Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-1.7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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:a15a892c333838a2a189677ccf2528336ca822961b8485f71b925c0deed2d35d
+size 6437272

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

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

checkpoint-1200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-1.7B
+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-1200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a852d15f63f8dcb554877298641596adba661051e94b7aed6cc0a4d4b50edb4a
+size 6437272

checkpoint-1200/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-1200/chat_template.jinja

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

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b372582cecad3c0f9cbd537c8bcde888536527cabdf17c35cf855a483f815b7a
+size 12939322

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6491446df31a2912b9d1a60b49bda81d28f2c908873228ddf880abedfe09408f
+size 14244

checkpoint-1200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942cfd7aded7d16363d1ae1a2911c01ef4e25f3c70ed059c88f1845d9b6c24dc
+size 988

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7354ee67eb69236e571cfc31a84eafa2c9ab85dbcc1b4be6674f1694f0f2d31a
+size 1064

checkpoint-1200/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-1200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c760c4e715b8fa39254607191eca619d9b0612d5b29d3002ac512a5b6cad7d55
+size 11422934

checkpoint-1200/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1200/trainer_state.json

@@ -0,0 +1,874 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.8,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.662043809890747,
+      "learning_rate": 0.00019856000000000002,
+      "loss": 5.1172,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.09335994720459,
+      "learning_rate": 0.00019696,
+      "loss": 3.3973,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.070610761642456,
+      "learning_rate": 0.00019536,
+      "loss": 2.4409,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.546707034111023,
+      "learning_rate": 0.00019376000000000002,
+      "loss": 1.8295,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.077188491821289,
+      "learning_rate": 0.00019216,
+      "loss": 1.4628,
+      "step": 50
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.9755876064300537,
+      "learning_rate": 0.00019056000000000002,
+      "loss": 1.1744,
+      "step": 60
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.5424978733062744,
+      "learning_rate": 0.00018896,
+      "loss": 0.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.3976635932922363,
+      "learning_rate": 0.00018736,
+      "loss": 0.7369,
+      "step": 80
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.6257755756378174,
+      "learning_rate": 0.00018576,
+      "loss": 0.5777,
+      "step": 90
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.4098658561706543,
+      "learning_rate": 0.00018416,
+      "loss": 0.4739,
+      "step": 100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8213107585906982,
+      "learning_rate": 0.00018256,
+      "loss": 0.4333,
+      "step": 110
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.391830325126648,
+      "learning_rate": 0.00018096000000000003,
+      "loss": 0.3763,
+      "step": 120
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5569283962249756,
+      "learning_rate": 0.00017936000000000002,
+      "loss": 0.3211,
+      "step": 130
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.2082979679107666,
+      "learning_rate": 0.00017776,
+      "loss": 0.2362,
+      "step": 140
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1237390041351318,
+      "learning_rate": 0.00017616000000000002,
+      "loss": 0.2214,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0618360042572021,
+      "learning_rate": 0.00017456,
+      "loss": 0.2058,
+      "step": 160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0728964805603027,
+      "learning_rate": 0.00017296,
+      "loss": 0.2121,
+      "step": 170
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0727243423461914,
+      "learning_rate": 0.00017136,
+      "loss": 0.2043,
+      "step": 180
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.809100329875946,
+      "learning_rate": 0.00016976,
+      "loss": 0.1936,
+      "step": 190
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2039737701416016,
+      "learning_rate": 0.00016816000000000002,
+      "loss": 0.1975,
+      "step": 200
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9775518774986267,
+      "learning_rate": 0.00016656,
+      "loss": 0.2004,
+      "step": 210
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.98033207654953,
+      "learning_rate": 0.00016496,
+      "loss": 0.1964,
+      "step": 220
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.0707979202270508,
+      "learning_rate": 0.00016336,
+      "loss": 0.1848,
+      "step": 230
