reserved_special_token_244|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128253": {
+ "content": "<|reserved_special_token_245|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128254": {
+ "content": "<|reserved_special_token_246|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128255": {
+ "content": "<|reserved_special_token_247|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|begin_of_text|>",
+ "chat_template": [
+ {
+ "name": "default",
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+ },
+ {
+ "name": "tool_use",
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" \" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within XML tags as follows:\n\" }}\n{{- \"\n\" }}\n{{- '{\"name\": , \"arguments\": }\n' }}\n{{- '<|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- else %}\n {{- '\n' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+ }
+ ],
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|im_end|>",
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 131072,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..faeab3b6106d3dbbecfaca8b19929608ba76a436
--- /dev/null
+++ b/checkpoint-800/trainer_state.json
@@ -0,0 +1,1473 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.724563644103874,
+ "eval_steps": 500,
+ "global_step": 800,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.017028522775649212,
+ "grad_norm": 6.522716999053955,
+ "learning_rate": 0.0001988623435722412,
+ "loss": 2.7211,
+ "mean_token_accuracy": 0.5789041496813297,
+ "num_tokens": 4727.0,
+ "step": 5
+ },
+ {
+ "epoch": 0.034057045551298425,
+ "grad_norm": 1.0070050954818726,
+ "learning_rate": 0.00019772468714448238,
+ "loss": 0.9998,
+ "mean_token_accuracy": 0.8499793156981468,
+ "num_tokens": 9471.0,
+ "step": 10
+ },
+ {
+ "epoch": 0.05108556832694764,
+ "grad_norm": 0.7373425960540771,
+ "learning_rate": 0.00019658703071672356,
+ "loss": 0.8303,
+ "mean_token_accuracy": 0.8681916877627373,
+ "num_tokens": 14013.0,
+ "step": 15
+ },
+ {
+ "epoch": 0.06811409110259685,
+ "grad_norm": 0.8468236327171326,
+ "learning_rate": 0.00019544937428896475,
+ "loss": 0.8404,
+ "mean_token_accuracy": 0.8622620105743408,
+ "num_tokens": 18725.0,
+ "step": 20
+ },
+ {
+ "epoch": 0.08514261387824607,
+ "grad_norm": 0.8178804516792297,
+ "learning_rate": 0.00019431171786120593,
+ "loss": 0.9073,
+ "mean_token_accuracy": 0.8524447843432427,
+ "num_tokens": 23497.0,
+ "step": 25
+ },
+ {
+ "epoch": 0.10217113665389528,
+ "grad_norm": 0.890177309513092,
+ "learning_rate": 0.00019317406143344712,
+ "loss": 0.8029,
+ "mean_token_accuracy": 0.8642359614372254,
+ "num_tokens": 28192.0,
+ "step": 30
+ },
+ {
+ "epoch": 0.11919965942954448,
+ "grad_norm": 1.0545469522476196,
+ "learning_rate": 0.0001920364050056883,
+ "loss": 0.7458,
+ "mean_token_accuracy": 0.8732351213693619,
+ "num_tokens": 32805.0,
+ "step": 35
+ },
+ {
+ "epoch": 0.1362281822051937,
+ "grad_norm": 1.0384492874145508,
+ "learning_rate": 0.00019089874857792946,
+ "loss": 0.9235,
+ "mean_token_accuracy": 0.8408558666706085,
+ "num_tokens": 37714.0,
+ "step": 40
+ },
+ {
+ "epoch": 0.1532567049808429,
+ "grad_norm": 0.6860374808311462,
+ "learning_rate": 0.00018976109215017067,
+ "loss": 0.7623,
+ "mean_token_accuracy": 0.8656536340713501,
+ "num_tokens": 42429.0,
+ "step": 45
+ },
+ {
+ "epoch": 0.17028522775649213,
+ "grad_norm": 0.7284501791000366,
+ "learning_rate": 0.00018862343572241183,
+ "loss": 0.7588,
+ "mean_token_accuracy": 0.8688850715756417,
+ "num_tokens": 47099.0,
+ "step": 50
+ },
+ {
+ "epoch": 0.18731375053214133,
+ "grad_norm": 0.8899862170219421,
+ "learning_rate": 0.00018748577929465302,
+ "loss": 0.7065,
+ "mean_token_accuracy": 0.8717748820781708,
+ "num_tokens": 51795.0,
+ "step": 55
+ },
+ {
+ "epoch": 0.20434227330779056,
+ "grad_norm": 0.5350505709648132,
+ "learning_rate": 0.0001863481228668942,
+ "loss": 0.6696,
+ "mean_token_accuracy": 0.8851396456360817,
+ "num_tokens": 56369.0,
+ "step": 60
+ },
+ {
+ "epoch": 0.22137079608343976,
+ "grad_norm": 0.6087013483047485,
+ "learning_rate": 0.0001852104664391354,
+ "loss": 0.7204,
+ "mean_token_accuracy": 0.8682332798838616,
+ "num_tokens": 61018.0,
+ "step": 65
+ },
+ {
+ "epoch": 0.23839931885908897,
+ "grad_norm": 0.7879019379615784,
+ "learning_rate": 0.00018407281001137657,
+ "loss": 0.7692,
+ "mean_token_accuracy": 0.8653983056545258,
+ "num_tokens": 65741.0,
+ "step": 70
+ },
+ {
+ "epoch": 0.2554278416347382,
+ "grad_norm": 0.6546444296836853,
+ "learning_rate": 0.00018293515358361776,
+ "loss": 0.7119,
+ "mean_token_accuracy": 0.8726310178637504,
+ "num_tokens": 70425.0,
+ "step": 75
+ },
+ {
+ "epoch": 0.2724563644103874,
+ "grad_norm": 0.770902156829834,
+ "learning_rate": 0.00018179749715585894,
+ "loss": 0.7035,
+ "mean_token_accuracy": 0.8711811751127243,
+ "num_tokens": 75101.0,
+ "step": 80
+ },
+ {
+ "epoch": 0.2894848871860366,
+ "grad_norm": 0.8873187899589539,
+ "learning_rate": 0.00018065984072810013,
+ "loss": 0.7419,
+ "mean_token_accuracy": 0.8616803497076034,
+ "num_tokens": 79888.0,
+ "step": 85
+ },
+ {
+ "epoch": 0.3065134099616858,
+ "grad_norm": 0.7061370015144348,
+ "learning_rate": 0.0001795221843003413,
+ "loss": 0.66,
+ "mean_token_accuracy": 0.8744896531105042,
+ "num_tokens": 84562.0,
+ "step": 90
+ },
+ {
+ "epoch": 0.32354193273733506,
+ "grad_norm": 0.8232033252716064,
+ "learning_rate": 0.0001783845278725825,
+ "loss": 0.7403,
+ "mean_token_accuracy": 0.8659066379070282,
+ "num_tokens": 89238.0,
+ "step": 95
+ },
+ {
+ "epoch": 0.34057045551298426,
+ "grad_norm": 0.7313310503959656,
+ "learning_rate": 0.00017724687144482368,
+ "loss": 0.7157,
+ "mean_token_accuracy": 0.8661555901169777,
+ "num_tokens": 93987.0,
+ "step": 100
+ },
+ {
+ "epoch": 0.35759897828863346,
+ "grad_norm": 0.7119390964508057,
+ "learning_rate": 0.00017610921501706487,
+ "loss": 0.7016,
+ "mean_token_accuracy": 0.8678551658987999,
+ "num_tokens": 98722.0,
+ "step": 105
+ },
+ {
+ "epoch": 0.37462750106428266,
+ "grad_norm": 0.7126006484031677,
+ "learning_rate": 0.00017497155858930602,
+ "loss": 0.7009,
+ "mean_token_accuracy": 0.867291408777237,
+ "num_tokens": 103439.0,
+ "step": 110
+ },
+ {
+ "epoch": 0.39165602383993187,
+ "grad_norm": 0.6158230304718018,
+ "learning_rate": 0.00017383390216154724,
+ "loss": 0.7236,
+ "mean_token_accuracy": 0.8636128515005111,
+ "num_tokens": 108209.0,
+ "step": 115
+ },
+ {
+ "epoch": 0.4086845466155811,
+ "grad_norm": 0.6498322486877441,
+ "learning_rate": 0.0001726962457337884,
+ "loss": 0.6813,
+ "mean_token_accuracy": 0.8757071048021317,
+ "num_tokens": 112855.0,
+ "step": 120
+ },
+ {
+ "epoch": 0.4257130693912303,
+ "grad_norm": 0.6594287157058716,
+ "learning_rate": 0.0001715585893060296,
+ "loss": 0.7062,
+ "mean_token_accuracy": 0.8650311172008515,
+ "num_tokens": 117653.0,
+ "step": 125
+ },
+ {
+ "epoch": 0.4427415921668795,
+ "grad_norm": 0.7375237941741943,
+ "learning_rate": 0.00017042093287827076,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8733970731496811,
+ "num_tokens": 122397.0,
+ "step": 130
+ },
+ {
+ "epoch": 0.45977011494252873,
+ "grad_norm": 0.5958442687988281,
+ "learning_rate": 0.00016928327645051198,
+ "loss": 0.691,
+ "mean_token_accuracy": 0.8681387722492218,
+ "num_tokens": 127136.0,
+ "step": 135
+ },
+ {
+ "epoch": 0.47679863771817793,
+ "grad_norm": 0.7407785654067993,
+ "learning_rate": 0.00016814562002275313,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8752307429909706,
+ "num_tokens": 131833.0,
+ "step": 140
+ },
+ {
+ "epoch": 0.49382716049382713,
+ "grad_norm": 0.8190199732780457,
+ "learning_rate": 0.00016700796359499432,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8762851104140281,
+ "num_tokens": 136441.0,
+ "step": 145
+ },
+ {
+ "epoch": 0.5108556832694764,
+ "grad_norm": 0.7571837306022644,
+ "learning_rate": 0.0001658703071672355,
+ "loss": 0.673,
+ "mean_token_accuracy": 0.8691665843129158,
+ "num_tokens": 141186.0,
+ "step": 150
+ },
+ {
+ "epoch": 0.5278842060451255,
+ "grad_norm": 0.6653426885604858,
+ "learning_rate": 0.0001647326507394767,
+ "loss": 0.7126,
+ "mean_token_accuracy": 0.8647830635309219,
+ "num_tokens": 145971.0,
+ "step": 155
+ },
+ {
+ "epoch": 0.5449127288207748,
+ "grad_norm": 0.7333567142486572,
+ "learning_rate": 0.00016359499431171787,
+ "loss": 0.6287,
+ "mean_token_accuracy": 0.878324082493782,
+ "num_tokens": 150669.0,
+ "step": 160
+ },
+ {
+ "epoch": 0.561941251596424,
+ "grad_norm": 0.8214460015296936,
+ "learning_rate": 0.00016245733788395906,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8729922890663147,
+ "num_tokens": 155374.0,
+ "step": 165
+ },
+ {
+ "epoch": 0.5789697743720732,
+ "grad_norm": 0.6251844167709351,
+ "learning_rate": 0.00016131968145620024,
+ "loss": 0.6556,
+ "mean_token_accuracy": 0.8770609870553017,
+ "num_tokens": 160068.0,
+ "step": 170
+ },
+ {
+ "epoch": 0.5959982971477225,
+ "grad_norm": 0.804166853427887,
+ "learning_rate": 0.00016018202502844143,
+ "loss": 0.6366,
+ "mean_token_accuracy": 0.8760894432663917,
+ "num_tokens": 164696.0,
+ "step": 175
+ },
+ {
+ "epoch": 0.6130268199233716,
+ "grad_norm": 0.7013877034187317,
+ "learning_rate": 0.0001590443686006826,
+ "loss": 0.6328,
+ "mean_token_accuracy": 0.8779815405607223,
+ "num_tokens": 169356.0,
+ "step": 180
+ },
+ {
+ "epoch": 0.6300553426990209,
+ "grad_norm": 1.0623070001602173,
+ "learning_rate": 0.0001579067121729238,
+ "loss": 0.6734,
+ "mean_token_accuracy": 0.8710577815771103,
+ "num_tokens": 174041.0,
+ "step": 185
+ },
+ {
+ "epoch": 0.6470838654746701,
+ "grad_norm": 0.7858535647392273,
+ "learning_rate": 0.00015676905574516496,
+ "loss": 0.6775,
+ "mean_token_accuracy": 0.8692880481481552,
+ "num_tokens": 178858.0,
+ "step": 190
+ },
+ {
+ "epoch": 0.6641123882503193,
+ "grad_norm": 0.8943309187889099,
+ "learning_rate": 0.00015563139931740617,
+ "loss": 0.6874,
+ "mean_token_accuracy": 0.868885512650013,
+ "num_tokens": 183669.0,
+ "step": 195
+ },
+ {
+ "epoch": 0.6811409110259685,
+ "grad_norm": 0.5898745656013489,
+ "learning_rate": 0.00015449374288964733,
+ "loss": 0.6907,
+ "mean_token_accuracy": 0.8661940798163414,
+ "num_tokens": 188473.0,
+ "step": 200
+ },
+ {
+ "epoch": 0.6981694338016177,
+ "grad_norm": 0.6333857774734497,
+ "learning_rate": 0.00015335608646188854,
+ "loss": 0.6129,
+ "mean_token_accuracy": 0.8817986205220223,
+ "num_tokens": 193171.0,
+ "step": 205
+ },
+ {
+ "epoch": 0.7151979565772669,
+ "grad_norm": 0.5913947820663452,
+ "learning_rate": 0.0001522184300341297,
+ "loss": 0.5896,
+ "mean_token_accuracy": 0.8822762459516525,
+ "num_tokens": 197817.0,
+ "step": 210
+ },
+ {
+ "epoch": 0.7322264793529162,
+ "grad_norm": 0.6990242004394531,
+ "learning_rate": 0.00015108077360637088,
+ "loss": 0.6512,
+ "mean_token_accuracy": 0.8739180400967598,
+ "num_tokens": 202556.0,
+ "step": 215
+ },
+ {
+ "epoch": 0.7492550021285653,
+ "grad_norm": 0.6869048476219177,
+ "learning_rate": 0.00014994311717861207,
+ "loss": 0.7025,
+ "mean_token_accuracy": 0.8662877783179284,
+ "num_tokens": 207294.0,
+ "step": 220
+ },
+ {
+ "epoch": 0.7662835249042146,
+ "grad_norm": 0.5135166049003601,
+ "learning_rate": 0.00014880546075085325,
+ "loss": 0.6382,
+ "mean_token_accuracy": 0.8849207311868668,
+ "num_tokens": 211927.0,
+ "step": 225
+ },
+ {
+ "epoch": 0.7833120476798637,
+ "grad_norm": 0.6304216980934143,
+ "learning_rate": 0.00014766780432309444,
+ "loss": 0.6834,
+ "mean_token_accuracy": 0.8688049465417862,
+ "num_tokens": 216626.0,
+ "step": 230
+ },
+ {
+ "epoch": 0.800340570455513,
+ "grad_norm": 0.6879922151565552,
+ "learning_rate": 0.00014653014789533562,
+ "loss": 0.6902,
+ "mean_token_accuracy": 0.8655798360705376,
+ "num_tokens": 221432.0,
+ "step": 235
+ },
+ {
+ "epoch": 0.8173690932311622,
+ "grad_norm": 0.6433548331260681,
+ "learning_rate": 0.0001453924914675768,
+ "loss": 0.6129,
+ "mean_token_accuracy": 0.8795880794525146,
+ "num_tokens": 226022.0,
+ "step": 240
+ },
+ {
+ "epoch": 0.8343976160068114,
+ "grad_norm": 0.7876724600791931,
+ "learning_rate": 0.000144254835039818,
+ "loss": 0.6441,
+ "mean_token_accuracy": 0.8729524433612823,
+ "num_tokens": 230692.0,
+ "step": 245
+ },
+ {
+ "epoch": 0.8514261387824607,
+ "grad_norm": 0.6494749188423157,
+ "learning_rate": 0.00014311717861205915,
+ "loss": 0.7033,
+ "mean_token_accuracy": 0.8632469072937965,
+ "num_tokens": 235400.0,
+ "step": 250
+ },
+ {
+ "epoch": 0.8684546615581098,
+ "grad_norm": 0.6332300305366516,
+ "learning_rate": 0.00014197952218430036,
+ "loss": 0.5947,
+ "mean_token_accuracy": 0.8860528379678726,
+ "num_tokens": 239997.0,
+ "step": 255
+ },
+ {
+ "epoch": 0.885483184333759,
+ "grad_norm": 0.7144895195960999,
+ "learning_rate": 0.00014084186575654152,
+ "loss": 0.649,
+ "mean_token_accuracy": 0.8745664536952973,
+ "num_tokens": 244704.0,
+ "step": 260
+ },
+ {
+ "epoch": 0.9025117071094083,
+ "grad_norm": 0.5460124015808105,
+ "learning_rate": 0.00013970420932878273,
+ "loss": 0.6622,
+ "mean_token_accuracy": 0.8692788198590279,
+ "num_tokens": 249428.0,
+ "step": 265
+ },
+ {
+ "epoch": 0.9195402298850575,
+ "grad_norm": 0.65619295835495,
+ "learning_rate": 0.0001385665529010239,
+ "loss": 0.657,
+ "mean_token_accuracy": 0.8737826406955719,
+ "num_tokens": 254150.0,
+ "step": 270
+ },
+ {
+ "epoch": 0.9365687526607067,
+ "grad_norm": 0.8474870324134827,
+ "learning_rate": 0.0001374288964732651,
+ "loss": 0.6607,
+ "mean_token_accuracy": 0.8756056800484657,
+ "num_tokens": 258826.0,
+ "step": 275
+ },
+ {
+ "epoch": 0.9535972754363559,
+ "grad_norm": 0.6054229736328125,
+ "learning_rate": 0.00013629124004550626,
+ "loss": 0.6526,
+ "mean_token_accuracy": 0.8718441724777222,
+ "num_tokens": 263524.0,
+ "step": 280
+ },
+ {
+ "epoch": 0.9706257982120051,
+ "grad_norm": 0.6568702459335327,
+ "learning_rate": 0.00013515358361774744,
+ "loss": 0.6174,
+ "mean_token_accuracy": 0.881709736585617,
+ "num_tokens": 268179.0,
+ "step": 285
+ },
+ {
+ "epoch": 0.9876543209876543,
+ "grad_norm": 0.7518045902252197,
+ "learning_rate": 0.00013401592718998863,
+ "loss": 0.5896,
+ "mean_token_accuracy": 0.885109031200409,
+ "num_tokens": 272803.0,
+ "step": 290
+ },
+ {
+ "epoch": 1.0046828437633035,
+ "grad_norm": 0.5392197370529175,
+ "learning_rate": 0.00013287827076222981,
+ "loss": 0.6753,
+ "mean_token_accuracy": 0.8788385137915611,
+ "num_tokens": 277527.0,
+ "step": 295
+ },
+ {
+ "epoch": 1.0217113665389528,
+ "grad_norm": 0.5845906734466553,
+ "learning_rate": 0.000131740614334471,
+ "loss": 0.5237,
+ "mean_token_accuracy": 0.8938747227191925,
+ "num_tokens": 282199.0,
+ "step": 300
+ },
+ {
+ "epoch": 1.038739889314602,
+ "grad_norm": 0.6392928957939148,
+ "learning_rate": 0.00013060295790671218,
+ "loss": 0.4973,
+ "mean_token_accuracy": 0.8982622623443604,
+ "num_tokens": 286951.0,
+ "step": 305
+ },
+ {
+ "epoch": 1.055768412090251,
+ "grad_norm": 0.5399300456047058,
+ "learning_rate": 0.00012946530147895337,
+ "loss": 0.5076,
+ "mean_token_accuracy": 0.9008002370595932,
+ "num_tokens": 291569.0,
+ "step": 310
+ },
+ {
+ "epoch": 1.0727969348659003,
+ "grad_norm": 0.6236026883125305,
+ "learning_rate": 0.00012832764505119455,
+ "loss": 0.5084,
+ "mean_token_accuracy": 0.8972577184438706,
+ "num_tokens": 296230.0,
+ "step": 315
+ },
+ {
+ "epoch": 1.0898254576415496,
+ "grad_norm": 0.7385813593864441,
+ "learning_rate": 0.0001271899886234357,
+ "loss": 0.5062,
+ "mean_token_accuracy": 0.8956585437059402,
+ "num_tokens": 301029.0,
+ "step": 320
+ },
+ {
+ "epoch": 1.1068539804171988,
+ "grad_norm": 0.7647150754928589,
+ "learning_rate": 0.00012605233219567692,
+ "loss": 0.5078,
+ "mean_token_accuracy": 0.8982979074120522,
+ "num_tokens": 305696.0,
+ "step": 325
+ },
+ {
+ "epoch": 1.123882503192848,
+ "grad_norm": 0.6433872580528259,
+ "learning_rate": 0.00012491467576791808,
+ "loss": 0.5215,
+ "mean_token_accuracy": 0.8974734947085381,
+ "num_tokens": 310343.0,
+ "step": 330
+ },
+ {
+ "epoch": 1.1409110259684971,
+ "grad_norm": 0.6470033526420593,
+ "learning_rate": 0.0001237770193401593,
+ "loss": 0.5261,
+ "mean_token_accuracy": 0.8938129872083664,
+ "num_tokens": 315097.0,
+ "step": 335
+ },
+ {
+ "epoch": 1.1579395487441464,
+ "grad_norm": 0.6738846302032471,
+ "learning_rate": 0.00012263936291240045,
+ "loss": 0.5277,
+ "mean_token_accuracy": 0.8924461513757705,
+ "num_tokens": 319861.0,
+ "step": 340
+ },
+ {
+ "epoch": 1.1749680715197957,
+ "grad_norm": 0.6639145016670227,
+ "learning_rate": 0.00012150170648464165,
+ "loss": 0.5127,
+ "mean_token_accuracy": 0.8926685571670532,
+ "num_tokens": 324544.0,
+ "step": 345
+ },
+ {
+ "epoch": 1.191996594295445,
+ "grad_norm": 0.7034420371055603,
+ "learning_rate": 0.00012036405005688282,
+ "loss": 0.51,
+ "mean_token_accuracy": 0.8971043467521668,
