Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1797/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: other
+base_model: Qwen3-8B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: decom_desc_bm25_sep_final
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# decom_desc_bm25_sep_final
+
+This model is a fine-tuned version of [/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B](https://huggingface.co//root/paddlejob/workspace/env_run/output/llm/Qwen3-8B) on the decom_desc_bm25_sep_final dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "q_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 sha256:9c623b00d9a2cf3b7d78ddeba1b9a8d65ffd0c847bd990dbd2db979a89c25a30
+size 87360584

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6.751297376408863e+17,
+    "train_loss": 0.4856139095743696,
+    "train_runtime": 18496.859,
+    "train_samples_per_second": 0.776,
+    "train_steps_per_second": 0.097
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /root/paddlejob/workspace/env_run/output/llm/Qwen3-8B
+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

checkpoint-1000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f6643d2e5d58fe464d3061f0cf784c0597c49788823ad86fbbda56b918cae30
+size 87360584

checkpoint-1000/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
+}

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37709a03bb0684e94bae563749d6ff7d334a71a10e0e9a9ecaf624f24852ab5f
+size 175012218

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2c996bfa0a7212ce63e74364908ea777a8ecfa74a40c5c1d0a99854d6f8ecf
+size 1064

checkpoint-1000/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
+  }
+}

checkpoint-1000/tokenizer.json

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

checkpoint-1000/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
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.670148318362231,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016711928138709004,
+      "grad_norm": 0.5531014800071716,
+      "learning_rate": 5e-06,
+      "loss": 0.9993,
+      "step": 10
+    },
+    {
+      "epoch": 0.03342385627741801,
+      "grad_norm": 0.5198462009429932,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 0.9973,
+      "step": 20
+    },
+    {
+      "epoch": 0.05013578441612701,
+      "grad_norm": 0.9699999094009399,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 0.9474,
+      "step": 30
+    },
+    {
+      "epoch": 0.06684771255483601,
+      "grad_norm": 0.3459213078022003,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.7622,
+      "step": 40
+    },
+    {
+      "epoch": 0.08355964069354502,
+      "grad_norm": 0.24512118101119995,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 0.7086,
+      "step": 50
+    },
+    {
+      "epoch": 0.10027156883225402,
+      "grad_norm": 0.21762403845787048,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 0.6895,
+      "step": 60
+    },
+    {
+      "epoch": 0.11698349697096302,
+      "grad_norm": 0.22329938411712646,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.6491,
+      "step": 70
+    },
+    {
+      "epoch": 0.13369542510967203,
+      "grad_norm": 0.19780907034873962,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 0.6225,
+      "step": 80
+    },
+    {
+      "epoch": 0.15040735324838103,
+      "grad_norm": 0.17309053242206573,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 0.6026,
+      "step": 90
+    },
+    {
+      "epoch": 0.16711928138709004,
+      "grad_norm": 0.20399844646453857,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5435,
+      "step": 100
+    },
+    {
+      "epoch": 0.18383120952579904,
+      "grad_norm": 0.21713724732398987,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 0.581,
+      "step": 110
+    },
+    {
+      "epoch": 0.20054313766450804,
+      "grad_norm": 0.24566805362701416,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 0.5203,
+      "step": 120
+    },
+    {
+      "epoch": 0.21725506580321705,
+      "grad_norm": 0.26538822054862976,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 0.5975,
+      "step": 130
+    },
+    {
+      "epoch": 0.23396699394192605,
+      "grad_norm": 0.24092447757720947,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 0.5627,
+      "step": 140
+    },
+    {
+      "epoch": 0.2506789220806351,
+      "grad_norm": 0.24146470427513123,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 0.5289,
+      "step": 150
+    },
+    {
+      "epoch": 0.26739085021934406,
+      "grad_norm": 0.8219459652900696,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 0.5347,
+      "step": 160
+    },
+    {
+      "epoch": 0.2841027783580531,
+      "grad_norm": 0.2518085241317749,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 0.5491,
+      "step": 170
+    },
+    {
+      "epoch": 0.30081470649676206,
+      "grad_norm": 0.2775290012359619,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 0.5701,
+      "step": 180
+    },
+    {
+      "epoch": 0.3175266346354711,
+      "grad_norm": 0.2761514186859131,
+      "learning_rate": 9.999235647539953e-05,
+      "loss": 0.5489,
+      "step": 190
+    },
+    {
+      "epoch": 0.33423856277418007,
+      "grad_norm": 0.32875457406044006,
+      "learning_rate": 9.996593741531468e-05,
+      "loss": 0.5374,
+      "step": 200
+    },
+    {
+      "epoch": 0.3509504909128891,
+      "grad_norm": 0.2761303186416626,
+      "learning_rate": 9.992065842489567e-05,
+      "loss": 0.4916,
+      "step": 210
+    },
+    {
+      "epoch": 0.3676624190515981,
+      "grad_norm": 0.2781451940536499,
+      "learning_rate": 9.985653659495773e-05,
+      "loss": 0.5826,
+      "step": 220
+    },
+    {
+      "epoch": 0.3843743471903071,
+      "grad_norm": 0.32615798711776733,
+      "learning_rate": 9.977359612865423e-05,
+      "loss": 0.532,
+      "step": 230
+    },
+    {
+      "epoch": 0.4010862753290161,
+      "grad_norm": 0.2824324667453766,
+      "learning_rate": 9.967186833234101e-05,
+      "loss": 0.5482,
+      "step": 240
+    },
+    {
+      "epoch": 0.4177982034677251,
+      "grad_norm": 0.2630137503147125,
+      "learning_rate": 9.955139160375959e-05,
+      "loss": 0.4917,
+      "step": 250
+    },
+    {
+      "epoch": 0.4345101316064341,
+      "grad_norm": 0.3076798915863037,
+      "learning_rate": 9.941221141754385e-05,
+      "loss": 0.5285,
+      "step": 260
+    },
+    {
+      "epoch": 0.4512220597451431,
+      "grad_norm": 0.3244406282901764,
+      "learning_rate": 9.925438030805518e-05,
+      "loss": 0.5178,
+      "step": 270
+    },
+    {
+      "epoch": 0.4679339878838521,
+      "grad_norm": 0.3224153220653534,
+      "learning_rate": 9.907795784955327e-05,
+      "loss": 0.5184,
+      "step": 280
+    },
+    {
+      "epoch": 0.48464591602256113,
+      "grad_norm": 0.3541305959224701,
+      "learning_rate": 9.888301063370934e-05,
+      "loss": 0.5327,
+      "step": 290
+    },
+    {
+      "epoch": 0.5013578441612702,
+      "grad_norm": 0.28691530227661133,
+      "learning_rate": 9.866961224447075e-05,
+      "loss": 0.5461,
+      "step": 300
+    },
+    {
+      "epoch": 0.5180697722999791,
+      "grad_norm": 0.4132674038410187,
+      "learning_rate": 9.843784323028638e-05,
+      "loss": 0.5242,
+      "step": 310
+    },
+    {
+      "epoch": 0.5347817004386881,
+      "grad_norm": 0.33508822321891785,
+      "learning_rate": 9.818779107370309e-05,
+      "loss": 0.5285,
+      "step": 320
+    },
+    {
+      "epoch": 0.5514936285773971,
+      "grad_norm": 0.2662738561630249,
+      "learning_rate": 9.791955015834492e-05,
+      "loss": 0.5287,
+      "step": 330
+    },
+    {
+      "epoch": 0.5682055567161062,
+      "grad_norm": 0.30024951696395874,
+      "learning_rate": 9.763322173328753e-05,
+      "loss": 0.5329,
+      "step": 340
+    },
+    {
+      "epoch": 0.5849174848548151,
+      "grad_norm": 0.27861520648002625,
+      "learning_rate": 9.732891387484104e-05,
+      "loss": 0.4656,
+      "step": 350
+    },
+    {
+      "epoch": 0.6016294129935241,
+      "grad_norm": 0.33017635345458984,
+      "learning_rate": 9.700674144575614e-05,
+      "loss": 0.5334,
+      "step": 360
+    },
+    {
+      "epoch": 0.6183413411322332,
+      "grad_norm": 0.3784632384777069,
+      "learning_rate": 9.666682605186835e-05,
+      "loss": 0.4669,
+      "step": 370
+    },
+    {
+      "epoch": 0.6350532692709422,
+      "grad_norm": 0.3362145721912384,
+      "learning_rate": 9.63092959961973e-05,
+      "loss": 0.4938,
+      "step": 380
+    },
+    {
+      "epoch": 0.6517651974096511,
+      "grad_norm": 0.2863125801086426,
+      "learning_rate": 9.593428623051792e-05,
+      "loss": 0.4815,
+      "step": 390
+    },
+    {
+      "epoch": 0.6684771255483601,
+      "grad_norm": 0.23034977912902832,
+      "learning_rate": 9.554193830442229e-05,
+      "loss": 0.5249,
+      "step": 400
+    },
+    {
+      "epoch": 0.6851890536870692,
+      "grad_norm": 0.29409608244895935,
+      "learning_rate": 9.513240031189067e-05,
+      "loss": 0.4899,
+      "step": 410
+    },
+    {
+      "epoch": 0.7019009818257782,
+      "grad_norm": 0.3073919415473938,
+      "learning_rate": 9.470582683539285e-05,
+      "loss": 0.5115,
+      "step": 420
+    },
+    {
+      "epoch": 0.7186129099644871,
+      "grad_norm": 0.33221715688705444,
+      "learning_rate": 9.42623788875399e-05,
+      "loss": 0.5021,
+      "step": 430
+    },
+    {
+      "epoch": 0.7353248381031962,
+      "grad_norm": 0.24137817323207855,
+      "learning_rate": 9.380222385030915e-05,
+      "loss": 0.4757,
+      "step": 440
+    },
+    {
+      "epoch": 0.7520367662419052,
+      "grad_norm": 0.28623566031455994,
+      "learning_rate": 9.332553541186485e-05,
+      "loss": 0.515,
+      "step": 450
+    },
+    {
+      "epoch": 0.7687486943806142,
+      "grad_norm": 0.30202344059944153,
+      "learning_rate": 9.283249350099859e-05,
+      "loss": 0.5259,
+      "step": 460
+    },
+    {
+      "epoch": 0.7854606225193231,
+      "grad_norm": 0.264213502407074,
+      "learning_rate": 9.23232842192142e-05,
+      "loss": 0.5224,
+      "step": 470
+    },
+    {
