Upload folder using huggingface_hub

.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

@@ -1,3 +1,208 @@
----
-license: apache-2.0
----
+---
+base_model: Qwen/Qwen2.5-VL-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-VL-3B-Instruct
+- lora
+- sft
+- 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 0.17.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": 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 sha256:0dd17437e1a6f8e42009d455efb426908f73785303951a9d710880e1e9cd4f70
+size 7396336

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d3815570d9e843c80ccf26b3d8a9a82b2ae4c9167d90abf4e3f02b6d7b993a
+size 14868666

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538895d153b0b7fa60530388758d4e21b062fdd1a2250eb7883579b715ce43de
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f86f0e0c6da5a463b023c18e9da657a3e1f176ecb68ca174094bb6423a74c41
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "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:ba0c439f7be467bf47d12a7e6f9adc6116201056fc60c67f431c679b7c16afc8
+size 11422064

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,376 @@
+{
+  "best_global_step": 180,
+  "best_metric": 0.9137479662895203,
+  "best_model_checkpoint": "/content/drive/MyDrive/tez-bildiri/qwen2.5-3b-instruct-trl-sft-mimic-cxr/checkpoint-180",
+  "epoch": 0.23502529786192264,
+  "eval_steps": 10,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013056960992329036,
+      "grad_norm": 8.122729301452637,
+      "learning_rate": 0.0002,
+      "loss": 25.0274,
+      "mean_token_accuracy": 0.49861262924969196,
+      "num_tokens": 172741.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.013056960992329036,
+      "eval_loss": 2.7354915142059326,
+      "eval_mean_token_accuracy": 0.5200360960499736,
+      "eval_num_tokens": 172741.0,
+      "eval_runtime": 583.8163,
+      "eval_samples_per_second": 5.247,
+      "eval_steps_per_second": 1.312,
+      "step": 10
+    },
+    {
+      "epoch": 0.026113921984658072,
+      "grad_norm": 9.37191104888916,
+      "learning_rate": 0.0002,
+      "loss": 20.059,
+      "mean_token_accuracy": 0.5394352838397026,
+      "num_tokens": 345170.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.026113921984658072,
+      "eval_loss": 2.262531280517578,
+      "eval_mean_token_accuracy": 0.5700084223915329,
+      "eval_num_tokens": 345170.0,
+      "eval_runtime": 584.3785,
+      "eval_samples_per_second": 5.241,
+      "eval_steps_per_second": 1.311,
+      "step": 20
+    },
+    {
+      "epoch": 0.039170882976987106,
+      "grad_norm": 8.885587692260742,
+      "learning_rate": 0.0002,
+      "loss": 16.4452,
+      "mean_token_accuracy": 0.6004979901015759,
+      "num_tokens": 518282.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.039170882976987106,
+      "eval_loss": 1.779425859451294,
+      "eval_mean_token_accuracy": 0.6544274031804684,
+      "eval_num_tokens": 518282.0,
+      "eval_runtime": 584.3483,
+      "eval_samples_per_second": 5.242,
+      "eval_steps_per_second": 1.311,
+      "step": 30
+    },
+    {
+      "epoch": 0.052227843969316144,
+      "grad_norm": 8.050444602966309,
+      "learning_rate": 0.0002,
+      "loss": 12.3059,
+      "mean_token_accuracy": 0.7168269947171211,
+      "num_tokens": 690414.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.052227843969316144,
+      "eval_loss": 1.309248924255371,
+      "eval_mean_token_accuracy": 0.7652701906684796,
+      "eval_num_tokens": 690414.0,
+      "eval_runtime": 583.5678,
+      "eval_samples_per_second": 5.249,
+      "eval_steps_per_second": 1.313,
+      "step": 40
+    },
+    {
+      "epoch": 0.06528480496164518,
+      "grad_norm": 2.590376615524292,
+      "learning_rate": 0.0002,
+      "loss": 10.1827,
+      "mean_token_accuracy": 0.7656703971326351,
+      "num_tokens": 863569.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.06528480496164518,