+ "num_tokens": 329302.0,
+ "step": 350
+ },
+ {
+ "epoch": 1.2090251170710942,
+ "grad_norm": 0.6675500273704529,
+ "learning_rate": 0.000119226393629124,
+ "loss": 0.5738,
+ "mean_token_accuracy": 0.8855719327926636,
+ "num_tokens": 334103.0,
+ "step": 355
+ },
+ {
+ "epoch": 1.2260536398467432,
+ "grad_norm": 0.6019395589828491,
+ "learning_rate": 0.00011808873720136519,
+ "loss": 0.476,
+ "mean_token_accuracy": 0.8989460453391075,
+ "num_tokens": 338666.0,
+ "step": 360
+ },
+ {
+ "epoch": 1.2430821626223925,
+ "grad_norm": 0.6599250435829163,
+ "learning_rate": 0.00011695108077360638,
+ "loss": 0.5178,
+ "mean_token_accuracy": 0.8887226998805999,
+ "num_tokens": 343333.0,
+ "step": 365
+ },
+ {
+ "epoch": 1.2601106853980417,
+ "grad_norm": 0.7334213852882385,
+ "learning_rate": 0.00011581342434584756,
+ "loss": 0.5378,
+ "mean_token_accuracy": 0.8895460113883018,
+ "num_tokens": 348092.0,
+ "step": 370
+ },
+ {
+ "epoch": 1.277139208173691,
+ "grad_norm": 0.7423357963562012,
+ "learning_rate": 0.00011467576791808873,
+ "loss": 0.5012,
+ "mean_token_accuracy": 0.8994292929768563,
+ "num_tokens": 352661.0,
+ "step": 375
+ },
+ {
+ "epoch": 1.29416773094934,
+ "grad_norm": 0.857515811920166,
+ "learning_rate": 0.00011353811149032993,
+ "loss": 0.507,
+ "mean_token_accuracy": 0.8979884222149849,
+ "num_tokens": 357330.0,
+ "step": 380
+ },
+ {
+ "epoch": 1.3111962537249893,
+ "grad_norm": 0.5656803250312805,
+ "learning_rate": 0.0001124004550625711,
+ "loss": 0.5009,
+ "mean_token_accuracy": 0.8934224143624305,
+ "num_tokens": 362020.0,
+ "step": 385
+ },
+ {
+ "epoch": 1.3282247765006385,
+ "grad_norm": 0.6634964942932129,
+ "learning_rate": 0.00011126279863481229,
+ "loss": 0.5414,
+ "mean_token_accuracy": 0.8910330131649971,
+ "num_tokens": 366728.0,
+ "step": 390
+ },
+ {
+ "epoch": 1.3452532992762878,
+ "grad_norm": 0.7004157304763794,
+ "learning_rate": 0.00011012514220705347,
+ "loss": 0.4922,
+ "mean_token_accuracy": 0.8992783546447753,
+ "num_tokens": 371381.0,
+ "step": 395
+ },
+ {
+ "epoch": 1.362281822051937,
+ "grad_norm": 0.6225594282150269,
+ "learning_rate": 0.00010898748577929466,
+ "loss": 0.5084,
+ "mean_token_accuracy": 0.8956901535391808,
+ "num_tokens": 376043.0,
+ "step": 400
+ },
+ {
+ "epoch": 1.3793103448275863,
+ "grad_norm": 0.8019647598266602,
+ "learning_rate": 0.00010784982935153584,
+ "loss": 0.5303,
+ "mean_token_accuracy": 0.8940754950046539,
+ "num_tokens": 380714.0,
+ "step": 405
+ },
+ {
+ "epoch": 1.3963388676032356,
+ "grad_norm": 0.8314201831817627,
+ "learning_rate": 0.00010671217292377703,
+ "loss": 0.5249,
+ "mean_token_accuracy": 0.8924115225672722,
+ "num_tokens": 385498.0,
+ "step": 410
+ },
+ {
+ "epoch": 1.4133673903788846,
+ "grad_norm": 0.6691393256187439,
+ "learning_rate": 0.00010557451649601821,
+ "loss": 0.4817,
+ "mean_token_accuracy": 0.89882483035326,
+ "num_tokens": 390179.0,
+ "step": 415
+ },
+ {
+ "epoch": 1.4303959131545338,
+ "grad_norm": 0.8554338216781616,
+ "learning_rate": 0.00010443686006825938,
+ "loss": 0.5191,
+ "mean_token_accuracy": 0.8876234069466591,
+ "num_tokens": 394930.0,
+ "step": 420
+ },
+ {
+ "epoch": 1.447424435930183,
+ "grad_norm": 0.696018636226654,
+ "learning_rate": 0.00010329920364050057,
+ "loss": 0.5386,
+ "mean_token_accuracy": 0.891503955423832,
+ "num_tokens": 399685.0,
+ "step": 425
+ },
+ {
+ "epoch": 1.4644529587058321,
+ "grad_norm": 0.7389529943466187,
+ "learning_rate": 0.00010216154721274175,
+ "loss": 0.4949,
+ "mean_token_accuracy": 0.9004919424653053,
+ "num_tokens": 404300.0,
+ "step": 430
+ },
+ {
+ "epoch": 1.4814814814814814,
+ "grad_norm": 1.0227491855621338,
+ "learning_rate": 0.00010102389078498294,
+ "loss": 0.54,
+ "mean_token_accuracy": 0.8893611416220665,
+ "num_tokens": 409079.0,
+ "step": 435
+ },
+ {
+ "epoch": 1.4985100042571307,
+ "grad_norm": 0.6526888012886047,
+ "learning_rate": 9.988623435722412e-05,
+ "loss": 0.4917,
+ "mean_token_accuracy": 0.8958082437515259,
+ "num_tokens": 413758.0,
+ "step": 440
+ },
+ {
+ "epoch": 1.51553852703278,
+ "grad_norm": 0.5875766277313232,
+ "learning_rate": 9.874857792946531e-05,
+ "loss": 0.4991,
+ "mean_token_accuracy": 0.8971148490905761,
+ "num_tokens": 418502.0,
+ "step": 445
+ },
+ {
+ "epoch": 1.5325670498084292,
+ "grad_norm": 0.6892980337142944,
+ "learning_rate": 9.761092150170649e-05,
+ "loss": 0.4551,
+ "mean_token_accuracy": 0.9068983420729637,
+ "num_tokens": 423099.0,
+ "step": 450
+ },
+ {
+ "epoch": 1.5495955725840784,
+ "grad_norm": 0.6264586448669434,
+ "learning_rate": 9.647326507394768e-05,
+ "loss": 0.468,
+ "mean_token_accuracy": 0.9043048679828644,
+ "num_tokens": 427701.0,
+ "step": 455
+ },
+ {
+ "epoch": 1.5666240953597277,
+ "grad_norm": 0.5398015379905701,
+ "learning_rate": 9.533560864618886e-05,
+ "loss": 0.4877,
+ "mean_token_accuracy": 0.8986729174852371,
+ "num_tokens": 432430.0,
+ "step": 460
+ },
+ {
+ "epoch": 1.5836526181353767,
+ "grad_norm": 0.827769935131073,
+ "learning_rate": 9.419795221843003e-05,
+ "loss": 0.4951,
+ "mean_token_accuracy": 0.9012611672282219,
+ "num_tokens": 437078.0,
+ "step": 465
+ },
+ {
+ "epoch": 1.600681140911026,
+ "grad_norm": 0.6888080835342407,
+ "learning_rate": 9.306029579067122e-05,
+ "loss": 0.5108,
+ "mean_token_accuracy": 0.8976602256298065,
+ "num_tokens": 441734.0,
+ "step": 470
+ },
+ {
+ "epoch": 1.617709663686675,
+ "grad_norm": 0.837681233882904,
+ "learning_rate": 9.19226393629124e-05,
+ "loss": 0.5377,
+ "mean_token_accuracy": 0.8850761532783509,
+ "num_tokens": 446637.0,
+ "step": 475
+ },
+ {
+ "epoch": 1.6347381864623243,
+ "grad_norm": 0.7211363315582275,
+ "learning_rate": 9.078498293515359e-05,
+ "loss": 0.5001,
+ "mean_token_accuracy": 0.898733913898468,
+ "num_tokens": 451301.0,
+ "step": 480
+ },
+ {
+ "epoch": 1.6517667092379735,
+ "grad_norm": 0.6663438081741333,
+ "learning_rate": 8.964732650739477e-05,
+ "loss": 0.5144,
+ "mean_token_accuracy": 0.8976200923323632,
+ "num_tokens": 455965.0,
+ "step": 485
+ },
+ {
+ "epoch": 1.6687952320136228,
+ "grad_norm": 0.8935639262199402,
+ "learning_rate": 8.850967007963596e-05,
+ "loss": 0.5331,
+ "mean_token_accuracy": 0.8960411131381989,
+ "num_tokens": 460716.0,
+ "step": 490
+ },
+ {
+ "epoch": 1.685823754789272,
+ "grad_norm": 0.7235546708106995,
+ "learning_rate": 8.737201365187714e-05,
+ "loss": 0.4831,
+ "mean_token_accuracy": 0.8972082689404488,
+ "num_tokens": 465370.0,
+ "step": 495
+ },
+ {
+ "epoch": 1.7028522775649213,
+ "grad_norm": 0.774000346660614,
+ "learning_rate": 8.623435722411833e-05,
+ "loss": 0.5186,
+ "mean_token_accuracy": 0.8950631290674209,
+ "num_tokens": 470043.0,
+ "step": 500
+ },
+ {
+ "epoch": 1.7198808003405706,
+ "grad_norm": 0.5213722586631775,
+ "learning_rate": 8.509670079635951e-05,
+ "loss": 0.4567,
+ "mean_token_accuracy": 0.9016156733036041,
+ "num_tokens": 474573.0,
+ "step": 505
+ },
+ {
+ "epoch": 1.7369093231162198,
+ "grad_norm": 0.7278684377670288,
+ "learning_rate": 8.395904436860069e-05,
+ "loss": 0.5545,
+ "mean_token_accuracy": 0.8925162181258202,
+ "num_tokens": 479305.0,
+ "step": 510
+ },
+ {
+ "epoch": 1.7539378458918689,
+ "grad_norm": 0.7252481579780579,
+ "learning_rate": 8.282138794084187e-05,
+ "loss": 0.496,
+ "mean_token_accuracy": 0.8953201442956924,
+ "num_tokens": 484033.0,
+ "step": 515
+ },
+ {
+ "epoch": 1.770966368667518,
+ "grad_norm": 0.727513313293457,
+ "learning_rate": 8.168373151308306e-05,
+ "loss": 0.5033,
+ "mean_token_accuracy": 0.8998701125383377,
+ "num_tokens": 488727.0,
+ "step": 520
+ },
+ {
+ "epoch": 1.7879948914431671,
+ "grad_norm": 0.5375337600708008,
+ "learning_rate": 8.054607508532424e-05,
+ "loss": 0.4903,
+ "mean_token_accuracy": 0.8960629358887673,
+ "num_tokens": 493411.0,
+ "step": 525
+ },
+ {
+ "epoch": 1.8050234142188164,
+ "grad_norm": 0.5851954221725464,
+ "learning_rate": 7.940841865756543e-05,
+ "loss": 0.5139,
+ "mean_token_accuracy": 0.8972602248191833,
+ "num_tokens": 498098.0,
+ "step": 530
+ },
+ {
+ "epoch": 1.8220519369944657,
+ "grad_norm": 0.6942209005355835,
+ "learning_rate": 7.827076222980661e-05,
+ "loss": 0.4728,
+ "mean_token_accuracy": 0.9009919315576553,
+ "num_tokens": 502717.0,
+ "step": 535
+ },
+ {
+ "epoch": 1.839080459770115,
+ "grad_norm": 0.9342221021652222,
+ "learning_rate": 7.71331058020478e-05,
+ "loss": 0.5283,
+ "mean_token_accuracy": 0.8924958631396294,
+ "num_tokens": 507462.0,
+ "step": 540
+ },
+ {
+ "epoch": 1.8561089825457642,
+ "grad_norm": 0.7415278553962708,
+ "learning_rate": 7.599544937428897e-05,
+ "loss": 0.5394,
+ "mean_token_accuracy": 0.8913042590022087,
+ "num_tokens": 512202.0,
+ "step": 545
+ },
+ {
+ "epoch": 1.8731375053214134,
+ "grad_norm": 0.7223448157310486,
+ "learning_rate": 7.485779294653015e-05,
+ "loss": 0.5473,
+ "mean_token_accuracy": 0.8873603999614715,
+ "num_tokens": 517047.0,
+ "step": 550
+ },
+ {
+ "epoch": 1.8901660280970627,
+ "grad_norm": 0.6324387192726135,
+ "learning_rate": 7.372013651877134e-05,
+ "loss": 0.4986,
+ "mean_token_accuracy": 0.9018153563141823,
+ "num_tokens": 521653.0,
+ "step": 555
+ },
+ {
+ "epoch": 1.907194550872712,
+ "grad_norm": 0.6177689433097839,
+ "learning_rate": 7.258248009101252e-05,
+ "loss": 0.5242,
+ "mean_token_accuracy": 0.8907949879765511,
+ "num_tokens": 526387.0,
+ "step": 560
+ },
+ {
+ "epoch": 1.924223073648361,
+ "grad_norm": 0.6327561140060425,
+ "learning_rate": 7.14448236632537e-05,
+ "loss": 0.4725,
+ "mean_token_accuracy": 0.9006670027971267,
+ "num_tokens": 531113.0,
+ "step": 565
+ },
+ {
+ "epoch": 1.9412515964240102,
+ "grad_norm": 0.6829894781112671,
+ "learning_rate": 7.030716723549489e-05,
+ "loss": 0.5255,
+ "mean_token_accuracy": 0.8897917374968529,
+ "num_tokens": 535963.0,
+ "step": 570
+ },
+ {
+ "epoch": 1.9582801191996593,
+ "grad_norm": 0.7764301896095276,
+ "learning_rate": 6.916951080773608e-05,
+ "loss": 0.5636,
+ "mean_token_accuracy": 0.8877105817198754,
+ "num_tokens": 540801.0,
+ "step": 575
+ },
+ {
+ "epoch": 1.9753086419753085,
+ "grad_norm": 0.7201740741729736,
+ "learning_rate": 6.803185437997726e-05,
+ "loss": 0.5279,
+ "mean_token_accuracy": 0.8954470381140709,
+ "num_tokens": 545507.0,
+ "step": 580
+ },
+ {
+ "epoch": 1.9923371647509578,
+ "grad_norm": 0.6038010716438293,
+ "learning_rate": 6.689419795221843e-05,
+ "loss": 0.505,
+ "mean_token_accuracy": 0.8970827981829643,
+ "num_tokens": 550257.0,
+ "step": 585
+ },
+ {
+ "epoch": 2.009365687526607,
+ "grad_norm": 0.5724640488624573,
+ "learning_rate": 6.575654152445962e-05,
+ "loss": 0.5361,
+ "mean_token_accuracy": 0.9015150561928749,
+ "num_tokens": 554990.0,
+ "step": 590
+ },
+ {
+ "epoch": 2.0263942103022563,
+ "grad_norm": 0.5974262952804565,
+ "learning_rate": 6.46188850967008e-05,
+ "loss": 0.3674,
+ "mean_token_accuracy": 0.922430993616581,
+ "num_tokens": 559672.0,
+ "step": 595
+ },
+ {
+ "epoch": 2.0434227330779056,
+ "grad_norm": 0.6744574904441833,
+ "learning_rate": 6.348122866894199e-05,
+ "loss": 0.3751,
+ "mean_token_accuracy": 0.9247258752584457,
+ "num_tokens": 564411.0,
+ "step": 600
+ },
+ {
+ "epoch": 2.060451255853555,
+ "grad_norm": 0.7185547351837158,
+ "learning_rate": 6.234357224118317e-05,
+ "loss": 0.3416,
+ "mean_token_accuracy": 0.929543960094452,
+ "num_tokens": 569003.0,
+ "step": 605
+ },
+ {
+ "epoch": 2.077479778629204,
+ "grad_norm": 0.5838123559951782,
+ "learning_rate": 6.120591581342436e-05,
+ "loss": 0.3537,
+ "mean_token_accuracy": 0.930443874001503,
+ "num_tokens": 573739.0,
+ "step": 610
+ },
+ {
+ "epoch": 2.0945083014048533,
+ "grad_norm": 0.8568351864814758,
+ "learning_rate": 6.0068259385665536e-05,
+ "loss": 0.3784,
+ "mean_token_accuracy": 0.9205309540033341,
+ "num_tokens": 578528.0,
+ "step": 615
+ },
+ {
+ "epoch": 2.111536824180502,
+ "grad_norm": 0.5337037444114685,
+ "learning_rate": 5.8930602957906714e-05,
+ "loss": 0.3617,
+ "mean_token_accuracy": 0.9245797485113144,
+ "num_tokens": 583227.0,
+ "step": 620
+ },
+ {
+ "epoch": 2.1285653469561514,
+ "grad_norm": 0.5879887938499451,
+ "learning_rate": 5.77929465301479e-05,
+ "loss": 0.3707,
+ "mean_token_accuracy": 0.9202131152153015,
+ "num_tokens": 587936.0,
+ "step": 625
+ },
+ {
+ "epoch": 2.1455938697318007,
+ "grad_norm": 0.6099004149436951,
+ "learning_rate": 5.665529010238908e-05,
+ "loss": 0.3774,
+ "mean_token_accuracy": 0.9187414139509201,
+ "num_tokens": 592638.0,
+ "step": 630
+ },
+ {
+ "epoch": 2.16262239250745,
+ "grad_norm": 0.6386281251907349,
+ "learning_rate": 5.551763367463026e-05,
+ "loss": 0.3618,
+ "mean_token_accuracy": 0.9270586878061294,
+ "num_tokens": 597181.0,
+ "step": 635
+ },
+ {
+ "epoch": 2.179650915283099,
+ "grad_norm": 0.9021700024604797,
+ "learning_rate": 5.437997724687145e-05,
+ "loss": 0.3585,
+ "mean_token_accuracy": 0.9271015107631684,
+ "num_tokens": 601859.0,
+ "step": 640
+ },
+ {
+ "epoch": 2.1966794380587484,
+ "grad_norm": 0.881395697593689,
+ "learning_rate": 5.324232081911263e-05,
+ "loss": 0.3557,
+ "mean_token_accuracy": 0.9272178143262864,
+ "num_tokens": 606633.0,
+ "step": 645
+ },
+ {
+ "epoch": 2.2137079608343977,
+ "grad_norm": 0.8289951086044312,
+ "learning_rate": 5.210466439135382e-05,
+ "loss": 0.3761,
+ "mean_token_accuracy": 0.9222683504223823,
+ "num_tokens": 611341.0,
+ "step": 650
+ },
+ {
+ "epoch": 2.230736483610047,
+ "grad_norm": 0.7716552019119263,
+ "learning_rate": 5.0967007963594995e-05,
+ "loss": 0.3806,
+ "mean_token_accuracy": 0.9193105801939965,
+ "num_tokens": 616076.0,
+ "step": 655
+ },
+ {
+ "epoch": 2.247765006385696,
+ "grad_norm": 0.7260558605194092,
+ "learning_rate": 4.982935153583618e-05,
+ "loss": 0.3641,
+ "mean_token_accuracy": 0.9221750542521476,
+ "num_tokens": 620729.0,
+ "step": 660
+ },
+ {
+ "epoch": 2.264793529161345,
+ "grad_norm": 0.6313159465789795,
+ "learning_rate": 4.8691695108077365e-05,
+ "loss": 0.3923,
+ "mean_token_accuracy": 0.9229970827698708,
+ "num_tokens": 625451.0,
+ "step": 665
+ },
+ {
+ "epoch": 2.2818220519369943,
+ "grad_norm": 0.6566217541694641,
+ "learning_rate": 4.755403868031855e-05,
+ "loss": 0.3404,
+ "mean_token_accuracy": 0.9257871210575104,
+ "num_tokens": 630049.0,
+ "step": 670
+ },
+ {
+ "epoch": 2.2988505747126435,
+ "grad_norm": 0.8146483302116394,
+ "learning_rate": 4.641638225255973e-05,
+ "loss": 0.3499,
+ "mean_token_accuracy": 0.9254049748182297,
+ "num_tokens": 634646.0,
+ "step": 675
+ },
+ {
+ "epoch": 2.315879097488293,
+ "grad_norm": 0.8177068829536438,
+ "learning_rate": 4.527872582480091e-05,
+ "loss": 0.3662,
+ "mean_token_accuracy": 0.9220140025019645,
+ "num_tokens": 639328.0,
+ "step": 680
+ },
+ {
+ "epoch": 2.332907620263942,
+ "grad_norm": 0.7193973660469055,
+ "learning_rate": 4.41410693970421e-05,
+ "loss": 0.3861,
+ "mean_token_accuracy": 0.9194135531783104,
+ "num_tokens": 644122.0,
+ "step": 685
+ },
+ {
+ "epoch": 2.3499361430395913,
+ "grad_norm": 0.8300774693489075,
+ "learning_rate": 4.300341296928328e-05,
+ "loss": 0.3924,
+ "mean_token_accuracy": 0.9165543273091317,
+ "num_tokens": 648957.0,
+ "step": 690
+ },
+ {
+ "epoch": 2.3669646658152406,
+ "grad_norm": 0.6429705023765564,
+ "learning_rate": 4.186575654152446e-05,
+ "loss": 0.3749,
+ "mean_token_accuracy": 0.922352360188961,
+ "num_tokens": 653645.0,
+ "step": 695
+ },
+ {
+ "epoch": 2.38399318859089,
+ "grad_norm": 0.9316811561584473,
+ "learning_rate": 4.0728100113765646e-05,
+ "loss": 0.3731,
+ "mean_token_accuracy": 0.9198509395122528,
+ "num_tokens": 658472.0,
+ "step": 700
+ },
+ {
+ "epoch": 2.401021711366539,
+ "grad_norm": 0.6092661023139954,
+ "learning_rate": 3.959044368600683e-05,
+ "loss": 0.3614,
+ "mean_token_accuracy": 0.9218982830643654,
+ "num_tokens": 663118.0,
+ "step": 705
+ },
+ {
+ "epoch": 2.4180502341421883,
+ "grad_norm": 0.909447968006134,
+ "learning_rate": 3.8452787258248016e-05,
+ "loss": 0.407,
+ "mean_token_accuracy": 0.9137230664491653,
+ "num_tokens": 668024.0,
+ "step": 710
+ },
+ {
+ "epoch": 2.4350787569178376,
+ "grad_norm": 0.6452695727348328,
+ "learning_rate": 3.7315130830489194e-05,
+ "loss": 0.3642,
+ "mean_token_accuracy": 0.9242654070258141,
+ "num_tokens": 672593.0,
+ "step": 715
+ },
+ {
+ "epoch": 2.4521072796934864,
+ "grad_norm": 0.7429100275039673,
+ "learning_rate": 3.617747440273038e-05,
+ "loss": 0.3762,
+ "mean_token_accuracy": 0.9200442656874657,
+ "num_tokens": 677246.0,
+ "step": 720
+ },
+ {
+ "epoch": 2.4691358024691357,
+ "grad_norm": 0.6262103319168091,
+ "learning_rate": 3.5039817974971564e-05,
+ "loss": 0.3631,
+ "mean_token_accuracy": 0.9242240786552429,
+ "num_tokens": 681899.0,
+ "step": 725
+ },
+ {
+ "epoch": 2.486164325244785,
+ "grad_norm": 0.7170459032058716,
+ "learning_rate": 3.390216154721274e-05,
+ "loss": 0.3518,
+ "mean_token_accuracy": 0.9257205232977868,
+ "num_tokens": 686559.0,
+ "step": 730
+ },
+ {
