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-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-954/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/sft_alfworld_trajectory_dataset_v5
+- u-10bei/dbbench_sft_dataset_react_v4
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- agent
+- tool-use
+- alfworld
+- dbbench
+---
+
+# Qwen3-4B ALFWorld+DBBench Mixed LoRA Adapter (r=64)
+
+This repository provides a **LoRA adapter** fine-tuned from
+**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
+
+This repository contains **LoRA adapter weights only**.
+The base model must be loaded separately.
+
+## Training Objective
+
+This adapter is trained to improve **multi-turn agent task performance**
+on ALFWorld (household tasks) and DBBench (database operations).
+
+Loss is applied to **all assistant turns** in the multi-turn trajectory,
+enabling the model to learn environment observation, action selection,
+tool use, and recovery from errors.
+
+## Training Configuration
+
+- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Method: LoRA (full precision base)
+- Max sequence length: 4096
+- Epochs: 3
+- Learning rate: 2e-04
+- LoRA: r=64, alpha=128
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "Qwen/Qwen3-4B-Instruct-2507"
+adapter = "your_id/your-repo"
+
+tokenizer = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(
+    base,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(model, adapter)
+```
+
+## Sources & Terms (IMPORTANT)
+
+Training data: u-10bei/sft_alfworld_trajectory_dataset_v5 + u-10bei/dbbench_sft_dataset_react_v4
+
+Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
+Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

adapter_config.json

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

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d21ec418e08d43bb35d68fa497aa84e8b6e1232f4fee226ceeeb4588fc98b6e
+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-900/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-900/adapter_config.json

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

checkpoint-900/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c398496c43ed195fe96735a5fca974402d935aee6531dca40f973ce5bba932
+size 528550256

checkpoint-900/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-900/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-900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a4493c114056549579f7a829ecc6ed8e819ca34c19bdde629a529250a60f7e
+size 1057397963

checkpoint-900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e4795a10a62ee126766c502e8472f07eb714bd601cdcad25bb1c5919b47639
+size 14645

checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8adcca80ac24e18ea9ed663118521a78d1a0b7c59e74016939507f73d945da5c
+size 1465

checkpoint-900/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-900/tokenizer.json

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

checkpoint-900/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-900/trainer_state.json