+      "epoch": 0.8021725506580322,
+      "grad_norm": 0.2509612739086151,
+      "learning_rate": 9.179809977048248e-05,
+      "loss": 0.5318,
+      "step": 480
+    },
+    {
+      "epoch": 0.8188844787967412,
+      "grad_norm": 0.28840652108192444,
+      "learning_rate": 9.125713838869299e-05,
+      "loss": 0.5287,
+      "step": 490
+    },
+    {
+      "epoch": 0.8355964069354502,
+      "grad_norm": 0.30437350273132324,
+      "learning_rate": 9.070060426282925e-05,
+      "loss": 0.5256,
+      "step": 500
+    },
+    {
+      "epoch": 0.8523083350741592,
+      "grad_norm": 0.3300555646419525,
+      "learning_rate": 9.012870745989663e-05,
+      "loss": 0.4876,
+      "step": 510
+    },
+    {
+      "epoch": 0.8690202632128682,
+      "grad_norm": 0.27293577790260315,
+      "learning_rate": 8.954166384563127e-05,
+      "loss": 0.5136,
+      "step": 520
+    },
+    {
+      "epoch": 0.8857321913515772,
+      "grad_norm": 0.29159626364707947,
+      "learning_rate": 8.893969500302031e-05,
+      "loss": 0.5224,
+      "step": 530
+    },
+    {
+      "epoch": 0.9024441194902862,
+      "grad_norm": 0.34646981954574585,
+      "learning_rate": 8.832302814866416e-05,
+      "loss": 0.5117,
+      "step": 540
+    },
+    {
+      "epoch": 0.9191560476289952,
+      "grad_norm": 0.2947717607021332,
+      "learning_rate": 8.76918960470122e-05,
+      "loss": 0.534,
+      "step": 550
+    },
+    {
+      "epoch": 0.9358679757677042,
+      "grad_norm": 0.2506949305534363,
+      "learning_rate": 8.704653692250466e-05,
+      "loss": 0.5013,
+      "step": 560
+    },
+    {
+      "epoch": 0.9525799039064132,
+      "grad_norm": 0.28196585178375244,
+      "learning_rate": 8.638719436965325e-05,
+      "loss": 0.5089,
+      "step": 570
+    },
+    {
+      "epoch": 0.9692918320451223,
+      "grad_norm": 0.26513898372650146,
+      "learning_rate": 8.571411726109519e-05,
+      "loss": 0.5346,
+      "step": 580
+    },
+    {
+      "epoch": 0.9860037601838312,
+      "grad_norm": 0.3039480149745941,
+      "learning_rate": 8.50275596536546e-05,
+      "loss": 0.5097,
+      "step": 590
+    },
+    {
+      "epoch": 1.0016711928138708,
+      "grad_norm": 0.2783941328525543,
+      "learning_rate": 8.432778069244749e-05,
+      "loss": 0.5139,
+      "step": 600
+    },
+    {
+      "epoch": 1.01838312095258,
+      "grad_norm": 0.2535961866378784,
+      "learning_rate": 8.361504451306585e-05,
+      "loss": 0.4471,
+      "step": 610
+    },
+    {
+      "epoch": 1.035095049091289,
+      "grad_norm": 0.32639509439468384,
+      "learning_rate": 8.288962014187811e-05,
+      "loss": 0.4725,
+      "step": 620
+    },
+    {
+      "epoch": 1.0518069772299978,
+      "grad_norm": 0.3780384361743927,
+      "learning_rate": 8.21517813944837e-05,
+      "loss": 0.4459,
+      "step": 630
+    },
+    {
+      "epoch": 1.068518905368707,
+      "grad_norm": 0.297475129365921,
+      "learning_rate": 8.14018067723597e-05,
+      "loss": 0.4515,
+      "step": 640
+    },
+    {
+      "epoch": 1.085230833507416,
+      "grad_norm": 0.32445859909057617,
+      "learning_rate": 8.063997935773885e-05,
+      "loss": 0.4648,
+      "step": 650
+    },
+    {
+      "epoch": 1.101942761646125,
+      "grad_norm": 0.333881676197052,
+      "learning_rate": 7.986658670675861e-05,
+      "loss": 0.4549,
+      "step": 660
+    },
+    {
+      "epoch": 1.118654689784834,
+      "grad_norm": 0.3279685974121094,
+      "learning_rate": 7.908192074092136e-05,
+      "loss": 0.4768,
+      "step": 670
+    },
+    {
+      "epoch": 1.1353666179235429,
+      "grad_norm": 0.36196866631507874,
+      "learning_rate": 7.828627763690697e-05,
+      "loss": 0.5039,
+      "step": 680
+    },
+    {
+      "epoch": 1.152078546062252,
+      "grad_norm": 0.3395329713821411,
+      "learning_rate": 7.747995771477928e-05,
+      "loss": 0.4628,
+      "step": 690
+    },
+    {
+      "epoch": 1.168790474200961,
+      "grad_norm": 0.3666079342365265,
+      "learning_rate": 7.666326532462842e-05,
+      "loss": 0.444,
+      "step": 700
+    },
+    {
+      "epoch": 1.1855024023396699,
+      "grad_norm": 0.3585106432437897,
+      "learning_rate": 7.583650873169232e-05,
+      "loss": 0.5077,
+      "step": 710
+    },
+    {
+      "epoch": 1.202214330478379,
+      "grad_norm": 0.3411233127117157,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4689,
+      "step": 720
+    },
+    {
+      "epoch": 1.218926258617088,
+      "grad_norm": 0.36491307616233826,
+      "learning_rate": 7.41540548745814e-05,
+      "loss": 0.4509,
+      "step": 730
+    },
+    {
+      "epoch": 1.2356381867557968,
+      "grad_norm": 0.3584769070148468,
+      "learning_rate": 7.329899266228748e-05,
+      "loss": 0.4782,
+      "step": 740
+    },
+    {
+      "epoch": 1.252350114894506,
+      "grad_norm": 0.3567698299884796,
+      "learning_rate": 7.243513611126608e-05,
+      "loss": 0.4287,
+      "step": 750
+    },
+    {
+      "epoch": 1.269062043033215,
+      "grad_norm": 0.36464792490005493,
+      "learning_rate": 7.156281128913871e-05,
+      "loss": 0.4642,
+      "step": 760
+    },
+    {
+      "epoch": 1.285773971171924,
+      "grad_norm": 0.41288235783576965,
+      "learning_rate": 7.068234745992456e-05,
+      "loss": 0.4659,
+      "step": 770
+    },
+    {
+      "epoch": 1.302485899310633,
+      "grad_norm": 0.8390935063362122,
+      "learning_rate": 6.979407695975776e-05,
+      "loss": 0.4932,
+      "step": 780
+    },
+    {
+      "epoch": 1.3191978274493419,
+      "grad_norm": 0.3990253806114197,
+      "learning_rate": 6.889833507144532e-05,
+      "loss": 0.494,
+      "step": 790
+    },
+    {
+      "epoch": 1.335909755588051,
+      "grad_norm": 0.39918258786201477,
+      "learning_rate": 6.799545989791268e-05,
+      "loss": 0.4307,
+      "step": 800
+    },
+    {
+      "epoch": 1.35262168372676,
+      "grad_norm": 0.3962526321411133,
+      "learning_rate": 6.708579223458475e-05,
+      "loss": 0.4515,
+      "step": 810
+    },
+    {
+      "epoch": 1.369333611865469,
+      "grad_norm": 0.366760790348053,
+      "learning_rate": 6.616967544075077e-05,
+      "loss": 0.4783,
+      "step": 820
+    },
+    {
+      "epoch": 1.386045540004178,
+      "grad_norm": 0.3852802515029907,
+      "learning_rate": 6.524745530996137e-05,
+      "loss": 0.4933,
+      "step": 830
+    },
+    {
+      "epoch": 1.402757468142887,
+      "grad_norm": 0.3308377265930176,
+      "learning_rate": 6.431947993950682e-05,
+      "loss": 0.525,
+      "step": 840
+    },
+    {
+      "epoch": 1.4194693962815959,
+      "grad_norm": 0.3748877942562103,
+      "learning_rate": 6.338609959902569e-05,
+      "loss": 0.4752,
+      "step": 850
+    },
+    {
+      "epoch": 1.436181324420305,
+      "grad_norm": 0.37608233094215393,
+      "learning_rate": 6.244766659829351e-05,
+      "loss": 0.4818,
+      "step": 860
+    },
+    {
+      "epoch": 1.452893252559014,
+      "grad_norm": 0.36020001769065857,
+      "learning_rate": 6.150453515424153e-05,
+      "loss": 0.4888,
+      "step": 870
+    },
+    {
+      "epoch": 1.469605180697723,
+      "grad_norm": 0.40768539905548096,
+      "learning_rate": 6.055706125725542e-05,
+      "loss": 0.5247,
+      "step": 880
+    },
+    {
+      "epoch": 1.486317108836432,
+      "grad_norm": 0.397224098443985,
+      "learning_rate": 5.9605602536804673e-05,
+      "loss": 0.4356,
+      "step": 890
+    },
+    {
+      "epoch": 1.503029036975141,
+      "grad_norm": 0.38998743891716003,
+      "learning_rate": 5.865051812645329e-05,
+      "loss": 0.473,
+      "step": 900
+    },
+    {
+      "epoch": 1.51974096511385,
+      "grad_norm": 0.3835464417934418,
+      "learning_rate": 5.7692168528302807e-05,
+      "loss": 0.4716,
+      "step": 910
+    },
+    {
+      "epoch": 1.536452893252559,
+      "grad_norm": 0.3747701644897461,
+      "learning_rate": 5.673091547691866e-05,
+      "loss": 0.432,
+      "step": 920
+    },
+    {
+      "epoch": 1.553164821391268,
+      "grad_norm": 0.3856564462184906,
+      "learning_rate": 5.576712180279133e-05,
+      "loss": 0.5033,
+      "step": 930
+    },
+    {
+      "epoch": 1.569876749529977,
+      "grad_norm": 0.3968600332736969,
+      "learning_rate": 5.480115129538409e-05,
+      "loss": 0.5051,
+      "step": 940
+    },
+    {
+      "epoch": 1.586588677668686,
+      "grad_norm": 0.4307195842266083,
+      "learning_rate": 5.383336856581833e-05,
+      "loss": 0.4576,
+      "step": 950
+    },
+    {
+      "epoch": 1.6033006058073949,
+      "grad_norm": 0.401885449886322,
+      "learning_rate": 5.2864138909249176e-05,
+      "loss": 0.4866,
+      "step": 960
+    },
+    {
+      "epoch": 1.620012533946104,
+      "grad_norm": 0.3600904941558838,
+      "learning_rate": 5.189382816698263e-05,
+      "loss": 0.4844,
+      "step": 970
+    },
+    {
+      "epoch": 1.6367244620848131,
+      "grad_norm": 0.35338348150253296,
+      "learning_rate": 5.0922802588386766e-05,
+      "loss": 0.4991,
+      "step": 980
+    },
+    {
+      "epoch": 1.653436390223522,
+      "grad_norm": 0.37117472290992737,
+      "learning_rate": 4.9951428692648664e-05,
+      "loss": 0.4709,
+      "step": 990
+    },
+    {
+      "epoch": 1.670148318362231,
+      "grad_norm": 0.3381313383579254,
+      "learning_rate": 4.898007313042975e-05,
+      "loss": 0.4474,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1797,
+  "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": 3.76025652115882e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c2331f16b8cdb74d728a7328480d3810e4c52d40a7803ab25c874ac59b6fa2
+size 5752

checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /root/paddlejob/workspace/env_run/output/llm/Qwen3-8B
+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

checkpoint-1500/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e41fbd9d7fafe99352bb0d0ff71aa80232dc243f079aafb84ae86e685e2edf
+size 87360584

checkpoint-1500/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
+}

checkpoint-1500/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8a2b99a9d0455bb760ea3f51c4a5bcf74801e088201fe69e9a468000d09b56
+size 175012218

