Upload QLoRA adapter weights

README.md

@@ -0,0 +1,202 @@
+---
+base_model: codellama/CodeLlama-7b-instruct-hf
+library_name: peft
+---
+
+# 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 0.14.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-instruct-hf",
+  "bias": "none",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8446036065ff2f0be76f75031b1044732266f50acc29d56d595ee47dddd50e85
+size 67143296

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a7ebb99baed0d51065168635a51c29c3c7f799625f6ad2046a04f858f7e497
+size 34380773

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9bed399efd8c5af12072924ce01df290bc1d60dfd38f09ec138eaef3884960
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41b658887e47f1ae7d010e5406b550d64c223bdb32c754d56d1055bb43fb40b
+size 1465

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "extra_special_tokens": {},
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,453 @@
+{
+  "best_metric": 0.040135130286216736,
+  "best_model_checkpoint": "/content/qlora_vuln_model/checkpoint-500",
+  "epoch": 0.9995294117647059,
+  "eval_steps": 100,
+  "global_step": 531,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018823529411764704,
+      "grad_norm": 10.599871635437012,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 24.749,
+      "step": 10
+    },
+    {
+      "epoch": 0.03764705882352941,
+      "grad_norm": 12.27408218383789,
+      "learning_rate": 7.037037037037038e-05,
+      "loss": 21.6719,
+      "step": 20
+    },
+    {
+      "epoch": 0.05647058823529412,
+      "grad_norm": 8.119482040405273,
+      "learning_rate": 9.999611462404875e-05,
+      "loss": 15.8453,
+      "step": 30
+    },
+    {
+      "epoch": 0.07529411764705882,
+      "grad_norm": 6.152805805206299,
+      "learning_rate": 9.986018985905901e-05,
+      "loss": 8.853,
+      "step": 40
+    },
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 3.1945641040802,
+      "learning_rate": 9.953059972065265e-05,
+      "loss": 5.7261,
+      "step": 50
+    },
+    {
+      "epoch": 0.11294117647058824,
+      "grad_norm": 4.127964496612549,
+      "learning_rate": 9.900862439242719e-05,
+      "loss": 4.4831,
+      "step": 60
+    },
+    {
+      "epoch": 0.13176470588235295,
+      "grad_norm": 4.9141082763671875,
+      "learning_rate": 9.829629131445342e-05,
+      "loss": 3.5453,
+      "step": 70
+    },
+    {
+      "epoch": 0.15058823529411763,
+      "grad_norm": 5.234217166900635,
+      "learning_rate": 9.73963673083566e-05,
+      "loss": 2.6558,
+      "step": 80
+    },
+    {
+      "epoch": 0.16941176470588235,
+      "grad_norm": 5.785156726837158,
+      "learning_rate": 9.631234783051544e-05,
+      "loss": 2.1081,
+      "step": 90
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 4.8869309425354,
+      "learning_rate": 9.504844339512095e-05,
+      "loss": 1.6306,
+      "step": 100
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "eval_loss": 0.09413356333971024,
+      "eval_runtime": 1659.6813,
+      "eval_samples_per_second": 0.904,
+      "eval_steps_per_second": 0.904,
+      "step": 100
+    },
+    {
+      "epoch": 0.20705882352941177,
+      "grad_norm": 5.362945556640625,
+      "learning_rate": 9.360956321983028e-05,
+      "loss": 1.3676,
+      "step": 110
+    },
+    {
+      "epoch": 0.22588235294117648,
+      "grad_norm": 3.2882444858551025,
+      "learning_rate": 9.200129615753859e-05,
+      "loss": 1.2626,
+      "step": 120
+    },
+    {
+      "epoch": 0.2447058823529412,
+      "grad_norm": 4.0295610427856445,
+      "learning_rate": 9.022988898833342e-05,
+      "loss": 1.1255,
+      "step": 130
+    },
+    {
+      "epoch": 0.2635294117647059,
+      "grad_norm": 3.485719680786133,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.003,
+      "step": 140
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 5.177315711975098,
