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-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1092/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": [
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_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:b772a2bd504d232db0aea7ea9ba6f7d0db437f902565b68171620406e9aaba69
+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-1000/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-1000/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": [
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b2e5657dcfb9ec586afd6266d6175b98a69dfb07cb5ac6b4baed1585498f514
+size 528550256

checkpoint-1000/added_tokens.json

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

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ae66f5be979b96d522ef865b7655fc83c04ba8846d545c9c2ab154186e42b7
+size 1057397963

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791e306163214f06c6b349951ec087c99f0dab0a96081fb6bf886a2d1885fbb2
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b770b95e299ac017f174e6b8dd039b0292dddb03c72f232373b0151d26d99642
+size 1465

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/tokenizer.json

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

checkpoint-1000/tokenizer_config.json

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

checkpoint-1000/trainer_state.json

@@ -0,0 +1,998 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8328365053886724,
+  "eval_steps": 30,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018344416418252695,
+      "grad_norm": 7.795040130615234,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 2.6173,
+      "step": 10
+    },
+    {
+      "epoch": 0.03668883283650539,
+      "grad_norm": 0.6880274415016174,
+      "learning_rate": 3.454545454545455e-05,
+      "loss": 0.9115,
+      "step": 20
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "grad_norm": 0.5830976963043213,
+      "learning_rate": 5.272727272727272e-05,
+      "loss": 0.5658,
+      "step": 30
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "eval_loss": 0.5072382092475891,
+      "eval_runtime": 49.4282,
+      "eval_samples_per_second": 4.653,
+      "eval_steps_per_second": 4.653,
+      "step": 30
+    },
+    {
+      "epoch": 0.07337766567301078,
+      "grad_norm": 0.6845789551734924,
+      "learning_rate": 7.090909090909092e-05,
+      "loss": 0.4196,
+      "step": 40
+    },
+    {
+      "epoch": 0.09172208209126347,
+      "grad_norm": 0.7662066221237183,
+      "learning_rate": 8.90909090909091e-05,
+      "loss": 0.3444,
+      "step": 50
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "grad_norm": 0.7642600536346436,
+      "learning_rate": 0.00010727272727272728,
+      "loss": 0.2597,
+      "step": 60
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "eval_loss": 0.25273433327674866,
+      "eval_runtime": 48.8989,
+      "eval_samples_per_second": 4.704,
+      "eval_steps_per_second": 4.704,
+      "step": 60
+    },
+    {
+      "epoch": 0.12841091492776885,
+      "grad_norm": 0.48377156257629395,
+      "learning_rate": 0.00012545454545454546,
+      "loss": 0.2275,
+      "step": 70
+    },
+    {
+      "epoch": 0.14675533134602156,
+      "grad_norm": 0.343270480632782,
+      "learning_rate": 0.00014363636363636363,
+      "loss": 0.227,
+      "step": 80
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "grad_norm": 0.4066845774650574,
+      "learning_rate": 0.00016181818181818184,
+      "loss": 0.1879,
+      "step": 90
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "eval_loss": 0.19945120811462402,
+      "eval_runtime": 48.8856,
+      "eval_samples_per_second": 4.705,
+      "eval_steps_per_second": 4.705,
+      "step": 90
+    },
+    {
+      "epoch": 0.18344416418252693,
+      "grad_norm": 0.31925588846206665,
+      "learning_rate": 0.00018,
+      "loss": 0.1751,
+      "step": 100
+    },
+    {
+      "epoch": 0.20178858060077964,
+      "grad_norm": 0.3936826288700104,
+      "learning_rate": 0.00019818181818181821,
+      "loss": 0.1742,
+      "step": 110
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "grad_norm": 0.3444064259529114,
+      "learning_rate": 0.00019995855217078221,
+      "loss": 0.1745,
+      "step": 120
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "eval_loss": 0.16547603905200958,
+      "eval_runtime": 49.0551,
+      "eval_samples_per_second": 4.689,
+      "eval_steps_per_second": 4.689,
+      "step": 120
+    },
+    {
+      "epoch": 0.238477413437285,
+      "grad_norm": 0.38167741894721985,
+      "learning_rate": 0.0001998153198346097,
+      "loss": 0.1758,
+      "step": 130
+    },
+    {
+      "epoch": 0.2568218298555377,
+      "grad_norm": 0.38544419407844543,
+      "learning_rate": 0.00019956993783702592,
+      "loss": 0.1559,
+      "step": 140
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "grad_norm": 0.19193893671035767,
+      "learning_rate": 0.00019922265729868066,
+      "loss": 0.1596,
+      "step": 150
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "eval_loss": 0.14603756368160248,
+      "eval_runtime": 48.8719,
+      "eval_samples_per_second": 4.706,
+      "eval_steps_per_second": 4.706,
+      "step": 150
+    },
+    {
+      "epoch": 0.2935106626920431,
+      "grad_norm": 0.2377977967262268,
+      "learning_rate": 0.0001987738336218254,
+      "loss": 0.1529,
+      "step": 160
+    },
+    {
+      "epoch": 0.3118550791102958,
+      "grad_norm": 0.24111273884773254,
+      "learning_rate": 0.00019822392612659965,
+      "loss": 0.1422,
+      "step": 170
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "grad_norm": 0.2043677717447281,
+      "learning_rate": 0.00019757349758096855,
+      "loss": 0.1466,
+      "step": 180
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "eval_loss": 0.14219357073307037,
+      "eval_runtime": 48.9834,
+      "eval_samples_per_second": 4.695,
+      "eval_steps_per_second": 4.695,
+      "step": 180
+    },
+    {
+      "epoch": 0.3485439119468012,
+      "grad_norm": 0.14538665115833282,
+      "learning_rate": 0.00019682321362479407,
+      "loss": 0.1431,
+      "step": 190
+    },
+    {
+      "epoch": 0.36688832836505386,
+      "grad_norm": 0.16464489698410034,
+      "learning_rate": 0.00019597384208862778,
+      "loss": 0.1462,
+      "step": 200
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 0.1624147742986679,
+      "learning_rate": 0.00019502625220792346,
+      "loss": 0.1405,
+      "step": 210
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "eval_loss": 0.1425054669380188,
+      "eval_runtime": 48.8411,
+      "eval_samples_per_second": 4.709,
+      "eval_steps_per_second": 4.709,