@@ -0,0 +1,904 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8874901652242329,
+  "eval_steps": 30,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02098085496984002,
+      "grad_norm": 1.8758461475372314,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 2.2028,
+      "step": 10
+    },
+    {
+      "epoch": 0.04196170993968004,
+      "grad_norm": 0.6216842532157898,
+      "learning_rate": 7.916666666666666e-05,
+      "loss": 0.6879,
+      "step": 20
+    },
+    {
+      "epoch": 0.06294256490952006,
+      "grad_norm": 0.5248464941978455,
+      "learning_rate": 0.00012083333333333333,
+      "loss": 0.4469,
+      "step": 30
+    },
+    {
+      "epoch": 0.06294256490952006,
+      "eval_loss": 0.3734886944293976,
+      "eval_runtime": 53.5314,
+      "eval_samples_per_second": 3.755,
+      "eval_steps_per_second": 3.755,
+      "step": 30
+    },
+    {
+      "epoch": 0.08392341987936008,
+      "grad_norm": 0.580585777759552,
+      "learning_rate": 0.00016250000000000002,
+      "loss": 0.3179,
+      "step": 40
+    },
+    {
+      "epoch": 0.1049042748492001,
+      "grad_norm": 0.3856310248374939,
+      "learning_rate": 0.00019999939880837878,
+      "loss": 0.2501,
+      "step": 50
+    },
+    {
+      "epoch": 0.12588512981904013,
+      "grad_norm": 0.39517685770988464,
+      "learning_rate": 0.00019992726456006157,
+      "loss": 0.2317,
+      "step": 60
+    },
+    {
+      "epoch": 0.12588512981904013,
+      "eval_loss": 0.2062484174966812,
+      "eval_runtime": 53.2039,
+      "eval_samples_per_second": 3.778,
+      "eval_steps_per_second": 3.778,
+      "step": 60
+    },
+    {
+      "epoch": 0.14686598478888016,
+      "grad_norm": 0.3303804397583008,
+      "learning_rate": 0.00019973499136147606,
+      "loss": 0.1999,
+      "step": 70
+    },
+    {
+      "epoch": 0.16784683975872017,
+      "grad_norm": 0.34801360964775085,
+      "learning_rate": 0.00019942281037576222,
+      "loss": 0.1834,
+      "step": 80
+    },
+    {
+      "epoch": 0.1888276947285602,
+      "grad_norm": 0.1771993190050125,
+      "learning_rate": 0.00019899109692687278,
+      "loss": 0.1827,
+      "step": 90
+    },
+    {
+      "epoch": 0.1888276947285602,
+      "eval_loss": 0.1743820756673813,
+      "eval_runtime": 53.1567,
+      "eval_samples_per_second": 3.781,
+      "eval_steps_per_second": 3.781,
+      "step": 90
+    },
+    {
+      "epoch": 0.2098085496984002,
+      "grad_norm": 0.2773347496986389,
+      "learning_rate": 0.00019844037004833473,
+      "loss": 0.1683,
+      "step": 100
+    },
+    {
+      "epoch": 0.23078940466824024,
+      "grad_norm": 0.16112257540225983,
+      "learning_rate": 0.00019777129185923395,
+      "loss": 0.1697,
+      "step": 110
+    },
+    {
+      "epoch": 0.25177025963808025,
+      "grad_norm": 0.26540514826774597,
+      "learning_rate": 0.00019698466676817348,
+      "loss": 0.168,
+      "step": 120
+    },
+    {
+      "epoch": 0.25177025963808025,
+      "eval_loss": 0.15549546480178833,
+      "eval_runtime": 53.5518,
+      "eval_samples_per_second": 3.753,
+      "eval_steps_per_second": 3.753,
+      "step": 120
+    },
+    {
+      "epoch": 0.2727511146079203,
+      "grad_norm": 0.1737111657857895,
+      "learning_rate": 0.0001960814405061619,
+      "loss": 0.1524,
+      "step": 130
+    },
+    {
+      "epoch": 0.2937319695777603,
+      "grad_norm": 0.23373852670192719,
+      "learning_rate": 0.000195062698989595,
+      "loss": 0.1577,
+      "step": 140
+    },
+    {
+      "epoch": 0.3147128245476003,
+      "grad_norm": 0.23839105665683746,
+      "learning_rate": 0.0001939296670146976,
+      "loss": 0.1562,
+      "step": 150
+    },
+    {
+      "epoch": 0.3147128245476003,
+      "eval_loss": 0.14308005571365356,
+      "eval_runtime": 53.5362,
+      "eval_samples_per_second": 3.754,
+      "eval_steps_per_second": 3.754,
+      "step": 150
+    },
+    {
+      "epoch": 0.33569367951744034,
+      "grad_norm": 0.22177831828594208,
+      "learning_rate": 0.00019268370678499533,
+      "loss": 0.1507,
+      "step": 160
+    },
+    {
+      "epoch": 0.35667453448728037,
+      "grad_norm": 0.16764189302921295,
+      "learning_rate": 0.0001913263162735862,
+      "loss": 0.15,
+      "step": 170
+    },
+    {
+      "epoch": 0.3776553894571204,
+      "grad_norm": 0.17721307277679443,
+      "learning_rate": 0.00018985912742218165,
+      "loss": 0.148,
+      "step": 180
+    },
+    {
+      "epoch": 0.3776553894571204,
+      "eval_loss": 0.13974663615226746,
+      "eval_runtime": 53.2066,
+      "eval_samples_per_second": 3.778,
+      "eval_steps_per_second": 3.778,
+      "step": 180
+    },
+    {
+      "epoch": 0.3986362444269604,
+      "grad_norm": 0.11757932603359222,
+      "learning_rate": 0.0001882839041790818,
+      "loss": 0.1482,
+      "step": 190
+    },
+    {
+      "epoch": 0.4196170993968004,
+      "grad_norm": 0.17747701704502106,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.1442,
+      "step": 200
+    },
+    {
+      "epoch": 0.44059795436664045,
+      "grad_norm": 0.15337860584259033,
+      "learning_rate": 0.0001848170574633937,
+      "loss": 0.1481,
+      "step": 210
+    },
+    {
+      "epoch": 0.44059795436664045,
+      "eval_loss": 0.13732697069644928,
+      "eval_runtime": 52.9478,
+      "eval_samples_per_second": 3.796,
+      "eval_steps_per_second": 3.796,
+      "step": 210
+    },
+    {
+      "epoch": 0.4615788093364805,
+      "grad_norm": 0.25963345170021057,
+      "learning_rate": 0.0001829296020557174,
+      "loss": 0.1557,
+      "step": 220
+    },
+    {
+      "epoch": 0.48255966430632047,
+      "grad_norm": 0.12170088291168213,
+      "learning_rate": 0.0001809424433750555,
+      "loss": 0.1401,
+      "step": 230
+    },
+    {
+      "epoch": 0.5035405192761605,
+      "grad_norm": 0.1923166960477829,
+      "learning_rate": 0.0001788579705107017,
+      "loss": 0.1455,
+      "step": 240
+    },
+    {
+      "epoch": 0.5035405192761605,
+      "eval_loss": 0.13553670048713684,
+      "eval_runtime": 53.4546,
+      "eval_samples_per_second": 3.76,
+      "eval_steps_per_second": 3.76,
+      "step": 240
+    },
+    {
+      "epoch": 0.5245213742460005,
+      "grad_norm": 0.11837635189294815,
+      "learning_rate": 0.00017667868954928694,
+      "loss": 0.147,
+      "step": 250
+    },
+    {
+      "epoch": 0.5455022292158406,
+      "grad_norm": 0.10800451040267944,
+      "learning_rate": 0.0001744072205618019,
+      "loss": 0.1362,
+      "step": 260
+    },
+    {
+      "epoch": 0.5664830841856806,
+      "grad_norm": 0.12966878712177277,
+      "learning_rate": 0.0001720462944535798,
+      "loss": 0.1509,
+      "step": 270
+    },
+    {
+      "epoch": 0.5664830841856806,
+      "eval_loss": 0.13392792642116547,
+      "eval_runtime": 53.5435,
+      "eval_samples_per_second": 3.754,
+      "eval_steps_per_second": 3.754,
+      "step": 270
+    },
+    {
+      "epoch": 0.5874639391555206,
+      "grad_norm": 0.11909834295511246,
+      "learning_rate": 0.00016959874968102735,
+      "loss": 0.1399,
+      "step": 280
+    },
+    {
+      "epoch": 0.6084447941253606,
+      "grad_norm": 0.1039784699678421,
+      "learning_rate": 0.00016706752883905107,
+      "loss": 0.141,
+      "step": 290
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "grad_norm": 0.11826395988464355,
+      "learning_rate": 0.0001644556751232812,
+      "loss": 0.1495,
+      "step": 300
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "eval_loss": 0.13278058171272278,
+      "eval_runtime": 53.7282,
+      "eval_samples_per_second": 3.741,
+      "eval_steps_per_second": 3.741,
+      "step": 300
