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-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1422/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": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_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 sha256:280765cb5c316d2ef927e44950b07a9adc84f0109075b234f0b0bf876b5ce9a6
+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-1400/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-1400/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": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62662e07c712b25ac393ba2dfc80e9a6120e02cd6db0d62ae4be99e81d6c2317
+size 528550256

checkpoint-1400/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-1400/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-1400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b831813024f23e1aaacbc824393653d2ba96e720631c224e839a6302457a427e
+size 1057397963

checkpoint-1400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d11748442b1ae118ac7a7cab9f2de52cd59f3242f8f10e09cadce89c68d455d
+size 14645

checkpoint-1400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7956269cda78a90e0c08970c0b788e5e609ffb0af96e0459804cb683f709be6
+size 1465

checkpoint-1400/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-1400/tokenizer.json

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

checkpoint-1400/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-1400/trainer_state.json

@@ -0,0 +1,1382 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9538380374571354,
+  "eval_steps": 30,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021102611448166712,
+      "grad_norm": 9.9413423538208,
+      "learning_rate": 1.2587412587412589e-05,
+      "loss": 2.7146,
+      "step": 10
+    },
+    {
+      "epoch": 0.042205222896333425,
+      "grad_norm": 1.0188082456588745,
+      "learning_rate": 2.6573426573426574e-05,
+      "loss": 1.1603,
+      "step": 20
+    },
+    {
+      "epoch": 0.06330783434450013,
+      "grad_norm": 0.9419231414794922,
+      "learning_rate": 4.055944055944056e-05,
+      "loss": 0.7015,
+      "step": 30
+    },
+    {
+      "epoch": 0.06330783434450013,
+      "eval_loss": 0.5692373514175415,
+      "eval_runtime": 43.1831,
+      "eval_samples_per_second": 4.631,
+      "eval_steps_per_second": 4.631,
+      "step": 30
+    },
+    {
+      "epoch": 0.08441044579266685,
+      "grad_norm": 0.7294736504554749,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.5017,
+      "step": 40
+    },
+    {
+      "epoch": 0.10551305724083355,
+      "grad_norm": 0.7030153870582581,
+      "learning_rate": 6.853146853146853e-05,
+      "loss": 0.3731,
+      "step": 50
+    },
+    {
+      "epoch": 0.12661566868900026,
+      "grad_norm": 0.5342110395431519,
+      "learning_rate": 8.251748251748252e-05,
+      "loss": 0.3089,
+      "step": 60
+    },
+    {
+      "epoch": 0.12661566868900026,
+      "eval_loss": 0.27030423283576965,
+      "eval_runtime": 42.6998,
+      "eval_samples_per_second": 4.684,
+      "eval_steps_per_second": 4.684,
+      "step": 60
+    },
+    {
+      "epoch": 0.14771828013716698,
+      "grad_norm": 0.5539342761039734,
+      "learning_rate": 9.65034965034965e-05,
+      "loss": 0.2545,
+      "step": 70
+    },
+    {
+      "epoch": 0.1688208915853337,
+      "grad_norm": 0.7872066497802734,
+      "learning_rate": 0.00011048951048951048,
+      "loss": 0.2126,
+      "step": 80
+    },
+    {
+      "epoch": 0.1899235030335004,
+      "grad_norm": 0.5423749089241028,
+      "learning_rate": 0.00012447552447552448,
+      "loss": 0.2035,
+      "step": 90
+    },
+    {
+      "epoch": 0.1899235030335004,
+      "eval_loss": 0.1911192387342453,
+      "eval_runtime": 42.5187,
+      "eval_samples_per_second": 4.704,
+      "eval_steps_per_second": 4.704,
+      "step": 90
+    },
+    {
+      "epoch": 0.2110261144816671,
+      "grad_norm": 0.34928596019744873,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.1822,
+      "step": 100
+    },
+    {
+      "epoch": 0.23212872592983383,
+      "grad_norm": 0.36143162846565247,
+      "learning_rate": 0.00015244755244755244,
+      "loss": 0.1673,
+      "step": 110
+    },
+    {
+      "epoch": 0.2532313373780005,
+      "grad_norm": 0.5100098252296448,
+      "learning_rate": 0.00016643356643356646,
+      "loss": 0.1844,
+      "step": 120
+    },
+    {
+      "epoch": 0.2532313373780005,
+      "eval_loss": 0.1640024334192276,
+      "eval_runtime": 42.7294,
+      "eval_samples_per_second": 4.681,
+      "eval_steps_per_second": 4.681,
+      "step": 120
+    },
+    {
+      "epoch": 0.27433394882616724,
+      "grad_norm": 0.5207167267799377,
+      "learning_rate": 0.00018041958041958042,
+      "loss": 0.1677,
+      "step": 130
+    },
+    {
+      "epoch": 0.29543656027433396,
+      "grad_norm": 0.3435003459453583,
+      "learning_rate": 0.0001944055944055944,
+      "loss": 0.1575,
+      "step": 140
+    },
+    {
+      "epoch": 0.3165391717225007,
+      "grad_norm": 0.4177781045436859,
+      "learning_rate": 0.0001999891401631506,
+      "loss": 0.1656,
+      "step": 150
+    },
+    {
+      "epoch": 0.3165391717225007,
+      "eval_loss": 0.1460759937763214,
+      "eval_runtime": 42.6392,
+      "eval_samples_per_second": 4.691,
+      "eval_steps_per_second": 4.691,
+      "step": 150
+    },
+    {
+      "epoch": 0.3376417831706674,
+      "grad_norm": 0.40304410457611084,
+      "learning_rate": 0.0001999227830351936,
+      "loss": 0.1466,
+      "step": 160
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.28438979387283325,
+      "learning_rate": 0.00019979614200701668,
+      "loss": 0.1466,
+      "step": 170
+    },
+    {
+      "epoch": 0.3798470060670008,
+      "grad_norm": 0.3558550179004669,
+      "learning_rate": 0.00019960929348176708,
+      "loss": 0.1505,
+      "step": 180
+    },
+    {
+      "epoch": 0.3798470060670008,
+      "eval_loss": 0.1364826261997223,
+      "eval_runtime": 42.7387,
+      "eval_samples_per_second": 4.68,
+      "eval_steps_per_second": 4.68,
+      "step": 180
+    },
+    {
+      "epoch": 0.4009496175151675,
+      "grad_norm": 0.7208640575408936,
+      "learning_rate": 0.0001993623501860674,
+      "loss": 0.1442,
+      "step": 190
+    },
+    {
+      "epoch": 0.4220522289633342,
+      "grad_norm": 0.22139093279838562,
+      "learning_rate": 0.00019905546110200704,
+      "loss": 0.153,
+      "step": 200
+    },
+    {
+      "epoch": 0.44315484041150094,
+      "grad_norm": 0.39185455441474915,
+      "learning_rate": 0.00019868881137726066,
+      "loss": 0.1395,
+      "step": 210
+    },
+    {
+      "epoch": 0.44315484041150094,
+      "eval_loss": 0.1368705779314041,
+      "eval_runtime": 42.4935,
+      "eval_samples_per_second": 4.707,
+      "eval_steps_per_second": 4.707,
+      "step": 210
+    },
+    {
+      "epoch": 0.46425745185966766,
+      "grad_norm": 0.15956981480121613,
+      "learning_rate": 0.0001982626222133876,
+      "loss": 0.142,
+      "step": 220
+    },
+    {
+      "epoch": 0.4853600633078343,
+      "grad_norm": 0.6167592406272888,
+      "learning_rate": 0.00019777715073237997,
+      "loss": 0.1478,
+      "step": 230
+    },
+    {
+      "epoch": 0.506462674756001,
+      "grad_norm": 0.34357866644859314,
+      "learning_rate": 0.00019723268982153966,
+      "loss": 0.145,
+      "step": 240
+    },
+    {
+      "epoch": 0.506462674756001,
+      "eval_loss": 0.13663160800933838,
+      "eval_runtime": 42.7492,
+      "eval_samples_per_second": 4.678,
+      "eval_steps_per_second": 4.678,
+      "step": 240
+    },
+    {
+      "epoch": 0.5275652862041678,
+      "grad_norm": 0.45330700278282166,
+      "learning_rate": 0.000196629567956778,
+      "loss": 0.1541,
+      "step": 250
+    },
+    {
+      "epoch": 0.5486678976523345,
+      "grad_norm": 0.3859712779521942,
+      "learning_rate": 0.00019596814900444475,
+      "loss": 0.1608,
+      "step": 260
+    },
+    {
+      "epoch": 0.5697705091005012,
+      "grad_norm": 0.14809803664684296,
+      "learning_rate": 0.00019524883200180558,
+      "loss": 0.1355,
+      "step": 270
+    },
+    {
+      "epoch": 0.5697705091005012,
+      "eval_loss": 0.132829487323761,
+      "eval_runtime": 42.6204,
+      "eval_samples_per_second": 4.693,
+      "eval_steps_per_second": 4.693,
+      "step": 270
+    },
+    {
+      "epoch": 0.5908731205486679,
+      "grad_norm": 0.1790543645620346,
+      "learning_rate": 0.00019447205091630115,
+      "loss": 0.1365,
+      "step": 280
+    },
+    {
+      "epoch": 0.6119757319968346,
+      "grad_norm": 0.4073638617992401,
+      "learning_rate": 0.00019363827438373233,
+      "loss": 0.1423,
+      "step": 290
+    },
+    {
+      "epoch": 0.6330783434450014,
+      "grad_norm": 0.13269440829753876,
+      "learning_rate": 0.0001927480054255299,
+      "loss": 0.1402,
+      "step": 300
+    },
+    {
+      "epoch": 0.6330783434450014,
+      "eval_loss": 0.1258172243833542,
+      "eval_runtime": 43.0037,
+      "eval_samples_per_second": 4.651,
+      "eval_steps_per_second": 4.651,
+      "step": 300
+    },
+    {
+      "epoch": 0.6541809548931681,
+      "grad_norm": 0.15398648381233215,
+      "learning_rate": 0.00019180178114527942,