+      "step": 210
+    },
+    {
+      "epoch": 0.4035771612015593,
+      "grad_norm": 0.32471776008605957,
+      "learning_rate": 0.00019398141373347318,
+      "loss": 0.1367,
+      "step": 220
+    },
+    {
+      "epoch": 0.42192157761981197,
+      "grad_norm": 0.1439230591058731,
+      "learning_rate": 0.00019284039593897733,
+      "loss": 0.1378,
+      "step": 230
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "grad_norm": 0.2199280858039856,
+      "learning_rate": 0.00019160436652676427,
+      "loss": 0.1471,
+      "step": 240
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "eval_loss": 0.1684170663356781,
+      "eval_runtime": 48.9029,
+      "eval_samples_per_second": 4.703,
+      "eval_steps_per_second": 4.703,
+      "step": 240
+    },
+    {
+      "epoch": 0.45861041045631734,
+      "grad_norm": 0.46398675441741943,
+      "learning_rate": 0.0001902745904327792,
+      "loss": 0.1367,
+      "step": 250
+    },
+    {
+      "epoch": 0.47695482687457,
+      "grad_norm": 0.45815974473953247,
+      "learning_rate": 0.00018885242853206605,
+      "loss": 0.1346,
+      "step": 260
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "grad_norm": 0.29094287753105164,
+      "learning_rate": 0.00018733933624606576,
+      "loss": 0.1443,
+      "step": 270
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "eval_loss": 0.1330244541168213,
+      "eval_runtime": 48.9904,
+      "eval_samples_per_second": 4.695,
+      "eval_steps_per_second": 4.695,
+      "step": 270
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 0.22784261405467987,
+      "learning_rate": 0.0001857368620531578,
+      "loss": 0.1403,
+      "step": 280
+    },
+    {
+      "epoch": 0.5319880761293282,
+      "grad_norm": 0.16252748668193817,
+      "learning_rate": 0.00018404664590396794,
+      "loss": 0.1375,
+      "step": 290
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "grad_norm": 0.296027809381485,
+      "learning_rate": 0.00018227041754306485,
+      "loss": 0.1429,
+      "step": 300
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "eval_loss": 0.1296931356191635,
+      "eval_runtime": 49.3388,
+      "eval_samples_per_second": 4.662,
+      "eval_steps_per_second": 4.662,
+      "step": 300
+    },
+    {
+      "epoch": 0.5686769089658336,
+      "grad_norm": 0.16931048035621643,
+      "learning_rate": 0.00018040999473876258,
+      "loss": 0.132,
+      "step": 310
+    },
+    {
+      "epoch": 0.5870213253840862,
+      "grad_norm": 0.15758486092090607,
+      "learning_rate": 0.0001784672814228409,
+      "loss": 0.1439,
+      "step": 320
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "grad_norm": 0.2505033016204834,
+      "learning_rate": 0.00017644426574208697,
+      "loss": 0.1313,
+      "step": 330
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "eval_loss": 0.1264232099056244,
+      "eval_runtime": 49.2647,
+      "eval_samples_per_second": 4.669,
+      "eval_steps_per_second": 4.669,
+      "step": 330
+    },
+    {
+      "epoch": 0.6237101582205916,
+      "grad_norm": 0.15784454345703125,
+      "learning_rate": 0.00017434301802365265,
+      "loss": 0.1359,
+      "step": 340
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 0.1714029461145401,
+      "learning_rate": 0.00017216568865630923,
+      "loss": 0.1394,
+      "step": 350
+    },
+    {
+      "epoch": 0.660398991057097,
+      "grad_norm": 0.1297195553779602,
+      "learning_rate": 0.0001699145058897685,
+      "loss": 0.1297,
+      "step": 360
+    },
+    {
+      "epoch": 0.660398991057097,
+      "eval_loss": 0.122822105884552,
+      "eval_runtime": 49.3023,
+      "eval_samples_per_second": 4.665,
+      "eval_steps_per_second": 4.665,
+      "step": 360
+    },
+    {
+      "epoch": 0.6787434074753497,
+      "grad_norm": 0.10573259741067886,
+      "learning_rate": 0.00016759177355432186,
+      "loss": 0.1253,
+      "step": 370
+    },
+    {
+      "epoch": 0.6970878238936024,
+      "grad_norm": 0.11619006097316742,
+      "learning_rate": 0.00016519986870313117,
+      "loss": 0.1361,
+      "step": 380
+    },
+    {
+      "epoch": 0.715432240311855,
+      "grad_norm": 0.11721345037221909,
+      "learning_rate": 0.00016274123917958436,
+      "loss": 0.123,
+      "step": 390
+    },
+    {
+      "epoch": 0.715432240311855,
+      "eval_loss": 0.12079351395368576,
+      "eval_runtime": 49.4755,
+      "eval_samples_per_second": 4.649,
+      "eval_steps_per_second": 4.649,
+      "step": 390
+    },
+    {
+      "epoch": 0.7337766567301077,
+      "grad_norm": 0.10461968928575516,
+      "learning_rate": 0.00016021840111220547,
+      "loss": 0.1186,
+      "step": 400
+    },
+    {
+      "epoch": 0.7521210731483605,
+      "grad_norm": 0.11793247610330582,
+      "learning_rate": 0.0001576339363396822,
+      "loss": 0.1326,
+      "step": 410
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "grad_norm": 0.09142949432134628,
+      "learning_rate": 0.00015499048976864698,
+      "loss": 0.1338,
+      "step": 420
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "eval_loss": 0.11926981061697006,
+      "eval_runtime": 49.3242,
+      "eval_samples_per_second": 4.663,
+      "eval_steps_per_second": 4.663,
+      "step": 420
+    },
+    {
+      "epoch": 0.7888099059848659,
+      "grad_norm": 0.12111407518386841,
+      "learning_rate": 0.0001522907666669147,
+      "loss": 0.1296,
+      "step": 430
+    },
+    {
+      "epoch": 0.8071543224031186,
+      "grad_norm": 0.1540282666683197,
+      "learning_rate": 0.00014953752989494814,
+      "loss": 0.1371,
+      "step": 440
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "grad_norm": 0.10127419233322144,
+      "learning_rate": 0.00014673359707838336,
+      "loss": 0.1263,
+      "step": 450
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "eval_loss": 0.11757560074329376,
+      "eval_runtime": 49.3842,
+      "eval_samples_per_second": 4.657,
+      "eval_steps_per_second": 4.657,
+      "step": 450
+    },
+    {
+      "epoch": 0.8438431552396239,
+      "grad_norm": 0.10976914316415787,
+      "learning_rate": 0.00014388183772450955,
+      "loss": 0.1268,
+      "step": 460
+    },
+    {
+      "epoch": 0.8621875716578766,
+      "grad_norm": 0.08922591060400009,
+      "learning_rate": 0.0001409851702856535,
+      "loss": 0.1252,
+      "step": 470
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "grad_norm": 0.09157353639602661,
+      "learning_rate": 0.00013804655917247472,
+      "loss": 0.1341,
+      "step": 480
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "eval_loss": 0.11754835397005081,
+      "eval_runtime": 49.3415,