+      "eval_loss": 1.1905678510665894,
+      "eval_mean_token_accuracy": 0.7744907616946467,
+      "eval_num_tokens": 863569.0,
+      "eval_runtime": 583.2888,
+      "eval_samples_per_second": 5.251,
+      "eval_steps_per_second": 1.313,
+      "step": 50
+    },
+    {
+      "epoch": 0.07834176595397421,
+      "grad_norm": 2.414226770401001,
+      "learning_rate": 0.0002,
+      "loss": 9.4839,
+      "mean_token_accuracy": 0.773311423510313,
+      "num_tokens": 1037125.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.07834176595397421,
+      "eval_loss": 1.119614601135254,
+      "eval_mean_token_accuracy": 0.7835657717976184,
+      "eval_num_tokens": 1037125.0,
+      "eval_runtime": 584.5117,
+      "eval_samples_per_second": 5.24,
+      "eval_steps_per_second": 1.31,
+      "step": 60
+    },
+    {
+      "epoch": 0.09139872694630324,
+      "grad_norm": 1.8030030727386475,
+      "learning_rate": 0.0002,
+      "loss": 8.8096,
+      "mean_token_accuracy": 0.7858213528990745,
+      "num_tokens": 1209583.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.09139872694630324,
+      "eval_loss": 1.0682815313339233,
+      "eval_mean_token_accuracy": 0.7881310254568842,
+      "eval_num_tokens": 1209583.0,
+      "eval_runtime": 585.4405,
+      "eval_samples_per_second": 5.232,
+      "eval_steps_per_second": 1.308,
+      "step": 70
+    },
+    {
+      "epoch": 0.10445568793863229,
+      "grad_norm": 2.2091376781463623,
+      "learning_rate": 0.0002,
+      "loss": 8.6008,
+      "mean_token_accuracy": 0.7877494558691979,
+      "num_tokens": 1381768.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.10445568793863229,
+      "eval_loss": 1.034247636795044,
+      "eval_mean_token_accuracy": 0.7920899202867214,
+      "eval_num_tokens": 1381768.0,
+      "eval_runtime": 587.3448,
+      "eval_samples_per_second": 5.215,
+      "eval_steps_per_second": 1.304,
+      "step": 80
+    },
+    {
+      "epoch": 0.11751264893096132,
+      "grad_norm": 2.903419256210327,
+      "learning_rate": 0.0002,
+      "loss": 8.1348,
+      "mean_token_accuracy": 0.7928629629313946,
+      "num_tokens": 1553850.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.11751264893096132,
+      "eval_loss": 1.009232759475708,
+      "eval_mean_token_accuracy": 0.7953966308978456,
+      "eval_num_tokens": 1553850.0,
+      "eval_runtime": 586.354,
+      "eval_samples_per_second": 5.224,
+      "eval_steps_per_second": 1.306,
+      "step": 90
+    },
+    {
+      "epoch": 0.13056960992329036,
+      "grad_norm": 2.6068789958953857,
+      "learning_rate": 0.0002,
+      "loss": 8.3369,
+      "mean_token_accuracy": 0.790278784930706,
+      "num_tokens": 1727356.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.13056960992329036,
+      "eval_loss": 0.9901596903800964,
+      "eval_mean_token_accuracy": 0.7973068164316233,
+      "eval_num_tokens": 1727356.0,
+      "eval_runtime": 584.3882,
+      "eval_samples_per_second": 5.241,
+      "eval_steps_per_second": 1.311,
+      "step": 100
+    },
+    {
+      "epoch": 0.1436265709156194,
+      "grad_norm": 2.7159364223480225,
+      "learning_rate": 0.0002,
+      "loss": 8.0685,
+      "mean_token_accuracy": 0.7934540964663028,
+      "num_tokens": 1900444.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.1436265709156194,
+      "eval_loss": 0.9750204086303711,
+      "eval_mean_token_accuracy": 0.7992984780910433,
+      "eval_num_tokens": 1900444.0,
+      "eval_runtime": 584.7476,
+      "eval_samples_per_second": 5.238,
+      "eval_steps_per_second": 1.31,
+      "step": 110
+    },
+    {
+      "epoch": 0.15668353190794843,
+      "grad_norm": 2.747244119644165,
+      "learning_rate": 0.0002,
+      "loss": 7.7226,
+      "mean_token_accuracy": 0.8012088306248188,
+      "num_tokens": 2071987.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.15668353190794843,