+      "learning_rate": 8.622578304296364e-05,
+      "loss": 0.9306,
+      "step": 150
+    },
+    {
+      "epoch": 0.30117647058823527,
+      "grad_norm": 3.201077938079834,
+      "learning_rate": 8.400863688854597e-05,
+      "loss": 0.9209,
+      "step": 160
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.020800828933716,
+      "learning_rate": 8.1659395461707e-05,
+      "loss": 0.8847,
+      "step": 170
+    },
+    {
+      "epoch": 0.3388235294117647,
+      "grad_norm": 2.2553532123565674,
+      "learning_rate": 7.91871836117395e-05,
+      "loss": 0.8919,
+      "step": 180
+    },
+    {
+      "epoch": 0.35764705882352943,
+      "grad_norm": 2.698606014251709,
+      "learning_rate": 7.660160382576683e-05,
+      "loss": 0.7767,
+      "step": 190
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 3.7030203342437744,
+      "learning_rate": 7.391269893106592e-05,
+      "loss": 0.7816,
+      "step": 200
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "eval_loss": 0.049124155193567276,
+      "eval_runtime": 1662.6885,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.902,
+      "step": 200
+    },
+    {
+      "epoch": 0.3952941176470588,
+      "grad_norm": 2.39546275138855,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.7294,
+      "step": 210
+    },
+    {
+      "epoch": 0.41411764705882353,
+      "grad_norm": 1.8437654972076416,
+      "learning_rate": 6.826705121831976e-05,
+      "loss": 0.7932,
+      "step": 220
+    },
+    {
+      "epoch": 0.4329411764705882,
+      "grad_norm": 3.2156364917755127,
+      "learning_rate": 6.533223704666672e-05,
+      "loss": 0.7796,
+      "step": 230
+    },
+    {
+      "epoch": 0.45176470588235296,
+      "grad_norm": 3.9197657108306885,
+      "learning_rate": 6.233786988451468e-05,
+      "loss": 0.7135,
+      "step": 240
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.7182209491729736,
+      "learning_rate": 5.9295580358145744e-05,
+      "loss": 0.772,
+      "step": 250
+    },
+    {
+      "epoch": 0.4894117647058824,
+      "grad_norm": 1.3930495977401733,
+      "learning_rate": 5.621718523237427e-05,
+      "loss": 0.7166,
+      "step": 260
+    },
+    {
+      "epoch": 0.508235294117647,
+      "grad_norm": 2.4380180835723877,
+      "learning_rate": 5.311464151224261e-05,
+      "loss": 0.7207,
+      "step": 270
+    },
+    {
+      "epoch": 0.5270588235294118,
+      "grad_norm": 2.6220102310180664,
+      "learning_rate": 5e-05,
+      "loss": 0.711,
+      "step": 280
+    },
+    {
+      "epoch": 0.5458823529411765,
+      "grad_norm": 1.6312707662582397,
+      "learning_rate": 4.68853584877574e-05,
+      "loss": 0.705,
+      "step": 290
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 2.2927358150482178,
+      "learning_rate": 4.378281476762576e-05,
+      "loss": 0.68,
+      "step": 300
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "eval_loss": 0.043063607066869736,
+      "eval_runtime": 1659.8453,
+      "eval_samples_per_second": 0.904,
+      "eval_steps_per_second": 0.904,
+      "step": 300
+    },
+    {
+      "epoch": 0.5835294117647059,
+      "grad_norm": 2.068061590194702,
+      "learning_rate": 4.0704419641854274e-05,
+      "loss": 0.7047,
+      "step": 310
+    },
+    {
+      "epoch": 0.6023529411764705,
+      "grad_norm": 1.5260778665542603,
+      "learning_rate": 3.7662130115485314e-05,
+      "loss": 0.6668,
+      "step": 320
+    },
+    {
+      "epoch": 0.6211764705882353,
+      "grad_norm": 1.9088001251220703,
+      "learning_rate": 3.4667762953333295e-05,
+      "loss": 0.6768,
+      "step": 330
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.6153029203414917,
+      "learning_rate": 3.173294878168025e-05,
+      "loss": 0.6679,
+      "step": 340
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 1.6346434354782104,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.6432,
