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-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-806/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=64)
+
+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: 4096
+- 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": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_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 sha256:10b98847acf9a0700162848e64e45bf29d6724eba1e79acb979f1f47bdbd39a4
+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-800/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-800/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": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f980cbbb24f88b27524e72fe1cef8c8b09a264a3b2fc8901842678974129d1c
+size 528550256

checkpoint-800/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-800/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-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5598ac3ec871281a4eb7b666120207d304f452387df62907e326da45912b546
+size 1057397963

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2dc3738cb4b0a71f01d20dd1bb37ae67d81b796bac24651ce577b5c57c6498c
+size 14645

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c457d425a9e8056a5fa55b6a2488bf8987cfec7f0ffd56ef7cee13de4b32680a
+size 1465

checkpoint-800/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-800/tokenizer.json

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

checkpoint-800/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-800/trainer_state.json

@@ -0,0 +1,802 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9860291834833903,
+  "eval_steps": 30,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024837007140639553,
+      "grad_norm": 11.272954940795898,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 2.7848,
+      "step": 10
+    },
+    {
+      "epoch": 0.04967401428127911,
+      "grad_norm": 1.125125765800476,
+      "learning_rate": 2.345679012345679e-05,
+      "loss": 1.2296,
+      "step": 20
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "grad_norm": 0.8439419269561768,
+      "learning_rate": 3.580246913580247e-05,
+      "loss": 0.6858,
+      "step": 30
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "eval_loss": 0.6361502408981323,
+      "eval_runtime": 38.0472,
+      "eval_samples_per_second": 4.468,
+      "eval_steps_per_second": 4.468,
+      "step": 30
+    },
+    {
+      "epoch": 0.09934802856255821,
+      "grad_norm": 0.639077365398407,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.5125,
+      "step": 40
+    },
+    {
+      "epoch": 0.12418503570319776,
+      "grad_norm": 0.6465684771537781,
+      "learning_rate": 6.049382716049383e-05,
+      "loss": 0.3889,
+      "step": 50
+    },
+    {
+      "epoch": 0.14902204284383733,
+      "grad_norm": 0.688926100730896,
+      "learning_rate": 7.283950617283951e-05,
+      "loss": 0.3039,
+      "step": 60
+    },
+    {
+      "epoch": 0.14902204284383733,
+      "eval_loss": 0.31402018666267395,
+      "eval_runtime": 37.4247,
+      "eval_samples_per_second": 4.542,
+      "eval_steps_per_second": 4.542,
+      "step": 60
+    },
+    {
+      "epoch": 0.17385904998447688,
+      "grad_norm": 0.6076411008834839,
+      "learning_rate": 8.518518518518518e-05,
+      "loss": 0.2683,
+      "step": 70
+    },
+    {
+      "epoch": 0.19869605712511643,
+      "grad_norm": 1.1276863813400269,
+      "learning_rate": 9.753086419753087e-05,
+      "loss": 0.2392,
+      "step": 80
+    },
+    {
+      "epoch": 0.22353306426575598,
+      "grad_norm": 0.5334923267364502,
+      "learning_rate": 9.996995997963675e-05,
+      "loss": 0.2136,
+      "step": 90
+    },
+    {
+      "epoch": 0.22353306426575598,
+      "eval_loss": 0.2120552957057953,
+      "eval_runtime": 37.372,
+      "eval_samples_per_second": 4.549,
+      "eval_steps_per_second": 4.549,
+      "step": 90
+    },
+    {
+      "epoch": 0.24837007140639553,
+      "grad_norm": 0.43537846207618713,
+      "learning_rate": 9.984798425822163e-05,
+      "loss": 0.1974,
+      "step": 100
+    },
+    {
+      "epoch": 0.2732070785470351,
+      "grad_norm": 0.7943837642669678,
+      "learning_rate": 9.963242415487557e-05,
+      "loss": 0.1678,
+      "step": 110
+    },
+    {
+      "epoch": 0.29804408568767465,
+      "grad_norm": 0.30124473571777344,
+      "learning_rate": 9.932368436116915e-05,
+      "loss": 0.1648,
+      "step": 120
+    },
+    {
+      "epoch": 0.29804408568767465,
+      "eval_loss": 0.15894636511802673,
+      "eval_runtime": 37.5461,
+      "eval_samples_per_second": 4.528,
+      "eval_steps_per_second": 4.528,
+      "step": 120
+    },
+    {
+      "epoch": 0.3228810928283142,
+      "grad_norm": 0.26191410422325134,
+      "learning_rate": 9.892234450380547e-05,
+      "loss": 0.1602,
+      "step": 130
+    },
+    {
+      "epoch": 0.34771809996895375,
+      "grad_norm": 0.5726041197776794,
+      "learning_rate": 9.842915805643155e-05,
+      "loss": 0.1647,
+      "step": 140
+    },
+    {
+      "epoch": 0.3725551071095933,
+      "grad_norm": 0.4395739436149597,
+      "learning_rate": 9.784505092507031e-05,
+      "loss": 0.1525,
+      "step": 150
+    },
+    {
+      "epoch": 0.3725551071095933,
+      "eval_loss": 0.14860223233699799,
+      "eval_runtime": 37.4998,
+      "eval_samples_per_second": 4.533,
+      "eval_steps_per_second": 4.533,
+      "step": 150
+    },
+    {
+      "epoch": 0.39739211425023285,