+ "epoch": 2.503192848020434,
+ "grad_norm": 0.7899272441864014,
+ "learning_rate": 3.276450511945393e-05,
+ "loss": 0.3408,
+ "mean_token_accuracy": 0.927695432305336,
+ "num_tokens": 691193.0,
+ "step": 735
+ },
+ {
+ "epoch": 2.5202213707960834,
+ "grad_norm": 0.8176191449165344,
+ "learning_rate": 3.162684869169511e-05,
+ "loss": 0.3554,
+ "mean_token_accuracy": 0.9244274586439133,
+ "num_tokens": 695862.0,
+ "step": 740
+ },
+ {
+ "epoch": 2.5372498935717327,
+ "grad_norm": 0.9307223558425903,
+ "learning_rate": 3.0489192263936294e-05,
+ "loss": 0.3762,
+ "mean_token_accuracy": 0.9196016103029251,
+ "num_tokens": 700732.0,
+ "step": 745
+ },
+ {
+ "epoch": 2.554278416347382,
+ "grad_norm": 0.7519947290420532,
+ "learning_rate": 2.9351535836177476e-05,
+ "loss": 0.37,
+ "mean_token_accuracy": 0.9214758723974228,
+ "num_tokens": 705428.0,
+ "step": 750
+ },
+ {
+ "epoch": 2.571306939123031,
+ "grad_norm": 0.7623237371444702,
+ "learning_rate": 2.8213879408418657e-05,
+ "loss": 0.3496,
+ "mean_token_accuracy": 0.9245725467801094,
+ "num_tokens": 710035.0,
+ "step": 755
+ },
+ {
+ "epoch": 2.58833546189868,
+ "grad_norm": 0.6571420431137085,
+ "learning_rate": 2.7076222980659842e-05,
+ "loss": 0.3662,
+ "mean_token_accuracy": 0.9226716786623002,
+ "num_tokens": 714753.0,
+ "step": 760
+ },
+ {
+ "epoch": 2.6053639846743293,
+ "grad_norm": 0.6745423078536987,
+ "learning_rate": 2.5938566552901024e-05,
+ "loss": 0.3672,
+ "mean_token_accuracy": 0.9193284913897515,
+ "num_tokens": 719410.0,
+ "step": 765
+ },
+ {
+ "epoch": 2.6223925074499785,
+ "grad_norm": 0.9500595927238464,
+ "learning_rate": 2.480091012514221e-05,
+ "loss": 0.3729,
+ "mean_token_accuracy": 0.9209223091602325,
+ "num_tokens": 724210.0,
+ "step": 770
+ },
+ {
+ "epoch": 2.639421030225628,
+ "grad_norm": 0.6964495182037354,
+ "learning_rate": 2.366325369738339e-05,
+ "loss": 0.3505,
+ "mean_token_accuracy": 0.9281451672315597,
+ "num_tokens": 728969.0,
+ "step": 775
+ },
+ {
+ "epoch": 2.656449553001277,
+ "grad_norm": 0.868914008140564,
+ "learning_rate": 2.2525597269624575e-05,
+ "loss": 0.3709,
+ "mean_token_accuracy": 0.9212313622236252,
+ "num_tokens": 733797.0,
+ "step": 780
+ },
+ {
+ "epoch": 2.6734780757769263,
+ "grad_norm": 0.7551370859146118,
+ "learning_rate": 2.138794084186576e-05,
+ "loss": 0.367,
+ "mean_token_accuracy": 0.9220638558268547,
+ "num_tokens": 738487.0,
+ "step": 785
+ },
+ {
+ "epoch": 2.6905065985525756,
+ "grad_norm": 0.7959733009338379,
+ "learning_rate": 2.025028441410694e-05,
+ "loss": 0.3634,
+ "mean_token_accuracy": 0.9227283328771592,
+ "num_tokens": 743145.0,
+ "step": 790
+ },
+ {
+ "epoch": 2.707535121328225,
+ "grad_norm": 0.8846186399459839,
+ "learning_rate": 1.9112627986348127e-05,
+ "loss": 0.3595,
+ "mean_token_accuracy": 0.9253345713019371,
+ "num_tokens": 747814.0,
+ "step": 795
+ },
+ {
+ "epoch": 2.724563644103874,
+ "grad_norm": 0.6306168437004089,
+ "learning_rate": 1.7974971558589308e-05,
+ "loss": 0.3507,
+ "mean_token_accuracy": 0.924257718026638,
+ "num_tokens": 752477.0,
+ "step": 800
+ }
+ ],
+ "logging_steps": 5,
+ "max_steps": 879,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 200,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 3.4073066251935744e+16,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d77eaa0f69f97b2b9813f53e641e4a6232bfa34d
--- /dev/null
+++ b/checkpoint-800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
+size 5624
diff --git a/checkpoint-879/README.md b/checkpoint-879/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9633d8f0130799d996b640335cd6d3846c495f5b
--- /dev/null
+++ b/checkpoint-879/README.md
@@ -0,0 +1,209 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+
+
+
+
+## Model Details
+
+### Model Description
+
+
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+
+
+### Direct Use
+
+
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+
+
+[More Information Needed]
+
+### Recommendations
+
+
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+
+
+[More Information Needed]
+
+### Training Procedure
+
+
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed]
+
+#### Speeds, Sizes, Times [optional]
+
+
+
+[More Information Needed]
+
+## Evaluation
+
+
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+
+
+[More Information Needed]
+
+#### Factors
+
+
+
+[More Information Needed]
+
+#### Metrics
+
+
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+
+
+[More Information Needed]
+
+## Environmental Impact
+
+
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0
\ No newline at end of file
diff --git a/checkpoint-879/adapter_config.json b/checkpoint-879/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..45edbb77201d4198da4bf26b8a7258da2bca8d90
--- /dev/null
+++ b/checkpoint-879/adapter_config.json
@@ -0,0 +1,50 @@
+{
+ "alora_invocation_tokens": null,
+ "alpha_pattern": {},
+ "arrow_config": null,
+ "auto_mapping": null,
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+ "bias": "none",
+ "corda_config": null,
+ "ensure_weight_tying": false,
+ "eva_config": null,
+ "exclude_modules": null,
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 32,
+ "lora_bias": false,
+ "lora_dropout": 0.05,
+ "lora_ga_config": null,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "monteclora_config": null,
+ "peft_type": "LORA",
+ "peft_version": "0.20.0",
+ "qalora_group_size": 16,
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_proj",
+ "k_proj",
+ "down_proj",
+ "up_proj",
+ "gate_proj",
+ "o_proj"
+ ],
+ "target_parameters": null,
+ "task_type": "CAUSAL_LM",
+ "trainable_token_indices": null,
+ "use_bdlora": null,
+ "use_dora": false,
+ "use_qalora": false,
+ "use_rslora": false,
+ "velora_config": null
+}
\ No newline at end of file
diff --git a/checkpoint-879/adapter_model.safetensors b/checkpoint-879/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ae6703c0a7630f91d92d75ebbdd48a896758d3dc
--- /dev/null
+++ b/checkpoint-879/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac73482dab07a18e9416036be9875bd9965b5fbb11900b7e33bf7618fb628c6
+size 167832240
diff --git a/checkpoint-879/optimizer.pt b/checkpoint-879/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..98cb5aab65e3ca20d8ad2611b11ebe613115b148
--- /dev/null
+++ b/checkpoint-879/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0b4e0223198ffa92bd2280315bddba3e539aed757bc7d16e1e5045598cca9b
+size 85728276
diff --git a/checkpoint-879/rng_state.pth b/checkpoint-879/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dca6fe1394bcd71fdf22ee0fbd02eb3abee73b40
--- /dev/null
+++ b/checkpoint-879/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e56d6263db375f3f1cabf17f953f6f2881fb804b31388d5443d4303c35938c8
+size 14244
diff --git a/checkpoint-879/scheduler.pt b/checkpoint-879/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4018abeef069931aa48f67f7f46d955c6306e836
--- /dev/null
+++ b/checkpoint-879/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e6f0af26f3b4982a424dd9de3d6bfa562672950d695d78c84ab95ef5228378
+size 1064
diff --git a/checkpoint-879/special_tokens_map.json b/checkpoint-879/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fed0491bb0ae0c4f0752f54ffddf7d69269daed
--- /dev/null
+++ b/checkpoint-879/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+ "bos_token": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|im_end|>"
+}
diff --git a/checkpoint-879/tokenizer.json b/checkpoint-879/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b
--- /dev/null
+++ b/checkpoint-879/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
+size 17209403
diff --git a/checkpoint-879/tokenizer_config.json b/checkpoint-879/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1dbecde59340b33dcf97ef6087584a5a01208ab5
--- /dev/null
+++ b/checkpoint-879/tokenizer_config.json
@@ -0,0 +1,2072 @@
+{
+ "added_tokens_decoder": {
+ "128000": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128001": {
+ "content": "<|end_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128002": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128003": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128004": {
+ "content": "<|finetune_right_pad_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128005": {
+ "content": "<|reserved_special_token_2|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128006": {
+ "content": "<|start_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128007": {
+ "content": "<|end_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128008": {
+ "content": "<|eom_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128009": {
+ "content": "<|eot_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128010": {
+ "content": "<|python_tag|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128011": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128012": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128013": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128014": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128015": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128016": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128017": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128018": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128019": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128020": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128021": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128022": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128023": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128024": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128025": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128026": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128027": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128028": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128029": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128030": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128031": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128032": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128033": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128034": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128035": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128036": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128037": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128038": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128039": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128040": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128041": {
+ "content": "<|reserved_special_token_33|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128042": {
+ "content": "<|reserved_special_token_34|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128043": {
+ "content": "<|reserved_special_token_35|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128044": {
+ "content": "<|reserved_special_token_36|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128045": {
+ "content": "<|reserved_special_token_37|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128046": {
+ "content": "<|reserved_special_token_38|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128047": {
+ "content": "<|reserved_special_token_39|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128048": {
+ "content": "<|reserved_special_token_40|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128049": {
+ "content": "<|reserved_special_token_41|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128050": {
+ "content": "<|reserved_special_token_42|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128051": {
+ "content": "<|reserved_special_token_43|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128052": {
+ "content": "<|reserved_special_token_44|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128053": {
+ "content": "<|reserved_special_token_45|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128054": {
+ "content": "<|reserved_special_token_46|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128055": {
+ "content": "<|reserved_special_token_47|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128056": {
+ "content": "<|reserved_special_token_48|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128057": {
+ "content": "<|reserved_special_token_49|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128058": {
+ "content": "<|reserved_special_token_50|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128059": {
+ "content": "<|reserved_special_token_51|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128060": {
+ "content": "<|reserved_special_token_52|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128061": {
+ "content": "<|reserved_special_token_53|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128062": {
+ "content": "<|reserved_special_token_54|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128063": {
+ "content": "<|reserved_special_token_55|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128064": {
+ "content": "<|reserved_special_token_56|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128065": {
+ "content": "<|reserved_special_token_57|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128066": {
+ "content": "<|reserved_special_token_58|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128067": {
+ "content": "<|reserved_special_token_59|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128068": {
+ "content": "<|reserved_special_token_60|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128069": {
+ "content": "<|reserved_special_token_61|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128070": {
+ "content": "<|reserved_special_token_62|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128071": {
+ "content": "<|reserved_special_token_63|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128072": {
+ "content": "<|reserved_special_token_64|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128073": {
+ "content": "<|reserved_special_token_65|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128074": {
+ "content": "<|reserved_special_token_66|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128075": {
+ "content": "<|reserved_special_token_67|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128076": {
+ "content": "<|reserved_special_token_68|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128077": {
+ "content": "<|reserved_special_token_69|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128078": {
+ "content": "<|reserved_special_token_70|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128079": {
+ "content": "<|reserved_special_token_71|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128080": {
+ "content": "<|reserved_special_token_72|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128081": {
+ "content": "<|reserved_special_token_73|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128082": {
+ "content": "<|reserved_special_token_74|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128083": {
+ "content": "<|reserved_special_token_75|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128084": {
+ "content": "<|reserved_special_token_76|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128085": {
+ "content": "<|reserved_special_token_77|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128086": {
+ "content": "<|reserved_special_token_78|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128087": {
+ "content": "<|reserved_special_token_79|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128088": {
+ "content": "<|reserved_special_token_80|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128089": {
+ "content": "<|reserved_special_token_81|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128090": {
+ "content": "<|reserved_special_token_82|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128091": {
+ "content": "<|reserved_special_token_83|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128092": {
+ "content": "<|reserved_special_token_84|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128093": {
+ "content": "<|reserved_special_token_85|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128094": {
+ "content": "<|reserved_special_token_86|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128095": {
+ "content": "<|reserved_special_token_87|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128096": {
+ "content": "<|reserved_special_token_88|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128097": {
+ "content": "<|reserved_special_token_89|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128098": {
+ "content": "<|reserved_special_token_90|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128099": {