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fb48de69ff180789e9e4e7d9eac10322226dc393b9723338be87c2983421c2
+size 1064

checkpoint-1500/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
+  }
+}

checkpoint-1500/tokenizer.json

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

checkpoint-1500/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
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.504700229789012,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016711928138709004,
+      "grad_norm": 0.5531014800071716,
+      "learning_rate": 5e-06,
+      "loss": 0.9993,
+      "step": 10
+    },
+    {
+      "epoch": 0.03342385627741801,
+      "grad_norm": 0.5198462009429932,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 0.9973,
+      "step": 20
+    },
+    {
+      "epoch": 0.05013578441612701,
+      "grad_norm": 0.9699999094009399,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 0.9474,
+      "step": 30
+    },
+    {
+      "epoch": 0.06684771255483601,
+      "grad_norm": 0.3459213078022003,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.7622,
+      "step": 40
+    },
+    {
+      "epoch": 0.08355964069354502,
+      "grad_norm": 0.24512118101119995,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 0.7086,
+      "step": 50
+    },
+    {
+      "epoch": 0.10027156883225402,
+      "grad_norm": 0.21762403845787048,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 0.6895,
+      "step": 60
+    },
+    {
+      "epoch": 0.11698349697096302,
+      "grad_norm": 0.22329938411712646,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.6491,
+      "step": 70
+    },
+    {
+      "epoch": 0.13369542510967203,
+      "grad_norm": 0.19780907034873962,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 0.6225,
+      "step": 80
+    },
+    {
+      "epoch": 0.15040735324838103,
+      "grad_norm": 0.17309053242206573,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 0.6026,
+      "step": 90
+    },
+    {
+      "epoch": 0.16711928138709004,
+      "grad_norm": 0.20399844646453857,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5435,
+      "step": 100
+    },
+    {
+      "epoch": 0.18383120952579904,
+      "grad_norm": 0.21713724732398987,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 0.581,
+      "step": 110
+    },
+    {
+      "epoch": 0.20054313766450804,
+      "grad_norm": 0.24566805362701416,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 0.5203,
+      "step": 120
+    },
+    {
+      "epoch": 0.21725506580321705,
+      "grad_norm": 0.26538822054862976,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 0.5975,
+      "step": 130
+    },
+    {
+      "epoch": 0.23396699394192605,
+      "grad_norm": 0.24092447757720947,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 0.5627,
+      "step": 140
+    },
+    {
+      "epoch": 0.2506789220806351,
+      "grad_norm": 0.24146470427513123,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 0.5289,
+      "step": 150
+    },
+    {
+      "epoch": 0.26739085021934406,
+      "grad_norm": 0.8219459652900696,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 0.5347,
+      "step": 160
+    },
+    {
+      "epoch": 0.2841027783580531,
+      "grad_norm": 0.2518085241317749,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 0.5491,
+      "step": 170
+    },
+    {
+      "epoch": 0.30081470649676206,
+      "grad_norm": 0.2775290012359619,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 0.5701,
+      "step": 180
+    },
+    {
+      "epoch": 0.3175266346354711,
+      "grad_norm": 0.2761514186859131,
+      "learning_rate": 9.999235647539953e-05,
+      "loss": 0.5489,
+      "step": 190
+    },
+    {
+      "epoch": 0.33423856277418007,
+      "grad_norm": 0.32875457406044006,
+      "learning_rate": 9.996593741531468e-05,
+      "loss": 0.5374,
+      "step": 200
+    },
+    {
+      "epoch": 0.3509504909128891,
+      "grad_norm": 0.2761303186416626,
+      "learning_rate": 9.992065842489567e-05,
+      "loss": 0.4916,
+      "step": 210
+    },
+    {
+      "epoch": 0.3676624190515981,
+      "grad_norm": 0.2781451940536499,
+      "learning_rate": 9.985653659495773e-05,
+      "loss": 0.5826,
+      "step": 220
+    },
+    {
+      "epoch": 0.3843743471903071,
+      "grad_norm": 0.32615798711776733,
+      "learning_rate": 9.977359612865423e-05,
+      "loss": 0.532,
+      "step": 230
+    },
+    {
+      "epoch": 0.4010862753290161,
+      "grad_norm": 0.2824324667453766,
+      "learning_rate": 9.967186833234101e-05,
+      "loss": 0.5482,
+      "step": 240
+    },
+    {
+      "epoch": 0.4177982034677251,
+      "grad_norm": 0.2630137503147125,
+      "learning_rate": 9.955139160375959e-05,
+      "loss": 0.4917,
+      "step": 250
+    },
+    {
+      "epoch": 0.4345101316064341,
+      "grad_norm": 0.3076798915863037,
+      "learning_rate": 9.941221141754385e-05,
+      "loss": 0.5285,
+      "step": 260
+    },
+    {
+      "epoch": 0.4512220597451431,
+      "grad_norm": 0.3244406282901764,
+      "learning_rate": 9.925438030805518e-05,
+      "loss": 0.5178,
+      "step": 270
+    },
+    {
+      "epoch": 0.4679339878838521,
+      "grad_norm": 0.3224153220653534,
+      "learning_rate": 9.907795784955327e-05,
+      "loss": 0.5184,
+      "step": 280
+    },
+    {
+      "epoch": 0.48464591602256113,
+      "grad_norm": 0.3541305959224701,
+      "learning_rate": 9.888301063370934e-05,
+      "loss": 0.5327,
+      "step": 290
+    },
+    {
+      "epoch": 0.5013578441612702,
+      "grad_norm": 0.28691530227661133,
+      "learning_rate": 9.866961224447075e-05,
+      "loss": 0.5461,
+      "step": 300
+    },
+    {
+      "epoch": 0.5180697722999791,
+      "grad_norm": 0.4132674038410187,
+      "learning_rate": 9.843784323028638e-05,
+      "loss": 0.5242,
+      "step": 310
+    },
+    {
+      "epoch": 0.5347817004386881,
+      "grad_norm": 0.33508822321891785,
+      "learning_rate": 9.818779107370309e-05,
+      "loss": 0.5285,
+      "step": 320
+    },
+    {
+      "epoch": 0.5514936285773971,
+      "grad_norm": 0.2662738561630249,
+      "learning_rate": 9.791955015834492e-05,
+      "loss": 0.5287,
+      "step": 330
+    },
+    {
+      "epoch": 0.5682055567161062,
+      "grad_norm": 0.30024951696395874,
+      "learning_rate": 9.763322173328753e-05,
+      "loss": 0.5329,
+      "step": 340
+    },
+    {
+      "epoch": 0.5849174848548151,
+      "grad_norm": 0.27861520648002625,
+      "learning_rate": 9.732891387484104e-05,
+      "loss": 0.4656,
+      "step": 350
+    },
+    {
+      "epoch": 0.6016294129935241,
+      "grad_norm": 0.33017635345458984,
+      "learning_rate": 9.700674144575614e-05,
+      "loss": 0.5334,
+      "step": 360
+    },
+    {
+      "epoch": 0.6183413411322332,
+      "grad_norm": 0.3784632384777069,
+      "learning_rate": 9.666682605186835e-05,
+      "loss": 0.4669,
+      "step": 370
+    },
+    {
+      "epoch": 0.6350532692709422,
+      "grad_norm": 0.3362145721912384,
+      "learning_rate": 9.63092959961973e-05,
+      "loss": 0.4938,
+      "step": 380
+    },
+    {
+      "epoch": 0.6517651974096511,
+      "grad_norm": 0.2863125801086426,
+      "learning_rate": 9.593428623051792e-05,
+      "loss": 0.4815,
+      "step": 390
+    },
+    {
+      "epoch": 0.6684771255483601,
+      "grad_norm": 0.23034977912902832,
+      "learning_rate": 9.554193830442229e-05,
+      "loss": 0.5249,
+      "step": 400
+    },
+    {
+      "epoch": 0.6851890536870692,
+      "grad_norm": 0.29409608244895935,
+      "learning_rate": 9.513240031189067e-05,
+      "loss": 0.4899,
+      "step": 410
+    },
+    {
+      "epoch": 0.7019009818257782,
+      "grad_norm": 0.3073919415473938,
+      "learning_rate": 9.470582683539285e-05,
+      "loss": 0.5115,
+      "step": 420
+    },
+    {
+      "epoch": 0.7186129099644871,
+      "grad_norm": 0.33221715688705444,
+      "learning_rate": 9.42623788875399e-05,
+      "loss": 0.5021,
+      "step": 430
+    },
+    {
+      "epoch": 0.7353248381031962,
+      "grad_norm": 0.24137817323207855,
+      "learning_rate": 9.380222385030915e-05,
+      "loss": 0.4757,
+      "step": 440
+    },
+    {
+      "epoch": 0.7520367662419052,
+      "grad_norm": 0.28623566031455994,
+      "learning_rate": 9.332553541186485e-05,
+      "loss": 0.515,
+      "step": 450
+    },
+    {
+      "epoch": 0.7687486943806142,
+      "grad_norm": 0.30202344059944153,
+      "learning_rate": 9.283249350099859e-05,
+      "loss": 0.5259,
+      "step": 460
+    },
+    {
+      "epoch": 0.7854606225193231,
+      "grad_norm": 0.264213502407074,
+      "learning_rate": 9.23232842192142e-05,
+      "loss": 0.5224,
+      "step": 470
+    },
+    {
+      "epoch": 0.8021725506580322,
+      "grad_norm": 0.2509612739086151,
+      "learning_rate": 9.179809977048248e-05,
+      "loss": 0.5318,
+      "step": 480
+    },
+    {
+      "epoch": 0.8188844787967412,
+      "grad_norm": 0.28840652108192444,
+      "learning_rate": 9.125713838869299e-05,
+      "loss": 0.5287,
+      "step": 490
+    },
+    {
+      "epoch": 0.8355964069354502,