+      "grad_norm": 0.33055049180984497,
+      "learning_rate": 9.717111970982869e-05,
+      "loss": 0.1555,
+      "step": 160
+    },
+    {
+      "epoch": 0.4222291213908724,
+      "grad_norm": 0.2741611897945404,
+      "learning_rate": 9.640862964614564e-05,
+      "loss": 0.1487,
+      "step": 170
+    },
+    {
+      "epoch": 0.44706612853151195,
+      "grad_norm": 0.3228336572647095,
+      "learning_rate": 9.555901222944468e-05,
+      "loss": 0.1564,
+      "step": 180
+    },
+    {
+      "epoch": 0.44706612853151195,
+      "eval_loss": 0.1397811621427536,
+      "eval_runtime": 37.4841,
+      "eval_samples_per_second": 4.535,
+      "eval_steps_per_second": 4.535,
+      "step": 180
+    },
+    {
+      "epoch": 0.47190313567215153,
+      "grad_norm": 0.23800568282604218,
+      "learning_rate": 9.462386252765087e-05,
+      "loss": 0.1443,
+      "step": 190
+    },
+    {
+      "epoch": 0.49674014281279105,
+      "grad_norm": 0.27476266026496887,
+      "learning_rate": 9.36049361866175e-05,
+      "loss": 0.1447,
+      "step": 200
+    },
+    {
+      "epoch": 0.5215771499534306,
+      "grad_norm": 0.1981421262025833,
+      "learning_rate": 9.250414613408427e-05,
+      "loss": 0.1448,
+      "step": 210
+    },
+    {
+      "epoch": 0.5215771499534306,
+      "eval_loss": 0.1324106752872467,
+      "eval_runtime": 37.3913,
+      "eval_samples_per_second": 4.547,
+      "eval_steps_per_second": 4.547,
+      "step": 210
+    },
+    {
+      "epoch": 0.5464141570940702,
+      "grad_norm": 0.21448366343975067,
+      "learning_rate": 9.132355898835556e-05,
+      "loss": 0.1401,
+      "step": 220
+    },
+    {
+      "epoch": 0.5712511642347097,
+      "grad_norm": 0.2850506603717804,
+      "learning_rate": 9.00653911784403e-05,
+      "loss": 0.1455,
+      "step": 230
+    },
+    {
+      "epoch": 0.5960881713753493,
+      "grad_norm": 0.22351579368114471,
+      "learning_rate": 8.873200478293826e-05,
+      "loss": 0.1478,
+      "step": 240
+    },
+    {
+      "epoch": 0.5960881713753493,
+      "eval_loss": 0.1282844841480255,
+      "eval_runtime": 37.4497,
+      "eval_samples_per_second": 4.539,
+      "eval_steps_per_second": 4.539,
+      "step": 240
+    },
+    {
+      "epoch": 0.6209251785159888,
+      "grad_norm": 0.2048240602016449,
+      "learning_rate": 8.732590309548416e-05,
+      "loss": 0.1357,
+      "step": 250
+    },
+    {
+      "epoch": 0.6457621856566284,
+      "grad_norm": 0.24408458173274994,
+      "learning_rate": 8.584972592507553e-05,
+      "loss": 0.1371,
+      "step": 260
+    },
+    {
+      "epoch": 0.670599192797268,
+      "grad_norm": 0.14031532406806946,
+      "learning_rate": 8.430624464010706e-05,
+      "loss": 0.1424,
+      "step": 270
+    },
+    {
+      "epoch": 0.670599192797268,
+      "eval_loss": 0.12568299472332,
+      "eval_runtime": 37.8149,
+      "eval_samples_per_second": 4.496,
+      "eval_steps_per_second": 4.496,
+      "step": 270
+    },
+    {
+      "epoch": 0.6954361999379075,
+      "grad_norm": 0.24387261271476746,
+      "learning_rate": 8.269835696541607e-05,
+      "loss": 0.1289,
+      "step": 280
+    },
+    {
+      "epoch": 0.720273207078547,
+      "grad_norm": 0.1631806641817093,
+      "learning_rate": 8.102908154210693e-05,
+      "loss": 0.1358,
+      "step": 290
+    },
+    {
+      "epoch": 0.7451102142191866,
+      "grad_norm": 0.1921030879020691,
+      "learning_rate": 7.93015522603677e-05,
+      "loss": 0.1466,
+      "step": 300
+    },
+    {
+      "epoch": 0.7451102142191866,
+      "eval_loss": 0.12537378072738647,
+      "eval_runtime": 37.7611,
+      "eval_samples_per_second": 4.502,
+      "eval_steps_per_second": 4.502,
+      "step": 300
+    },
+    {
+      "epoch": 0.7699472213598262,
+      "grad_norm": 0.17755988240242004,
+      "learning_rate": 7.751901237591887e-05,
+      "loss": 0.1423,
+      "step": 310
+    },
+    {
+      "epoch": 0.7947842285004657,
+      "grad_norm": 0.22009995579719543,
+      "learning_rate": 7.568480842113952e-05,
+      "loss": 0.1399,
+      "step": 320
+    },
+    {
+      "epoch": 0.8196212356411052,
+      "grad_norm": 0.19072045385837555,
+      "learning_rate": 7.380238392230257e-05,
+      "loss": 0.1429,
+      "step": 330
+    },
+    {
+      "epoch": 0.8196212356411052,
+      "eval_loss": 0.12434083968400955,
+      "eval_runtime": 37.8732,
+      "eval_samples_per_second": 4.489,
+      "eval_steps_per_second": 4.489,
+      "step": 330
+    },
+    {
+      "epoch": 0.8444582427817448,
+      "grad_norm": 0.13499405980110168,
+      "learning_rate": 7.187527293471385e-05,
+      "loss": 0.1388,
+      "step": 340
+    },
+    {
+      "epoch": 0.8692952499223844,
+      "grad_norm": 0.1576332151889801,
+      "learning_rate": 6.990709340789273e-05,
+      "loss": 0.1308,
+      "step": 350
+    },
+    {
+      "epoch": 0.8941322570630239,
+      "grad_norm": 0.13361729681491852,
+      "learning_rate": 6.790154039324975e-05,
+      "loss": 0.132,
+      "step": 360
+    },
+    {
+      "epoch": 0.8941322570630239,
+      "eval_loss": 0.12276456505060196,
+      "eval_runtime": 37.8657,
+      "eval_samples_per_second": 4.49,
+      "eval_steps_per_second": 4.49,
+      "step": 360
+    },
+    {
+      "epoch": 0.9189692642036634,
+      "grad_norm": 0.13873551785945892,
+      "learning_rate": 6.586237910701374e-05,
+      "loss": 0.1454,
+      "step": 370
+    },
+    {
