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

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3.5-4B
+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

README.md

@@ -1,3 +1,202 @@
 ---
-license: apache-2.0
+base_model: Qwen/Qwen3.5-4B
+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 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "gate_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 sha256:531a28f9bfc6d23e91415c24942162179547ee8f22f9686f5ba1828322a60b98
+size 339772792

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620882e35002ef27837774c5640886e0bb74c70a43a9cb45ebecaec0203dd414
+size 172834021

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7358dd7e384ba5584b458f8d5661662d03cb4f8d2460bdc49a8568d4f50e21b7
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b348da36e1c2458a552c6c201c9f4702f93f45e6f57b6deb9d631d368680b291
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

trainer_state.json

@@ -0,0 +1,497 @@
+{
+  "best_global_step": 650,
+  "best_metric": 0.6772647500038147,
+  "best_model_checkpoint": "./tamilrav_checkpoints/checkpoint-650",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015396458814472672,
+      "grad_norm": 0.29363131523132324,
+      "learning_rate": 1.8e-05,
+      "loss": 1.4163263320922852,
+      "step": 10
+    },
+    {
+      "epoch": 0.030792917628945343,
+      "grad_norm": 0.265934020280838,
+      "learning_rate": 3.8e-05,
+      "loss": 1.188729953765869,
+      "step": 20
+    },
+    {
+      "epoch": 0.046189376443418015,
+      "grad_norm": 0.1696174591779709,
+      "learning_rate": 5.8e-05,
+      "loss": 1.0048276901245117,
+      "step": 30
+    },
+    {
+      "epoch": 0.061585835257890686,
+      "grad_norm": 0.1621861755847931,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.939247989654541,
+      "step": 40
+    },
+    {
+      "epoch": 0.07698229407236336,
+      "grad_norm": 0.16908901929855347,
+      "learning_rate": 9.8e-05,
+      "loss": 0.9107258796691895,
+      "step": 50
+    },
+    {
+      "epoch": 0.09237875288683603,
+      "grad_norm": 0.16060316562652588,
+      "learning_rate": 0.000118,
+      "loss": 0.8661402702331543,
+      "step": 60
+    },
+    {
+      "epoch": 0.1077752117013087,
+      "grad_norm": 0.15463921427726746,
+      "learning_rate": 0.000138,
+      "loss": 0.8585456848144531,
+      "step": 70
+    },
+    {
+      "epoch": 0.12317167051578137,
+      "grad_norm": 0.14651408791542053,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.8524063110351563,
+      "step": 80
+    },
+    {
+      "epoch": 0.13856812933025403,
+      "grad_norm": 0.1593480259180069,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.8573471069335937,
+      "step": 90
+    },
+    {
+      "epoch": 0.15396458814472672,
+      "grad_norm": 0.14837513864040375,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.8089125633239747,
+      "step": 100
+    },
+    {
+      "epoch": 0.16936104695919937,
+      "grad_norm": 0.1440625786781311,
+      "learning_rate": 0.00019998832107530538,
+      "loss": 0.8235550880432129,
+      "step": 110
+    },
+    {
+      "epoch": 0.18475750577367206,
+      "grad_norm": 0.1411304473876953,
+      "learning_rate": 0.00019994795298602624,
+      "loss": 0.8093386650085449,
+      "step": 120
+    },
+    {
+      "epoch": 0.20015396458814472,
+      "grad_norm": 0.1452978402376175,
+      "learning_rate": 0.0001998787631859678,
+      "loss": 0.8320710182189941,
