Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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-313/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+model_name: qwen_text2sql_sft_lora
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for qwen_text2sql_sft_lora
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.19.1
+- TRL: 1.3.0
+- Transformers: 5.8.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.8.5
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e8ac9e937b0b224193945ba3e26ce2e351206456425e4e254bafec0073ae9b
+size 275342392

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-313/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[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 0.19.1

checkpoint-313/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-313/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e8ac9e937b0b224193945ba3e26ce2e351206456425e4e254bafec0073ae9b
+size 275342392

checkpoint-313/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-313/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7266f81b5507c89b0eeba59009ca830cbf3d0d364db1a765a615fc8384d8e9e
+size 280363173

checkpoint-313/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06549d0ed8b889e8d3eaef12f422b710b4a8fcea47c1a9d877a910c4ee61451c
+size 14645

checkpoint-313/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4500bbbe9a63aee1fe12ea8707fbc415e0287ab582d921b1f6fa97f386a06a1f
+size 1465

checkpoint-313/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-313/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-313/trainer_state.json

@@ -0,0 +1,355 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 313,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.09649655148386956,
+      "epoch": 0.032,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 0.00018,
+      "loss": 0.14522699117660523,
+      "mean_token_accuracy": 0.9369595624506474,
+      "num_tokens": 66476.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.08880856377654708,
+      "epoch": 0.064,
+      "grad_norm": 0.173828125,
+      "learning_rate": 0.0001995649347969019,
+      "loss": 0.08154842257499695,
+      "mean_token_accuracy": 0.9461333908140659,
+      "num_tokens": 140569.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.08434813401545398,
+      "epoch": 0.096,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.0001980658652386421,
+      "loss": 0.08437747955322265,
+      "mean_token_accuracy": 0.9686024446040392,
+      "num_tokens": 204086.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.0869230936281383,
+      "epoch": 0.128,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 0.0001955135170885202,
+      "loss": 0.07795352935791015,
+      "mean_token_accuracy": 0.9808623071759939,
+      "num_tokens": 271252.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.07329072935972362,
+      "epoch": 0.16,
+      "grad_norm": 0.19140625,
+      "learning_rate": 0.00019193530389822363,
+      "loss": 0.08132061958312989,
+      "mean_token_accuracy": 0.9672858133912087,
+      "num_tokens": 337656.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.0891664584632963,
+      "epoch": 0.192,
+      "grad_norm": 0.17578125,
+      "learning_rate": 0.00018736965754556528,
+      "loss": 0.09287956953048707,
+      "mean_token_accuracy": 0.9650922071188688,
+      "num_tokens": 410305.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.07671013890067116,
+      "epoch": 0.224,
+      "grad_norm": 0.203125,
+      "learning_rate": 0.00018186561545605054,
+      "loss": 0.07794617414474488,
+      "mean_token_accuracy": 0.9760642010718584,
+      "num_tokens": 477217.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.0767284018744249,
+      "epoch": 0.256,
+      "grad_norm": 0.123046875,
+      "learning_rate": 0.00017548229391532572,
+      "loss": 0.08190351128578185,
+      "mean_token_accuracy": 0.9707993991672993,
+      "num_tokens": 549230.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.0770263057667762,
+      "epoch": 0.288,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.00016828825312940592,
+      "loss": 0.06415510773658753,
+      "mean_token_accuracy": 0.9708753030747175,
+      "num_tokens": 616669.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.06914123268215917,
+      "epoch": 0.32,
+      "grad_norm": 0.13671875,
+      "learning_rate": 0.00016036076085226814,
+      "loss": 0.07777998447418213,
+      "mean_token_accuracy": 0.9653518848121166,
+      "num_tokens": 686556.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06991175076691433,
+      "epoch": 0.352,
+      "grad_norm": 0.166015625,
+      "learning_rate": 0.00015178496248983254,
+      "loss": 0.07323018312454224,
+      "mean_token_accuracy": 0.9576951999217271,
+      "num_tokens": 759521.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.09207692868367304,
+      "epoch": 0.384,
+      "grad_norm": 0.21484375,
+      "learning_rate": 0.00014265296659384956,
+      "loss": 0.09533499479293824,
+      "mean_token_accuracy": 0.9764811851084232,
+      "num_tokens": 826869.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.08726739198318682,
+      "epoch": 0.416,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00013306285556796495,
+      "loss": 0.08955158591270447,
+      "mean_token_accuracy": 0.956151831895113,
+      "num_tokens": 898111.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.06639394556113984,
+      "epoch": 0.448,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 0.000123117632211497,
+      "loss": 0.06314496397972107,
+      "mean_token_accuracy": 0.9615629483014345,
