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-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1638/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": [
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_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:b0ee1347b361c2231ff892eb70c3bb763d10e7762b727c3c1a59b58247e28e9b
+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-1600/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-1600/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": [
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35ae40e501e7ce04e0bf8caca6b6255606a6835fa1482dfb4b463e80ae7e1bc
+size 528550256

checkpoint-1600/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-1600/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-1600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67440f3878d71dbb9f1854c730ae2592e0b53d3667b562d29d8fa30972576846
+size 1057397963

checkpoint-1600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc8e1922203ac1eb0fa75fe7cbce0c0813ef8239ea1d44b77ba87693caebd08
+size 14645

checkpoint-1600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765d444c09a68f357a3b73f7125359c06bf1dc213c88afef1b769aa8afc2da8a
+size 1465

checkpoint-1600/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-1600/tokenizer.json

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

checkpoint-1600/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-1600/trainer_state.json

@@ -0,0 +1,1578 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.931896354047237,
+  "eval_steps": 30,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018344416418252695,
+      "grad_norm": 11.986655235290527,
+      "learning_rate": 1.0975609756097562e-05,
+      "loss": 2.8049,
+      "step": 10
+    },
+    {
+      "epoch": 0.03668883283650539,
+      "grad_norm": 1.3442561626434326,
+      "learning_rate": 2.3170731707317075e-05,
+      "loss": 1.2643,
+      "step": 20
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "grad_norm": 1.0081877708435059,
+      "learning_rate": 3.5365853658536584e-05,
+      "loss": 0.7278,
+      "step": 30
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "eval_loss": 0.6342164874076843,
+      "eval_runtime": 47.3806,
+      "eval_samples_per_second": 4.854,
+      "eval_steps_per_second": 4.854,
+      "step": 30
+    },
+    {
+      "epoch": 0.07337766567301078,
+      "grad_norm": 0.8855087757110596,
+      "learning_rate": 4.75609756097561e-05,
+      "loss": 0.5154,
+      "step": 40
+    },
+    {
+      "epoch": 0.09172208209126347,
+      "grad_norm": 0.7658259272575378,
+      "learning_rate": 5.975609756097561e-05,
+      "loss": 0.4091,
+      "step": 50
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "grad_norm": 1.1029750108718872,
+      "learning_rate": 7.195121951219513e-05,
+      "loss": 0.3197,
+      "step": 60
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "eval_loss": 0.26837778091430664,
+      "eval_runtime": 47.1026,
+      "eval_samples_per_second": 4.883,
+      "eval_steps_per_second": 4.883,
+      "step": 60
+    },
+    {
+      "epoch": 0.12841091492776885,
+      "grad_norm": 0.5400053262710571,
+      "learning_rate": 8.414634146341464e-05,
+      "loss": 0.2753,
+      "step": 70
+    },
+    {
+      "epoch": 0.14675533134602156,
+      "grad_norm": 0.5874791145324707,
+      "learning_rate": 9.634146341463415e-05,
+      "loss": 0.243,
+      "step": 80
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "grad_norm": 0.47156110405921936,
+      "learning_rate": 0.00010853658536585367,
+      "loss": 0.2144,
+      "step": 90
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "eval_loss": 0.18793882429599762,
+      "eval_runtime": 46.9461,
+      "eval_samples_per_second": 4.899,
+      "eval_steps_per_second": 4.899,
+      "step": 90
+    },
+    {
+      "epoch": 0.18344416418252693,
+      "grad_norm": 0.6732025146484375,
+      "learning_rate": 0.00012073170731707318,
+      "loss": 0.1804,
+      "step": 100
+    },
+    {
+      "epoch": 0.20178858060077964,
+      "grad_norm": 0.4138810336589813,
+      "learning_rate": 0.0001329268292682927,
+      "loss": 0.1704,
+      "step": 110
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "grad_norm": 0.3548312783241272,
+      "learning_rate": 0.0001451219512195122,
+      "loss": 0.1642,
+      "step": 120
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "eval_loss": 0.14807145297527313,
+      "eval_runtime": 47.16,
+      "eval_samples_per_second": 4.877,
+      "eval_steps_per_second": 4.877,
+      "step": 120
+    },
+    {
+      "epoch": 0.238477413437285,
+      "grad_norm": 0.5005571842193604,
+      "learning_rate": 0.00015731707317073173,
+      "loss": 0.1688,
+      "step": 130
+    },
+    {
+      "epoch": 0.2568218298555377,
+      "grad_norm": 0.4382654130458832,
+      "learning_rate": 0.00016951219512195123,
+      "loss": 0.1479,
+      "step": 140
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "grad_norm": 0.3288620114326477,
+      "learning_rate": 0.00018170731707317075,
+      "loss": 0.1542,
+      "step": 150
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "eval_loss": 0.13612844049930573,
+      "eval_runtime": 46.9463,
+      "eval_samples_per_second": 4.899,
+      "eval_steps_per_second": 4.899,
+      "step": 150
+    },
+    {
+      "epoch": 0.2935106626920431,
+      "grad_norm": 0.48989060521125793,
+      "learning_rate": 0.00019390243902439025,
+      "loss": 0.1536,
+      "step": 160
+    },
+    {
+      "epoch": 0.3118550791102958,
+      "grad_norm": 0.2770105004310608,
+      "learning_rate": 0.00019999432180005332,
+      "loss": 0.1407,
+      "step": 170
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "grad_norm": 1.1703704595565796,
+      "learning_rate": 0.00019994890006944105,
+      "loss": 0.1485,
+      "step": 180
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "eval_loss": 0.13879014551639557,
+      "eval_runtime": 46.9507,
+      "eval_samples_per_second": 4.899,
+      "eval_steps_per_second": 4.899,
+      "step": 180
+    },
+    {
+      "epoch": 0.3485439119468012,
+      "grad_norm": 0.4198831617832184,
+      "learning_rate": 0.0001998580772407242,
+      "loss": 0.1488,
+      "step": 190
+    },
+    {
+      "epoch": 0.36688832836505386,
+      "grad_norm": 0.5260700583457947,
+      "learning_rate": 0.00019972189456954594,
+      "loss": 0.1589,
+      "step": 200
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 0.34109413623809814,
+      "learning_rate": 0.00019954041391594487,
+      "loss": 0.1429,
+      "step": 210
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "eval_loss": 0.1368015855550766,
+      "eval_runtime": 46.9592,
+      "eval_samples_per_second": 4.898,
+      "eval_steps_per_second": 4.898,
+      "step": 210
+    },
+    {
+      "epoch": 0.4035771612015593,
+      "grad_norm": 0.5479871034622192,
+      "learning_rate": 0.00019931371771625544,
+      "loss": 0.1413,