+      "step": 130
+    },
+    {
+      "epoch": 0.2155504234026174,
+      "grad_norm": 0.13940446078777313,
+      "learning_rate": 0.00019978077162719857,
+      "loss": 0.821429443359375,
+      "step": 140
+    },
+    {
+      "epoch": 0.23094688221709006,
+      "grad_norm": 0.14506584405899048,
+      "learning_rate": 0.00019965400656726942,
+      "loss": 0.7923899173736573,
+      "step": 150
+    },
+    {
+      "epoch": 0.24634334103156275,
+      "grad_norm": 0.14369885623455048,
+      "learning_rate": 0.000199498504561065,
+      "loss": 0.7901590824127197,
+      "step": 160
+    },
+    {
+      "epoch": 0.2617397998460354,
+      "grad_norm": 0.14093971252441406,
+      "learning_rate": 0.00019931431045026255,
+      "loss": 0.8111134529113769,
+      "step": 170
+    },
+    {
+      "epoch": 0.27713625866050806,
+      "grad_norm": 0.13777726888656616,
+      "learning_rate": 0.00019910147735040102,
+      "loss": 0.791386604309082,
+      "step": 180
+    },
+    {
+      "epoch": 0.2925327174749808,
+      "grad_norm": 0.1432289332151413,
+      "learning_rate": 0.00019886006663556426,
+      "loss": 0.7923940181732178,
+      "step": 190
+    },
+    {
+      "epoch": 0.30792917628945343,
+      "grad_norm": 0.13564977049827576,
+      "learning_rate": 0.00019859014792068282,
+      "loss": 0.7843753337860108,
+      "step": 200
+    },
+    {
+      "epoch": 0.3233256351039261,
+      "grad_norm": 0.13792838156223297,
+      "learning_rate": 0.00019829179904145918,
+      "loss": 0.7822946071624756,
+      "step": 210
+    },
+    {
+      "epoch": 0.33872209391839875,
+      "grad_norm": 0.13952118158340454,
+      "learning_rate": 0.00019796510603192253,
+      "loss": 0.7925955772399902,
+      "step": 220
+    },
+    {
+      "epoch": 0.35411855273287146,
+      "grad_norm": 0.13627943396568298,
+      "learning_rate": 0.00019761016309961948,
+      "loss": 0.7559749603271484,
+      "step": 230
+    },
+    {
+      "epoch": 0.3695150115473441,
+      "grad_norm": 0.13699838519096375,
+      "learning_rate": 0.00019722707259844756,
+      "loss": 0.769603681564331,
+      "step": 240
+    },
+    {
+      "epoch": 0.3849114703618168,
+      "grad_norm": 0.13574793934822083,
+      "learning_rate": 0.0001968159449991397,
+      "loss": 0.7658140659332275,
+      "step": 250
+    },
+    {
+      "epoch": 0.40030792917628943,
+      "grad_norm": 0.13491615653038025,
+      "learning_rate": 0.00019637689885740827,
+      "loss": 0.7487314701080322,
+      "step": 260
+    },
+    {
+      "epoch": 0.41570438799076215,
+      "grad_norm": 0.1336905062198639,
+      "learning_rate": 0.0001959100607797573,
+      "loss": 0.7576127052307129,
+      "step": 270
+    },
+    {
+      "epoch": 0.4311008468052348,
+      "grad_norm": 0.12657032907009125,
+      "learning_rate": 0.0001954155653869735,
+      "loss": 0.7317625999450683,
+      "step": 280
+    },
+    {
+      "epoch": 0.44649730561970746,
+      "grad_norm": 0.13930626213550568,
+      "learning_rate": 0.00019489355527530576,
+      "loss": 0.7514139652252197,
+      "step": 290
+    },
+    {
+      "epoch": 0.4618937644341801,
+      "grad_norm": 0.1464177966117859,
+      "learning_rate": 0.00019434418097534554,
+      "loss": 0.750247573852539,
+      "step": 300
+    },
+    {
+      "epoch": 0.47729022324865283,
+      "grad_norm": 0.14013901352882385,
+      "learning_rate": 0.00019376760090861824,
+      "loss": 0.736499834060669,