+      "eval_samples_per_second": 4.661,
+      "eval_steps_per_second": 4.661,
+      "step": 480
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.2666095793247223,
+      "learning_rate": 0.00013506901172022722,
+      "loss": 0.1235,
+      "step": 490
+    },
+    {
+      "epoch": 0.9172208209126347,
+      "grad_norm": 0.10213123261928558,
+      "learning_rate": 0.00013205557511109295,
+      "loss": 0.1221,
+      "step": 500
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "grad_norm": 0.11488551646471024,
+      "learning_rate": 0.00012900933325573637,
+      "loss": 0.129,
+      "step": 510
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "eval_loss": 0.11715804040431976,
+      "eval_runtime": 49.2999,
+      "eval_samples_per_second": 4.665,
+      "eval_steps_per_second": 4.665,
+      "step": 510
+    },
+    {
+      "epoch": 0.95390965374914,
+      "grad_norm": 0.12331929802894592,
+      "learning_rate": 0.00012593340363727131,
+      "loss": 0.1224,
+      "step": 520
+    },
+    {
+      "epoch": 0.9722540701673928,
+      "grad_norm": 0.11989827454090118,
+      "learning_rate": 0.000122830934120871,
+      "loss": 0.1269,
+      "step": 530
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "grad_norm": 0.08979545533657074,
+      "learning_rate": 0.00011970509973228458,
+      "loss": 0.1223,
+      "step": 540
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "eval_loss": 0.11745806038379669,
+      "eval_runtime": 49.2732,
+      "eval_samples_per_second": 4.668,
+      "eval_steps_per_second": 4.668,
+      "step": 540
+    },
+    {
+      "epoch": 1.0073377665673011,
+      "grad_norm": 0.10322548449039459,
+      "learning_rate": 0.00011655909940855851,
+      "loss": 0.111,
+      "step": 550
+    },
+    {
+      "epoch": 1.0256821829855538,
+      "grad_norm": 0.09024786949157715,
+      "learning_rate": 0.0001133961527242872,
+      "loss": 0.1142,
+      "step": 560
+    },
+    {
+      "epoch": 1.0440265994038065,
+      "grad_norm": 0.09547445923089981,
+      "learning_rate": 0.00011021949659674338,
+      "loss": 0.1322,
+      "step": 570
+    },
+    {
+      "epoch": 1.0440265994038065,
+      "eval_loss": 0.11743354052305222,
+      "eval_runtime": 49.2711,
+      "eval_samples_per_second": 4.668,
+      "eval_steps_per_second": 4.668,
+      "step": 570
+    },
+    {
+      "epoch": 1.0623710158220592,
+      "grad_norm": 0.08737261593341827,
+      "learning_rate": 0.00010703238197326042,
+      "loss": 0.1224,
+      "step": 580
+    },
+    {
+      "epoch": 1.0807154322403119,
+      "grad_norm": 0.08432964235544205,
+      "learning_rate": 0.00010383807050425646,
+      "loss": 0.12,
+      "step": 590
+    },
+    {
+      "epoch": 1.0990598486585645,
+      "grad_norm": 0.09570309519767761,
+      "learning_rate": 0.0001006398312053048,
+      "loss": 0.1142,
+      "step": 600
+    },
+    {
+      "epoch": 1.0990598486585645,
+      "eval_loss": 0.11705348640680313,
+      "eval_runtime": 49.3215,
+      "eval_samples_per_second": 4.663,
+      "eval_steps_per_second": 4.663,
+      "step": 600
+    },
+    {
+      "epoch": 1.1174042650768172,
+      "grad_norm": 0.10215649008750916,
+      "learning_rate": 9.744093711166744e-05,
+      "loss": 0.1256,
+      "step": 610
+    },
+    {
+      "epoch": 1.13574868149507,
+      "grad_norm": 0.09788327664136887,
+      "learning_rate": 9.42446619287144e-05,
+      "loss": 0.1285,
+      "step": 620
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "grad_norm": 0.07625731825828552,
+      "learning_rate": 9.105427668165755e-05,
+      "loss": 0.1188,
+      "step": 630
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "eval_loss": 0.11599662899971008,
+      "eval_runtime": 49.3627,
+      "eval_samples_per_second": 4.659,
+      "eval_steps_per_second": 4.659,
+      "step": 630
+    },
+    {
+      "epoch": 1.1724375143315753,
+      "grad_norm": 0.07791601866483688,
+      "learning_rate": 8.787304636802742e-05,
+      "loss": 0.1192,
+      "step": 640
+    },
+    {
+      "epoch": 1.190781930749828,
+      "grad_norm": 0.08331194519996643,
+      "learning_rate": 8.47042266163181e-05,
+      "loss": 0.1224,
+      "step": 650
+    },
+    {
+      "epoch": 1.2091263471680807,
+      "grad_norm": 0.1000560000538826,
+      "learning_rate": 8.155106035422095e-05,
+      "loss": 0.1187,
+      "step": 660
+    },
+    {
+      "epoch": 1.2091263471680807,
+      "eval_loss": 0.11565903574228287,
+      "eval_runtime": 49.4108,
+      "eval_samples_per_second": 4.655,
+      "eval_steps_per_second": 4.655,
+      "step": 660
+    },
+    {
+      "epoch": 1.2274707635863333,
+      "grad_norm": 0.09680289030075073,
+      "learning_rate": 7.841677448985571e-05,
+      "loss": 0.1203,
+      "step": 670
+    },
+    {
+      "epoch": 1.245815180004586,
+      "grad_norm": 0.0752745121717453,
+      "learning_rate": 7.530457660939587e-05,
+      "loss": 0.1208,
+      "step": 680
+    },
+    {
+      "epoch": 1.264159596422839,
+      "grad_norm": 0.5036187171936035,
+      "learning_rate": 7.22176516944682e-05,
+      "loss": 0.1179,
+      "step": 690
+    },
+    {
+      "epoch": 1.264159596422839,
+      "eval_loss": 0.11543552577495575,
+      "eval_runtime": 49.3311,
+      "eval_samples_per_second": 4.662,
+      "eval_steps_per_second": 4.662,
+      "step": 690
+    },
+    {
+      "epoch": 1.2825040128410916,
+      "grad_norm": 0.09510516375303268,
+      "learning_rate": 6.915915886268485e-05,
+      "loss": 0.1215,
+      "step": 700
+    },
+    {
+      "epoch": 1.3008484292593443,
+      "grad_norm": 0.08249227702617645,
+      "learning_rate": 6.613222813464508e-05,
+      "loss": 0.1192,
+      "step": 710
+    },
+    {
+      "epoch": 1.319192845677597,
+      "grad_norm": 0.0947667732834816,
+      "learning_rate": 6.313995723071377e-05,
+      "loss": 0.1248,
+      "step": 720
+    },
+    {
+      "epoch": 1.319192845677597,
+      "eval_loss": 0.11455719918012619,
+      "eval_runtime": 49.2423,
+      "eval_samples_per_second": 4.671,
+      "eval_steps_per_second": 4.671,
+      "step": 720
+    },
+    {
+      "epoch": 1.3375372620958497,
+      "grad_norm": 0.09012740105390549,
+      "learning_rate": 6.0185408400856116e-05,
+      "loss": 0.1152,
+      "step": 730
+    },
+    {
+      "epoch": 1.3558816785141024,
+      "grad_norm": 0.11220687627792358,
+      "learning_rate": 5.727160529077189e-05,
+      "loss": 0.1232,
+      "step": 740
+    },
+    {
+      "epoch": 1.374226094932355,
+      "grad_norm": 0.09022535383701324,
+      "learning_rate": 5.440152984753709e-05,
+      "loss": 0.1179,
+      "step": 750
+    },
+    {
