Upload DeepCoder14B_DSPy LoRA adapter checkpoint

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: agentica-org/DeepCoder-14B-Preview
+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 0.15.2

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "agentica-org/DeepCoder-14B-Preview",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "lm_head",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229486ce1d4253a54d0cd47c5005c0eacd850b87a95cd3216a73e019d10945c6
+size 6799256256

chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5062a362186c064ec8701c9f44214104908f82eb3da4e29d6a4dcd1e277acdcb
+size 6519149878

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7642d4d8677c028eb706576fdd39c921ffb1007ec52044603d519b96b28ba821
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f276f737c8546acf52b47aa0a82341e11a9aa193441ce56e73d93c1135b634
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_global_step": 275,
+  "best_metric": 0.9421520233154297,
+  "best_model_checkpoint": "./dspy-8bit-lora-deepcoder-safe/checkpoint-275",
+  "epoch": 1.9415929203539823,
+  "eval_steps": 25,
+  "global_step": 275,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 0.6848811507225037,
+      "learning_rate": 4.8e-05,
+      "loss": 1.9452,
+      "mean_token_accuracy": 0.5935992772877217,
+      "num_tokens": 53941.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "eval_loss": 1.9623712301254272,
+      "eval_mean_token_accuracy": 0.6255391545593738,
+      "eval_num_tokens": 53941.0,
+      "eval_runtime": 96.8734,
+      "eval_samples_per_second": 2.065,
+      "eval_steps_per_second": 2.065,
+      "step": 25
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 5.549977779388428,
+      "learning_rate": 9.8e-05,
+      "loss": 1.4238,
+      "mean_token_accuracy": 0.6662441535294056,
+      "num_tokens": 110474.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "eval_loss": 1.394215703010559,
+      "eval_mean_token_accuracy": 0.6895178978145122,
+      "eval_num_tokens": 110474.0,
+      "eval_runtime": 96.6623,
+      "eval_samples_per_second": 2.069,
+      "eval_steps_per_second": 2.069,
+      "step": 50
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.6720989942550659,
+      "learning_rate": 0.000148,
+      "loss": 1.198,
+      "mean_token_accuracy": 0.7074533948302268,
+      "num_tokens": 162407.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "eval_loss": 1.203566074371338,
+      "eval_mean_token_accuracy": 0.7197688557207584,
+      "eval_num_tokens": 162407.0,
+      "eval_runtime": 97.3608,
+      "eval_samples_per_second": 2.054,
+      "eval_steps_per_second": 2.054,
+      "step": 75
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.5576093792915344,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.0969,
+      "mean_token_accuracy": 0.7274327605962754,
+      "num_tokens": 225140.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "eval_loss": 1.1339093446731567,
+      "eval_mean_token_accuracy": 0.7314411370456219,
+      "eval_num_tokens": 225140.0,
+      "eval_runtime": 98.1154,
+      "eval_samples_per_second": 2.038,
+      "eval_steps_per_second": 2.038,
+      "step": 100
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.5583345293998718,
+      "learning_rate": 0.0001852760736196319,
+      "loss": 1.0369,
+      "mean_token_accuracy": 0.7487157288193703,
+      "num_tokens": 285818.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "eval_loss": 1.0866804122924805,
+      "eval_mean_token_accuracy": 0.739626374989748,
+      "eval_num_tokens": 285818.0,
+      "eval_runtime": 97.5506,
+      "eval_samples_per_second": 2.05,
+      "eval_steps_per_second": 2.05,
+      "step": 125
+    },
+    {
+      "epoch": 1.056637168141593,
+      "grad_norm": 1.0887213945388794,
+      "learning_rate": 0.00016993865030674846,
+      "loss": 0.9094,
+      "mean_token_accuracy": 0.767275901492109,
+      "num_tokens": 338145.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.056637168141593,
+      "eval_loss": 1.091628074645996,
+      "eval_mean_token_accuracy": 0.7472012284398079,
+      "eval_num_tokens": 338145.0,
+      "eval_runtime": 97.9463,
+      "eval_samples_per_second": 2.042,
+      "eval_steps_per_second": 2.042,
+      "step": 150
+    },
+    {
+      "epoch": 1.2336283185840708,
+      "grad_norm": 1.2973228693008423,
+      "learning_rate": 0.00015460122699386504,
+      "loss": 0.7983,
+      "mean_token_accuracy": 0.786946276128292,
+      "num_tokens": 395324.0,
+      "step": 175
+    },
+    {
+      "epoch": 1.2336283185840708,
+      "eval_loss": 1.0309680700302124,
+      "eval_mean_token_accuracy": 0.7567924955487251,
+      "eval_num_tokens": 395324.0,
+      "eval_runtime": 97.3557,
+      "eval_samples_per_second": 2.054,
+      "eval_steps_per_second": 2.054,
+      "step": 175
+    },
+    {
+      "epoch": 1.4106194690265488,
+      "grad_norm": 0.8981689810752869,
+      "learning_rate": 0.00013926380368098159,
+      "loss": 0.8004,
+      "mean_token_accuracy": 0.7892016369104385,
+      "num_tokens": 453392.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.4106194690265488,
+      "eval_loss": 1.0047160387039185,
+      "eval_mean_token_accuracy": 0.7607714273035526,
+      "eval_num_tokens": 453392.0,
+      "eval_runtime": 97.3422,
+      "eval_samples_per_second": 2.055,
+      "eval_steps_per_second": 2.055,
+      "step": 200
+    },
+    {
+      "epoch": 1.5876106194690265,
+      "grad_norm": 1.3156253099441528,
+      "learning_rate": 0.00012392638036809816,
+      "loss": 0.7496,
+      "mean_token_accuracy": 0.800215690433979,
+      "num_tokens": 513773.0,
+      "step": 225
+    },
+    {
+      "epoch": 1.5876106194690265,
+      "eval_loss": 0.9816662073135376,
+      "eval_mean_token_accuracy": 0.7670722763240337,
+      "eval_num_tokens": 513773.0,
+      "eval_runtime": 98.5747,
+      "eval_samples_per_second": 2.029,
+      "eval_steps_per_second": 2.029,
+      "step": 225
+    },
+    {
+      "epoch": 1.7646017699115044,
+      "grad_norm": 0.7007508277893066,
+      "learning_rate": 0.00010858895705521473,
+      "loss": 0.7315,
+      "mean_token_accuracy": 0.805658475458622,
+      "num_tokens": 571382.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.7646017699115044,
+      "eval_loss": 0.95888352394104,
+      "eval_mean_token_accuracy": 0.7721423482894898,
+      "eval_num_tokens": 571382.0,
+      "eval_runtime": 97.9779,
+      "eval_samples_per_second": 2.041,
+      "eval_steps_per_second": 2.041,
+      "step": 250
+    },
+    {
+      "epoch": 1.9415929203539823,
+      "grad_norm": 0.8127393126487732,
+      "learning_rate": 9.325153374233129e-05,
+      "loss": 0.7173,
+      "mean_token_accuracy": 0.8105942443013191,
+      "num_tokens": 628449.0,
+      "step": 275
+    },
+    {
+      "epoch": 1.9415929203539823,
+      "eval_loss": 0.9421520233154297,
+      "eval_mean_token_accuracy": 0.7754264496266842,
+      "eval_num_tokens": 628449.0,
+      "eval_runtime": 97.1509,
+      "eval_samples_per_second": 2.059,
+      "eval_steps_per_second": 2.059,
+      "step": 275
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 426,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.329544702974157e+16,
+  "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 sha256:7464b1925680aabc465131e3ad7e77f68d790607b939f26d2e645998254158cd
+size 5688