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 0.12009374052286148,
+      "learning_rate": 0.0001617663286713474,
+      "loss": 0.1407,
+      "step": 310
+    },
+    {
+      "epoch": 0.6713873590348807,
+      "grad_norm": 0.11825403571128845,
+      "learning_rate": 0.00015900272278760407,
+      "loss": 0.1387,
+      "step": 320
+    },
+    {
+      "epoch": 0.6923682140047207,
+      "grad_norm": 0.11216018348932266,
+      "learning_rate": 0.00015616818005584554,
+      "loss": 0.1404,
+      "step": 330
+    },
+    {
+      "epoch": 0.6923682140047207,
+      "eval_loss": 0.13230031728744507,
+      "eval_runtime": 53.7398,
+      "eval_samples_per_second": 3.74,
+      "eval_steps_per_second": 3.74,
+      "step": 330
+    },
+    {
+      "epoch": 0.7133490689745607,
+      "grad_norm": 0.10475457459688187,
+      "learning_rate": 0.0001532661083446829,
+      "loss": 0.1503,
+      "step": 340
+    },
+    {
+      "epoch": 0.7343299239444008,
+      "grad_norm": 0.11185269057750702,
+      "learning_rate": 0.00015029999671038635,
+      "loss": 0.1321,
+      "step": 350
+    },
+    {
+      "epoch": 0.7553107789142408,
+      "grad_norm": 0.0922306478023529,
+      "learning_rate": 0.00014727341120211867,
+      "loss": 0.1428,
+      "step": 360
+    },
+    {
+      "epoch": 0.7553107789142408,
+      "eval_loss": 0.1310930848121643,
+      "eval_runtime": 53.6353,
+      "eval_samples_per_second": 3.748,
+      "eval_steps_per_second": 3.748,
+      "step": 360
+    },
+    {
+      "epoch": 0.7762916338840807,
+      "grad_norm": 0.12543067336082458,
+      "learning_rate": 0.00014418999057460276,
+      "loss": 0.1437,
+      "step": 370
+    },
+    {
+      "epoch": 0.7972724888539208,
+      "grad_norm": 0.11975102126598358,
+      "learning_rate": 0.0001410534419133778,
+      "loss": 0.1357,
+      "step": 380
+    },
+    {
+      "epoch": 0.8182533438237608,
+      "grad_norm": 0.09955570101737976,
+      "learning_rate": 0.00013786753617790404,
+      "loss": 0.1446,
+      "step": 390
+    },
+    {
+      "epoch": 0.8182533438237608,
+      "eval_loss": 0.13151544332504272,
+      "eval_runtime": 53.6082,
+      "eval_samples_per_second": 3.749,
+      "eval_steps_per_second": 3.749,
+      "step": 390
+    },
+    {
+      "epoch": 0.8392341987936008,
+      "grad_norm": 0.11849252134561539,
+      "learning_rate": 0.00013463610366787392,
+      "loss": 0.1452,
+      "step": 400
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.10621926933526993,
+      "learning_rate": 0.00013136302941818085,
+      "loss": 0.1411,
+      "step": 410
+    },
+    {
+      "epoch": 0.8811959087332809,
+      "grad_norm": 0.09327146410942078,
+      "learning_rate": 0.00012805224852808163,
+      "loss": 0.1391,
+      "step": 420
+    },
+    {
+      "epoch": 0.8811959087332809,
+      "eval_loss": 0.13071787357330322,
+      "eval_runtime": 53.9186,
+      "eval_samples_per_second": 3.728,
+      "eval_steps_per_second": 3.728,
+      "step": 420
+    },
+    {
+      "epoch": 0.9021767637031209,
+      "grad_norm": 0.5398991703987122,
+      "learning_rate": 0.00012470774143016853,
+      "loss": 0.1399,
+      "step": 430
+    },
+    {
+      "epoch": 0.923157618672961,
+      "grad_norm": 0.18647532165050507,
+      "learning_rate": 0.00012133352910483838,
+      "loss": 0.1399,
+      "step": 440
+    },
+    {
+      "epoch": 0.9441384736428009,
+      "grad_norm": 0.16210441291332245,
+      "learning_rate": 0.0001179336682460128,
+      "loss": 0.1509,
+      "step": 450
+    },
+    {
+      "epoch": 0.9441384736428009,
+      "eval_loss": 0.13233241438865662,
+      "eval_runtime": 53.9437,
+      "eval_samples_per_second": 3.726,
+      "eval_steps_per_second": 3.726,
+      "step": 450
+    },
+    {
+      "epoch": 0.9651193286126409,
+      "grad_norm": 0.09105144441127777,
+      "learning_rate": 0.00011451224638392129,
+      "loss": 0.1428,
+      "step": 460
+    },
+    {
+      "epoch": 0.986100183582481,
+      "grad_norm": 0.08386187255382538,
+      "learning_rate": 0.0001110733769708108,
+      "loss": 0.14,
+      "step": 470
+    },
+    {
+      "epoch": 1.006294256490952,
+      "grad_norm": 0.07673283666372299,
+      "learning_rate": 0.00010762119443549035,
+      "loss": 0.142,
+      "step": 480
+    },
+    {
+      "epoch": 1.006294256490952,
+      "eval_loss": 0.1293467879295349,
+      "eval_runtime": 53.6668,
+      "eval_samples_per_second": 3.745,
+      "eval_steps_per_second": 3.745,
+      "step": 480
+    },
+    {
+      "epoch": 1.027275111460792,
+      "grad_norm": 0.09950114041566849,
+      "learning_rate": 0.00010415984921265609,
+      "loss": 0.1365,
+      "step": 490
+    },
+    {
+      "epoch": 1.0482559664306321,
+      "grad_norm": 0.08757766336202621,
+      "learning_rate": 0.00010069350275297337,
+      "loss": 0.1297,
+      "step": 500
+    },
+    {
+      "epoch": 1.0692368214004722,
+      "grad_norm": 0.08058227598667145,
+      "learning_rate": 9.722632251991444e-05,
+      "loss": 0.1258,
+      "step": 510
+    },
+    {
+      "epoch": 1.0692368214004722,
+      "eval_loss": 0.1290971338748932,
+      "eval_runtime": 53.9631,
+      "eval_samples_per_second": 3.725,
+      "eval_steps_per_second": 3.725,
+      "step": 510
+    },
+    {
+      "epoch": 1.0902176763703122,
+      "grad_norm": 0.14287236332893372,
+      "learning_rate": 9.376247697936719e-05,
+      "loss": 0.1405,
+      "step": 520
+    },
+    {
+      "epoch": 1.1111985313401522,
+      "grad_norm": 0.10073138028383255,
+      "learning_rate": 9.030613058803881e-05,
+      "loss": 0.1372,
+      "step": 530
+    },
+    {
+      "epoch": 1.132179386309992,
+      "grad_norm": 0.09560772776603699,
+      "learning_rate": 8.686143878667965e-05,
+      "loss": 0.1344,
+      "step": 540
+    },
+    {
+      "epoch": 1.132179386309992,
+      "eval_loss": 0.1287485510110855,
+      "eval_runtime": 53.9488,
+      "eval_samples_per_second": 3.726,
+      "eval_steps_per_second": 3.726,
+      "step": 540
+    },
+    {
+      "epoch": 1.153160241279832,
+      "grad_norm": 0.09153210371732712,
+      "learning_rate": 8.343254300414628e-05,
+      "loss": 0.1379,
+      "step": 550
+    },
+    {
+      "epoch": 1.1741410962496721,
+      "grad_norm": 0.0932949036359787,
+      "learning_rate": 8.002356567831103e-05,
+      "loss": 0.1361,
+      "step": 560
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "grad_norm": 0.1091330498456955,
+      "learning_rate": 7.663860529980317e-05,
+      "loss": 0.1356,
+      "step": 570
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "eval_loss": 0.13008803129196167,
+      "eval_runtime": 53.6432,
+      "eval_samples_per_second": 3.747,
+      "eval_steps_per_second": 3.747,
+      "step": 570
+    },
+    {
+      "epoch": 1.2161028061893522,
+      "grad_norm": 0.08824314922094345,
+      "learning_rate": 7.328173148454151e-05,
+      "loss": 0.1335,
+      "step": 580
+    },
+    {
+      "epoch": 1.2370836611591922,
+      "grad_norm": 0.12611347436904907,
+      "learning_rate": 6.99569800809816e-05,
+      "loss": 0.1353,
+      "step": 590
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 0.08815793693065643,
+      "learning_rate": 6.66683483179608e-05,
+      "loss": 0.1365,
+      "step": 600
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "eval_loss": 0.12925004959106445,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 3.747,
+      "eval_steps_per_second": 3.747,
+      "step": 600
+    },
+    {
+      "epoch": 1.2790453710988723,
+      "grad_norm": 0.12618786096572876,
+      "learning_rate": 6.341978999897365e-05,
+      "loss": 0.1408,