+      "epoch": 1.374226094932355,
+      "eval_loss": 0.1143663227558136,
+      "eval_runtime": 49.3543,
+      "eval_samples_per_second": 4.66,
+      "eval_steps_per_second": 4.66,
+      "step": 750
+    },
+    {
+      "epoch": 1.3925705113506077,
+      "grad_norm": 0.08042389154434204,
+      "learning_rate": 5.157811926791905e-05,
+      "loss": 0.1219,
+      "step": 760
+    },
+    {
+      "epoch": 1.4109149277688604,
+      "grad_norm": 0.09887140244245529,
+      "learning_rate": 4.880426299248867e-05,
+      "loss": 0.1172,
+      "step": 770
+    },
+    {
+      "epoch": 1.429259344187113,
+      "grad_norm": 0.08288570493459702,
+      "learning_rate": 4.608279974860581e-05,
+      "loss": 0.1222,
+      "step": 780
+    },
+    {
+      "epoch": 1.429259344187113,
+      "eval_loss": 0.11446955054998398,
+      "eval_runtime": 49.3093,
+      "eval_samples_per_second": 4.664,
+      "eval_steps_per_second": 4.664,
+      "step": 780
+    },
+    {
+      "epoch": 1.4476037606053658,
+      "grad_norm": 0.08059478551149368,
+      "learning_rate": 4.341651464530341e-05,
+      "loss": 0.1236,
+      "step": 790
+    },
+    {
+      "epoch": 1.4659481770236185,
+      "grad_norm": 0.08869417011737823,
+      "learning_rate": 4.0808136323044554e-05,
+      "loss": 0.1209,
+      "step": 800
+    },
+    {
+      "epoch": 1.4842925934418711,
+      "grad_norm": 0.09369216859340668,
+      "learning_rate": 3.8260334161268077e-05,
+      "loss": 0.1228,
+      "step": 810
+    },
+    {
+      "epoch": 1.4842925934418711,
+      "eval_loss": 0.11371872574090958,
+      "eval_runtime": 49.2681,
+      "eval_samples_per_second": 4.668,
+      "eval_steps_per_second": 4.668,
+      "step": 810
+    },
+    {
+      "epoch": 1.5026370098601238,
+      "grad_norm": 0.07937419414520264,
+      "learning_rate": 3.577571554658154e-05,
+      "loss": 0.1144,
+      "step": 820
+    },
+    {
+      "epoch": 1.5209814262783765,
+      "grad_norm": 0.09610588103532791,
+      "learning_rate": 3.33568232043967e-05,
+      "loss": 0.1158,
+      "step": 830
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 0.1910742223262787,
+      "learning_rate": 3.100613259673843e-05,
+      "loss": 0.1261,
+      "step": 840
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "eval_loss": 0.11366112530231476,
+      "eval_runtime": 49.3771,
+      "eval_samples_per_second": 4.658,
+      "eval_steps_per_second": 4.658,
+      "step": 840
+    },
+    {
+      "epoch": 1.5576702591148819,
+      "grad_norm": 0.07669960707426071,
+      "learning_rate": 2.8726049388889807e-05,
+      "loss": 0.1165,
+      "step": 850
+    },
+    {
+      "epoch": 1.5760146755331346,
+      "grad_norm": 0.08569029718637466,
+      "learning_rate": 2.651890698746682e-05,
+      "loss": 0.1192,
+      "step": 860
+    },
+    {
+      "epoch": 1.5943590919513873,
+      "grad_norm": 0.09321046620607376,
+      "learning_rate": 2.4386964152441018e-05,
+      "loss": 0.1237,
+      "step": 870
+    },
+    {
+      "epoch": 1.5943590919513873,
+      "eval_loss": 0.11372239142656326,
+      "eval_runtime": 49.3141,
+      "eval_samples_per_second": 4.664,
+      "eval_steps_per_second": 4.664,
+      "step": 870
+    },
+    {
+      "epoch": 1.61270350836964,
+      "grad_norm": 0.08224959671497345,
+      "learning_rate": 2.2332402685554876e-05,
+      "loss": 0.1149,
+      "step": 880
+    },
+    {
+      "epoch": 1.6310479247878926,
+      "grad_norm": 0.07479019463062286,
+      "learning_rate": 2.035732519749528e-05,
+      "loss": 0.1237,
+      "step": 890
+    },
+    {
+      "epoch": 1.6493923412061453,
+      "grad_norm": 0.0903916209936142,
+      "learning_rate": 1.8463752956109615e-05,
+      "loss": 0.1167,
+      "step": 900
+    },
+    {
+      "epoch": 1.6493923412061453,
+      "eval_loss": 0.1136728897690773,
+      "eval_runtime": 49.4665,
+      "eval_samples_per_second": 4.65,
+      "eval_steps_per_second": 4.65,
+      "step": 900
+    },
+    {
+      "epoch": 1.667736757624398,
+      "grad_norm": 0.08336473256349564,
+      "learning_rate": 1.6653623817867637e-05,
+      "loss": 0.1171,
+      "step": 910
+    },
+    {
+      "epoch": 1.6860811740426507,
+      "grad_norm": 0.08168327063322067,
+      "learning_rate": 1.4928790244684865e-05,
+      "loss": 0.1189,
+      "step": 920
+    },
+    {
+      "epoch": 1.7044255904609034,
+      "grad_norm": 0.08606237918138504,
+      "learning_rate": 1.3291017408138006e-05,
+      "loss": 0.1184,
+      "step": 930
+    },
+    {
+      "epoch": 1.7044255904609034,
+      "eval_loss": 0.11324052512645721,
+      "eval_runtime": 49.4226,
+      "eval_samples_per_second": 4.654,
+      "eval_steps_per_second": 4.654,
+      "step": 930
+    },
+    {
+      "epoch": 1.722770006879156,
+      "grad_norm": 0.09091446548700333,
+      "learning_rate": 1.1741981383011924e-05,
+      "loss": 0.1184,
+      "step": 940
+    },
+    {
+      "epoch": 1.7411144232974087,
+      "grad_norm": 0.0911412388086319,
+      "learning_rate": 1.02832674320273e-05,
+      "loss": 0.1156,
+      "step": 950
+    },
+    {
+      "epoch": 1.7594588397156614,
+      "grad_norm": 0.11093633621931076,
+      "learning_rate": 8.916368383503781e-06,
+      "loss": 0.1231,
+      "step": 960
+    },
+    {
+      "epoch": 1.7594588397156614,
+      "eval_loss": 0.11301500350236893,
+      "eval_runtime": 49.4575,
+      "eval_samples_per_second": 4.65,
+      "eval_steps_per_second": 4.65,
+      "step": 960
+    },
+    {
+      "epoch": 1.777803256133914,
+      "grad_norm": 0.08233562856912613,
+      "learning_rate": 7.642683103619686e-06,
+      "loss": 0.1193,
+      "step": 970
+    },
+    {
+      "epoch": 1.7961476725521668,
+      "grad_norm": 0.08492106199264526,
+      "learning_rate": 6.463515064830916e-06,
+      "loss": 0.1113,
+      "step": 980
+    },
+    {
+      "epoch": 1.8144920889704195,
+      "grad_norm": 0.07636568695306778,
+      "learning_rate": 5.380071011914822e-06,
+      "loss": 0.1229,
+      "step": 990
+    },
+    {
+      "epoch": 1.8144920889704195,
+      "eval_loss": 0.11294619739055634,
+      "eval_runtime": 49.6347,
+      "eval_samples_per_second": 4.634,
+      "eval_steps_per_second": 4.634,
+      "step": 990
+    },
+    {
+      "epoch": 1.8328365053886724,
+      "grad_norm": 0.08528682589530945,
+      "learning_rate": 4.393459727003701e-06,
+      "loss": 0.1297,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1092,
+  "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": 1.4621136161220403e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1f0a10aa743528b337db958330beda85917a812f1f8076421cfa4df3e349ce
+size 5777