+ "content": "<|reserved_special_token_91|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128100": {
+ "content": "<|reserved_special_token_92|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128101": {
+ "content": "<|reserved_special_token_93|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128102": {
+ "content": "<|reserved_special_token_94|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128103": {
+ "content": "<|reserved_special_token_95|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128104": {
+ "content": "<|reserved_special_token_96|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128105": {
+ "content": "<|reserved_special_token_97|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128106": {
+ "content": "<|reserved_special_token_98|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128107": {
+ "content": "<|reserved_special_token_99|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128108": {
+ "content": "<|reserved_special_token_100|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128109": {
+ "content": "<|reserved_special_token_101|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128110": {
+ "content": "<|reserved_special_token_102|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128111": {
+ "content": "<|reserved_special_token_103|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128112": {
+ "content": "<|reserved_special_token_104|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128113": {
+ "content": "<|reserved_special_token_105|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128114": {
+ "content": "<|reserved_special_token_106|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128115": {
+ "content": "<|reserved_special_token_107|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128116": {
+ "content": "<|reserved_special_token_108|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128117": {
+ "content": "<|reserved_special_token_109|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128118": {
+ "content": "<|reserved_special_token_110|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128119": {
+ "content": "<|reserved_special_token_111|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128120": {
+ "content": "<|reserved_special_token_112|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128121": {
+ "content": "<|reserved_special_token_113|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128122": {
+ "content": "<|reserved_special_token_114|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128123": {
+ "content": "<|reserved_special_token_115|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128124": {
+ "content": "<|reserved_special_token_116|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128125": {
+ "content": "<|reserved_special_token_117|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128126": {
+ "content": "<|reserved_special_token_118|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128127": {
+ "content": "<|reserved_special_token_119|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128128": {
+ "content": "<|reserved_special_token_120|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128129": {
+ "content": "<|reserved_special_token_121|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128130": {
+ "content": "<|reserved_special_token_122|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128131": {
+ "content": "<|reserved_special_token_123|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128132": {
+ "content": "<|reserved_special_token_124|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128133": {
+ "content": "<|reserved_special_token_125|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128134": {
+ "content": "<|reserved_special_token_126|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128135": {
+ "content": "<|reserved_special_token_127|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128136": {
+ "content": "<|reserved_special_token_128|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128137": {
+ "content": "<|reserved_special_token_129|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128138": {
+ "content": "<|reserved_special_token_130|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128139": {
+ "content": "<|reserved_special_token_131|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128140": {
+ "content": "<|reserved_special_token_132|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128141": {
+ "content": "<|reserved_special_token_133|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128142": {
+ "content": "<|reserved_special_token_134|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128143": {
+ "content": "<|reserved_special_token_135|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128144": {
+ "content": "<|reserved_special_token_136|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128145": {
+ "content": "<|reserved_special_token_137|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128146": {
+ "content": "<|reserved_special_token_138|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128147": {
+ "content": "<|reserved_special_token_139|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128148": {
+ "content": "<|reserved_special_token_140|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128149": {
+ "content": "<|reserved_special_token_141|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128150": {
+ "content": "<|reserved_special_token_142|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128151": {
+ "content": "<|reserved_special_token_143|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128152": {
+ "content": "<|reserved_special_token_144|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128153": {
+ "content": "<|reserved_special_token_145|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128154": {
+ "content": "<|reserved_special_token_146|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128155": {
+ "content": "<|reserved_special_token_147|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128156": {
+ "content": "<|reserved_special_token_148|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128157": {
+ "content": "<|reserved_special_token_149|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128158": {
+ "content": "<|reserved_special_token_150|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128159": {
+ "content": "<|reserved_special_token_151|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128160": {
+ "content": "<|reserved_special_token_152|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128161": {
+ "content": "<|reserved_special_token_153|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128162": {
+ "content": "<|reserved_special_token_154|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128163": {
+ "content": "<|reserved_special_token_155|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128164": {
+ "content": "<|reserved_special_token_156|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128165": {
+ "content": "<|reserved_special_token_157|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128166": {
+ "content": "<|reserved_special_token_158|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128167": {
+ "content": "<|reserved_special_token_159|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128168": {
+ "content": "<|reserved_special_token_160|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128169": {
+ "content": "<|reserved_special_token_161|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128170": {
+ "content": "<|reserved_special_token_162|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128171": {
+ "content": "<|reserved_special_token_163|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128172": {
+ "content": "<|reserved_special_token_164|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128173": {
+ "content": "<|reserved_special_token_165|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128174": {
+ "content": "<|reserved_special_token_166|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128175": {
+ "content": "<|reserved_special_token_167|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128176": {
+ "content": "<|reserved_special_token_168|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128177": {
+ "content": "<|reserved_special_token_169|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128178": {
+ "content": "<|reserved_special_token_170|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128179": {
+ "content": "<|reserved_special_token_171|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128180": {
+ "content": "<|reserved_special_token_172|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128181": {
+ "content": "<|reserved_special_token_173|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128182": {
+ "content": "<|reserved_special_token_174|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128183": {
+ "content": "<|reserved_special_token_175|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128184": {
+ "content": "<|reserved_special_token_176|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128185": {
+ "content": "<|reserved_special_token_177|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128186": {
+ "content": "<|reserved_special_token_178|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128187": {
+ "content": "<|reserved_special_token_179|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128188": {
+ "content": "<|reserved_special_token_180|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128189": {
+ "content": "<|reserved_special_token_181|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128190": {
+ "content": "<|reserved_special_token_182|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128191": {
+ "content": "<|reserved_special_token_183|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128192": {
+ "content": "<|reserved_special_token_184|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128193": {
+ "content": "<|reserved_special_token_185|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128194": {
+ "content": "<|reserved_special_token_186|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128195": {
+ "content": "<|reserved_special_token_187|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128196": {
+ "content": "<|reserved_special_token_188|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128197": {
+ "content": "<|reserved_special_token_189|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128198": {
+ "content": "<|reserved_special_token_190|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128199": {
+ "content": "<|reserved_special_token_191|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128200": {
+ "content": "<|reserved_special_token_192|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128201": {
+ "content": "<|reserved_special_token_193|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128202": {
+ "content": "<|reserved_special_token_194|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128203": {
+ "content": "<|reserved_special_token_195|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128204": {
+ "content": "<|reserved_special_token_196|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128205": {
+ "content": "<|reserved_special_token_197|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128206": {
+ "content": "<|reserved_special_token_198|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128207": {
+ "content": "<|reserved_special_token_199|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128208": {
+ "content": "<|reserved_special_token_200|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128209": {
+ "content": "<|reserved_special_token_201|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128210": {
+ "content": "<|reserved_special_token_202|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128211": {
+ "content": "<|reserved_special_token_203|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128212": {
+ "content": "<|reserved_special_token_204|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128213": {
+ "content": "<|reserved_special_token_205|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128214": {
+ "content": "<|reserved_special_token_206|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128215": {
+ "content": "<|reserved_special_token_207|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128216": {
+ "content": "<|reserved_special_token_208|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128217": {
+ "content": "<|reserved_special_token_209|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128218": {
+ "content": "<|reserved_special_token_210|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128219": {
+ "content": "<|reserved_special_token_211|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128220": {
+ "content": "<|reserved_special_token_212|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128221": {
+ "content": "<|reserved_special_token_213|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128222": {
+ "content": "<|reserved_special_token_214|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128223": {
+ "content": "<|reserved_special_token_215|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128224": {
+ "content": "<|reserved_special_token_216|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128225": {
+ "content": "<|reserved_special_token_217|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128226": {
+ "content": "<|reserved_special_token_218|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128227": {
+ "content": "<|reserved_special_token_219|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128228": {
+ "content": "<|reserved_special_token_220|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128229": {
+ "content": "<|reserved_special_token_221|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128230": {
+ "content": "<|reserved_special_token_222|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128231": {
+ "content": "<|reserved_special_token_223|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128232": {
+ "content": "<|reserved_special_token_224|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128233": {
+ "content": "<|reserved_special_token_225|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128234": {
+ "content": "<|reserved_special_token_226|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128235": {
+ "content": "<|reserved_special_token_227|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128236": {
+ "content": "<|reserved_special_token_228|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128237": {
+ "content": "<|reserved_special_token_229|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128238": {
+ "content": "<|reserved_special_token_230|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128239": {
+ "content": "<|reserved_special_token_231|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128240": {
+ "content": "<|reserved_special_token_232|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128241": {
+ "content": "<|reserved_special_token_233|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128242": {
+ "content": "<|reserved_special_token_234|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128243": {
+ "content": "<|reserved_special_token_235|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128244": {
+ "content": "<|reserved_special_token_236|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128245": {
+ "content": "<|reserved_special_token_237|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128246": {
+ "content": "<|reserved_special_token_238|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128247": {
+ "content": "<|reserved_special_token_239|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128248": {
+ "content": "<|reserved_special_token_240|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128249": {
+ "content": "<|reserved_special_token_241|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128250": {
+ "content": "<|reserved_special_token_242|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128251": {
+ "content": "<|reserved_special_token_243|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128252": {
+ "content": "<|reserved_special_token_244|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128253": {
+ "content": "<|reserved_special_token_245|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128254": {
+ "content": "<|reserved_special_token_246|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128255": {
+ "content": "<|reserved_special_token_247|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|begin_of_text|>",