+      "step": 610
+    },
+    {
+      "epoch": 1.3000262260687123,
+      "grad_norm": 0.0881665050983429,
+      "learning_rate": 6.021521074865678e-05,
+      "loss": 0.1384,
+      "step": 620
+    },
+    {
+      "epoch": 1.3210070810385524,
+      "grad_norm": 0.08780647069215775,
+      "learning_rate": 5.705846331719675e-05,
+      "loss": 0.138,
+      "step": 630
+    },
+    {
+      "epoch": 1.3210070810385524,
+      "eval_loss": 0.12802067399024963,
+      "eval_runtime": 53.8068,
+      "eval_samples_per_second": 3.736,
+      "eval_steps_per_second": 3.736,
+      "step": 630
+    },
+    {
+      "epoch": 1.3419879360083924,
+      "grad_norm": 0.08264625817537308,
+      "learning_rate": 5.395334294830765e-05,
+      "loss": 0.1376,
+      "step": 640
+    },
+    {
+      "epoch": 1.3629687909782324,
+      "grad_norm": 0.08895017951726913,
+      "learning_rate": 5.090358281634594e-05,
+      "loss": 0.1325,
+      "step": 650
+    },
+    {
+      "epoch": 1.3839496459480725,
+      "grad_norm": 0.08006913214921951,
+      "learning_rate": 4.791284953804969e-05,
+      "loss": 0.1336,
+      "step": 660
+    },
+    {
+      "epoch": 1.3839496459480725,
+      "eval_loss": 0.1273050308227539,
+      "eval_runtime": 53.8944,
+      "eval_samples_per_second": 3.73,
+      "eval_steps_per_second": 3.73,
+      "step": 660
+    },
+    {
+      "epoch": 1.4049305009179123,
+      "grad_norm": 0.09627630561590195,
+      "learning_rate": 4.498473876429726e-05,
+      "loss": 0.1341,
+      "step": 670
+    },
+    {
+      "epoch": 1.4259113558877523,
+      "grad_norm": 0.08036801964044571,
+      "learning_rate": 4.21227708571858e-05,
+      "loss": 0.1419,
+      "step": 680
+    },
+    {
+      "epoch": 1.4468922108575923,
+      "grad_norm": 0.1135723665356636,
+      "learning_rate": 3.93303866576267e-05,
+      "loss": 0.13,
+      "step": 690
+    },
+    {
+      "epoch": 1.4468922108575923,
+      "eval_loss": 0.12765151262283325,
+      "eval_runtime": 53.9209,
+      "eval_samples_per_second": 3.728,
+      "eval_steps_per_second": 3.728,
+      "step": 690
+    },
+    {
+      "epoch": 1.4678730658274324,
+      "grad_norm": 0.07758687436580658,
+      "learning_rate": 3.6610943348546526e-05,
+      "loss": 0.1427,
+      "step": 700
+    },
+    {
+      "epoch": 1.4888539207972724,
+      "grad_norm": 0.09151093661785126,
+      "learning_rate": 3.3967710418666984e-05,
+      "loss": 0.1372,
+      "step": 710
+    },
+    {
+      "epoch": 1.5098347757671124,
+      "grad_norm": 0.10960382223129272,
+      "learning_rate": 3.1403865731716266e-05,
+      "loss": 0.134,
+      "step": 720
+    },
+    {
+      "epoch": 1.5098347757671124,
+      "eval_loss": 0.12656451761722565,
+      "eval_runtime": 53.601,
+      "eval_samples_per_second": 3.75,
+      "eval_steps_per_second": 3.75,
+      "step": 720
+    },
+    {
+      "epoch": 1.5308156307369525,
+      "grad_norm": 0.10491708666086197,
+      "learning_rate": 2.892249170579826e-05,
+      "loss": 0.1341,
+      "step": 730
+    },
+    {
+      "epoch": 1.5517964857067925,
+      "grad_norm": 0.09089571982622147,
+      "learning_rate": 2.652657160751193e-05,
+      "loss": 0.1377,
+      "step": 740
+    },
+    {
+      "epoch": 1.5727773406766326,
+      "grad_norm": 0.07756100594997406,
+      "learning_rate": 2.4218985965277675e-05,
+      "loss": 0.1325,
+      "step": 750
+    },
+    {
+      "epoch": 1.5727773406766326,
+      "eval_loss": 0.12670381367206573,
+      "eval_runtime": 53.6584,
+      "eval_samples_per_second": 3.746,
+      "eval_steps_per_second": 3.746,
+      "step": 750
+    },
+    {
+      "epoch": 1.5937581956464726,
+      "grad_norm": 0.10038470476865768,
+      "learning_rate": 2.2002509106181624e-05,
+      "loss": 0.1275,
+      "step": 760
+    },
+    {
+      "epoch": 1.6147390506163126,
+      "grad_norm": 0.09714746475219727,
+      "learning_rate": 1.9879805820502174e-05,
+      "loss": 0.138,
+      "step": 770
+    },
+    {
+      "epoch": 1.6357199055861527,
+      "grad_norm": 0.10250572115182877,
+      "learning_rate": 1.785342815792862e-05,
+      "loss": 0.1337,
+      "step": 780
+    },
+    {
+      "epoch": 1.6357199055861527,
+      "eval_loss": 0.12649498879909515,
+      "eval_runtime": 53.9776,
+      "eval_samples_per_second": 3.724,
+      "eval_steps_per_second": 3.724,
+      "step": 780
+    },
+    {
+      "epoch": 1.6567007605559927,
+      "grad_norm": 0.10221794247627258,
+      "learning_rate": 1.5925812359323745e-05,
+      "loss": 0.138,
+      "step": 790
+    },
+    {
+      "epoch": 1.6776816155258327,
+      "grad_norm": 0.08815432339906693,
+      "learning_rate": 1.4099275927719235e-05,
+      "loss": 0.1308,
+      "step": 800
+    },
+    {
+      "epoch": 1.6986624704956728,
+      "grad_norm": 0.08850682526826859,
+      "learning_rate": 1.2376014842065265e-05,
+      "loss": 0.1385,
+      "step": 810
+    },
+    {
+      "epoch": 1.6986624704956728,
+      "eval_loss": 0.12599113583564758,
+      "eval_runtime": 53.6591,
+      "eval_samples_per_second": 3.746,
+      "eval_steps_per_second": 3.746,
+      "step": 810
+    },
+    {
+      "epoch": 1.7196433254655128,
+      "grad_norm": 0.0861755833029747,
+      "learning_rate": 1.0758100917083991e-05,
+      "loss": 0.1321,
+      "step": 820
+    },
+    {
+      "epoch": 1.7406241804353528,
+      "grad_norm": 0.09379922598600388,
+      "learning_rate": 9.247479312401641e-06,
+      "loss": 0.1288,
+      "step": 830
+    },
+    {
+      "epoch": 1.7616050354051929,
+      "grad_norm": 0.11254911869764328,
+      "learning_rate": 7.845966193952824e-06,
+      "loss": 0.126,
+      "step": 840
+    },
+    {
+      "epoch": 1.7616050354051929,
+      "eval_loss": 0.12584222853183746,
+      "eval_runtime": 54.0496,
+      "eval_samples_per_second": 3.719,
+      "eval_steps_per_second": 3.719,
+      "step": 840
+    },
+    {
+      "epoch": 1.782585890375033,
+      "grad_norm": 0.09247393906116486,
+      "learning_rate": 6.555246550469907e-06,
+      "loss": 0.1365,
+      "step": 850
+    },
+    {
+      "epoch": 1.803566745344873,
+      "grad_norm": 0.11225956678390503,
+      "learning_rate": 5.376872167681635e-06,
+      "loss": 0.1325,
+      "step": 860
+    },
+    {
+      "epoch": 1.824547600314713,
+      "grad_norm": 0.08813902735710144,
+      "learning_rate": 4.312259762657145e-06,
+      "loss": 0.1321,
+      "step": 870
+    },
+    {
+      "epoch": 1.824547600314713,
+      "eval_loss": 0.12573501467704773,
+      "eval_runtime": 53.8714,
+      "eval_samples_per_second": 3.731,
+      "eval_steps_per_second": 3.731,
+      "step": 870
+    },
+    {
+      "epoch": 1.845528455284553,
+      "grad_norm": 0.09407710283994675,
+      "learning_rate": 3.3626892805379562e-06,
+      "loss": 0.1295,
+      "step": 880
+    },
+    {
+      "epoch": 1.8665093102543928,
+      "grad_norm": 0.10119906812906265,
+      "learning_rate": 2.5293023557061644e-06,
+      "loss": 0.1259,
+      "step": 890
+    },
+    {
+      "epoch": 1.8874901652242329,
+      "grad_norm": 0.12075681984424591,
+      "learning_rate": 1.8131009392384323e-06,
+      "loss": 0.1338,
+      "step": 900
+    },
+    {
+      "epoch": 1.8874901652242329,
+      "eval_loss": 0.12563975155353546,
+      "eval_runtime": 53.9437,
+      "eval_samples_per_second": 3.726,
+      "eval_steps_per_second": 3.726,
+      "step": 900
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 954,
+  "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": 1.4996258681421312e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c440813fc825035a683e2f0277799f1d9de906c1a6c2d0246e8e9788def58820
+size 5777

