Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)

.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-1209/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/sft_alfworld_trajectory_dataset_v5
+- u-10bei/dbbench_sft_dataset_react_v4
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- agent
+- tool-use
+- alfworld
+- dbbench
+---
+
+# Qwen3-4B ALFWorld+DBBench Mixed LoRA Adapter (r=16)
+
+This repository provides a **LoRA adapter** fine-tuned from
+**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
+
+This repository contains **LoRA adapter weights only**.
+The base model must be loaded separately.
+
+## Training Objective
+
+This adapter is trained to improve **multi-turn agent task performance**
+on ALFWorld (household tasks) and DBBench (database operations).
+
+Loss is applied to **all assistant turns** in the multi-turn trajectory,
+enabling the model to learn environment observation, action selection,
+tool use, and recovery from errors.
+
+## Training Configuration
+
+- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Method: LoRA (full precision base)
+- Max sequence length: 2048
+- Epochs: 3
+- Learning rate: 2e-04
+- LoRA: r=64, alpha=128
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "Qwen/Qwen3-4B-Instruct-2507"
+adapter = "your_id/your-repo"
+
+tokenizer = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(
+    base,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(model, adapter)
+```
+
+## Sources & Terms (IMPORTANT)
+
+Training data: u-10bei/sft_alfworld_trajectory_dataset_v5 + u-10bei/dbbench_sft_dataset_react_v4
+
+Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
+Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e400301d8693b1de988737f82e1a522cf7d5718360b346f2c289243fca70254d
+size 528550256

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 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-1200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+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 0.13.2

checkpoint-1200/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "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:f1068ef62389ff7202e36c42ba6d3e770db19b7381e7a0944131547205e81b84
+size 528550256

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 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8929b61de1ac8d808f5518984c37990e9d32c5ed1458a101548a3b618dc58b
+size 1057397963

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a391d68393a9b12fcd7cd2dd5b614c1d3918af5767128296916cb37d2d8485bf
+size 14645

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b7cd797d7038407a10de2a71435723413be94806d803fa58d42eb83a9eaa09
+size 1465

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": "<|vision_pad|>",
+    "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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-1200/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1200/trainer_state.json