+      "loss": 0.1313,
+      "step": 310
+    },
+    {
+      "epoch": 0.6752835663413348,
+      "grad_norm": 0.18669337034225464,
+      "learning_rate": 0.00019080017240468393,
+      "loss": 0.1441,
+      "step": 320
+    },
+    {
+      "epoch": 0.6963861777895014,
+      "grad_norm": 0.2585830092430115,
+      "learning_rate": 0.00018974378347916035,
+      "loss": 0.1338,
+      "step": 330
+    },
+    {
+      "epoch": 0.6963861777895014,
+      "eval_loss": 0.12394458800554276,
+      "eval_runtime": 42.955,
+      "eval_samples_per_second": 4.656,
+      "eval_steps_per_second": 4.656,
+      "step": 330
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.15704883635044098,
+      "learning_rate": 0.00018863325169327718,
+      "loss": 0.1254,
+      "step": 340
+    },
+    {
+      "epoch": 0.7385914006858348,
+      "grad_norm": 0.12733563780784607,
+      "learning_rate": 0.00018746924703625344,
+      "loss": 0.137,
+      "step": 350
+    },
+    {
+      "epoch": 0.7596940121340016,
+      "grad_norm": 0.2758557200431824,
+      "learning_rate": 0.000186252471757751,
+      "loss": 0.1329,
+      "step": 360
+    },
+    {
+      "epoch": 0.7596940121340016,
+      "eval_loss": 0.12415071576833725,
+      "eval_runtime": 42.9293,
+      "eval_samples_per_second": 4.659,
+      "eval_steps_per_second": 4.659,
+      "step": 360
+    },
+    {
+      "epoch": 0.7807966235821683,
+      "grad_norm": 0.20145803689956665,
+      "learning_rate": 0.00018498365994420394,
+      "loss": 0.1298,
+      "step": 370
+    },
+    {
+      "epoch": 0.801899235030335,
+      "grad_norm": 0.13150104880332947,
+      "learning_rate": 0.0001836635770759406,
+      "loss": 0.1401,
+      "step": 380
+    },
+    {
+      "epoch": 0.8230018464785017,
+      "grad_norm": 0.14411461353302002,
+      "learning_rate": 0.0001822930195653656,
+      "loss": 0.131,
+      "step": 390
+    },
+    {
+      "epoch": 0.8230018464785017,
+      "eval_loss": 0.12136167287826538,
+      "eval_runtime": 43.0344,
+      "eval_samples_per_second": 4.647,
+      "eval_steps_per_second": 4.647,
+      "step": 390
+    },
+    {
+      "epoch": 0.8441044579266684,
+      "grad_norm": 0.11295611411333084,
+      "learning_rate": 0.00018087281427648025,
+      "loss": 0.1291,
+      "step": 400
+    },
+    {
+      "epoch": 0.8652070693748352,
+      "grad_norm": 0.11478397250175476,
+      "learning_rate": 0.00017940381802603188,
+      "loss": 0.1254,
+      "step": 410
+    },
+    {
+      "epoch": 0.8863096808230019,
+      "grad_norm": 0.11431597918272018,
+      "learning_rate": 0.00017788691706659154,
+      "loss": 0.12,
+      "step": 420
+    },
+    {
+      "epoch": 0.8863096808230019,
+      "eval_loss": 0.124061718583107,
+      "eval_runtime": 43.0846,
+      "eval_samples_per_second": 4.642,
+      "eval_steps_per_second": 4.642,
+      "step": 420
+    },
+    {
+      "epoch": 0.9074122922711686,
+      "grad_norm": 0.1042429730296135,
+      "learning_rate": 0.00017632302655187402,
+      "loss": 0.1403,
+      "step": 430
+    },
+    {
+      "epoch": 0.9285149037193353,
+      "grad_norm": 0.11291960626840591,
+      "learning_rate": 0.00017471308998462097,
+      "loss": 0.1418,
+      "step": 440
+    },
+    {
+      "epoch": 0.9496175151675019,
+      "grad_norm": 0.11094669252634048,
+      "learning_rate": 0.00017305807864738106,
+      "loss": 0.1306,
+      "step": 450
+    },
+    {
+      "epoch": 0.9496175151675019,
+      "eval_loss": 0.12037019431591034,
+      "eval_runtime": 42.9632,
+      "eval_samples_per_second": 4.655,
+      "eval_steps_per_second": 4.655,
+      "step": 450
+    },
+    {
+      "epoch": 0.9707201266156686,
+      "grad_norm": 0.10620168596506119,
+      "learning_rate": 0.00017135899101653065,
+      "loss": 0.1163,
+      "step": 460
+    },
+    {
+      "epoch": 0.9918227380638354,
+      "grad_norm": 0.10655219852924347,
+      "learning_rate": 0.000169616852159888,
+      "loss": 0.1336,
+      "step": 470
+    },
+    {
+      "epoch": 1.0126615668689,
+      "grad_norm": 0.12968231737613678,
+      "learning_rate": 0.00016783271311828494,
+      "loss": 0.1284,
+      "step": 480
+    },
+    {
+      "epoch": 1.0126615668689,
+      "eval_loss": 0.12156519293785095,
+      "eval_runtime": 42.9531,
+      "eval_samples_per_second": 4.656,
+      "eval_steps_per_second": 4.656,
+      "step": 480
+    },
+    {
+      "epoch": 1.0337641783170668,
+      "grad_norm": 0.11897017806768417,
+      "learning_rate": 0.00016600765027146894,
+      "loss": 0.129,
+      "step": 490
+    },
+    {
+      "epoch": 1.0548667897652335,
+      "grad_norm": 0.127396360039711,
+      "learning_rate": 0.00016414276468871777,
+      "loss": 0.1291,
+      "step": 500
+    },
+    {
+      "epoch": 1.0759694012134002,
+      "grad_norm": 0.11823620647192001,
+      "learning_rate": 0.00016223918146455918,
+      "loss": 0.131,
+      "step": 510
+    },
+    {
+      "epoch": 1.0759694012134002,
+      "eval_loss": 0.12118449807167053,
+      "eval_runtime": 42.9587,
+      "eval_samples_per_second": 4.656,
+      "eval_steps_per_second": 4.656,
+      "step": 510
+    },
+    {
+      "epoch": 1.097072012661567,
+      "grad_norm": 0.10815704613924026,
+      "learning_rate": 0.00016029804903999596,
+      "loss": 0.133,
+      "step": 520
+    },
+    {
+      "epoch": 1.1181746241097337,
+      "grad_norm": 0.10010864585638046,
+      "learning_rate": 0.0001583205385096457,
+      "loss": 0.1232,
+      "step": 530
+    },
+    {
+      "epoch": 1.1392772355579002,
+      "grad_norm": 0.12100092321634293,
+      "learning_rate": 0.00015630784291521403,
+      "loss": 0.1323,
+      "step": 540
+    },
+    {
+      "epoch": 1.1392772355579002,
+      "eval_loss": 0.11961612850427628,
+      "eval_runtime": 42.905,
+      "eval_samples_per_second": 4.661,
+      "eval_steps_per_second": 4.661,
+      "step": 540
+    },
+    {
+      "epoch": 1.160379847006067,
+      "grad_norm": 0.08296310156583786,
+      "learning_rate": 0.00015426117652572648,
+      "loss": 0.1273,
+      "step": 550
+    },
+    {
+      "epoch": 1.1814824584542336,
+      "grad_norm": 0.10136981308460236,
+      "learning_rate": 0.00015218177410495422,
+      "loss": 0.1254,
+      "step": 560
+    },
+    {
+      "epoch": 1.2025850699024003,
+      "grad_norm": 0.09671589732170105,
+      "learning_rate": 0.00015007089016647512,
+      "loss": 0.1235,
+      "step": 570
+    },
+    {
+      "epoch": 1.2025850699024003,
+      "eval_loss": 0.11970534175634384,
+      "eval_runtime": 42.9709,
+      "eval_samples_per_second": 4.654,
+      "eval_steps_per_second": 4.654,
+      "step": 570
+    },
+    {
+      "epoch": 1.223687681350567,
+      "grad_norm": 0.09472666680812836,
+      "learning_rate": 0.00014792979821681948,
+      "loss": 0.1237,
+      "step": 580
+    },
+    {
+      "epoch": 1.2447902927987338,
+      "grad_norm": 0.16830433905124664,
+      "learning_rate": 0.0001457597899871574,
+      "loss": 0.127,
+      "step": 590
+    },
+    {
+      "epoch": 1.2658929042469005,
+      "grad_norm": 0.08856591582298279,
+      "learning_rate": 0.00014356217465399124,
+      "loss": 0.123,
+      "step": 600
+    },
+    {
+      "epoch": 1.2658929042469005,
+      "eval_loss": 0.11881241202354431,
+      "eval_runtime": 42.9169,
+      "eval_samples_per_second": 4.66,
+      "eval_steps_per_second": 4.66,
+      "step": 600
+    },
+    {
+      "epoch": 1.2869955156950672,
+      "grad_norm": 0.11379825323820114,
+      "learning_rate": 0.00014133827804932282,
+      "loss": 0.1242,
+      "step": 610
+    },
+    {
+      "epoch": 1.308098127143234,
+      "grad_norm": 0.08634220063686371,
+      "learning_rate": 0.0001390894418607728,
+      "loss": 0.1289,
+      "step": 620
+    },
+    {
+      "epoch": 1.3292007385914006,
+      "grad_norm": 0.08761777728796005,
+      "learning_rate": 0.0001368170228221339,
+      "loss": 0.1209,
+      "step": 630
+    },
+    {
+      "epoch": 1.3292007385914006,
+      "eval_loss": 0.11858396232128143,
+      "eval_runtime": 42.8741,
+      "eval_samples_per_second": 4.665,
+      "eval_steps_per_second": 4.665,
+      "step": 630
+    },
+    {
+      "epoch": 1.3503033500395674,
+      "grad_norm": 0.09664271026849747,
+      "learning_rate": 0.00013452239189484666,
+      "loss": 0.1247,
+      "step": 640
+    },
+    {
+      "epoch": 1.371405961487734,
+      "grad_norm": 0.1144590675830841,
+      "learning_rate": 0.0001322069334408921,
+      "loss": 0.1268,
+      "step": 650
+    },
+    {
+      "epoch": 1.3925085729359008,
+      "grad_norm": 0.1012091338634491,
+      "learning_rate": 0.00012987204438759904,
+      "loss": 0.1256,
+      "step": 660
+    },
+    {
+      "epoch": 1.3925085729359008,
+      "eval_loss": 0.11804136633872986,
+      "eval_runtime": 43.1847,
+      "eval_samples_per_second": 4.631,
+      "eval_steps_per_second": 4.631,
+      "step": 660
+    },
+    {
+      "epoch": 1.4136111843840675,
+      "grad_norm": 0.09839442372322083,
+      "learning_rate": 0.00012751913338487135,
+      "loss": 0.1275,
+      "step": 670
+    },
+    {
+      "epoch": 1.4347137958322342,
+      "grad_norm": 0.30278143286705017,
+      "learning_rate": 0.00012514961995534248,