+      "epoch": 0.9438062713443031,
+      "grad_norm": 0.12903927266597748,
+      "learning_rate": 6.379343786143184e-05,
+      "loss": 0.1325,
+      "step": 380
+    },
+    {
+      "epoch": 0.9686432784849426,
+      "grad_norm": 0.12467560917139053,
+      "learning_rate": 6.169860087751321e-05,
+      "loss": 0.1389,
+      "step": 390
+    },
+    {
+      "epoch": 0.9686432784849426,
+      "eval_loss": 0.1223841980099678,
+      "eval_runtime": 37.8137,
+      "eval_samples_per_second": 4.496,
+      "eval_steps_per_second": 4.496,
+      "step": 390
+    },
+    {
+      "epoch": 0.9934802856255821,
+      "grad_norm": 0.1413436084985733,
+      "learning_rate": 5.95818009928099e-05,
+      "loss": 0.1283,
+      "step": 400
+    },
+    {
+      "epoch": 1.0173859049984477,
+      "grad_norm": 0.17072723805904388,
+      "learning_rate": 5.744701227792538e-05,
+      "loss": 0.1351,
+      "step": 410
+    },
+    {
+      "epoch": 1.0422229121390871,
+      "grad_norm": 0.15790237486362457,
+      "learning_rate": 5.529824257561212e-05,
+      "loss": 0.1346,
+      "step": 420
+    },
+    {
+      "epoch": 1.0422229121390871,
+      "eval_loss": 0.12222303450107574,
+      "eval_runtime": 37.8365,
+      "eval_samples_per_second": 4.493,
+      "eval_steps_per_second": 4.493,
+      "step": 420
+    },
+    {
+      "epoch": 1.0670599192797268,
+      "grad_norm": 0.14720048010349274,
+      "learning_rate": 5.313952597646568e-05,
+      "loss": 0.1324,
+      "step": 430
+    },
+    {
+      "epoch": 1.0918969264203664,
+      "grad_norm": 0.12014240026473999,
+      "learning_rate": 5.097491524534106e-05,
+      "loss": 0.1315,
+      "step": 440
+    },
+    {
+      "epoch": 1.1167339335610058,
+      "grad_norm": 0.18464700877666473,
+      "learning_rate": 4.88084742127102e-05,
+      "loss": 0.1201,
+      "step": 450
+    },
+    {
+      "epoch": 1.1167339335610058,
+      "eval_loss": 0.12194804102182388,
+      "eval_runtime": 37.6494,
+      "eval_samples_per_second": 4.515,
+      "eval_steps_per_second": 4.515,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415709407016454,
+      "grad_norm": 0.1334882378578186,
+      "learning_rate": 4.664427014524492e-05,
+      "loss": 0.1309,
+      "step": 460
+    },
+    {
+      "epoch": 1.166407947842285,
+      "grad_norm": 0.14938846230506897,
+      "learning_rate": 4.448636610994857e-05,
+      "loss": 0.1313,
+      "step": 470
+    },
+    {
+      "epoch": 1.1912449549829245,
+      "grad_norm": 0.11317029595375061,
+      "learning_rate": 4.2338813346172476e-05,
+      "loss": 0.1297,
+      "step": 480
+    },
+    {
+      "epoch": 1.1912449549829245,
+      "eval_loss": 0.12136982381343842,
+      "eval_runtime": 38.0285,
+      "eval_samples_per_second": 4.47,
+      "eval_steps_per_second": 4.47,
+      "step": 480
+    },
+    {
+      "epoch": 1.2160819621235641,
+      "grad_norm": 0.15464289486408234,
+      "learning_rate": 4.020564365983722e-05,
+      "loss": 0.1344,
+      "step": 490
+    },
+    {
+      "epoch": 1.2409189692642038,
+      "grad_norm": 0.13622425496578217,
+      "learning_rate": 3.80908618541384e-05,
+      "loss": 0.1321,
+      "step": 500
+    },
+    {
+      "epoch": 1.2657559764048432,
+      "grad_norm": 0.18376871943473816,
+      "learning_rate": 3.5998438210946937e-05,
+      "loss": 0.1252,
+      "step": 510
+    },
+    {
+      "epoch": 1.2657559764048432,
+      "eval_loss": 0.12068537622690201,
+      "eval_runtime": 37.8008,
+      "eval_samples_per_second": 4.497,
+      "eval_steps_per_second": 4.497,
+      "step": 510
+    },
+    {
+      "epoch": 1.2905929835454828,
+      "grad_norm": 0.1372678130865097,
+      "learning_rate": 3.393230103701989e-05,
+      "loss": 0.13,
+      "step": 520
+    },
+    {
+      "epoch": 1.3154299906861224,
+      "grad_norm": 0.12849152088165283,
+      "learning_rate": 3.1896329289014846e-05,
+      "loss": 0.1317,
+      "step": 530
+    },
+    {
+      "epoch": 1.3402669978267618,
+      "grad_norm": 0.11176390945911407,
+      "learning_rate": 2.9894345291154202e-05,
+      "loss": 0.13,
+      "step": 540
+    },
+    {
+      "epoch": 1.3402669978267618,
+      "eval_loss": 0.12049100548028946,
+      "eval_runtime": 37.9715,
+      "eval_samples_per_second": 4.477,
+      "eval_steps_per_second": 4.477,
+      "step": 540
+    },
+    {
+      "epoch": 1.3651040049674015,
+      "grad_norm": 0.16603630781173706,
+      "learning_rate": 2.793010755921068e-05,
+      "loss": 0.1272,
+      "step": 550
+    },
+    {
+      "epoch": 1.389941012108041,
+      "grad_norm": 0.1615874320268631,
+      "learning_rate": 2.6007303744286844e-05,
+      "loss": 0.1309,
+      "step": 560
+    },
+    {
+      "epoch": 1.4147780192486805,
+      "grad_norm": 0.13734523952007294,
+      "learning_rate": 2.4129543709635378e-05,
+      "loss": 0.1303,
+      "step": 570
+    },
+    {
+      "epoch": 1.4147780192486805,
+      "eval_loss": 0.12090769410133362,
+      "eval_runtime": 38.0585,
+      "eval_samples_per_second": 4.467,
+      "eval_steps_per_second": 4.467,
+      "step": 570
+    },
+    {
+      "epoch": 1.4396150263893202,
+      "grad_norm": 0.13437435030937195,
+      "learning_rate": 2.230035275351806e-05,
+      "loss": 0.1338,
+      "step": 580
+    },
+    {
+      "epoch": 1.4644520335299596,
+      "grad_norm": 0.12444904446601868,
+      "learning_rate": 2.0523164990826543e-05,
+      "loss": 0.1281,
+      "step": 590