checkpoint-954/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-954/adapter_config.json

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

checkpoint-954/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d21ec418e08d43bb35d68fa497aa84e8b6e1232f4fee226ceeeb4588fc98b6e
+size 528550256

checkpoint-954/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-954/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-954/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e10c636778d364dfa9015e107eb7ea52ffbfb02ba4dd25b09e9045db5c3e291
+size 1057397963

checkpoint-954/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6223799d7acba489067a0ce364fa78bc1a048a5204277a67d5b49feb629210b4
+size 14645

checkpoint-954/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f28d25a5cb401d73efbe0df1b91ddf24c33f0cc64b73579bd3841dc8d3ca9e
+size 1465

checkpoint-954/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-954/tokenizer.json

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

checkpoint-954/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-954/trainer_state.json

@@ -0,0 +1,947 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 30,
+  "global_step": 954,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02098085496984002,
+      "grad_norm": 1.8758461475372314,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 2.2028,
+      "step": 10
+    },
+    {
+      "epoch": 0.04196170993968004,
+      "grad_norm": 0.6216842532157898,
+      "learning_rate": 7.916666666666666e-05,
+      "loss": 0.6879,
+      "step": 20
+    },
+    {
+      "epoch": 0.06294256490952006,
+      "grad_norm": 0.5248464941978455,
+      "learning_rate": 0.00012083333333333333,
+      "loss": 0.4469,
+      "step": 30
+    },
+    {
+      "epoch": 0.06294256490952006,
+      "eval_loss": 0.3734886944293976,
+      "eval_runtime": 53.5314,
+      "eval_samples_per_second": 3.755,
+      "eval_steps_per_second": 3.755,
+      "step": 30
+    },
+    {
+      "epoch": 0.08392341987936008,
+      "grad_norm": 0.580585777759552,
+      "learning_rate": 0.00016250000000000002,
+      "loss": 0.3179,
+      "step": 40
+    },
+    {
+      "epoch": 0.1049042748492001,
+      "grad_norm": 0.3856310248374939,
+      "learning_rate": 0.00019999939880837878,
+      "loss": 0.2501,
+      "step": 50
+    },
+    {
+      "epoch": 0.12588512981904013,
+      "grad_norm": 0.39517685770988464,
+      "learning_rate": 0.00019992726456006157,
+      "loss": 0.2317,
+      "step": 60
+    },
+    {
+      "epoch": 0.12588512981904013,
+      "eval_loss": 0.2062484174966812,
+      "eval_runtime": 53.2039,
+      "eval_samples_per_second": 3.778,
+      "eval_steps_per_second": 3.778,
+      "step": 60
+    },
+    {
+      "epoch": 0.14686598478888016,
+      "grad_norm": 0.3303804397583008,
+      "learning_rate": 0.00019973499136147606,
+      "loss": 0.1999,
+      "step": 70
+    },
+    {
+      "epoch": 0.16784683975872017,
+      "grad_norm": 0.34801360964775085,
+      "learning_rate": 0.00019942281037576222,
+      "loss": 0.1834,
+      "step": 80
+    },
+    {
+      "epoch": 0.1888276947285602,
+      "grad_norm": 0.1771993190050125,
+      "learning_rate": 0.00019899109692687278,
+      "loss": 0.1827,
+      "step": 90
+    },
+    {
+      "epoch": 0.1888276947285602,
+      "eval_loss": 0.1743820756673813,
+      "eval_runtime": 53.1567,
+      "eval_samples_per_second": 3.781,
+      "eval_steps_per_second": 3.781,
+      "step": 90
+    },
+    {
+      "epoch": 0.2098085496984002,
+      "grad_norm": 0.2773347496986389,
+      "learning_rate": 0.00019844037004833473,
+      "loss": 0.1683,
+      "step": 100
+    },
+    {
+      "epoch": 0.23078940466824024,
+      "grad_norm": 0.16112257540225983,
+      "learning_rate": 0.00019777129185923395,
+      "loss": 0.1697,
+      "step": 110
+    },
+    {
+      "epoch": 0.25177025963808025,
+      "grad_norm": 0.26540514826774597,
+      "learning_rate": 0.00019698466676817348,
+      "loss": 0.168,
+      "step": 120
+    },
+    {
+      "epoch": 0.25177025963808025,
+      "eval_loss": 0.15549546480178833,
+      "eval_runtime": 53.5518,
+      "eval_samples_per_second": 3.753,
+      "eval_steps_per_second": 3.753,
+      "step": 120
+    },
+    {
+      "epoch": 0.2727511146079203,
+      "grad_norm": 0.1737111657857895,
+      "learning_rate": 0.0001960814405061619,
+      "loss": 0.1524,
+      "step": 130
+    },
+    {
+      "epoch": 0.2937319695777603,
+      "grad_norm": 0.23373852670192719,
+      "learning_rate": 0.000195062698989595,
+      "loss": 0.1577,
+      "step": 140
+    },
+    {
+      "epoch": 0.3147128245476003,
+      "grad_norm": 0.23839105665683746,
+      "learning_rate": 0.0001939296670146976,
+      "loss": 0.1562,
+      "step": 150
+    },
+    {
+      "epoch": 0.3147128245476003,
+      "eval_loss": 0.14308005571365356,
+      "eval_runtime": 53.5362,
+      "eval_samples_per_second": 3.754,
+      "eval_steps_per_second": 3.754,
+      "step": 150
+    },
+    {
+      "epoch": 0.33569367951744034,
+      "grad_norm": 0.22177831828594208,
+      "learning_rate": 0.00019268370678499533,
+      "loss": 0.1507,
+      "step": 160
+    },
+    {
+      "epoch": 0.35667453448728037,
+      "grad_norm": 0.16764189302921295,
+      "learning_rate": 0.0001913263162735862,
+      "loss": 0.15,
+      "step": 170
+    },
+    {
+      "epoch": 0.3776553894571204,
+      "grad_norm": 0.17721307277679443,
+      "learning_rate": 0.00018985912742218165,
+      "loss": 0.148,
+      "step": 180
+    },
+    {
+      "epoch": 0.3776553894571204,
+      "eval_loss": 0.13974663615226746,
+      "eval_runtime": 53.2066,
+      "eval_samples_per_second": 3.778,
+      "eval_steps_per_second": 3.778,
+      "step": 180
+    },
+    {
+      "epoch": 0.3986362444269604,
+      "grad_norm": 0.11757932603359222,
+      "learning_rate": 0.0001882839041790818,
+      "loss": 0.1482,
+      "step": 190
+    },
+    {
+      "epoch": 0.4196170993968004,
+      "grad_norm": 0.17747701704502106,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.1442,
+      "step": 200
+    },
+    {
+      "epoch": 0.44059795436664045,
+      "grad_norm": 0.15337860584259033,
+      "learning_rate": 0.0001848170574633937,
+      "loss": 0.1481,
+      "step": 210
+    },
+    {
+      "epoch": 0.44059795436664045,
+      "eval_loss": 0.13732697069644928,
+      "eval_runtime": 52.9478,