+      "loss": 0.1241,
+      "step": 680
+    },
+    {
+      "epoch": 1.455816407280401,
+      "grad_norm": 0.07915577292442322,
+      "learning_rate": 0.00012276493363797054,
+      "loss": 0.126,
+      "step": 690
+    },
+    {
+      "epoch": 1.455816407280401,
+      "eval_loss": 0.11796753108501434,
+      "eval_runtime": 43.3648,
+      "eval_samples_per_second": 4.612,
+      "eval_steps_per_second": 4.612,
+      "step": 690
+    },
+    {
+      "epoch": 1.4769190187285677,
+      "grad_norm": 0.09405189752578735,
+      "learning_rate": 0.00012036651312559069,
+      "loss": 0.1218,
+      "step": 700
+    },
+    {
+      "epoch": 1.4980216301767344,
+      "grad_norm": 0.10401446372270584,
+      "learning_rate": 0.00011795580539694441,
+      "loss": 0.1241,
+      "step": 710
+    },
+    {
+      "epoch": 1.5191242416249011,
+      "grad_norm": 0.08657781034708023,
+      "learning_rate": 0.00011553426484371064,
+      "loss": 0.1229,
+      "step": 720
+    },
+    {
+      "epoch": 1.5191242416249011,
+      "eval_loss": 0.11668255180120468,
+      "eval_runtime": 43.2352,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 4.626,
+      "step": 720
+    },
+    {
+      "epoch": 1.5402268530730678,
+      "grad_norm": 0.09666746109724045,
+      "learning_rate": 0.00011310335239306384,
+      "loss": 0.129,
+      "step": 730
+    },
+    {
+      "epoch": 1.5613294645212346,
+      "grad_norm": 0.08991085737943649,
+      "learning_rate": 0.00011066453462628978,
+      "loss": 0.1207,
+      "step": 740
+    },
+    {
+      "epoch": 1.5824320759694013,
+      "grad_norm": 0.08485621958971024,
+      "learning_rate": 0.00010821928289398974,
+      "loss": 0.1175,
+      "step": 750
+    },
+    {
+      "epoch": 1.5824320759694013,
+      "eval_loss": 0.11763760447502136,
+      "eval_runtime": 43.082,
+      "eval_samples_per_second": 4.642,
+      "eval_steps_per_second": 4.642,
+      "step": 750
+    },
+    {
+      "epoch": 1.603534687417568,
+      "grad_norm": 0.08351397514343262,
+      "learning_rate": 0.00010576907242840782,
+      "loss": 0.1318,
+      "step": 760
+    },
+    {
+      "epoch": 1.6246372988657347,
+      "grad_norm": 0.09473424404859543,
+      "learning_rate": 0.00010331538145341579,
+      "loss": 0.1202,
+      "step": 770
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "grad_norm": 0.08496669679880142,
+      "learning_rate": 0.00010085969029269375,
+      "loss": 0.1233,
+      "step": 780
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "eval_loss": 0.11757928878068924,
+      "eval_runtime": 42.9019,
+      "eval_samples_per_second": 4.662,
+      "eval_steps_per_second": 4.662,
+      "step": 780
+    },
+    {
+      "epoch": 1.6668425217620682,
+      "grad_norm": 0.07978235930204391,
+      "learning_rate": 9.84034804766436e-05,
+      "loss": 0.122,
+      "step": 790
+    },
+    {
+      "epoch": 1.6879451332102349,
+      "grad_norm": 0.09555214643478394,
+      "learning_rate": 9.594823384857439e-05,
+      "loss": 0.1233,
+      "step": 800
+    },
+    {
+      "epoch": 1.7090477446584016,
+      "grad_norm": 1.1965069770812988,
+      "learning_rate": 9.34954316706993e-05,
+      "loss": 0.1139,
+      "step": 810
+    },
+    {
+      "epoch": 1.7090477446584016,
+      "eval_loss": 0.1184568777680397,
+      "eval_runtime": 42.9485,
+      "eval_samples_per_second": 4.657,
+      "eval_steps_per_second": 4.657,
+      "step": 810
+    },
+    {
+      "epoch": 1.7301503561065683,
+      "grad_norm": 0.09275703132152557,
+      "learning_rate": 9.104655373048281e-05,
+      "loss": 0.129,
+      "step": 820
+    },
+    {
+      "epoch": 1.751252967554735,
+      "grad_norm": 0.08251888304948807,
+      "learning_rate": 8.860307744787772e-05,
+      "loss": 0.1195,
+      "step": 830
+    },
+    {
+      "epoch": 1.7723555790029017,
+      "grad_norm": 0.20448611676692963,
+      "learning_rate": 8.616647698399065e-05,
+      "loss": 0.1244,
+      "step": 840
+    },
+    {
+      "epoch": 1.7723555790029017,
+      "eval_loss": 0.11751535534858704,
+      "eval_runtime": 43.1584,
+      "eval_samples_per_second": 4.634,
+      "eval_steps_per_second": 4.634,
+      "step": 840
+    },
+    {
+      "epoch": 1.7934581904510685,
+      "grad_norm": 0.09854628890752792,
+      "learning_rate": 8.373822235171327e-05,
+      "loss": 0.1188,
+      "step": 850
+    },
+    {
+      "epoch": 1.8145608018992352,
+      "grad_norm": 0.10301581025123596,
+      "learning_rate": 8.131977852885666e-05,
+      "loss": 0.1275,
+      "step": 860
+    },
+    {
+      "epoch": 1.835663413347402,
+      "grad_norm": 0.11739084124565125,
+      "learning_rate": 7.89126045743228e-05,
+      "loss": 0.122,
+      "step": 870
+    },
+    {
+      "epoch": 1.835663413347402,
+      "eval_loss": 0.11938333511352539,
+      "eval_runtime": 43.0848,
+      "eval_samples_per_second": 4.642,
+      "eval_steps_per_second": 4.642,
+      "step": 870
+    },
+    {
+      "epoch": 1.8567660247955684,
+      "grad_norm": 0.11293812841176987,
+      "learning_rate": 7.651815274784751e-05,
+      "loss": 0.1319,
+      "step": 880
+    },
+    {
+      "epoch": 1.8778686362437351,
+      "grad_norm": 0.11208591610193253,
+      "learning_rate": 7.413786763384491e-05,
+      "loss": 0.1254,
+      "step": 890
+    },
+    {
+      "epoch": 1.8989712476919018,
+      "grad_norm": 0.0833379328250885,
+      "learning_rate": 7.177318526988264e-05,
+      "loss": 0.1214,
+      "step": 900
+    },
+    {
+      "epoch": 1.8989712476919018,
+      "eval_loss": 0.11639796197414398,
+      "eval_runtime": 43.0753,
+      "eval_samples_per_second": 4.643,
+      "eval_steps_per_second": 4.643,
+      "step": 900
+    },
+    {
+      "epoch": 1.9200738591400686,
+      "grad_norm": 0.09288811683654785,
+      "learning_rate": 6.94255322803136e-05,
+      "loss": 0.1283,
+      "step": 910
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.08512190729379654,
+      "learning_rate": 6.709632501558631e-05,
+      "loss": 0.1213,
+      "step": 920
+    },
+    {
+      "epoch": 1.962279082036402,
+      "grad_norm": 0.0763729065656662,
+      "learning_rate": 6.478696869775401e-05,
+      "loss": 0.1269,
+      "step": 930
+    },
+    {
+      "epoch": 1.962279082036402,
+      "eval_loss": 0.11652935296297073,
+      "eval_runtime": 42.9622,
+      "eval_samples_per_second": 4.655,
+      "eval_steps_per_second": 4.655,
+      "step": 930
+    },
+    {
+      "epoch": 1.9833816934845687,
+      "grad_norm": 0.11486316472291946,
+      "learning_rate": 6.249885657269722e-05,
+      "loss": 0.1224,
+      "step": 940
+    },
+    {
+      "epoch": 2.0042205222896334,
+      "grad_norm": 0.07140278816223145,
+      "learning_rate": 6.023336906957188e-05,
+      "loss": 0.1293,
+      "step": 950
+    },
+    {
+      "epoch": 2.0253231337378,
+      "grad_norm": 0.08281326293945312,
+      "learning_rate": 5.7991872967989536e-05,
+      "loss": 0.1198,
+      "step": 960
+    },
+    {
+      "epoch": 2.0253231337378,
+      "eval_loss": 0.11602704972028732,
+      "eval_runtime": 43.3093,
+      "eval_samples_per_second": 4.618,
+      "eval_steps_per_second": 4.618,
+      "step": 960
+    },
+    {
+      "epoch": 2.046425745185967,
+      "grad_norm": 0.09625944495201111,
+      "learning_rate": 5.5775720573432764e-05,
+      "loss": 0.1219,
+      "step": 970
+    },
+    {
+      "epoch": 2.0675283566341336,
+      "grad_norm": 0.10757429152727127,
+      "learning_rate": 5.358624890140263e-05,
+      "loss": 0.1203,
+      "step": 980
+    },
+    {
+      "epoch": 2.0886309680823003,
+      "grad_norm": 0.10341180860996246,
+      "learning_rate": 5.1424778870790645e-05,
+      "loss": 0.1131,
+      "step": 990
+    },
+    {
+      "epoch": 2.0886309680823003,
+      "eval_loss": 0.11575788259506226,
+      "eval_runtime": 43.2104,
+      "eval_samples_per_second": 4.629,
+      "eval_steps_per_second": 4.629,
+      "step": 990
+    },
+    {
+      "epoch": 2.109733579530467,
+      "grad_norm": 0.08683689683675766,
+      "learning_rate": 4.929261450696228e-05,
+      "loss": 0.1221,
+      "step": 1000
+    },
+    {
+      "epoch": 2.1308361909786337,
+      "grad_norm": 0.11907190829515457,
+      "learning_rate": 4.719104215503172e-05,
+      "loss": 0.1252,
+      "step": 1010
+    },
+    {
+      "epoch": 2.1519388024268005,
+      "grad_norm": 0.11070162802934647,
+      "learning_rate": 4.5121329703803935e-05,
+      "loss": 0.1296,
+      "step": 1020
+    },
+    {
+      "epoch": 2.1519388024268005,
+      "eval_loss": 0.11595886200666428,
+      "eval_runtime": 43.3948,
+      "eval_samples_per_second": 4.609,
+      "eval_steps_per_second": 4.609,
+      "step": 1020
+    },
+    {
+      "epoch": 2.173041413874967,
+      "grad_norm": 0.08530761301517487,
+      "learning_rate": 4.308472582085104e-05,
+      "loss": 0.1129,
+      "step": 1030
+    },
+    {
+      "epoch": 2.194144025323134,
+      "grad_norm": 0.09313362836837769,
+      "learning_rate": 4.10824591991852e-05,
+      "loss": 0.118,
+      "step": 1040
+    },
+    {
+      "epoch": 2.2152466367713006,
+      "grad_norm": 0.08985672891139984,
+      "learning_rate": 3.9115737815982024e-05,