@@ -0,0 +1,1194 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.978274363749224,
+  "eval_steps": 30,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024829298572315334,
+      "grad_norm": 8.391741752624512,
+      "learning_rate": 1.487603305785124e-05,
+      "loss": 2.6023,
+      "step": 10
+    },
+    {
+      "epoch": 0.04965859714463067,
+      "grad_norm": 0.7645617723464966,
+      "learning_rate": 3.1404958677685955e-05,
+      "loss": 1.0126,
+      "step": 20
+    },
+    {
+      "epoch": 0.074487895716946,
+      "grad_norm": 0.7797226905822754,
+      "learning_rate": 4.793388429752066e-05,
+      "loss": 0.6236,
+      "step": 30
+    },
+    {
+      "epoch": 0.074487895716946,
+      "eval_loss": 0.5439823865890503,
+      "eval_runtime": 41.1617,
+      "eval_samples_per_second": 4.13,
+      "eval_steps_per_second": 2.065,
+      "step": 30
+    },
+    {
+      "epoch": 0.09931719428926133,
+      "grad_norm": 0.5489462614059448,
+      "learning_rate": 6.446280991735537e-05,
+      "loss": 0.4543,
+      "step": 40
+    },
+    {
+      "epoch": 0.12414649286157665,
+      "grad_norm": 0.7057201266288757,
+      "learning_rate": 8.099173553719009e-05,
+      "loss": 0.369,
+      "step": 50
+    },
+    {
+      "epoch": 0.148975791433892,
+      "grad_norm": 0.44007009267807007,
+      "learning_rate": 9.75206611570248e-05,
+      "loss": 0.2855,
+      "step": 60
+    },
+    {
+      "epoch": 0.148975791433892,
+      "eval_loss": 0.28305545449256897,
+      "eval_runtime": 40.404,
+      "eval_samples_per_second": 4.208,
+      "eval_steps_per_second": 2.104,
+      "step": 60
+    },
+    {
+      "epoch": 0.17380509000620734,
+      "grad_norm": 0.5000414848327637,
+      "learning_rate": 0.0001140495867768595,
+      "loss": 0.2506,
+      "step": 70
+    },
+    {
+      "epoch": 0.19863438857852267,
+      "grad_norm": 0.6662213802337646,
+      "learning_rate": 0.00013057851239669423,
+      "loss": 0.2262,
+      "step": 80
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.4713539481163025,
+      "learning_rate": 0.00014710743801652894,
+      "loss": 0.1983,
+      "step": 90
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "eval_loss": 0.2015635371208191,
+      "eval_runtime": 40.5434,
+      "eval_samples_per_second": 4.193,
+      "eval_steps_per_second": 2.097,
+      "step": 90
+    },
+    {
+      "epoch": 0.2482929857231533,
+      "grad_norm": 0.3806518316268921,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.1905,
+      "step": 100
+    },
+    {
+      "epoch": 0.27312228429546864,
+      "grad_norm": 0.537176251411438,
+      "learning_rate": 0.00018016528925619835,
+      "loss": 0.1681,
+      "step": 110
+    },
+    {
+      "epoch": 0.297951582867784,
+      "grad_norm": 0.39260727167129517,
+      "learning_rate": 0.0001966942148760331,
+      "loss": 0.1619,
+      "step": 120
+    },
+    {
+      "epoch": 0.297951582867784,
+      "eval_loss": 0.1580844670534134,
+      "eval_runtime": 40.5961,
+      "eval_samples_per_second": 4.188,
+      "eval_steps_per_second": 2.094,
+      "step": 120
+    },
+    {
+      "epoch": 0.3227808814400993,
+      "grad_norm": 0.2614082396030426,
+      "learning_rate": 0.00019997332081116373,
+      "loss": 0.156,
+      "step": 130
+    },
+    {
+      "epoch": 0.34761018001241467,
+      "grad_norm": 0.4994271993637085,
+      "learning_rate": 0.00019986496100395275,
+      "loss": 0.1591,
+      "step": 140
+    },
+    {
+      "epoch": 0.37243947858473,
+      "grad_norm": 0.2901883125305176,
+      "learning_rate": 0.000199673343399533,
+      "loss": 0.1536,
+      "step": 150
+    },
+    {
+      "epoch": 0.37243947858473,
+      "eval_loss": 0.15050268173217773,
+      "eval_runtime": 40.6229,
+      "eval_samples_per_second": 4.185,
+      "eval_steps_per_second": 2.092,
+      "step": 150
+    },
+    {
+      "epoch": 0.39726877715704534,
+      "grad_norm": 0.4040389657020569,
+      "learning_rate": 0.00019939862775022893,
+      "loss": 0.1614,
+      "step": 160
+    },
+    {
+      "epoch": 0.42209807572936064,
+      "grad_norm": 0.3563652038574219,
+      "learning_rate": 0.0001990410430875205,
+      "loss": 0.1489,
+      "step": 170
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.21592873334884644,
+      "learning_rate": 0.00019860088753109896,
+      "loss": 0.1491,
+      "step": 180
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "eval_loss": 0.14503230154514313,
+      "eval_runtime": 40.5377,
+      "eval_samples_per_second": 4.194,
+      "eval_steps_per_second": 2.097,
+      "step": 180
+    },
+    {
+      "epoch": 0.4717566728739913,
+      "grad_norm": 0.293130487203598,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.1388,
+      "step": 190
+    },
+    {
+      "epoch": 0.4965859714463066,
+      "grad_norm": 0.5099315643310547,
+      "learning_rate": 0.00019747440010828383,
+      "loss": 0.1398,
+      "step": 200
+    },
+    {
+      "epoch": 0.521415270018622,
+      "grad_norm": 0.3809162974357605,
+      "learning_rate": 0.00019678900739873226,
+      "loss": 0.1484,
+      "step": 210
+    },
+    {
+      "epoch": 0.521415270018622,
+      "eval_loss": 0.1399187594652176,
+      "eval_runtime": 40.3775,
+      "eval_samples_per_second": 4.21,
+      "eval_steps_per_second": 2.105,
+      "step": 210
+    },
+    {
+      "epoch": 0.5462445685909373,
+      "grad_norm": 0.2565288245677948,
+      "learning_rate": 0.000196022921326173,
+      "loss": 0.1406,
+      "step": 220
+    },
+    {
+      "epoch": 0.5710738671632526,
+      "grad_norm": 0.25355908274650574,
+      "learning_rate": 0.00019517678057947384,
+      "loss": 0.1436,
+      "step": 230
+    },
+    {
+      "epoch": 0.595903165735568,
+      "grad_norm": 0.3126136064529419,
+      "learning_rate": 0.00019425129058938832,
+      "loss": 0.1437,
+      "step": 240
+    },
+    {
+      "epoch": 0.595903165735568,
+      "eval_loss": 0.13724148273468018,
+      "eval_runtime": 40.489,
+      "eval_samples_per_second": 4.199,
+      "eval_steps_per_second": 2.099,
+      "step": 240
+    },
+    {
+      "epoch": 0.6207324643078833,
+      "grad_norm": 0.32518845796585083,
+      "learning_rate": 0.00019324722294043558,
+      "loss": 0.1391,
+      "step": 250
+    },
+    {
+      "epoch": 0.6455617628801986,
+      "grad_norm": 0.32164257764816284,
+      "learning_rate": 0.00019216541472762735,
+      "loss": 0.1386,
+      "step": 260
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.37033355236053467,
+      "learning_rate": 0.0001910067678585786,
+      "loss": 0.1329,
+      "step": 270
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "eval_loss": 0.12901660799980164,
+      "eval_runtime": 40.5259,
+      "eval_samples_per_second": 4.195,
+      "eval_steps_per_second": 2.097,
+      "step": 270
+    },
+    {
+      "epoch": 0.6952203600248293,
+      "grad_norm": 0.24198684096336365,
+      "learning_rate": 0.0001897722483015838,
+      "loss": 0.1262,
+      "step": 280
+    },
+    {
+      "epoch": 0.7200496585971446,
+      "grad_norm": 0.20765037834644318,
+      "learning_rate": 0.00018846288528028555,
+      "loss": 0.1281,
+      "step": 290
+    },
+    {
+      "epoch": 0.74487895716946,
+      "grad_norm": 0.1669204831123352,
+      "learning_rate": 0.0001870797704156067,
+      "loss": 0.1376,
+      "step": 300
+    },
+    {
+      "epoch": 0.74487895716946,
+      "eval_loss": 0.1301908791065216,
+      "eval_runtime": 40.6681,
+      "eval_samples_per_second": 4.18,
+      "eval_steps_per_second": 2.09,
+      "step": 300
+    },
+    {
+      "epoch": 0.7697082557417753,
+      "grad_norm": 0.17013825476169586,
+      "learning_rate": 0.00018562405681566216,
+      "loss": 0.1407,
+      "step": 310
+    },
+    {
+      "epoch": 0.7945375543140907,
+      "grad_norm": 0.1282002329826355,
+      "learning_rate": 0.00018409695811440796,
+      "loss": 0.1365,
+      "step": 320
+    },
+    {
+      "epoch": 0.819366852886406,
+      "grad_norm": 0.12342263758182526,
+      "learning_rate": 0.00018249974745983023,
+      "loss": 0.13,
+      "step": 330
+    },
+    {
+      "epoch": 0.819366852886406,
+      "eval_loss": 0.1285768747329712,
+      "eval_runtime": 40.5047,
+      "eval_samples_per_second": 4.197,
+      "eval_steps_per_second": 2.099,
+      "step": 330
+    },
+    {
+      "epoch": 0.8441961514587213,
+      "grad_norm": 0.14901821315288544,
+      "learning_rate": 0.00018083375645251684,
+      "loss": 0.1347,
+      "step": 340
+    },
+    {
+      "epoch": 0.8690254500310366,
+      "grad_norm": 0.17922259867191315,
+      "learning_rate": 0.00017910037403549693,
+      "loss": 0.1325,
+      "step": 350
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.09752878546714783,
+      "learning_rate": 0.0001773010453362737,
+      "loss": 0.1272,
+      "step": 360
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "eval_loss": 0.12547558546066284,
+      "eval_runtime": 40.6167,
+      "eval_samples_per_second": 4.185,
+      "eval_steps_per_second": 2.093,
+      "step": 360
+    },
+    {
+      "epoch": 0.9186840471756673,
+      "grad_norm": 0.17390093207359314,
+      "learning_rate": 0.0001754372704620164,
+      "loss": 0.1334,
+      "step": 370
+    },
+    {
+      "epoch": 0.9435133457479826,
+      "grad_norm": 0.10675700008869171,
+      "learning_rate": 0.00017351060324891502,
+      "loss": 0.1299,
+      "step": 380
+    },
+    {
+      "epoch": 0.9683426443202979,
+      "grad_norm": 0.13889861106872559,
+      "learning_rate": 0.00017152264996674136,
+      "loss": 0.1366,
+      "step": 390
+    },
+    {
+      "epoch": 0.9683426443202979,
+      "eval_loss": 0.12701915204524994,
+      "eval_runtime": 40.4376,
+      "eval_samples_per_second": 4.204,
+      "eval_steps_per_second": 2.102,
+      "step": 390
+    },
+    {
+      "epoch": 0.9931719428926132,
+      "grad_norm": 0.24341008067131042,
+      "learning_rate": 0.00016947506797969562,
+      "loss": 0.1262,
+      "step": 400
+    },
+    {
+      "epoch": 1.0173805090006207,
+      "grad_norm": 0.16011632978916168,
+      "learning_rate": 0.00016736956436465573,