+      "step": 310
+    },
+    {
+      "epoch": 0.4926866820631255,
+      "grad_norm": 0.131071999669075,
+      "learning_rate": 0.0001931639813419,
+      "loss": 0.7452194690704346,
+      "step": 320
+    },
+    {
+      "epoch": 0.5080831408775982,
+      "grad_norm": 0.13927963376045227,
+      "learning_rate": 0.0001925334963392717,
+      "loss": 0.7342241764068603,
+      "step": 330
+    },
+    {
+      "epoch": 0.5234795996920708,
+      "grad_norm": 0.1341823786497116,
+      "learning_rate": 0.00019187632771192466,
+      "loss": 0.7511595726013184,
+      "step": 340
+    },
+    {
+      "epoch": 0.5388760585065435,
+      "grad_norm": 0.13563531637191772,
+      "learning_rate": 0.00019119266496573208,
+      "loss": 0.7299445629119873,
+      "step": 350
+    },
+    {
+      "epoch": 0.5542725173210161,
+      "grad_norm": 0.1313074827194214,
+      "learning_rate": 0.00019048270524660196,
+      "loss": 0.7165977001190186,
+      "step": 360
+    },
+    {
+      "epoch": 0.5696689761354888,
+      "grad_norm": 0.14486627280712128,
+      "learning_rate": 0.00018974665328362654,
+      "loss": 0.710158109664917,
+      "step": 370
+    },
+    {
+      "epoch": 0.5850654349499615,
+      "grad_norm": 0.14865578711032867,
+      "learning_rate": 0.00018898472133004531,
+      "loss": 0.7281487941741943,
+      "step": 380
+    },
+    {
+      "epoch": 0.6004618937644342,
+      "grad_norm": 0.14025066792964935,
+      "learning_rate": 0.00018819712910203795,
+      "loss": 0.7306881904602051,
+      "step": 390
+    },
+    {
+      "epoch": 0.6158583525789069,
+      "grad_norm": 0.1385616809129715,
+      "learning_rate": 0.00018738410371536545,
+      "loss": 0.715015983581543,
+      "step": 400
+    },
+    {
+      "epoch": 0.6312548113933796,
+      "grad_norm": 0.13913969695568085,
+      "learning_rate": 0.00018654587961987754,
+      "loss": 0.6998976230621338,
+      "step": 410
+    },
+    {
+      "epoch": 0.6466512702078522,
+      "grad_norm": 0.14493151009082794,
+      "learning_rate": 0.00018568269853190482,
+      "loss": 0.7252633094787597,
+      "step": 420
+    },
+    {
+      "epoch": 0.6620477290223249,
+      "grad_norm": 0.1407926082611084,
+      "learning_rate": 0.00018479480936455577,
+      "loss": 0.705822229385376,
+      "step": 430
+    },
+    {
+      "epoch": 0.6774441878367975,
+      "grad_norm": 0.1485988348722458,
+      "learning_rate": 0.00018388246815593848,
+      "loss": 0.7083362579345703,
+      "step": 440
+    },
+    {
+      "epoch": 0.6928406466512702,
+      "grad_norm": 0.13596095144748688,
+      "learning_rate": 0.00018294593799532752,
+      "loss": 0.7086032867431641,
+      "step": 450
+    },
+    {
+      "epoch": 0.7082371054657429,
+      "grad_norm": 0.1445472687482834,
+      "learning_rate": 0.00018198548894729765,
+      "loss": 0.7101798057556152,
+      "step": 460
+    },
+    {
+      "epoch": 0.7236335642802155,
+      "grad_norm": 0.13956452906131744,
+      "learning_rate": 0.0001810013979738462,
+      "loss": 0.6983530044555664,
+      "step": 470
+    },
+    {
+      "epoch": 0.7390300230946882,
+      "grad_norm": 0.14123016595840454,
+      "learning_rate": 0.00017999394885452605,
+      "loss": 0.6674805641174316,
+      "step": 480
+    },
+    {
+      "epoch": 0.7544264819091608,
+      "grad_norm": 0.1448190063238144,
+      "learning_rate": 0.00017896343210461319,
+      "loss": 0.68931565284729,
+      "step": 490
+    },
+    {