+      "step": 220
+    },
+    {
+      "epoch": 0.42192157761981197,
+      "grad_norm": 0.2849060297012329,
+      "learning_rate": 0.00019904190894566194,
+      "loss": 0.1329,
+      "step": 230
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "grad_norm": 0.2200181484222412,
+      "learning_rate": 0.00019872511107142261,
+      "loss": 0.15,
+      "step": 240
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "eval_loss": 0.12958292663097382,
+      "eval_runtime": 46.9085,
+      "eval_samples_per_second": 4.903,
+      "eval_steps_per_second": 4.903,
+      "step": 240
+    },
+    {
+      "epoch": 0.45861041045631734,
+      "grad_norm": 0.31030556559562683,
+      "learning_rate": 0.00019836346799678568,
+      "loss": 0.1277,
+      "step": 250
+    },
+    {
+      "epoch": 0.47695482687457,
+      "grad_norm": 0.1974978893995285,
+      "learning_rate": 0.00019795714399562197,
+      "loss": 0.1293,
+      "step": 260
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "grad_norm": 0.40907976031303406,
+      "learning_rate": 0.00019750632363780505,
+      "loss": 0.1437,
+      "step": 270
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "eval_loss": 0.12063605338335037,
+      "eval_runtime": 47.4843,
+      "eval_samples_per_second": 4.844,
+      "eval_steps_per_second": 4.844,
+      "step": 270
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 0.37478116154670715,
+      "learning_rate": 0.00019701121170537125,
+      "loss": 0.1388,
+      "step": 280
+    },
+    {
+      "epoch": 0.5319880761293282,
+      "grad_norm": 0.24447715282440186,
+      "learning_rate": 0.00019647203309949913,
+      "loss": 0.1316,
+      "step": 290
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "grad_norm": 0.44361746311187744,
+      "learning_rate": 0.00019588903273834953,
+      "loss": 0.14,
+      "step": 300
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "eval_loss": 0.12744086980819702,
+      "eval_runtime": 47.4937,
+      "eval_samples_per_second": 4.843,
+      "eval_steps_per_second": 4.843,
+      "step": 300
+    },
+    {
+      "epoch": 0.5686769089658336,
+      "grad_norm": 0.734635591506958,
+      "learning_rate": 0.00019526247544581312,
+      "loss": 0.1403,
+      "step": 310
+    },
+    {
+      "epoch": 0.5870213253840862,
+      "grad_norm": 0.16803057491779327,
+      "learning_rate": 0.00019459264583121622,
+      "loss": 0.138,
+      "step": 320
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "grad_norm": 0.29355189204216003,
+      "learning_rate": 0.00019387984816003867,
+      "loss": 0.1292,
+      "step": 330
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "eval_loss": 0.11417385935783386,
+      "eval_runtime": 47.4735,
+      "eval_samples_per_second": 4.845,
+      "eval_steps_per_second": 4.845,
+      "step": 330
+    },
+    {
+      "epoch": 0.6237101582205916,
+      "grad_norm": 0.14734932780265808,
+      "learning_rate": 0.00019312440621570355,
+      "loss": 0.1319,
+      "step": 340
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 0.1784052848815918,
+      "learning_rate": 0.00019232666315250078,
+      "loss": 0.133,
+      "step": 350
+    },
+    {
+      "epoch": 0.660398991057097,
+      "grad_norm": 0.21272070705890656,
+      "learning_rate": 0.00019148698133971155,
+      "loss": 0.1244,
+      "step": 360
+    },
+    {
+      "epoch": 0.660398991057097,
+      "eval_loss": 0.11460884660482407,
+      "eval_runtime": 47.2816,
+      "eval_samples_per_second": 4.864,
+      "eval_steps_per_second": 4.864,
+      "step": 360
+    },
+    {
+      "epoch": 0.6787434074753497,
+      "grad_norm": 0.14382557570934296,
+      "learning_rate": 0.0001906057421970046,
+      "loss": 0.1252,
+      "step": 370
+    },
+    {
+      "epoch": 0.6970878238936024,
+      "grad_norm": 0.138260617852211,
+      "learning_rate": 0.00018968334602117906,
+      "loss": 0.1358,
+      "step": 380
+    },
+    {
+      "epoch": 0.715432240311855,
+      "grad_norm": 0.14098672568798065,
+      "learning_rate": 0.00018872021180433232,
+      "loss": 0.1183,
+      "step": 390
+    },
+    {
+      "epoch": 0.715432240311855,
+      "eval_loss": 0.11497555673122406,
+      "eval_runtime": 47.5258,
+      "eval_samples_per_second": 4.839,
+      "eval_steps_per_second": 4.839,
+      "step": 390
+    },
+    {
+      "epoch": 0.7337766567301077,
+      "grad_norm": 0.5053527355194092,
+      "learning_rate": 0.0001877167770435357,
+      "loss": 0.1181,
+      "step": 400
+    },
+    {
+      "epoch": 0.7521210731483605,
+      "grad_norm": 0.12653136253356934,
+      "learning_rate": 0.00018667349754210457,
+      "loss": 0.1274,
+      "step": 410
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "grad_norm": 0.11409477144479752,
+      "learning_rate": 0.00018559084720255276,
+      "loss": 0.1336,
+      "step": 420
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "eval_loss": 0.11223822832107544,
+      "eval_runtime": 47.4963,
+      "eval_samples_per_second": 4.842,
+      "eval_steps_per_second": 4.842,
+      "step": 420
+    },
+    {
+      "epoch": 0.7888099059848659,
+      "grad_norm": 0.12272641062736511,
+      "learning_rate": 0.00018446931781132553,
+      "loss": 0.1297,
+      "step": 430
+    },
+    {
+      "epoch": 0.8071543224031186,
+      "grad_norm": 0.1796967089176178,
+      "learning_rate": 0.00018330941881540915,
+      "loss": 0.1378,
+      "step": 440
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "grad_norm": 0.11490087956190109,
+      "learning_rate": 0.00018211167709091802,
+      "loss": 0.1262,
+      "step": 450
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "eval_loss": 0.11122166365385056,
+      "eval_runtime": 47.6342,
+      "eval_samples_per_second": 4.828,
+      "eval_steps_per_second": 4.828,
+      "step": 450
+    },
+    {
+      "epoch": 0.8438431552396239,
+      "grad_norm": 0.1275721788406372,
+      "learning_rate": 0.00018087663670376483,
+      "loss": 0.1244,
+      "step": 460
+    },
+    {
+      "epoch": 0.8621875716578766,
+      "grad_norm": 0.10838750749826431,
+      "learning_rate": 0.0001796048586625223,
+      "loss": 0.1278,
+      "step": 470
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "grad_norm": 0.132126122713089,
+      "learning_rate": 0.00017829692066358914,
+      "loss": 0.1365,
+      "step": 480
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "eval_loss": 0.11278139054775238,
+      "eval_runtime": 47.4269,
+      "eval_samples_per_second": 4.85,
+      "eval_steps_per_second": 4.85,
+      "step": 480
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.130384624004364,
+      "learning_rate": 0.0001769534168287752,
+      "loss": 0.1215,
+      "step": 490
+    },
+    {
+      "epoch": 0.9172208209126347,
+      "grad_norm": 0.11609125882387161,
+      "learning_rate": 0.00017557495743542585,
+      "loss": 0.1178,
+      "step": 500