+      "eval_loss": 0.9617533683776855,
+      "eval_mean_token_accuracy": 0.8009014339733372,
+      "eval_num_tokens": 2071987.0,
+      "eval_runtime": 584.8225,
+      "eval_samples_per_second": 5.237,
+      "eval_steps_per_second": 1.31,
+      "step": 120
+    },
+    {
+      "epoch": 0.16974049290027746,
+      "grad_norm": 2.888685464859009,
+      "learning_rate": 0.0002,
+      "loss": 7.7642,
+      "mean_token_accuracy": 0.7987834617495537,
+      "num_tokens": 2245073.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.16974049290027746,
+      "eval_loss": 0.951227605342865,
+      "eval_mean_token_accuracy": 0.8025058584175907,
+      "eval_num_tokens": 2245073.0,
+      "eval_runtime": 585.0529,
+      "eval_samples_per_second": 5.235,
+      "eval_steps_per_second": 1.309,
+      "step": 130
+    },
+    {
+      "epoch": 0.1827974538926065,
+      "grad_norm": 3.1910297870635986,
+      "learning_rate": 0.0002,
+      "loss": 7.6321,
+      "mean_token_accuracy": 0.8011799998581409,
+      "num_tokens": 2417106.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.1827974538926065,
+      "eval_loss": 0.941814661026001,
+      "eval_mean_token_accuracy": 0.8037396753425697,
+      "eval_num_tokens": 2417106.0,
+      "eval_runtime": 586.384,
+      "eval_samples_per_second": 5.224,
+      "eval_steps_per_second": 1.306,
+      "step": 140
+    },
+    {
+      "epoch": 0.19585441488493552,
+      "grad_norm": 3.866354465484619,
+      "learning_rate": 0.0002,
+      "loss": 7.6023,
+      "mean_token_accuracy": 0.8026318639516831,
+      "num_tokens": 2589875.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.19585441488493552,
+      "eval_loss": 0.932219922542572,
+      "eval_mean_token_accuracy": 0.8049114516914357,
+      "eval_num_tokens": 2589875.0,
+      "eval_runtime": 586.7629,
+      "eval_samples_per_second": 5.22,
+      "eval_steps_per_second": 1.305,
+      "step": 150
+    },
+    {
+      "epoch": 0.20891137587726458,
+      "grad_norm": 3.0838913917541504,
+      "learning_rate": 0.0002,
+      "loss": 7.2869,
+      "mean_token_accuracy": 0.8092540368437767,
+      "num_tokens": 2761587.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.20891137587726458,
+      "eval_loss": 0.9249224066734314,
+      "eval_mean_token_accuracy": 0.8061499763717851,
+      "eval_num_tokens": 2761587.0,
+      "eval_runtime": 587.3149,
+      "eval_samples_per_second": 5.215,
+      "eval_steps_per_second": 1.304,
+      "step": 160
+    },
+    {
+      "epoch": 0.2219683368695936,
+      "grad_norm": 3.295142889022827,
+      "learning_rate": 0.0002,
+      "loss": 7.3085,
+      "mean_token_accuracy": 0.8087648630142212,
+      "num_tokens": 2933386.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219683368695936,
+      "eval_loss": 0.9189748167991638,
+      "eval_mean_token_accuracy": 0.807062828431864,
+      "eval_num_tokens": 2933386.0,
+      "eval_runtime": 587.1146,
+      "eval_samples_per_second": 5.217,
+      "eval_steps_per_second": 1.305,
+      "step": 170
+    },
+    {
+      "epoch": 0.23502529786192264,
+      "grad_norm": 3.147334337234497,
+      "learning_rate": 0.0002,
+      "loss": 7.5534,
+      "mean_token_accuracy": 0.8029283680021763,
+      "num_tokens": 3105920.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.23502529786192264,
+      "eval_loss": 0.9137479662895203,
+      "eval_mean_token_accuracy": 0.8077044271457912,
+      "eval_num_tokens": 3105920.0,
+      "eval_runtime": 587.163,
+      "eval_samples_per_second": 5.217,
+      "eval_steps_per_second": 1.305,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2298,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.973832705428685e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56fb6112ac0b7078a8e80e19d682edd0375924d7bad919108b805da17ba9308e
+size 5880