+      "loss": 0.1144,
+      "step": 1050
+    },
+    {
+      "epoch": 2.2152466367713006,
+      "eval_loss": 0.11535269021987915,
+      "eval_runtime": 43.4078,
+      "eval_samples_per_second": 4.607,
+      "eval_steps_per_second": 4.607,
+      "step": 1050
+    },
+    {
+      "epoch": 2.2363492482194673,
+      "grad_norm": 0.07902213931083679,
+      "learning_rate": 3.7185748203802175e-05,
+      "loss": 0.1224,
+      "step": 1060
+    },
+    {
+      "epoch": 2.2574518596676336,
+      "grad_norm": 0.10935928672552109,
+      "learning_rate": 3.5293654734750624e-05,
+      "loss": 0.1255,
+      "step": 1070
+    },
+    {
+      "epoch": 2.2785544711158003,
+      "grad_norm": 0.07709987461566925,
+      "learning_rate": 3.344059891800493e-05,
+      "loss": 0.1076,
+      "step": 1080
+    },
+    {
+      "epoch": 2.2785544711158003,
+      "eval_loss": 0.11529315263032913,
+      "eval_runtime": 43.4366,
+      "eval_samples_per_second": 4.604,
+      "eval_steps_per_second": 4.604,
+      "step": 1080
+    },
+    {
+      "epoch": 2.299657082563967,
+      "grad_norm": 0.06928491592407227,
+      "learning_rate": 3.1627698711137675e-05,
+      "loss": 0.116,
+      "step": 1090
+    },
+    {
+      "epoch": 2.320759694012134,
+      "grad_norm": 0.09970607608556747,
+      "learning_rate": 2.9856047845646885e-05,
+      "loss": 0.1196,
+      "step": 1100
+    },
+    {
+      "epoch": 2.3418623054603005,
+      "grad_norm": 0.08794471621513367,
+      "learning_rate": 2.812671516710268e-05,
+      "loss": 0.1187,
+      "step": 1110
+    },
+    {
+      "epoch": 2.3418623054603005,
+      "eval_loss": 0.11543689668178558,
+      "eval_runtime": 43.1236,
+      "eval_samples_per_second": 4.638,
+      "eval_steps_per_second": 4.638,
+      "step": 1110
+    },
+    {
+      "epoch": 2.362964916908467,
+      "grad_norm": 0.0703900158405304,
+      "learning_rate": 2.644074399030747e-05,
+      "loss": 0.1212,
+      "step": 1120
+    },
+    {
+      "epoch": 2.384067528356634,
+      "grad_norm": 0.07885488122701645,
+      "learning_rate": 2.4799151469859138e-05,
+      "loss": 0.1244,
+      "step": 1130
+    },
+    {
+      "epoch": 2.4051701398048007,
+      "grad_norm": 0.09196896851062775,
+      "learning_rate": 2.320292798649666e-05,
+      "loss": 0.1272,
+      "step": 1140
+    },
+    {
+      "epoch": 2.4051701398048007,
+      "eval_loss": 0.11482755839824677,
+      "eval_runtime": 43.4076,
+      "eval_samples_per_second": 4.607,
+      "eval_steps_per_second": 4.607,
+      "step": 1140
+    },
+    {
+      "epoch": 2.4262727512529674,
+      "grad_norm": 0.0955575704574585,
+      "learning_rate": 2.1653036549598625e-05,
+      "loss": 0.1162,
+      "step": 1150
+    },
+    {
+      "epoch": 2.447375362701134,
+      "grad_norm": 0.07071451842784882,
+      "learning_rate": 2.015041221619508e-05,
+      "loss": 0.1174,
+      "step": 1160
+    },
+    {
+      "epoch": 2.468477974149301,
+      "grad_norm": 0.09692156314849854,
+      "learning_rate": 1.8695961526842965e-05,
+      "loss": 0.1197,
+      "step": 1170
+    },
+    {
+      "epoch": 2.468477974149301,
+      "eval_loss": 0.11504064500331879,
+      "eval_runtime": 43.1488,
+      "eval_samples_per_second": 4.635,
+      "eval_steps_per_second": 4.635,
+      "step": 1170
+    },
+    {
+      "epoch": 2.4895805855974675,
+      "grad_norm": 0.0731809139251709,
+      "learning_rate": 1.729056195870574e-05,
+      "loss": 0.1176,
+      "step": 1180
+    },
+    {
+      "epoch": 2.5106831970456343,
+      "grad_norm": 0.10312127321958542,
+      "learning_rate": 1.593506139616743e-05,
+      "loss": 0.1234,
+      "step": 1190
+    },
+    {
+      "epoch": 2.531785808493801,
+      "grad_norm": 0.09296080470085144,
+      "learning_rate": 1.4630277619299537e-05,
+      "loss": 0.1153,
+      "step": 1200
+    },
+    {
+      "epoch": 2.531785808493801,
+      "eval_loss": 0.11464487016201019,
+      "eval_runtime": 43.2221,
+      "eval_samples_per_second": 4.627,
+      "eval_steps_per_second": 4.627,
+      "step": 1200
+    },
+    {
+      "epoch": 2.5528884199419677,
+      "grad_norm": 0.09009134024381638,
+      "learning_rate": 1.3376997810490576e-05,
+      "loss": 0.1253,
+      "step": 1210
+    },
+    {
+      "epoch": 2.5739910313901344,
+      "grad_norm": 0.08268299698829651,
+      "learning_rate": 1.2175978079534945e-05,
+      "loss": 0.1242,
+      "step": 1220
+    },
+    {
+      "epoch": 2.595093642838301,
+      "grad_norm": 0.09951610863208771,
+      "learning_rate": 1.1027943007468445e-05,
+      "loss": 0.1155,
+      "step": 1230
+    },
+    {
+      "epoch": 2.595093642838301,
+      "eval_loss": 0.11441557854413986,
+      "eval_runtime": 43.2884,
+      "eval_samples_per_second": 4.62,
+      "eval_steps_per_second": 4.62,
+      "step": 1230
+    },
+    {
+      "epoch": 2.616196254286468,
+      "grad_norm": 0.08455725014209747,
+      "learning_rate": 9.933585209424724e-06,
+      "loss": 0.1174,
+      "step": 1240
+    },
+    {
+      "epoch": 2.6372988657346346,
+      "grad_norm": 0.09866108000278473,
+      "learning_rate": 8.89356491677743e-06,
+      "loss": 0.124,
+      "step": 1250
+    },
+    {
+      "epoch": 2.6584014771828013,
+      "grad_norm": 0.07583078742027283,
+      "learning_rate": 7.908509578819412e-06,
+      "loss": 0.1192,
+      "step": 1260
+    },
+    {
+      "epoch": 2.6584014771828013,
+      "eval_loss": 0.11456166207790375,
+      "eval_runtime": 43.4252,
+      "eval_samples_per_second": 4.606,
+      "eval_steps_per_second": 4.606,
+      "step": 1260
+    },
+    {
+      "epoch": 2.679504088630968,
+      "grad_norm": 0.08594157546758652,
+      "learning_rate": 6.97901348421931e-06,
+      "loss": 0.1075,
+      "step": 1270
+    },
+    {
+      "epoch": 2.7006067000791347,
+      "grad_norm": 0.0794958546757698,
+      "learning_rate": 6.105637402484587e-06,
+      "loss": 0.1174,
+      "step": 1280
+    },
+    {
+      "epoch": 2.7217093115273014,
+      "grad_norm": 0.08967737853527069,
+      "learning_rate": 5.288908245646374e-06,
+      "loss": 0.1199,
+      "step": 1290
+    },
+    {
+      "epoch": 2.7217093115273014,
+      "eval_loss": 0.11449629813432693,
+      "eval_runtime": 43.3857,
+      "eval_samples_per_second": 4.61,
+      "eval_steps_per_second": 4.61,
+      "step": 1290
+    },
+    {
+      "epoch": 2.742811922975468,
+      "grad_norm": 0.08780141174793243,
+      "learning_rate": 4.5293187503709145e-06,
+      "loss": 0.1227,
+      "step": 1300
+    },
+    {
+      "epoch": 2.763914534423635,
+      "grad_norm": 0.084247887134552,
+      "learning_rate": 3.827327180689233e-06,
+      "loss": 0.118,
+      "step": 1310
+    },
+    {
+      "epoch": 2.7850171458718016,
+      "grad_norm": 0.0994938537478447,
+      "learning_rate": 3.183357051524094e-06,
+      "loss": 0.1117,
+      "step": 1320
+    },
+    {
+      "epoch": 2.7850171458718016,
+      "eval_loss": 0.11442971974611282,
+      "eval_runtime": 43.583,
+      "eval_samples_per_second": 4.589,
+      "eval_steps_per_second": 4.589,
+      "step": 1320
+    },
+    {
+      "epoch": 2.8061197573199683,
+      "grad_norm": 0.08884406089782715,
+      "learning_rate": 2.5977968731814793e-06,
+      "loss": 0.1201,
+      "step": 1330
+    },
+    {
+      "epoch": 2.827222368768135,
+      "grad_norm": 0.07794331759214401,
+      "learning_rate": 2.0709999169604035e-06,
+      "loss": 0.1156,
+      "step": 1340
+    },
+    {
+      "epoch": 2.8483249802163018,
+      "grad_norm": 0.08900859951972961,
+      "learning_rate": 1.6032840020226314e-06,
+      "loss": 0.1216,
+      "step": 1350
+    },
+    {
+      "epoch": 2.8483249802163018,
+      "eval_loss": 0.1145409420132637,
+      "eval_runtime": 43.2122,
+      "eval_samples_per_second": 4.628,
+      "eval_steps_per_second": 4.628,
+      "step": 1350
+    },
+    {
+      "epoch": 2.8694275916644685,
+      "grad_norm": 0.10006270557641983,
+      "learning_rate": 1.1949313036508257e-06,
+      "loss": 0.1209,
+      "step": 1360
+    },
+    {
+      "epoch": 2.890530203112635,
+      "grad_norm": 0.08598820120096207,
+      "learning_rate": 8.46188183010832e-07,
+      "loss": 0.1176,
+      "step": 1370
+    },
+    {
+      "epoch": 2.911632814560802,
+      "grad_norm": 0.0863473117351532,
+      "learning_rate": 5.572650385208045e-07,
+      "loss": 0.1215,
+      "step": 1380
+    },
+    {
+      "epoch": 2.911632814560802,
+      "eval_loss": 0.1144556924700737,
+      "eval_runtime": 43.2455,
+      "eval_samples_per_second": 4.625,
+      "eval_steps_per_second": 4.625,
+      "step": 1380
+    },
+    {
+      "epoch": 2.9327354260089686,
+      "grad_norm": 0.07715385407209396,
+      "learning_rate": 3.2833617891676604e-07,
+      "loss": 0.1177,
+      "step": 1390
+    },
+    {
+      "epoch": 2.9538380374571354,
+      "grad_norm": 0.10536118596792221,
+      "learning_rate": 1.595397180913949e-07,
+      "loss": 0.1165,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1422,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.04586498063829e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a190647831ef4d240aaa100e304429580fe89ce26089d2a605758671e6ef9b4c
+size 5777