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "grad_norm": 0.12103743851184845,
+      "learning_rate": 0.0001741621686392077,
+      "loss": 0.125,
+      "step": 510
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "eval_loss": 0.11113429814577103,
+      "eval_runtime": 47.2207,
+      "eval_samples_per_second": 4.871,
+      "eval_steps_per_second": 4.871,
+      "step": 510
+    },
+    {
+      "epoch": 0.95390965374914,
+      "grad_norm": 0.13481061160564423,
+      "learning_rate": 0.00017271569218968175,
+      "loss": 0.1233,
+      "step": 520
+    },
+    {
+      "epoch": 0.9722540701673928,
+      "grad_norm": 0.12927769124507904,
+      "learning_rate": 0.00017123618513879295,
+      "loss": 0.1237,
+      "step": 530
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "grad_norm": 0.1044018417596817,
+      "learning_rate": 0.00016972431954240906,
+      "loss": 0.1222,
+      "step": 540
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "eval_loss": 0.11119447648525238,
+      "eval_runtime": 47.6107,
+      "eval_samples_per_second": 4.831,
+      "eval_steps_per_second": 4.831,
+      "step": 540
+    },
+    {
+      "epoch": 1.0073377665673011,
+      "grad_norm": 0.10839453339576721,
+      "learning_rate": 0.0001681807821550438,
+      "loss": 0.1076,
+      "step": 550
+    },
+    {
+      "epoch": 1.0256821829855538,
+      "grad_norm": 0.151426762342453,
+      "learning_rate": 0.00016660627411790329,
+      "loss": 0.1131,
+      "step": 560
+    },
+    {
+      "epoch": 1.0440265994038065,
+      "grad_norm": 0.1167786568403244,
+      "learning_rate": 0.00016500151064039766,
+      "loss": 0.1332,
+      "step": 570
+    },
+    {
+      "epoch": 1.0440265994038065,
+      "eval_loss": 0.11187437176704407,
+      "eval_runtime": 47.4208,
+      "eval_samples_per_second": 4.85,
+      "eval_steps_per_second": 4.85,
+      "step": 570
+    },
+    {
+      "epoch": 1.0623710158220592,
+      "grad_norm": 0.0833975151181221,
+      "learning_rate": 0.0001633672206752621,
+      "loss": 0.1236,
+      "step": 580
+    },
+    {
+      "epoch": 1.0807154322403119,
+      "grad_norm": 0.08196871727705002,
+      "learning_rate": 0.00016170414658743488,
+      "loss": 0.1177,
+      "step": 590
+    },
+    {
+      "epoch": 1.0990598486585645,
+      "grad_norm": 0.1361839324235916,
+      "learning_rate": 0.00016001304381684347,
+      "loss": 0.1103,
+      "step": 600
+    },
+    {
+      "epoch": 1.0990598486585645,
+      "eval_loss": 0.11141453683376312,
+      "eval_runtime": 47.4348,
+      "eval_samples_per_second": 4.849,
+      "eval_steps_per_second": 4.849,
+      "step": 600
+    },
+    {
+      "epoch": 1.1174042650768172,
+      "grad_norm": 0.1309792697429657,
+      "learning_rate": 0.00015829468053525102,
+      "loss": 0.1285,
+      "step": 610
+    },
+    {
+      "epoch": 1.13574868149507,
+      "grad_norm": 0.09610354155302048,
+      "learning_rate": 0.00015654983729731977,
+      "loss": 0.1278,
+      "step": 620
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "grad_norm": 0.08027515560388565,
+      "learning_rate": 0.00015477930668604916,
+      "loss": 0.117,
+      "step": 630
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "eval_loss": 0.11004864424467087,
+      "eval_runtime": 47.4023,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 4.852,
+      "step": 630
+    },
+    {
+      "epoch": 1.1724375143315753,
+      "grad_norm": 0.25526005029678345,
+      "learning_rate": 0.00015298389295275098,
+      "loss": 0.1179,
+      "step": 640
+    },
+    {
+      "epoch": 1.190781930749828,
+      "grad_norm": 0.2913426458835602,
+      "learning_rate": 0.00015116441165172328,
+      "loss": 0.1226,
+      "step": 650
+    },
+    {
+      "epoch": 1.2091263471680807,
+      "grad_norm": 0.12240047007799149,
+      "learning_rate": 0.00014932168926979074,
+      "loss": 0.1206,
+      "step": 660
+    },
+    {
+      "epoch": 1.2091263471680807,
+      "eval_loss": 0.11615979671478271,
+      "eval_runtime": 47.3821,
+      "eval_samples_per_second": 4.854,
+      "eval_steps_per_second": 4.854,
+      "step": 660
+    },
+    {
+      "epoch": 1.2274707635863333,
+      "grad_norm": 0.5275110602378845,
+      "learning_rate": 0.00014745656285087866,
+      "loss": 0.131,
+      "step": 670
+    },
+    {
+      "epoch": 1.245815180004586,
+      "grad_norm": 0.08649874478578568,
+      "learning_rate": 0.00014556987961579146,
+      "loss": 0.1273,
+      "step": 680
+    },
+    {
+      "epoch": 1.264159596422839,
+      "grad_norm": 0.21493305265903473,
+      "learning_rate": 0.00014366249657736866,
+      "loss": 0.1238,
+      "step": 690
+    },
+    {
+      "epoch": 1.264159596422839,
+      "eval_loss": 0.11726190149784088,
+      "eval_runtime": 47.4729,
+      "eval_samples_per_second": 4.845,
+      "eval_steps_per_second": 4.845,
+      "step": 690
+    },
+    {
+      "epoch": 1.2825040128410916,
+      "grad_norm": 0.2242494374513626,
+      "learning_rate": 0.00014173528015119246,
+      "loss": 0.1267,
+      "step": 700
+    },
+    {
+      "epoch": 1.3008484292593443,
+      "grad_norm": 0.1080465167760849,
+      "learning_rate": 0.0001397891057620247,
+      "loss": 0.1275,
+      "step": 710
+    },
+    {
+      "epoch": 1.319192845677597,
+      "grad_norm": 0.11881080269813538,
+      "learning_rate": 0.00013782485744615096,
+      "loss": 0.1265,
+      "step": 720
+    },
+    {
+      "epoch": 1.319192845677597,
+      "eval_loss": 0.11231047660112381,
+      "eval_runtime": 47.5156,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 720
+    },
+    {
+      "epoch": 1.3375372620958497,
+      "grad_norm": 0.11510378122329712,
+      "learning_rate": 0.0001358434274498134,
+      "loss": 0.118,
+      "step": 730
+    },
+    {
+      "epoch": 1.3558816785141024,
+      "grad_norm": 0.1533641517162323,
+      "learning_rate": 0.00013384571582391393,
+      "loss": 0.1239,
+      "step": 740
+    },
+    {
+      "epoch": 1.374226094932355,
+      "grad_norm": 0.09978242218494415,
+      "learning_rate": 0.00013183263001517224,
+      "loss": 0.1206,
+      "step": 750
+    },
+    {
+      "epoch": 1.374226094932355,
+      "eval_loss": 0.1097174733877182,
+      "eval_runtime": 47.3489,
+      "eval_samples_per_second": 4.858,
+      "eval_steps_per_second": 4.858,
+      "step": 750
+    },
+    {
+      "epoch": 1.3925705113506077,
+      "grad_norm": 0.10042322427034378,
+      "learning_rate": 0.0001298050844539246,
+      "loss": 0.1244,
+      "step": 760
+    },
+    {
+      "epoch": 1.4109149277688604,
+      "grad_norm": 0.09835106879472733,
+      "learning_rate": 0.00012776400013875006,
+      "loss": 0.1157,
+      "step": 770
+    },
+    {
+      "epoch": 1.429259344187113,
+      "grad_norm": 0.0930342748761177,
+      "learning_rate": 0.00012571030421811314,
+      "loss": 0.1236,
+      "step": 780
+    },
+    {
+      "epoch": 1.429259344187113,
+      "eval_loss": 0.11065001785755157,