+      "loss": 0.1338,
+      "step": 410
+    },
+    {
+      "epoch": 1.042209807572936,
+      "grad_norm": 0.13081607222557068,
+      "learning_rate": 0.00016520789448798087,
+      "loss": 0.1236,
+      "step": 420
+    },
+    {
+      "epoch": 1.042209807572936,
+      "eval_loss": 0.12546835839748383,
+      "eval_runtime": 40.6293,
+      "eval_samples_per_second": 4.184,
+      "eval_steps_per_second": 2.092,
+      "step": 420
+    },
+    {
+      "epoch": 1.0670391061452513,
+      "grad_norm": 0.10969800502061844,
+      "learning_rate": 0.00016299186054205577,
+      "loss": 0.1263,
+      "step": 430
+    },
+    {
+      "epoch": 1.0918684047175666,
+      "grad_norm": 0.16010411083698273,
+      "learning_rate": 0.00016072331004279614,
+      "loss": 0.1163,
+      "step": 440
+    },
+    {
+      "epoch": 1.1166977032898822,
+      "grad_norm": 0.15039803087711334,
+      "learning_rate": 0.00015840413428936767,
+      "loss": 0.1207,
+      "step": 450
+    },
+    {
+      "epoch": 1.1166977032898822,
+      "eval_loss": 0.12573280930519104,
+      "eval_runtime": 40.5321,
+      "eval_samples_per_second": 4.194,
+      "eval_steps_per_second": 2.097,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415270018621975,
+      "grad_norm": 0.10430776327848434,
+      "learning_rate": 0.00015603626678740263,
+      "loss": 0.1277,
+      "step": 460
+    },
+    {
+      "epoch": 1.1663563004345128,
+      "grad_norm": 0.11445056647062302,
+      "learning_rate": 0.000153621681637029,
+      "loss": 0.1279,
+      "step": 470
+    },
+    {
+      "epoch": 1.191185599006828,
+      "grad_norm": 0.08513262867927551,
+      "learning_rate": 0.00015116239188705556,
+      "loss": 0.1247,
+      "step": 480
+    },
+    {
+      "epoch": 1.191185599006828,
+      "eval_loss": 0.12441173195838928,
+      "eval_runtime": 40.608,
+      "eval_samples_per_second": 4.186,
+      "eval_steps_per_second": 2.093,
+      "step": 480
+    },
+    {
+      "epoch": 1.2160148975791434,
+      "grad_norm": 0.13227878510951996,
+      "learning_rate": 0.00014866044785668563,
+      "loss": 0.1302,
+      "step": 490
+    },
+    {
+      "epoch": 1.2408441961514587,
+      "grad_norm": 0.11930737644433975,
+      "learning_rate": 0.00014611793542615803,
+      "loss": 0.1269,
+      "step": 500
+    },
+    {
+      "epoch": 1.265673494723774,
+      "grad_norm": 0.08728877454996109,
+      "learning_rate": 0.00014353697429774084,
+      "loss": 0.1217,
+      "step": 510
+    },
+    {
+      "epoch": 1.265673494723774,
+      "eval_loss": 0.1240459457039833,
+      "eval_runtime": 40.3865,
+      "eval_samples_per_second": 4.209,
+      "eval_steps_per_second": 2.105,
+      "step": 510
+    },
+    {
+      "epoch": 1.2905027932960893,
+      "grad_norm": 0.08365845680236816,
+      "learning_rate": 0.0001409197162285275,
+      "loss": 0.1222,
+      "step": 520
+    },
+    {
+      "epoch": 1.3153320918684046,
+      "grad_norm": 0.07661114633083344,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.1239,
+      "step": 530
+    },
+    {
+      "epoch": 1.34016139044072,
+      "grad_norm": 0.10216409713029861,
+      "learning_rate": 0.00013558506578141682,
+      "loss": 0.1307,
+      "step": 540
+    },
+    {
+      "epoch": 1.34016139044072,
+      "eval_loss": 0.12202484905719757,
+      "eval_runtime": 40.6661,
+      "eval_samples_per_second": 4.18,
+      "eval_steps_per_second": 2.09,
+      "step": 540
+    },
+    {
+      "epoch": 1.3649906890130354,
+      "grad_norm": 0.12297932803630829,
+      "learning_rate": 0.00013287212092185464,
+      "loss": 0.1162,
+      "step": 550
+    },
+    {
+      "epoch": 1.3898199875853507,
+      "grad_norm": 0.1034003421664238,
+      "learning_rate": 0.00013013177045025374,
+      "loss": 0.1239,
+      "step": 560
+    },
+    {
+      "epoch": 1.414649286157666,
+      "grad_norm": 0.09044180065393448,
+      "learning_rate": 0.0001273662990072083,
+      "loss": 0.1267,
+      "step": 570
+    },
+    {
+      "epoch": 1.414649286157666,
+      "eval_loss": 0.12448150664567947,
+      "eval_runtime": 40.6346,
+      "eval_samples_per_second": 4.184,
+      "eval_steps_per_second": 2.092,
+      "step": 570
+    },
+    {
+      "epoch": 1.4394785847299814,
+      "grad_norm": 0.25621697306632996,
+      "learning_rate": 0.00012457801217676182,
+      "loss": 0.1271,
+      "step": 580
+    },
+    {
+      "epoch": 1.4643078833022967,
+      "grad_norm": 0.1325441151857376,
+      "learning_rate": 0.00012176923456423284,
+      "loss": 0.1201,
+      "step": 590
+    },
+    {
+      "epoch": 1.489137181874612,
+      "grad_norm": 0.09877412766218185,
+      "learning_rate": 0.00011894230785818284,
+      "loss": 0.1244,
+      "step": 600
+    },
+    {
+      "epoch": 1.489137181874612,
+      "eval_loss": 0.12183106690645218,
+      "eval_runtime": 40.5526,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.096,
+      "step": 600
+    },
+    {
+      "epoch": 1.5139664804469275,
+      "grad_norm": 0.0995541661977768,
+      "learning_rate": 0.00011609958887814129,
+      "loss": 0.1281,
+      "step": 610
+    },
+    {
+      "epoch": 1.5387957790192428,
+      "grad_norm": 0.07273132354021072,
+      "learning_rate": 0.00011324344760971671,
+      "loss": 0.1231,
+      "step": 620
+    },
+    {
+      "epoch": 1.563625077591558,
+      "grad_norm": 0.0884179100394249,
+      "learning_rate": 0.00011037626522873019,
+      "loss": 0.1325,
+      "step": 630
+    },
+    {
+      "epoch": 1.563625077591558,
+      "eval_loss": 0.12128450721502304,
+      "eval_runtime": 40.5099,
+      "eval_samples_per_second": 4.197,
+      "eval_steps_per_second": 2.098,
+      "step": 630
+    },
+    {
+      "epoch": 1.5884543761638734,
+      "grad_norm": 0.10035305470228195,
+      "learning_rate": 0.00010750043211602045,
+      "loss": 0.1225,
+      "step": 640
+    },
+    {
+      "epoch": 1.6132836747361887,
+      "grad_norm": 0.10183248668909073,
+      "learning_rate": 0.00010461834586457398,
+      "loss": 0.1238,
+      "step": 650
+    },
+    {
+      "epoch": 1.638112973308504,
+      "grad_norm": 0.07954993844032288,
+      "learning_rate": 0.00010173240928064285,
+      "loss": 0.1122,
+      "step": 660
+    },
+    {
+      "epoch": 1.638112973308504,
+      "eval_loss": 0.12219967693090439,
+      "eval_runtime": 40.5696,
+      "eval_samples_per_second": 4.19,
+      "eval_steps_per_second": 2.095,
+      "step": 660
+    },
+    {
+      "epoch": 1.6629422718808193,
+      "grad_norm": 0.06452041119337082,
+      "learning_rate": 9.884502838051595e-05,
+      "loss": 0.1224,
+      "step": 670
+    },
+    {
+      "epoch": 1.6877715704531346,
+      "grad_norm": 0.13734178245067596,
+      "learning_rate": 9.595861038461398e-05,
+      "loss": 0.1209,
+      "step": 680
+    },
+    {
+      "epoch": 1.71260086902545,
+      "grad_norm": 0.23182320594787598,
+      "learning_rate": 9.307556171058085e-05,
+      "loss": 0.1259,
+      "step": 690
+    },
+    {
+      "epoch": 1.71260086902545,
+      "eval_loss": 0.12142278999090195,
+      "eval_runtime": 40.5173,
+      "eval_samples_per_second": 4.196,
+      "eval_steps_per_second": 2.098,
+      "step": 690
+    },
+    {
+      "epoch": 1.7374301675977653,
+      "grad_norm": 0.07282444834709167,
+      "learning_rate": 9.019828596704394e-05,
+      "loss": 0.1277,
+      "step": 700
+    },
+    {
+      "epoch": 1.7622594661700806,
+      "grad_norm": 0.09642595052719116,
+      "learning_rate": 8.732918194971664e-05,
+      "loss": 0.1195,
+      "step": 710
+    },
+    {
+      "epoch": 1.7870887647423959,
+      "grad_norm": 0.08414994180202484,
+      "learning_rate": 8.447064164151304e-05,
+      "loss": 0.1318,
+      "step": 720
+    },
+    {
+      "epoch": 1.7870887647423959,
+      "eval_loss": 0.12068802118301392,
+      "eval_runtime": 40.6257,
+      "eval_samples_per_second": 4.185,
+      "eval_steps_per_second": 2.092,
+      "step": 720
+    },
+    {
+      "epoch": 1.8119180633147114,
+      "grad_norm": 0.10453636199235916,
+      "learning_rate": 8.162504821834295e-05,
+      "loss": 0.1218,
+      "step": 730
+    },
+    {
+      "epoch": 1.8367473618870267,
+      "grad_norm": 0.07897430658340454,
+      "learning_rate": 7.879477406224894e-05,
+      "loss": 0.1242,
+      "step": 740
+    },
+    {
+      "epoch": 1.861576660459342,
+      "grad_norm": 0.08946316689252853,
+      "learning_rate": 7.598217878354237e-05,
+      "loss": 0.1178,
+      "step": 750
+    },
+    {
+      "epoch": 1.861576660459342,
+      "eval_loss": 0.12083352357149124,
+      "eval_runtime": 40.4985,
+      "eval_samples_per_second": 4.198,
+      "eval_steps_per_second": 2.099,
+      "step": 750
+    },
+    {
+      "epoch": 1.8864059590316573,
+      "grad_norm": 0.10244396328926086,
+      "learning_rate": 7.318960725358741e-05,
+      "loss": 0.1239,
+      "step": 760
+    },
+    {
+      "epoch": 1.9112352576039728,
+      "grad_norm": 0.07139507681131363,
+      "learning_rate": 7.041938764987297e-05,
+      "loss": 0.1129,
+      "step": 770
+    },
+    {
+      "epoch": 1.9360645561762881,
+      "grad_norm": 0.10991553962230682,
+      "learning_rate": 6.767382951500204e-05,
+      "loss": 0.1165,
+      "step": 780
+    },
+    {
+      "epoch": 1.9360645561762881,
+      "eval_loss": 0.12075280398130417,
+      "eval_runtime": 40.5036,
+      "eval_samples_per_second": 4.197,
+      "eval_steps_per_second": 2.099,
+      "step": 780
+    },
+    {
+      "epoch": 1.9608938547486034,
+      "grad_norm": 0.0928761437535286,
+      "learning_rate": 6.495522183121741e-05,
+      "loss": 0.1286,
+      "step": 790
+    },
+    {
+      "epoch": 1.9857231533209188,
+      "grad_norm": 0.08117903023958206,
+      "learning_rate": 6.226583111206856e-05,
+      "loss": 0.1217,
+      "step": 800
+    },
+    {
+      "epoch": 2.009931719428926,
+      "grad_norm": 0.08340153843164444,
+      "learning_rate": 5.960789951281052e-05,
+      "loss": 0.1138,
+      "step": 810
+    },
+    {
+      "epoch": 2.009931719428926,
+      "eval_loss": 0.11938990652561188,