checkpoint-1422/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-1422/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": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1422/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280765cb5c316d2ef927e44950b07a9adc84f0109075b234f0b0bf876b5ce9a6
+size 528550256

checkpoint-1422/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-1422/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-1422/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b720efae0574f85ad574b66cec3bcc8b88f2cc6ed7fb50e1aa9c4bb9157a6878
+size 1057397963

checkpoint-1422/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38124947b831cdcdd8cdf19f6ed6a666abbdb3e02595175fca746d267c0e943d
+size 14645

checkpoint-1422/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0462d8ef5d05a80923ad8237a0f7355264f0f1b9f60914e676626f2e60e1b22
+size 1465

checkpoint-1422/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-1422/tokenizer.json

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

checkpoint-1422/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-1422/trainer_state.json

@@ -0,0 +1,1404 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 30,
+  "global_step": 1422,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021102611448166712,
+      "grad_norm": 9.9413423538208,
+      "learning_rate": 1.2587412587412589e-05,
+      "loss": 2.7146,
+      "step": 10
+    },
+    {
+      "epoch": 0.042205222896333425,
+      "grad_norm": 1.0188082456588745,
+      "learning_rate": 2.6573426573426574e-05,
+      "loss": 1.1603,
+      "step": 20
+    },
+    {
+      "epoch": 0.06330783434450013,
+      "grad_norm": 0.9419231414794922,
+      "learning_rate": 4.055944055944056e-05,
+      "loss": 0.7015,
+      "step": 30
+    },
+    {
+      "epoch": 0.06330783434450013,
+      "eval_loss": 0.5692373514175415,
+      "eval_runtime": 43.1831,
+      "eval_samples_per_second": 4.631,
+      "eval_steps_per_second": 4.631,
+      "step": 30
+    },
+    {
+      "epoch": 0.08441044579266685,
+      "grad_norm": 0.7294736504554749,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.5017,
+      "step": 40
+    },
+    {
+      "epoch": 0.10551305724083355,
+      "grad_norm": 0.7030153870582581,
+      "learning_rate": 6.853146853146853e-05,
+      "loss": 0.3731,
+      "step": 50
+    },
+    {
+      "epoch": 0.12661566868900026,
+      "grad_norm": 0.5342110395431519,
+      "learning_rate": 8.251748251748252e-05,
+      "loss": 0.3089,
+      "step": 60
+    },
+    {
+      "epoch": 0.12661566868900026,
+      "eval_loss": 0.27030423283576965,
+      "eval_runtime": 42.6998,
+      "eval_samples_per_second": 4.684,
+      "eval_steps_per_second": 4.684,
+      "step": 60
+    },
+    {
+      "epoch": 0.14771828013716698,
+      "grad_norm": 0.5539342761039734,
+      "learning_rate": 9.65034965034965e-05,
+      "loss": 0.2545,
+      "step": 70
+    },
+    {
+      "epoch": 0.1688208915853337,
+      "grad_norm": 0.7872066497802734,
+      "learning_rate": 0.00011048951048951048,
+      "loss": 0.2126,
+      "step": 80
+    },
+    {
+      "epoch": 0.1899235030335004,
+      "grad_norm": 0.5423749089241028,
+      "learning_rate": 0.00012447552447552448,
+      "loss": 0.2035,
+      "step": 90
+    },
+    {
+      "epoch": 0.1899235030335004,
+      "eval_loss": 0.1911192387342453,
+      "eval_runtime": 42.5187,
+      "eval_samples_per_second": 4.704,
+      "eval_steps_per_second": 4.704,
+      "step": 90
+    },
+    {
+      "epoch": 0.2110261144816671,
+      "grad_norm": 0.34928596019744873,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.1822,
+      "step": 100
+    },
+    {
+      "epoch": 0.23212872592983383,
+      "grad_norm": 0.36143162846565247,
+      "learning_rate": 0.00015244755244755244,
+      "loss": 0.1673,
+      "step": 110
+    },
+    {
+      "epoch": 0.2532313373780005,
+      "grad_norm": 0.5100098252296448,
+      "learning_rate": 0.00016643356643356646,
+      "loss": 0.1844,
+      "step": 120
+    },
+    {
+      "epoch": 0.2532313373780005,
+      "eval_loss": 0.1640024334192276,
+      "eval_runtime": 42.7294,
+      "eval_samples_per_second": 4.681,
+      "eval_steps_per_second": 4.681,
+      "step": 120
+    },
+    {
+      "epoch": 0.27433394882616724,
+      "grad_norm": 0.5207167267799377,
+      "learning_rate": 0.00018041958041958042,
+      "loss": 0.1677,
+      "step": 130
+    },
+    {
+      "epoch": 0.29543656027433396,
+      "grad_norm": 0.3435003459453583,
+      "learning_rate": 0.0001944055944055944,
+      "loss": 0.1575,
+      "step": 140
+    },
+    {
+      "epoch": 0.3165391717225007,
+      "grad_norm": 0.4177781045436859,
+      "learning_rate": 0.0001999891401631506,
+      "loss": 0.1656,
+      "step": 150
+    },
+    {
+      "epoch": 0.3165391717225007,
+      "eval_loss": 0.1460759937763214,
+      "eval_runtime": 42.6392,
+      "eval_samples_per_second": 4.691,
+      "eval_steps_per_second": 4.691,
+      "step": 150
+    },
+    {
+      "epoch": 0.3376417831706674,
+      "grad_norm": 0.40304410457611084,
+      "learning_rate": 0.0001999227830351936,
+      "loss": 0.1466,
+      "step": 160
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.28438979387283325,
+      "learning_rate": 0.00019979614200701668,
+      "loss": 0.1466,
+      "step": 170
+    },
+    {
+      "epoch": 0.3798470060670008,
+      "grad_norm": 0.3558550179004669,
+      "learning_rate": 0.00019960929348176708,
+      "loss": 0.1505,
+      "step": 180
+    },
+    {
+      "epoch": 0.3798470060670008,
+      "eval_loss": 0.1364826261997223,
+      "eval_runtime": 42.7387,
+      "eval_samples_per_second": 4.68,
+      "eval_steps_per_second": 4.68,
+      "step": 180
+    },
+    {
+      "epoch": 0.4009496175151675,
+      "grad_norm": 0.7208640575408936,
+      "learning_rate": 0.0001993623501860674,
+      "loss": 0.1442,
+      "step": 190
+    },
+    {
+      "epoch": 0.4220522289633342,
+      "grad_norm": 0.22139093279838562,
+      "learning_rate": 0.00019905546110200704,
+      "loss": 0.153,
+      "step": 200
+    },
+    {
+      "epoch": 0.44315484041150094,
+      "grad_norm": 0.39185455441474915,
+      "learning_rate": 0.00019868881137726066,
+      "loss": 0.1395,
+      "step": 210
+    },
+    {
+      "epoch": 0.44315484041150094,
+      "eval_loss": 0.1368705779314041,
+      "eval_runtime": 42.4935,
+      "eval_samples_per_second": 4.707,
+      "eval_steps_per_second": 4.707,
+      "step": 210
+    },
+    {
+      "epoch": 0.46425745185966766,
+      "grad_norm": 0.15956981480121613,
+      "learning_rate": 0.0001982626222133876,
+      "loss": 0.142,
+      "step": 220
+    },
+    {
+      "epoch": 0.4853600633078343,
+      "grad_norm": 0.6167592406272888,
+      "learning_rate": 0.00019777715073237997,
+      "loss": 0.1478,
+      "step": 230
+    },
+    {
+      "epoch": 0.506462674756001,
+      "grad_norm": 0.34357866644859314,
+      "learning_rate": 0.00019723268982153966,
+      "loss": 0.145,
+      "step": 240
+    },
+    {
+      "epoch": 0.506462674756001,
+      "eval_loss": 0.13663160800933838,
+      "eval_runtime": 42.7492,
+      "eval_samples_per_second": 4.678,
+      "eval_steps_per_second": 4.678,
+      "step": 240
+    },
+    {
+      "epoch": 0.5275652862041678,
+      "grad_norm": 0.45330700278282166,
+      "learning_rate": 0.000196629567956778,
+      "loss": 0.1541,
+      "step": 250
+    },
+    {
+      "epoch": 0.5486678976523345,
+      "grad_norm": 0.3859712779521942,
+      "learning_rate": 0.00019596814900444475,
+      "loss": 0.1608,
+      "step": 260
+    },
+    {
+      "epoch": 0.5697705091005012,
+      "grad_norm": 0.14809803664684296,
+      "learning_rate": 0.00019524883200180558,
+      "loss": 0.1355,
+      "step": 270
+    },
+    {
+      "epoch": 0.5697705091005012,
+      "eval_loss": 0.132829487323761,
+      "eval_runtime": 42.6204,
+      "eval_samples_per_second": 4.693,
+      "eval_steps_per_second": 4.693,
+      "step": 270
+    },
+    {
+      "epoch": 0.5908731205486679,
+      "grad_norm": 0.1790543645620346,
+      "learning_rate": 0.00019447205091630115,
+      "loss": 0.1365,
+      "step": 280
+    },
+    {
+      "epoch": 0.6119757319968346,
+      "grad_norm": 0.4073638617992401,
+      "learning_rate": 0.00019363827438373233,
+      "loss": 0.1423,
+      "step": 290
+    },
+    {
+      "epoch": 0.6330783434450014,
+      "grad_norm": 0.13269440829753876,
+      "learning_rate": 0.0001927480054255299,
+      "loss": 0.1402,
+      "step": 300
+    },
+    {
+      "epoch": 0.6330783434450014,
+      "eval_loss": 0.1258172243833542,
+      "eval_runtime": 43.0037,
+      "eval_samples_per_second": 4.651,
+      "eval_steps_per_second": 4.651,
+      "step": 300
+    },
+    {
+      "epoch": 0.6541809548931681,
+      "grad_norm": 0.15398648381233215,
+      "learning_rate": 0.00019180178114527942,
+      "loss": 0.1313,
+      "step": 310
+    },
+    {
+      "epoch": 0.6752835663413348,
+      "grad_norm": 0.18669337034225464,
+      "learning_rate": 0.00019080017240468393,
+      "loss": 0.1441,
+      "step": 320
+    },
+    {
+      "epoch": 0.6963861777895014,
+      "grad_norm": 0.2585830092430115,
+      "learning_rate": 0.00018974378347916035,
+      "loss": 0.1338,
+      "step": 330
+    },
+    {
+      "epoch": 0.6963861777895014,
+      "eval_loss": 0.12394458800554276,