+      "eval_runtime": 47.4754,
+      "eval_samples_per_second": 4.845,
+      "eval_steps_per_second": 4.845,
+      "step": 780
+    },
+    {
+      "epoch": 1.4476037606053658,
+      "grad_norm": 0.08919622749090195,
+      "learning_rate": 0.0001236449295692131,
+      "loss": 0.1261,
+      "step": 790
+    },
+    {
+      "epoch": 1.4659481770236185,
+      "grad_norm": 0.0871356800198555,
+      "learning_rate": 0.00012156881437423103,
+      "loss": 0.1215,
+      "step": 800
+    },
+    {
+      "epoch": 1.4842925934418711,
+      "grad_norm": 0.11698926240205765,
+      "learning_rate": 0.00011948290169416682,
+      "loss": 0.1269,
+      "step": 810
+    },
+    {
+      "epoch": 1.4842925934418711,
+      "eval_loss": 0.10887381434440613,
+      "eval_runtime": 47.4819,
+      "eval_samples_per_second": 4.844,
+      "eval_steps_per_second": 4.844,
+      "step": 810
+    },
+    {
+      "epoch": 1.5026370098601238,
+      "grad_norm": 0.06746023893356323,
+      "learning_rate": 0.00011738813904046044,
+      "loss": 0.1122,
+      "step": 820
+    },
+    {
+      "epoch": 1.5209814262783765,
+      "grad_norm": 0.09794127196073532,
+      "learning_rate": 0.00011528547794459128,
+      "loss": 0.1161,
+      "step": 830
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 0.15457604825496674,
+      "learning_rate": 0.00011317587352585157,
+      "loss": 0.1281,
+      "step": 840
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "eval_loss": 0.10888072103261948,
+      "eval_runtime": 47.3656,
+      "eval_samples_per_second": 4.856,
+      "eval_steps_per_second": 4.856,
+      "step": 840
+    },
+    {
+      "epoch": 1.5576702591148819,
+      "grad_norm": 0.08662489801645279,
+      "learning_rate": 0.00011106028405749005,
+      "loss": 0.1191,
+      "step": 850
+    },
+    {
+      "epoch": 1.5760146755331346,
+      "grad_norm": 0.08548998087644577,
+      "learning_rate": 0.00010893967053142296,
+      "loss": 0.1196,
+      "step": 860
+    },
+    {
+      "epoch": 1.5943590919513873,
+      "grad_norm": 0.10732567310333252,
+      "learning_rate": 0.00010681499622171005,
+      "loss": 0.1246,
+      "step": 870
+    },
+    {
+      "epoch": 1.5943590919513873,
+      "eval_loss": 0.10937893390655518,
+      "eval_runtime": 47.5072,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 870
+    },
+    {
+      "epoch": 1.61270350836964,
+      "grad_norm": 0.07822810858488083,
+      "learning_rate": 0.00010468722624699401,
+      "loss": 0.1121,
+      "step": 880
+    },
+    {
+      "epoch": 1.6310479247878926,
+      "grad_norm": 0.07400278747081757,
+      "learning_rate": 0.00010255732713210206,
+      "loss": 0.124,
+      "step": 890
+    },
+    {
+      "epoch": 1.6493923412061453,
+      "grad_norm": 0.0789525955915451,
+      "learning_rate": 0.00010042626636900856,
+      "loss": 0.1181,
+      "step": 900
+    },
+    {
+      "epoch": 1.6493923412061453,
+      "eval_loss": 0.10813174396753311,
+      "eval_runtime": 47.5685,
+      "eval_samples_per_second": 4.835,
+      "eval_steps_per_second": 4.835,
+      "step": 900
+    },
+    {
+      "epoch": 1.667736757624398,
+      "grad_norm": 0.07806720584630966,
+      "learning_rate": 9.829501197735866e-05,
+      "loss": 0.1172,
+      "step": 910
+    },
+    {
+      "epoch": 1.6860811740426507,
+      "grad_norm": 0.09959676861763,
+      "learning_rate": 9.616453206475179e-05,
+      "loss": 0.1214,
+      "step": 920
+    },
+    {
+      "epoch": 1.7044255904609034,
+      "grad_norm": 0.07471271604299545,
+      "learning_rate": 9.40357943869858e-05,
+      "loss": 0.1212,
+      "step": 930
+    },
+    {
+      "epoch": 1.7044255904609034,
+      "eval_loss": 0.1081625297665596,
+      "eval_runtime": 47.4204,
+      "eval_samples_per_second": 4.85,
+      "eval_steps_per_second": 4.85,
+      "step": 930
+    },
+    {
+      "epoch": 1.722770006879156,
+      "grad_norm": 0.0786692202091217,
+      "learning_rate": 9.190976590846027e-05,
+      "loss": 0.1187,
+      "step": 940
+    },
+    {
+      "epoch": 1.7411144232974087,
+      "grad_norm": 0.09310892224311829,
+      "learning_rate": 8.978741236293973e-05,
+      "loss": 0.115,
+      "step": 950
+    },
+    {
+      "epoch": 1.7594588397156614,
+      "grad_norm": 0.10510563850402832,
+      "learning_rate": 8.766969781487578e-05,
+      "loss": 0.1254,
+      "step": 960
+    },
+    {
+      "epoch": 1.7594588397156614,
+      "eval_loss": 0.10792473703622818,
+      "eval_runtime": 47.4662,
+      "eval_samples_per_second": 4.846,
+      "eval_steps_per_second": 4.846,
+      "step": 960
+    },
+    {
+      "epoch": 1.777803256133914,
+      "grad_norm": 0.07966180145740509,
+      "learning_rate": 8.555758422148745e-05,
+      "loss": 0.121,
+      "step": 970
+    },
+    {
+      "epoch": 1.7961476725521668,
+      "grad_norm": 0.08049053698778152,
+      "learning_rate": 8.345203099579874e-05,
+      "loss": 0.11,
+      "step": 980
+    },
+    {
+      "epoch": 1.8144920889704195,
+      "grad_norm": 0.06832806766033173,
+      "learning_rate": 8.13539945708319e-05,
+      "loss": 0.1236,
+      "step": 990
+    },
+    {
+      "epoch": 1.8144920889704195,
+      "eval_loss": 0.10886505246162415,
+      "eval_runtime": 47.5036,
+      "eval_samples_per_second": 4.842,
+      "eval_steps_per_second": 4.842,
+      "step": 990
+    },
+    {
+      "epoch": 1.8328365053886724,
+      "grad_norm": 0.08461681008338928,
+      "learning_rate": 7.926442796515429e-05,
+      "loss": 0.1341,
+      "step": 1000
+    },
+    {
+      "epoch": 1.851180921806925,
+      "grad_norm": 0.07851795107126236,
+      "learning_rate": 7.71842803499764e-05,
+      "loss": 0.1306,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8695253382251777,
+      "grad_norm": 0.0859571248292923,
+      "learning_rate": 7.51144966179972e-05,
+      "loss": 0.1155,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8695253382251777,
+      "eval_loss": 0.107667475938797,
+      "eval_runtime": 47.4797,
+      "eval_samples_per_second": 4.844,
+      "eval_steps_per_second": 4.844,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8878697546434304,
+      "grad_norm": 0.08879910409450531,
+      "learning_rate": 7.305601695419323e-05,
+      "loss": 0.1173,
+      "step": 1030
+    },
+    {
+      "epoch": 1.9062141710616831,
+      "grad_norm": 0.07893572747707367,
+      "learning_rate": 7.10097764087462e-05,
+      "loss": 0.1109,
+      "step": 1040
+    },
+    {
+      "epoch": 1.9245585874799358,
+      "grad_norm": 0.0726647600531578,
+      "learning_rate": 6.897670447230262e-05,
+      "loss": 0.1136,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9245585874799358,
+      "eval_loss": 0.10811686515808105,
+      "eval_runtime": 47.401,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 4.852,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9429030038981885,