+      "eval_runtime": 40.4386,
+      "eval_samples_per_second": 4.204,
+      "eval_steps_per_second": 2.102,
+      "step": 810
+    },
+    {
+      "epoch": 2.0347610180012414,
+      "grad_norm": 0.0680561512708664,
+      "learning_rate": 5.698364296111056e-05,
+      "loss": 0.1194,
+      "step": 820
+    },
+    {
+      "epoch": 2.0595903165735567,
+      "grad_norm": 0.09459295123815536,
+      "learning_rate": 5.43952493096211e-05,
+      "loss": 0.1136,
+      "step": 830
+    },
+    {
+      "epoch": 2.084419615145872,
+      "grad_norm": 0.07785169035196304,
+      "learning_rate": 5.184487651195825e-05,
+      "loss": 0.12,
+      "step": 840
+    },
+    {
+      "epoch": 2.084419615145872,
+      "eval_loss": 0.12003041803836823,
+      "eval_runtime": 40.5516,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.096,
+      "step": 840
+    },
+    {
+      "epoch": 2.1092489137181873,
+      "grad_norm": 0.08185684680938721,
+      "learning_rate": 4.933465082360807e-05,
+      "loss": 0.1262,
+      "step": 850
+    },
+    {
+      "epoch": 2.1340782122905027,
+      "grad_norm": 0.08443768322467804,
+      "learning_rate": 4.686666502925908e-05,
+      "loss": 0.1192,
+      "step": 860
+    },
+    {
+      "epoch": 2.158907510862818,
+      "grad_norm": 0.08123073726892471,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.1213,
+      "step": 870
+    },
+    {
+      "epoch": 2.158907510862818,
+      "eval_loss": 0.1197180226445198,
+      "eval_runtime": 40.546,
+      "eval_samples_per_second": 4.193,
+      "eval_steps_per_second": 2.096,
+      "step": 870
+    },
+    {
+      "epoch": 2.1837368094351333,
+      "grad_norm": 0.09900680184364319,
+      "learning_rate": 4.206560646811545e-05,
+      "loss": 0.123,
+      "step": 880
+    },
+    {
+      "epoch": 2.2085661080074486,
+      "grad_norm": 0.08664524555206299,
+      "learning_rate": 3.973653636207437e-05,
+      "loss": 0.11,
+      "step": 890
+    },
+    {
+      "epoch": 2.2333954065797643,
+      "grad_norm": 0.0986846536397934,
+      "learning_rate": 3.745770813450824e-05,
+      "loss": 0.1175,
+      "step": 900
+    },
+    {
+      "epoch": 2.2333954065797643,
+      "eval_loss": 0.11943857371807098,
+      "eval_runtime": 40.5782,
+      "eval_samples_per_second": 4.189,
+      "eval_steps_per_second": 2.095,
+      "step": 900
+    },
+    {
+      "epoch": 2.2582247051520796,
+      "grad_norm": 0.07558804750442505,
+      "learning_rate": 3.523102165316381e-05,
+      "loss": 0.1148,
+      "step": 910
+    },
+    {
+      "epoch": 2.283054003724395,
+      "grad_norm": 0.08511102199554443,
+      "learning_rate": 3.3058333315016065e-05,
+      "loss": 0.1157,
+      "step": 920
+    },
+    {
+      "epoch": 2.3078833022967102,
+      "grad_norm": 0.10936655849218369,
+      "learning_rate": 3.094145449858285e-05,
+      "loss": 0.1202,
+      "step": 930
+    },
+    {
+      "epoch": 2.3078833022967102,
+      "eval_loss": 0.11901655793190002,
+      "eval_runtime": 40.5004,
+      "eval_samples_per_second": 4.197,
+      "eval_steps_per_second": 2.099,
+      "step": 930
+    },
+    {
+      "epoch": 2.3327126008690255,
+      "grad_norm": 0.07215583324432373,
+      "learning_rate": 2.8882150053771995e-05,
+      "loss": 0.1127,
+      "step": 940
+    },
+    {
+      "epoch": 2.357541899441341,
+      "grad_norm": 0.08981175720691681,
+      "learning_rate": 2.688213683051892e-05,
+      "loss": 0.1232,
+      "step": 950
+    },
+    {
+      "epoch": 2.382371198013656,
+      "grad_norm": 0.09188387542963028,
+      "learning_rate": 2.4943082247442585e-05,
+      "loss": 0.1122,
+      "step": 960
+    },
+    {
+      "epoch": 2.382371198013656,
+      "eval_loss": 0.11975335329771042,
+      "eval_runtime": 40.5374,
+      "eval_samples_per_second": 4.194,
+      "eval_steps_per_second": 2.097,
+      "step": 960
+    },
+    {
+      "epoch": 2.4072004965859715,
+      "grad_norm": 0.09929151087999344,
+      "learning_rate": 2.3066602901712108e-05,
+      "loss": 0.1224,
+      "step": 970
+    },
+    {
+      "epoch": 2.4320297951582868,
+      "grad_norm": 0.08618225902318954,
+      "learning_rate": 2.1254263221283654e-05,
+      "loss": 0.1092,
+      "step": 980
+    },
+    {
+      "epoch": 2.456859093730602,
+      "grad_norm": 0.09560118615627289,
+      "learning_rate": 1.950757416063077e-05,
+      "loss": 0.1139,
+      "step": 990
+    },
+    {
+      "epoch": 2.456859093730602,
+      "eval_loss": 0.11890735477209091,
+      "eval_runtime": 40.6128,
+      "eval_samples_per_second": 4.186,
+      "eval_steps_per_second": 2.093,
+      "step": 990
+    },
+    {
+      "epoch": 2.4816883923029174,
+      "grad_norm": 0.10124364495277405,
+      "learning_rate": 1.7827991941056177e-05,
+      "loss": 0.112,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5065176908752327,
+      "grad_norm": 0.0958225354552269,
+      "learning_rate": 1.621691683663418e-05,
+      "loss": 0.1224,
+      "step": 1010
+    },
+    {
+      "epoch": 2.531346989447548,
+      "grad_norm": 0.08832782506942749,
+      "learning_rate": 1.4675692006797137e-05,
+      "loss": 0.1187,
+      "step": 1020
+    },
+    {
+      "epoch": 2.531346989447548,
+      "eval_loss": 0.11912033706903458,
+      "eval_runtime": 40.6481,
+      "eval_samples_per_second": 4.182,
+      "eval_steps_per_second": 2.091,
+      "step": 1020
+    },
+    {
+      "epoch": 2.5561762880198633,
+      "grad_norm": 0.1004873588681221,
+      "learning_rate": 1.3205602376538163e-05,
+      "loss": 0.124,
+      "step": 1030
+    },
+    {
+      "epoch": 2.5810055865921786,
+      "grad_norm": 0.08371691405773163,
+      "learning_rate": 1.1807873565164506e-05,
+      "loss": 0.1173,
+      "step": 1040
+    },
+    {
+      "epoch": 2.6058348851644944,
+      "grad_norm": 0.16757965087890625,
+      "learning_rate": 1.0483670864493778e-05,
+      "loss": 0.1201,
+      "step": 1050
+    },
+    {
+      "epoch": 2.6058348851644944,
+      "eval_loss": 0.11892388015985489,
+      "eval_runtime": 40.6187,
+      "eval_samples_per_second": 4.185,
+      "eval_steps_per_second": 2.093,
+      "step": 1050
+    },
+    {
+      "epoch": 2.630664183736809,
+      "grad_norm": 0.0729515329003334,
+      "learning_rate": 9.234098267345958e-06,
+      "loss": 0.1145,
+      "step": 1060
+    },
+    {
+      "epoch": 2.655493482309125,
+      "grad_norm": 0.12517458200454712,
+      "learning_rate": 8.060197547140347e-06,
+      "loss": 0.1124,
+      "step": 1070
+    },
+    {
+      "epoch": 2.68032278088144,
+      "grad_norm": 0.0805535688996315,
+      "learning_rate": 6.962947389365071e-06,
+      "loss": 0.1165,
+      "step": 1080
+    },
+    {
+      "epoch": 2.68032278088144,
+      "eval_loss": 0.11893562972545624,
+      "eval_runtime": 40.5518,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.096,
+      "step": 1080
+    },
+    {
+      "epoch": 2.7051520794537556,
+      "grad_norm": 0.1218450516462326,
+      "learning_rate": 5.943262575643238e-06,
+      "loss": 0.1275,
+      "step": 1090
+    },
+    {
+      "epoch": 2.729981378026071,
+      "grad_norm": 0.09670189023017883,
+      "learning_rate": 5.001993221076162e-06,
+      "loss": 0.1187,
+      "step": 1100
+    },
+    {
+      "epoch": 2.754810676598386,
+      "grad_norm": 0.09584905207157135,
+      "learning_rate": 4.139924065499035e-06,
+      "loss": 0.115,
+      "step": 1110
+    },
+    {
+      "epoch": 2.754810676598386,
+      "eval_loss": 0.1188565194606781,
+      "eval_runtime": 40.4097,
+      "eval_samples_per_second": 4.207,
+      "eval_steps_per_second": 2.103,
+      "step": 1110
+    },
+    {
+      "epoch": 2.7796399751707015,
+      "grad_norm": 0.11602101475000381,
+      "learning_rate": 3.3577738192404395e-06,
+      "loss": 0.1132,
+      "step": 1120
+    },
+    {
+      "epoch": 2.804469273743017,
+      "grad_norm": 0.09847009181976318,
+      "learning_rate": 2.656194563930714e-06,
+      "loss": 0.1158,
+      "step": 1130
+    },
+    {
+      "epoch": 2.829298572315332,
+      "grad_norm": 0.0924677848815918,
+      "learning_rate": 2.035771208859194e-06,
+      "loss": 0.1156,
+      "step": 1140
+    },
+    {
+      "epoch": 2.829298572315332,
+      "eval_loss": 0.11884363740682602,
+      "eval_runtime": 40.55,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.096,
+      "step": 1140
+    },
+    {
+      "epoch": 2.8541278708876474,
+      "grad_norm": 0.10300548374652863,
+      "learning_rate": 1.49702100333291e-06,
+      "loss": 0.1124,
+      "step": 1150
+    },
+    {
+      "epoch": 2.8789571694599627,
+      "grad_norm": 0.12260911613702774,
+      "learning_rate": 1.0403931054440374e-06,
+      "loss": 0.1171,
+      "step": 1160
+    },
+    {
+      "epoch": 2.903786468032278,
+      "grad_norm": 0.10273098200559616,
+      "learning_rate": 6.662682076050031e-07,
+      "loss": 0.1076,
+      "step": 1170
+    },
+    {
+      "epoch": 2.903786468032278,
+      "eval_loss": 0.1188308522105217,
+      "eval_runtime": 40.5462,
+      "eval_samples_per_second": 4.193,
+      "eval_steps_per_second": 2.096,
+      "step": 1170
+    },
+    {
+      "epoch": 2.9286157666045933,
+      "grad_norm": 0.10531267523765564,
+      "learning_rate": 3.7495821916382344e-07,
+      "loss": 0.1255,
+      "step": 1180
+    },
+    {
+      "epoch": 2.9534450651769086,
+      "grad_norm": 0.12192708998918533,
+      "learning_rate": 1.6670600636403687e-07,
+      "loss": 0.1037,
+      "step": 1190
+    },
+    {
+      "epoch": 2.978274363749224,
+      "grad_norm": 0.09150505810976028,
+      "learning_rate": 4.168518986628067e-08,
+      "loss": 0.1113,
+      "step": 1200
+    },
+    {
+      "epoch": 2.978274363749224,
+      "eval_loss": 0.11880358308553696,
+      "eval_runtime": 40.6429,
+      "eval_samples_per_second": 4.183,
+      "eval_steps_per_second": 2.091,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1209,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2911362158634496e+17,
+  "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 sha256:00d087435218e239e4df8100cc62f15f59065baae886c06ade5b1d254e0ced98
+size 5777