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0125160217285156,
+      "learning_rate": 0.00016176,
+      "loss": 0.1883,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.845367431640625,
+      "learning_rate": 0.00016016,
+      "loss": 0.182,
+      "step": 250
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.103655219078064,
+      "learning_rate": 0.00015856,
+      "loss": 0.1867,
+      "step": 260
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.8383971452713013,
+      "learning_rate": 0.00015696000000000002,
+      "loss": 0.179,
+      "step": 270
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.2054169178009033,
+      "learning_rate": 0.00015536,
+      "loss": 0.1792,
+      "step": 280
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.8676064014434814,
+      "learning_rate": 0.00015376000000000002,
+      "loss": 0.1814,
+      "step": 290
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.96745765209198,
+      "learning_rate": 0.00015216,
+      "loss": 0.1795,
+      "step": 300
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.7773518562316895,
+      "learning_rate": 0.00015056000000000002,
+      "loss": 0.1834,
+      "step": 310
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.7711182832717896,
+      "learning_rate": 0.00014896,
+      "loss": 0.1809,
+      "step": 320
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.850913405418396,
+      "learning_rate": 0.00014736,
+      "loss": 0.1815,
+      "step": 330
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.7834895849227905,
+      "learning_rate": 0.00014576000000000001,
+      "loss": 0.1733,
+      "step": 340
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.8648977279663086,
+      "learning_rate": 0.00014416,
+      "loss": 0.1812,
+      "step": 350
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.8799195289611816,
+      "learning_rate": 0.00014256000000000002,
+      "loss": 0.1718,
+      "step": 360
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.9176751971244812,
+      "learning_rate": 0.00014096,
+      "loss": 0.184,
+      "step": 370
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.7774612307548523,
+      "learning_rate": 0.00013936,
+      "loss": 0.1767,
+      "step": 380
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.781733512878418,
+      "learning_rate": 0.00013776,
+      "loss": 0.1802,
+      "step": 390
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7516366243362427,
+      "learning_rate": 0.00013616,
+      "loss": 0.1752,
+      "step": 400
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.8264226317405701,
+      "learning_rate": 0.00013455999999999999,
+      "loss": 0.1687,
+      "step": 410
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.7846059799194336,
+      "learning_rate": 0.00013296,
+      "loss": 0.1686,
+      "step": 420
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.6655611991882324,
+      "learning_rate": 0.00013136000000000002,
+      "loss": 0.173,
+      "step": 430
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.832114040851593,
+      "learning_rate": 0.00012976,
+      "loss": 0.1722,
+      "step": 440
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.8001246452331543,
+      "learning_rate": 0.00012816000000000002,
+      "loss": 0.174,
+      "step": 450
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.8609862923622131,
+      "learning_rate": 0.00012656,
+      "loss": 0.1683,
+      "step": 460
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7916587591171265,
+      "learning_rate": 0.00012496000000000002,
+      "loss": 0.1725,
+      "step": 470
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.6860988736152649,
+      "learning_rate": 0.00012336,
+      "loss": 0.1705,
+      "step": 480
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.8100546002388,
+      "learning_rate": 0.00012176000000000001,
+      "loss": 0.1753,
+      "step": 490
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9110960364341736,
+      "learning_rate": 0.00012016,
+      "loss": 0.1747,
+      "step": 500
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 1.0109771490097046,
+      "learning_rate": 0.00011856,
+      "loss": 0.1649,
+      "step": 510
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.7710285782814026,
+      "learning_rate": 0.00011696,
+      "loss": 0.1688,
+      "step": 520
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.7115465998649597,
+      "learning_rate": 0.00011536000000000001,
+      "loss": 0.1639,
+      "step": 530
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.8671514987945557,
+      "learning_rate": 0.00011376,
+      "loss": 0.1647,
+      "step": 540
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9132635593414307,
+      "learning_rate": 0.00011216,
+      "loss": 0.1649,
+      "step": 550
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.7357370257377625,
+      "learning_rate": 0.00011056,
+      "loss": 0.1601,
+      "step": 560
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7205009460449219,