+      "grad_norm": 0.08151935786008835,
+      "learning_rate": 6.69577246537593e-05,
+      "loss": 0.1145,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9612474203164412,
+      "grad_norm": 0.09550312161445618,
+      "learning_rate": 6.495375406076573e-05,
+      "loss": 0.1215,
+      "step": 1070
+    },
+    {
+      "epoch": 1.9795918367346939,
+      "grad_norm": 0.20997484028339386,
+      "learning_rate": 6.296570298313431e-05,
+      "loss": 0.1222,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9795918367346939,
+      "eval_loss": 0.1070978045463562,
+      "eval_runtime": 47.3536,
+      "eval_samples_per_second": 4.857,
+      "eval_steps_per_second": 4.857,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9979362531529465,
+      "grad_norm": 0.07865249365568161,
+      "learning_rate": 6.099447447934743e-05,
+      "loss": 0.1113,
+      "step": 1090
+    },
+    {
+      "epoch": 2.0146755331346022,
+      "grad_norm": 0.08859091252088547,
+      "learning_rate": 5.904096396634935e-05,
+      "loss": 0.1253,
+      "step": 1100
+    },
+    {
+      "epoch": 2.033019949552855,
+      "grad_norm": 0.08467495441436768,
+      "learning_rate": 5.710605881280939e-05,
+      "loss": 0.1168,
+      "step": 1110
+    },
+    {
+      "epoch": 2.033019949552855,
+      "eval_loss": 0.10781675577163696,
+      "eval_runtime": 47.5138,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 1110
+    },
+    {
+      "epoch": 2.0513643659711076,
+      "grad_norm": 0.07836291193962097,
+      "learning_rate": 5.519063793604067e-05,
+      "loss": 0.1138,
+      "step": 1120
+    },
+    {
+      "epoch": 2.0697087823893603,
+      "grad_norm": 0.10746737569570541,
+      "learning_rate": 5.329557140275801e-05,
+      "loss": 0.1146,
+      "step": 1130
+    },
+    {
+      "epoch": 2.088053198807613,
+      "grad_norm": 0.06803814321756363,
+      "learning_rate": 5.1421720033856216e-05,
+      "loss": 0.1148,
+      "step": 1140
+    },
+    {
+      "epoch": 2.088053198807613,
+      "eval_loss": 0.10701934248209,
+      "eval_runtime": 47.4053,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 4.852,
+      "step": 1140
+    },
+    {
+      "epoch": 2.1063976152258657,
+      "grad_norm": 0.08060242980718613,
+      "learning_rate": 4.9569935013388125e-05,
+      "loss": 0.1099,
+      "step": 1150
+    },
+    {
+      "epoch": 2.1247420316441183,
+      "grad_norm": 0.08353856205940247,
+      "learning_rate": 4.774105750192e-05,
+      "loss": 0.1203,
+      "step": 1160
+    },
+    {
+      "epoch": 2.143086448062371,
+      "grad_norm": 0.08800723403692245,
+      "learning_rate": 4.593591825444028e-05,
+      "loss": 0.112,
+      "step": 1170
+    },
+    {
+      "epoch": 2.143086448062371,
+      "eval_loss": 0.10760512948036194,
+      "eval_runtime": 47.4958,
+      "eval_samples_per_second": 4.843,
+      "eval_steps_per_second": 4.843,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1614308644806237,
+      "grad_norm": 0.07223484665155411,
+      "learning_rate": 4.415533724299471e-05,
+      "loss": 0.1221,
+      "step": 1180
+    },
+    {
+      "epoch": 2.1797752808988764,
+      "grad_norm": 0.07669170200824738,
+      "learning_rate": 4.240012328421997e-05,
+      "loss": 0.1088,
+      "step": 1190
+    },
+    {
+      "epoch": 2.198119697317129,
+      "grad_norm": 0.07591399550437927,
+      "learning_rate": 4.067107367194397e-05,
+      "loss": 0.1115,
+      "step": 1200
+    },
+    {
+      "epoch": 2.198119697317129,
+      "eval_loss": 0.1069360300898552,
+      "eval_runtime": 47.5987,
+      "eval_samples_per_second": 4.832,
+      "eval_steps_per_second": 4.832,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2164641137353818,
+      "grad_norm": 0.0850834846496582,
+      "learning_rate": 3.8968973815020806e-05,
+      "loss": 0.1149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.2348085301536345,
+      "grad_norm": 0.08643563091754913,
+      "learning_rate": 3.729459688056427e-05,
+      "loss": 0.1125,
+      "step": 1220
+    },
+    {
+      "epoch": 2.253152946571887,
+      "grad_norm": 0.07351703196763992,
+      "learning_rate": 3.564870344274185e-05,
+      "loss": 0.1099,
+      "step": 1230
+    },
+    {
+      "epoch": 2.253152946571887,
+      "eval_loss": 0.10722808539867401,
+      "eval_runtime": 47.5417,
+      "eval_samples_per_second": 4.838,
+      "eval_steps_per_second": 4.838,
+      "step": 1230
+    },
+    {
+      "epoch": 2.27149736299014,
+      "grad_norm": 0.09461668133735657,
+      "learning_rate": 3.403204113728933e-05,
+      "loss": 0.1189,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2898417794083925,
+      "grad_norm": 0.09557740390300751,
+      "learning_rate": 3.244534432190225e-05,
+      "loss": 0.1219,
+      "step": 1250
+    },
+    {
+      "epoch": 2.308186195826645,
+      "grad_norm": 0.09171107411384583,
+      "learning_rate": 3.088933374265919e-05,
+      "loss": 0.1199,
+      "step": 1260
+    },
+    {
+      "epoch": 2.308186195826645,
+      "eval_loss": 0.10666479170322418,
+      "eval_runtime": 47.7241,
+      "eval_samples_per_second": 4.819,
+      "eval_steps_per_second": 4.819,
+      "step": 1260
+    },
+    {
+      "epoch": 2.326530612244898,
+      "grad_norm": 0.09569697827100754,
+      "learning_rate": 2.936471620662763e-05,
+      "loss": 0.1018,
+      "step": 1270
+    },
+    {
+      "epoch": 2.3448750286631506,
+      "grad_norm": 0.10778363794088364,
+      "learning_rate": 2.7872184260801838e-05,
+      "loss": 0.1156,
+      "step": 1280
+    },
+    {
+      "epoch": 2.3632194450814032,
+      "grad_norm": 0.07144766300916672,
+      "learning_rate": 2.6412415877518238e-05,
+      "loss": 0.1171,
+      "step": 1290
+    },
+    {
+      "epoch": 2.3632194450814032,
+      "eval_loss": 0.10628043115139008,
+      "eval_runtime": 47.8715,
+      "eval_samples_per_second": 4.805,
+      "eval_steps_per_second": 4.805,
+      "step": 1290
+    },
+    {
+      "epoch": 2.381563861499656,
+      "grad_norm": 0.10883186757564545,
+      "learning_rate": 2.4986074146490967e-05,
+      "loss": 0.115,
+      "step": 1300
+    },
+    {
+      "epoch": 2.3999082779179086,
+      "grad_norm": 0.08375997096300125,
+      "learning_rate": 2.35938069736081e-05,
+      "loss": 0.1134,
+      "step": 1310
+    },
+    {
+      "epoch": 2.4182526943361613,
+      "grad_norm": 0.09004294127225876,
+      "learning_rate": 2.2236246786624792e-05,
+      "loss": 0.1067,
+      "step": 1320
+    },
+    {
+      "epoch": 2.4182526943361613,
+      "eval_loss": 0.10667029023170471,
+      "eval_runtime": 47.8027,
+      "eval_samples_per_second": 4.811,
+      "eval_steps_per_second": 4.811,
+      "step": 1320
+    },
+    {
+      "epoch": 2.436597110754414,
+      "grad_norm": 0.08431920409202576,
+      "learning_rate": 2.091401024788745e-05,
+      "loss": 0.1175,
+      "step": 1330
+    },
+    {
+      "epoch": 2.4549415271726667,