+      "grad_norm": 0.30437350273132324,
+      "learning_rate": 9.070060426282925e-05,
+      "loss": 0.5256,
+      "step": 500
+    },
+    {
+      "epoch": 0.8523083350741592,
+      "grad_norm": 0.3300555646419525,
+      "learning_rate": 9.012870745989663e-05,
+      "loss": 0.4876,
+      "step": 510
+    },
+    {
+      "epoch": 0.8690202632128682,
+      "grad_norm": 0.27293577790260315,
+      "learning_rate": 8.954166384563127e-05,
+      "loss": 0.5136,
+      "step": 520
+    },
+    {
+      "epoch": 0.8857321913515772,
+      "grad_norm": 0.29159626364707947,
+      "learning_rate": 8.893969500302031e-05,
+      "loss": 0.5224,
+      "step": 530
+    },
+    {
+      "epoch": 0.9024441194902862,
+      "grad_norm": 0.34646981954574585,
+      "learning_rate": 8.832302814866416e-05,
+      "loss": 0.5117,
+      "step": 540
+    },
+    {
+      "epoch": 0.9191560476289952,
+      "grad_norm": 0.2947717607021332,
+      "learning_rate": 8.76918960470122e-05,
+      "loss": 0.534,
+      "step": 550
+    },
+    {
+      "epoch": 0.9358679757677042,
+      "grad_norm": 0.2506949305534363,
+      "learning_rate": 8.704653692250466e-05,
+      "loss": 0.5013,
+      "step": 560
+    },
+    {
+      "epoch": 0.9525799039064132,
+      "grad_norm": 0.28196585178375244,
+      "learning_rate": 8.638719436965325e-05,
+      "loss": 0.5089,
+      "step": 570
+    },
+    {
+      "epoch": 0.9692918320451223,
+      "grad_norm": 0.26513898372650146,
+      "learning_rate": 8.571411726109519e-05,
+      "loss": 0.5346,
+      "step": 580
+    },
+    {
+      "epoch": 0.9860037601838312,
+      "grad_norm": 0.3039480149745941,
+      "learning_rate": 8.50275596536546e-05,
+      "loss": 0.5097,
+      "step": 590
+    },
+    {
+      "epoch": 1.0016711928138708,
+      "grad_norm": 0.2783941328525543,
+      "learning_rate": 8.432778069244749e-05,
+      "loss": 0.5139,
+      "step": 600
+    },
+    {
+      "epoch": 1.01838312095258,
+      "grad_norm": 0.2535961866378784,
+      "learning_rate": 8.361504451306585e-05,
+      "loss": 0.4471,
+      "step": 610
+    },
+    {
+      "epoch": 1.035095049091289,
+      "grad_norm": 0.32639509439468384,
+      "learning_rate": 8.288962014187811e-05,
+      "loss": 0.4725,
+      "step": 620
+    },
+    {
+      "epoch": 1.0518069772299978,
+      "grad_norm": 0.3780384361743927,
+      "learning_rate": 8.21517813944837e-05,
+      "loss": 0.4459,
+      "step": 630
+    },
+    {
+      "epoch": 1.068518905368707,
+      "grad_norm": 0.297475129365921,
+      "learning_rate": 8.14018067723597e-05,
+      "loss": 0.4515,
+      "step": 640
+    },
+    {
+      "epoch": 1.085230833507416,
+      "grad_norm": 0.32445859909057617,
+      "learning_rate": 8.063997935773885e-05,
+      "loss": 0.4648,
+      "step": 650
+    },
+    {
+      "epoch": 1.101942761646125,
+      "grad_norm": 0.333881676197052,
+      "learning_rate": 7.986658670675861e-05,
+      "loss": 0.4549,
+      "step": 660
+    },
+    {
+      "epoch": 1.118654689784834,
+      "grad_norm": 0.3279685974121094,
+      "learning_rate": 7.908192074092136e-05,
+      "loss": 0.4768,
+      "step": 670
+    },
+    {
+      "epoch": 1.1353666179235429,
+      "grad_norm": 0.36196866631507874,
+      "learning_rate": 7.828627763690697e-05,
+      "loss": 0.5039,
+      "step": 680
+    },
+    {
+      "epoch": 1.152078546062252,
+      "grad_norm": 0.3395329713821411,
+      "learning_rate": 7.747995771477928e-05,
+      "loss": 0.4628,
+      "step": 690
+    },
+    {
+      "epoch": 1.168790474200961,
+      "grad_norm": 0.3666079342365265,
+      "learning_rate": 7.666326532462842e-05,
+      "loss": 0.444,
+      "step": 700
+    },
+    {
+      "epoch": 1.1855024023396699,
+      "grad_norm": 0.3585106432437897,
+      "learning_rate": 7.583650873169232e-05,
+      "loss": 0.5077,
+      "step": 710
+    },
+    {
+      "epoch": 1.202214330478379,
+      "grad_norm": 0.3411233127117157,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4689,
+      "step": 720
+    },
+    {
+      "epoch": 1.218926258617088,
+      "grad_norm": 0.36491307616233826,
+      "learning_rate": 7.41540548745814e-05,
+      "loss": 0.4509,
+      "step": 730
+    },
+    {
+      "epoch": 1.2356381867557968,
+      "grad_norm": 0.3584769070148468,
+      "learning_rate": 7.329899266228748e-05,
+      "loss": 0.4782,
+      "step": 740
+    },
+    {
+      "epoch": 1.252350114894506,
+      "grad_norm": 0.3567698299884796,
+      "learning_rate": 7.243513611126608e-05,
+      "loss": 0.4287,
+      "step": 750
+    },
+    {
+      "epoch": 1.269062043033215,
+      "grad_norm": 0.36464792490005493,
+      "learning_rate": 7.156281128913871e-05,
+      "loss": 0.4642,
+      "step": 760
+    },
+    {
+      "epoch": 1.285773971171924,
+      "grad_norm": 0.41288235783576965,
+      "learning_rate": 7.068234745992456e-05,
+      "loss": 0.4659,
+      "step": 770
+    },
+    {
+      "epoch": 1.302485899310633,
+      "grad_norm": 0.8390935063362122,
+      "learning_rate": 6.979407695975776e-05,
+      "loss": 0.4932,
+      "step": 780
+    },
+    {
+      "epoch": 1.3191978274493419,
+      "grad_norm": 0.3990253806114197,
+      "learning_rate": 6.889833507144532e-05,
+      "loss": 0.494,
+      "step": 790
+    },
+    {
+      "epoch": 1.335909755588051,
+      "grad_norm": 0.39918258786201477,
+      "learning_rate": 6.799545989791268e-05,
+      "loss": 0.4307,
+      "step": 800
+    },
+    {
+      "epoch": 1.35262168372676,
+      "grad_norm": 0.3962526321411133,
+      "learning_rate": 6.708579223458475e-05,
+      "loss": 0.4515,
+      "step": 810
+    },
+    {
+      "epoch": 1.369333611865469,
+      "grad_norm": 0.366760790348053,
+      "learning_rate": 6.616967544075077e-05,
+      "loss": 0.4783,
+      "step": 820
+    },
+    {
+      "epoch": 1.386045540004178,
+      "grad_norm": 0.3852802515029907,
+      "learning_rate": 6.524745530996137e-05,
+      "loss": 0.4933,
+      "step": 830
+    },
+    {
+      "epoch": 1.402757468142887,
+      "grad_norm": 0.3308377265930176,
+      "learning_rate": 6.431947993950682e-05,
+      "loss": 0.525,
+      "step": 840
+    },
+    {
+      "epoch": 1.4194693962815959,
+      "grad_norm": 0.3748877942562103,
+      "learning_rate": 6.338609959902569e-05,
+      "loss": 0.4752,
+      "step": 850
+    },
+    {
+      "epoch": 1.436181324420305,
+      "grad_norm": 0.37608233094215393,
+      "learning_rate": 6.244766659829351e-05,
+      "loss": 0.4818,
+      "step": 860
+    },
+    {
+      "epoch": 1.452893252559014,
+      "grad_norm": 0.36020001769065857,
+      "learning_rate": 6.150453515424153e-05,
+      "loss": 0.4888,
+      "step": 870
+    },
+    {
+      "epoch": 1.469605180697723,
+      "grad_norm": 0.40768539905548096,
+      "learning_rate": 6.055706125725542e-05,
+      "loss": 0.5247,
+      "step": 880
+    },
+    {
+      "epoch": 1.486317108836432,
+      "grad_norm": 0.397224098443985,
+      "learning_rate": 5.9605602536804673e-05,
+      "loss": 0.4356,
+      "step": 890
+    },
+    {
+      "epoch": 1.503029036975141,
+      "grad_norm": 0.38998743891716003,
+      "learning_rate": 5.865051812645329e-05,
+      "loss": 0.473,
+      "step": 900
+    },
+    {
+      "epoch": 1.51974096511385,
+      "grad_norm": 0.3835464417934418,
+      "learning_rate": 5.7692168528302807e-05,
+      "loss": 0.4716,
+      "step": 910
+    },
+    {
+      "epoch": 1.536452893252559,
+      "grad_norm": 0.3747701644897461,
+      "learning_rate": 5.673091547691866e-05,
+      "loss": 0.432,
+      "step": 920
+    },
+    {
+      "epoch": 1.553164821391268,
+      "grad_norm": 0.3856564462184906,
+      "learning_rate": 5.576712180279133e-05,
+      "loss": 0.5033,
+      "step": 930
+    },
+    {
+      "epoch": 1.569876749529977,
+      "grad_norm": 0.3968600332736969,
+      "learning_rate": 5.480115129538409e-05,
+      "loss": 0.5051,
+      "step": 940
+    },
+    {
+      "epoch": 1.586588677668686,
+      "grad_norm": 0.4307195842266083,
+      "learning_rate": 5.383336856581833e-05,
+      "loss": 0.4576,
+      "step": 950
+    },
+    {
+      "epoch": 1.6033006058073949,
+      "grad_norm": 0.401885449886322,
+      "learning_rate": 5.2864138909249176e-05,
+      "loss": 0.4866,
+      "step": 960
+    },
+    {
+      "epoch": 1.620012533946104,
+      "grad_norm": 0.3600904941558838,
+      "learning_rate": 5.189382816698263e-05,
+      "loss": 0.4844,
+      "step": 970
+    },
+    {
+      "epoch": 1.6367244620848131,
+      "grad_norm": 0.35338348150253296,
+      "learning_rate": 5.0922802588386766e-05,
+      "loss": 0.4991,
+      "step": 980
+    },
+    {
+      "epoch": 1.653436390223522,
+      "grad_norm": 0.37117472290992737,
+      "learning_rate": 4.9951428692648664e-05,
+      "loss": 0.4709,
+      "step": 990
+    },
+    {
+      "epoch": 1.670148318362231,
+      "grad_norm": 0.3381313383579254,
+      "learning_rate": 4.898007313042975e-05,
+      "loss": 0.4474,
+      "step": 1000
+    },
+    {
+      "epoch": 1.68686024650094,
+      "grad_norm": 0.4141668677330017,
