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

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-0.6B
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.17.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "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": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4bc71636aca18e206054b352704e8f3a7450395db6fb5d8215648186f43d04
+size 161533160

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- 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" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|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 %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e6b753e419e9092dad768d0742a34ba2886ebb8e032d34561d57546688d295
+size 323292202

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594c9f8b4bafe4f8c7c0b5afd9191e5cb90e136ab2d808c146fa45308dbef310
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff1061c5bdeb11c4c38e360f441dc47630b321d7a3cd172e05e907c6dc028ee
+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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,428 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.09639734774827957,
+  "best_model_checkpoint": "/workspace/Paper/Llama-Factory-out-FINAL/checkpoint-150",
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 469,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021333333333333333,
+      "grad_norm": 6.965007305145264,
+      "learning_rate": 1.9148936170212767e-06,
+      "loss": 0.5826,
+      "step": 10
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 8.343825340270996,
+      "learning_rate": 4.042553191489362e-06,
+      "loss": 0.221,
+      "step": 20
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 4.366076946258545,
+      "learning_rate": 6.170212765957447e-06,
+      "loss": 0.1193,
+      "step": 30
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 6.206355571746826,
+      "learning_rate": 8.297872340425532e-06,
+      "loss": 0.0886,
+      "step": 40
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 5.6667680740356445,
+      "learning_rate": 9.99944579961847e-06,
+      "loss": 0.0802,
+      "step": 50
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "eval_loss": 0.10694650560617447,
+      "eval_runtime": 97.3131,
+      "eval_samples_per_second": 10.276,
+      "eval_steps_per_second": 1.028,
+      "step": 50
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.066320419311523,
+      "learning_rate": 9.980061683013594e-06,
+      "loss": 0.0673,
+      "step": 60
+    },
+    {
+      "epoch": 0.14933333333333335,
+      "grad_norm": 5.067573547363281,
+      "learning_rate": 9.93309028019428e-06,
+      "loss": 0.0708,
+      "step": 70
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 3.1410481929779053,
+      "learning_rate": 9.858791791458431e-06,
+      "loss": 0.048,
+      "step": 80
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 3.2491090297698975,
+      "learning_rate": 9.757577796783268e-06,
+      "loss": 0.0558,
+      "step": 90
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.984602451324463,
+      "learning_rate": 9.630008975858667e-06,
+      "loss": 0.0405,
+      "step": 100
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 0.11375788599252701,
+      "eval_runtime": 96.5254,
+      "eval_samples_per_second": 10.36,
+      "eval_steps_per_second": 1.036,
+      "step": 100
+    },
+    {
+      "epoch": 0.23466666666666666,
+      "grad_norm": 4.064432621002197,
+      "learning_rate": 9.476792002175621e-06,
+      "loss": 0.0487,
+      "step": 110
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 4.923866271972656,
+      "learning_rate": 9.29877562837515e-06,
+      "loss": 0.0341,
+      "step": 120
+    },
+    {
+      "epoch": 0.2773333333333333,
+      "grad_norm": 4.464139938354492,
+      "learning_rate": 9.096945984543082e-06,
+      "loss": 0.0377,
+      "step": 130
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 4.207685470581055,
+      "learning_rate": 8.872421115495996e-06,
+      "loss": 0.0301,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.483502149581909,
+      "learning_rate": 8.62644478731932e-06,
+      "loss": 0.0456,
+      "step": 150
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.09639734774827957,
+      "eval_runtime": 96.7578,
+      "eval_samples_per_second": 10.335,
+      "eval_steps_per_second": 1.034,
+      "step": 150
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 2.220848321914673,
+      "learning_rate": 8.360379597466519e-06,
+      "loss": 0.0333,
+      "step": 160
+    },
+    {
+      "epoch": 0.3626666666666667,
+      "grad_norm": 0.7694166302680969,
+      "learning_rate": 8.075699426586345e-06,
+      "loss": 0.0356,
+      "step": 170
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.7014467120170593,
+      "learning_rate": 7.773981273891563e-06,
+      "loss": 0.0296,
+      "step": 180
+    },
+    {
+      "epoch": 0.4053333333333333,
+      "grad_norm": 11.522379875183105,
+      "learning_rate": 7.456896521297554e-06,
+      "loss": 0.0287,
+      "step": 190
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 3.0580711364746094,
+      "learning_rate": 7.126201674723493e-06,
+      "loss": 0.0441,
+      "step": 200
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_loss": 0.10796768218278885,
+      "eval_runtime": 93.5705,
+      "eval_samples_per_second": 10.687,
+      "eval_steps_per_second": 1.069,
+      "step": 200