+      "learning_rate": 0.00010896,
+      "loss": 0.164,
+      "step": 570
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.5780007243156433,
+      "learning_rate": 0.00010736000000000002,
+      "loss": 0.163,
+      "step": 580
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.8277910351753235,
+      "learning_rate": 0.00010576000000000002,
+      "loss": 0.172,
+      "step": 590
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.9455693960189819,
+      "learning_rate": 0.00010416000000000002,
+      "loss": 0.1622,
+      "step": 600
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.7017955183982849,
+      "learning_rate": 0.00010256000000000001,
+      "loss": 0.1726,
+      "step": 610
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.9842478036880493,
+      "learning_rate": 0.00010096000000000001,
+      "loss": 0.1694,
+      "step": 620
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.8026475310325623,
+      "learning_rate": 9.936000000000001e-05,
+      "loss": 0.1712,
+      "step": 630
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7248204350471497,
+      "learning_rate": 9.776000000000001e-05,
+      "loss": 0.1619,
+      "step": 640
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7692832946777344,
+      "learning_rate": 9.616e-05,
+      "loss": 0.1653,
+      "step": 650
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.7658987045288086,
+      "learning_rate": 9.456e-05,
+      "loss": 0.1688,
+      "step": 660
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.9279910326004028,
+      "learning_rate": 9.296e-05,
+      "loss": 0.1665,
+      "step": 670
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.7004180550575256,
+      "learning_rate": 9.136e-05,
+      "loss": 0.1649,
+      "step": 680
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.6005715131759644,
+      "learning_rate": 8.976e-05,
+      "loss": 0.1632,
+      "step": 690
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.7223785519599915,
+      "learning_rate": 8.816000000000001e-05,
+      "loss": 0.1613,
+      "step": 700
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.6642827391624451,
+      "learning_rate": 8.656000000000001e-05,
+      "loss": 0.1637,
+      "step": 710
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.9670928120613098,
+      "learning_rate": 8.496e-05,
+      "loss": 0.1604,
+      "step": 720
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.8518811464309692,
+      "learning_rate": 8.336e-05,
+      "loss": 0.1617,
+      "step": 730
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.6708147525787354,
+      "learning_rate": 8.176e-05,
+      "loss": 0.1687,
+      "step": 740
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7940568923950195,
+      "learning_rate": 8.016e-05,
+      "loss": 0.1664,
+      "step": 750
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.719121515750885,
+      "learning_rate": 7.856000000000001e-05,
+      "loss": 0.1595,
+      "step": 760
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 0.6775493025779724,
+      "learning_rate": 7.696e-05,
+      "loss": 0.16,
+      "step": 770
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 0.6409350037574768,
+      "learning_rate": 7.536000000000001e-05,
+      "loss": 0.1561,
+      "step": 780
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.6943857073783875,
+      "learning_rate": 7.376000000000001e-05,
+      "loss": 0.1627,
+      "step": 790
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.7445305585861206,
+      "learning_rate": 7.216e-05,
+      "loss": 0.1624,
+      "step": 800
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 0.8992999792098999,
+      "learning_rate": 7.056e-05,
+      "loss": 0.1608,
+      "step": 810
+    },
+    {
+      "epoch": 3.2800000000000002,
+      "grad_norm": 0.66852867603302,
+      "learning_rate": 6.896e-05,
+      "loss": 0.1576,
+      "step": 820
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 0.9884709119796753,
+      "learning_rate": 6.736e-05,
+      "loss": 0.1579,
+      "step": 830
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.8799577355384827,
+      "learning_rate": 6.576e-05,
+      "loss": 0.1648,
+      "step": 840
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.591947615146637,
+      "learning_rate": 6.416e-05,
+      "loss": 0.1553,
+      "step": 850
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 0.7027560472488403,
+      "learning_rate": 6.256000000000001e-05,
+      "loss": 0.1586,
+      "step": 860
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 0.7294725179672241,
+      "learning_rate": 6.0960000000000006e-05,
+      "loss": 0.154,
+      "step": 870
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.909156322479248,
+      "learning_rate": 5.936000000000001e-05,
+      "loss": 0.1651,
+      "step": 880
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.902925431728363,
+      "learning_rate": 5.776e-05,
+      "loss": 0.1595,
+      "step": 890