checkpoint-1092/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-1092/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": [
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1092/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b772a2bd504d232db0aea7ea9ba6f7d0db437f902565b68171620406e9aaba69
+size 528550256

checkpoint-1092/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-1092/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-1092/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a7e4be76ed02338d4e6f965caeb2be97e41425897e3a401aac2c7658409130
+size 1057397963

checkpoint-1092/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e0a0d52c71392fce8a63c936d62ac4f79dedd652f26b664aee06482c890b8c
+size 14645

checkpoint-1092/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d107ce8f6e1ce627765bea2c6df3fcd56e201855cf4544120f89df109ed6fc
+size 1465

checkpoint-1092/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-1092/tokenizer.json

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

checkpoint-1092/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-1092/trainer_state.json

@@ -0,0 +1,1085 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 30,
+  "global_step": 1092,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018344416418252695,
+      "grad_norm": 7.795040130615234,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 2.6173,
+      "step": 10
+    },
+    {
+      "epoch": 0.03668883283650539,
+      "grad_norm": 0.6880274415016174,
+      "learning_rate": 3.454545454545455e-05,
+      "loss": 0.9115,
+      "step": 20
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "grad_norm": 0.5830976963043213,
+      "learning_rate": 5.272727272727272e-05,
+      "loss": 0.5658,
+      "step": 30
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "eval_loss": 0.5072382092475891,
+      "eval_runtime": 49.4282,
+      "eval_samples_per_second": 4.653,
+      "eval_steps_per_second": 4.653,
+      "step": 30
+    },
+    {
+      "epoch": 0.07337766567301078,
+      "grad_norm": 0.6845789551734924,
+      "learning_rate": 7.090909090909092e-05,
+      "loss": 0.4196,
+      "step": 40
+    },
+    {
+      "epoch": 0.09172208209126347,
+      "grad_norm": 0.7662066221237183,
+      "learning_rate": 8.90909090909091e-05,
+      "loss": 0.3444,
+      "step": 50
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "grad_norm": 0.7642600536346436,
+      "learning_rate": 0.00010727272727272728,
+      "loss": 0.2597,
+      "step": 60
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "eval_loss": 0.25273433327674866,
+      "eval_runtime": 48.8989,
+      "eval_samples_per_second": 4.704,
+      "eval_steps_per_second": 4.704,
+      "step": 60
+    },
+    {
+      "epoch": 0.12841091492776885,
+      "grad_norm": 0.48377156257629395,
+      "learning_rate": 0.00012545454545454546,
+      "loss": 0.2275,
+      "step": 70
+    },
+    {
+      "epoch": 0.14675533134602156,
+      "grad_norm": 0.343270480632782,
+      "learning_rate": 0.00014363636363636363,
+      "loss": 0.227,
+      "step": 80
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "grad_norm": 0.4066845774650574,
+      "learning_rate": 0.00016181818181818184,
+      "loss": 0.1879,
+      "step": 90
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "eval_loss": 0.19945120811462402,
+      "eval_runtime": 48.8856,
+      "eval_samples_per_second": 4.705,
+      "eval_steps_per_second": 4.705,
+      "step": 90
+    },
+    {
+      "epoch": 0.18344416418252693,
+      "grad_norm": 0.31925588846206665,
+      "learning_rate": 0.00018,
+      "loss": 0.1751,
+      "step": 100
+    },
+    {
+      "epoch": 0.20178858060077964,
+      "grad_norm": 0.3936826288700104,
+      "learning_rate": 0.00019818181818181821,
+      "loss": 0.1742,
+      "step": 110
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "grad_norm": 0.3444064259529114,
+      "learning_rate": 0.00019995855217078221,
+      "loss": 0.1745,
+      "step": 120
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "eval_loss": 0.16547603905200958,
+      "eval_runtime": 49.0551,
+      "eval_samples_per_second": 4.689,
+      "eval_steps_per_second": 4.689,
+      "step": 120
+    },
+    {
+      "epoch": 0.238477413437285,
+      "grad_norm": 0.38167741894721985,
+      "learning_rate": 0.0001998153198346097,
+      "loss": 0.1758,
+      "step": 130
+    },
+    {
+      "epoch": 0.2568218298555377,
+      "grad_norm": 0.38544419407844543,
+      "learning_rate": 0.00019956993783702592,
+      "loss": 0.1559,
+      "step": 140
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "grad_norm": 0.19193893671035767,
+      "learning_rate": 0.00019922265729868066,
+      "loss": 0.1596,
+      "step": 150
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "eval_loss": 0.14603756368160248,
+      "eval_runtime": 48.8719,
+      "eval_samples_per_second": 4.706,
+      "eval_steps_per_second": 4.706,
+      "step": 150
+    },
+    {
+      "epoch": 0.2935106626920431,
+      "grad_norm": 0.2377977967262268,
+      "learning_rate": 0.0001987738336218254,
+      "loss": 0.1529,
+      "step": 160
+    },
+    {
+      "epoch": 0.3118550791102958,
+      "grad_norm": 0.24111273884773254,
+      "learning_rate": 0.00019822392612659965,
+      "loss": 0.1422,
+      "step": 170
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "grad_norm": 0.2043677717447281,
+      "learning_rate": 0.00019757349758096855,
+      "loss": 0.1466,
+      "step": 180
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "eval_loss": 0.14219357073307037,
+      "eval_runtime": 48.9834,
+      "eval_samples_per_second": 4.695,
+      "eval_steps_per_second": 4.695,
+      "step": 180
+    },
+    {
+      "epoch": 0.3485439119468012,
+      "grad_norm": 0.14538665115833282,
+      "learning_rate": 0.00019682321362479407,
+      "loss": 0.1431,
+      "step": 190
+    },
+    {
+      "epoch": 0.36688832836505386,
+      "grad_norm": 0.16464489698410034,
+      "learning_rate": 0.00019597384208862778,
+      "loss": 0.1462,
+      "step": 200
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 0.1624147742986679,
+      "learning_rate": 0.00019502625220792346,
+      "loss": 0.1405,
+      "step": 210
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "eval_loss": 0.1425054669380188,
+      "eval_runtime": 48.8411,
+      "eval_samples_per_second": 4.709,
+      "eval_steps_per_second": 4.709,
+      "step": 210
+    },
+    {
+      "epoch": 0.4035771612015593,
+      "grad_norm": 0.32471776008605957,
+      "learning_rate": 0.00019398141373347318,
+      "loss": 0.1367,
+      "step": 220
+    },
+    {
+      "epoch": 0.42192157761981197,
+      "grad_norm": 0.1439230591058731,
+      "learning_rate": 0.00019284039593897733,
+      "loss": 0.1378,
+      "step": 230
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "grad_norm": 0.2199280858039856,
+      "learning_rate": 0.00019160436652676427,
+      "loss": 0.1471,
+      "step": 240
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "eval_loss": 0.1684170663356781,
+      "eval_runtime": 48.9029,
+      "eval_samples_per_second": 4.703,
+      "eval_steps_per_second": 4.703,
+      "step": 240
+    },
+    {
+      "epoch": 0.45861041045631734,
+      "grad_norm": 0.46398675441741943,