+      "learning_rate": 4.8009102545471355e-05,
+      "loss": 0.4849,
+      "step": 1010
+    },
+    {
+      "epoch": 1.703572174639649,
+      "grad_norm": 0.34374451637268066,
+      "learning_rate": 4.7038883436202955e-05,
+      "loss": 0.4409,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7202841027783582,
+      "grad_norm": 0.38313835859298706,
+      "learning_rate": 4.606978201740518e-05,
+      "loss": 0.5049,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7369960309170671,
+      "grad_norm": 0.4117642939090729,
+      "learning_rate": 4.510216408197996e-05,
+      "loss": 0.4487,
+      "step": 1040
+    },
+    {
+      "epoch": 1.753707959055776,
+      "grad_norm": 0.3720339238643646,
+      "learning_rate": 4.4136394862879914e-05,
+      "loss": 0.4641,
+      "step": 1050
+    },
+    {
+      "epoch": 1.770419887194485,
+      "grad_norm": 0.389915406703949,
+      "learning_rate": 4.3172838895249036e-05,
+      "loss": 0.4522,
+      "step": 1060
+    },
+    {
+      "epoch": 1.787131815333194,
+      "grad_norm": 0.4209120273590088,
+      "learning_rate": 4.221185987882684e-05,
+      "loss": 0.485,
+      "step": 1070
+    },
+    {
+      "epoch": 1.803843743471903,
+      "grad_norm": 0.35964861512184143,
+      "learning_rate": 4.125382054066781e-05,
+      "loss": 0.4153,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8205556716106122,
+      "grad_norm": 0.39036113023757935,
+      "learning_rate": 4.029908249822795e-05,
+      "loss": 0.4543,
+      "step": 1090
+    },
+    {
+      "epoch": 1.837267599749321,
+      "grad_norm": 0.41336700320243835,
+      "learning_rate": 3.934800612287019e-05,
+      "loss": 0.4304,
+      "step": 1100
+    },
+    {
+      "epoch": 1.85397952788803,
+      "grad_norm": 0.3797999620437622,
+      "learning_rate": 3.840095040384023e-05,
+      "loss": 0.4792,
+      "step": 1110
+    },
+    {
+      "epoch": 1.870691456026739,
+      "grad_norm": 0.3731176555156708,
+      "learning_rate": 3.7458272812763875e-05,
+      "loss": 0.4559,
+      "step": 1120
+    },
+    {
+      "epoch": 1.887403384165448,
+      "grad_norm": 0.46234622597694397,
+      "learning_rate": 3.652032916871737e-05,
+      "loss": 0.4722,
+      "step": 1130
+    },
+    {
+      "epoch": 1.9041153123041572,
+      "grad_norm": 0.41888976097106934,
+      "learning_rate": 3.558747350392146e-05,
+      "loss": 0.4874,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9208272404428661,
+      "grad_norm": 0.4406299889087677,
+      "learning_rate": 3.466005793010985e-05,
+      "loss": 0.49,
+      "step": 1150
+    },
+    {
+      "epoch": 1.937539168581575,
+      "grad_norm": 0.3967576324939728,
+      "learning_rate": 3.373843250562265e-05,
+      "loss": 0.4246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.954251096720284,
+      "grad_norm": 0.4108339548110962,
+      "learning_rate": 3.282294510327478e-05,
+      "loss": 0.4895,
+      "step": 1170
+    },
+    {
+      "epoch": 1.970963024858993,
+      "grad_norm": 0.4071328341960907,
+      "learning_rate": 3.1913941279049467e-05,
+      "loss": 0.5052,
+      "step": 1180
+    },
+    {
+      "epoch": 1.9876749529977022,
+      "grad_norm": 0.36455124616622925,
+      "learning_rate": 3.101176414166605e-05,
+      "loss": 0.4732,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0033423856277417,
+      "grad_norm": 0.3723292648792267,
+      "learning_rate": 3.011675422307172e-05,
+      "loss": 0.4492,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0200543137664506,
+      "grad_norm": 0.3702923059463501,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.4607,
+      "step": 1210
+    },
+    {
+      "epoch": 2.03676624190516,
+      "grad_norm": 0.3676780164241791,
+      "learning_rate": 2.834958451598465e-05,
+      "loss": 0.4592,
+      "step": 1220
+    },
+    {
+      "epoch": 2.053478170043869,
+      "grad_norm": 0.3695000112056732,
+      "learning_rate": 2.7478091755857422e-05,
+      "loss": 0.4135,
+      "step": 1230
+    },
+    {
+      "epoch": 2.070190098182578,
+      "grad_norm": 0.44124835729599,
+      "learning_rate": 2.6615100019476535e-05,
+      "loss": 0.4485,
+      "step": 1240
+    },
+    {
+      "epoch": 2.0869020263212867,
+      "grad_norm": 0.7185173034667969,
+      "learning_rate": 2.576093504803432e-05,
+      "loss": 0.4462,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1036139544599957,
+      "grad_norm": 0.44661805033683777,
+      "learning_rate": 2.491591925100985e-05,
+      "loss": 0.4683,
+      "step": 1260
+    },
+    {
+      "epoch": 2.120325882598705,
+      "grad_norm": 0.4305351972579956,
+      "learning_rate": 2.4080371584473748e-05,
+      "loss": 0.4428,
+      "step": 1270
+    },
+    {
+      "epoch": 2.137037810737414,
+      "grad_norm": 0.3181787133216858,
+      "learning_rate": 2.325460743069639e-05,
+      "loss": 0.4265,
+      "step": 1280
+    },
+    {
+      "epoch": 2.153749738876123,
+      "grad_norm": 0.4223162829875946,
+      "learning_rate": 2.2438938479104952e-05,
+      "loss": 0.4507,
+      "step": 1290
+    },
+    {
+      "epoch": 2.170461667014832,
+      "grad_norm": 0.4869953989982605,
+      "learning_rate": 2.1633672608634524e-05,
+      "loss": 0.4231,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1871735951535407,
+      "grad_norm": 0.47924432158470154,
+      "learning_rate": 2.0839113771517467e-05,
+      "loss": 0.4123,
+      "step": 1310
+    },
+    {
+      "epoch": 2.20388552329225,
+      "grad_norm": 0.42630112171173096,
+      "learning_rate": 2.0055561878554792e-05,
+      "loss": 0.3807,
+      "step": 1320
+    },
+    {
+      "epoch": 2.220597451430959,
+      "grad_norm": 0.40105777978897095,
+      "learning_rate": 1.928331268591315e-05,
+      "loss": 0.4123,
+      "step": 1330
+    },
+    {
+      "epoch": 2.237309379569668,
+      "grad_norm": 0.39029476046562195,
+      "learning_rate": 1.852265768349006e-05,
+      "loss": 0.4407,
+      "step": 1340
+    },
+    {
+      "epoch": 2.254021307708377,
+      "grad_norm": 0.466331422328949,
+      "learning_rate": 1.777388398488918e-05,
+      "loss": 0.4078,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2707332358470858,
+      "grad_norm": 0.44317781925201416,
+      "learning_rate": 1.7037274219047798e-05,
+      "loss": 0.417,
+      "step": 1360
+    },
+    {
+      "epoch": 2.2874451639857947,
+      "grad_norm": 0.43465059995651245,
+      "learning_rate": 1.6313106423556878e-05,
+      "loss": 0.4599,
+      "step": 1370
+    },
+    {
+      "epoch": 2.304157092124504,
+      "grad_norm": 0.494806706905365,
+      "learning_rate": 1.5601653939714074e-05,
+      "loss": 0.4595,
+      "step": 1380
+    },
+    {
+      "epoch": 2.320869020263213,
+      "grad_norm": 0.3743044435977936,
+      "learning_rate": 1.490318530934957e-05,
+      "loss": 0.4418,
+      "step": 1390
+    },
+    {
+      "epoch": 2.337580948401922,
+      "grad_norm": 0.4087362587451935,
+      "learning_rate": 1.4217964173463472e-05,
+      "loss": 0.4198,
+      "step": 1400
+    },
+    {
+      "epoch": 2.354292876540631,
+      "grad_norm": 0.46890708804130554,
+      "learning_rate": 1.3546249172712849e-05,
+      "loss": 0.4463,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3710048046793397,
+      "grad_norm": 0.43129852414131165,
+      "learning_rate": 1.2888293849786503e-05,
+      "loss": 0.4485,
+      "step": 1420
+    },
+    {
+      "epoch": 2.387716732818049,
+      "grad_norm": 0.456182599067688,
+      "learning_rate": 1.2244346553703667e-05,
+      "loss": 0.4389,
+      "step": 1430
+    },
+    {
+      "epoch": 2.404428660956758,
+      "grad_norm": 0.4355461895465851,
+      "learning_rate": 1.161465034607332e-05,
+      "loss": 0.3875,
+      "step": 1440
+    },
+    {
+      "epoch": 2.421140589095467,
+      "grad_norm": 0.37242934107780457,
+      "learning_rate": 1.0999442909349217e-05,
+      "loss": 0.405,
+      "step": 1450
+    },
+    {
+      "epoch": 2.437852517234176,
+      "grad_norm": 0.4564312696456909,
+      "learning_rate": 1.0398956457115194e-05,
+      "loss": 0.4153,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4545644453728848,
+      "grad_norm": 0.4565236270427704,
+      "learning_rate": 9.813417646434864e-06,
+      "loss": 0.4386,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4712763735115937,
+      "grad_norm": 0.4497516453266144,
+      "learning_rate": 9.243047492298634e-06,
+      "loss": 0.4188,
+      "step": 1480
+    },
+    {
+      "epoch": 2.487988301650303,
+      "grad_norm": 0.5003072619438171,
+      "learning_rate": 8.688061284200266e-06,
+      "loss": 0.3996,
+      "step": 1490
+    },
+    {
+      "epoch": 2.504700229789012,
+      "grad_norm": 0.45389190316200256,
+      "learning_rate": 8.148668504874623e-06,
+      "loss": 0.377,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1797,
+  "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": 5.635063727605678e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c2331f16b8cdb74d728a7328480d3810e4c52d40a7803ab25c874ac59b6fa2
+size 5752