+      "step": 350
+    },
+    {
+      "epoch": 0.6776470588235294,
+      "grad_norm": 2.301887273788452,
+      "learning_rate": 2.6087301068934106e-05,
+      "loss": 0.6596,
+      "step": 360
+    },
+    {
+      "epoch": 0.6964705882352941,
+      "grad_norm": 1.4241043329238892,
+      "learning_rate": 2.3398396174233178e-05,
+      "loss": 0.646,
+      "step": 370
+    },
+    {
+      "epoch": 0.7152941176470589,
+      "grad_norm": 1.6611512899398804,
+      "learning_rate": 2.0812816388260518e-05,
+      "loss": 0.646,
+      "step": 380
+    },
+    {
+      "epoch": 0.7341176470588235,
+      "grad_norm": 1.8180968761444092,
+      "learning_rate": 1.8340604538293015e-05,
+      "loss": 0.6794,
+      "step": 390
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 1.842568039894104,
+      "learning_rate": 1.599136311145402e-05,
+      "loss": 0.6595,
+      "step": 400
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "eval_loss": 0.0410185307264328,
+      "eval_runtime": 1654.6683,
+      "eval_samples_per_second": 0.907,
+      "eval_steps_per_second": 0.907,
+      "step": 400
+    },
+    {
+      "epoch": 0.7717647058823529,
+      "grad_norm": 1.68463134765625,
+      "learning_rate": 1.3774216957036367e-05,
+      "loss": 0.6562,
+      "step": 410
+    },
+    {
+      "epoch": 0.7905882352941176,
+      "grad_norm": 1.7055809497833252,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.667,
+      "step": 420
+    },
+    {
+      "epoch": 0.8094117647058824,
+      "grad_norm": 1.723899245262146,
+      "learning_rate": 9.770111011666583e-06,
+      "loss": 0.6825,
+      "step": 430
+    },
+    {
+      "epoch": 0.8282352941176471,
+      "grad_norm": 1.6462485790252686,
+      "learning_rate": 7.998703842461431e-06,
+      "loss": 0.6474,
+      "step": 440
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 2.414433717727661,
+      "learning_rate": 6.390436780169734e-06,
+      "loss": 0.6615,
+      "step": 450
+    },
+    {
+      "epoch": 0.8658823529411764,
+      "grad_norm": 1.415352463722229,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 0.6418,
+      "step": 460
+    },
+    {
+      "epoch": 0.8847058823529412,
+      "grad_norm": 1.53042733669281,
+      "learning_rate": 3.687652169484568e-06,
+      "loss": 0.6491,
+      "step": 470
+    },
+    {
+      "epoch": 0.9035294117647059,
+      "grad_norm": 2.4654157161712646,
+      "learning_rate": 2.603632691643415e-06,
+      "loss": 0.6648,
+      "step": 480
+    },
+    {
+      "epoch": 0.9223529411764706,
+      "grad_norm": 1.743988037109375,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6416,
+      "step": 490
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 1.802857756614685,
+      "learning_rate": 9.913756075728087e-07,
+      "loss": 0.6335,
+      "step": 500
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "eval_loss": 0.040135130286216736,
+      "eval_runtime": 1659.3157,
+      "eval_samples_per_second": 0.904,
+      "eval_steps_per_second": 0.904,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6982253789901733,
+      "learning_rate": 4.6940027934735954e-07,
+      "loss": 0.628,
+      "step": 510
+    },
+    {
+      "epoch": 0.9788235294117648,
+      "grad_norm": 1.3386036157608032,
+      "learning_rate": 1.3981014094099353e-07,
+      "loss": 0.6857,
+      "step": 520
+    },
+    {
+      "epoch": 0.9976470588235294,
+      "grad_norm": 2.097684621810913,
+      "learning_rate": 3.885375951256931e-09,
+      "loss": 0.6498,
+      "step": 530
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 531,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3002607472723558e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61259e410b22cb91b2149a275febf34afe98e4128a8f56483c148f55279135a2
+size 6033