+      "eval_samples_per_second": 3.796,
+      "eval_steps_per_second": 3.796,
+      "step": 210
+    },
+    {
+      "epoch": 0.4615788093364805,
+      "grad_norm": 0.25963345170021057,
+      "learning_rate": 0.0001829296020557174,
+      "loss": 0.1557,
+      "step": 220
+    },
+    {
+      "epoch": 0.48255966430632047,
+      "grad_norm": 0.12170088291168213,
+      "learning_rate": 0.0001809424433750555,
+      "loss": 0.1401,
+      "step": 230
+    },
+    {
+      "epoch": 0.5035405192761605,
+      "grad_norm": 0.1923166960477829,
+      "learning_rate": 0.0001788579705107017,
+      "loss": 0.1455,
+      "step": 240
+    },
+    {
+      "epoch": 0.5035405192761605,
+      "eval_loss": 0.13553670048713684,
+      "eval_runtime": 53.4546,
+      "eval_samples_per_second": 3.76,
+      "eval_steps_per_second": 3.76,
+      "step": 240
+    },
+    {
+      "epoch": 0.5245213742460005,
+      "grad_norm": 0.11837635189294815,
+      "learning_rate": 0.00017667868954928694,
+      "loss": 0.147,
+      "step": 250
+    },
+    {
+      "epoch": 0.5455022292158406,
+      "grad_norm": 0.10800451040267944,
+      "learning_rate": 0.0001744072205618019,
+      "loss": 0.1362,
+      "step": 260
+    },
+    {
+      "epoch": 0.5664830841856806,
+      "grad_norm": 0.12966878712177277,
+      "learning_rate": 0.0001720462944535798,
+      "loss": 0.1509,
+      "step": 270
+    },
+    {
+      "epoch": 0.5664830841856806,
+      "eval_loss": 0.13392792642116547,
+      "eval_runtime": 53.5435,
+      "eval_samples_per_second": 3.754,
+      "eval_steps_per_second": 3.754,
+      "step": 270
+    },
+    {
+      "epoch": 0.5874639391555206,
+      "grad_norm": 0.11909834295511246,
+      "learning_rate": 0.00016959874968102735,
+      "loss": 0.1399,
+      "step": 280
+    },
+    {
+      "epoch": 0.6084447941253606,
+      "grad_norm": 0.1039784699678421,
+      "learning_rate": 0.00016706752883905107,
+      "loss": 0.141,
+      "step": 290
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "grad_norm": 0.11826395988464355,
+      "learning_rate": 0.0001644556751232812,
+      "loss": 0.1495,
+      "step": 300
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "eval_loss": 0.13278058171272278,
+      "eval_runtime": 53.7282,
+      "eval_samples_per_second": 3.741,
+      "eval_steps_per_second": 3.741,
+      "step": 300
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 0.12009374052286148,
+      "learning_rate": 0.0001617663286713474,
+      "loss": 0.1407,
+      "step": 310
+    },
+    {
+      "epoch": 0.6713873590348807,
+      "grad_norm": 0.11825403571128845,
+      "learning_rate": 0.00015900272278760407,
+      "loss": 0.1387,
+      "step": 320
+    },
+    {
+      "epoch": 0.6923682140047207,
+      "grad_norm": 0.11216018348932266,
+      "learning_rate": 0.00015616818005584554,
+      "loss": 0.1404,
+      "step": 330
+    },
+    {
+      "epoch": 0.6923682140047207,
+      "eval_loss": 0.13230031728744507,
+      "eval_runtime": 53.7398,
+      "eval_samples_per_second": 3.74,
+      "eval_steps_per_second": 3.74,
+      "step": 330
+    },
+    {
+      "epoch": 0.7133490689745607,
+      "grad_norm": 0.10475457459688187,
+      "learning_rate": 0.0001532661083446829,
+      "loss": 0.1503,
+      "step": 340
+    },
+    {
+      "epoch": 0.7343299239444008,
+      "grad_norm": 0.11185269057750702,
+      "learning_rate": 0.00015029999671038635,
+      "loss": 0.1321,
+      "step": 350
+    },
+    {
+      "epoch": 0.7553107789142408,
+      "grad_norm": 0.0922306478023529,
+      "learning_rate": 0.00014727341120211867,
+      "loss": 0.1428,
+      "step": 360
+    },
+    {
+      "epoch": 0.7553107789142408,
+      "eval_loss": 0.1310930848121643,
+      "eval_runtime": 53.6353,
+      "eval_samples_per_second": 3.748,
+      "eval_steps_per_second": 3.748,
+      "step": 360
+    },
+    {
+      "epoch": 0.7762916338840807,
+      "grad_norm": 0.12543067336082458,
+      "learning_rate": 0.00014418999057460276,
+      "loss": 0.1437,
+      "step": 370
+    },
+    {
+      "epoch": 0.7972724888539208,
+      "grad_norm": 0.11975102126598358,
+      "learning_rate": 0.0001410534419133778,
+      "loss": 0.1357,
+      "step": 380
+    },
+    {
+      "epoch": 0.8182533438237608,
+      "grad_norm": 0.09955570101737976,
+      "learning_rate": 0.00013786753617790404,
+      "loss": 0.1446,
+      "step": 390
+    },
+    {
+      "epoch": 0.8182533438237608,
+      "eval_loss": 0.13151544332504272,
+      "eval_runtime": 53.6082,
+      "eval_samples_per_second": 3.749,
+      "eval_steps_per_second": 3.749,
+      "step": 390
+    },
+    {
+      "epoch": 0.8392341987936008,
+      "grad_norm": 0.11849252134561539,
+      "learning_rate": 0.00013463610366787392,
+      "loss": 0.1452,
+      "step": 400
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.10621926933526993,
+      "learning_rate": 0.00013136302941818085,
+      "loss": 0.1411,
+      "step": 410
+    },
+    {
+      "epoch": 0.8811959087332809,
+      "grad_norm": 0.09327146410942078,
+      "learning_rate": 0.00012805224852808163,
+      "loss": 0.1391,
+      "step": 420
+    },
+    {
+      "epoch": 0.8811959087332809,
+      "eval_loss": 0.13071787357330322,
+      "eval_runtime": 53.9186,
+      "eval_samples_per_second": 3.728,
+      "eval_steps_per_second": 3.728,
+      "step": 420
+    },
+    {
+      "epoch": 0.9021767637031209,
+      "grad_norm": 0.5398991703987122,
+      "learning_rate": 0.00012470774143016853,
+      "loss": 0.1399,
+      "step": 430
+    },
+    {
+      "epoch": 0.923157618672961,
+      "grad_norm": 0.18647532165050507,
+      "learning_rate": 0.00012133352910483838,
+      "loss": 0.1399,
+      "step": 440
+    },
+    {
+      "epoch": 0.9441384736428009,
+      "grad_norm": 0.16210441291332245,
+      "learning_rate": 0.0001179336682460128,
+      "loss": 0.1509,
+      "step": 450
+    },
+    {
+      "epoch": 0.9441384736428009,
+      "eval_loss": 0.13233241438865662,
+      "eval_runtime": 53.9437,
+      "eval_samples_per_second": 3.726,
+      "eval_steps_per_second": 3.726,
+      "step": 450
+    },
+    {
+      "epoch": 0.9651193286126409,
+      "grad_norm": 0.09105144441127777,
+      "learning_rate": 0.00011451224638392129,
+      "loss": 0.1428,
+      "step": 460
+    },
+    {
+      "epoch": 0.986100183582481,
+      "grad_norm": 0.08386187255382538,