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.7759191393852234,
+      "learning_rate": 5.6160000000000004e-05,
+      "loss": 0.1533,
+      "step": 900
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.8666660189628601,
+      "learning_rate": 5.456e-05,
+      "loss": 0.1643,
+      "step": 910
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 0.7910454869270325,
+      "learning_rate": 5.296e-05,
+      "loss": 0.1597,
+      "step": 920
+    },
+    {
+      "epoch": 3.7199999999999998,
+      "grad_norm": 0.7616341710090637,
+      "learning_rate": 5.1359999999999996e-05,
+      "loss": 0.1594,
+      "step": 930
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 0.9938385486602783,
+      "learning_rate": 4.976e-05,
+      "loss": 0.1618,
+      "step": 940
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.6616437435150146,
+      "learning_rate": 4.816e-05,
+      "loss": 0.1595,
+      "step": 950
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.7744466662406921,
+      "learning_rate": 4.656e-05,
+      "loss": 0.1582,
+      "step": 960
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.6923044323921204,
+      "learning_rate": 4.496e-05,
+      "loss": 0.1637,
+      "step": 970
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 0.6732594966888428,
+      "learning_rate": 4.336e-05,
+      "loss": 0.16,
+      "step": 980
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.6819525361061096,
+      "learning_rate": 4.176000000000001e-05,
+      "loss": 0.1575,
+      "step": 990
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6316683888435364,
+      "learning_rate": 4.016e-05,
+      "loss": 0.1595,
+      "step": 1000
+    },
+    {
+      "epoch": 4.04,
+      "grad_norm": 0.750050961971283,
+      "learning_rate": 3.8560000000000004e-05,
+      "loss": 0.1579,
+      "step": 1010
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.7207621932029724,
+      "learning_rate": 3.696e-05,
+      "loss": 0.15,
+      "step": 1020
+    },
+    {
+      "epoch": 4.12,
+      "grad_norm": 0.7863367199897766,
+      "learning_rate": 3.536000000000001e-05,
+      "loss": 0.154,
+      "step": 1030
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.7777521014213562,
+      "learning_rate": 3.376e-05,
+      "loss": 0.1537,
+      "step": 1040
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 0.9184511303901672,
+      "learning_rate": 3.2160000000000004e-05,
+      "loss": 0.1552,
+      "step": 1050
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 0.6183204054832458,
+      "learning_rate": 3.056e-05,
+      "loss": 0.1508,
+      "step": 1060
+    },
+    {
+      "epoch": 4.28,
+      "grad_norm": 0.8320776224136353,
+      "learning_rate": 2.8960000000000004e-05,
+      "loss": 0.1538,
+      "step": 1070
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.7392308115959167,
+      "learning_rate": 2.7360000000000002e-05,
+      "loss": 0.1569,
+      "step": 1080
+    },
+    {
+      "epoch": 4.36,
+      "grad_norm": 0.8047224879264832,
+      "learning_rate": 2.576e-05,
+      "loss": 0.1567,
+      "step": 1090
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.9632170796394348,
+      "learning_rate": 2.4160000000000002e-05,
+      "loss": 0.1588,
+      "step": 1100
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 0.877510130405426,
+      "learning_rate": 2.256e-05,
+      "loss": 0.153,
+      "step": 1110
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.7020285129547119,
+      "learning_rate": 2.0960000000000003e-05,
+      "loss": 0.1535,
+      "step": 1120
+    },
+    {
+      "epoch": 4.52,
+      "grad_norm": 0.8973066210746765,
+      "learning_rate": 1.936e-05,
+      "loss": 0.158,
+      "step": 1130
+    },
+    {
+      "epoch": 4.5600000000000005,
+      "grad_norm": 0.7732061147689819,
+      "learning_rate": 1.7760000000000003e-05,
+      "loss": 0.1571,
+      "step": 1140
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 0.9279715418815613,
+      "learning_rate": 1.616e-05,
+      "loss": 0.1522,
+      "step": 1150
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.8018597960472107,
+      "learning_rate": 1.4560000000000001e-05,
+      "loss": 0.1538,
+      "step": 1160
+    },
+    {
+      "epoch": 4.68,
+      "grad_norm": 0.8969665169715881,
+      "learning_rate": 1.296e-05,
+      "loss": 0.1565,
+      "step": 1170
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 0.7768281698226929,
+      "learning_rate": 1.1360000000000001e-05,
+      "loss": 0.1564,
+      "step": 1180
+    },
+    {
+      "epoch": 4.76,
+      "grad_norm": 0.7520988583564758,
+      "learning_rate": 9.760000000000001e-06,
+      "loss": 0.1569,
+      "step": 1190
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.86794513463974,
+      "learning_rate": 8.160000000000001e-06,
+      "loss": 0.1565,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.1612545622016e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55256ccc51a255b5e5ab0b6de6a63bc5714b2655a59ccd257b869e18f3dfbd5
+size 5240