+ "chat_template": [
+ {
+ "name": "default",
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+ },
+ {
+ "name": "tool_use",
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" \" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within XML tags as follows:\n\" }}\n{{- \"\n\" }}\n{{- '{\"name\": , \"arguments\": }\n' }}\n{{- '<|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- else %}\n {{- '\n' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+ }
+ ],
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|im_end|>",
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 131072,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-879/trainer_state.json b/checkpoint-879/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..85289bda9b89baeffa73ac770b2c7dfa38974ecf
--- /dev/null
+++ b/checkpoint-879/trainer_state.json
@@ -0,0 +1,1608 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.9936143039591316,
+ "eval_steps": 500,
+ "global_step": 879,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.017028522775649212,
+ "grad_norm": 6.522716999053955,
+ "learning_rate": 0.0001988623435722412,
+ "loss": 2.7211,
+ "mean_token_accuracy": 0.5789041496813297,
+ "num_tokens": 4727.0,
+ "step": 5
+ },
+ {
+ "epoch": 0.034057045551298425,
+ "grad_norm": 1.0070050954818726,
+ "learning_rate": 0.00019772468714448238,
+ "loss": 0.9998,
+ "mean_token_accuracy": 0.8499793156981468,
+ "num_tokens": 9471.0,
+ "step": 10
+ },
+ {
+ "epoch": 0.05108556832694764,
+ "grad_norm": 0.7373425960540771,
+ "learning_rate": 0.00019658703071672356,
+ "loss": 0.8303,
+ "mean_token_accuracy": 0.8681916877627373,
+ "num_tokens": 14013.0,
+ "step": 15
+ },
+ {
+ "epoch": 0.06811409110259685,
+ "grad_norm": 0.8468236327171326,
+ "learning_rate": 0.00019544937428896475,
+ "loss": 0.8404,
+ "mean_token_accuracy": 0.8622620105743408,
+ "num_tokens": 18725.0,
+ "step": 20
+ },
+ {
+ "epoch": 0.08514261387824607,
+ "grad_norm": 0.8178804516792297,
+ "learning_rate": 0.00019431171786120593,
+ "loss": 0.9073,
+ "mean_token_accuracy": 0.8524447843432427,
+ "num_tokens": 23497.0,
+ "step": 25
+ },
+ {
+ "epoch": 0.10217113665389528,
+ "grad_norm": 0.890177309513092,
+ "learning_rate": 0.00019317406143344712,
+ "loss": 0.8029,
+ "mean_token_accuracy": 0.8642359614372254,
+ "num_tokens": 28192.0,
+ "step": 30
+ },
+ {
+ "epoch": 0.11919965942954448,
+ "grad_norm": 1.0545469522476196,
+ "learning_rate": 0.0001920364050056883,
+ "loss": 0.7458,
+ "mean_token_accuracy": 0.8732351213693619,
+ "num_tokens": 32805.0,
+ "step": 35
+ },
+ {
+ "epoch": 0.1362281822051937,
+ "grad_norm": 1.0384492874145508,
+ "learning_rate": 0.00019089874857792946,
+ "loss": 0.9235,
+ "mean_token_accuracy": 0.8408558666706085,
+ "num_tokens": 37714.0,
+ "step": 40
+ },
+ {
+ "epoch": 0.1532567049808429,
+ "grad_norm": 0.6860374808311462,
+ "learning_rate": 0.00018976109215017067,
+ "loss": 0.7623,
+ "mean_token_accuracy": 0.8656536340713501,
+ "num_tokens": 42429.0,
+ "step": 45
+ },
+ {
+ "epoch": 0.17028522775649213,
+ "grad_norm": 0.7284501791000366,
+ "learning_rate": 0.00018862343572241183,
+ "loss": 0.7588,
+ "mean_token_accuracy": 0.8688850715756417,
+ "num_tokens": 47099.0,
+ "step": 50
+ },
+ {
+ "epoch": 0.18731375053214133,
+ "grad_norm": 0.8899862170219421,
+ "learning_rate": 0.00018748577929465302,
+ "loss": 0.7065,
+ "mean_token_accuracy": 0.8717748820781708,
+ "num_tokens": 51795.0,
+ "step": 55
+ },
+ {
+ "epoch": 0.20434227330779056,
+ "grad_norm": 0.5350505709648132,
+ "learning_rate": 0.0001863481228668942,
+ "loss": 0.6696,
+ "mean_token_accuracy": 0.8851396456360817,
+ "num_tokens": 56369.0,
+ "step": 60
+ },
+ {
+ "epoch": 0.22137079608343976,
+ "grad_norm": 0.6087013483047485,
+ "learning_rate": 0.0001852104664391354,
+ "loss": 0.7204,
+ "mean_token_accuracy": 0.8682332798838616,
+ "num_tokens": 61018.0,
+ "step": 65
+ },
+ {
+ "epoch": 0.23839931885908897,
+ "grad_norm": 0.7879019379615784,
+ "learning_rate": 0.00018407281001137657,
+ "loss": 0.7692,
+ "mean_token_accuracy": 0.8653983056545258,
+ "num_tokens": 65741.0,
+ "step": 70
+ },
+ {
+ "epoch": 0.2554278416347382,
+ "grad_norm": 0.6546444296836853,
+ "learning_rate": 0.00018293515358361776,
+ "loss": 0.7119,
+ "mean_token_accuracy": 0.8726310178637504,
+ "num_tokens": 70425.0,
+ "step": 75
+ },
+ {
+ "epoch": 0.2724563644103874,
+ "grad_norm": 0.770902156829834,
+ "learning_rate": 0.00018179749715585894,
+ "loss": 0.7035,
+ "mean_token_accuracy": 0.8711811751127243,
+ "num_tokens": 75101.0,
+ "step": 80
+ },
+ {
+ "epoch": 0.2894848871860366,
+ "grad_norm": 0.8873187899589539,
+ "learning_rate": 0.00018065984072810013,
+ "loss": 0.7419,
+ "mean_token_accuracy": 0.8616803497076034,
+ "num_tokens": 79888.0,
+ "step": 85
+ },
+ {
+ "epoch": 0.3065134099616858,
+ "grad_norm": 0.7061370015144348,
+ "learning_rate": 0.0001795221843003413,
+ "loss": 0.66,
+ "mean_token_accuracy": 0.8744896531105042,
+ "num_tokens": 84562.0,
+ "step": 90
+ },
+ {
+ "epoch": 0.32354193273733506,
+ "grad_norm": 0.8232033252716064,
+ "learning_rate": 0.0001783845278725825,
+ "loss": 0.7403,
+ "mean_token_accuracy": 0.8659066379070282,
+ "num_tokens": 89238.0,
+ "step": 95
+ },
+ {
+ "epoch": 0.34057045551298426,
+ "grad_norm": 0.7313310503959656,
+ "learning_rate": 0.00017724687144482368,
+ "loss": 0.7157,
+ "mean_token_accuracy": 0.8661555901169777,
+ "num_tokens": 93987.0,
+ "step": 100
+ },
+ {
+ "epoch": 0.35759897828863346,
+ "grad_norm": 0.7119390964508057,
+ "learning_rate": 0.00017610921501706487,
+ "loss": 0.7016,
+ "mean_token_accuracy": 0.8678551658987999,
+ "num_tokens": 98722.0,
+ "step": 105
+ },
+ {
+ "epoch": 0.37462750106428266,
+ "grad_norm": 0.7126006484031677,
+ "learning_rate": 0.00017497155858930602,
+ "loss": 0.7009,
+ "mean_token_accuracy": 0.867291408777237,
+ "num_tokens": 103439.0,
+ "step": 110
+ },
+ {
+ "epoch": 0.39165602383993187,
+ "grad_norm": 0.6158230304718018,
+ "learning_rate": 0.00017383390216154724,
+ "loss": 0.7236,
+ "mean_token_accuracy": 0.8636128515005111,
+ "num_tokens": 108209.0,
+ "step": 115
+ },
+ {
+ "epoch": 0.4086845466155811,
+ "grad_norm": 0.6498322486877441,
+ "learning_rate": 0.0001726962457337884,
+ "loss": 0.6813,
+ "mean_token_accuracy": 0.8757071048021317,
+ "num_tokens": 112855.0,
+ "step": 120
+ },
+ {
+ "epoch": 0.4257130693912303,
+ "grad_norm": 0.6594287157058716,
+ "learning_rate": 0.0001715585893060296,
+ "loss": 0.7062,
+ "mean_token_accuracy": 0.8650311172008515,
+ "num_tokens": 117653.0,
+ "step": 125
+ },
+ {
+ "epoch": 0.4427415921668795,
+ "grad_norm": 0.7375237941741943,
+ "learning_rate": 0.00017042093287827076,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8733970731496811,
+ "num_tokens": 122397.0,
+ "step": 130
+ },
+ {
+ "epoch": 0.45977011494252873,
+ "grad_norm": 0.5958442687988281,
+ "learning_rate": 0.00016928327645051198,
+ "loss": 0.691,
+ "mean_token_accuracy": 0.8681387722492218,
+ "num_tokens": 127136.0,
+ "step": 135
+ },
+ {
+ "epoch": 0.47679863771817793,
+ "grad_norm": 0.7407785654067993,
+ "learning_rate": 0.00016814562002275313,
+ "loss": 0.6477,
+ "mean_token_accuracy": 0.8752307429909706,
+ "num_tokens": 131833.0,
+ "step": 140
+ },
+ {
+ "epoch": 0.49382716049382713,
+ "grad_norm": 0.8190199732780457,
+ "learning_rate": 0.00016700796359499432,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8762851104140281,
+ "num_tokens": 136441.0,
+ "step": 145
+ },
+ {
+ "epoch": 0.5108556832694764,
+ "grad_norm": 0.7571837306022644,
+ "learning_rate": 0.0001658703071672355,
+ "loss": 0.673,
+ "mean_token_accuracy": 0.8691665843129158,
+ "num_tokens": 141186.0,
+ "step": 150
+ },
+ {
+ "epoch": 0.5278842060451255,
+ "grad_norm": 0.6653426885604858,
+ "learning_rate": 0.0001647326507394767,
+ "loss": 0.7126,
+ "mean_token_accuracy": 0.8647830635309219,
+ "num_tokens": 145971.0,
+ "step": 155
+ },
+ {
+ "epoch": 0.5449127288207748,
+ "grad_norm": 0.7333567142486572,
+ "learning_rate": 0.00016359499431171787,
+ "loss": 0.6287,
+ "mean_token_accuracy": 0.878324082493782,
+ "num_tokens": 150669.0,
+ "step": 160
+ },
+ {
+ "epoch": 0.561941251596424,
+ "grad_norm": 0.8214460015296936,
+ "learning_rate": 0.00016245733788395906,
+ "loss": 0.6608,
+ "mean_token_accuracy": 0.8729922890663147,
+ "num_tokens": 155374.0,
+ "step": 165
+ },
+ {
+ "epoch": 0.5789697743720732,
+ "grad_norm": 0.6251844167709351,
+ "learning_rate": 0.00016131968145620024,
+ "loss": 0.6556,
+ "mean_token_accuracy": 0.8770609870553017,
+ "num_tokens": 160068.0,
+ "step": 170
+ },
+ {
+ "epoch": 0.5959982971477225,
+ "grad_norm": 0.804166853427887,
+ "learning_rate": 0.00016018202502844143,
+ "loss": 0.6366,
+ "mean_token_accuracy": 0.8760894432663917,
+ "num_tokens": 164696.0,
+ "step": 175
+ },
+ {
+ "epoch": 0.6130268199233716,
+ "grad_norm": 0.7013877034187317,
+ "learning_rate": 0.0001590443686006826,
+ "loss": 0.6328,
+ "mean_token_accuracy": 0.8779815405607223,
+ "num_tokens": 169356.0,
+ "step": 180
+ },
+ {
+ "epoch": 0.6300553426990209,
+ "grad_norm": 1.0623070001602173,
+ "learning_rate": 0.0001579067121729238,
+ "loss": 0.6734,
+ "mean_token_accuracy": 0.8710577815771103,
+ "num_tokens": 174041.0,
+ "step": 185
+ },
+ {
+ "epoch": 0.6470838654746701,
+ "grad_norm": 0.7858535647392273,
+ "learning_rate": 0.00015676905574516496,
+ "loss": 0.6775,
+ "mean_token_accuracy": 0.8692880481481552,
+ "num_tokens": 178858.0,
+ "step": 190
+ },
+ {
+ "epoch": 0.6641123882503193,
+ "grad_norm": 0.8943309187889099,
+ "learning_rate": 0.00015563139931740617,
+ "loss": 0.6874,
+ "mean_token_accuracy": 0.868885512650013,
+ "num_tokens": 183669.0,
+ "step": 195
+ },
+ {
+ "epoch": 0.6811409110259685,
+ "grad_norm": 0.5898745656013489,
+ "learning_rate": 0.00015449374288964733,
+ "loss": 0.6907,
+ "mean_token_accuracy": 0.8661940798163414,
+ "num_tokens": 188473.0,
+ "step": 200
+ },
+ {
+ "epoch": 0.6981694338016177,
+ "grad_norm": 0.6333857774734497,
+ "learning_rate": 0.00015335608646188854,
+ "loss": 0.6129,
+ "mean_token_accuracy": 0.8817986205220223,
+ "num_tokens": 193171.0,
+ "step": 205
+ },
+ {
+ "epoch": 0.7151979565772669,
+ "grad_norm": 0.5913947820663452,
+ "learning_rate": 0.0001522184300341297,
+ "loss": 0.5896,
+ "mean_token_accuracy": 0.8822762459516525,
+ "num_tokens": 197817.0,
+ "step": 210
+ },
+ {
+ "epoch": 0.7322264793529162,
+ "grad_norm": 0.6990242004394531,
+ "learning_rate": 0.00015108077360637088,
+ "loss": 0.6512,
+ "mean_token_accuracy": 0.8739180400967598,
+ "num_tokens": 202556.0,
+ "step": 215
+ },
+ {
+ "epoch": 0.7492550021285653,
+ "grad_norm": 0.6869048476219177,
+ "learning_rate": 0.00014994311717861207,
+ "loss": 0.7025,
+ "mean_token_accuracy": 0.8662877783179284,
+ "num_tokens": 207294.0,
+ "step": 220
+ },
+ {
+ "epoch": 0.7662835249042146,
+ "grad_norm": 0.5135166049003601,
+ "learning_rate": 0.00014880546075085325,
+ "loss": 0.6382,
+ "mean_token_accuracy": 0.8849207311868668,
+ "num_tokens": 211927.0,
+ "step": 225
+ },
+ {
+ "epoch": 0.7833120476798637,
+ "grad_norm": 0.6304216980934143,
+ "learning_rate": 0.00014766780432309444,
+ "loss": 0.6834,
+ "mean_token_accuracy": 0.8688049465417862,
+ "num_tokens": 216626.0,
+ "step": 230
+ },
+ {
+ "epoch": 0.800340570455513,
+ "grad_norm": 0.6879922151565552,
+ "learning_rate": 0.00014653014789533562,
+ "loss": 0.6902,
+ "mean_token_accuracy": 0.8655798360705376,
+ "num_tokens": 221432.0,
+ "step": 235
+ },
+ {
+ "epoch": 0.8173690932311622,
+ "grad_norm": 0.6433548331260681,
+ "learning_rate": 0.0001453924914675768,
+ "loss": 0.6129,
+ "mean_token_accuracy": 0.8795880794525146,
+ "num_tokens": 226022.0,
+ "step": 240
+ },
+ {
+ "epoch": 0.8343976160068114,
+ "grad_norm": 0.7876724600791931,
+ "learning_rate": 0.000144254835039818,
+ "loss": 0.6441,
+ "mean_token_accuracy": 0.8729524433612823,
+ "num_tokens": 230692.0,
+ "step": 245
+ },
+ {
+ "epoch": 0.8514261387824607,
+ "grad_norm": 0.6494749188423157,
+ "learning_rate": 0.00014311717861205915,
+ "loss": 0.7033,
+ "mean_token_accuracy": 0.8632469072937965,
+ "num_tokens": 235400.0,
+ "step": 250
+ },
+ {
+ "epoch": 0.8684546615581098,
+ "grad_norm": 0.6332300305366516,
+ "learning_rate": 0.00014197952218430036,
+ "loss": 0.5947,
+ "mean_token_accuracy": 0.8860528379678726,
+ "num_tokens": 239997.0,
+ "step": 255
+ },
+ {
+ "epoch": 0.885483184333759,
+ "grad_norm": 0.7144895195960999,
+ "learning_rate": 0.00014084186575654152,
+ "loss": 0.649,
+ "mean_token_accuracy": 0.8745664536952973,
+ "num_tokens": 244704.0,
+ "step": 260
+ },
+ {
+ "epoch": 0.9025117071094083,
+ "grad_norm": 0.5460124015808105,
+ "learning_rate": 0.00013970420932878273,
+ "loss": 0.6622,
+ "mean_token_accuracy": 0.8692788198590279,
+ "num_tokens": 249428.0,
+ "step": 265
+ },
+ {
+ "epoch": 0.9195402298850575,
+ "grad_norm": 0.65619295835495,
+ "learning_rate": 0.0001385665529010239,
+ "loss": 0.657,
+ "mean_token_accuracy": 0.8737826406955719,
+ "num_tokens": 254150.0,
+ "step": 270
+ },
+ {
+ "epoch": 0.9365687526607067,
+ "grad_norm": 0.8474870324134827,
+ "learning_rate": 0.0001374288964732651,
+ "loss": 0.6607,
+ "mean_token_accuracy": 0.8756056800484657,
+ "num_tokens": 258826.0,
+ "step": 275
+ },
+ {
+ "epoch": 0.9535972754363559,
+ "grad_norm": 0.6054229736328125,
+ "learning_rate": 0.00013629124004550626,
+ "loss": 0.6526,
+ "mean_token_accuracy": 0.8718441724777222,
+ "num_tokens": 263524.0,
+ "step": 280
+ },
+ {
+ "epoch": 0.9706257982120051,
+ "grad_norm": 0.6568702459335327,
+ "learning_rate": 0.00013515358361774744,
+ "loss": 0.6174,
+ "mean_token_accuracy": 0.881709736585617,
+ "num_tokens": 268179.0,
+ "step": 285
+ },
+ {
+ "epoch": 0.9876543209876543,
+ "grad_norm": 0.7518045902252197,
+ "learning_rate": 0.00013401592718998863,
+ "loss": 0.5896,
+ "mean_token_accuracy": 0.885109031200409,
+ "num_tokens": 272803.0,
+ "step": 290
+ },
+ {
+ "epoch": 1.0046828437633035,
+ "grad_norm": 0.5392197370529175,
+ "learning_rate": 0.00013287827076222981,
+ "loss": 0.6753,
+ "mean_token_accuracy": 0.8788385137915611,
+ "num_tokens": 277527.0,
+ "step": 295
+ },
+ {
+ "epoch": 1.0217113665389528,
+ "grad_norm": 0.5845906734466553,
+ "learning_rate": 0.000131740614334471,
+ "loss": 0.5237,
+ "mean_token_accuracy": 0.8938747227191925,
+ "num_tokens": 282199.0,
+ "step": 300
+ },
+ {
+ "epoch": 1.038739889314602,
+ "grad_norm": 0.6392928957939148,
+ "learning_rate": 0.00013060295790671218,
+ "loss": 0.4973,
+ "mean_token_accuracy": 0.8982622623443604,
+ "num_tokens": 286951.0,
+ "step": 305
+ },
+ {
+ "epoch": 1.055768412090251,
+ "grad_norm": 0.5399300456047058,
+ "learning_rate": 0.00012946530147895337,
+ "loss": 0.5076,
+ "mean_token_accuracy": 0.9008002370595932,
+ "num_tokens": 291569.0,
+ "step": 310
+ },
+ {
+ "epoch": 1.0727969348659003,
+ "grad_norm": 0.6236026883125305,
+ "learning_rate": 0.00012832764505119455,
+ "loss": 0.5084,
+ "mean_token_accuracy": 0.8972577184438706,
+ "num_tokens": 296230.0,
+ "step": 315
+ },
+ {
+ "epoch": 1.0898254576415496,
+ "grad_norm": 0.7385813593864441,
+ "learning_rate": 0.0001271899886234357,
+ "loss": 0.5062,
+ "mean_token_accuracy": 0.8956585437059402,
+ "num_tokens": 301029.0,
+ "step": 320
+ },
+ {
+ "epoch": 1.1068539804171988,
+ "grad_norm": 0.7647150754928589,
+ "learning_rate": 0.00012605233219567692,
+ "loss": 0.5078,
+ "mean_token_accuracy": 0.8982979074120522,
+ "num_tokens": 305696.0,
+ "step": 325
+ },
+ {
+ "epoch": 1.123882503192848,
+ "grad_norm": 0.6433872580528259,
+ "learning_rate": 0.00012491467576791808,
+ "loss": 0.5215,
+ "mean_token_accuracy": 0.8974734947085381,
+ "num_tokens": 310343.0,
+ "step": 330
+ },
+ {
+ "epoch": 1.1409110259684971,
+ "grad_norm": 0.6470033526420593,
+ "learning_rate": 0.0001237770193401593,
+ "loss": 0.5261,
+ "mean_token_accuracy": 0.8938129872083664,
+ "num_tokens": 315097.0,
+ "step": 335
+ },
+ {
+ "epoch": 1.1579395487441464,
+ "grad_norm": 0.6738846302032471,
+ "learning_rate": 0.00012263936291240045,
+ "loss": 0.5277,
+ "mean_token_accuracy": 0.8924461513757705,
+ "num_tokens": 319861.0,
+ "step": 340
+ },
+ {
+ "epoch": 1.1749680715197957,
+ "grad_norm": 0.6639145016670227,
+ "learning_rate": 0.00012150170648464165,
+ "loss": 0.5127,
+ "mean_token_accuracy": 0.8926685571670532,
+ "num_tokens": 324544.0,
+ "step": 345
+ },
+ {
+ "epoch": 1.191996594295445,
+ "grad_norm": 0.7034420371055603,
+ "learning_rate": 0.00012036405005688282,
+ "loss": 0.51,
+ "mean_token_accuracy": 0.8971043467521668,
+ "num_tokens": 329302.0,
+ "step": 350
+ },
+ {
+ "epoch": 1.2090251170710942,
+ "grad_norm": 0.6675500273704529,
+ "learning_rate": 0.000119226393629124,
+ "loss": 0.5738,
+ "mean_token_accuracy": 0.8855719327926636,
+ "num_tokens": 334103.0,
+ "step": 355
+ },
+ {
+ "epoch": 1.2260536398467432,