+      "epoch": 0.7698229407236336,
+      "grad_norm": 0.14515918493270874,
+      "learning_rate": 0.00017791014489133147,
+      "loss": 0.6919535636901856,
+      "step": 500
+    },
+    {
+      "epoch": 0.7852193995381063,
+      "grad_norm": 0.13914334774017334,
+      "learning_rate": 0.00017683439094815938,
+      "loss": 0.6638880729675293,
+      "step": 510
+    },
+    {
+      "epoch": 0.8006158583525789,
+      "grad_norm": 0.14346542954444885,
+      "learning_rate": 0.00017573648048724327,
+      "loss": 0.6776976585388184,
+      "step": 520
+    },
+    {
+      "epoch": 0.8160123171670516,
+      "grad_norm": 0.1400802731513977,
+      "learning_rate": 0.00017461673010994236,
+      "loss": 0.7085250854492188,
+      "step": 530
+    },
+    {
+      "epoch": 0.8314087759815243,
+      "grad_norm": 0.1518496870994568,
+      "learning_rate": 0.0001734754627155313,
+      "loss": 0.6884902000427247,
+      "step": 540
+    },
+    {
+      "epoch": 0.8468052347959969,
+      "grad_norm": 0.14645785093307495,
+      "learning_rate": 0.00017231300740808654,
+      "loss": 0.7027451992034912,
+      "step": 550
+    },
+    {
+      "epoch": 0.8622016936104696,
+      "grad_norm": 0.14037857949733734,
+      "learning_rate": 0.00017112969940158359,
+      "loss": 0.6541213035583496,
+      "step": 560
+    },
+    {
+      "epoch": 0.8775981524249422,
+      "grad_norm": 0.14151780307292938,
+      "learning_rate": 0.0001699258799232323,
+      "loss": 0.6418449401855468,
+      "step": 570
+    },
+    {
+      "epoch": 0.8929946112394149,
+      "grad_norm": 0.14554472267627716,
+      "learning_rate": 0.00016870189611507813,
+      "loss": 0.6883684635162354,
+      "step": 580
+    },
+    {
+      "epoch": 0.9083910700538876,
+      "grad_norm": 0.14308355748653412,
+      "learning_rate": 0.00016745810093389766,
+      "loss": 0.6611432552337646,
+      "step": 590
+    },
+    {
+      "epoch": 0.9237875288683602,
+      "grad_norm": 0.153996542096138,
+      "learning_rate": 0.0001661948530494176,
+      "loss": 0.6723202705383301,
+      "step": 600
+    },
+    {
+      "epoch": 0.939183987682833,
+      "grad_norm": 0.14034205675125122,
+      "learning_rate": 0.00016491251674088613,
+      "loss": 0.6433265686035157,
+      "step": 610
+    },
+    {
+      "epoch": 0.9545804464973057,
+      "grad_norm": 0.15295536816120148,
+      "learning_rate": 0.00016361146179202666,
+      "loss": 0.6759867191314697,
+      "step": 620
+    },
+    {
+      "epoch": 0.9699769053117783,
+      "grad_norm": 0.14949378371238708,
+      "learning_rate": 0.00016229206338440447,
+      "loss": 0.6557295799255372,
+      "step": 630
+    },
+    {
+      "epoch": 0.985373364126251,
+      "grad_norm": 0.15767240524291992,
+      "learning_rate": 0.00016095470198923648,
+      "loss": 0.6578701972961426,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3094935119152069,
+      "learning_rate": 0.00015959976325767607,
+      "loss": 0.656089973449707,
+      "step": 650
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6772647500038147,
+      "eval_runtime": 193.0976,
+      "eval_samples_per_second": 2.978,
+      "eval_steps_per_second": 0.373,
+      "step": 650
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1950,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.665508132426875e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e508dcf42d6a52462fed16c5b2a27d24640b2a46227d1adfab2402dc46d199a
+size 5457