checkpoint-1250/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-1.7B
+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-1250/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15a892c333838a2a189677ccf2528336ca822961b8485f71b925c0deed2d35d
+size 6437272

checkpoint-1250/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-1250/chat_template.jinja

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

checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9be8a95906285c220e9a85ed54591039eb3d6919fc7df6125b8036c3bf313d
+size 12939322

checkpoint-1250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db907cbfe4282141ab1e40857e4291920145f374125db0aa1b65f22b759ca506
+size 14244

checkpoint-1250/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f1986269c74ce38fd01c56e0770c176375c55daeed6953aaf84f06cae775ba
+size 988

checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903a795738170ff70d70024a9e98d14e0ee1b641c05cf14651af4125ea88faaf
+size 1064

checkpoint-1250/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-1250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c760c4e715b8fa39254607191eca619d9b0612d5b29d3002ac512a5b6cad7d55
+size 11422934

checkpoint-1250/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1250/trainer_state.json

@@ -0,0 +1,909 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.662043809890747,
+      "learning_rate": 0.00019856000000000002,
+      "loss": 5.1172,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.09335994720459,
+      "learning_rate": 0.00019696,
+      "loss": 3.3973,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.070610761642456,
+      "learning_rate": 0.00019536,
+      "loss": 2.4409,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.546707034111023,
+      "learning_rate": 0.00019376000000000002,
+      "loss": 1.8295,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.077188491821289,
+      "learning_rate": 0.00019216,
+      "loss": 1.4628,
+      "step": 50
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.9755876064300537,
+      "learning_rate": 0.00019056000000000002,
+      "loss": 1.1744,
+      "step": 60
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.5424978733062744,
+      "learning_rate": 0.00018896,
+      "loss": 0.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.3976635932922363,
+      "learning_rate": 0.00018736,
+      "loss": 0.7369,
+      "step": 80
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.6257755756378174,
+      "learning_rate": 0.00018576,
+      "loss": 0.5777,
+      "step": 90
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.4098658561706543,
+      "learning_rate": 0.00018416,
+      "loss": 0.4739,
+      "step": 100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.8213107585906982,
+      "learning_rate": 0.00018256,
+      "loss": 0.4333,
+      "step": 110
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.391830325126648,
+      "learning_rate": 0.00018096000000000003,
+      "loss": 0.3763,
+      "step": 120
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5569283962249756,
+      "learning_rate": 0.00017936000000000002,
+      "loss": 0.3211,
+      "step": 130
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.2082979679107666,
+      "learning_rate": 0.00017776,
+      "loss": 0.2362,
+      "step": 140
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1237390041351318,
+      "learning_rate": 0.00017616000000000002,
+      "loss": 0.2214,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0618360042572021,
+      "learning_rate": 0.00017456,
+      "loss": 0.2058,
+      "step": 160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0728964805603027,
+      "learning_rate": 0.00017296,
+      "loss": 0.2121,
+      "step": 170
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0727243423461914,
+      "learning_rate": 0.00017136,
+      "loss": 0.2043,
+      "step": 180
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.809100329875946,
+      "learning_rate": 0.00016976,
+      "loss": 0.1936,
+      "step": 190
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2039737701416016,
+      "learning_rate": 0.00016816000000000002,
+      "loss": 0.1975,
+      "step": 200
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9775518774986267,
+      "learning_rate": 0.00016656,
+      "loss": 0.2004,
+      "step": 210
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.98033207654953,
+      "learning_rate": 0.00016496,
+      "loss": 0.1964,
+      "step": 220
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.0707979202270508,
+      "learning_rate": 0.00016336,
+      "loss": 0.1848,
+      "step": 230
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0125160217285156,
+      "learning_rate": 0.00016176,
+      "loss": 0.1883,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.845367431640625,
+      "learning_rate": 0.00016016,
+      "loss": 0.182,
+      "step": 250
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.103655219078064,
+      "learning_rate": 0.00015856,
+      "loss": 0.1867,
+      "step": 260
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.8383971452713013,
+      "learning_rate": 0.00015696000000000002,