+      "learning_rate": 0.0001902745904327792,
+      "loss": 0.1367,
+      "step": 250
+    },
+    {
+      "epoch": 0.47695482687457,
+      "grad_norm": 0.45815974473953247,
+      "learning_rate": 0.00018885242853206605,
+      "loss": 0.1346,
+      "step": 260
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "grad_norm": 0.29094287753105164,
+      "learning_rate": 0.00018733933624606576,
+      "loss": 0.1443,
+      "step": 270
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "eval_loss": 0.1330244541168213,
+      "eval_runtime": 48.9904,
+      "eval_samples_per_second": 4.695,
+      "eval_steps_per_second": 4.695,
+      "step": 270
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 0.22784261405467987,
+      "learning_rate": 0.0001857368620531578,
+      "loss": 0.1403,
+      "step": 280
+    },
+    {
+      "epoch": 0.5319880761293282,
+      "grad_norm": 0.16252748668193817,
+      "learning_rate": 0.00018404664590396794,
+      "loss": 0.1375,
+      "step": 290
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "grad_norm": 0.296027809381485,
+      "learning_rate": 0.00018227041754306485,
+      "loss": 0.1429,
+      "step": 300
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "eval_loss": 0.1296931356191635,
+      "eval_runtime": 49.3388,
+      "eval_samples_per_second": 4.662,
+      "eval_steps_per_second": 4.662,
+      "step": 300
+    },
+    {
+      "epoch": 0.5686769089658336,
+      "grad_norm": 0.16931048035621643,
+      "learning_rate": 0.00018040999473876258,
+      "loss": 0.132,
+      "step": 310
+    },
+    {
+      "epoch": 0.5870213253840862,
+      "grad_norm": 0.15758486092090607,
+      "learning_rate": 0.0001784672814228409,
+      "loss": 0.1439,
+      "step": 320
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "grad_norm": 0.2505033016204834,
+      "learning_rate": 0.00017644426574208697,
+      "loss": 0.1313,
+      "step": 330
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "eval_loss": 0.1264232099056244,
+      "eval_runtime": 49.2647,
+      "eval_samples_per_second": 4.669,
+      "eval_steps_per_second": 4.669,
+      "step": 330
+    },
+    {
+      "epoch": 0.6237101582205916,
+      "grad_norm": 0.15784454345703125,
+      "learning_rate": 0.00017434301802365265,
+      "loss": 0.1359,
+      "step": 340
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 0.1714029461145401,
+      "learning_rate": 0.00017216568865630923,
+      "loss": 0.1394,
+      "step": 350
+    },
+    {
+      "epoch": 0.660398991057097,
+      "grad_norm": 0.1297195553779602,
+      "learning_rate": 0.0001699145058897685,
+      "loss": 0.1297,
+      "step": 360
+    },
+    {
+      "epoch": 0.660398991057097,
+      "eval_loss": 0.122822105884552,
+      "eval_runtime": 49.3023,
+      "eval_samples_per_second": 4.665,
+      "eval_steps_per_second": 4.665,
+      "step": 360
+    },
+    {
+      "epoch": 0.6787434074753497,
+      "grad_norm": 0.10573259741067886,
+      "learning_rate": 0.00016759177355432186,
+      "loss": 0.1253,
+      "step": 370
+    },
+    {
+      "epoch": 0.6970878238936024,
+      "grad_norm": 0.11619006097316742,
+      "learning_rate": 0.00016519986870313117,
+      "loss": 0.1361,
+      "step": 380
+    },
+    {
+      "epoch": 0.715432240311855,
+      "grad_norm": 0.11721345037221909,
+      "learning_rate": 0.00016274123917958436,
+      "loss": 0.123,
+      "step": 390
+    },
+    {
+      "epoch": 0.715432240311855,
+      "eval_loss": 0.12079351395368576,
+      "eval_runtime": 49.4755,
+      "eval_samples_per_second": 4.649,
+      "eval_steps_per_second": 4.649,
+      "step": 390
+    },
+    {
+      "epoch": 0.7337766567301077,
+      "grad_norm": 0.10461968928575516,
+      "learning_rate": 0.00016021840111220547,
+      "loss": 0.1186,
+      "step": 400
+    },
+    {
+      "epoch": 0.7521210731483605,
+      "grad_norm": 0.11793247610330582,
+      "learning_rate": 0.0001576339363396822,
+      "loss": 0.1326,
+      "step": 410
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "grad_norm": 0.09142949432134628,
+      "learning_rate": 0.00015499048976864698,
+      "loss": 0.1338,
+      "step": 420
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "eval_loss": 0.11926981061697006,
+      "eval_runtime": 49.3242,
+      "eval_samples_per_second": 4.663,
+      "eval_steps_per_second": 4.663,
+      "step": 420
+    },
+    {
+      "epoch": 0.7888099059848659,
+      "grad_norm": 0.12111407518386841,
+      "learning_rate": 0.0001522907666669147,
+      "loss": 0.1296,
+      "step": 430
+    },
+    {
+      "epoch": 0.8071543224031186,
+      "grad_norm": 0.1540282666683197,
+      "learning_rate": 0.00014953752989494814,
+      "loss": 0.1371,
+      "step": 440
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "grad_norm": 0.10127419233322144,
+      "learning_rate": 0.00014673359707838336,
+      "loss": 0.1263,
+      "step": 450
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "eval_loss": 0.11757560074329376,
+      "eval_runtime": 49.3842,
+      "eval_samples_per_second": 4.657,
+      "eval_steps_per_second": 4.657,
+      "step": 450
+    },
+    {
+      "epoch": 0.8438431552396239,
+      "grad_norm": 0.10976914316415787,
+      "learning_rate": 0.00014388183772450955,
+      "loss": 0.1268,
+      "step": 460
+    },
+    {
+      "epoch": 0.8621875716578766,
+      "grad_norm": 0.08922591060400009,
+      "learning_rate": 0.0001409851702856535,
+      "loss": 0.1252,
+      "step": 470
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "grad_norm": 0.09157353639602661,
+      "learning_rate": 0.00013804655917247472,
+      "loss": 0.1341,
+      "step": 480
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "eval_loss": 0.11754835397005081,
+      "eval_runtime": 49.3415,
+      "eval_samples_per_second": 4.661,
+      "eval_steps_per_second": 4.661,
+      "step": 480
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.2666095793247223,
+      "learning_rate": 0.00013506901172022722,
+      "loss": 0.1235,
+      "step": 490
+    },
+    {
+      "epoch": 0.9172208209126347,
+      "grad_norm": 0.10213123261928558,
+      "learning_rate": 0.00013205557511109295,
+      "loss": 0.1221,
+      "step": 500
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "grad_norm": 0.11488551646471024,
+      "learning_rate": 0.00012900933325573637,
+      "loss": 0.129,
+      "step": 510
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "eval_loss": 0.11715804040431976,
+      "eval_runtime": 49.2999,
+      "eval_samples_per_second": 4.665,
+      "eval_steps_per_second": 4.665,
+      "step": 510
+    },
+    {
+      "epoch": 0.95390965374914,
+      "grad_norm": 0.12331929802894592,
+      "learning_rate": 0.00012593340363727131,
+      "loss": 0.1224,
+      "step": 520
+    },
+    {
+      "epoch": 0.9722540701673928,
+      "grad_norm": 0.11989827454090118,
+      "learning_rate": 0.000122830934120871,
+      "loss": 0.1269,
+      "step": 530
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "grad_norm": 0.08979545533657074,
+      "learning_rate": 0.00011970509973228458,
+      "loss": 0.1223,
+      "step": 540
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "eval_loss": 0.11745806038379669,