+      "grad_norm": 0.06736938655376434,
+      "learning_rate": 1.962769797421895e-05,
+      "loss": 0.1081,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4732859435909194,
+      "grad_norm": 0.0825665220618248,
+      "learning_rate": 1.83778942640927e-05,
+      "loss": 0.1144,
+      "step": 1350
+    },
+    {
+      "epoch": 2.4732859435909194,
+      "eval_loss": 0.10638684034347534,
+      "eval_runtime": 47.5125,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 1350
+    },
+    {
+      "epoch": 2.491630360009172,
+      "grad_norm": 0.09597857296466827,
+      "learning_rate": 1.716516683221906e-05,
+      "loss": 0.1174,
+      "step": 1360
+    },
+    {
+      "epoch": 2.509974776427425,
+      "grad_norm": 0.087304025888443,
+      "learning_rate": 1.5990066551664906e-05,
+      "loss": 0.1217,
+      "step": 1370
+    },
+    {
+      "epoch": 2.528319192845678,
+      "grad_norm": 0.1020963117480278,
+      "learning_rate": 1.4853127203623252e-05,
+      "loss": 0.1206,
+      "step": 1380
+    },
+    {
+      "epoch": 2.528319192845678,
+      "eval_loss": 0.10611271858215332,
+      "eval_runtime": 47.5951,
+      "eval_samples_per_second": 4.832,
+      "eval_steps_per_second": 4.832,
+      "step": 1380
+    },
+    {
+      "epoch": 2.5466636092639305,
+      "grad_norm": 0.09987211227416992,
+      "learning_rate": 1.3754865234946835e-05,
+      "loss": 0.1237,
+      "step": 1390
+    },
+    {
+      "epoch": 2.5650080256821832,
+      "grad_norm": 0.09537294507026672,
+      "learning_rate": 1.2695779523555829e-05,
+      "loss": 0.1074,
+      "step": 1400
+    },
+    {
+      "epoch": 2.583352442100436,
+      "grad_norm": 0.06951133906841278,
+      "learning_rate": 1.1676351151825804e-05,
+      "loss": 0.1113,
+      "step": 1410
+    },
+    {
+      "epoch": 2.583352442100436,
+      "eval_loss": 0.10620437562465668,
+      "eval_runtime": 47.5731,
+      "eval_samples_per_second": 4.835,
+      "eval_steps_per_second": 4.835,
+      "step": 1410
+    },
+    {
+      "epoch": 2.6016968585186886,
+      "grad_norm": 0.08393154293298721,
+      "learning_rate": 1.0697043188059475e-05,
+      "loss": 0.1082,
+      "step": 1420
+    },
+    {
+      "epoch": 2.6200412749369413,
+      "grad_norm": 0.08919060230255127,
+      "learning_rate": 9.75830047614117e-06,
+      "loss": 0.1129,
+      "step": 1430
+    },
+    {
+      "epoch": 2.638385691355194,
+      "grad_norm": 0.08663026988506317,
+      "learning_rate": 8.860549433469444e-06,
+      "loss": 0.1151,
+      "step": 1440
+    },
+    {
+      "epoch": 2.638385691355194,
+      "eval_loss": 0.10626456141471863,
+      "eval_runtime": 47.3921,
+      "eval_samples_per_second": 4.853,
+      "eval_steps_per_second": 4.853,
+      "step": 1440
+    },
+    {
+      "epoch": 2.6567301077734466,
+      "grad_norm": 0.09450593590736389,
+      "learning_rate": 8.004197857260042e-06,
+      "loss": 0.1154,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6750745241916993,
+      "grad_norm": 0.08700842410326004,
+      "learning_rate": 7.189634739306705e-06,
+      "loss": 0.1113,
+      "step": 1460
+    },
+    {
+      "epoch": 2.693418940609952,
+      "grad_norm": 0.08897579461336136,
+      "learning_rate": 6.4172300892844425e-06,
+      "loss": 0.1068,
+      "step": 1470
+    },
+    {
+      "epoch": 2.693418940609952,
+      "eval_loss": 0.10611724108457565,
+      "eval_runtime": 47.6236,
+      "eval_samples_per_second": 4.83,
+      "eval_steps_per_second": 4.83,
+      "step": 1470
+    },
+    {
+      "epoch": 2.7117633570282047,
+      "grad_norm": 0.08531934022903442,
+      "learning_rate": 5.687334766675123e-06,
+      "loss": 0.1057,
+      "step": 1480
+    },
+    {
+      "epoch": 2.7301077734464574,
+      "grad_norm": 0.08912410587072372,
+      "learning_rate": 5.000280321392004e-06,
+      "loss": 0.1179,
+      "step": 1490
+    },
+    {
+      "epoch": 2.74845218986471,
+      "grad_norm": 0.0903608500957489,
+      "learning_rate": 4.356378843175446e-06,
+      "loss": 0.1137,
+      "step": 1500
+    },
+    {
+      "epoch": 2.74845218986471,
+      "eval_loss": 0.10605704039335251,
+      "eval_runtime": 47.5904,
+      "eval_samples_per_second": 4.833,
+      "eval_steps_per_second": 4.833,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7667966062829628,
+      "grad_norm": 0.08206541836261749,
+      "learning_rate": 3.75592281982835e-06,
+      "loss": 0.121,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7851410227012154,
+      "grad_norm": 0.08107905834913254,
+      "learning_rate": 3.1991850043555425e-06,
+      "loss": 0.1141,
+      "step": 1520
+    },
+    {
+      "epoch": 2.803485439119468,
+      "grad_norm": 0.09001165628433228,
+      "learning_rate": 2.6864182910676273e-06,
+      "loss": 0.1135,
+      "step": 1530
+    },
+    {
+      "epoch": 2.803485439119468,
+      "eval_loss": 0.10597212612628937,
+      "eval_runtime": 47.6034,
+      "eval_samples_per_second": 4.832,
+      "eval_steps_per_second": 4.832,
+      "step": 1530
+    },
+    {
+      "epoch": 2.821829855537721,
+      "grad_norm": 0.08551483601331711,
+      "learning_rate": 2.2178556007054872e-06,
+      "loss": 0.1209,
+      "step": 1540
+    },
+    {
+      "epoch": 2.8401742719559735,
+      "grad_norm": 0.09350485354661942,
+      "learning_rate": 1.793709774637653e-06,
+      "loss": 0.1174,
+      "step": 1550
+    },
+    {
+      "epoch": 2.858518688374226,
+      "grad_norm": 0.08843007683753967,
+      "learning_rate": 1.41417347817856e-06,
+      "loss": 0.1146,
+      "step": 1560
+    },
+    {
+      "epoch": 2.858518688374226,
+      "eval_loss": 0.10600461810827255,
+      "eval_runtime": 47.5109,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 1560
+    },
+    {
+      "epoch": 2.876863104792479,
+      "grad_norm": 0.0968756377696991,
+      "learning_rate": 1.079419113071678e-06,
+      "loss": 0.1239,
+      "step": 1570
+    },
+    {
+      "epoch": 2.8952075212107315,
+      "grad_norm": 0.09828708320856094,
+      "learning_rate": 7.895987391771997e-07,
+      "loss": 0.1206,
+      "step": 1580
+    },
+    {
+      "epoch": 2.9135519376289842,
+      "grad_norm": 0.09327838569879532,
+      "learning_rate": 5.448440053999137e-07,
+      "loss": 0.1173,
+      "step": 1590
+    },
+    {
+      "epoch": 2.9135519376289842,
+      "eval_loss": 0.10602891445159912,
+      "eval_runtime": 47.5894,
+      "eval_samples_per_second": 4.833,
+      "eval_steps_per_second": 4.833,
+      "step": 1590
+    },
+    {
+      "epoch": 2.931896354047237,
+      "grad_norm": 0.07366887480020523,
+      "learning_rate": 3.45266089888574e-07,
+      "loss": 0.1076,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1638,
+  "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": 2.2220701474596557e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb94d765a48e318252257e53de978a3a40e6c28abef27316e8b307b4e3c5023
+size 5777