+      "loss": 0.179,
+      "step": 270
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.2054169178009033,
+      "learning_rate": 0.00015536,
+      "loss": 0.1792,
+      "step": 280
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.8676064014434814,
+      "learning_rate": 0.00015376000000000002,
+      "loss": 0.1814,
+      "step": 290
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.96745765209198,
+      "learning_rate": 0.00015216,
+      "loss": 0.1795,
+      "step": 300
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.7773518562316895,
+      "learning_rate": 0.00015056000000000002,
+      "loss": 0.1834,
+      "step": 310
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.7711182832717896,
+      "learning_rate": 0.00014896,
+      "loss": 0.1809,
+      "step": 320
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.850913405418396,
+      "learning_rate": 0.00014736,
+      "loss": 0.1815,
+      "step": 330
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.7834895849227905,
+      "learning_rate": 0.00014576000000000001,
+      "loss": 0.1733,
+      "step": 340
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.8648977279663086,
+      "learning_rate": 0.00014416,
+      "loss": 0.1812,
+      "step": 350
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.8799195289611816,
+      "learning_rate": 0.00014256000000000002,
+      "loss": 0.1718,
+      "step": 360
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.9176751971244812,
+      "learning_rate": 0.00014096,
+      "loss": 0.184,
+      "step": 370
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.7774612307548523,
+      "learning_rate": 0.00013936,
+      "loss": 0.1767,
+      "step": 380
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.781733512878418,
+      "learning_rate": 0.00013776,
+      "loss": 0.1802,
+      "step": 390
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7516366243362427,
+      "learning_rate": 0.00013616,
+      "loss": 0.1752,
+      "step": 400
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.8264226317405701,
+      "learning_rate": 0.00013455999999999999,
+      "loss": 0.1687,
+      "step": 410
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.7846059799194336,
+      "learning_rate": 0.00013296,
+      "loss": 0.1686,
+      "step": 420
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.6655611991882324,
+      "learning_rate": 0.00013136000000000002,
+      "loss": 0.173,
+      "step": 430
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.832114040851593,
+      "learning_rate": 0.00012976,
+      "loss": 0.1722,
+      "step": 440
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.8001246452331543,
+      "learning_rate": 0.00012816000000000002,
+      "loss": 0.174,
+      "step": 450
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.8609862923622131,
+      "learning_rate": 0.00012656,
+      "loss": 0.1683,
+      "step": 460
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7916587591171265,
+      "learning_rate": 0.00012496000000000002,
+      "loss": 0.1725,
+      "step": 470
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.6860988736152649,
+      "learning_rate": 0.00012336,
+      "loss": 0.1705,
+      "step": 480
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.8100546002388,
+      "learning_rate": 0.00012176000000000001,
+      "loss": 0.1753,
+      "step": 490
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9110960364341736,
+      "learning_rate": 0.00012016,
+      "loss": 0.1747,
+      "step": 500
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 1.0109771490097046,
+      "learning_rate": 0.00011856,
+      "loss": 0.1649,
+      "step": 510
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.7710285782814026,
+      "learning_rate": 0.00011696,
+      "loss": 0.1688,
+      "step": 520
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.7115465998649597,
+      "learning_rate": 0.00011536000000000001,
+      "loss": 0.1639,
+      "step": 530
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.8671514987945557,
+      "learning_rate": 0.00011376,
+      "loss": 0.1647,
+      "step": 540
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9132635593414307,
+      "learning_rate": 0.00011216,
+      "loss": 0.1649,
+      "step": 550
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.7357370257377625,
+      "learning_rate": 0.00011056,
+      "loss": 0.1601,
+      "step": 560
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7205009460449219,
+      "learning_rate": 0.00010896,
+      "loss": 0.164,
+      "step": 570
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.5780007243156433,
+      "learning_rate": 0.00010736000000000002,
+      "loss": 0.163,
+      "step": 580
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.8277910351753235,
+      "learning_rate": 0.00010576000000000002,
+      "loss": 0.172,
+      "step": 590
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.9455693960189819,
+      "learning_rate": 0.00010416000000000002,
+      "loss": 0.1622,
+      "step": 600
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.7017955183982849,