+      "eval_runtime": 49.2732,
+      "eval_samples_per_second": 4.668,
+      "eval_steps_per_second": 4.668,
+      "step": 540
+    },
+    {
+      "epoch": 1.0073377665673011,
+      "grad_norm": 0.10322548449039459,
+      "learning_rate": 0.00011655909940855851,
+      "loss": 0.111,
+      "step": 550
+    },
+    {
+      "epoch": 1.0256821829855538,
+      "grad_norm": 0.09024786949157715,
+      "learning_rate": 0.0001133961527242872,
+      "loss": 0.1142,
+      "step": 560
+    },
+    {
+      "epoch": 1.0440265994038065,
+      "grad_norm": 0.09547445923089981,
+      "learning_rate": 0.00011021949659674338,
+      "loss": 0.1322,
+      "step": 570
+    },
+    {
+      "epoch": 1.0440265994038065,
+      "eval_loss": 0.11743354052305222,
+      "eval_runtime": 49.2711,
+      "eval_samples_per_second": 4.668,
+      "eval_steps_per_second": 4.668,
+      "step": 570
+    },
+    {
+      "epoch": 1.0623710158220592,
+      "grad_norm": 0.08737261593341827,
+      "learning_rate": 0.00010703238197326042,
+      "loss": 0.1224,
+      "step": 580
+    },
+    {
+      "epoch": 1.0807154322403119,
+      "grad_norm": 0.08432964235544205,
+      "learning_rate": 0.00010383807050425646,
+      "loss": 0.12,
+      "step": 590
+    },
+    {
+      "epoch": 1.0990598486585645,
+      "grad_norm": 0.09570309519767761,
+      "learning_rate": 0.0001006398312053048,
+      "loss": 0.1142,
+      "step": 600
+    },
+    {
+      "epoch": 1.0990598486585645,
+      "eval_loss": 0.11705348640680313,
+      "eval_runtime": 49.3215,
+      "eval_samples_per_second": 4.663,
+      "eval_steps_per_second": 4.663,
+      "step": 600
+    },
+    {
+      "epoch": 1.1174042650768172,
+      "grad_norm": 0.10215649008750916,
+      "learning_rate": 9.744093711166744e-05,
+      "loss": 0.1256,
+      "step": 610
+    },
+    {
+      "epoch": 1.13574868149507,
+      "grad_norm": 0.09788327664136887,
+      "learning_rate": 9.42446619287144e-05,
+      "loss": 0.1285,
+      "step": 620
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "grad_norm": 0.07625731825828552,
+      "learning_rate": 9.105427668165755e-05,
+      "loss": 0.1188,
+      "step": 630
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "eval_loss": 0.11599662899971008,
+      "eval_runtime": 49.3627,
+      "eval_samples_per_second": 4.659,
+      "eval_steps_per_second": 4.659,
+      "step": 630
+    },
+    {
+      "epoch": 1.1724375143315753,
+      "grad_norm": 0.07791601866483688,
+      "learning_rate": 8.787304636802742e-05,
+      "loss": 0.1192,
+      "step": 640
+    },
+    {
+      "epoch": 1.190781930749828,
+      "grad_norm": 0.08331194519996643,
+      "learning_rate": 8.47042266163181e-05,
+      "loss": 0.1224,
+      "step": 650
+    },
+    {
+      "epoch": 1.2091263471680807,
+      "grad_norm": 0.1000560000538826,
+      "learning_rate": 8.155106035422095e-05,
+      "loss": 0.1187,
+      "step": 660
+    },
+    {
+      "epoch": 1.2091263471680807,
+      "eval_loss": 0.11565903574228287,
+      "eval_runtime": 49.4108,
+      "eval_samples_per_second": 4.655,
+      "eval_steps_per_second": 4.655,
+      "step": 660
+    },
+    {
+      "epoch": 1.2274707635863333,
+      "grad_norm": 0.09680289030075073,
+      "learning_rate": 7.841677448985571e-05,
+      "loss": 0.1203,
+      "step": 670
+    },
+    {
+      "epoch": 1.245815180004586,
+      "grad_norm": 0.0752745121717453,
+      "learning_rate": 7.530457660939587e-05,
+      "loss": 0.1208,
+      "step": 680
+    },
+    {
+      "epoch": 1.264159596422839,
+      "grad_norm": 0.5036187171936035,
+      "learning_rate": 7.22176516944682e-05,
+      "loss": 0.1179,
+      "step": 690
+    },
+    {
+      "epoch": 1.264159596422839,
+      "eval_loss": 0.11543552577495575,
+      "eval_runtime": 49.3311,
+      "eval_samples_per_second": 4.662,
+      "eval_steps_per_second": 4.662,
+      "step": 690
+    },
+    {
+      "epoch": 1.2825040128410916,
+      "grad_norm": 0.09510516375303268,
+      "learning_rate": 6.915915886268485e-05,
+      "loss": 0.1215,
+      "step": 700
+    },
+    {
+      "epoch": 1.3008484292593443,
+      "grad_norm": 0.08249227702617645,
+      "learning_rate": 6.613222813464508e-05,
+      "loss": 0.1192,
+      "step": 710
+    },
+    {
+      "epoch": 1.319192845677597,
+      "grad_norm": 0.0947667732834816,
+      "learning_rate": 6.313995723071377e-05,
+      "loss": 0.1248,
+      "step": 720
+    },
+    {
+      "epoch": 1.319192845677597,
+      "eval_loss": 0.11455719918012619,
+      "eval_runtime": 49.2423,
+      "eval_samples_per_second": 4.671,
+      "eval_steps_per_second": 4.671,
+      "step": 720
+    },
+    {
+      "epoch": 1.3375372620958497,
+      "grad_norm": 0.09012740105390549,
+      "learning_rate": 6.0185408400856116e-05,
+      "loss": 0.1152,
+      "step": 730
+    },
+    {
+      "epoch": 1.3558816785141024,
+      "grad_norm": 0.11220687627792358,
+      "learning_rate": 5.727160529077189e-05,
+      "loss": 0.1232,
+      "step": 740
+    },
+    {
+      "epoch": 1.374226094932355,
+      "grad_norm": 0.09022535383701324,
+      "learning_rate": 5.440152984753709e-05,
+      "loss": 0.1179,
+      "step": 750
+    },
+    {
+      "epoch": 1.374226094932355,
+      "eval_loss": 0.1143663227558136,
+      "eval_runtime": 49.3543,
+      "eval_samples_per_second": 4.66,
+      "eval_steps_per_second": 4.66,
+      "step": 750
+    },
+    {
+      "epoch": 1.3925705113506077,
+      "grad_norm": 0.08042389154434204,
+      "learning_rate": 5.157811926791905e-05,
+      "loss": 0.1219,
+      "step": 760
+    },
+    {
+      "epoch": 1.4109149277688604,
+      "grad_norm": 0.09887140244245529,
+      "learning_rate": 4.880426299248867e-05,
+      "loss": 0.1172,
+      "step": 770
+    },
+    {
+      "epoch": 1.429259344187113,
+      "grad_norm": 0.08288570493459702,
+      "learning_rate": 4.608279974860581e-05,
+      "loss": 0.1222,
+      "step": 780
+    },
+    {
+      "epoch": 1.429259344187113,
+      "eval_loss": 0.11446955054998398,
+      "eval_runtime": 49.3093,
+      "eval_samples_per_second": 4.664,
+      "eval_steps_per_second": 4.664,
+      "step": 780
+    },
+    {
+      "epoch": 1.4476037606053658,
+      "grad_norm": 0.08059478551149368,
+      "learning_rate": 4.341651464530341e-05,
+      "loss": 0.1236,
+      "step": 790
+    },
+    {
+      "epoch": 1.4659481770236185,
+      "grad_norm": 0.08869417011737823,
+      "learning_rate": 4.0808136323044554e-05,
+      "loss": 0.1209,
+      "step": 800
+    },
+    {
+      "epoch": 1.4842925934418711,
+      "grad_norm": 0.09369216859340668,
+      "learning_rate": 3.8260334161268077e-05,
+      "loss": 0.1228,
+      "step": 810
+    },
+    {
+      "epoch": 1.4842925934418711,
+      "eval_loss": 0.11371872574090958,
+      "eval_runtime": 49.2681,
+      "eval_samples_per_second": 4.668,
+      "eval_steps_per_second": 4.668,
+      "step": 810
+    },
+    {
+      "epoch": 1.5026370098601238,
+      "grad_norm": 0.07937419414520264,
+      "learning_rate": 3.577571554658154e-05,
+      "loss": 0.1144,
+      "step": 820
+    },
+    {
+      "epoch": 1.5209814262783765,
+      "grad_norm": 0.09610588103532791,
+      "learning_rate": 3.33568232043967e-05,
+      "loss": 0.1158,