+    },
+    {
+      "epoch": 1.4892890406705992,
+      "grad_norm": 0.14093923568725586,
+      "learning_rate": 1.8801316905890583e-05,
+      "loss": 0.1307,
+      "step": 600
+    },
+    {
+      "epoch": 1.4892890406705992,
+      "eval_loss": 0.11982201784849167,
+      "eval_runtime": 37.9037,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 600
+    },
+    {
+      "epoch": 1.5141260478112386,
+      "grad_norm": 0.14758960902690887,
+      "learning_rate": 1.7138041088577267e-05,
+      "loss": 0.1299,
+      "step": 610
+    },
+    {
+      "epoch": 1.5389630549518785,
+      "grad_norm": 0.13439303636550903,
+      "learning_rate": 1.5536460165441323e-05,
+      "loss": 0.1285,
+      "step": 620
+    },
+    {
+      "epoch": 1.5638000620925179,
+      "grad_norm": 0.1315300315618515,
+      "learning_rate": 1.3999580937320011e-05,
+      "loss": 0.1294,
+      "step": 630
+    },
+    {
+      "epoch": 1.5638000620925179,
+      "eval_loss": 0.11952362954616547,
+      "eval_runtime": 37.8235,
+      "eval_samples_per_second": 4.495,
+      "eval_steps_per_second": 4.495,
+      "step": 630
+    },
+    {
+      "epoch": 1.5886370692331573,
+      "grad_norm": 0.13855591416358948,
+      "learning_rate": 1.2530288734378764e-05,
+      "loss": 0.1302,
+      "step": 640
+    },
+    {
+      "epoch": 1.613474076373797,
+      "grad_norm": 0.14461226761341095,
+      "learning_rate": 1.1131341999205274e-05,
+      "loss": 0.1241,
+      "step": 650
+    },
+    {
+      "epoch": 1.6383110835144366,
+      "grad_norm": 0.1513630747795105,
+      "learning_rate": 9.805367108121761e-06,
+      "loss": 0.1177,
+      "step": 660
+    },
+    {
+      "epoch": 1.6383110835144366,
+      "eval_loss": 0.11914250999689102,
+      "eval_runtime": 37.8427,
+      "eval_samples_per_second": 4.492,
+      "eval_steps_per_second": 4.492,
+      "step": 660
+    },
+    {
+      "epoch": 1.663148090655076,
+      "grad_norm": 0.3891820013523102,
+      "learning_rate": 8.554853440437805e-06,
+      "loss": 0.1297,
+      "step": 670
+    },
+    {
+      "epoch": 1.6879850977957156,
+      "grad_norm": 0.1408233791589737,
+      "learning_rate": 7.382148704900882e-06,
+      "loss": 0.1302,
+      "step": 680
+    },
+    {
+      "epoch": 1.7128221049363552,
+      "grad_norm": 0.15466411411762238,
+      "learning_rate": 6.289454532118444e-06,
+      "loss": 0.1288,
+      "step": 690
+    },
+    {
+      "epoch": 1.7128221049363552,
+      "eval_loss": 0.11917895078659058,
+      "eval_runtime": 37.8925,
+      "eval_samples_per_second": 4.486,
+      "eval_steps_per_second": 4.486,
+      "step": 690
+    },
+    {
+      "epoch": 1.7376591120769946,
+      "grad_norm": 0.09873683750629425,
+      "learning_rate": 5.278822341226519e-06,
+      "loss": 0.1296,
+      "step": 700
+    },
+    {
+      "epoch": 1.7624961192176343,
+      "grad_norm": 0.13227960467338562,
+      "learning_rate": 4.352149488564605e-06,
+      "loss": 0.1241,
+      "step": 710
+    },
+    {
+      "epoch": 1.787333126358274,
+      "grad_norm": 0.12939970195293427,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.1362,
+      "step": 720
+    },
+    {
+      "epoch": 1.787333126358274,
+      "eval_loss": 0.11892342567443848,
+      "eval_runtime": 37.9012,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 720
+    },
+    {
+      "epoch": 1.8121701334989133,
+      "grad_norm": 0.15326713025569916,
+      "learning_rate": 2.75747983270091e-06,
+      "loss": 0.1287,
+      "step": 730
+    },
+    {
+      "epoch": 1.837007140639553,
+      "grad_norm": 0.13985218107700348,
+      "learning_rate": 2.0924768551542463e-06,
+      "loss": 0.1298,
+      "step": 740
+    },
+    {
+      "epoch": 1.8618441477801926,
+      "grad_norm": 0.14625447988510132,
+      "learning_rate": 1.517415246552978e-06,
+      "loss": 0.1295,
+      "step": 750
+    },
+    {
+      "epoch": 1.8618441477801926,
+      "eval_loss": 0.11896809190511703,
+      "eval_runtime": 37.7631,
+      "eval_samples_per_second": 4.502,
+      "eval_steps_per_second": 4.502,
+      "step": 750
+    },
+    {
+      "epoch": 1.886681154920832,
+      "grad_norm": 0.134150892496109,
+      "learning_rate": 1.033374624980249e-06,
+      "loss": 0.1252,
+      "step": 760
+    },
+    {
+      "epoch": 1.9115181620614716,
+      "grad_norm": 0.1421349197626114,
+      "learning_rate": 6.412637261266396e-07,
+      "loss": 0.1224,
+      "step": 770
+    },
+    {
+      "epoch": 1.9363551692021113,
+      "grad_norm": 0.1370449662208557,
+      "learning_rate": 3.418186972338977e-07,
+      "loss": 0.1305,
+      "step": 780
+    },
+    {
+      "epoch": 1.9363551692021113,
+      "eval_loss": 0.11897934973239899,
+      "eval_runtime": 37.8217,
+      "eval_samples_per_second": 4.495,
+      "eval_steps_per_second": 4.495,
+      "step": 780
+    },
+    {
+      "epoch": 1.9611921763427507,
+      "grad_norm": 0.14134632050991058,
+      "learning_rate": 1.356017150553557e-07,
+      "loss": 0.1298,
+      "step": 790
+    },
+    {
+      "epoch": 1.9860291834833903,
+      "grad_norm": 0.13970708847045898,
+      "learning_rate": 2.299993042786941e-08,
+      "loss": 0.1286,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 806,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.2428317974302515e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e44568f8bf26e68c5a24546f6c205919eef34f726abef048aadaf2d067a5197
+size 5777