+      "learning_rate": 0.00010256000000000001,
+      "loss": 0.1726,
+      "step": 610
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.9842478036880493,
+      "learning_rate": 0.00010096000000000001,
+      "loss": 0.1694,
+      "step": 620
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.8026475310325623,
+      "learning_rate": 9.936000000000001e-05,
+      "loss": 0.1712,
+      "step": 630
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7248204350471497,
+      "learning_rate": 9.776000000000001e-05,
+      "loss": 0.1619,
+      "step": 640
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7692832946777344,
+      "learning_rate": 9.616e-05,
+      "loss": 0.1653,
+      "step": 650
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.7658987045288086,
+      "learning_rate": 9.456e-05,
+      "loss": 0.1688,
+      "step": 660
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.9279910326004028,
+      "learning_rate": 9.296e-05,
+      "loss": 0.1665,
+      "step": 670
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.7004180550575256,
+      "learning_rate": 9.136e-05,
+      "loss": 0.1649,
+      "step": 680
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.6005715131759644,
+      "learning_rate": 8.976e-05,
+      "loss": 0.1632,
+      "step": 690
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.7223785519599915,
+      "learning_rate": 8.816000000000001e-05,
+      "loss": 0.1613,
+      "step": 700
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.6642827391624451,
+      "learning_rate": 8.656000000000001e-05,
+      "loss": 0.1637,
+      "step": 710
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.9670928120613098,
+      "learning_rate": 8.496e-05,
+      "loss": 0.1604,
+      "step": 720
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.8518811464309692,
+      "learning_rate": 8.336e-05,
+      "loss": 0.1617,
+      "step": 730
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.6708147525787354,
+      "learning_rate": 8.176e-05,
+      "loss": 0.1687,
+      "step": 740
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7940568923950195,
+      "learning_rate": 8.016e-05,
+      "loss": 0.1664,
+      "step": 750
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.719121515750885,
+      "learning_rate": 7.856000000000001e-05,
+      "loss": 0.1595,
+      "step": 760
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 0.6775493025779724,
+      "learning_rate": 7.696e-05,
+      "loss": 0.16,
+      "step": 770
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 0.6409350037574768,
+      "learning_rate": 7.536000000000001e-05,
+      "loss": 0.1561,
+      "step": 780
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.6943857073783875,
+      "learning_rate": 7.376000000000001e-05,
+      "loss": 0.1627,
+      "step": 790
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.7445305585861206,
+      "learning_rate": 7.216e-05,
+      "loss": 0.1624,
+      "step": 800
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 0.8992999792098999,
+      "learning_rate": 7.056e-05,
+      "loss": 0.1608,
+      "step": 810
+    },
+    {
+      "epoch": 3.2800000000000002,
+      "grad_norm": 0.66852867603302,
+      "learning_rate": 6.896e-05,
+      "loss": 0.1576,
+      "step": 820
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 0.9884709119796753,
+      "learning_rate": 6.736e-05,
+      "loss": 0.1579,
+      "step": 830
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.8799577355384827,
+      "learning_rate": 6.576e-05,
+      "loss": 0.1648,
+      "step": 840
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.591947615146637,
+      "learning_rate": 6.416e-05,
+      "loss": 0.1553,
+      "step": 850
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 0.7027560472488403,
+      "learning_rate": 6.256000000000001e-05,
+      "loss": 0.1586,
+      "step": 860
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 0.7294725179672241,
+      "learning_rate": 6.0960000000000006e-05,
+      "loss": 0.154,
+      "step": 870
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.909156322479248,
+      "learning_rate": 5.936000000000001e-05,
+      "loss": 0.1651,
+      "step": 880
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.902925431728363,
+      "learning_rate": 5.776e-05,
+      "loss": 0.1595,
+      "step": 890
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.7759191393852234,
+      "learning_rate": 5.6160000000000004e-05,
+      "loss": 0.1533,
+      "step": 900
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.8666660189628601,
+      "learning_rate": 5.456e-05,
+      "loss": 0.1643,
+      "step": 910
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 0.7910454869270325,
+      "learning_rate": 5.296e-05,
+      "loss": 0.1597,
+      "step": 920
+    },
+    {
+      "epoch": 3.7199999999999998,
+      "grad_norm": 0.7616341710090637,
+      "learning_rate": 5.1359999999999996e-05,
+      "loss": 0.1594,
+      "step": 930
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 0.9938385486602783,
+      "learning_rate": 4.976e-05,
+      "loss": 0.1618,
+      "step": 940