checkpoint-1638/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-1638/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": [
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1638/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ee1347b361c2231ff892eb70c3bb763d10e7762b727c3c1a59b58247e28e9b
+size 528550256

checkpoint-1638/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-1638/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-1638/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fb79b958614db6501a293d2d46ed691065466a21c04e45aafd46b671acfc25
+size 1057397963

checkpoint-1638/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24742996ab93a4dd79e3bb6d7a2fee3d91076ae07e0f0252fe59b3acd263bbb2
+size 14645

checkpoint-1638/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30221d2371277d9c2ee0a99b44f86b7d2fe6174ffcee6c591737073fbc903359
+size 1465

checkpoint-1638/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-1638/tokenizer.json

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

checkpoint-1638/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-1638/trainer_state.json

@@ -0,0 +1,1607 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 30,
+  "global_step": 1638,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018344416418252695,
+      "grad_norm": 11.986655235290527,
+      "learning_rate": 1.0975609756097562e-05,
+      "loss": 2.8049,
+      "step": 10
+    },
+    {
+      "epoch": 0.03668883283650539,
+      "grad_norm": 1.3442561626434326,
+      "learning_rate": 2.3170731707317075e-05,
+      "loss": 1.2643,
+      "step": 20
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "grad_norm": 1.0081877708435059,
+      "learning_rate": 3.5365853658536584e-05,
+      "loss": 0.7278,
+      "step": 30
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "eval_loss": 0.6342164874076843,
+      "eval_runtime": 47.3806,
+      "eval_samples_per_second": 4.854,
+      "eval_steps_per_second": 4.854,
+      "step": 30
+    },
+    {
+      "epoch": 0.07337766567301078,
+      "grad_norm": 0.8855087757110596,
+      "learning_rate": 4.75609756097561e-05,
+      "loss": 0.5154,
+      "step": 40
+    },
+    {
+      "epoch": 0.09172208209126347,
+      "grad_norm": 0.7658259272575378,
+      "learning_rate": 5.975609756097561e-05,
+      "loss": 0.4091,
+      "step": 50
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "grad_norm": 1.1029750108718872,
+      "learning_rate": 7.195121951219513e-05,
+      "loss": 0.3197,
+      "step": 60
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "eval_loss": 0.26837778091430664,
+      "eval_runtime": 47.1026,
+      "eval_samples_per_second": 4.883,
+      "eval_steps_per_second": 4.883,
+      "step": 60
+    },
+    {
+      "epoch": 0.12841091492776885,
+      "grad_norm": 0.5400053262710571,
+      "learning_rate": 8.414634146341464e-05,
+      "loss": 0.2753,
+      "step": 70
+    },
+    {
+      "epoch": 0.14675533134602156,
+      "grad_norm": 0.5874791145324707,
+      "learning_rate": 9.634146341463415e-05,
+      "loss": 0.243,
+      "step": 80
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "grad_norm": 0.47156110405921936,
+      "learning_rate": 0.00010853658536585367,
+      "loss": 0.2144,
+      "step": 90
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "eval_loss": 0.18793882429599762,
+      "eval_runtime": 46.9461,
+      "eval_samples_per_second": 4.899,
+      "eval_steps_per_second": 4.899,
+      "step": 90
+    },
+    {
+      "epoch": 0.18344416418252693,
+      "grad_norm": 0.6732025146484375,
+      "learning_rate": 0.00012073170731707318,
+      "loss": 0.1804,
+      "step": 100
+    },
+    {
+      "epoch": 0.20178858060077964,
+      "grad_norm": 0.4138810336589813,
+      "learning_rate": 0.0001329268292682927,
+      "loss": 0.1704,
+      "step": 110
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "grad_norm": 0.3548312783241272,
+      "learning_rate": 0.0001451219512195122,
+      "loss": 0.1642,
+      "step": 120
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "eval_loss": 0.14807145297527313,
+      "eval_runtime": 47.16,
+      "eval_samples_per_second": 4.877,
+      "eval_steps_per_second": 4.877,
+      "step": 120
+    },
+    {
+      "epoch": 0.238477413437285,
+      "grad_norm": 0.5005571842193604,
+      "learning_rate": 0.00015731707317073173,
+      "loss": 0.1688,
+      "step": 130
+    },
+    {
+      "epoch": 0.2568218298555377,
+      "grad_norm": 0.4382654130458832,
+      "learning_rate": 0.00016951219512195123,
+      "loss": 0.1479,
+      "step": 140
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "grad_norm": 0.3288620114326477,
+      "learning_rate": 0.00018170731707317075,
+      "loss": 0.1542,
+      "step": 150
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "eval_loss": 0.13612844049930573,
+      "eval_runtime": 46.9463,
+      "eval_samples_per_second": 4.899,
+      "eval_steps_per_second": 4.899,
+      "step": 150
+    },
+    {
+      "epoch": 0.2935106626920431,
+      "grad_norm": 0.48989060521125793,
+      "learning_rate": 0.00019390243902439025,
+      "loss": 0.1536,
+      "step": 160
+    },
+    {
+      "epoch": 0.3118550791102958,
+      "grad_norm": 0.2770105004310608,
+      "learning_rate": 0.00019999432180005332,
+      "loss": 0.1407,
+      "step": 170
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "grad_norm": 1.1703704595565796,
+      "learning_rate": 0.00019994890006944105,
+      "loss": 0.1485,
+      "step": 180
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "eval_loss": 0.13879014551639557,
+      "eval_runtime": 46.9507,
+      "eval_samples_per_second": 4.899,
+      "eval_steps_per_second": 4.899,
+      "step": 180
+    },
+    {
+      "epoch": 0.3485439119468012,
+      "grad_norm": 0.4198831617832184,
+      "learning_rate": 0.0001998580772407242,
+      "loss": 0.1488,
+      "step": 190
+    },
+    {
+      "epoch": 0.36688832836505386,
+      "grad_norm": 0.5260700583457947,
+      "learning_rate": 0.00019972189456954594,
+      "loss": 0.1589,
+      "step": 200
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 0.34109413623809814,
+      "learning_rate": 0.00019954041391594487,
+      "loss": 0.1429,
+      "step": 210
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "eval_loss": 0.1368015855550766,
+      "eval_runtime": 46.9592,
+      "eval_samples_per_second": 4.898,
+      "eval_steps_per_second": 4.898,
+      "step": 210
+    },
+    {
+      "epoch": 0.4035771612015593,
+      "grad_norm": 0.5479871034622192,
+      "learning_rate": 0.00019931371771625544,
+      "loss": 0.1413,
+      "step": 220
+    },
+    {
+      "epoch": 0.42192157761981197,
+      "grad_norm": 0.2849060297012329,
+      "learning_rate": 0.00019904190894566194,
+      "loss": 0.1329,
+      "step": 230
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "grad_norm": 0.2200181484222412,
+      "learning_rate": 0.00019872511107142261,
+      "loss": 0.15,
+      "step": 240
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "eval_loss": 0.12958292663097382,
+      "eval_runtime": 46.9085,
+      "eval_samples_per_second": 4.903,
+      "eval_steps_per_second": 4.903,
+      "step": 240
+    },
+    {
+      "epoch": 0.45861041045631734,
+      "grad_norm": 0.31030556559562683,
+      "learning_rate": 0.00019836346799678568,
+      "loss": 0.1277,
+      "step": 250
+    },
+    {
+      "epoch": 0.47695482687457,
+      "grad_norm": 0.1974978893995285,
+      "learning_rate": 0.00019795714399562197,
+      "loss": 0.1293,
+      "step": 260
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "grad_norm": 0.40907976031303406,
+      "learning_rate": 0.00019750632363780505,
+      "loss": 0.1437,
+      "step": 270
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "eval_loss": 0.12063605338335037,
+      "eval_runtime": 47.4843,
+      "eval_samples_per_second": 4.844,
+      "eval_steps_per_second": 4.844,
+      "step": 270
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 0.37478116154670715,
+      "learning_rate": 0.00019701121170537125,
+      "loss": 0.1388,
+      "step": 280
+    },
+    {
+      "epoch": 0.5319880761293282,
+      "grad_norm": 0.24447715282440186,
+      "learning_rate": 0.00019647203309949913,