checkpoint-1209/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+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 0.13.2

checkpoint-1209/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1209/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e400301d8693b1de988737f82e1a522cf7d5718360b346f2c289243fca70254d
+size 528550256

checkpoint-1209/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-1209/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-1209/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce1c9ce9b862dda27f8edf6d031f9827d9ac3fe857b1b6f733b05510cf027b2
+size 1057397963

checkpoint-1209/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a391d68393a9b12fcd7cd2dd5b614c1d3918af5767128296916cb37d2d8485bf
+size 14645

checkpoint-1209/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ca2a4b69e015220d60276cfac87721f2d90f53e75cd915ea3a21d4b56ffb30
+size 1465

checkpoint-1209/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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1209/tokenizer.json

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

checkpoint-1209/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1209/trainer_state.json

@@ -0,0 +1,1194 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 30,
+  "global_step": 1209,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024829298572315334,
+      "grad_norm": 8.391741752624512,
+      "learning_rate": 1.487603305785124e-05,
+      "loss": 2.6023,
+      "step": 10
+    },
+    {
+      "epoch": 0.04965859714463067,
+      "grad_norm": 0.7645617723464966,
+      "learning_rate": 3.1404958677685955e-05,
+      "loss": 1.0126,
+      "step": 20
+    },
+    {
+      "epoch": 0.074487895716946,
+      "grad_norm": 0.7797226905822754,
+      "learning_rate": 4.793388429752066e-05,
+      "loss": 0.6236,
+      "step": 30
+    },
+    {
+      "epoch": 0.074487895716946,
+      "eval_loss": 0.5439823865890503,
+      "eval_runtime": 41.1617,
+      "eval_samples_per_second": 4.13,
+      "eval_steps_per_second": 2.065,
+      "step": 30
+    },
+    {
+      "epoch": 0.09931719428926133,
+      "grad_norm": 0.5489462614059448,
+      "learning_rate": 6.446280991735537e-05,
+      "loss": 0.4543,
+      "step": 40
+    },
+    {
+      "epoch": 0.12414649286157665,
+      "grad_norm": 0.7057201266288757,
+      "learning_rate": 8.099173553719009e-05,
+      "loss": 0.369,
+      "step": 50
+    },
+    {
+      "epoch": 0.148975791433892,
+      "grad_norm": 0.44007009267807007,
+      "learning_rate": 9.75206611570248e-05,
+      "loss": 0.2855,
+      "step": 60
+    },
+    {
+      "epoch": 0.148975791433892,
+      "eval_loss": 0.28305545449256897,
+      "eval_runtime": 40.404,
+      "eval_samples_per_second": 4.208,
+      "eval_steps_per_second": 2.104,
+      "step": 60
+    },
+    {
+      "epoch": 0.17380509000620734,
+      "grad_norm": 0.5000414848327637,
+      "learning_rate": 0.0001140495867768595,
+      "loss": 0.2506,
+      "step": 70
+    },
+    {
+      "epoch": 0.19863438857852267,
+      "grad_norm": 0.6662213802337646,
+      "learning_rate": 0.00013057851239669423,
+      "loss": 0.2262,
+      "step": 80
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.4713539481163025,
+      "learning_rate": 0.00014710743801652894,
+      "loss": 0.1983,
+      "step": 90
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "eval_loss": 0.2015635371208191,
+      "eval_runtime": 40.5434,
+      "eval_samples_per_second": 4.193,
+      "eval_steps_per_second": 2.097,
+      "step": 90
+    },
+    {
+      "epoch": 0.2482929857231533,
+      "grad_norm": 0.3806518316268921,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.1905,
+      "step": 100
+    },
+    {
+      "epoch": 0.27312228429546864,
+      "grad_norm": 0.537176251411438,
+      "learning_rate": 0.00018016528925619835,
+      "loss": 0.1681,
+      "step": 110
+    },
+    {
+      "epoch": 0.297951582867784,
+      "grad_norm": 0.39260727167129517,
+      "learning_rate": 0.0001966942148760331,
+      "loss": 0.1619,
+      "step": 120
+    },
+    {
+      "epoch": 0.297951582867784,
+      "eval_loss": 0.1580844670534134,
+      "eval_runtime": 40.5961,
+      "eval_samples_per_second": 4.188,
+      "eval_steps_per_second": 2.094,
+      "step": 120
+    },
+    {
+      "epoch": 0.3227808814400993,
+      "grad_norm": 0.2614082396030426,
+      "learning_rate": 0.00019997332081116373,
+      "loss": 0.156,
+      "step": 130
+    },
+    {
+      "epoch": 0.34761018001241467,
+      "grad_norm": 0.4994271993637085,
+      "learning_rate": 0.00019986496100395275,
+      "loss": 0.1591,
+      "step": 140
+    },
+    {
+      "epoch": 0.37243947858473,
+      "grad_norm": 0.2901883125305176,
+      "learning_rate": 0.000199673343399533,
+      "loss": 0.1536,
+      "step": 150
+    },
+    {
+      "epoch": 0.37243947858473,
+      "eval_loss": 0.15050268173217773,
+      "eval_runtime": 40.6229,
+      "eval_samples_per_second": 4.185,
+      "eval_steps_per_second": 2.092,
+      "step": 150
+    },
+    {
+      "epoch": 0.39726877715704534,
+      "grad_norm": 0.4040389657020569,
+      "learning_rate": 0.00019939862775022893,
+      "loss": 0.1614,
+      "step": 160
+    },
+    {
+      "epoch": 0.42209807572936064,
+      "grad_norm": 0.3563652038574219,
+      "learning_rate": 0.0001990410430875205,
+      "loss": 0.1489,
+      "step": 170
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.21592873334884644,
+      "learning_rate": 0.00019860088753109896,
+      "loss": 0.1491,
+      "step": 180
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "eval_loss": 0.14503230154514313,
+      "eval_runtime": 40.5377,
+      "eval_samples_per_second": 4.194,
+      "eval_steps_per_second": 2.097,
+      "step": 180
+    },
+    {
+      "epoch": 0.4717566728739913,
+      "grad_norm": 0.293130487203598,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.1388,
+      "step": 190
+    },
+    {
+      "epoch": 0.4965859714463066,
+      "grad_norm": 0.5099315643310547,
+      "learning_rate": 0.00019747440010828383,
+      "loss": 0.1398,
+      "step": 200
+    },
+    {
+      "epoch": 0.521415270018622,
+      "grad_norm": 0.3809162974357605,
+      "learning_rate": 0.00019678900739873226,
+      "loss": 0.1484,
+      "step": 210
+    },
+    {
+      "epoch": 0.521415270018622,
+      "eval_loss": 0.1399187594652176,
+      "eval_runtime": 40.3775,
+      "eval_samples_per_second": 4.21,
+      "eval_steps_per_second": 2.105,
+      "step": 210
+    },
+    {
+      "epoch": 0.5462445685909373,
+      "grad_norm": 0.2565288245677948,
+      "learning_rate": 0.000196022921326173,
+      "loss": 0.1406,
+      "step": 220
+    },
+    {
+      "epoch": 0.5710738671632526,
+      "grad_norm": 0.25355908274650574,
+      "learning_rate": 0.00019517678057947384,
+      "loss": 0.1436,
+      "step": 230
+    },
+    {
+      "epoch": 0.595903165735568,
+      "grad_norm": 0.3126136064529419,
+      "learning_rate": 0.00019425129058938832,
+      "loss": 0.1437,
+      "step": 240
+    },
+    {
+      "epoch": 0.595903165735568,
+      "eval_loss": 0.13724148273468018,
+      "eval_runtime": 40.489,
+      "eval_samples_per_second": 4.199,
+      "eval_steps_per_second": 2.099,
+      "step": 240
+    },
+    {
+      "epoch": 0.6207324643078833,
+      "grad_norm": 0.32518845796585083,
+      "learning_rate": 0.00019324722294043558,
+      "loss": 0.1391,
+      "step": 250
+    },
+    {
+      "epoch": 0.6455617628801986,
+      "grad_norm": 0.32164257764816284,
+      "learning_rate": 0.00019216541472762735,
+      "loss": 0.1386,
+      "step": 260
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.37033355236053467,
+      "learning_rate": 0.0001910067678585786,
+      "loss": 0.1329,
+      "step": 270
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "eval_loss": 0.12901660799980164,
+      "eval_runtime": 40.5259,
+      "eval_samples_per_second": 4.195,
+      "eval_steps_per_second": 2.097,
+      "step": 270
+    },
+    {