checkpoint-1797/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /root/paddlejob/workspace/env_run/output/llm/Qwen3-8B
+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

checkpoint-1797/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1797/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c623b00d9a2cf3b7d78ddeba1b9a8d65ffd0c847bd990dbd2db979a89c25a30
+size 87360584

checkpoint-1797/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
+}

checkpoint-1797/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-1797/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f07b92ed22e38dced2b81cefa99d7ac569d8a395f21c05ec61ebc6a733201fdf
+size 175012218

checkpoint-1797/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-1797/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509e8c22eb5337b17cd47669f188570d521aec1349ed035b4f24cb2c48c0e4ba
+size 1064

checkpoint-1797/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
+  }
+}

checkpoint-1797/tokenizer.json

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

checkpoint-1797/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
+}

checkpoint-1797/trainer_state.json

@@ -0,0 +1,1287 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1797,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016711928138709004,
+      "grad_norm": 0.5531014800071716,
+      "learning_rate": 5e-06,
+      "loss": 0.9993,
+      "step": 10
+    },
+    {
+      "epoch": 0.03342385627741801,
+      "grad_norm": 0.5198462009429932,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 0.9973,
+      "step": 20
+    },
+    {
+      "epoch": 0.05013578441612701,
+      "grad_norm": 0.9699999094009399,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 0.9474,
+      "step": 30
+    },
+    {
+      "epoch": 0.06684771255483601,
+      "grad_norm": 0.3459213078022003,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.7622,
+      "step": 40
+    },
+    {
+      "epoch": 0.08355964069354502,
+      "grad_norm": 0.24512118101119995,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 0.7086,
+      "step": 50
+    },
+    {
+      "epoch": 0.10027156883225402,
+      "grad_norm": 0.21762403845787048,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 0.6895,
+      "step": 60
+    },
+    {
+      "epoch": 0.11698349697096302,
+      "grad_norm": 0.22329938411712646,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.6491,
+      "step": 70
+    },
+    {
+      "epoch": 0.13369542510967203,
+      "grad_norm": 0.19780907034873962,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 0.6225,
+      "step": 80
+    },
+    {
+      "epoch": 0.15040735324838103,
+      "grad_norm": 0.17309053242206573,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 0.6026,
+      "step": 90
+    },
+    {
+      "epoch": 0.16711928138709004,
+      "grad_norm": 0.20399844646453857,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5435,
+      "step": 100
+    },
+    {
+      "epoch": 0.18383120952579904,
+      "grad_norm": 0.21713724732398987,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 0.581,
+      "step": 110
+    },
+    {
+      "epoch": 0.20054313766450804,
+      "grad_norm": 0.24566805362701416,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 0.5203,
+      "step": 120
+    },
+    {
+      "epoch": 0.21725506580321705,
+      "grad_norm": 0.26538822054862976,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 0.5975,
+      "step": 130
+    },
+    {
+      "epoch": 0.23396699394192605,
+      "grad_norm": 0.24092447757720947,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 0.5627,
+      "step": 140
+    },
+    {
+      "epoch": 0.2506789220806351,
+      "grad_norm": 0.24146470427513123,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 0.5289,
+      "step": 150
+    },
+    {
+      "epoch": 0.26739085021934406,
+      "grad_norm": 0.8219459652900696,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 0.5347,
+      "step": 160
+    },
+    {
+      "epoch": 0.2841027783580531,
+      "grad_norm": 0.2518085241317749,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 0.5491,
+      "step": 170
+    },
+    {
+      "epoch": 0.30081470649676206,
+      "grad_norm": 0.2775290012359619,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 0.5701,
+      "step": 180
+    },
+    {
+      "epoch": 0.3175266346354711,
+      "grad_norm": 0.2761514186859131,
+      "learning_rate": 9.999235647539953e-05,
+      "loss": 0.5489,
+      "step": 190
+    },
+    {
+      "epoch": 0.33423856277418007,
+      "grad_norm": 0.32875457406044006,
+      "learning_rate": 9.996593741531468e-05,
+      "loss": 0.5374,
+      "step": 200
+    },
+    {
+      "epoch": 0.3509504909128891,
+      "grad_norm": 0.2761303186416626,
+      "learning_rate": 9.992065842489567e-05,
+      "loss": 0.4916,
+      "step": 210
+    },
+    {
+      "epoch": 0.3676624190515981,
+      "grad_norm": 0.2781451940536499,
+      "learning_rate": 9.985653659495773e-05,
+      "loss": 0.5826,
+      "step": 220
+    },
+    {
+      "epoch": 0.3843743471903071,
+      "grad_norm": 0.32615798711776733,
+      "learning_rate": 9.977359612865423e-05,
+      "loss": 0.532,
+      "step": 230
+    },
+    {
+      "epoch": 0.4010862753290161,
+      "grad_norm": 0.2824324667453766,
+      "learning_rate": 9.967186833234101e-05,
+      "loss": 0.5482,
+      "step": 240
+    },
+    {
+      "epoch": 0.4177982034677251,
+      "grad_norm": 0.2630137503147125,
+      "learning_rate": 9.955139160375959e-05,
+      "loss": 0.4917,
+      "step": 250
+    },
+    {
+      "epoch": 0.4345101316064341,
+      "grad_norm": 0.3076798915863037,
+      "learning_rate": 9.941221141754385e-05,
+      "loss": 0.5285,
+      "step": 260
+    },
+    {
+      "epoch": 0.4512220597451431,
+      "grad_norm": 0.3244406282901764,
+      "learning_rate": 9.925438030805518e-05,
+      "loss": 0.5178,
+      "step": 270
+    },
+    {
+      "epoch": 0.4679339878838521,
+      "grad_norm": 0.3224153220653534,
+      "learning_rate": 9.907795784955327e-05,
+      "loss": 0.5184,
+      "step": 280
+    },
+    {
+      "epoch": 0.48464591602256113,
+      "grad_norm": 0.3541305959224701,
+      "learning_rate": 9.888301063370934e-05,
+      "loss": 0.5327,
+      "step": 290
+    },
+    {
+      "epoch": 0.5013578441612702,
+      "grad_norm": 0.28691530227661133,
+      "learning_rate": 9.866961224447075e-05,
+      "loss": 0.5461,
+      "step": 300
+    },
+    {
+      "epoch": 0.5180697722999791,
+      "grad_norm": 0.4132674038410187,
+      "learning_rate": 9.843784323028638e-05,
+      "loss": 0.5242,
+      "step": 310
+    },
+    {
+      "epoch": 0.5347817004386881,
+      "grad_norm": 0.33508822321891785,
+      "learning_rate": 9.818779107370309e-05,
+      "loss": 0.5285,
+      "step": 320
+    },
+    {
+      "epoch": 0.5514936285773971,
+      "grad_norm": 0.2662738561630249,
+      "learning_rate": 9.791955015834492e-05,
+      "loss": 0.5287,
+      "step": 330
+    },
+    {
+      "epoch": 0.5682055567161062,
+      "grad_norm": 0.30024951696395874,
+      "learning_rate": 9.763322173328753e-05,
+      "loss": 0.5329,
+      "step": 340
+    },
+    {
+      "epoch": 0.5849174848548151,
+      "grad_norm": 0.27861520648002625,
+      "learning_rate": 9.732891387484104e-05,
+      "loss": 0.4656,
+      "step": 350
+    },
+    {
+      "epoch": 0.6016294129935241,
+      "grad_norm": 0.33017635345458984,
+      "learning_rate": 9.700674144575614e-05,
+      "loss": 0.5334,
+      "step": 360
+    },
+    {
+      "epoch": 0.6183413411322332,
+      "grad_norm": 0.3784632384777069,
+      "learning_rate": 9.666682605186835e-05,
+      "loss": 0.4669,
+      "step": 370
+    },
+    {
+      "epoch": 0.6350532692709422,
+      "grad_norm": 0.3362145721912384,
+      "learning_rate": 9.63092959961973e-05,
+      "loss": 0.4938,
+      "step": 380
+    },
+    {
+      "epoch": 0.6517651974096511,
+      "grad_norm": 0.2863125801086426,
+      "learning_rate": 9.593428623051792e-05,
+      "loss": 0.4815,
+      "step": 390
+    },
+    {
+      "epoch": 0.6684771255483601,
+      "grad_norm": 0.23034977912902832,
+      "learning_rate": 9.554193830442229e-05,
+      "loss": 0.5249,
+      "step": 400
+    },
+    {
+      "epoch": 0.6851890536870692,
+      "grad_norm": 0.29409608244895935,
+      "learning_rate": 9.513240031189067e-05,
+      "loss": 0.4899,
+      "step": 410
+    },
+    {
+      "epoch": 0.7019009818257782,
+      "grad_norm": 0.3073919415473938,
+      "learning_rate": 9.470582683539285e-05,
+      "loss": 0.5115,
+      "step": 420
+    },
+    {
+      "epoch": 0.7186129099644871,
+      "grad_norm": 0.33221715688705444,
+      "learning_rate": 9.42623788875399e-05,
+      "loss": 0.5021,
+      "step": 430
+    },
+    {
+      "epoch": 0.7353248381031962,
+      "grad_norm": 0.24137817323207855,
+      "learning_rate": 9.380222385030915e-05,
+      "loss": 0.4757,
+      "step": 440
+    },
+    {
+      "epoch": 0.7520367662419052,
+      "grad_norm": 0.28623566031455994,
+      "learning_rate": 9.332553541186485e-05,
+      "loss": 0.515,
+      "step": 450
+    },
+    {
+      "epoch": 0.7687486943806142,
+      "grad_norm": 0.30202344059944153,
+      "learning_rate": 9.283249350099859e-05,
+      "loss": 0.5259,
+      "step": 460
+    },
+    {
+      "epoch": 0.7854606225193231,
+      "grad_norm": 0.264213502407074,
+      "learning_rate": 9.23232842192142e-05,
+      "loss": 0.5224,
+      "step": 470
+    },
+    {
+      "epoch": 0.8021725506580322,
+      "grad_norm": 0.2509612739086151,
+      "learning_rate": 9.179809977048248e-05,
+      "loss": 0.5318,
+      "step": 480
+    },
+    {
+      "epoch": 0.8188844787967412,
+      "grad_norm": 0.28840652108192444,
+      "learning_rate": 9.125713838869299e-05,
+      "loss": 0.5287,
+      "step": 490
+    },
+    {
+      "epoch": 0.8355964069354502,
+      "grad_norm": 0.30437350273132324,
+      "learning_rate": 9.070060426282925e-05,
+      "loss": 0.5256,
+      "step": 500
+    },
+    {
+      "epoch": 0.8523083350741592,
+      "grad_norm": 0.3300555646419525,
+      "learning_rate": 9.012870745989663e-05,
+      "loss": 0.4876,
+      "step": 510
+    },
+    {
+      "epoch": 0.8690202632128682,
+      "grad_norm": 0.27293577790260315,
+      "learning_rate": 8.954166384563127e-05,
+      "loss": 0.5136,
+      "step": 520
+    },
+    {
+      "epoch": 0.8857321913515772,
+      "grad_norm": 0.29159626364707947,
+      "learning_rate": 8.893969500302031e-05,
+      "loss": 0.5224,
+      "step": 530
+    },
+    {
+      "epoch": 0.9024441194902862,
+      "grad_norm": 0.34646981954574585,
+      "learning_rate": 8.832302814866416e-05,
+      "loss": 0.5117,
+      "step": 540
+    },
+    {
+      "epoch": 0.9191560476289952,
+      "grad_norm": 0.2947717607021332,
+      "learning_rate": 8.76918960470122e-05,
+      "loss": 0.534,
+      "step": 550
+    },
+    {
+      "epoch": 0.9358679757677042,
+      "grad_norm": 0.2506949305534363,
+      "learning_rate": 8.704653692250466e-05,
+      "loss": 0.5013,