+      "step": 830
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 0.1910742223262787,
+      "learning_rate": 3.100613259673843e-05,
+      "loss": 0.1261,
+      "step": 840
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "eval_loss": 0.11366112530231476,
+      "eval_runtime": 49.3771,
+      "eval_samples_per_second": 4.658,
+      "eval_steps_per_second": 4.658,
+      "step": 840
+    },
+    {
+      "epoch": 1.5576702591148819,
+      "grad_norm": 0.07669960707426071,
+      "learning_rate": 2.8726049388889807e-05,
+      "loss": 0.1165,
+      "step": 850
+    },
+    {
+      "epoch": 1.5760146755331346,
+      "grad_norm": 0.08569029718637466,
+      "learning_rate": 2.651890698746682e-05,
+      "loss": 0.1192,
+      "step": 860
+    },
+    {
+      "epoch": 1.5943590919513873,
+      "grad_norm": 0.09321046620607376,
+      "learning_rate": 2.4386964152441018e-05,
+      "loss": 0.1237,
+      "step": 870
+    },
+    {
+      "epoch": 1.5943590919513873,
+      "eval_loss": 0.11372239142656326,
+      "eval_runtime": 49.3141,
+      "eval_samples_per_second": 4.664,
+      "eval_steps_per_second": 4.664,
+      "step": 870
+    },
+    {
+      "epoch": 1.61270350836964,
+      "grad_norm": 0.08224959671497345,
+      "learning_rate": 2.2332402685554876e-05,
+      "loss": 0.1149,
+      "step": 880
+    },
+    {
+      "epoch": 1.6310479247878926,
+      "grad_norm": 0.07479019463062286,
+      "learning_rate": 2.035732519749528e-05,
+      "loss": 0.1237,
+      "step": 890
+    },
+    {
+      "epoch": 1.6493923412061453,
+      "grad_norm": 0.0903916209936142,
+      "learning_rate": 1.8463752956109615e-05,
+      "loss": 0.1167,
+      "step": 900
+    },
+    {
+      "epoch": 1.6493923412061453,
+      "eval_loss": 0.1136728897690773,
+      "eval_runtime": 49.4665,
+      "eval_samples_per_second": 4.65,
+      "eval_steps_per_second": 4.65,
+      "step": 900
+    },
+    {
+      "epoch": 1.667736757624398,
+      "grad_norm": 0.08336473256349564,
+      "learning_rate": 1.6653623817867637e-05,
+      "loss": 0.1171,
+      "step": 910
+    },
+    {
+      "epoch": 1.6860811740426507,
+      "grad_norm": 0.08168327063322067,
+      "learning_rate": 1.4928790244684865e-05,
+      "loss": 0.1189,
+      "step": 920
+    },
+    {
+      "epoch": 1.7044255904609034,
+      "grad_norm": 0.08606237918138504,
+      "learning_rate": 1.3291017408138006e-05,
+      "loss": 0.1184,
+      "step": 930
+    },
+    {
+      "epoch": 1.7044255904609034,
+      "eval_loss": 0.11324052512645721,
+      "eval_runtime": 49.4226,
+      "eval_samples_per_second": 4.654,
+      "eval_steps_per_second": 4.654,
+      "step": 930
+    },
+    {
+      "epoch": 1.722770006879156,
+      "grad_norm": 0.09091446548700333,
+      "learning_rate": 1.1741981383011924e-05,
+      "loss": 0.1184,
+      "step": 940
+    },
+    {
+      "epoch": 1.7411144232974087,
+      "grad_norm": 0.0911412388086319,
+      "learning_rate": 1.02832674320273e-05,
+      "loss": 0.1156,
+      "step": 950
+    },
+    {
+      "epoch": 1.7594588397156614,
+      "grad_norm": 0.11093633621931076,
+      "learning_rate": 8.916368383503781e-06,
+      "loss": 0.1231,
+      "step": 960
+    },
+    {
+      "epoch": 1.7594588397156614,
+      "eval_loss": 0.11301500350236893,
+      "eval_runtime": 49.4575,
+      "eval_samples_per_second": 4.65,
+      "eval_steps_per_second": 4.65,
+      "step": 960
+    },
+    {
+      "epoch": 1.777803256133914,
+      "grad_norm": 0.08233562856912613,
+      "learning_rate": 7.642683103619686e-06,
+      "loss": 0.1193,
+      "step": 970
+    },
+    {
+      "epoch": 1.7961476725521668,
+      "grad_norm": 0.08492106199264526,
+      "learning_rate": 6.463515064830916e-06,
+      "loss": 0.1113,
+      "step": 980
+    },
+    {
+      "epoch": 1.8144920889704195,
+      "grad_norm": 0.07636568695306778,
+      "learning_rate": 5.380071011914822e-06,
+      "loss": 0.1229,
+      "step": 990
+    },
+    {
+      "epoch": 1.8144920889704195,
+      "eval_loss": 0.11294619739055634,
+      "eval_runtime": 49.6347,
+      "eval_samples_per_second": 4.634,
+      "eval_steps_per_second": 4.634,
+      "step": 990
+    },
+    {
+      "epoch": 1.8328365053886724,
+      "grad_norm": 0.08528682589530945,
+      "learning_rate": 4.393459727003701e-06,
+      "loss": 0.1297,
+      "step": 1000
+    },
+    {
+      "epoch": 1.851180921806925,
+      "grad_norm": 0.10250170528888702,
+      "learning_rate": 3.5046908948720648e-06,
+      "loss": 0.1298,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8695253382251777,
+      "grad_norm": 0.08484761416912079,
+      "learning_rate": 2.714674069638712e-06,
+      "loss": 0.1149,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8695253382251777,
+      "eval_loss": 0.11291447281837463,
+      "eval_runtime": 49.44,
+      "eval_samples_per_second": 4.652,
+      "eval_steps_per_second": 4.652,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8878697546434304,
+      "grad_norm": 0.09421465545892715,
+      "learning_rate": 2.024217743941259e-06,
+      "loss": 0.1178,
+      "step": 1030
+    },
+    {
+      "epoch": 1.9062141710616831,
+      "grad_norm": 0.08403041958808899,
+      "learning_rate": 1.4340285215355575e-06,
+      "loss": 0.1147,
+      "step": 1040
+    },
+    {
+      "epoch": 1.9245585874799358,
+      "grad_norm": 0.0791555717587471,
+      "learning_rate": 9.447103941669588e-07,
+      "loss": 0.1164,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9245585874799358,
+      "eval_loss": 0.1128077432513237,
+      "eval_runtime": 49.4899,
+      "eval_samples_per_second": 4.647,
+      "eval_steps_per_second": 4.647,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9429030038981885,
+      "grad_norm": 0.08551088720560074,
+      "learning_rate": 5.567641234531684e-07,
+      "loss": 0.1126,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9612474203164412,
+      "grad_norm": 0.1025078073143959,
+      "learning_rate": 2.705867284115482e-07,
+      "loss": 0.1238,
+      "step": 1070
+    },
+    {
+      "epoch": 1.9795918367346939,
+      "grad_norm": 0.09163203835487366,
+      "learning_rate": 8.647107915519259e-08,
+      "loss": 0.1188,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9795918367346939,
+      "eval_loss": 0.11287853121757507,
+      "eval_runtime": 49.8096,
+      "eval_samples_per_second": 4.618,
+      "eval_steps_per_second": 4.618,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9979362531529465,
+      "grad_norm": 0.07899416238069534,
+      "learning_rate": 4.605597173534814e-09,
+      "loss": 0.1142,
+      "step": 1090
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1092,
+  "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": 1.593536299545047e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1092/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1f0a10aa743528b337db958330beda85917a812f1f8076421cfa4df3e349ce
+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 sha256:2e6561d5f06a6beabb00f65de120c02ecbacdad1552e084381ac59646e788b87
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3022b6f83b94a1234cb7a710e44bd4f6d006b6561e6e69e68674ad768d4ba41b
+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
+}