checkpoint-806/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-806/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": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-806/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b98847acf9a0700162848e64e45bf29d6724eba1e79acb979f1f47bdbd39a4
+size 528550256

checkpoint-806/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-806/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-806/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8cb728c50ac3bbe0bc230c6dc94dee4b1840ed71a8af153ae63a6768238bbe0
+size 1057397963

checkpoint-806/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2dc3738cb4b0a71f01d20dd1bb37ae67d81b796bac24651ce577b5c57c6498c
+size 14645

checkpoint-806/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05b614abf3826aa94fe6e2f7a5d94f4967ebffa30ee56f5512c61ba7dce572b
+size 1465

checkpoint-806/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-806/tokenizer.json

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

checkpoint-806/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-806/trainer_state.json

@@ -0,0 +1,802 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 30,
+  "global_step": 806,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024837007140639553,
+      "grad_norm": 11.272954940795898,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 2.7848,
+      "step": 10
+    },
+    {
+      "epoch": 0.04967401428127911,
+      "grad_norm": 1.125125765800476,
+      "learning_rate": 2.345679012345679e-05,
+      "loss": 1.2296,
+      "step": 20
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "grad_norm": 0.8439419269561768,
+      "learning_rate": 3.580246913580247e-05,
+      "loss": 0.6858,
+      "step": 30
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "eval_loss": 0.6361502408981323,
+      "eval_runtime": 38.0472,
+      "eval_samples_per_second": 4.468,
+      "eval_steps_per_second": 4.468,
+      "step": 30
+    },
+    {
+      "epoch": 0.09934802856255821,
+      "grad_norm": 0.639077365398407,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.5125,
+      "step": 40
+    },
+    {
+      "epoch": 0.12418503570319776,
+      "grad_norm": 0.6465684771537781,
+      "learning_rate": 6.049382716049383e-05,
+      "loss": 0.3889,
+      "step": 50
+    },
+    {
+      "epoch": 0.14902204284383733,
+      "grad_norm": 0.688926100730896,
+      "learning_rate": 7.283950617283951e-05,
+      "loss": 0.3039,
+      "step": 60
+    },
+    {
+      "epoch": 0.14902204284383733,
+      "eval_loss": 0.31402018666267395,
+      "eval_runtime": 37.4247,
+      "eval_samples_per_second": 4.542,
+      "eval_steps_per_second": 4.542,
+      "step": 60
+    },
+    {
+      "epoch": 0.17385904998447688,
+      "grad_norm": 0.6076411008834839,
+      "learning_rate": 8.518518518518518e-05,
+      "loss": 0.2683,
+      "step": 70
+    },
+    {
+      "epoch": 0.19869605712511643,
+      "grad_norm": 1.1276863813400269,
+      "learning_rate": 9.753086419753087e-05,
+      "loss": 0.2392,
+      "step": 80
+    },
+    {
+      "epoch": 0.22353306426575598,
+      "grad_norm": 0.5334923267364502,
+      "learning_rate": 9.996995997963675e-05,
+      "loss": 0.2136,
+      "step": 90
+    },
+    {
+      "epoch": 0.22353306426575598,
+      "eval_loss": 0.2120552957057953,
+      "eval_runtime": 37.372,
+      "eval_samples_per_second": 4.549,
+      "eval_steps_per_second": 4.549,
+      "step": 90
+    },
+    {
+      "epoch": 0.24837007140639553,
+      "grad_norm": 0.43537846207618713,
+      "learning_rate": 9.984798425822163e-05,
+      "loss": 0.1974,
+      "step": 100
+    },
+    {
+      "epoch": 0.2732070785470351,
+      "grad_norm": 0.7943837642669678,
+      "learning_rate": 9.963242415487557e-05,
+      "loss": 0.1678,
+      "step": 110
+    },
+    {
+      "epoch": 0.29804408568767465,
+      "grad_norm": 0.30124473571777344,
+      "learning_rate": 9.932368436116915e-05,
+      "loss": 0.1648,
+      "step": 120
+    },
+    {
+      "epoch": 0.29804408568767465,
+      "eval_loss": 0.15894636511802673,
+      "eval_runtime": 37.5461,
+      "eval_samples_per_second": 4.528,
+      "eval_steps_per_second": 4.528,
+      "step": 120
+    },
+    {
+      "epoch": 0.3228810928283142,
+      "grad_norm": 0.26191410422325134,
+      "learning_rate": 9.892234450380547e-05,
+      "loss": 0.1602,
+      "step": 130
+    },
+    {
+      "epoch": 0.34771809996895375,
+      "grad_norm": 0.5726041197776794,
+      "learning_rate": 9.842915805643155e-05,
+      "loss": 0.1647,
+      "step": 140
+    },
+    {
+      "epoch": 0.3725551071095933,
+      "grad_norm": 0.4395739436149597,
+      "learning_rate": 9.784505092507031e-05,
+      "loss": 0.1525,
+      "step": 150
+    },
+    {
+      "epoch": 0.3725551071095933,
+      "eval_loss": 0.14860223233699799,
+      "eval_runtime": 37.4998,
+      "eval_samples_per_second": 4.533,
+      "eval_steps_per_second": 4.533,
+      "step": 150
+    },
+    {
+      "epoch": 0.39739211425023285,
+      "grad_norm": 0.33055049180984497,
+      "learning_rate": 9.717111970982869e-05,
+      "loss": 0.1555,
+      "step": 160
+    },
+    {
+      "epoch": 0.4222291213908724,
+      "grad_norm": 0.2741611897945404,
+      "learning_rate": 9.640862964614564e-05,
+      "loss": 0.1487,
+      "step": 170
+    },
+    {
+      "epoch": 0.44706612853151195,
+      "grad_norm": 0.3228336572647095,
+      "learning_rate": 9.555901222944468e-05,