+ "grad_norm": 0.6019395589828491,
+ "learning_rate": 0.00011808873720136519,
+ "loss": 0.476,
+ "mean_token_accuracy": 0.8989460453391075,
+ "num_tokens": 338666.0,
+ "step": 360
+ },
+ {
+ "epoch": 1.2430821626223925,
+ "grad_norm": 0.6599250435829163,
+ "learning_rate": 0.00011695108077360638,
+ "loss": 0.5178,
+ "mean_token_accuracy": 0.8887226998805999,
+ "num_tokens": 343333.0,
+ "step": 365
+ },
+ {
+ "epoch": 1.2601106853980417,
+ "grad_norm": 0.7334213852882385,
+ "learning_rate": 0.00011581342434584756,
+ "loss": 0.5378,
+ "mean_token_accuracy": 0.8895460113883018,
+ "num_tokens": 348092.0,
+ "step": 370
+ },
+ {
+ "epoch": 1.277139208173691,
+ "grad_norm": 0.7423357963562012,
+ "learning_rate": 0.00011467576791808873,
+ "loss": 0.5012,
+ "mean_token_accuracy": 0.8994292929768563,
+ "num_tokens": 352661.0,
+ "step": 375
+ },
+ {
+ "epoch": 1.29416773094934,
+ "grad_norm": 0.857515811920166,
+ "learning_rate": 0.00011353811149032993,
+ "loss": 0.507,
+ "mean_token_accuracy": 0.8979884222149849,
+ "num_tokens": 357330.0,
+ "step": 380
+ },
+ {
+ "epoch": 1.3111962537249893,
+ "grad_norm": 0.5656803250312805,
+ "learning_rate": 0.0001124004550625711,
+ "loss": 0.5009,
+ "mean_token_accuracy": 0.8934224143624305,
+ "num_tokens": 362020.0,
+ "step": 385
+ },
+ {
+ "epoch": 1.3282247765006385,
+ "grad_norm": 0.6634964942932129,
+ "learning_rate": 0.00011126279863481229,
+ "loss": 0.5414,
+ "mean_token_accuracy": 0.8910330131649971,
+ "num_tokens": 366728.0,
+ "step": 390
+ },
+ {
+ "epoch": 1.3452532992762878,
+ "grad_norm": 0.7004157304763794,
+ "learning_rate": 0.00011012514220705347,
+ "loss": 0.4922,
+ "mean_token_accuracy": 0.8992783546447753,
+ "num_tokens": 371381.0,
+ "step": 395
+ },
+ {
+ "epoch": 1.362281822051937,
+ "grad_norm": 0.6225594282150269,
+ "learning_rate": 0.00010898748577929466,
+ "loss": 0.5084,
+ "mean_token_accuracy": 0.8956901535391808,
+ "num_tokens": 376043.0,
+ "step": 400
+ },
+ {
+ "epoch": 1.3793103448275863,
+ "grad_norm": 0.8019647598266602,
+ "learning_rate": 0.00010784982935153584,
+ "loss": 0.5303,
+ "mean_token_accuracy": 0.8940754950046539,
+ "num_tokens": 380714.0,
+ "step": 405
+ },
+ {
+ "epoch": 1.3963388676032356,
+ "grad_norm": 0.8314201831817627,
+ "learning_rate": 0.00010671217292377703,
+ "loss": 0.5249,
+ "mean_token_accuracy": 0.8924115225672722,
+ "num_tokens": 385498.0,
+ "step": 410
+ },
+ {
+ "epoch": 1.4133673903788846,
+ "grad_norm": 0.6691393256187439,
+ "learning_rate": 0.00010557451649601821,
+ "loss": 0.4817,
+ "mean_token_accuracy": 0.89882483035326,
+ "num_tokens": 390179.0,
+ "step": 415
+ },
+ {
+ "epoch": 1.4303959131545338,
+ "grad_norm": 0.8554338216781616,
+ "learning_rate": 0.00010443686006825938,
+ "loss": 0.5191,
+ "mean_token_accuracy": 0.8876234069466591,
+ "num_tokens": 394930.0,
+ "step": 420
+ },
+ {
+ "epoch": 1.447424435930183,
+ "grad_norm": 0.696018636226654,
+ "learning_rate": 0.00010329920364050057,
+ "loss": 0.5386,
+ "mean_token_accuracy": 0.891503955423832,
+ "num_tokens": 399685.0,
+ "step": 425
+ },
+ {
+ "epoch": 1.4644529587058321,
+ "grad_norm": 0.7389529943466187,
+ "learning_rate": 0.00010216154721274175,
+ "loss": 0.4949,
+ "mean_token_accuracy": 0.9004919424653053,
+ "num_tokens": 404300.0,
+ "step": 430
+ },
+ {
+ "epoch": 1.4814814814814814,
+ "grad_norm": 1.0227491855621338,
+ "learning_rate": 0.00010102389078498294,
+ "loss": 0.54,
+ "mean_token_accuracy": 0.8893611416220665,
+ "num_tokens": 409079.0,
+ "step": 435
+ },
+ {
+ "epoch": 1.4985100042571307,
+ "grad_norm": 0.6526888012886047,
+ "learning_rate": 9.988623435722412e-05,
+ "loss": 0.4917,
+ "mean_token_accuracy": 0.8958082437515259,
+ "num_tokens": 413758.0,
+ "step": 440
+ },
+ {
+ "epoch": 1.51553852703278,
+ "grad_norm": 0.5875766277313232,
+ "learning_rate": 9.874857792946531e-05,
+ "loss": 0.4991,
+ "mean_token_accuracy": 0.8971148490905761,
+ "num_tokens": 418502.0,
+ "step": 445
+ },
+ {
+ "epoch": 1.5325670498084292,
+ "grad_norm": 0.6892980337142944,
+ "learning_rate": 9.761092150170649e-05,
+ "loss": 0.4551,
+ "mean_token_accuracy": 0.9068983420729637,
+ "num_tokens": 423099.0,
+ "step": 450
+ },
+ {
+ "epoch": 1.5495955725840784,
+ "grad_norm": 0.6264586448669434,
+ "learning_rate": 9.647326507394768e-05,
+ "loss": 0.468,
+ "mean_token_accuracy": 0.9043048679828644,
+ "num_tokens": 427701.0,
+ "step": 455
+ },
+ {
+ "epoch": 1.5666240953597277,
+ "grad_norm": 0.5398015379905701,
+ "learning_rate": 9.533560864618886e-05,
+ "loss": 0.4877,
+ "mean_token_accuracy": 0.8986729174852371,
+ "num_tokens": 432430.0,
+ "step": 460
+ },
+ {
+ "epoch": 1.5836526181353767,
+ "grad_norm": 0.827769935131073,
+ "learning_rate": 9.419795221843003e-05,
+ "loss": 0.4951,
+ "mean_token_accuracy": 0.9012611672282219,
+ "num_tokens": 437078.0,
+ "step": 465
+ },
+ {
+ "epoch": 1.600681140911026,
+ "grad_norm": 0.6888080835342407,
+ "learning_rate": 9.306029579067122e-05,
+ "loss": 0.5108,
+ "mean_token_accuracy": 0.8976602256298065,
+ "num_tokens": 441734.0,
+ "step": 470
+ },
+ {
+ "epoch": 1.617709663686675,
+ "grad_norm": 0.837681233882904,
+ "learning_rate": 9.19226393629124e-05,
+ "loss": 0.5377,
+ "mean_token_accuracy": 0.8850761532783509,
+ "num_tokens": 446637.0,
+ "step": 475
+ },
+ {
+ "epoch": 1.6347381864623243,
+ "grad_norm": 0.7211363315582275,
+ "learning_rate": 9.078498293515359e-05,
+ "loss": 0.5001,
+ "mean_token_accuracy": 0.898733913898468,
+ "num_tokens": 451301.0,
+ "step": 480
+ },
+ {
+ "epoch": 1.6517667092379735,
+ "grad_norm": 0.6663438081741333,
+ "learning_rate": 8.964732650739477e-05,
+ "loss": 0.5144,
+ "mean_token_accuracy": 0.8976200923323632,
+ "num_tokens": 455965.0,
+ "step": 485
+ },
+ {
+ "epoch": 1.6687952320136228,
+ "grad_norm": 0.8935639262199402,
+ "learning_rate": 8.850967007963596e-05,
+ "loss": 0.5331,
+ "mean_token_accuracy": 0.8960411131381989,
+ "num_tokens": 460716.0,
+ "step": 490
+ },
+ {
+ "epoch": 1.685823754789272,
+ "grad_norm": 0.7235546708106995,
+ "learning_rate": 8.737201365187714e-05,
+ "loss": 0.4831,
+ "mean_token_accuracy": 0.8972082689404488,
+ "num_tokens": 465370.0,
+ "step": 495
+ },
+ {
+ "epoch": 1.7028522775649213,
+ "grad_norm": 0.774000346660614,
+ "learning_rate": 8.623435722411833e-05,
+ "loss": 0.5186,
+ "mean_token_accuracy": 0.8950631290674209,
+ "num_tokens": 470043.0,
+ "step": 500
+ },
+ {
+ "epoch": 1.7198808003405706,
+ "grad_norm": 0.5213722586631775,
+ "learning_rate": 8.509670079635951e-05,
+ "loss": 0.4567,
+ "mean_token_accuracy": 0.9016156733036041,
+ "num_tokens": 474573.0,
+ "step": 505
+ },
+ {
+ "epoch": 1.7369093231162198,
+ "grad_norm": 0.7278684377670288,
+ "learning_rate": 8.395904436860069e-05,
+ "loss": 0.5545,
+ "mean_token_accuracy": 0.8925162181258202,
+ "num_tokens": 479305.0,
+ "step": 510
+ },
+ {
+ "epoch": 1.7539378458918689,
+ "grad_norm": 0.7252481579780579,
+ "learning_rate": 8.282138794084187e-05,
+ "loss": 0.496,
+ "mean_token_accuracy": 0.8953201442956924,
+ "num_tokens": 484033.0,
+ "step": 515
+ },
+ {
+ "epoch": 1.770966368667518,
+ "grad_norm": 0.727513313293457,
+ "learning_rate": 8.168373151308306e-05,
+ "loss": 0.5033,
+ "mean_token_accuracy": 0.8998701125383377,
+ "num_tokens": 488727.0,
+ "step": 520
+ },
+ {
+ "epoch": 1.7879948914431671,
+ "grad_norm": 0.5375337600708008,
+ "learning_rate": 8.054607508532424e-05,
+ "loss": 0.4903,
+ "mean_token_accuracy": 0.8960629358887673,
+ "num_tokens": 493411.0,
+ "step": 525
+ },
+ {
+ "epoch": 1.8050234142188164,
+ "grad_norm": 0.5851954221725464,
+ "learning_rate": 7.940841865756543e-05,
+ "loss": 0.5139,
+ "mean_token_accuracy": 0.8972602248191833,
+ "num_tokens": 498098.0,
+ "step": 530
+ },
+ {
+ "epoch": 1.8220519369944657,
+ "grad_norm": 0.6942209005355835,
+ "learning_rate": 7.827076222980661e-05,
+ "loss": 0.4728,
+ "mean_token_accuracy": 0.9009919315576553,
+ "num_tokens": 502717.0,
+ "step": 535
+ },
+ {
+ "epoch": 1.839080459770115,
+ "grad_norm": 0.9342221021652222,
+ "learning_rate": 7.71331058020478e-05,
+ "loss": 0.5283,
+ "mean_token_accuracy": 0.8924958631396294,
+ "num_tokens": 507462.0,
+ "step": 540
+ },
+ {
+ "epoch": 1.8561089825457642,
+ "grad_norm": 0.7415278553962708,
+ "learning_rate": 7.599544937428897e-05,
+ "loss": 0.5394,
+ "mean_token_accuracy": 0.8913042590022087,
+ "num_tokens": 512202.0,
+ "step": 545
+ },
+ {
+ "epoch": 1.8731375053214134,
+ "grad_norm": 0.7223448157310486,
+ "learning_rate": 7.485779294653015e-05,
+ "loss": 0.5473,
+ "mean_token_accuracy": 0.8873603999614715,
+ "num_tokens": 517047.0,
+ "step": 550
+ },
+ {
+ "epoch": 1.8901660280970627,
+ "grad_norm": 0.6324387192726135,
+ "learning_rate": 7.372013651877134e-05,
+ "loss": 0.4986,
+ "mean_token_accuracy": 0.9018153563141823,
+ "num_tokens": 521653.0,
+ "step": 555
+ },
+ {
+ "epoch": 1.907194550872712,
+ "grad_norm": 0.6177689433097839,
+ "learning_rate": 7.258248009101252e-05,
+ "loss": 0.5242,
+ "mean_token_accuracy": 0.8907949879765511,
+ "num_tokens": 526387.0,
+ "step": 560
+ },
+ {
+ "epoch": 1.924223073648361,
+ "grad_norm": 0.6327561140060425,
+ "learning_rate": 7.14448236632537e-05,
+ "loss": 0.4725,
+ "mean_token_accuracy": 0.9006670027971267,
+ "num_tokens": 531113.0,
+ "step": 565
+ },
+ {
+ "epoch": 1.9412515964240102,
+ "grad_norm": 0.6829894781112671,
+ "learning_rate": 7.030716723549489e-05,
+ "loss": 0.5255,
+ "mean_token_accuracy": 0.8897917374968529,
+ "num_tokens": 535963.0,
+ "step": 570
+ },
+ {
+ "epoch": 1.9582801191996593,
+ "grad_norm": 0.7764301896095276,
+ "learning_rate": 6.916951080773608e-05,
+ "loss": 0.5636,
+ "mean_token_accuracy": 0.8877105817198754,
+ "num_tokens": 540801.0,
+ "step": 575
+ },
+ {
+ "epoch": 1.9753086419753085,
+ "grad_norm": 0.7201740741729736,
+ "learning_rate": 6.803185437997726e-05,
+ "loss": 0.5279,
+ "mean_token_accuracy": 0.8954470381140709,
+ "num_tokens": 545507.0,
+ "step": 580
+ },
+ {
+ "epoch": 1.9923371647509578,
+ "grad_norm": 0.6038010716438293,
+ "learning_rate": 6.689419795221843e-05,
+ "loss": 0.505,
+ "mean_token_accuracy": 0.8970827981829643,
+ "num_tokens": 550257.0,
+ "step": 585
+ },
+ {
+ "epoch": 2.009365687526607,
+ "grad_norm": 0.5724640488624573,
+ "learning_rate": 6.575654152445962e-05,
+ "loss": 0.5361,
+ "mean_token_accuracy": 0.9015150561928749,
+ "num_tokens": 554990.0,
+ "step": 590
+ },
+ {
+ "epoch": 2.0263942103022563,
+ "grad_norm": 0.5974262952804565,
+ "learning_rate": 6.46188850967008e-05,
+ "loss": 0.3674,
+ "mean_token_accuracy": 0.922430993616581,
+ "num_tokens": 559672.0,
+ "step": 595
+ },
+ {
+ "epoch": 2.0434227330779056,
+ "grad_norm": 0.6744574904441833,
+ "learning_rate": 6.348122866894199e-05,
+ "loss": 0.3751,
+ "mean_token_accuracy": 0.9247258752584457,
+ "num_tokens": 564411.0,
+ "step": 600
+ },
+ {
+ "epoch": 2.060451255853555,
+ "grad_norm": 0.7185547351837158,
+ "learning_rate": 6.234357224118317e-05,
+ "loss": 0.3416,
+ "mean_token_accuracy": 0.929543960094452,
+ "num_tokens": 569003.0,
+ "step": 605
+ },
+ {
+ "epoch": 2.077479778629204,
+ "grad_norm": 0.5838123559951782,
+ "learning_rate": 6.120591581342436e-05,
+ "loss": 0.3537,
+ "mean_token_accuracy": 0.930443874001503,
+ "num_tokens": 573739.0,
+ "step": 610
+ },
+ {
+ "epoch": 2.0945083014048533,
+ "grad_norm": 0.8568351864814758,
+ "learning_rate": 6.0068259385665536e-05,
+ "loss": 0.3784,
+ "mean_token_accuracy": 0.9205309540033341,
+ "num_tokens": 578528.0,
+ "step": 615
+ },
+ {
+ "epoch": 2.111536824180502,
+ "grad_norm": 0.5337037444114685,
+ "learning_rate": 5.8930602957906714e-05,
+ "loss": 0.3617,
+ "mean_token_accuracy": 0.9245797485113144,
+ "num_tokens": 583227.0,
+ "step": 620
+ },
+ {
+ "epoch": 2.1285653469561514,
+ "grad_norm": 0.5879887938499451,
+ "learning_rate": 5.77929465301479e-05,
+ "loss": 0.3707,
+ "mean_token_accuracy": 0.9202131152153015,
+ "num_tokens": 587936.0,
+ "step": 625
+ },
+ {
+ "epoch": 2.1455938697318007,
+ "grad_norm": 0.6099004149436951,
+ "learning_rate": 5.665529010238908e-05,
+ "loss": 0.3774,
+ "mean_token_accuracy": 0.9187414139509201,
+ "num_tokens": 592638.0,
+ "step": 630
+ },
+ {
+ "epoch": 2.16262239250745,
+ "grad_norm": 0.6386281251907349,
+ "learning_rate": 5.551763367463026e-05,
+ "loss": 0.3618,
+ "mean_token_accuracy": 0.9270586878061294,
+ "num_tokens": 597181.0,
+ "step": 635
+ },
+ {
+ "epoch": 2.179650915283099,
+ "grad_norm": 0.9021700024604797,
+ "learning_rate": 5.437997724687145e-05,
+ "loss": 0.3585,
+ "mean_token_accuracy": 0.9271015107631684,
+ "num_tokens": 601859.0,
+ "step": 640
+ },
+ {
+ "epoch": 2.1966794380587484,
+ "grad_norm": 0.881395697593689,
+ "learning_rate": 5.324232081911263e-05,
+ "loss": 0.3557,
+ "mean_token_accuracy": 0.9272178143262864,
+ "num_tokens": 606633.0,
+ "step": 645
+ },
+ {
+ "epoch": 2.2137079608343977,
+ "grad_norm": 0.8289951086044312,
+ "learning_rate": 5.210466439135382e-05,
+ "loss": 0.3761,
+ "mean_token_accuracy": 0.9222683504223823,
+ "num_tokens": 611341.0,
+ "step": 650
+ },
+ {
+ "epoch": 2.230736483610047,
+ "grad_norm": 0.7716552019119263,
+ "learning_rate": 5.0967007963594995e-05,
+ "loss": 0.3806,
+ "mean_token_accuracy": 0.9193105801939965,
+ "num_tokens": 616076.0,
+ "step": 655
+ },
+ {
+ "epoch": 2.247765006385696,
+ "grad_norm": 0.7260558605194092,
+ "learning_rate": 4.982935153583618e-05,
+ "loss": 0.3641,
+ "mean_token_accuracy": 0.9221750542521476,
+ "num_tokens": 620729.0,
+ "step": 660
+ },
+ {
+ "epoch": 2.264793529161345,
+ "grad_norm": 0.6313159465789795,
+ "learning_rate": 4.8691695108077365e-05,
+ "loss": 0.3923,
+ "mean_token_accuracy": 0.9229970827698708,
+ "num_tokens": 625451.0,
+ "step": 665
+ },
+ {
+ "epoch": 2.2818220519369943,
+ "grad_norm": 0.6566217541694641,
+ "learning_rate": 4.755403868031855e-05,
+ "loss": 0.3404,
+ "mean_token_accuracy": 0.9257871210575104,
+ "num_tokens": 630049.0,
+ "step": 670
+ },
+ {
+ "epoch": 2.2988505747126435,
+ "grad_norm": 0.8146483302116394,
+ "learning_rate": 4.641638225255973e-05,
+ "loss": 0.3499,
+ "mean_token_accuracy": 0.9254049748182297,
+ "num_tokens": 634646.0,
+ "step": 675
+ },
+ {
+ "epoch": 2.315879097488293,
+ "grad_norm": 0.8177068829536438,
+ "learning_rate": 4.527872582480091e-05,
+ "loss": 0.3662,
+ "mean_token_accuracy": 0.9220140025019645,
+ "num_tokens": 639328.0,
+ "step": 680
+ },
+ {
+ "epoch": 2.332907620263942,
+ "grad_norm": 0.7193973660469055,
+ "learning_rate": 4.41410693970421e-05,
+ "loss": 0.3861,
+ "mean_token_accuracy": 0.9194135531783104,
+ "num_tokens": 644122.0,
+ "step": 685
+ },
+ {
+ "epoch": 2.3499361430395913,
+ "grad_norm": 0.8300774693489075,
+ "learning_rate": 4.300341296928328e-05,
+ "loss": 0.3924,
+ "mean_token_accuracy": 0.9165543273091317,
+ "num_tokens": 648957.0,
+ "step": 690
+ },
+ {
+ "epoch": 2.3669646658152406,
+ "grad_norm": 0.6429705023765564,
+ "learning_rate": 4.186575654152446e-05,
+ "loss": 0.3749,
+ "mean_token_accuracy": 0.922352360188961,
+ "num_tokens": 653645.0,
+ "step": 695
+ },
+ {
+ "epoch": 2.38399318859089,
+ "grad_norm": 0.9316811561584473,
+ "learning_rate": 4.0728100113765646e-05,
+ "loss": 0.3731,
+ "mean_token_accuracy": 0.9198509395122528,
+ "num_tokens": 658472.0,
+ "step": 700
+ },
+ {
+ "epoch": 2.401021711366539,
+ "grad_norm": 0.6092661023139954,
+ "learning_rate": 3.959044368600683e-05,
+ "loss": 0.3614,
+ "mean_token_accuracy": 0.9218982830643654,
+ "num_tokens": 663118.0,
+ "step": 705
+ },
+ {
+ "epoch": 2.4180502341421883,
+ "grad_norm": 0.909447968006134,
+ "learning_rate": 3.8452787258248016e-05,
+ "loss": 0.407,
+ "mean_token_accuracy": 0.9137230664491653,
+ "num_tokens": 668024.0,
+ "step": 710
+ },
+ {
+ "epoch": 2.4350787569178376,
+ "grad_norm": 0.6452695727348328,
+ "learning_rate": 3.7315130830489194e-05,
+ "loss": 0.3642,
+ "mean_token_accuracy": 0.9242654070258141,
+ "num_tokens": 672593.0,
+ "step": 715
+ },
+ {
+ "epoch": 2.4521072796934864,
+ "grad_norm": 0.7429100275039673,
+ "learning_rate": 3.617747440273038e-05,
+ "loss": 0.3762,
+ "mean_token_accuracy": 0.9200442656874657,
+ "num_tokens": 677246.0,
+ "step": 720
+ },
+ {
+ "epoch": 2.4691358024691357,
+ "grad_norm": 0.6262103319168091,
+ "learning_rate": 3.5039817974971564e-05,
+ "loss": 0.3631,
+ "mean_token_accuracy": 0.9242240786552429,
+ "num_tokens": 681899.0,
+ "step": 725
+ },
+ {
+ "epoch": 2.486164325244785,
+ "grad_norm": 0.7170459032058716,
+ "learning_rate": 3.390216154721274e-05,
+ "loss": 0.3518,
+ "mean_token_accuracy": 0.9257205232977868,
+ "num_tokens": 686559.0,
+ "step": 730
+ },
+ {
+ "epoch": 2.503192848020434,
+ "grad_norm": 0.7899272441864014,
+ "learning_rate": 3.276450511945393e-05,
+ "loss": 0.3408,
+ "mean_token_accuracy": 0.927695432305336,
+ "num_tokens": 691193.0,
+ "step": 735
+ },
+ {
+ "epoch": 2.5202213707960834,
+ "grad_norm": 0.8176191449165344,