+      "eval_runtime": 42.955,
+      "eval_samples_per_second": 4.656,
+      "eval_steps_per_second": 4.656,
+      "step": 330
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.15704883635044098,
+      "learning_rate": 0.00018863325169327718,
+      "loss": 0.1254,
+      "step": 340
+    },
+    {
+      "epoch": 0.7385914006858348,
+      "grad_norm": 0.12733563780784607,
+      "learning_rate": 0.00018746924703625344,
+      "loss": 0.137,
+      "step": 350
+    },
+    {
+      "epoch": 0.7596940121340016,
+      "grad_norm": 0.2758557200431824,
+      "learning_rate": 0.000186252471757751,
+      "loss": 0.1329,
+      "step": 360
+    },
+    {
+      "epoch": 0.7596940121340016,
+      "eval_loss": 0.12415071576833725,
+      "eval_runtime": 42.9293,
+      "eval_samples_per_second": 4.659,
+      "eval_steps_per_second": 4.659,
+      "step": 360
+    },
+    {
+      "epoch": 0.7807966235821683,
+      "grad_norm": 0.20145803689956665,
+      "learning_rate": 0.00018498365994420394,
+      "loss": 0.1298,
+      "step": 370
+    },
+    {
+      "epoch": 0.801899235030335,
+      "grad_norm": 0.13150104880332947,
+      "learning_rate": 0.0001836635770759406,
+      "loss": 0.1401,
+      "step": 380
+    },
+    {
+      "epoch": 0.8230018464785017,
+      "grad_norm": 0.14411461353302002,
+      "learning_rate": 0.0001822930195653656,
+      "loss": 0.131,
+      "step": 390
+    },
+    {
+      "epoch": 0.8230018464785017,
+      "eval_loss": 0.12136167287826538,
+      "eval_runtime": 43.0344,
+      "eval_samples_per_second": 4.647,
+      "eval_steps_per_second": 4.647,
+      "step": 390
+    },
+    {
+      "epoch": 0.8441044579266684,
+      "grad_norm": 0.11295611411333084,
+      "learning_rate": 0.00018087281427648025,
+      "loss": 0.1291,
+      "step": 400
+    },
+    {
+      "epoch": 0.8652070693748352,
+      "grad_norm": 0.11478397250175476,
+      "learning_rate": 0.00017940381802603188,
+      "loss": 0.1254,
+      "step": 410
+    },
+    {
+      "epoch": 0.8863096808230019,
+      "grad_norm": 0.11431597918272018,
+      "learning_rate": 0.00017788691706659154,
+      "loss": 0.12,
+      "step": 420
+    },
+    {
+      "epoch": 0.8863096808230019,
+      "eval_loss": 0.124061718583107,
+      "eval_runtime": 43.0846,
+      "eval_samples_per_second": 4.642,
+      "eval_steps_per_second": 4.642,
+      "step": 420
+    },
+    {
+      "epoch": 0.9074122922711686,
+      "grad_norm": 0.1042429730296135,
+      "learning_rate": 0.00017632302655187402,
+      "loss": 0.1403,
+      "step": 430
+    },
+    {
+      "epoch": 0.9285149037193353,
+      "grad_norm": 0.11291960626840591,
+      "learning_rate": 0.00017471308998462097,
+      "loss": 0.1418,
+      "step": 440
+    },
+    {
+      "epoch": 0.9496175151675019,
+      "grad_norm": 0.11094669252634048,
+      "learning_rate": 0.00017305807864738106,
+      "loss": 0.1306,
+      "step": 450
+    },
+    {
+      "epoch": 0.9496175151675019,
+      "eval_loss": 0.12037019431591034,
+      "eval_runtime": 42.9632,
+      "eval_samples_per_second": 4.655,
+      "eval_steps_per_second": 4.655,
+      "step": 450
+    },
+    {
+      "epoch": 0.9707201266156686,
+      "grad_norm": 0.10620168596506119,
+      "learning_rate": 0.00017135899101653065,
+      "loss": 0.1163,
+      "step": 460
+    },
+    {
+      "epoch": 0.9918227380638354,
+      "grad_norm": 0.10655219852924347,
+      "learning_rate": 0.000169616852159888,
+      "loss": 0.1336,
+      "step": 470
+    },
+    {
+      "epoch": 1.0126615668689,
+      "grad_norm": 0.12968231737613678,
+      "learning_rate": 0.00016783271311828494,
+      "loss": 0.1284,
+      "step": 480
+    },
+    {
+      "epoch": 1.0126615668689,
+      "eval_loss": 0.12156519293785095,
+      "eval_runtime": 42.9531,
+      "eval_samples_per_second": 4.656,
+      "eval_steps_per_second": 4.656,
+      "step": 480
+    },
+    {
+      "epoch": 1.0337641783170668,
+      "grad_norm": 0.11897017806768417,
+      "learning_rate": 0.00016600765027146894,
+      "loss": 0.129,
+      "step": 490
+    },
+    {
+      "epoch": 1.0548667897652335,
+      "grad_norm": 0.127396360039711,
+      "learning_rate": 0.00016414276468871777,
+      "loss": 0.1291,
+      "step": 500
+    },
+    {
+      "epoch": 1.0759694012134002,
+      "grad_norm": 0.11823620647192001,
+      "learning_rate": 0.00016223918146455918,
+      "loss": 0.131,
+      "step": 510
+    },
+    {
+      "epoch": 1.0759694012134002,
+      "eval_loss": 0.12118449807167053,
+      "eval_runtime": 42.9587,
+      "eval_samples_per_second": 4.656,
+      "eval_steps_per_second": 4.656,
+      "step": 510
+    },
+    {
+      "epoch": 1.097072012661567,
+      "grad_norm": 0.10815704613924026,
+      "learning_rate": 0.00016029804903999596,
+      "loss": 0.133,
+      "step": 520
+    },
+    {
+      "epoch": 1.1181746241097337,
+      "grad_norm": 0.10010864585638046,
+      "learning_rate": 0.0001583205385096457,
+      "loss": 0.1232,
+      "step": 530
+    },
+    {
+      "epoch": 1.1392772355579002,
+      "grad_norm": 0.12100092321634293,
+      "learning_rate": 0.00015630784291521403,
+      "loss": 0.1323,
+      "step": 540
+    },
+    {
+      "epoch": 1.1392772355579002,
+      "eval_loss": 0.11961612850427628,
+      "eval_runtime": 42.905,
+      "eval_samples_per_second": 4.661,
+      "eval_steps_per_second": 4.661,
+      "step": 540
+    },
+    {
+      "epoch": 1.160379847006067,
+      "grad_norm": 0.08296310156583786,
+      "learning_rate": 0.00015426117652572648,
+      "loss": 0.1273,
+      "step": 550
+    },
+    {
+      "epoch": 1.1814824584542336,
+      "grad_norm": 0.10136981308460236,
+      "learning_rate": 0.00015218177410495422,
+      "loss": 0.1254,
+      "step": 560
+    },
+    {
+      "epoch": 1.2025850699024003,
+      "grad_norm": 0.09671589732170105,
+      "learning_rate": 0.00015007089016647512,
+      "loss": 0.1235,
+      "step": 570
+    },
+    {
+      "epoch": 1.2025850699024003,
+      "eval_loss": 0.11970534175634384,
+      "eval_runtime": 42.9709,
+      "eval_samples_per_second": 4.654,
+      "eval_steps_per_second": 4.654,
+      "step": 570
+    },
+    {
+      "epoch": 1.223687681350567,
+      "grad_norm": 0.09472666680812836,
+      "learning_rate": 0.00014792979821681948,
+      "loss": 0.1237,
+      "step": 580
+    },
+    {
+      "epoch": 1.2447902927987338,
+      "grad_norm": 0.16830433905124664,
+      "learning_rate": 0.0001457597899871574,
+      "loss": 0.127,
+      "step": 590
+    },
+    {
+      "epoch": 1.2658929042469005,
+      "grad_norm": 0.08856591582298279,
+      "learning_rate": 0.00014356217465399124,
+      "loss": 0.123,
+      "step": 600
+    },
+    {
+      "epoch": 1.2658929042469005,
+      "eval_loss": 0.11881241202354431,
+      "eval_runtime": 42.9169,
+      "eval_samples_per_second": 4.66,
+      "eval_steps_per_second": 4.66,
+      "step": 600
+    },
+    {
+      "epoch": 1.2869955156950672,
+      "grad_norm": 0.11379825323820114,
+      "learning_rate": 0.00014133827804932282,
+      "loss": 0.1242,
+      "step": 610
+    },
+    {
+      "epoch": 1.308098127143234,
+      "grad_norm": 0.08634220063686371,
+      "learning_rate": 0.0001390894418607728,
+      "loss": 0.1289,
+      "step": 620
+    },
+    {
+      "epoch": 1.3292007385914006,
+      "grad_norm": 0.08761777728796005,
+      "learning_rate": 0.0001368170228221339,
+      "loss": 0.1209,
+      "step": 630
+    },
+    {
+      "epoch": 1.3292007385914006,
+      "eval_loss": 0.11858396232128143,
+      "eval_runtime": 42.8741,
+      "eval_samples_per_second": 4.665,
+      "eval_steps_per_second": 4.665,
+      "step": 630
+    },
+    {
+      "epoch": 1.3503033500395674,
+      "grad_norm": 0.09664271026849747,
+      "learning_rate": 0.00013452239189484666,
+      "loss": 0.1247,
+      "step": 640
+    },
+    {
+      "epoch": 1.371405961487734,
+      "grad_norm": 0.1144590675830841,
+      "learning_rate": 0.0001322069334408921,
+      "loss": 0.1268,
+      "step": 650
+    },
+    {
+      "epoch": 1.3925085729359008,
+      "grad_norm": 0.1012091338634491,
+      "learning_rate": 0.00012987204438759904,
+      "loss": 0.1256,
+      "step": 660
+    },
+    {
+      "epoch": 1.3925085729359008,
+      "eval_loss": 0.11804136633872986,
+      "eval_runtime": 43.1847,
+      "eval_samples_per_second": 4.631,
+      "eval_steps_per_second": 4.631,
+      "step": 660
+    },
+    {
+      "epoch": 1.4136111843840675,
+      "grad_norm": 0.09839442372322083,
+      "learning_rate": 0.00012751913338487135,
+      "loss": 0.1275,
+      "step": 670
+    },
+    {
+      "epoch": 1.4347137958322342,
+      "grad_norm": 0.30278143286705017,
+      "learning_rate": 0.00012514961995534248,
+      "loss": 0.1241,
+      "step": 680
+    },
+    {
+      "epoch": 1.455816407280401,
+      "grad_norm": 0.07915577292442322,
+      "learning_rate": 0.00012276493363797054,
+      "loss": 0.126,
+      "step": 690
+    },
+    {
+      "epoch": 1.455816407280401,
+      "eval_loss": 0.11796753108501434,
+      "eval_runtime": 43.3648,
+      "eval_samples_per_second": 4.612,
+      "eval_steps_per_second": 4.612,
+      "step": 690
+    },
+    {
+      "epoch": 1.4769190187285677,
+      "grad_norm": 0.09405189752578735,
+      "learning_rate": 0.00012036651312559069,
+      "loss": 0.1218,
+      "step": 700