+      "loss": 0.1564,
+      "step": 180
+    },
+    {
+      "epoch": 0.44706612853151195,
+      "eval_loss": 0.1397811621427536,
+      "eval_runtime": 37.4841,
+      "eval_samples_per_second": 4.535,
+      "eval_steps_per_second": 4.535,
+      "step": 180
+    },
+    {
+      "epoch": 0.47190313567215153,
+      "grad_norm": 0.23800568282604218,
+      "learning_rate": 9.462386252765087e-05,
+      "loss": 0.1443,
+      "step": 190
+    },
+    {
+      "epoch": 0.49674014281279105,
+      "grad_norm": 0.27476266026496887,
+      "learning_rate": 9.36049361866175e-05,
+      "loss": 0.1447,
+      "step": 200
+    },
+    {
+      "epoch": 0.5215771499534306,
+      "grad_norm": 0.1981421262025833,
+      "learning_rate": 9.250414613408427e-05,
+      "loss": 0.1448,
+      "step": 210
+    },
+    {
+      "epoch": 0.5215771499534306,
+      "eval_loss": 0.1324106752872467,
+      "eval_runtime": 37.3913,
+      "eval_samples_per_second": 4.547,
+      "eval_steps_per_second": 4.547,
+      "step": 210
+    },
+    {
+      "epoch": 0.5464141570940702,
+      "grad_norm": 0.21448366343975067,
+      "learning_rate": 9.132355898835556e-05,
+      "loss": 0.1401,
+      "step": 220
+    },
+    {
+      "epoch": 0.5712511642347097,
+      "grad_norm": 0.2850506603717804,
+      "learning_rate": 9.00653911784403e-05,
+      "loss": 0.1455,
+      "step": 230
+    },
+    {
+      "epoch": 0.5960881713753493,
+      "grad_norm": 0.22351579368114471,
+      "learning_rate": 8.873200478293826e-05,
+      "loss": 0.1478,
+      "step": 240
+    },
+    {
+      "epoch": 0.5960881713753493,
+      "eval_loss": 0.1282844841480255,
+      "eval_runtime": 37.4497,
+      "eval_samples_per_second": 4.539,
+      "eval_steps_per_second": 4.539,
+      "step": 240
+    },
+    {
+      "epoch": 0.6209251785159888,
+      "grad_norm": 0.2048240602016449,
+      "learning_rate": 8.732590309548416e-05,
+      "loss": 0.1357,
+      "step": 250
+    },
+    {
+      "epoch": 0.6457621856566284,
+      "grad_norm": 0.24408458173274994,
+      "learning_rate": 8.584972592507553e-05,
+      "loss": 0.1371,
+      "step": 260
+    },
+    {
+      "epoch": 0.670599192797268,
+      "grad_norm": 0.14031532406806946,
+      "learning_rate": 8.430624464010706e-05,
+      "loss": 0.1424,
+      "step": 270
+    },
+    {
+      "epoch": 0.670599192797268,
+      "eval_loss": 0.12568299472332,
+      "eval_runtime": 37.8149,
+      "eval_samples_per_second": 4.496,
+      "eval_steps_per_second": 4.496,
+      "step": 270
+    },
+    {
+      "epoch": 0.6954361999379075,
+      "grad_norm": 0.24387261271476746,
+      "learning_rate": 8.269835696541607e-05,
+      "loss": 0.1289,
+      "step": 280
+    },
+    {
+      "epoch": 0.720273207078547,
+      "grad_norm": 0.1631806641817093,
+      "learning_rate": 8.102908154210693e-05,
+      "loss": 0.1358,
+      "step": 290
+    },
+    {
+      "epoch": 0.7451102142191866,
+      "grad_norm": 0.1921030879020691,
+      "learning_rate": 7.93015522603677e-05,
+      "loss": 0.1466,
+      "step": 300
+    },
+    {
+      "epoch": 0.7451102142191866,
+      "eval_loss": 0.12537378072738647,
+      "eval_runtime": 37.7611,
+      "eval_samples_per_second": 4.502,
+      "eval_steps_per_second": 4.502,
+      "step": 300
+    },
+    {
+      "epoch": 0.7699472213598262,
+      "grad_norm": 0.17755988240242004,
+      "learning_rate": 7.751901237591887e-05,
+      "loss": 0.1423,
+      "step": 310
+    },
+    {
+      "epoch": 0.7947842285004657,
+      "grad_norm": 0.22009995579719543,
+      "learning_rate": 7.568480842113952e-05,
+      "loss": 0.1399,
+      "step": 320
+    },
+    {
+      "epoch": 0.8196212356411052,
+      "grad_norm": 0.19072045385837555,
+      "learning_rate": 7.380238392230257e-05,
+      "loss": 0.1429,
+      "step": 330
+    },
+    {
+      "epoch": 0.8196212356411052,
+      "eval_loss": 0.12434083968400955,
+      "eval_runtime": 37.8732,
+      "eval_samples_per_second": 4.489,
+      "eval_steps_per_second": 4.489,
+      "step": 330
+    },
+    {
+      "epoch": 0.8444582427817448,
+      "grad_norm": 0.13499405980110168,
+      "learning_rate": 7.187527293471385e-05,
+      "loss": 0.1388,
+      "step": 340
+    },
+    {
+      "epoch": 0.8692952499223844,
+      "grad_norm": 0.1576332151889801,
+      "learning_rate": 6.990709340789273e-05,
+      "loss": 0.1308,
+      "step": 350
+    },
+    {
+      "epoch": 0.8941322570630239,
+      "grad_norm": 0.13361729681491852,
+      "learning_rate": 6.790154039324975e-05,
+      "loss": 0.132,
+      "step": 360
+    },
+    {
+      "epoch": 0.8941322570630239,
+      "eval_loss": 0.12276456505060196,
+      "eval_runtime": 37.8657,
+      "eval_samples_per_second": 4.49,
+      "eval_steps_per_second": 4.49,
+      "step": 360
+    },
+    {
+      "epoch": 0.9189692642036634,
+      "grad_norm": 0.13873551785945892,
+      "learning_rate": 6.586237910701374e-05,
+      "loss": 0.1454,
+      "step": 370
+    },
+    {
+      "epoch": 0.9438062713443031,
+      "grad_norm": 0.12903927266597748,
+      "learning_rate": 6.379343786143184e-05,
+      "loss": 0.1325,
+      "step": 380
+    },
+    {
+      "epoch": 0.9686432784849426,
+      "grad_norm": 0.12467560917139053,
+      "learning_rate": 6.169860087751321e-05,
+      "loss": 0.1389,
+      "step": 390
+    },
+    {
+      "epoch": 0.9686432784849426,
+      "eval_loss": 0.1223841980099678,