+      "step": 560
+    },
+    {
+      "epoch": 0.9525799039064132,
+      "grad_norm": 0.28196585178375244,
+      "learning_rate": 8.638719436965325e-05,
+      "loss": 0.5089,
+      "step": 570
+    },
+    {
+      "epoch": 0.9692918320451223,
+      "grad_norm": 0.26513898372650146,
+      "learning_rate": 8.571411726109519e-05,
+      "loss": 0.5346,
+      "step": 580
+    },
+    {
+      "epoch": 0.9860037601838312,
+      "grad_norm": 0.3039480149745941,
+      "learning_rate": 8.50275596536546e-05,
+      "loss": 0.5097,
+      "step": 590
+    },
+    {
+      "epoch": 1.0016711928138708,
+      "grad_norm": 0.2783941328525543,
+      "learning_rate": 8.432778069244749e-05,
+      "loss": 0.5139,
+      "step": 600
+    },
+    {
+      "epoch": 1.01838312095258,
+      "grad_norm": 0.2535961866378784,
+      "learning_rate": 8.361504451306585e-05,
+      "loss": 0.4471,
+      "step": 610
+    },
+    {
+      "epoch": 1.035095049091289,
+      "grad_norm": 0.32639509439468384,
+      "learning_rate": 8.288962014187811e-05,
+      "loss": 0.4725,
+      "step": 620
+    },
+    {
+      "epoch": 1.0518069772299978,
+      "grad_norm": 0.3780384361743927,
+      "learning_rate": 8.21517813944837e-05,
+      "loss": 0.4459,
+      "step": 630
+    },
+    {
+      "epoch": 1.068518905368707,
+      "grad_norm": 0.297475129365921,
+      "learning_rate": 8.14018067723597e-05,
+      "loss": 0.4515,
+      "step": 640
+    },
+    {
+      "epoch": 1.085230833507416,
+      "grad_norm": 0.32445859909057617,
+      "learning_rate": 8.063997935773885e-05,
+      "loss": 0.4648,
+      "step": 650
+    },
+    {
+      "epoch": 1.101942761646125,
+      "grad_norm": 0.333881676197052,
+      "learning_rate": 7.986658670675861e-05,
+      "loss": 0.4549,
+      "step": 660
+    },
+    {
+      "epoch": 1.118654689784834,
+      "grad_norm": 0.3279685974121094,
+      "learning_rate": 7.908192074092136e-05,
+      "loss": 0.4768,
+      "step": 670
+    },
+    {
+      "epoch": 1.1353666179235429,
+      "grad_norm": 0.36196866631507874,
+      "learning_rate": 7.828627763690697e-05,
+      "loss": 0.5039,
+      "step": 680
+    },
+    {
+      "epoch": 1.152078546062252,
+      "grad_norm": 0.3395329713821411,
+      "learning_rate": 7.747995771477928e-05,
+      "loss": 0.4628,
+      "step": 690
+    },
+    {
+      "epoch": 1.168790474200961,
+      "grad_norm": 0.3666079342365265,
+      "learning_rate": 7.666326532462842e-05,
+      "loss": 0.444,
+      "step": 700
+    },
+    {
+      "epoch": 1.1855024023396699,
+      "grad_norm": 0.3585106432437897,
+      "learning_rate": 7.583650873169232e-05,
+      "loss": 0.5077,
+      "step": 710
+    },
+    {
+      "epoch": 1.202214330478379,
+      "grad_norm": 0.3411233127117157,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4689,
+      "step": 720
+    },
+    {
+      "epoch": 1.218926258617088,
+      "grad_norm": 0.36491307616233826,
+      "learning_rate": 7.41540548745814e-05,
+      "loss": 0.4509,
+      "step": 730
+    },
+    {
+      "epoch": 1.2356381867557968,
+      "grad_norm": 0.3584769070148468,
+      "learning_rate": 7.329899266228748e-05,
+      "loss": 0.4782,
+      "step": 740
+    },
+    {
+      "epoch": 1.252350114894506,
+      "grad_norm": 0.3567698299884796,
+      "learning_rate": 7.243513611126608e-05,
+      "loss": 0.4287,
+      "step": 750
+    },
+    {
+      "epoch": 1.269062043033215,
+      "grad_norm": 0.36464792490005493,
+      "learning_rate": 7.156281128913871e-05,
+      "loss": 0.4642,
+      "step": 760
+    },
+    {
+      "epoch": 1.285773971171924,
+      "grad_norm": 0.41288235783576965,
+      "learning_rate": 7.068234745992456e-05,
+      "loss": 0.4659,
+      "step": 770
+    },
+    {
+      "epoch": 1.302485899310633,
+      "grad_norm": 0.8390935063362122,
+      "learning_rate": 6.979407695975776e-05,
+      "loss": 0.4932,
+      "step": 780
+    },
+    {
+      "epoch": 1.3191978274493419,
+      "grad_norm": 0.3990253806114197,
+      "learning_rate": 6.889833507144532e-05,
+      "loss": 0.494,
+      "step": 790
+    },
+    {
+      "epoch": 1.335909755588051,
+      "grad_norm": 0.39918258786201477,
+      "learning_rate": 6.799545989791268e-05,
+      "loss": 0.4307,
+      "step": 800
+    },
+    {
+      "epoch": 1.35262168372676,
+      "grad_norm": 0.3962526321411133,
+      "learning_rate": 6.708579223458475e-05,
+      "loss": 0.4515,
+      "step": 810
+    },
+    {
+      "epoch": 1.369333611865469,
+      "grad_norm": 0.366760790348053,
+      "learning_rate": 6.616967544075077e-05,
+      "loss": 0.4783,
+      "step": 820
+    },
+    {
+      "epoch": 1.386045540004178,
+      "grad_norm": 0.3852802515029907,
+      "learning_rate": 6.524745530996137e-05,
+      "loss": 0.4933,
+      "step": 830
+    },
+    {
+      "epoch": 1.402757468142887,
+      "grad_norm": 0.3308377265930176,
+      "learning_rate": 6.431947993950682e-05,
+      "loss": 0.525,
+      "step": 840
+    },
+    {
+      "epoch": 1.4194693962815959,
+      "grad_norm": 0.3748877942562103,
+      "learning_rate": 6.338609959902569e-05,
+      "loss": 0.4752,
+      "step": 850
+    },
+    {
+      "epoch": 1.436181324420305,
+      "grad_norm": 0.37608233094215393,
+      "learning_rate": 6.244766659829351e-05,
+      "loss": 0.4818,
+      "step": 860
+    },
+    {
+      "epoch": 1.452893252559014,
+      "grad_norm": 0.36020001769065857,
+      "learning_rate": 6.150453515424153e-05,
+      "loss": 0.4888,
+      "step": 870
+    },
+    {
+      "epoch": 1.469605180697723,
+      "grad_norm": 0.40768539905548096,
+      "learning_rate": 6.055706125725542e-05,
+      "loss": 0.5247,
+      "step": 880
+    },
+    {
+      "epoch": 1.486317108836432,
+      "grad_norm": 0.397224098443985,
+      "learning_rate": 5.9605602536804673e-05,
+      "loss": 0.4356,
+      "step": 890
+    },
+    {
+      "epoch": 1.503029036975141,
+      "grad_norm": 0.38998743891716003,
+      "learning_rate": 5.865051812645329e-05,
+      "loss": 0.473,
+      "step": 900
+    },
+    {
+      "epoch": 1.51974096511385,
+      "grad_norm": 0.3835464417934418,
+      "learning_rate": 5.7692168528302807e-05,
+      "loss": 0.4716,
+      "step": 910
+    },
+    {
+      "epoch": 1.536452893252559,
+      "grad_norm": 0.3747701644897461,
+      "learning_rate": 5.673091547691866e-05,
+      "loss": 0.432,
+      "step": 920
+    },
+    {
+      "epoch": 1.553164821391268,
+      "grad_norm": 0.3856564462184906,
+      "learning_rate": 5.576712180279133e-05,
+      "loss": 0.5033,
+      "step": 930
+    },
+    {
+      "epoch": 1.569876749529977,
+      "grad_norm": 0.3968600332736969,
+      "learning_rate": 5.480115129538409e-05,
+      "loss": 0.5051,
+      "step": 940
+    },
+    {
+      "epoch": 1.586588677668686,
+      "grad_norm": 0.4307195842266083,
+      "learning_rate": 5.383336856581833e-05,
+      "loss": 0.4576,
+      "step": 950
+    },
+    {
+      "epoch": 1.6033006058073949,
+      "grad_norm": 0.401885449886322,
+      "learning_rate": 5.2864138909249176e-05,
+      "loss": 0.4866,
+      "step": 960
+    },
+    {
+      "epoch": 1.620012533946104,
+      "grad_norm": 0.3600904941558838,
+      "learning_rate": 5.189382816698263e-05,
+      "loss": 0.4844,
+      "step": 970
+    },
+    {
+      "epoch": 1.6367244620848131,
+      "grad_norm": 0.35338348150253296,
+      "learning_rate": 5.0922802588386766e-05,
+      "loss": 0.4991,
+      "step": 980
+    },
+    {
+      "epoch": 1.653436390223522,
+      "grad_norm": 0.37117472290992737,
+      "learning_rate": 4.9951428692648664e-05,
+      "loss": 0.4709,
+      "step": 990
+    },
+    {
+      "epoch": 1.670148318362231,
+      "grad_norm": 0.3381313383579254,
+      "learning_rate": 4.898007313042975e-05,
+      "loss": 0.4474,
+      "step": 1000
+    },
+    {
+      "epoch": 1.68686024650094,
+      "grad_norm": 0.4141668677330017,
+      "learning_rate": 4.8009102545471355e-05,
+      "loss": 0.4849,
+      "step": 1010
+    },
+    {
+      "epoch": 1.703572174639649,
+      "grad_norm": 0.34374451637268066,
+      "learning_rate": 4.7038883436202955e-05,
+      "loss": 0.4409,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7202841027783582,
+      "grad_norm": 0.38313835859298706,
+      "learning_rate": 4.606978201740518e-05,
+      "loss": 0.5049,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7369960309170671,
+      "grad_norm": 0.4117642939090729,
+      "learning_rate": 4.510216408197996e-05,
+      "loss": 0.4487,
+      "step": 1040
+    },
+    {
+      "epoch": 1.753707959055776,
+      "grad_norm": 0.3720339238643646,
+      "learning_rate": 4.4136394862879914e-05,
+      "loss": 0.4641,
+      "step": 1050
+    },
+    {
+      "epoch": 1.770419887194485,
+      "grad_norm": 0.389915406703949,
+      "learning_rate": 4.3172838895249036e-05,
+      "loss": 0.4522,
+      "step": 1060
+    },
+    {
+      "epoch": 1.787131815333194,
+      "grad_norm": 0.4209120273590088,
+      "learning_rate": 4.221185987882684e-05,
+      "loss": 0.485,
+      "step": 1070
+    },
+    {
+      "epoch": 1.803843743471903,
+      "grad_norm": 0.35964861512184143,
+      "learning_rate": 4.125382054066781e-05,
+      "loss": 0.4153,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8205556716106122,
+      "grad_norm": 0.39036113023757935,
+      "learning_rate": 4.029908249822795e-05,
+      "loss": 0.4543,
+      "step": 1090
+    },
+    {
+      "epoch": 1.837267599749321,
+      "grad_norm": 0.41336700320243835,
+      "learning_rate": 3.934800612287019e-05,
+      "loss": 0.4304,
+      "step": 1100
+    },
+    {
+      "epoch": 1.85397952788803,
+      "grad_norm": 0.3797999620437622,
+      "learning_rate": 3.840095040384023e-05,
+      "loss": 0.4792,
+      "step": 1110
+    },
+    {
+      "epoch": 1.870691456026739,
+      "grad_norm": 0.3731176555156708,
+      "learning_rate": 3.7458272812763875e-05,
+      "loss": 0.4559,
+      "step": 1120
+    },
+    {
+      "epoch": 1.887403384165448,
+      "grad_norm": 0.46234622597694397,
+      "learning_rate": 3.652032916871737e-05,
+      "loss": 0.4722,
+      "step": 1130
+    },
+    {
+      "epoch": 1.9041153123041572,
+      "grad_norm": 0.41888976097106934,
+      "learning_rate": 3.558747350392146e-05,
+      "loss": 0.4874,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9208272404428661,
+      "grad_norm": 0.4406299889087677,
+      "learning_rate": 3.466005793010985e-05,
+      "loss": 0.49,
+      "step": 1150
+    },
+    {
+      "epoch": 1.937539168581575,
+      "grad_norm": 0.3967576324939728,
+      "learning_rate": 3.373843250562265e-05,
+      "loss": 0.4246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.954251096720284,
+      "grad_norm": 0.4108339548110962,
+      "learning_rate": 3.282294510327478e-05,
+      "loss": 0.4895,
+      "step": 1170
+    },
+    {
+      "epoch": 1.970963024858993,
+      "grad_norm": 0.4071328341960907,
+      "learning_rate": 3.1913941279049467e-05,
+      "loss": 0.5052,
+      "step": 1180
+    },
+    {