+      "epoch": 0.6952203600248293,
+      "grad_norm": 0.24198684096336365,
+      "learning_rate": 0.0001897722483015838,
+      "loss": 0.1262,
+      "step": 280
+    },
+    {
+      "epoch": 0.7200496585971446,
+      "grad_norm": 0.20765037834644318,
+      "learning_rate": 0.00018846288528028555,
+      "loss": 0.1281,
+      "step": 290
+    },
+    {
+      "epoch": 0.74487895716946,
+      "grad_norm": 0.1669204831123352,
+      "learning_rate": 0.0001870797704156067,
+      "loss": 0.1376,
+      "step": 300
+    },
+    {
+      "epoch": 0.74487895716946,
+      "eval_loss": 0.1301908791065216,
+      "eval_runtime": 40.6681,
+      "eval_samples_per_second": 4.18,
+      "eval_steps_per_second": 2.09,
+      "step": 300
+    },
+    {
+      "epoch": 0.7697082557417753,
+      "grad_norm": 0.17013825476169586,
+      "learning_rate": 0.00018562405681566216,
+      "loss": 0.1407,
+      "step": 310
+    },
+    {
+      "epoch": 0.7945375543140907,
+      "grad_norm": 0.1282002329826355,
+      "learning_rate": 0.00018409695811440796,
+      "loss": 0.1365,
+      "step": 320
+    },
+    {
+      "epoch": 0.819366852886406,
+      "grad_norm": 0.12342263758182526,
+      "learning_rate": 0.00018249974745983023,
+      "loss": 0.13,
+      "step": 330
+    },
+    {
+      "epoch": 0.819366852886406,
+      "eval_loss": 0.1285768747329712,
+      "eval_runtime": 40.5047,
+      "eval_samples_per_second": 4.197,
+      "eval_steps_per_second": 2.099,
+      "step": 330
+    },
+    {
+      "epoch": 0.8441961514587213,
+      "grad_norm": 0.14901821315288544,
+      "learning_rate": 0.00018083375645251684,
+      "loss": 0.1347,
+      "step": 340
+    },
+    {
+      "epoch": 0.8690254500310366,
+      "grad_norm": 0.17922259867191315,
+      "learning_rate": 0.00017910037403549693,
+      "loss": 0.1325,
+      "step": 350
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.09752878546714783,
+      "learning_rate": 0.0001773010453362737,
+      "loss": 0.1272,
+      "step": 360
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "eval_loss": 0.12547558546066284,
+      "eval_runtime": 40.6167,
+      "eval_samples_per_second": 4.185,
+      "eval_steps_per_second": 2.093,
+      "step": 360
+    },
+    {
+      "epoch": 0.9186840471756673,
+      "grad_norm": 0.17390093207359314,
+      "learning_rate": 0.0001754372704620164,
+      "loss": 0.1334,
+      "step": 370
+    },
+    {
+      "epoch": 0.9435133457479826,
+      "grad_norm": 0.10675700008869171,
+      "learning_rate": 0.00017351060324891502,
+      "loss": 0.1299,
+      "step": 380
+    },
+    {
+      "epoch": 0.9683426443202979,
+      "grad_norm": 0.13889861106872559,
+      "learning_rate": 0.00017152264996674136,
+      "loss": 0.1366,
+      "step": 390
+    },
+    {
+      "epoch": 0.9683426443202979,
+      "eval_loss": 0.12701915204524994,
+      "eval_runtime": 40.4376,
+      "eval_samples_per_second": 4.204,
+      "eval_steps_per_second": 2.102,
+      "step": 390
+    },
+    {
+      "epoch": 0.9931719428926132,
+      "grad_norm": 0.24341008067131042,
+      "learning_rate": 0.00016947506797969562,
+      "loss": 0.1262,
+      "step": 400
+    },
+    {
+      "epoch": 1.0173805090006207,
+      "grad_norm": 0.16011632978916168,
+      "learning_rate": 0.00016736956436465573,
+      "loss": 0.1338,
+      "step": 410
+    },
+    {
+      "epoch": 1.042209807572936,
+      "grad_norm": 0.13081607222557068,
+      "learning_rate": 0.00016520789448798087,
+      "loss": 0.1236,
+      "step": 420
+    },
+    {
+      "epoch": 1.042209807572936,
+      "eval_loss": 0.12546835839748383,
+      "eval_runtime": 40.6293,
+      "eval_samples_per_second": 4.184,
+      "eval_steps_per_second": 2.092,
+      "step": 420
+    },
+    {
+      "epoch": 1.0670391061452513,
+      "grad_norm": 0.10969800502061844,
+      "learning_rate": 0.00016299186054205577,
+      "loss": 0.1263,
+      "step": 430
+    },
+    {
+      "epoch": 1.0918684047175666,
+      "grad_norm": 0.16010411083698273,
+      "learning_rate": 0.00016072331004279614,
+      "loss": 0.1163,
+      "step": 440
+    },
+    {
+      "epoch": 1.1166977032898822,
+      "grad_norm": 0.15039803087711334,
+      "learning_rate": 0.00015840413428936767,
+      "loss": 0.1207,
+      "step": 450
+    },
+    {
+      "epoch": 1.1166977032898822,
+      "eval_loss": 0.12573280930519104,
+      "eval_runtime": 40.5321,
+      "eval_samples_per_second": 4.194,
+      "eval_steps_per_second": 2.097,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415270018621975,
+      "grad_norm": 0.10430776327848434,
+      "learning_rate": 0.00015603626678740263,
+      "loss": 0.1277,
+      "step": 460
+    },
+    {
+      "epoch": 1.1663563004345128,
+      "grad_norm": 0.11445056647062302,
+      "learning_rate": 0.000153621681637029,
+      "loss": 0.1279,
+      "step": 470
+    },
+    {
+      "epoch": 1.191185599006828,
+      "grad_norm": 0.08513262867927551,
+      "learning_rate": 0.00015116239188705556,
+      "loss": 0.1247,
+      "step": 480
+    },
+    {
+      "epoch": 1.191185599006828,
+      "eval_loss": 0.12441173195838928,
+      "eval_runtime": 40.608,
+      "eval_samples_per_second": 4.186,
+      "eval_steps_per_second": 2.093,
+      "step": 480
+    },
+    {
+      "epoch": 1.2160148975791434,
+      "grad_norm": 0.13227878510951996,
+      "learning_rate": 0.00014866044785668563,
+      "loss": 0.1302,
+      "step": 490
+    },
+    {
+      "epoch": 1.2408441961514587,
+      "grad_norm": 0.11930737644433975,
+      "learning_rate": 0.00014611793542615803,
+      "loss": 0.1269,
+      "step": 500
+    },
+    {
+      "epoch": 1.265673494723774,
+      "grad_norm": 0.08728877454996109,
+      "learning_rate": 0.00014353697429774084,
+      "loss": 0.1217,
+      "step": 510
+    },
+    {
+      "epoch": 1.265673494723774,
+      "eval_loss": 0.1240459457039833,
+      "eval_runtime": 40.3865,
+      "eval_samples_per_second": 4.209,
+      "eval_steps_per_second": 2.105,
+      "step": 510
+    },
+    {
+      "epoch": 1.2905027932960893,
+      "grad_norm": 0.08365845680236816,
+      "learning_rate": 0.0001409197162285275,
+      "loss": 0.1222,
+      "step": 520
+    },
+    {
+      "epoch": 1.3153320918684046,
+      "grad_norm": 0.07661114633083344,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.1239,
+      "step": 530
+    },
+    {
+      "epoch": 1.34016139044072,
+      "grad_norm": 0.10216409713029861,
+      "learning_rate": 0.00013558506578141682,
+      "loss": 0.1307,
+      "step": 540
+    },
+    {
+      "epoch": 1.34016139044072,
+      "eval_loss": 0.12202484905719757,
+      "eval_runtime": 40.6661,
+      "eval_samples_per_second": 4.18,
+      "eval_steps_per_second": 2.09,
+      "step": 540
+    },
+    {
+      "epoch": 1.3649906890130354,
+      "grad_norm": 0.12297932803630829,
+      "learning_rate": 0.00013287212092185464,
+      "loss": 0.1162,
+      "step": 550
+    },
+    {
+      "epoch": 1.3898199875853507,
+      "grad_norm": 0.1034003421664238,
+      "learning_rate": 0.00013013177045025374,
+      "loss": 0.1239,
+      "step": 560
+    },
+    {
+      "epoch": 1.414649286157666,
+      "grad_norm": 0.09044180065393448,
+      "learning_rate": 0.0001273662990072083,
+      "loss": 0.1267,
+      "step": 570
+    },
+    {
+      "epoch": 1.414649286157666,
+      "eval_loss": 0.12448150664567947,
+      "eval_runtime": 40.6346,
+      "eval_samples_per_second": 4.184,
+      "eval_steps_per_second": 2.092,
+      "step": 570
+    },
+    {
+      "epoch": 1.4394785847299814,
+      "grad_norm": 0.25621697306632996,
+      "learning_rate": 0.00012457801217676182,
+      "loss": 0.1271,
+      "step": 580
+    },
+    {
+      "epoch": 1.4643078833022967,
+      "grad_norm": 0.1325441151857376,
+      "learning_rate": 0.00012176923456423284,
+      "loss": 0.1201,
+      "step": 590
+    },
+    {
+      "epoch": 1.489137181874612,
+      "grad_norm": 0.09877412766218185,
+      "learning_rate": 0.00011894230785818284,