+      "eval_runtime": 37.8137,
+      "eval_samples_per_second": 4.496,
+      "eval_steps_per_second": 4.496,
+      "step": 390
+    },
+    {
+      "epoch": 0.9934802856255821,
+      "grad_norm": 0.1413436084985733,
+      "learning_rate": 5.95818009928099e-05,
+      "loss": 0.1283,
+      "step": 400
+    },
+    {
+      "epoch": 1.0173859049984477,
+      "grad_norm": 0.17072723805904388,
+      "learning_rate": 5.744701227792538e-05,
+      "loss": 0.1351,
+      "step": 410
+    },
+    {
+      "epoch": 1.0422229121390871,
+      "grad_norm": 0.15790237486362457,
+      "learning_rate": 5.529824257561212e-05,
+      "loss": 0.1346,
+      "step": 420
+    },
+    {
+      "epoch": 1.0422229121390871,
+      "eval_loss": 0.12222303450107574,
+      "eval_runtime": 37.8365,
+      "eval_samples_per_second": 4.493,
+      "eval_steps_per_second": 4.493,
+      "step": 420
+    },
+    {
+      "epoch": 1.0670599192797268,
+      "grad_norm": 0.14720048010349274,
+      "learning_rate": 5.313952597646568e-05,
+      "loss": 0.1324,
+      "step": 430
+    },
+    {
+      "epoch": 1.0918969264203664,
+      "grad_norm": 0.12014240026473999,
+      "learning_rate": 5.097491524534106e-05,
+      "loss": 0.1315,
+      "step": 440
+    },
+    {
+      "epoch": 1.1167339335610058,
+      "grad_norm": 0.18464700877666473,
+      "learning_rate": 4.88084742127102e-05,
+      "loss": 0.1201,
+      "step": 450
+    },
+    {
+      "epoch": 1.1167339335610058,
+      "eval_loss": 0.12194804102182388,
+      "eval_runtime": 37.6494,
+      "eval_samples_per_second": 4.515,
+      "eval_steps_per_second": 4.515,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415709407016454,
+      "grad_norm": 0.1334882378578186,
+      "learning_rate": 4.664427014524492e-05,
+      "loss": 0.1309,
+      "step": 460
+    },
+    {
+      "epoch": 1.166407947842285,
+      "grad_norm": 0.14938846230506897,
+      "learning_rate": 4.448636610994857e-05,
+      "loss": 0.1313,
+      "step": 470
+    },
+    {
+      "epoch": 1.1912449549829245,
+      "grad_norm": 0.11317029595375061,
+      "learning_rate": 4.2338813346172476e-05,
+      "loss": 0.1297,
+      "step": 480
+    },
+    {
+      "epoch": 1.1912449549829245,
+      "eval_loss": 0.12136982381343842,
+      "eval_runtime": 38.0285,
+      "eval_samples_per_second": 4.47,
+      "eval_steps_per_second": 4.47,
+      "step": 480
+    },
+    {
+      "epoch": 1.2160819621235641,
+      "grad_norm": 0.15464289486408234,
+      "learning_rate": 4.020564365983722e-05,
+      "loss": 0.1344,
+      "step": 490
+    },
+    {
+      "epoch": 1.2409189692642038,
+      "grad_norm": 0.13622425496578217,
+      "learning_rate": 3.80908618541384e-05,
+      "loss": 0.1321,
+      "step": 500
+    },
+    {
+      "epoch": 1.2657559764048432,
+      "grad_norm": 0.18376871943473816,
+      "learning_rate": 3.5998438210946937e-05,
+      "loss": 0.1252,
+      "step": 510
+    },
+    {
+      "epoch": 1.2657559764048432,
+      "eval_loss": 0.12068537622690201,
+      "eval_runtime": 37.8008,
+      "eval_samples_per_second": 4.497,
+      "eval_steps_per_second": 4.497,
+      "step": 510
+    },
+    {
+      "epoch": 1.2905929835454828,
+      "grad_norm": 0.1372678130865097,
+      "learning_rate": 3.393230103701989e-05,
+      "loss": 0.13,
+      "step": 520
+    },
+    {
+      "epoch": 1.3154299906861224,
+      "grad_norm": 0.12849152088165283,
+      "learning_rate": 3.1896329289014846e-05,
+      "loss": 0.1317,
+      "step": 530
+    },
+    {
+      "epoch": 1.3402669978267618,
+      "grad_norm": 0.11176390945911407,
+      "learning_rate": 2.9894345291154202e-05,
+      "loss": 0.13,
+      "step": 540
+    },
+    {
+      "epoch": 1.3402669978267618,
+      "eval_loss": 0.12049100548028946,
+      "eval_runtime": 37.9715,
+      "eval_samples_per_second": 4.477,
+      "eval_steps_per_second": 4.477,
+      "step": 540
+    },
+    {
+      "epoch": 1.3651040049674015,
+      "grad_norm": 0.16603630781173706,
+      "learning_rate": 2.793010755921068e-05,
+      "loss": 0.1272,
+      "step": 550
+    },
+    {
+      "epoch": 1.389941012108041,
+      "grad_norm": 0.1615874320268631,
+      "learning_rate": 2.6007303744286844e-05,
+      "loss": 0.1309,
+      "step": 560
+    },
+    {
+      "epoch": 1.4147780192486805,
+      "grad_norm": 0.13734523952007294,
+      "learning_rate": 2.4129543709635378e-05,
+      "loss": 0.1303,
+      "step": 570
+    },
+    {
+      "epoch": 1.4147780192486805,
+      "eval_loss": 0.12090769410133362,
+      "eval_runtime": 38.0585,
+      "eval_samples_per_second": 4.467,
+      "eval_steps_per_second": 4.467,
+      "step": 570
+    },
+    {
+      "epoch": 1.4396150263893202,
+      "grad_norm": 0.13437435030937195,
+      "learning_rate": 2.230035275351806e-05,
+      "loss": 0.1338,
+      "step": 580
+    },
+    {
+      "epoch": 1.4644520335299596,
+      "grad_norm": 0.12444904446601868,
+      "learning_rate": 2.0523164990826543e-05,
+      "loss": 0.1281,
+      "step": 590
+    },
+    {
+      "epoch": 1.4892890406705992,
+      "grad_norm": 0.14093923568725586,
+      "learning_rate": 1.8801316905890583e-05,
+      "loss": 0.1307,
+      "step": 600
+    },
+    {
+      "epoch": 1.4892890406705992,
+      "eval_loss": 0.11982201784849167,
+      "eval_runtime": 37.9037,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 600
+    },
+    {
+      "epoch": 1.5141260478112386,