+      "epoch": 1.9876749529977022,
+      "grad_norm": 0.36455124616622925,
+      "learning_rate": 3.101176414166605e-05,
+      "loss": 0.4732,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0033423856277417,
+      "grad_norm": 0.3723292648792267,
+      "learning_rate": 3.011675422307172e-05,
+      "loss": 0.4492,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0200543137664506,
+      "grad_norm": 0.3702923059463501,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.4607,
+      "step": 1210
+    },
+    {
+      "epoch": 2.03676624190516,
+      "grad_norm": 0.3676780164241791,
+      "learning_rate": 2.834958451598465e-05,
+      "loss": 0.4592,
+      "step": 1220
+    },
+    {
+      "epoch": 2.053478170043869,
+      "grad_norm": 0.3695000112056732,
+      "learning_rate": 2.7478091755857422e-05,
+      "loss": 0.4135,
+      "step": 1230
+    },
+    {
+      "epoch": 2.070190098182578,
+      "grad_norm": 0.44124835729599,
+      "learning_rate": 2.6615100019476535e-05,
+      "loss": 0.4485,
+      "step": 1240
+    },
+    {
+      "epoch": 2.0869020263212867,
+      "grad_norm": 0.7185173034667969,
+      "learning_rate": 2.576093504803432e-05,
+      "loss": 0.4462,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1036139544599957,
+      "grad_norm": 0.44661805033683777,
+      "learning_rate": 2.491591925100985e-05,
+      "loss": 0.4683,
+      "step": 1260
+    },
+    {
+      "epoch": 2.120325882598705,
+      "grad_norm": 0.4305351972579956,
+      "learning_rate": 2.4080371584473748e-05,
+      "loss": 0.4428,
+      "step": 1270
+    },
+    {
+      "epoch": 2.137037810737414,
+      "grad_norm": 0.3181787133216858,
+      "learning_rate": 2.325460743069639e-05,
+      "loss": 0.4265,
+      "step": 1280
+    },
+    {
+      "epoch": 2.153749738876123,
+      "grad_norm": 0.4223162829875946,
+      "learning_rate": 2.2438938479104952e-05,
+      "loss": 0.4507,
+      "step": 1290
+    },
+    {
+      "epoch": 2.170461667014832,
+      "grad_norm": 0.4869953989982605,
+      "learning_rate": 2.1633672608634524e-05,
+      "loss": 0.4231,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1871735951535407,
+      "grad_norm": 0.47924432158470154,
+      "learning_rate": 2.0839113771517467e-05,
+      "loss": 0.4123,
+      "step": 1310
+    },
+    {
+      "epoch": 2.20388552329225,
+      "grad_norm": 0.42630112171173096,
+      "learning_rate": 2.0055561878554792e-05,
+      "loss": 0.3807,
+      "step": 1320
+    },
+    {
+      "epoch": 2.220597451430959,
+      "grad_norm": 0.40105777978897095,
+      "learning_rate": 1.928331268591315e-05,
+      "loss": 0.4123,
+      "step": 1330
+    },
+    {
+      "epoch": 2.237309379569668,
+      "grad_norm": 0.39029476046562195,
+      "learning_rate": 1.852265768349006e-05,
+      "loss": 0.4407,
+      "step": 1340
+    },
+    {
+      "epoch": 2.254021307708377,
+      "grad_norm": 0.466331422328949,
+      "learning_rate": 1.777388398488918e-05,
+      "loss": 0.4078,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2707332358470858,
+      "grad_norm": 0.44317781925201416,
+      "learning_rate": 1.7037274219047798e-05,
+      "loss": 0.417,
+      "step": 1360
+    },
+    {
+      "epoch": 2.2874451639857947,
+      "grad_norm": 0.43465059995651245,
+      "learning_rate": 1.6313106423556878e-05,
+      "loss": 0.4599,
+      "step": 1370
+    },
+    {
+      "epoch": 2.304157092124504,
+      "grad_norm": 0.494806706905365,
+      "learning_rate": 1.5601653939714074e-05,
+      "loss": 0.4595,
+      "step": 1380
+    },
+    {
+      "epoch": 2.320869020263213,
+      "grad_norm": 0.3743044435977936,
+      "learning_rate": 1.490318530934957e-05,
+      "loss": 0.4418,
+      "step": 1390
+    },
+    {
+      "epoch": 2.337580948401922,
+      "grad_norm": 0.4087362587451935,
+      "learning_rate": 1.4217964173463472e-05,
+      "loss": 0.4198,
+      "step": 1400
+    },
+    {
+      "epoch": 2.354292876540631,
+      "grad_norm": 0.46890708804130554,
+      "learning_rate": 1.3546249172712849e-05,
+      "loss": 0.4463,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3710048046793397,
+      "grad_norm": 0.43129852414131165,
+      "learning_rate": 1.2888293849786503e-05,
+      "loss": 0.4485,
+      "step": 1420
+    },
+    {
+      "epoch": 2.387716732818049,
+      "grad_norm": 0.456182599067688,
+      "learning_rate": 1.2244346553703667e-05,
+      "loss": 0.4389,
+      "step": 1430
+    },
+    {
+      "epoch": 2.404428660956758,
+      "grad_norm": 0.4355461895465851,
+      "learning_rate": 1.161465034607332e-05,
+      "loss": 0.3875,
+      "step": 1440
+    },
+    {
+      "epoch": 2.421140589095467,
+      "grad_norm": 0.37242934107780457,
+      "learning_rate": 1.0999442909349217e-05,
+      "loss": 0.405,
+      "step": 1450
+    },
+    {
+      "epoch": 2.437852517234176,
+      "grad_norm": 0.4564312696456909,
+      "learning_rate": 1.0398956457115194e-05,
+      "loss": 0.4153,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4545644453728848,
+      "grad_norm": 0.4565236270427704,
+      "learning_rate": 9.813417646434864e-06,
+      "loss": 0.4386,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4712763735115937,
+      "grad_norm": 0.4497516453266144,
+      "learning_rate": 9.243047492298634e-06,
+      "loss": 0.4188,
+      "step": 1480
+    },
+    {
+      "epoch": 2.487988301650303,
+      "grad_norm": 0.5003072619438171,
+      "learning_rate": 8.688061284200266e-06,
+      "loss": 0.3996,
+      "step": 1490
+    },
+    {
+      "epoch": 2.504700229789012,
+      "grad_norm": 0.45389190316200256,
+      "learning_rate": 8.148668504874623e-06,
+      "loss": 0.377,
+      "step": 1500
+    },
+    {
+      "epoch": 2.521412157927721,
+      "grad_norm": 0.4920840263366699,
+      "learning_rate": 7.625072751227297e-06,
+      "loss": 0.3939,
+      "step": 1510
+    },
+    {
+      "epoch": 2.53812408606643,
+      "grad_norm": 0.38830721378326416,
+      "learning_rate": 7.117471657485663e-06,
+      "loss": 0.4011,
+      "step": 1520
+    },
+    {
+      "epoch": 2.554836014205139,
+      "grad_norm": 0.47151267528533936,
+      "learning_rate": 6.626056820600768e-06,
+      "loss": 0.4485,
+      "step": 1530
+    },
+    {
+      "epoch": 2.571547942343848,
+      "grad_norm": 0.47489333152770996,
+      "learning_rate": 6.151013727927984e-06,
+      "loss": 0.4418,
+      "step": 1540
+    },
+    {
+      "epoch": 2.588259870482557,
+      "grad_norm": 0.4408549666404724,
+      "learning_rate": 5.69252168721367e-06,
+      "loss": 0.4077,
+      "step": 1550
+    },
+    {
+      "epoch": 2.604971798621266,
+      "grad_norm": 0.45609548687934875,
+      "learning_rate": 5.250753758914506e-06,
+      "loss": 0.398,
+      "step": 1560
+    },
+    {
+      "epoch": 2.621683726759975,
+      "grad_norm": 0.4423038363456726,
+      "learning_rate": 4.82587669087477e-06,
+      "loss": 0.4327,
+      "step": 1570
+    },
+    {
+      "epoch": 2.6383956548986838,
+      "grad_norm": 0.4574050307273865,
+      "learning_rate": 4.418050855386413e-06,
+      "loss": 0.388,
+      "step": 1580
+    },
+    {
+      "epoch": 2.6551075830373927,
+      "grad_norm": 0.4758591949939728,
+      "learning_rate": 4.027430188655684e-06,
+      "loss": 0.4684,
+      "step": 1590
+    },
+    {
+      "epoch": 2.671819511176102,
+      "grad_norm": 0.44531774520874023,
+      "learning_rate": 3.654162132698918e-06,
+      "loss": 0.4378,
+      "step": 1600
+    },
+    {
+      "epoch": 2.688531439314811,
+      "grad_norm": 0.45729854702949524,
+      "learning_rate": 3.298387579689771e-06,
+      "loss": 0.4334,
+      "step": 1610
+    },
+    {
+      "epoch": 2.70524336745352,
+      "grad_norm": 0.3810584247112274,
+      "learning_rate": 2.960240818778659e-06,
+      "loss": 0.3903,
+      "step": 1620
+    },
+    {
+      "epoch": 2.721955295592229,
+      "grad_norm": 0.39533549547195435,
+      "learning_rate": 2.639849485404505e-06,
+      "loss": 0.4296,
+      "step": 1630
+    },
+    {
+      "epoch": 2.738667223730938,
+      "grad_norm": 0.36610159277915955,
+      "learning_rate": 2.3373345131180224e-06,
+      "loss": 0.4175,
+      "step": 1640
+    },
+    {
+      "epoch": 2.755379151869647,
+      "grad_norm": 0.45609691739082336,
+      "learning_rate": 2.052810087934698e-06,
+      "loss": 0.3886,
+      "step": 1650
+    },
+    {
+      "epoch": 2.772091080008356,
+      "grad_norm": 0.44251516461372375,
+      "learning_rate": 1.7863836052345429e-06,
+      "loss": 0.4099,
+      "step": 1660
+    },
+    {
+      "epoch": 2.788803008147065,
+      "grad_norm": 0.4892220199108124,
+      "learning_rate": 1.5381556292251632e-06,
+      "loss": 0.4733,
+      "step": 1670
+    },
+    {
+      "epoch": 2.805514936285774,
+      "grad_norm": 0.43403947353363037,
+      "learning_rate": 1.3082198549831836e-06,
+      "loss": 0.4303,
+      "step": 1680
+    },
+    {
+      "epoch": 2.822226864424483,
+      "grad_norm": 0.5250228643417358,
+      "learning_rate": 1.0966630730884887e-06,
+      "loss": 0.438,
+      "step": 1690
+    },
+    {
+      "epoch": 2.8389387925631917,
+      "grad_norm": 0.46305549144744873,
+      "learning_rate": 9.035651368646648e-07,
+      "loss": 0.4379,
+      "step": 1700
+    },
+    {
+      "epoch": 2.855650720701901,
+      "grad_norm": 0.48225823044776917,
+      "learning_rate": 7.289989322378732e-07,
+      "loss": 0.4258,
+      "step": 1710
+    },
+    {
+      "epoch": 2.87236264884061,
+      "grad_norm": 0.4875478744506836,
+      "learning_rate": 5.730303502256341e-07,
+      "loss": 0.4194,
+      "step": 1720
+    },
+    {
+      "epoch": 2.889074576979319,
+      "grad_norm": 0.4659990668296814,
+      "learning_rate": 4.3571826206590396e-07,
+      "loss": 0.4083,
+      "step": 1730
+    },
+    {
+      "epoch": 2.905786505118028,
+      "grad_norm": 0.467338889837265,
+      "learning_rate": 3.1711449699576845e-07,
+      "loss": 0.4081,
+      "step": 1740
+    },
+    {
+      "epoch": 2.922498433256737,
+      "grad_norm": 0.4802572727203369,
+      "learning_rate": 2.172638226882129e-07,
+      "loss": 0.3996,
+      "step": 1750
+    },
+    {
+      "epoch": 2.939210361395446,
+      "grad_norm": 0.41945475339889526,
+      "learning_rate": 1.3620392835430596e-07,
+      "loss": 0.3647,
+      "step": 1760
+    },
+    {
+      "epoch": 2.955922289534155,
+      "grad_norm": 0.47264522314071655,
+      "learning_rate": 7.396541051717942e-08,
+      "loss": 0.4691,
+      "step": 1770
+    },
+    {
+      "epoch": 2.972634217672864,
+      "grad_norm": 0.45545369386672974,
+      "learning_rate": 3.057176146319951e-08,
+      "loss": 0.4034,
+      "step": 1780
+    },
+    {
+      "epoch": 2.989346145811573,
+      "grad_norm": 0.5081713795661926,
+      "learning_rate": 6.0393603746822235e-09,
+      "loss": 0.4652,
+      "step": 1790
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1797,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.751297376408863e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}