+      "loss": 0.1244,
+      "step": 600
+    },
+    {
+      "epoch": 1.489137181874612,
+      "eval_loss": 0.12183106690645218,
+      "eval_runtime": 40.5526,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.096,
+      "step": 600
+    },
+    {
+      "epoch": 1.5139664804469275,
+      "grad_norm": 0.0995541661977768,
+      "learning_rate": 0.00011609958887814129,
+      "loss": 0.1281,
+      "step": 610
+    },
+    {
+      "epoch": 1.5387957790192428,
+      "grad_norm": 0.07273132354021072,
+      "learning_rate": 0.00011324344760971671,
+      "loss": 0.1231,
+      "step": 620
+    },
+    {
+      "epoch": 1.563625077591558,
+      "grad_norm": 0.0884179100394249,
+      "learning_rate": 0.00011037626522873019,
+      "loss": 0.1325,
+      "step": 630
+    },
+    {
+      "epoch": 1.563625077591558,
+      "eval_loss": 0.12128450721502304,
+      "eval_runtime": 40.5099,
+      "eval_samples_per_second": 4.197,
+      "eval_steps_per_second": 2.098,
+      "step": 630
+    },
+    {
+      "epoch": 1.5884543761638734,
+      "grad_norm": 0.10035305470228195,
+      "learning_rate": 0.00010750043211602045,
+      "loss": 0.1225,
+      "step": 640
+    },
+    {
+      "epoch": 1.6132836747361887,
+      "grad_norm": 0.10183248668909073,
+      "learning_rate": 0.00010461834586457398,
+      "loss": 0.1238,
+      "step": 650
+    },
+    {
+      "epoch": 1.638112973308504,
+      "grad_norm": 0.07954993844032288,
+      "learning_rate": 0.00010173240928064285,
+      "loss": 0.1122,
+      "step": 660
+    },
+    {
+      "epoch": 1.638112973308504,
+      "eval_loss": 0.12219967693090439,
+      "eval_runtime": 40.5696,
+      "eval_samples_per_second": 4.19,
+      "eval_steps_per_second": 2.095,
+      "step": 660
+    },
+    {
+      "epoch": 1.6629422718808193,
+      "grad_norm": 0.06452041119337082,
+      "learning_rate": 9.884502838051595e-05,
+      "loss": 0.1224,
+      "step": 670
+    },
+    {
+      "epoch": 1.6877715704531346,
+      "grad_norm": 0.13734178245067596,
+      "learning_rate": 9.595861038461398e-05,
+      "loss": 0.1209,
+      "step": 680
+    },
+    {
+      "epoch": 1.71260086902545,
+      "grad_norm": 0.23182320594787598,
+      "learning_rate": 9.307556171058085e-05,
+      "loss": 0.1259,
+      "step": 690
+    },
+    {
+      "epoch": 1.71260086902545,
+      "eval_loss": 0.12142278999090195,
+      "eval_runtime": 40.5173,
+      "eval_samples_per_second": 4.196,
+      "eval_steps_per_second": 2.098,
+      "step": 690
+    },
+    {
+      "epoch": 1.7374301675977653,
+      "grad_norm": 0.07282444834709167,
+      "learning_rate": 9.019828596704394e-05,
+      "loss": 0.1277,
+      "step": 700
+    },
+    {
+      "epoch": 1.7622594661700806,
+      "grad_norm": 0.09642595052719116,
+      "learning_rate": 8.732918194971664e-05,
+      "loss": 0.1195,
+      "step": 710
+    },
+    {
+      "epoch": 1.7870887647423959,
+      "grad_norm": 0.08414994180202484,
+      "learning_rate": 8.447064164151304e-05,
+      "loss": 0.1318,
+      "step": 720
+    },
+    {
+      "epoch": 1.7870887647423959,
+      "eval_loss": 0.12068802118301392,
+      "eval_runtime": 40.6257,
+      "eval_samples_per_second": 4.185,
+      "eval_steps_per_second": 2.092,
+      "step": 720
+    },
+    {
+      "epoch": 1.8119180633147114,
+      "grad_norm": 0.10453636199235916,
+      "learning_rate": 8.162504821834295e-05,
+      "loss": 0.1218,
+      "step": 730
+    },
+    {
+      "epoch": 1.8367473618870267,
+      "grad_norm": 0.07897430658340454,
+      "learning_rate": 7.879477406224894e-05,
+      "loss": 0.1242,
+      "step": 740
+    },
+    {
+      "epoch": 1.861576660459342,
+      "grad_norm": 0.08946316689252853,
+      "learning_rate": 7.598217878354237e-05,
+      "loss": 0.1178,
+      "step": 750
+    },
+    {
+      "epoch": 1.861576660459342,
+      "eval_loss": 0.12083352357149124,
+      "eval_runtime": 40.4985,
+      "eval_samples_per_second": 4.198,
+      "eval_steps_per_second": 2.099,
+      "step": 750
+    },
+    {
+      "epoch": 1.8864059590316573,
+      "grad_norm": 0.10244396328926086,
+      "learning_rate": 7.318960725358741e-05,
+      "loss": 0.1239,
+      "step": 760
+    },
+    {
+      "epoch": 1.9112352576039728,
+      "grad_norm": 0.07139507681131363,
+      "learning_rate": 7.041938764987297e-05,
+      "loss": 0.1129,
+      "step": 770
+    },
+    {
+      "epoch": 1.9360645561762881,
+      "grad_norm": 0.10991553962230682,
+      "learning_rate": 6.767382951500204e-05,
+      "loss": 0.1165,
+      "step": 780
+    },
+    {
+      "epoch": 1.9360645561762881,
+      "eval_loss": 0.12075280398130417,
+      "eval_runtime": 40.5036,
+      "eval_samples_per_second": 4.197,
+      "eval_steps_per_second": 2.099,
+      "step": 780
+    },
+    {
+      "epoch": 1.9608938547486034,
+      "grad_norm": 0.0928761437535286,
+      "learning_rate": 6.495522183121741e-05,
+      "loss": 0.1286,
+      "step": 790
+    },
+    {
+      "epoch": 1.9857231533209188,
+      "grad_norm": 0.08117903023958206,
+      "learning_rate": 6.226583111206856e-05,
+      "loss": 0.1217,
+      "step": 800
+    },
+    {
+      "epoch": 2.009931719428926,
+      "grad_norm": 0.08340153843164444,
+      "learning_rate": 5.960789951281052e-05,
+      "loss": 0.1138,
+      "step": 810
+    },
+    {
+      "epoch": 2.009931719428926,
+      "eval_loss": 0.11938990652561188,
+      "eval_runtime": 40.4386,
+      "eval_samples_per_second": 4.204,
+      "eval_steps_per_second": 2.102,
+      "step": 810
+    },
+    {
+      "epoch": 2.0347610180012414,
+      "grad_norm": 0.0680561512708664,
+      "learning_rate": 5.698364296111056e-05,
+      "loss": 0.1194,
+      "step": 820
+    },
+    {
+      "epoch": 2.0595903165735567,
+      "grad_norm": 0.09459295123815536,
+      "learning_rate": 5.43952493096211e-05,
+      "loss": 0.1136,
+      "step": 830
+    },
+    {
+      "epoch": 2.084419615145872,
+      "grad_norm": 0.07785169035196304,
+      "learning_rate": 5.184487651195825e-05,
+      "loss": 0.12,
+      "step": 840
+    },
+    {
+      "epoch": 2.084419615145872,
+      "eval_loss": 0.12003041803836823,
+      "eval_runtime": 40.5516,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.096,
+      "step": 840
+    },
+    {
+      "epoch": 2.1092489137181873,
+      "grad_norm": 0.08185684680938721,
+      "learning_rate": 4.933465082360807e-05,
+      "loss": 0.1262,
+      "step": 850
+    },
+    {
+      "epoch": 2.1340782122905027,
+      "grad_norm": 0.08443768322467804,
+      "learning_rate": 4.686666502925908e-05,
+      "loss": 0.1192,
+      "step": 860
+    },
+    {
+      "epoch": 2.158907510862818,
+      "grad_norm": 0.08123073726892471,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.1213,
+      "step": 870
+    },
+    {
+      "epoch": 2.158907510862818,
+      "eval_loss": 0.1197180226445198,
+      "eval_runtime": 40.546,
+      "eval_samples_per_second": 4.193,
+      "eval_steps_per_second": 2.096,
+      "step": 870
+    },
+    {
+      "epoch": 2.1837368094351333,
+      "grad_norm": 0.09900680184364319,
+      "learning_rate": 4.206560646811545e-05,
+      "loss": 0.123,
+      "step": 880
+    },
+    {
+      "epoch": 2.2085661080074486,
+      "grad_norm": 0.08664524555206299,
+      "learning_rate": 3.973653636207437e-05,
+      "loss": 0.11,
+      "step": 890
+    },
+    {
+      "epoch": 2.2333954065797643,
+      "grad_norm": 0.0986846536397934,
+      "learning_rate": 3.745770813450824e-05,
+      "loss": 0.1175,
+      "step": 900
+    },
+    {
+      "epoch": 2.2333954065797643,
+      "eval_loss": 0.11943857371807098,
+      "eval_runtime": 40.5782,
+      "eval_samples_per_second": 4.189,
+      "eval_steps_per_second": 2.095,
+      "step": 900
+    },
+    {
+      "epoch": 2.2582247051520796,
+      "grad_norm": 0.07558804750442505,
+      "learning_rate": 3.523102165316381e-05,
+      "loss": 0.1148,
+      "step": 910
+    },
+    {
+      "epoch": 2.283054003724395,
+      "grad_norm": 0.08511102199554443,