+      "grad_norm": 0.14758960902690887,
+      "learning_rate": 1.7138041088577267e-05,
+      "loss": 0.1299,
+      "step": 610
+    },
+    {
+      "epoch": 1.5389630549518785,
+      "grad_norm": 0.13439303636550903,
+      "learning_rate": 1.5536460165441323e-05,
+      "loss": 0.1285,
+      "step": 620
+    },
+    {
+      "epoch": 1.5638000620925179,
+      "grad_norm": 0.1315300315618515,
+      "learning_rate": 1.3999580937320011e-05,
+      "loss": 0.1294,
+      "step": 630
+    },
+    {
+      "epoch": 1.5638000620925179,
+      "eval_loss": 0.11952362954616547,
+      "eval_runtime": 37.8235,
+      "eval_samples_per_second": 4.495,
+      "eval_steps_per_second": 4.495,
+      "step": 630
+    },
+    {
+      "epoch": 1.5886370692331573,
+      "grad_norm": 0.13855591416358948,
+      "learning_rate": 1.2530288734378764e-05,
+      "loss": 0.1302,
+      "step": 640
+    },
+    {
+      "epoch": 1.613474076373797,
+      "grad_norm": 0.14461226761341095,
+      "learning_rate": 1.1131341999205274e-05,
+      "loss": 0.1241,
+      "step": 650
+    },
+    {
+      "epoch": 1.6383110835144366,
+      "grad_norm": 0.1513630747795105,
+      "learning_rate": 9.805367108121761e-06,
+      "loss": 0.1177,
+      "step": 660
+    },
+    {
+      "epoch": 1.6383110835144366,
+      "eval_loss": 0.11914250999689102,
+      "eval_runtime": 37.8427,
+      "eval_samples_per_second": 4.492,
+      "eval_steps_per_second": 4.492,
+      "step": 660
+    },
+    {
+      "epoch": 1.663148090655076,
+      "grad_norm": 0.3891820013523102,
+      "learning_rate": 8.554853440437805e-06,
+      "loss": 0.1297,
+      "step": 670
+    },
+    {
+      "epoch": 1.6879850977957156,
+      "grad_norm": 0.1408233791589737,
+      "learning_rate": 7.382148704900882e-06,
+      "loss": 0.1302,
+      "step": 680
+    },
+    {
+      "epoch": 1.7128221049363552,
+      "grad_norm": 0.15466411411762238,
+      "learning_rate": 6.289454532118444e-06,
+      "loss": 0.1288,
+      "step": 690
+    },
+    {
+      "epoch": 1.7128221049363552,
+      "eval_loss": 0.11917895078659058,
+      "eval_runtime": 37.8925,
+      "eval_samples_per_second": 4.486,
+      "eval_steps_per_second": 4.486,
+      "step": 690
+    },
+    {
+      "epoch": 1.7376591120769946,
+      "grad_norm": 0.09873683750629425,
+      "learning_rate": 5.278822341226519e-06,
+      "loss": 0.1296,
+      "step": 700
+    },
+    {
+      "epoch": 1.7624961192176343,
+      "grad_norm": 0.13227960467338562,
+      "learning_rate": 4.352149488564605e-06,
+      "loss": 0.1241,
+      "step": 710
+    },
+    {
+      "epoch": 1.787333126358274,
+      "grad_norm": 0.12939970195293427,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.1362,
+      "step": 720
+    },
+    {
+      "epoch": 1.787333126358274,
+      "eval_loss": 0.11892342567443848,
+      "eval_runtime": 37.9012,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 720
+    },
+    {
+      "epoch": 1.8121701334989133,
+      "grad_norm": 0.15326713025569916,
+      "learning_rate": 2.75747983270091e-06,
+      "loss": 0.1287,
+      "step": 730
+    },
+    {
+      "epoch": 1.837007140639553,
+      "grad_norm": 0.13985218107700348,
+      "learning_rate": 2.0924768551542463e-06,
+      "loss": 0.1298,
+      "step": 740
+    },
+    {
+      "epoch": 1.8618441477801926,
+      "grad_norm": 0.14625447988510132,
+      "learning_rate": 1.517415246552978e-06,
+      "loss": 0.1295,
+      "step": 750
+    },
+    {
+      "epoch": 1.8618441477801926,
+      "eval_loss": 0.11896809190511703,
+      "eval_runtime": 37.7631,
+      "eval_samples_per_second": 4.502,
+      "eval_steps_per_second": 4.502,
+      "step": 750
+    },
+    {
+      "epoch": 1.886681154920832,
+      "grad_norm": 0.134150892496109,
+      "learning_rate": 1.033374624980249e-06,
+      "loss": 0.1252,
+      "step": 760
+    },
+    {
+      "epoch": 1.9115181620614716,
+      "grad_norm": 0.1421349197626114,
+      "learning_rate": 6.412637261266396e-07,
+      "loss": 0.1224,
+      "step": 770
+    },
+    {
+      "epoch": 1.9363551692021113,
+      "grad_norm": 0.1370449662208557,
+      "learning_rate": 3.418186972338977e-07,
+      "loss": 0.1305,
+      "step": 780
+    },
+    {
+      "epoch": 1.9363551692021113,
+      "eval_loss": 0.11897934973239899,
+      "eval_runtime": 37.8217,
+      "eval_samples_per_second": 4.495,
+      "eval_steps_per_second": 4.495,
+      "step": 780
+    },
+    {
+      "epoch": 1.9611921763427507,
+      "grad_norm": 0.14134632050991058,
+      "learning_rate": 1.356017150553557e-07,
+      "loss": 0.1298,
+      "step": 790
+    },
+    {
+      "epoch": 1.9860291834833903,
+      "grad_norm": 0.13970708847045898,
+      "learning_rate": 2.299993042786941e-08,
+      "loss": 0.1286,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 806,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.2510107512463155e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-806/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e44568f8bf26e68c5a24546f6c205919eef34f726abef048aadaf2d067a5197
+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:e0506f557dc38686bfa3baf8014818086892a91b26e50a3aad8a714fa034b9ba
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8317e857c404b2b8a58b38de9513383d07590744db5aa227b385191ac5d19fe9
+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": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}