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 1.6532104015350342,
+      "learning_rate": 6.783728633845076e-06,
+      "loss": 0.0355,
+      "step": 210
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 4.158193111419678,
+      "learning_rate": 6.431374544200013e-06,
+      "loss": 0.0393,
+      "step": 220
+    },
+    {
+      "epoch": 0.49066666666666664,
+      "grad_norm": 0.9233776926994324,
+      "learning_rate": 6.071091287860973e-06,
+      "loss": 0.0383,
+      "step": 230
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.443118155002594,
+      "learning_rate": 5.7048746708929295e-06,
+      "loss": 0.0338,
+      "step": 240
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.7420737147331238,
+      "learning_rate": 5.33475336749147e-06,
+      "loss": 0.0268,
+      "step": 250
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.1099962517619133,
+      "eval_runtime": 94.2519,
+      "eval_samples_per_second": 10.61,
+      "eval_steps_per_second": 1.061,
+      "step": 250
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 6.573488235473633,
+      "learning_rate": 4.962777682046565e-06,
+      "loss": 0.0306,
+      "step": 260
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.7128705382347107,
+      "learning_rate": 4.591008191384839e-06,
+      "loss": 0.033,
+      "step": 270
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 3.958656072616577,
+      "learning_rate": 4.221504330107204e-06,
+      "loss": 0.0334,
+      "step": 280
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": 1.2071937322616577,
+      "learning_rate": 3.856312982253909e-06,
+      "loss": 0.0374,
+      "step": 290
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0882517099380493,
+      "learning_rate": 3.4974571424940008e-06,
+      "loss": 0.0352,
+      "step": 300
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.11102046072483063,
+      "eval_runtime": 96.6838,
+      "eval_samples_per_second": 10.343,
+      "eval_steps_per_second": 1.034,
+      "step": 300
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": 1.3209381103515625,
+      "learning_rate": 3.1469247096510893e-06,
+      "loss": 0.0344,
+      "step": 310
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 1.4569178819656372,
+      "learning_rate": 2.8066574746442044e-06,
+      "loss": 0.0298,
+      "step": 320
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 1.3207861185073853,
+      "learning_rate": 2.4785403638455537e-06,
+      "loss": 0.0262,
+      "step": 330
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 1.223027229309082,
+      "learning_rate": 2.1643909974421167e-06,
+      "loss": 0.0366,
+      "step": 340
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 10.417492866516113,
+      "learning_rate": 1.8659496206430306e-06,
+      "loss": 0.0466,
+      "step": 350
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "eval_loss": 0.11615587025880814,
+      "eval_runtime": 95.1488,
+      "eval_samples_per_second": 10.51,
+      "eval_steps_per_second": 1.051,
+      "step": 350
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.6926187872886658,
+      "learning_rate": 1.58486946350929e-06,
+      "loss": 0.0332,
+      "step": 360
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": 0.1623552292585373,
+      "learning_rate": 1.3227075828079833e-06,
+      "loss": 0.021,
+      "step": 370
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 1.2165261507034302,
+      "learning_rate": 1.0809162366229996e-06,
+      "loss": 0.0295,
+      "step": 380
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 6.5908918380737305,
+      "learning_rate": 8.608348395029859e-07,
+      "loss": 0.0351,
+      "step": 390
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.6747581958770752,
+      "learning_rate": 6.636825427113719e-07,
+      "loss": 0.0308,
+      "step": 400
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_loss": 0.11269181966781616,
+      "eval_runtime": 95.2731,
+      "eval_samples_per_second": 10.496,
+      "eval_steps_per_second": 1.05,
+      "step": 400
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 1.3703091144561768,
+      "learning_rate": 4.905514806805456e-07,
+      "loss": 0.0304,
+      "step": 410
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.5667533278465271,
+      "learning_rate": 3.424007210817248e-07,
+      "loss": 0.0307,
+      "step": 420
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 1.5054301023483276,
+      "learning_rate": 2.200509520244326e-07,
+      "loss": 0.0154,
+      "step": 430
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 2.8148467540740967,
+      "learning_rate": 1.2417993581606446e-07,
+      "loss": 0.0331,
+      "step": 440
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.3720769882202148,
+      "learning_rate": 5.5318754465671366e-08,
+      "loss": 0.0315,
+      "step": 450
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.1133466511964798,
+      "eval_runtime": 96.6743,
+      "eval_samples_per_second": 10.344,
+      "eval_steps_per_second": 1.034,
+      "step": 450
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.2468981146812439,
+      "learning_rate": 1.3848867730158477e-08,
+      "loss": 0.0265,
+      "step": 460
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 469,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6387352710191514e+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:baa9112fa51e361b8981fc3ea29debcf69c95f4e2cf1ba970726c766a3717fe6
+size 6008