+      "learning_rate": 3.3058333315016065e-05,
+      "loss": 0.1157,
+      "step": 920
+    },
+    {
+      "epoch": 2.3078833022967102,
+      "grad_norm": 0.10936655849218369,
+      "learning_rate": 3.094145449858285e-05,
+      "loss": 0.1202,
+      "step": 930
+    },
+    {
+      "epoch": 2.3078833022967102,
+      "eval_loss": 0.11901655793190002,
+      "eval_runtime": 40.5004,
+      "eval_samples_per_second": 4.197,
+      "eval_steps_per_second": 2.099,
+      "step": 930
+    },
+    {
+      "epoch": 2.3327126008690255,
+      "grad_norm": 0.07215583324432373,
+      "learning_rate": 2.8882150053771995e-05,
+      "loss": 0.1127,
+      "step": 940
+    },
+    {
+      "epoch": 2.357541899441341,
+      "grad_norm": 0.08981175720691681,
+      "learning_rate": 2.688213683051892e-05,
+      "loss": 0.1232,
+      "step": 950
+    },
+    {
+      "epoch": 2.382371198013656,
+      "grad_norm": 0.09188387542963028,
+      "learning_rate": 2.4943082247442585e-05,
+      "loss": 0.1122,
+      "step": 960
+    },
+    {
+      "epoch": 2.382371198013656,
+      "eval_loss": 0.11975335329771042,
+      "eval_runtime": 40.5374,
+      "eval_samples_per_second": 4.194,
+      "eval_steps_per_second": 2.097,
+      "step": 960
+    },
+    {
+      "epoch": 2.4072004965859715,
+      "grad_norm": 0.09929151087999344,
+      "learning_rate": 2.3066602901712108e-05,
+      "loss": 0.1224,
+      "step": 970
+    },
+    {
+      "epoch": 2.4320297951582868,
+      "grad_norm": 0.08618225902318954,
+      "learning_rate": 2.1254263221283654e-05,
+      "loss": 0.1092,
+      "step": 980
+    },
+    {
+      "epoch": 2.456859093730602,
+      "grad_norm": 0.09560118615627289,
+      "learning_rate": 1.950757416063077e-05,
+      "loss": 0.1139,
+      "step": 990
+    },
+    {
+      "epoch": 2.456859093730602,
+      "eval_loss": 0.11890735477209091,
+      "eval_runtime": 40.6128,
+      "eval_samples_per_second": 4.186,
+      "eval_steps_per_second": 2.093,
+      "step": 990
+    },
+    {
+      "epoch": 2.4816883923029174,
+      "grad_norm": 0.10124364495277405,
+      "learning_rate": 1.7827991941056177e-05,
+      "loss": 0.112,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5065176908752327,
+      "grad_norm": 0.0958225354552269,
+      "learning_rate": 1.621691683663418e-05,
+      "loss": 0.1224,
+      "step": 1010
+    },
+    {
+      "epoch": 2.531346989447548,
+      "grad_norm": 0.08832782506942749,
+      "learning_rate": 1.4675692006797137e-05,
+      "loss": 0.1187,
+      "step": 1020
+    },
+    {
+      "epoch": 2.531346989447548,
+      "eval_loss": 0.11912033706903458,
+      "eval_runtime": 40.6481,
+      "eval_samples_per_second": 4.182,
+      "eval_steps_per_second": 2.091,
+      "step": 1020
+    },
+    {
+      "epoch": 2.5561762880198633,
+      "grad_norm": 0.1004873588681221,
+      "learning_rate": 1.3205602376538163e-05,
+      "loss": 0.124,
+      "step": 1030
+    },
+    {
+      "epoch": 2.5810055865921786,
+      "grad_norm": 0.08371691405773163,
+      "learning_rate": 1.1807873565164506e-05,
+      "loss": 0.1173,
+      "step": 1040
+    },
+    {
+      "epoch": 2.6058348851644944,
+      "grad_norm": 0.16757965087890625,
+      "learning_rate": 1.0483670864493778e-05,
+      "loss": 0.1201,
+      "step": 1050
+    },
+    {
+      "epoch": 2.6058348851644944,
+      "eval_loss": 0.11892388015985489,
+      "eval_runtime": 40.6187,
+      "eval_samples_per_second": 4.185,
+      "eval_steps_per_second": 2.093,
+      "step": 1050
+    },
+    {
+      "epoch": 2.630664183736809,
+      "grad_norm": 0.0729515329003334,
+      "learning_rate": 9.234098267345958e-06,
+      "loss": 0.1145,
+      "step": 1060
+    },
+    {
+      "epoch": 2.655493482309125,
+      "grad_norm": 0.12517458200454712,
+      "learning_rate": 8.060197547140347e-06,
+      "loss": 0.1124,
+      "step": 1070
+    },
+    {
+      "epoch": 2.68032278088144,
+      "grad_norm": 0.0805535688996315,
+      "learning_rate": 6.962947389365071e-06,
+      "loss": 0.1165,
+      "step": 1080
+    },
+    {
+      "epoch": 2.68032278088144,
+      "eval_loss": 0.11893562972545624,
+      "eval_runtime": 40.5518,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.096,
+      "step": 1080
+    },
+    {
+      "epoch": 2.7051520794537556,
+      "grad_norm": 0.1218450516462326,
+      "learning_rate": 5.943262575643238e-06,
+      "loss": 0.1275,
+      "step": 1090
+    },
+    {
+      "epoch": 2.729981378026071,
+      "grad_norm": 0.09670189023017883,
+      "learning_rate": 5.001993221076162e-06,
+      "loss": 0.1187,
+      "step": 1100
+    },
+    {
+      "epoch": 2.754810676598386,
+      "grad_norm": 0.09584905207157135,
+      "learning_rate": 4.139924065499035e-06,
+      "loss": 0.115,
+      "step": 1110
+    },
+    {
+      "epoch": 2.754810676598386,
+      "eval_loss": 0.1188565194606781,
+      "eval_runtime": 40.4097,
+      "eval_samples_per_second": 4.207,
+      "eval_steps_per_second": 2.103,
+      "step": 1110
+    },
+    {
+      "epoch": 2.7796399751707015,
+      "grad_norm": 0.11602101475000381,
+      "learning_rate": 3.3577738192404395e-06,
+      "loss": 0.1132,
+      "step": 1120
+    },
+    {
+      "epoch": 2.804469273743017,
+      "grad_norm": 0.09847009181976318,
+      "learning_rate": 2.656194563930714e-06,
+      "loss": 0.1158,
+      "step": 1130
+    },
+    {
+      "epoch": 2.829298572315332,
+      "grad_norm": 0.0924677848815918,
+      "learning_rate": 2.035771208859194e-06,
+      "loss": 0.1156,
+      "step": 1140
+    },
+    {
+      "epoch": 2.829298572315332,
+      "eval_loss": 0.11884363740682602,
+      "eval_runtime": 40.55,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.096,
+      "step": 1140
+    },
+    {
+      "epoch": 2.8541278708876474,
+      "grad_norm": 0.10300548374652863,
+      "learning_rate": 1.49702100333291e-06,
+      "loss": 0.1124,
+      "step": 1150
+    },
+    {
+      "epoch": 2.8789571694599627,
+      "grad_norm": 0.12260911613702774,
+      "learning_rate": 1.0403931054440374e-06,
+      "loss": 0.1171,
+      "step": 1160
+    },
+    {
+      "epoch": 2.903786468032278,
+      "grad_norm": 0.10273098200559616,
+      "learning_rate": 6.662682076050031e-07,
+      "loss": 0.1076,
+      "step": 1170
+    },
+    {
+      "epoch": 2.903786468032278,
+      "eval_loss": 0.1188308522105217,
+      "eval_runtime": 40.5462,
+      "eval_samples_per_second": 4.193,
+      "eval_steps_per_second": 2.096,
+      "step": 1170
+    },
+    {
+      "epoch": 2.9286157666045933,
+      "grad_norm": 0.10531267523765564,
+      "learning_rate": 3.7495821916382344e-07,
+      "loss": 0.1255,
+      "step": 1180
+    },
+    {
+      "epoch": 2.9534450651769086,
+      "grad_norm": 0.12192708998918533,
+      "learning_rate": 1.6670600636403687e-07,
+      "loss": 0.1037,
+      "step": 1190
+    },
+    {
+      "epoch": 2.978274363749224,
+      "grad_norm": 0.09150505810976028,
+      "learning_rate": 4.168518986628067e-08,
+      "loss": 0.1113,
+      "step": 1200
+    },
+    {
+      "epoch": 2.978274363749224,
+      "eval_loss": 0.11880358308553696,
+      "eval_runtime": 40.6429,
+      "eval_samples_per_second": 4.183,
+      "eval_steps_per_second": 2.091,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1209,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3038099792711373e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1209/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d087435218e239e4df8100cc62f15f59065baae886c06ade5b1d254e0ced98
+size 5777

config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.12.7",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 262144,
+  "pad_token_id": 151654,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42bb4fbe23b8488236a2cddd0e9f48d7488382afb817805a364de66b9f4ee3a2
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01e367666f9eecd1a7dcc4b88f0ff4e5c086b55389e7558db72b7749b78c1b1
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}