+      "num_tokens": 969339.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.0558678554254584,
+      "epoch": 0.48,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.0001129241134155949,
+      "loss": 0.06386124491691589,
+      "mean_token_accuracy": 0.9733367815613747,
+      "num_tokens": 1036672.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.060232574946712705,
+      "epoch": 0.512,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00010259178289406011,
+      "loss": 0.06906680464744568,
+      "mean_token_accuracy": 0.9617645684629679,
+      "num_tokens": 1108529.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.06748775953310542,
+      "epoch": 0.544,
+      "grad_norm": 0.14453125,
+      "learning_rate": 9.223161527109937e-05,
+      "loss": 0.06768612861633301,
+      "mean_token_accuracy": 0.9634172908961773,
+      "num_tokens": 1184675.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.06814730220357887,
+      "epoch": 0.576,
+      "grad_norm": 0.185546875,
+      "learning_rate": 8.195488415592238e-05,
+      "loss": 0.06328855752944947,
+      "mean_token_accuracy": 0.9700407199561596,
+      "num_tokens": 1256207.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.07081062349316199,
+      "epoch": 0.608,
+      "grad_norm": 0.55859375,
+      "learning_rate": 7.187196700608373e-05,
+      "loss": 0.06718837618827819,
+      "mean_token_accuracy": 0.9618636917322874,
+      "num_tokens": 1328169.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.06150082344538532,
+      "epoch": 0.64,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 6.209115961596208e-05,
+      "loss": 0.05759283900260925,
+      "mean_token_accuracy": 0.9679569214582443,
+      "num_tokens": 1399956.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.06286092348891544,
+      "epoch": 0.672,
+      "grad_norm": 0.197265625,
+      "learning_rate": 5.271751296338823e-05,
+      "loss": 0.06326322555541992,
+      "mean_token_accuracy": 0.9615916445851326,
+      "num_tokens": 1475214.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.0519205622273148,
+      "epoch": 0.704,
+      "grad_norm": 0.169921875,
+      "learning_rate": 4.385170490729712e-05,
+      "loss": 0.05610005855560303,
+      "mean_token_accuracy": 0.972290551662445,
+      "num_tokens": 1546118.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.058427285050856884,
+      "epoch": 0.736,
+      "grad_norm": 0.224609375,
+      "learning_rate": 3.558895885496023e-05,
+      "loss": 0.05968340039253235,
+      "mean_token_accuracy": 0.9686542131006718,
+      "num_tokens": 1620482.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.06077302123012487,
+      "epoch": 0.768,
+      "grad_norm": 0.115234375,
+      "learning_rate": 2.8018021012875994e-05,
+      "loss": 0.05487210750579834,
+      "mean_token_accuracy": 0.9765994187444449,
+      "num_tokens": 1686508.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.05762897890235763,
+      "epoch": 0.8,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 2.1220207206178688e-05,
+      "loss": 0.06742877364158631,
+      "mean_token_accuracy": 0.9620399903506041,
+      "num_tokens": 1764710.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.059268097168387615,
+      "epoch": 0.832,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.526852950422226e-05,
+      "loss": 0.058321452140808104,
+      "mean_token_accuracy": 0.9726373586803675,
+      "num_tokens": 1832644.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.05387882571376394,
+      "epoch": 0.864,
+      "grad_norm": 0.1796875,
+      "learning_rate": 1.0226912032836611e-05,
+      "loss": 0.04902423620223999,
+      "mean_token_accuracy": 0.9753172263503075,
+      "num_tokens": 1901629.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.05652731657464756,
+      "epoch": 0.896,
+      "grad_norm": 0.322265625,
+      "learning_rate": 6.149504395842087e-06,
+      "loss": 0.0603355348110199,
+      "mean_token_accuracy": 0.9647678934037686,
+      "num_tokens": 1975257.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.05044347028888296,
+      "epoch": 0.928,
+      "grad_norm": 0.1484375,
+      "learning_rate": 3.0801000800333877e-06,
+      "loss": 0.04434172809123993,
+      "mean_token_accuracy": 0.970330499112606,
+      "num_tokens": 2042770.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.05634855758107733,
+      "epoch": 0.96,
+      "grad_norm": 0.123046875,
+      "learning_rate": 1.0516660902673448e-06,
+      "loss": 0.053922271728515624,
+      "mean_token_accuracy": 0.9622644379734993,
+      "num_tokens": 2111795.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.06218618047278142,
+      "epoch": 0.992,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 8.598886661895788e-08,
+      "loss": 0.06558623909950256,
+      "mean_token_accuracy": 0.9811610858887434,
+      "num_tokens": 2182727.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.10073611672315747,
+      "eval_loss": 0.283896803855896,
+      "eval_mean_token_accuracy": 0.931689467549324,
+      "eval_num_tokens": 2202446.0,
+      "eval_runtime": 135.118,
+      "eval_samples_per_second": 3.7,
+      "eval_steps_per_second": 3.7,
+      "step": 313
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 313,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.867113674568868e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-313/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403b3a517ff68b9bb70036fa98c8629d7bf3a4c3941f1be3dfd823e2f0fadbe3
+size 6417

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403b3a517ff68b9bb70036fa98c8629d7bf3a4c3941f1be3dfd823e2f0fadbe3
+size 6417