+ "learning_rate": 3.162684869169511e-05,
+ "loss": 0.3554,
+ "mean_token_accuracy": 0.9244274586439133,
+ "num_tokens": 695862.0,
+ "step": 740
+ },
+ {
+ "epoch": 2.5372498935717327,
+ "grad_norm": 0.9307223558425903,
+ "learning_rate": 3.0489192263936294e-05,
+ "loss": 0.3762,
+ "mean_token_accuracy": 0.9196016103029251,
+ "num_tokens": 700732.0,
+ "step": 745
+ },
+ {
+ "epoch": 2.554278416347382,
+ "grad_norm": 0.7519947290420532,
+ "learning_rate": 2.9351535836177476e-05,
+ "loss": 0.37,
+ "mean_token_accuracy": 0.9214758723974228,
+ "num_tokens": 705428.0,
+ "step": 750
+ },
+ {
+ "epoch": 2.571306939123031,
+ "grad_norm": 0.7623237371444702,
+ "learning_rate": 2.8213879408418657e-05,
+ "loss": 0.3496,
+ "mean_token_accuracy": 0.9245725467801094,
+ "num_tokens": 710035.0,
+ "step": 755
+ },
+ {
+ "epoch": 2.58833546189868,
+ "grad_norm": 0.6571420431137085,
+ "learning_rate": 2.7076222980659842e-05,
+ "loss": 0.3662,
+ "mean_token_accuracy": 0.9226716786623002,
+ "num_tokens": 714753.0,
+ "step": 760
+ },
+ {
+ "epoch": 2.6053639846743293,
+ "grad_norm": 0.6745423078536987,
+ "learning_rate": 2.5938566552901024e-05,
+ "loss": 0.3672,
+ "mean_token_accuracy": 0.9193284913897515,
+ "num_tokens": 719410.0,
+ "step": 765
+ },
+ {
+ "epoch": 2.6223925074499785,
+ "grad_norm": 0.9500595927238464,
+ "learning_rate": 2.480091012514221e-05,
+ "loss": 0.3729,
+ "mean_token_accuracy": 0.9209223091602325,
+ "num_tokens": 724210.0,
+ "step": 770
+ },
+ {
+ "epoch": 2.639421030225628,
+ "grad_norm": 0.6964495182037354,
+ "learning_rate": 2.366325369738339e-05,
+ "loss": 0.3505,
+ "mean_token_accuracy": 0.9281451672315597,
+ "num_tokens": 728969.0,
+ "step": 775
+ },
+ {
+ "epoch": 2.656449553001277,
+ "grad_norm": 0.868914008140564,
+ "learning_rate": 2.2525597269624575e-05,
+ "loss": 0.3709,
+ "mean_token_accuracy": 0.9212313622236252,
+ "num_tokens": 733797.0,
+ "step": 780
+ },
+ {
+ "epoch": 2.6734780757769263,
+ "grad_norm": 0.7551370859146118,
+ "learning_rate": 2.138794084186576e-05,
+ "loss": 0.367,
+ "mean_token_accuracy": 0.9220638558268547,
+ "num_tokens": 738487.0,
+ "step": 785
+ },
+ {
+ "epoch": 2.6905065985525756,
+ "grad_norm": 0.7959733009338379,
+ "learning_rate": 2.025028441410694e-05,
+ "loss": 0.3634,
+ "mean_token_accuracy": 0.9227283328771592,
+ "num_tokens": 743145.0,
+ "step": 790
+ },
+ {
+ "epoch": 2.707535121328225,
+ "grad_norm": 0.8846186399459839,
+ "learning_rate": 1.9112627986348127e-05,
+ "loss": 0.3595,
+ "mean_token_accuracy": 0.9253345713019371,
+ "num_tokens": 747814.0,
+ "step": 795
+ },
+ {
+ "epoch": 2.724563644103874,
+ "grad_norm": 0.6306168437004089,
+ "learning_rate": 1.7974971558589308e-05,
+ "loss": 0.3507,
+ "mean_token_accuracy": 0.924257718026638,
+ "num_tokens": 752477.0,
+ "step": 800
+ },
+ {
+ "epoch": 2.7415921668795233,
+ "grad_norm": 0.644291877746582,
+ "learning_rate": 1.683731513083049e-05,
+ "loss": 0.3671,
+ "mean_token_accuracy": 0.9233185186982155,
+ "num_tokens": 757104.0,
+ "step": 805
+ },
+ {
+ "epoch": 2.7586206896551726,
+ "grad_norm": 0.9190324544906616,
+ "learning_rate": 1.5699658703071675e-05,
+ "loss": 0.3623,
+ "mean_token_accuracy": 0.9234949722886086,
+ "num_tokens": 761828.0,
+ "step": 810
+ },
+ {
+ "epoch": 2.775649212430822,
+ "grad_norm": 0.8166772723197937,
+ "learning_rate": 1.4562002275312856e-05,
+ "loss": 0.3567,
+ "mean_token_accuracy": 0.9209295436739922,
+ "num_tokens": 766584.0,
+ "step": 815
+ },
+ {
+ "epoch": 2.792677735206471,
+ "grad_norm": 0.8470193147659302,
+ "learning_rate": 1.342434584755404e-05,
+ "loss": 0.3567,
+ "mean_token_accuracy": 0.9275827333331108,
+ "num_tokens": 771231.0,
+ "step": 820
+ },
+ {
+ "epoch": 2.80970625798212,
+ "grad_norm": 0.828468382358551,
+ "learning_rate": 1.2286689419795223e-05,
+ "loss": 0.3811,
+ "mean_token_accuracy": 0.921853768825531,
+ "num_tokens": 775914.0,
+ "step": 825
+ },
+ {
+ "epoch": 2.826734780757769,
+ "grad_norm": 1.0459518432617188,
+ "learning_rate": 1.1149032992036406e-05,
+ "loss": 0.3735,
+ "mean_token_accuracy": 0.9238664403557777,
+ "num_tokens": 780620.0,
+ "step": 830
+ },
+ {
+ "epoch": 2.8437633035334184,
+ "grad_norm": 0.9584795236587524,
+ "learning_rate": 1.001137656427759e-05,
+ "loss": 0.3815,
+ "mean_token_accuracy": 0.9181834146380424,
+ "num_tokens": 785379.0,
+ "step": 835
+ },
+ {
+ "epoch": 2.8607918263090677,
+ "grad_norm": 0.6356697082519531,
+ "learning_rate": 8.873720136518773e-06,
+ "loss": 0.3654,
+ "mean_token_accuracy": 0.922317098081112,
+ "num_tokens": 789999.0,
+ "step": 840
+ },
+ {
+ "epoch": 2.877820349084717,
+ "grad_norm": 0.7349090576171875,
+ "learning_rate": 7.736063708759956e-06,
+ "loss": 0.3518,
+ "mean_token_accuracy": 0.9259620174765587,
+ "num_tokens": 794652.0,
+ "step": 845
+ },
+ {
+ "epoch": 2.894848871860366,
+ "grad_norm": 0.7430603504180908,
+ "learning_rate": 6.598407281001138e-06,
+ "loss": 0.36,
+ "mean_token_accuracy": 0.9223412945866585,
+ "num_tokens": 799357.0,
+ "step": 850
+ },
+ {
+ "epoch": 2.9118773946360155,
+ "grad_norm": 1.1674597263336182,
+ "learning_rate": 5.4607508532423215e-06,
+ "loss": 0.3746,
+ "mean_token_accuracy": 0.9221721008419991,
+ "num_tokens": 803966.0,
+ "step": 855
+ },
+ {
+ "epoch": 2.9289059174116643,
+ "grad_norm": 0.8011245131492615,
+ "learning_rate": 4.323094425483505e-06,
+ "loss": 0.356,
+ "mean_token_accuracy": 0.9252967059612274,
+ "num_tokens": 808708.0,
+ "step": 860
+ },
+ {
+ "epoch": 2.9459344401873135,
+ "grad_norm": 0.694900631904602,
+ "learning_rate": 3.185437997724687e-06,
+ "loss": 0.3599,
+ "mean_token_accuracy": 0.9245758801698685,
+ "num_tokens": 813443.0,
+ "step": 865
+ },
+ {
+ "epoch": 2.962962962962963,
+ "grad_norm": 0.8267349004745483,
+ "learning_rate": 2.0477815699658705e-06,
+ "loss": 0.3436,
+ "mean_token_accuracy": 0.9228143081068992,
+ "num_tokens": 818266.0,
+ "step": 870
+ },
+ {
+ "epoch": 2.979991485738612,
+ "grad_norm": 0.8551934957504272,
+ "learning_rate": 9.101251422070535e-07,
+ "loss": 0.3602,
+ "mean_token_accuracy": 0.9237398013472558,
+ "num_tokens": 822993.0,
+ "step": 875
+ }
+ ],
+ "logging_steps": 5,
+ "max_steps": 879,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 200,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": true
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 3.74393164074025e+16,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-879/training_args.bin b/checkpoint-879/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d77eaa0f69f97b2b9813f53e641e4a6232bfa34d
--- /dev/null
+++ b/checkpoint-879/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
+size 5624
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fed0491bb0ae0c4f0752f54ffddf7d69269daed
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+ "bos_token": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|im_end|>"
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
+size 17209403
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1dbecde59340b33dcf97ef6087584a5a01208ab5
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,2072 @@
+{
+ "added_tokens_decoder": {
+ "128000": {
+ "content": "<|begin_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128001": {
+ "content": "<|end_of_text|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128002": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128003": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128004": {
+ "content": "<|finetune_right_pad_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128005": {
+ "content": "<|reserved_special_token_2|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128006": {
+ "content": "<|start_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128007": {
+ "content": "<|end_header_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128008": {
+ "content": "<|eom_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128009": {
+ "content": "<|eot_id|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128010": {
+ "content": "<|python_tag|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128011": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128012": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128013": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128014": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128015": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128016": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128017": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128018": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128019": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128020": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128021": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128022": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128023": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128024": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128025": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128026": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128027": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128028": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128029": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128030": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128031": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128032": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128033": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128034": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128035": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128036": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128037": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128038": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128039": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128040": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128041": {
+ "content": "<|reserved_special_token_33|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128042": {
+ "content": "<|reserved_special_token_34|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128043": {
+ "content": "<|reserved_special_token_35|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128044": {
+ "content": "<|reserved_special_token_36|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128045": {
+ "content": "<|reserved_special_token_37|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128046": {
+ "content": "<|reserved_special_token_38|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128047": {
+ "content": "<|reserved_special_token_39|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128048": {
+ "content": "<|reserved_special_token_40|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128049": {
+ "content": "<|reserved_special_token_41|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128050": {
+ "content": "<|reserved_special_token_42|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128051": {
+ "content": "<|reserved_special_token_43|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128052": {
+ "content": "<|reserved_special_token_44|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128053": {
+ "content": "<|reserved_special_token_45|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128054": {
+ "content": "<|reserved_special_token_46|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128055": {
+ "content": "<|reserved_special_token_47|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128056": {
+ "content": "<|reserved_special_token_48|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128057": {
+ "content": "<|reserved_special_token_49|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128058": {
+ "content": "<|reserved_special_token_50|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128059": {
+ "content": "<|reserved_special_token_51|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128060": {
+ "content": "<|reserved_special_token_52|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128061": {
+ "content": "<|reserved_special_token_53|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128062": {
+ "content": "<|reserved_special_token_54|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128063": {
+ "content": "<|reserved_special_token_55|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128064": {
+ "content": "<|reserved_special_token_56|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128065": {
+ "content": "<|reserved_special_token_57|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128066": {
+ "content": "<|reserved_special_token_58|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128067": {
+ "content": "<|reserved_special_token_59|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128068": {
+ "content": "<|reserved_special_token_60|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128069": {
+ "content": "<|reserved_special_token_61|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128070": {
+ "content": "<|reserved_special_token_62|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128071": {
+ "content": "<|reserved_special_token_63|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128072": {
+ "content": "<|reserved_special_token_64|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128073": {
+ "content": "<|reserved_special_token_65|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128074": {
+ "content": "<|reserved_special_token_66|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128075": {
+ "content": "<|reserved_special_token_67|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128076": {
+ "content": "<|reserved_special_token_68|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128077": {
+ "content": "<|reserved_special_token_69|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128078": {
+ "content": "<|reserved_special_token_70|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128079": {
+ "content": "<|reserved_special_token_71|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128080": {
+ "content": "<|reserved_special_token_72|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128081": {
+ "content": "<|reserved_special_token_73|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128082": {
+ "content": "<|reserved_special_token_74|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128083": {
+ "content": "<|reserved_special_token_75|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128084": {
+ "content": "<|reserved_special_token_76|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128085": {
+ "content": "<|reserved_special_token_77|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128086": {
+ "content": "<|reserved_special_token_78|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128087": {
+ "content": "<|reserved_special_token_79|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128088": {
+ "content": "<|reserved_special_token_80|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128089": {
+ "content": "<|reserved_special_token_81|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128090": {
+ "content": "<|reserved_special_token_82|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128091": {
+ "content": "<|reserved_special_token_83|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128092": {
+ "content": "<|reserved_special_token_84|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128093": {
+ "content": "<|reserved_special_token_85|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128094": {
+ "content": "<|reserved_special_token_86|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128095": {
+ "content": "<|reserved_special_token_87|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128096": {
+ "content": "<|reserved_special_token_88|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128097": {
+ "content": "<|reserved_special_token_89|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128098": {
+ "content": "<|reserved_special_token_90|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128099": {
+ "content": "<|reserved_special_token_91|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128100": {
+ "content": "<|reserved_special_token_92|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128101": {
+ "content": "<|reserved_special_token_93|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128102": {
+ "content": "<|reserved_special_token_94|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128103": {
+ "content": "<|reserved_special_token_95|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128104": {
+ "content": "<|reserved_special_token_96|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128105": {
+ "content": "<|reserved_special_token_97|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128106": {