+    },
+    {
+      "epoch": 1.4980216301767344,
+      "grad_norm": 0.10401446372270584,
+      "learning_rate": 0.00011795580539694441,
+      "loss": 0.1241,
+      "step": 710
+    },
+    {
+      "epoch": 1.5191242416249011,
+      "grad_norm": 0.08657781034708023,
+      "learning_rate": 0.00011553426484371064,
+      "loss": 0.1229,
+      "step": 720
+    },
+    {
+      "epoch": 1.5191242416249011,
+      "eval_loss": 0.11668255180120468,
+      "eval_runtime": 43.2352,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 4.626,
+      "step": 720
+    },
+    {
+      "epoch": 1.5402268530730678,
+      "grad_norm": 0.09666746109724045,
+      "learning_rate": 0.00011310335239306384,
+      "loss": 0.129,
+      "step": 730
+    },
+    {
+      "epoch": 1.5613294645212346,
+      "grad_norm": 0.08991085737943649,
+      "learning_rate": 0.00011066453462628978,
+      "loss": 0.1207,
+      "step": 740
+    },
+    {
+      "epoch": 1.5824320759694013,
+      "grad_norm": 0.08485621958971024,
+      "learning_rate": 0.00010821928289398974,
+      "loss": 0.1175,
+      "step": 750
+    },
+    {
+      "epoch": 1.5824320759694013,
+      "eval_loss": 0.11763760447502136,
+      "eval_runtime": 43.082,
+      "eval_samples_per_second": 4.642,
+      "eval_steps_per_second": 4.642,
+      "step": 750
+    },
+    {
+      "epoch": 1.603534687417568,
+      "grad_norm": 0.08351397514343262,
+      "learning_rate": 0.00010576907242840782,
+      "loss": 0.1318,
+      "step": 760
+    },
+    {
+      "epoch": 1.6246372988657347,
+      "grad_norm": 0.09473424404859543,
+      "learning_rate": 0.00010331538145341579,
+      "loss": 0.1202,
+      "step": 770
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "grad_norm": 0.08496669679880142,
+      "learning_rate": 0.00010085969029269375,
+      "loss": 0.1233,
+      "step": 780
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "eval_loss": 0.11757928878068924,
+      "eval_runtime": 42.9019,
+      "eval_samples_per_second": 4.662,
+      "eval_steps_per_second": 4.662,
+      "step": 780
+    },
+    {
+      "epoch": 1.6668425217620682,
+      "grad_norm": 0.07978235930204391,
+      "learning_rate": 9.84034804766436e-05,
+      "loss": 0.122,
+      "step": 790
+    },
+    {
+      "epoch": 1.6879451332102349,
+      "grad_norm": 0.09555214643478394,
+      "learning_rate": 9.594823384857439e-05,
+      "loss": 0.1233,
+      "step": 800
+    },
+    {
+      "epoch": 1.7090477446584016,
+      "grad_norm": 1.1965069770812988,
+      "learning_rate": 9.34954316706993e-05,
+      "loss": 0.1139,
+      "step": 810
+    },
+    {
+      "epoch": 1.7090477446584016,
+      "eval_loss": 0.1184568777680397,
+      "eval_runtime": 42.9485,
+      "eval_samples_per_second": 4.657,
+      "eval_steps_per_second": 4.657,
+      "step": 810
+    },
+    {
+      "epoch": 1.7301503561065683,
+      "grad_norm": 0.09275703132152557,
+      "learning_rate": 9.104655373048281e-05,
+      "loss": 0.129,
+      "step": 820
+    },
+    {
+      "epoch": 1.751252967554735,
+      "grad_norm": 0.08251888304948807,
+      "learning_rate": 8.860307744787772e-05,
+      "loss": 0.1195,
+      "step": 830
+    },
+    {
+      "epoch": 1.7723555790029017,
+      "grad_norm": 0.20448611676692963,
+      "learning_rate": 8.616647698399065e-05,
+      "loss": 0.1244,
+      "step": 840
+    },
+    {
+      "epoch": 1.7723555790029017,
+      "eval_loss": 0.11751535534858704,
+      "eval_runtime": 43.1584,
+      "eval_samples_per_second": 4.634,
+      "eval_steps_per_second": 4.634,
+      "step": 840
+    },
+    {
+      "epoch": 1.7934581904510685,
+      "grad_norm": 0.09854628890752792,
+      "learning_rate": 8.373822235171327e-05,
+      "loss": 0.1188,
+      "step": 850
+    },
+    {
+      "epoch": 1.8145608018992352,
+      "grad_norm": 0.10301581025123596,
+      "learning_rate": 8.131977852885666e-05,
+      "loss": 0.1275,
+      "step": 860
+    },
+    {
+      "epoch": 1.835663413347402,
+      "grad_norm": 0.11739084124565125,
+      "learning_rate": 7.89126045743228e-05,
+      "loss": 0.122,
+      "step": 870
+    },
+    {
+      "epoch": 1.835663413347402,
+      "eval_loss": 0.11938333511352539,
+      "eval_runtime": 43.0848,
+      "eval_samples_per_second": 4.642,
+      "eval_steps_per_second": 4.642,
+      "step": 870
+    },
+    {
+      "epoch": 1.8567660247955684,
+      "grad_norm": 0.11293812841176987,
+      "learning_rate": 7.651815274784751e-05,
+      "loss": 0.1319,
+      "step": 880
+    },
+    {
+      "epoch": 1.8778686362437351,
+      "grad_norm": 0.11208591610193253,
+      "learning_rate": 7.413786763384491e-05,
+      "loss": 0.1254,
+      "step": 890
+    },
+    {
+      "epoch": 1.8989712476919018,
+      "grad_norm": 0.0833379328250885,
+      "learning_rate": 7.177318526988264e-05,
+      "loss": 0.1214,
+      "step": 900
+    },
+    {
+      "epoch": 1.8989712476919018,
+      "eval_loss": 0.11639796197414398,
+      "eval_runtime": 43.0753,
+      "eval_samples_per_second": 4.643,
+      "eval_steps_per_second": 4.643,
+      "step": 900
+    },
+    {
+      "epoch": 1.9200738591400686,
+      "grad_norm": 0.09288811683654785,
+      "learning_rate": 6.94255322803136e-05,
+      "loss": 0.1283,
+      "step": 910
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.08512190729379654,
+      "learning_rate": 6.709632501558631e-05,
+      "loss": 0.1213,
+      "step": 920
+    },
+    {
+      "epoch": 1.962279082036402,
+      "grad_norm": 0.0763729065656662,
+      "learning_rate": 6.478696869775401e-05,
+      "loss": 0.1269,
+      "step": 930
+    },
+    {
+      "epoch": 1.962279082036402,
+      "eval_loss": 0.11652935296297073,
+      "eval_runtime": 42.9622,
+      "eval_samples_per_second": 4.655,
+      "eval_steps_per_second": 4.655,
+      "step": 930
+    },
+    {
+      "epoch": 1.9833816934845687,
+      "grad_norm": 0.11486316472291946,
+      "learning_rate": 6.249885657269722e-05,
+      "loss": 0.1224,
+      "step": 940
+    },
+    {
+      "epoch": 2.0042205222896334,
+      "grad_norm": 0.07140278816223145,
+      "learning_rate": 6.023336906957188e-05,
+      "loss": 0.1293,
+      "step": 950
+    },
+    {
+      "epoch": 2.0253231337378,
+      "grad_norm": 0.08281326293945312,
+      "learning_rate": 5.7991872967989536e-05,
+      "loss": 0.1198,
+      "step": 960
+    },
+    {
+      "epoch": 2.0253231337378,
+      "eval_loss": 0.11602704972028732,
+      "eval_runtime": 43.3093,
+      "eval_samples_per_second": 4.618,
+      "eval_steps_per_second": 4.618,
+      "step": 960
+    },
+    {
+      "epoch": 2.046425745185967,
+      "grad_norm": 0.09625944495201111,
+      "learning_rate": 5.5775720573432764e-05,
+      "loss": 0.1219,
+      "step": 970
+    },
+    {
+      "epoch": 2.0675283566341336,
+      "grad_norm": 0.10757429152727127,
+      "learning_rate": 5.358624890140263e-05,
+      "loss": 0.1203,
+      "step": 980
+    },
+    {
+      "epoch": 2.0886309680823003,
+      "grad_norm": 0.10341180860996246,
+      "learning_rate": 5.1424778870790645e-05,
+      "loss": 0.1131,
+      "step": 990
+    },
+    {
+      "epoch": 2.0886309680823003,
+      "eval_loss": 0.11575788259506226,
+      "eval_runtime": 43.2104,
+      "eval_samples_per_second": 4.629,
+      "eval_steps_per_second": 4.629,
+      "step": 990
+    },
+    {
+      "epoch": 2.109733579530467,
+      "grad_norm": 0.08683689683675766,
+      "learning_rate": 4.929261450696228e-05,
+      "loss": 0.1221,
+      "step": 1000
+    },
+    {
+      "epoch": 2.1308361909786337,
+      "grad_norm": 0.11907190829515457,
+      "learning_rate": 4.719104215503172e-05,
+      "loss": 0.1252,
+      "step": 1010
+    },
+    {
+      "epoch": 2.1519388024268005,
+      "grad_norm": 0.11070162802934647,
+      "learning_rate": 4.5121329703803935e-05,
+      "loss": 0.1296,
+      "step": 1020
+    },
+    {
+      "epoch": 2.1519388024268005,
+      "eval_loss": 0.11595886200666428,
+      "eval_runtime": 43.3948,
+      "eval_samples_per_second": 4.609,
+      "eval_steps_per_second": 4.609,
+      "step": 1020
+    },
+    {
+      "epoch": 2.173041413874967,
+      "grad_norm": 0.08530761301517487,
+      "learning_rate": 4.308472582085104e-05,
+      "loss": 0.1129,
+      "step": 1030
+    },
+    {
+      "epoch": 2.194144025323134,
+      "grad_norm": 0.09313362836837769,
+      "learning_rate": 4.10824591991852e-05,
+      "loss": 0.118,
+      "step": 1040
+    },
+    {
+      "epoch": 2.2152466367713006,
+      "grad_norm": 0.08985672891139984,
+      "learning_rate": 3.9115737815982024e-05,
+      "loss": 0.1144,
+      "step": 1050
+    },
+    {
+      "epoch": 2.2152466367713006,
+      "eval_loss": 0.11535269021987915,
+      "eval_runtime": 43.4078,
+      "eval_samples_per_second": 4.607,
+      "eval_steps_per_second": 4.607,
+      "step": 1050
+    },
+    {
+      "epoch": 2.2363492482194673,
+      "grad_norm": 0.07902213931083679,
+      "learning_rate": 3.7185748203802175e-05,
+      "loss": 0.1224,
+      "step": 1060
+    },
+    {
+      "epoch": 2.2574518596676336,
+      "grad_norm": 0.10935928672552109,
+      "learning_rate": 3.5293654734750624e-05,
+      "loss": 0.1255,
+      "step": 1070
+    },
+    {
+      "epoch": 2.2785544711158003,
+      "grad_norm": 0.07709987461566925,
+      "learning_rate": 3.344059891800493e-05,
+      "loss": 0.1076,