+      "learning_rate": 0.0001110733769708108,
+      "loss": 0.14,
+      "step": 470
+    },
+    {
+      "epoch": 1.006294256490952,
+      "grad_norm": 0.07673283666372299,
+      "learning_rate": 0.00010762119443549035,
+      "loss": 0.142,
+      "step": 480
+    },
+    {
+      "epoch": 1.006294256490952,
+      "eval_loss": 0.1293467879295349,
+      "eval_runtime": 53.6668,
+      "eval_samples_per_second": 3.745,
+      "eval_steps_per_second": 3.745,
+      "step": 480
+    },
+    {
+      "epoch": 1.027275111460792,
+      "grad_norm": 0.09950114041566849,
+      "learning_rate": 0.00010415984921265609,
+      "loss": 0.1365,
+      "step": 490
+    },
+    {
+      "epoch": 1.0482559664306321,
+      "grad_norm": 0.08757766336202621,
+      "learning_rate": 0.00010069350275297337,
+      "loss": 0.1297,
+      "step": 500
+    },
+    {
+      "epoch": 1.0692368214004722,
+      "grad_norm": 0.08058227598667145,
+      "learning_rate": 9.722632251991444e-05,
+      "loss": 0.1258,
+      "step": 510
+    },
+    {
+      "epoch": 1.0692368214004722,
+      "eval_loss": 0.1290971338748932,
+      "eval_runtime": 53.9631,
+      "eval_samples_per_second": 3.725,
+      "eval_steps_per_second": 3.725,
+      "step": 510
+    },
+    {
+      "epoch": 1.0902176763703122,
+      "grad_norm": 0.14287236332893372,
+      "learning_rate": 9.376247697936719e-05,
+      "loss": 0.1405,
+      "step": 520
+    },
+    {
+      "epoch": 1.1111985313401522,
+      "grad_norm": 0.10073138028383255,
+      "learning_rate": 9.030613058803881e-05,
+      "loss": 0.1372,
+      "step": 530
+    },
+    {
+      "epoch": 1.132179386309992,
+      "grad_norm": 0.09560772776603699,
+      "learning_rate": 8.686143878667965e-05,
+      "loss": 0.1344,
+      "step": 540
+    },
+    {
+      "epoch": 1.132179386309992,
+      "eval_loss": 0.1287485510110855,
+      "eval_runtime": 53.9488,
+      "eval_samples_per_second": 3.726,
+      "eval_steps_per_second": 3.726,
+      "step": 540
+    },
+    {
+      "epoch": 1.153160241279832,
+      "grad_norm": 0.09153210371732712,
+      "learning_rate": 8.343254300414628e-05,
+      "loss": 0.1379,
+      "step": 550
+    },
+    {
+      "epoch": 1.1741410962496721,
+      "grad_norm": 0.0932949036359787,
+      "learning_rate": 8.002356567831103e-05,
+      "loss": 0.1361,
+      "step": 560
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "grad_norm": 0.1091330498456955,
+      "learning_rate": 7.663860529980317e-05,
+      "loss": 0.1356,
+      "step": 570
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "eval_loss": 0.13008803129196167,
+      "eval_runtime": 53.6432,
+      "eval_samples_per_second": 3.747,
+      "eval_steps_per_second": 3.747,
+      "step": 570
+    },
+    {
+      "epoch": 1.2161028061893522,
+      "grad_norm": 0.08824314922094345,
+      "learning_rate": 7.328173148454151e-05,
+      "loss": 0.1335,
+      "step": 580
+    },
+    {
+      "epoch": 1.2370836611591922,
+      "grad_norm": 0.12611347436904907,
+      "learning_rate": 6.99569800809816e-05,
+      "loss": 0.1353,
+      "step": 590
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 0.08815793693065643,
+      "learning_rate": 6.66683483179608e-05,
+      "loss": 0.1365,
+      "step": 600
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "eval_loss": 0.12925004959106445,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 3.747,
+      "eval_steps_per_second": 3.747,
+      "step": 600
+    },
+    {
+      "epoch": 1.2790453710988723,
+      "grad_norm": 0.12618786096572876,
+      "learning_rate": 6.341978999897365e-05,
+      "loss": 0.1408,
+      "step": 610
+    },
+    {
+      "epoch": 1.3000262260687123,
+      "grad_norm": 0.0881665050983429,
+      "learning_rate": 6.021521074865678e-05,
+      "loss": 0.1384,
+      "step": 620
+    },
+    {
+      "epoch": 1.3210070810385524,
+      "grad_norm": 0.08780647069215775,
+      "learning_rate": 5.705846331719675e-05,
+      "loss": 0.138,
+      "step": 630
+    },
+    {
+      "epoch": 1.3210070810385524,
+      "eval_loss": 0.12802067399024963,
+      "eval_runtime": 53.8068,
+      "eval_samples_per_second": 3.736,
+      "eval_steps_per_second": 3.736,
+      "step": 630
+    },
+    {
+      "epoch": 1.3419879360083924,
+      "grad_norm": 0.08264625817537308,
+      "learning_rate": 5.395334294830765e-05,
+      "loss": 0.1376,
+      "step": 640
+    },
+    {
+      "epoch": 1.3629687909782324,
+      "grad_norm": 0.08895017951726913,
+      "learning_rate": 5.090358281634594e-05,
+      "loss": 0.1325,
+      "step": 650
+    },
+    {
+      "epoch": 1.3839496459480725,
+      "grad_norm": 0.08006913214921951,
+      "learning_rate": 4.791284953804969e-05,
+      "loss": 0.1336,
+      "step": 660
+    },
+    {
+      "epoch": 1.3839496459480725,
+      "eval_loss": 0.1273050308227539,
+      "eval_runtime": 53.8944,
+      "eval_samples_per_second": 3.73,
+      "eval_steps_per_second": 3.73,
+      "step": 660
+    },
+    {
+      "epoch": 1.4049305009179123,
+      "grad_norm": 0.09627630561590195,
+      "learning_rate": 4.498473876429726e-05,
+      "loss": 0.1341,
+      "step": 670
+    },
+    {
+      "epoch": 1.4259113558877523,
+      "grad_norm": 0.08036801964044571,
+      "learning_rate": 4.21227708571858e-05,
+      "loss": 0.1419,
+      "step": 680
+    },
+    {
+      "epoch": 1.4468922108575923,
+      "grad_norm": 0.1135723665356636,
+      "learning_rate": 3.93303866576267e-05,
+      "loss": 0.13,
+      "step": 690
+    },
+    {
+      "epoch": 1.4468922108575923,
+      "eval_loss": 0.12765151262283325,
+      "eval_runtime": 53.9209,
+      "eval_samples_per_second": 3.728,
+      "eval_steps_per_second": 3.728,
+      "step": 690
+    },
+    {
+      "epoch": 1.4678730658274324,
+      "grad_norm": 0.07758687436580658,
+      "learning_rate": 3.6610943348546526e-05,
+      "loss": 0.1427,
+      "step": 700
+    },
+    {
+      "epoch": 1.4888539207972724,
+      "grad_norm": 0.09151093661785126,
+      "learning_rate": 3.3967710418666984e-05,
+      "loss": 0.1372,
+      "step": 710
+    },
+    {
+      "epoch": 1.5098347757671124,
+      "grad_norm": 0.10960382223129272,
+      "learning_rate": 3.1403865731716266e-05,
+      "loss": 0.134,
+      "step": 720
+    },
+    {
+      "epoch": 1.5098347757671124,
+      "eval_loss": 0.12656451761722565,