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.6616437435150146,
+      "learning_rate": 4.816e-05,
+      "loss": 0.1595,
+      "step": 950
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.7744466662406921,
+      "learning_rate": 4.656e-05,
+      "loss": 0.1582,
+      "step": 960
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.6923044323921204,
+      "learning_rate": 4.496e-05,
+      "loss": 0.1637,
+      "step": 970
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 0.6732594966888428,
+      "learning_rate": 4.336e-05,
+      "loss": 0.16,
+      "step": 980
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.6819525361061096,
+      "learning_rate": 4.176000000000001e-05,
+      "loss": 0.1575,
+      "step": 990
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6316683888435364,
+      "learning_rate": 4.016e-05,
+      "loss": 0.1595,
+      "step": 1000
+    },
+    {
+      "epoch": 4.04,
+      "grad_norm": 0.750050961971283,
+      "learning_rate": 3.8560000000000004e-05,
+      "loss": 0.1579,
+      "step": 1010
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.7207621932029724,
+      "learning_rate": 3.696e-05,
+      "loss": 0.15,
+      "step": 1020
+    },
+    {
+      "epoch": 4.12,
+      "grad_norm": 0.7863367199897766,
+      "learning_rate": 3.536000000000001e-05,
+      "loss": 0.154,
+      "step": 1030
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.7777521014213562,
+      "learning_rate": 3.376e-05,
+      "loss": 0.1537,
+      "step": 1040
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 0.9184511303901672,
+      "learning_rate": 3.2160000000000004e-05,
+      "loss": 0.1552,
+      "step": 1050
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 0.6183204054832458,
+      "learning_rate": 3.056e-05,
+      "loss": 0.1508,
+      "step": 1060
+    },
+    {
+      "epoch": 4.28,
+      "grad_norm": 0.8320776224136353,
+      "learning_rate": 2.8960000000000004e-05,
+      "loss": 0.1538,
+      "step": 1070
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.7392308115959167,
+      "learning_rate": 2.7360000000000002e-05,
+      "loss": 0.1569,
+      "step": 1080
+    },
+    {
+      "epoch": 4.36,
+      "grad_norm": 0.8047224879264832,
+      "learning_rate": 2.576e-05,
+      "loss": 0.1567,
+      "step": 1090
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.9632170796394348,
+      "learning_rate": 2.4160000000000002e-05,
+      "loss": 0.1588,
+      "step": 1100
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 0.877510130405426,
+      "learning_rate": 2.256e-05,
+      "loss": 0.153,
+      "step": 1110
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.7020285129547119,
+      "learning_rate": 2.0960000000000003e-05,
+      "loss": 0.1535,
+      "step": 1120
+    },
+    {
+      "epoch": 4.52,
+      "grad_norm": 0.8973066210746765,
+      "learning_rate": 1.936e-05,
+      "loss": 0.158,
+      "step": 1130
+    },
+    {
+      "epoch": 4.5600000000000005,
+      "grad_norm": 0.7732061147689819,
+      "learning_rate": 1.7760000000000003e-05,
+      "loss": 0.1571,
+      "step": 1140
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 0.9279715418815613,
+      "learning_rate": 1.616e-05,
+      "loss": 0.1522,
+      "step": 1150
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.8018597960472107,
+      "learning_rate": 1.4560000000000001e-05,
+      "loss": 0.1538,
+      "step": 1160
+    },
+    {
+      "epoch": 4.68,
+      "grad_norm": 0.8969665169715881,
+      "learning_rate": 1.296e-05,
+      "loss": 0.1565,
+      "step": 1170
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 0.7768281698226929,
+      "learning_rate": 1.1360000000000001e-05,
+      "loss": 0.1564,
+      "step": 1180
+    },
+    {
+      "epoch": 4.76,
+      "grad_norm": 0.7520988583564758,
+      "learning_rate": 9.760000000000001e-06,
+      "loss": 0.1569,
+      "step": 1190
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.86794513463974,
+      "learning_rate": 8.160000000000001e-06,
+      "loss": 0.1565,
+      "step": 1200
+    },
+    {
+      "epoch": 4.84,
+      "grad_norm": 0.9098602533340454,
+      "learning_rate": 6.560000000000001e-06,
+      "loss": 0.16,
+      "step": 1210
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.7595716118812561,
+      "learning_rate": 4.96e-06,
+      "loss": 0.1562,
+      "step": 1220
+    },
+    {
+      "epoch": 4.92,
+      "grad_norm": 0.837422251701355,
+      "learning_rate": 3.36e-06,
+      "loss": 0.1526,
+      "step": 1230
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.7402159571647644,
+      "learning_rate": 1.76e-06,
+      "loss": 0.158,
+      "step": 1240
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.0475088357925415,
+      "learning_rate": 1.6e-07,
+      "loss": 0.1496,
+      "step": 1250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.33464016896e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55256ccc51a255b5e5ab0b6de6a63bc5714b2655a59ccd257b869e18f3dfbd5
+size 5240

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c760c4e715b8fa39254607191eca619d9b0612d5b29d3002ac512a5b6cad7d55
+size 11422934

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}