+ "content": "<|reserved_special_token_98|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128107": {
+ "content": "<|reserved_special_token_99|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128108": {
+ "content": "<|reserved_special_token_100|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128109": {
+ "content": "<|reserved_special_token_101|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128110": {
+ "content": "<|reserved_special_token_102|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128111": {
+ "content": "<|reserved_special_token_103|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128112": {
+ "content": "<|reserved_special_token_104|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128113": {
+ "content": "<|reserved_special_token_105|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128114": {
+ "content": "<|reserved_special_token_106|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128115": {
+ "content": "<|reserved_special_token_107|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128116": {
+ "content": "<|reserved_special_token_108|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128117": {
+ "content": "<|reserved_special_token_109|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128118": {
+ "content": "<|reserved_special_token_110|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128119": {
+ "content": "<|reserved_special_token_111|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128120": {
+ "content": "<|reserved_special_token_112|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128121": {
+ "content": "<|reserved_special_token_113|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128122": {
+ "content": "<|reserved_special_token_114|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128123": {
+ "content": "<|reserved_special_token_115|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128124": {
+ "content": "<|reserved_special_token_116|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128125": {
+ "content": "<|reserved_special_token_117|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128126": {
+ "content": "<|reserved_special_token_118|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128127": {
+ "content": "<|reserved_special_token_119|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128128": {
+ "content": "<|reserved_special_token_120|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128129": {
+ "content": "<|reserved_special_token_121|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128130": {
+ "content": "<|reserved_special_token_122|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128131": {
+ "content": "<|reserved_special_token_123|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128132": {
+ "content": "<|reserved_special_token_124|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128133": {
+ "content": "<|reserved_special_token_125|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128134": {
+ "content": "<|reserved_special_token_126|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128135": {
+ "content": "<|reserved_special_token_127|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128136": {
+ "content": "<|reserved_special_token_128|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128137": {
+ "content": "<|reserved_special_token_129|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128138": {
+ "content": "<|reserved_special_token_130|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128139": {
+ "content": "<|reserved_special_token_131|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128140": {
+ "content": "<|reserved_special_token_132|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128141": {
+ "content": "<|reserved_special_token_133|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128142": {
+ "content": "<|reserved_special_token_134|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128143": {
+ "content": "<|reserved_special_token_135|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128144": {
+ "content": "<|reserved_special_token_136|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128145": {
+ "content": "<|reserved_special_token_137|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128146": {
+ "content": "<|reserved_special_token_138|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128147": {
+ "content": "<|reserved_special_token_139|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128148": {
+ "content": "<|reserved_special_token_140|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128149": {
+ "content": "<|reserved_special_token_141|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128150": {
+ "content": "<|reserved_special_token_142|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128151": {
+ "content": "<|reserved_special_token_143|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128152": {
+ "content": "<|reserved_special_token_144|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128153": {
+ "content": "<|reserved_special_token_145|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128154": {
+ "content": "<|reserved_special_token_146|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128155": {
+ "content": "<|reserved_special_token_147|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128156": {
+ "content": "<|reserved_special_token_148|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128157": {
+ "content": "<|reserved_special_token_149|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128158": {
+ "content": "<|reserved_special_token_150|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128159": {
+ "content": "<|reserved_special_token_151|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128160": {
+ "content": "<|reserved_special_token_152|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128161": {
+ "content": "<|reserved_special_token_153|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128162": {
+ "content": "<|reserved_special_token_154|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128163": {
+ "content": "<|reserved_special_token_155|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128164": {
+ "content": "<|reserved_special_token_156|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128165": {
+ "content": "<|reserved_special_token_157|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128166": {
+ "content": "<|reserved_special_token_158|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128167": {
+ "content": "<|reserved_special_token_159|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128168": {
+ "content": "<|reserved_special_token_160|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128169": {
+ "content": "<|reserved_special_token_161|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128170": {
+ "content": "<|reserved_special_token_162|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128171": {
+ "content": "<|reserved_special_token_163|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128172": {
+ "content": "<|reserved_special_token_164|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128173": {
+ "content": "<|reserved_special_token_165|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128174": {
+ "content": "<|reserved_special_token_166|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128175": {
+ "content": "<|reserved_special_token_167|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128176": {
+ "content": "<|reserved_special_token_168|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128177": {
+ "content": "<|reserved_special_token_169|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128178": {
+ "content": "<|reserved_special_token_170|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128179": {
+ "content": "<|reserved_special_token_171|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128180": {
+ "content": "<|reserved_special_token_172|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128181": {
+ "content": "<|reserved_special_token_173|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128182": {
+ "content": "<|reserved_special_token_174|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128183": {
+ "content": "<|reserved_special_token_175|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128184": {
+ "content": "<|reserved_special_token_176|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128185": {
+ "content": "<|reserved_special_token_177|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128186": {
+ "content": "<|reserved_special_token_178|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128187": {
+ "content": "<|reserved_special_token_179|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128188": {
+ "content": "<|reserved_special_token_180|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128189": {
+ "content": "<|reserved_special_token_181|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128190": {
+ "content": "<|reserved_special_token_182|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128191": {
+ "content": "<|reserved_special_token_183|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128192": {
+ "content": "<|reserved_special_token_184|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128193": {
+ "content": "<|reserved_special_token_185|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128194": {
+ "content": "<|reserved_special_token_186|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128195": {
+ "content": "<|reserved_special_token_187|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128196": {
+ "content": "<|reserved_special_token_188|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128197": {
+ "content": "<|reserved_special_token_189|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128198": {
+ "content": "<|reserved_special_token_190|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128199": {
+ "content": "<|reserved_special_token_191|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128200": {
+ "content": "<|reserved_special_token_192|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128201": {
+ "content": "<|reserved_special_token_193|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128202": {
+ "content": "<|reserved_special_token_194|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128203": {
+ "content": "<|reserved_special_token_195|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128204": {
+ "content": "<|reserved_special_token_196|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128205": {
+ "content": "<|reserved_special_token_197|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128206": {
+ "content": "<|reserved_special_token_198|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128207": {
+ "content": "<|reserved_special_token_199|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128208": {
+ "content": "<|reserved_special_token_200|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128209": {
+ "content": "<|reserved_special_token_201|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128210": {
+ "content": "<|reserved_special_token_202|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128211": {
+ "content": "<|reserved_special_token_203|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128212": {
+ "content": "<|reserved_special_token_204|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128213": {
+ "content": "<|reserved_special_token_205|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128214": {
+ "content": "<|reserved_special_token_206|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128215": {
+ "content": "<|reserved_special_token_207|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128216": {
+ "content": "<|reserved_special_token_208|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128217": {
+ "content": "<|reserved_special_token_209|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128218": {
+ "content": "<|reserved_special_token_210|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128219": {
+ "content": "<|reserved_special_token_211|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128220": {
+ "content": "<|reserved_special_token_212|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128221": {
+ "content": "<|reserved_special_token_213|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128222": {
+ "content": "<|reserved_special_token_214|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128223": {
+ "content": "<|reserved_special_token_215|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128224": {
+ "content": "<|reserved_special_token_216|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128225": {
+ "content": "<|reserved_special_token_217|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128226": {
+ "content": "<|reserved_special_token_218|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128227": {
+ "content": "<|reserved_special_token_219|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128228": {
+ "content": "<|reserved_special_token_220|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128229": {
+ "content": "<|reserved_special_token_221|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128230": {
+ "content": "<|reserved_special_token_222|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128231": {
+ "content": "<|reserved_special_token_223|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128232": {
+ "content": "<|reserved_special_token_224|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128233": {
+ "content": "<|reserved_special_token_225|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128234": {
+ "content": "<|reserved_special_token_226|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128235": {
+ "content": "<|reserved_special_token_227|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128236": {
+ "content": "<|reserved_special_token_228|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128237": {
+ "content": "<|reserved_special_token_229|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128238": {
+ "content": "<|reserved_special_token_230|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128239": {
+ "content": "<|reserved_special_token_231|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128240": {
+ "content": "<|reserved_special_token_232|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128241": {
+ "content": "<|reserved_special_token_233|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128242": {
+ "content": "<|reserved_special_token_234|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128243": {
+ "content": "<|reserved_special_token_235|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128244": {
+ "content": "<|reserved_special_token_236|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128245": {
+ "content": "<|reserved_special_token_237|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128246": {
+ "content": "<|reserved_special_token_238|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128247": {
+ "content": "<|reserved_special_token_239|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128248": {
+ "content": "<|reserved_special_token_240|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128249": {
+ "content": "<|reserved_special_token_241|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128250": {
+ "content": "<|reserved_special_token_242|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128251": {
+ "content": "<|reserved_special_token_243|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128252": {
+ "content": "<|reserved_special_token_244|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128253": {
+ "content": "<|reserved_special_token_245|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128254": {
+ "content": "<|reserved_special_token_246|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "128255": {
+ "content": "<|reserved_special_token_247|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|begin_of_text|>",
+ "chat_template": [
+ {
+ "name": "default",
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+ },
+ {
+ "name": "tool_use",
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" \" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within XML tags as follows:\n\" }}\n{{- \"\n\" }}\n{{- '{\"name\": , \"arguments\": }\n' }}\n{{- '<|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- else %}\n {{- '\n' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+ }
+ ],
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|im_end|>",
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 131072,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}