+      "eval_runtime": 53.601,
+      "eval_samples_per_second": 3.75,
+      "eval_steps_per_second": 3.75,
+      "step": 720
+    },
+    {
+      "epoch": 1.5308156307369525,
+      "grad_norm": 0.10491708666086197,
+      "learning_rate": 2.892249170579826e-05,
+      "loss": 0.1341,
+      "step": 730
+    },
+    {
+      "epoch": 1.5517964857067925,
+      "grad_norm": 0.09089571982622147,
+      "learning_rate": 2.652657160751193e-05,
+      "loss": 0.1377,
+      "step": 740
+    },
+    {
+      "epoch": 1.5727773406766326,
+      "grad_norm": 0.07756100594997406,
+      "learning_rate": 2.4218985965277675e-05,
+      "loss": 0.1325,
+      "step": 750
+    },
+    {
+      "epoch": 1.5727773406766326,
+      "eval_loss": 0.12670381367206573,
+      "eval_runtime": 53.6584,
+      "eval_samples_per_second": 3.746,
+      "eval_steps_per_second": 3.746,
+      "step": 750
+    },
+    {
+      "epoch": 1.5937581956464726,
+      "grad_norm": 0.10038470476865768,
+      "learning_rate": 2.2002509106181624e-05,
+      "loss": 0.1275,
+      "step": 760
+    },
+    {
+      "epoch": 1.6147390506163126,
+      "grad_norm": 0.09714746475219727,
+      "learning_rate": 1.9879805820502174e-05,
+      "loss": 0.138,
+      "step": 770
+    },
+    {
+      "epoch": 1.6357199055861527,
+      "grad_norm": 0.10250572115182877,
+      "learning_rate": 1.785342815792862e-05,
+      "loss": 0.1337,
+      "step": 780
+    },
+    {
+      "epoch": 1.6357199055861527,
+      "eval_loss": 0.12649498879909515,
+      "eval_runtime": 53.9776,
+      "eval_samples_per_second": 3.724,
+      "eval_steps_per_second": 3.724,
+      "step": 780
+    },
+    {
+      "epoch": 1.6567007605559927,
+      "grad_norm": 0.10221794247627258,
+      "learning_rate": 1.5925812359323745e-05,
+      "loss": 0.138,
+      "step": 790
+    },
+    {
+      "epoch": 1.6776816155258327,
+      "grad_norm": 0.08815432339906693,
+      "learning_rate": 1.4099275927719235e-05,
+      "loss": 0.1308,
+      "step": 800
+    },
+    {
+      "epoch": 1.6986624704956728,
+      "grad_norm": 0.08850682526826859,
+      "learning_rate": 1.2376014842065265e-05,
+      "loss": 0.1385,
+      "step": 810
+    },
+    {
+      "epoch": 1.6986624704956728,
+      "eval_loss": 0.12599113583564758,
+      "eval_runtime": 53.6591,
+      "eval_samples_per_second": 3.746,
+      "eval_steps_per_second": 3.746,
+      "step": 810
+    },
+    {
+      "epoch": 1.7196433254655128,
+      "grad_norm": 0.0861755833029747,
+      "learning_rate": 1.0758100917083991e-05,
+      "loss": 0.1321,
+      "step": 820
+    },
+    {
+      "epoch": 1.7406241804353528,
+      "grad_norm": 0.09379922598600388,
+      "learning_rate": 9.247479312401641e-06,
+      "loss": 0.1288,
+      "step": 830
+    },
+    {
+      "epoch": 1.7616050354051929,
+      "grad_norm": 0.11254911869764328,
+      "learning_rate": 7.845966193952824e-06,
+      "loss": 0.126,
+      "step": 840
+    },
+    {
+      "epoch": 1.7616050354051929,
+      "eval_loss": 0.12584222853183746,
+      "eval_runtime": 54.0496,
+      "eval_samples_per_second": 3.719,
+      "eval_steps_per_second": 3.719,
+      "step": 840
+    },
+    {
+      "epoch": 1.782585890375033,
+      "grad_norm": 0.09247393906116486,
+      "learning_rate": 6.555246550469907e-06,
+      "loss": 0.1365,
+      "step": 850
+    },
+    {
+      "epoch": 1.803566745344873,
+      "grad_norm": 0.11225956678390503,
+      "learning_rate": 5.376872167681635e-06,
+      "loss": 0.1325,
+      "step": 860
+    },
+    {
+      "epoch": 1.824547600314713,
+      "grad_norm": 0.08813902735710144,
+      "learning_rate": 4.312259762657145e-06,
+      "loss": 0.1321,
+      "step": 870
+    },
+    {
+      "epoch": 1.824547600314713,
+      "eval_loss": 0.12573501467704773,
+      "eval_runtime": 53.8714,
+      "eval_samples_per_second": 3.731,
+      "eval_steps_per_second": 3.731,
+      "step": 870
+    },
+    {
+      "epoch": 1.845528455284553,
+      "grad_norm": 0.09407710283994675,
+      "learning_rate": 3.3626892805379562e-06,
+      "loss": 0.1295,
+      "step": 880
+    },
+    {
+      "epoch": 1.8665093102543928,
+      "grad_norm": 0.10119906812906265,
+      "learning_rate": 2.5293023557061644e-06,
+      "loss": 0.1259,
+      "step": 890
+    },
+    {
+      "epoch": 1.8874901652242329,
+      "grad_norm": 0.12075681984424591,
+      "learning_rate": 1.8131009392384323e-06,
+      "loss": 0.1338,
+      "step": 900
+    },
+    {
+      "epoch": 1.8874901652242329,
+      "eval_loss": 0.12563975155353546,
+      "eval_runtime": 53.9437,
+      "eval_samples_per_second": 3.726,
+      "eval_steps_per_second": 3.726,
+      "step": 900
+    },
+    {
+      "epoch": 1.9084710201940729,
+      "grad_norm": 0.09039806574583054,
+      "learning_rate": 1.2149460942964098e-06,
+      "loss": 0.1304,
+      "step": 910
+    },
+    {
+      "epoch": 1.929451875163913,
+      "grad_norm": 0.096430204808712,
+      "learning_rate": 7.35556960901429e-07,
+      "loss": 0.1317,
+      "step": 920
+    },
+    {
+      "epoch": 1.950432730133753,
+      "grad_norm": 0.09920115768909454,
+      "learning_rate": 3.755098913384325e-07,
+      "loss": 0.1291,
+      "step": 930
+    },
+    {
+      "epoch": 1.950432730133753,
+      "eval_loss": 0.12557660043239594,
+      "eval_runtime": 53.8013,
+      "eval_samples_per_second": 3.736,
+      "eval_steps_per_second": 3.736,
+      "step": 930
+    },
+    {
+      "epoch": 1.971413585103593,
+      "grad_norm": 0.09501874446868896,
+      "learning_rate": 1.3523775722834587e-07,
+      "loss": 0.1356,
+      "step": 940
+    },
+    {
+      "epoch": 1.992394440073433,
+      "grad_norm": 0.09108738601207733,
+      "learning_rate": 1.502942910212024e-08,
+      "loss": 0.128,
+      "step": 950
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 954,
+  "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": 1.5910740277581005e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-954/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c440813fc825035a683e2f0277799f1d9de906c1a6c2d0246e8e9788def58820
+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:aa2d17f255701731847c074e82fd864ddef5bca1dbe7140d03cbfeb778478ceb
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5110780f538f06183337d50399e4f05634954e20d8b58ae23a53ada2637d9b7f
+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
+}