+      "step": 1080
+    },
+    {
+      "epoch": 2.2785544711158003,
+      "eval_loss": 0.11529315263032913,
+      "eval_runtime": 43.4366,
+      "eval_samples_per_second": 4.604,
+      "eval_steps_per_second": 4.604,
+      "step": 1080
+    },
+    {
+      "epoch": 2.299657082563967,
+      "grad_norm": 0.06928491592407227,
+      "learning_rate": 3.1627698711137675e-05,
+      "loss": 0.116,
+      "step": 1090
+    },
+    {
+      "epoch": 2.320759694012134,
+      "grad_norm": 0.09970607608556747,
+      "learning_rate": 2.9856047845646885e-05,
+      "loss": 0.1196,
+      "step": 1100
+    },
+    {
+      "epoch": 2.3418623054603005,
+      "grad_norm": 0.08794471621513367,
+      "learning_rate": 2.812671516710268e-05,
+      "loss": 0.1187,
+      "step": 1110
+    },
+    {
+      "epoch": 2.3418623054603005,
+      "eval_loss": 0.11543689668178558,
+      "eval_runtime": 43.1236,
+      "eval_samples_per_second": 4.638,
+      "eval_steps_per_second": 4.638,
+      "step": 1110
+    },
+    {
+      "epoch": 2.362964916908467,
+      "grad_norm": 0.0703900158405304,
+      "learning_rate": 2.644074399030747e-05,
+      "loss": 0.1212,
+      "step": 1120
+    },
+    {
+      "epoch": 2.384067528356634,
+      "grad_norm": 0.07885488122701645,
+      "learning_rate": 2.4799151469859138e-05,
+      "loss": 0.1244,
+      "step": 1130
+    },
+    {
+      "epoch": 2.4051701398048007,
+      "grad_norm": 0.09196896851062775,
+      "learning_rate": 2.320292798649666e-05,
+      "loss": 0.1272,
+      "step": 1140
+    },
+    {
+      "epoch": 2.4051701398048007,
+      "eval_loss": 0.11482755839824677,
+      "eval_runtime": 43.4076,
+      "eval_samples_per_second": 4.607,
+      "eval_steps_per_second": 4.607,
+      "step": 1140
+    },
+    {
+      "epoch": 2.4262727512529674,
+      "grad_norm": 0.0955575704574585,
+      "learning_rate": 2.1653036549598625e-05,
+      "loss": 0.1162,
+      "step": 1150
+    },
+    {
+      "epoch": 2.447375362701134,
+      "grad_norm": 0.07071451842784882,
+      "learning_rate": 2.015041221619508e-05,
+      "loss": 0.1174,
+      "step": 1160
+    },
+    {
+      "epoch": 2.468477974149301,
+      "grad_norm": 0.09692156314849854,
+      "learning_rate": 1.8695961526842965e-05,
+      "loss": 0.1197,
+      "step": 1170
+    },
+    {
+      "epoch": 2.468477974149301,
+      "eval_loss": 0.11504064500331879,
+      "eval_runtime": 43.1488,
+      "eval_samples_per_second": 4.635,
+      "eval_steps_per_second": 4.635,
+      "step": 1170
+    },
+    {
+      "epoch": 2.4895805855974675,
+      "grad_norm": 0.0731809139251709,
+      "learning_rate": 1.729056195870574e-05,
+      "loss": 0.1176,
+      "step": 1180
+    },
+    {
+      "epoch": 2.5106831970456343,
+      "grad_norm": 0.10312127321958542,
+      "learning_rate": 1.593506139616743e-05,
+      "loss": 0.1234,
+      "step": 1190
+    },
+    {
+      "epoch": 2.531785808493801,
+      "grad_norm": 0.09296080470085144,
+      "learning_rate": 1.4630277619299537e-05,
+      "loss": 0.1153,
+      "step": 1200
+    },
+    {
+      "epoch": 2.531785808493801,
+      "eval_loss": 0.11464487016201019,
+      "eval_runtime": 43.2221,
+      "eval_samples_per_second": 4.627,
+      "eval_steps_per_second": 4.627,
+      "step": 1200
+    },
+    {
+      "epoch": 2.5528884199419677,
+      "grad_norm": 0.09009134024381638,
+      "learning_rate": 1.3376997810490576e-05,
+      "loss": 0.1253,
+      "step": 1210
+    },
+    {
+      "epoch": 2.5739910313901344,
+      "grad_norm": 0.08268299698829651,
+      "learning_rate": 1.2175978079534945e-05,
+      "loss": 0.1242,
+      "step": 1220
+    },
+    {
+      "epoch": 2.595093642838301,
+      "grad_norm": 0.09951610863208771,
+      "learning_rate": 1.1027943007468445e-05,
+      "loss": 0.1155,
+      "step": 1230
+    },
+    {
+      "epoch": 2.595093642838301,
+      "eval_loss": 0.11441557854413986,
+      "eval_runtime": 43.2884,
+      "eval_samples_per_second": 4.62,
+      "eval_steps_per_second": 4.62,
+      "step": 1230
+    },
+    {
+      "epoch": 2.616196254286468,
+      "grad_norm": 0.08455725014209747,
+      "learning_rate": 9.933585209424724e-06,
+      "loss": 0.1174,
+      "step": 1240
+    },
+    {
+      "epoch": 2.6372988657346346,
+      "grad_norm": 0.09866108000278473,
+      "learning_rate": 8.89356491677743e-06,
+      "loss": 0.124,
+      "step": 1250
+    },
+    {
+      "epoch": 2.6584014771828013,
+      "grad_norm": 0.07583078742027283,
+      "learning_rate": 7.908509578819412e-06,
+      "loss": 0.1192,
+      "step": 1260
+    },
+    {
+      "epoch": 2.6584014771828013,
+      "eval_loss": 0.11456166207790375,
+      "eval_runtime": 43.4252,
+      "eval_samples_per_second": 4.606,
+      "eval_steps_per_second": 4.606,
+      "step": 1260
+    },
+    {
+      "epoch": 2.679504088630968,
+      "grad_norm": 0.08594157546758652,
+      "learning_rate": 6.97901348421931e-06,
+      "loss": 0.1075,
+      "step": 1270
+    },
+    {
+      "epoch": 2.7006067000791347,
+      "grad_norm": 0.0794958546757698,
+      "learning_rate": 6.105637402484587e-06,
+      "loss": 0.1174,
+      "step": 1280
+    },
+    {
+      "epoch": 2.7217093115273014,
+      "grad_norm": 0.08967737853527069,
+      "learning_rate": 5.288908245646374e-06,
+      "loss": 0.1199,
+      "step": 1290
+    },
+    {
+      "epoch": 2.7217093115273014,
+      "eval_loss": 0.11449629813432693,
+      "eval_runtime": 43.3857,
+      "eval_samples_per_second": 4.61,
+      "eval_steps_per_second": 4.61,
+      "step": 1290
+    },
+    {
+      "epoch": 2.742811922975468,
+      "grad_norm": 0.08780141174793243,
+      "learning_rate": 4.5293187503709145e-06,
+      "loss": 0.1227,
+      "step": 1300
+    },
+    {
+      "epoch": 2.763914534423635,
+      "grad_norm": 0.084247887134552,
+      "learning_rate": 3.827327180689233e-06,
+      "loss": 0.118,
+      "step": 1310
+    },
+    {
+      "epoch": 2.7850171458718016,
+      "grad_norm": 0.0994938537478447,
+      "learning_rate": 3.183357051524094e-06,
+      "loss": 0.1117,
+      "step": 1320
+    },
+    {
+      "epoch": 2.7850171458718016,
+      "eval_loss": 0.11442971974611282,
+      "eval_runtime": 43.583,
+      "eval_samples_per_second": 4.589,
+      "eval_steps_per_second": 4.589,
+      "step": 1320
+    },
+    {
+      "epoch": 2.8061197573199683,
+      "grad_norm": 0.08884406089782715,
+      "learning_rate": 2.5977968731814793e-06,
+      "loss": 0.1201,
+      "step": 1330
+    },
+    {
+      "epoch": 2.827222368768135,
+      "grad_norm": 0.07794331759214401,
+      "learning_rate": 2.0709999169604035e-06,
+      "loss": 0.1156,
+      "step": 1340
+    },
+    {
+      "epoch": 2.8483249802163018,
+      "grad_norm": 0.08900859951972961,
+      "learning_rate": 1.6032840020226314e-06,
+      "loss": 0.1216,
+      "step": 1350
+    },
+    {
+      "epoch": 2.8483249802163018,
+      "eval_loss": 0.1145409420132637,
+      "eval_runtime": 43.2122,
+      "eval_samples_per_second": 4.628,
+      "eval_steps_per_second": 4.628,
+      "step": 1350
+    },
+    {
+      "epoch": 2.8694275916644685,
+      "grad_norm": 0.10006270557641983,
+      "learning_rate": 1.1949313036508257e-06,
+      "loss": 0.1209,
+      "step": 1360
+    },
+    {
+      "epoch": 2.890530203112635,
+      "grad_norm": 0.08598820120096207,
+      "learning_rate": 8.46188183010832e-07,
+      "loss": 0.1176,
+      "step": 1370
+    },
+    {
+      "epoch": 2.911632814560802,
+      "grad_norm": 0.0863473117351532,
+      "learning_rate": 5.572650385208045e-07,
+      "loss": 0.1215,
+      "step": 1380
+    },
+    {
+      "epoch": 2.911632814560802,
+      "eval_loss": 0.1144556924700737,
+      "eval_runtime": 43.2455,
+      "eval_samples_per_second": 4.625,
+      "eval_steps_per_second": 4.625,
+      "step": 1380
+    },
+    {
+      "epoch": 2.9327354260089686,
+      "grad_norm": 0.07715385407209396,
+      "learning_rate": 3.2833617891676604e-07,
+      "loss": 0.1177,
+      "step": 1390
+    },
+    {
+      "epoch": 2.9538380374571354,
+      "grad_norm": 0.10536118596792221,
+      "learning_rate": 1.595397180913949e-07,
+      "loss": 0.1165,
+      "step": 1400
+    },
+    {
+      "epoch": 2.974940648905302,
+      "grad_norm": 0.09866279363632202,
+      "learning_rate": 5.097749176916633e-08,
+      "loss": 0.1147,
+      "step": 1410
+    },
+    {
+      "epoch": 2.974940648905302,
+      "eval_loss": 0.11441905051469803,
+      "eval_runtime": 43.3669,
+      "eval_samples_per_second": 4.612,
+      "eval_steps_per_second": 4.612,
+      "step": 1410
+    },
+    {
+      "epoch": 2.996043260353469,
+      "grad_norm": 0.06903047114610672,
+      "learning_rate": 2.7149960683758858e-09,
+      "loss": 0.1151,
+      "step": 1420
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1422,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0750749167212237e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1422/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a190647831ef4d240aaa100e304429580fe89ce26089d2a605758671e6ef9b4c
+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:f9a7cb39dff391e65fb357955777e5768cdf8cdf4c0b1acebd06048fcbbd0ed6
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4146778673332408b37d5dd9ea42e679b9f75abf1ebd2daf39f1753ce14566
+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
+}