+      "loss": 0.1316,
+      "step": 290
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "grad_norm": 0.44361746311187744,
+      "learning_rate": 0.00019588903273834953,
+      "loss": 0.14,
+      "step": 300
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "eval_loss": 0.12744086980819702,
+      "eval_runtime": 47.4937,
+      "eval_samples_per_second": 4.843,
+      "eval_steps_per_second": 4.843,
+      "step": 300
+    },
+    {
+      "epoch": 0.5686769089658336,
+      "grad_norm": 0.734635591506958,
+      "learning_rate": 0.00019526247544581312,
+      "loss": 0.1403,
+      "step": 310
+    },
+    {
+      "epoch": 0.5870213253840862,
+      "grad_norm": 0.16803057491779327,
+      "learning_rate": 0.00019459264583121622,
+      "loss": 0.138,
+      "step": 320
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "grad_norm": 0.29355189204216003,
+      "learning_rate": 0.00019387984816003867,
+      "loss": 0.1292,
+      "step": 330
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "eval_loss": 0.11417385935783386,
+      "eval_runtime": 47.4735,
+      "eval_samples_per_second": 4.845,
+      "eval_steps_per_second": 4.845,
+      "step": 330
+    },
+    {
+      "epoch": 0.6237101582205916,
+      "grad_norm": 0.14734932780265808,
+      "learning_rate": 0.00019312440621570355,
+      "loss": 0.1319,
+      "step": 340
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 0.1784052848815918,
+      "learning_rate": 0.00019232666315250078,
+      "loss": 0.133,
+      "step": 350
+    },
+    {
+      "epoch": 0.660398991057097,
+      "grad_norm": 0.21272070705890656,
+      "learning_rate": 0.00019148698133971155,
+      "loss": 0.1244,
+      "step": 360
+    },
+    {
+      "epoch": 0.660398991057097,
+      "eval_loss": 0.11460884660482407,
+      "eval_runtime": 47.2816,
+      "eval_samples_per_second": 4.864,
+      "eval_steps_per_second": 4.864,
+      "step": 360
+    },
+    {
+      "epoch": 0.6787434074753497,
+      "grad_norm": 0.14382557570934296,
+      "learning_rate": 0.0001906057421970046,
+      "loss": 0.1252,
+      "step": 370
+    },
+    {
+      "epoch": 0.6970878238936024,
+      "grad_norm": 0.138260617852211,
+      "learning_rate": 0.00018968334602117906,
+      "loss": 0.1358,
+      "step": 380
+    },
+    {
+      "epoch": 0.715432240311855,
+      "grad_norm": 0.14098672568798065,
+      "learning_rate": 0.00018872021180433232,
+      "loss": 0.1183,
+      "step": 390
+    },
+    {
+      "epoch": 0.715432240311855,
+      "eval_loss": 0.11497555673122406,
+      "eval_runtime": 47.5258,
+      "eval_samples_per_second": 4.839,
+      "eval_steps_per_second": 4.839,
+      "step": 390
+    },
+    {
+      "epoch": 0.7337766567301077,
+      "grad_norm": 0.5053527355194092,
+      "learning_rate": 0.0001877167770435357,
+      "loss": 0.1181,
+      "step": 400
+    },
+    {
+      "epoch": 0.7521210731483605,
+      "grad_norm": 0.12653136253356934,
+      "learning_rate": 0.00018667349754210457,
+      "loss": 0.1274,
+      "step": 410
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "grad_norm": 0.11409477144479752,
+      "learning_rate": 0.00018559084720255276,
+      "loss": 0.1336,
+      "step": 420
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "eval_loss": 0.11223822832107544,
+      "eval_runtime": 47.4963,
+      "eval_samples_per_second": 4.842,
+      "eval_steps_per_second": 4.842,
+      "step": 420
+    },
+    {
+      "epoch": 0.7888099059848659,
+      "grad_norm": 0.12272641062736511,
+      "learning_rate": 0.00018446931781132553,
+      "loss": 0.1297,
+      "step": 430
+    },
+    {
+      "epoch": 0.8071543224031186,
+      "grad_norm": 0.1796967089176178,
+      "learning_rate": 0.00018330941881540915,
+      "loss": 0.1378,
+      "step": 440
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "grad_norm": 0.11490087956190109,
+      "learning_rate": 0.00018211167709091802,
+      "loss": 0.1262,
+      "step": 450
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "eval_loss": 0.11122166365385056,
+      "eval_runtime": 47.6342,
+      "eval_samples_per_second": 4.828,
+      "eval_steps_per_second": 4.828,
+      "step": 450
+    },
+    {
+      "epoch": 0.8438431552396239,
+      "grad_norm": 0.1275721788406372,
+      "learning_rate": 0.00018087663670376483,
+      "loss": 0.1244,
+      "step": 460
+    },
+    {
+      "epoch": 0.8621875716578766,
+      "grad_norm": 0.10838750749826431,
+      "learning_rate": 0.0001796048586625223,
+      "loss": 0.1278,
+      "step": 470
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "grad_norm": 0.132126122713089,
+      "learning_rate": 0.00017829692066358914,
+      "loss": 0.1365,
+      "step": 480
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "eval_loss": 0.11278139054775238,
+      "eval_runtime": 47.4269,
+      "eval_samples_per_second": 4.85,
+      "eval_steps_per_second": 4.85,
+      "step": 480
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.130384624004364,
+      "learning_rate": 0.0001769534168287752,
+      "loss": 0.1215,
+      "step": 490
+    },
+    {
+      "epoch": 0.9172208209126347,
+      "grad_norm": 0.11609125882387161,
+      "learning_rate": 0.00017557495743542585,
+      "loss": 0.1178,
+      "step": 500
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "grad_norm": 0.12103743851184845,
+      "learning_rate": 0.0001741621686392077,
+      "loss": 0.125,
+      "step": 510
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "eval_loss": 0.11113429814577103,
+      "eval_runtime": 47.2207,
+      "eval_samples_per_second": 4.871,
+      "eval_steps_per_second": 4.871,
+      "step": 510
+    },
+    {
+      "epoch": 0.95390965374914,
+      "grad_norm": 0.13481061160564423,
+      "learning_rate": 0.00017271569218968175,
+      "loss": 0.1233,
+      "step": 520
+    },
+    {
+      "epoch": 0.9722540701673928,
+      "grad_norm": 0.12927769124507904,
+      "learning_rate": 0.00017123618513879295,
+      "loss": 0.1237,
+      "step": 530
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "grad_norm": 0.1044018417596817,
+      "learning_rate": 0.00016972431954240906,
+      "loss": 0.1222,
+      "step": 540
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "eval_loss": 0.11119447648525238,
+      "eval_runtime": 47.6107,
+      "eval_samples_per_second": 4.831,
+      "eval_steps_per_second": 4.831,
+      "step": 540
+    },
+    {
+      "epoch": 1.0073377665673011,
+      "grad_norm": 0.10839453339576721,
+      "learning_rate": 0.0001681807821550438,
+      "loss": 0.1076,
+      "step": 550
+    },
+    {
+      "epoch": 1.0256821829855538,
+      "grad_norm": 0.151426762342453,
+      "learning_rate": 0.00016660627411790329,
+      "loss": 0.1131,
+      "step": 560
+    },
+    {
+      "epoch": 1.0440265994038065,
+      "grad_norm": 0.1167786568403244,
+      "learning_rate": 0.00016500151064039766,
+      "loss": 0.1332,
+      "step": 570
+    },
+    {
+      "epoch": 1.0440265994038065,
+      "eval_loss": 0.11187437176704407,
+      "eval_runtime": 47.4208,
+      "eval_samples_per_second": 4.85,
+      "eval_steps_per_second": 4.85,
+      "step": 570
+    },
+    {
+      "epoch": 1.0623710158220592,
+      "grad_norm": 0.0833975151181221,
+      "learning_rate": 0.0001633672206752621,
+      "loss": 0.1236,
+      "step": 580
+    },
+    {
+      "epoch": 1.0807154322403119,
+      "grad_norm": 0.08196871727705002,
+      "learning_rate": 0.00016170414658743488,
+      "loss": 0.1177,
+      "step": 590
+    },
+    {
+      "epoch": 1.0990598486585645,
+      "grad_norm": 0.1361839324235916,
+      "learning_rate": 0.00016001304381684347,
+      "loss": 0.1103,
+      "step": 600
+    },
+    {
+      "epoch": 1.0990598486585645,
+      "eval_loss": 0.11141453683376312,
+      "eval_runtime": 47.4348,
+      "eval_samples_per_second": 4.849,
+      "eval_steps_per_second": 4.849,
+      "step": 600
+    },
+    {
+      "epoch": 1.1174042650768172,
+      "grad_norm": 0.1309792697429657,
+      "learning_rate": 0.00015829468053525102,
+      "loss": 0.1285,
+      "step": 610
+    },
+    {
+      "epoch": 1.13574868149507,
+      "grad_norm": 0.09610354155302048,
+      "learning_rate": 0.00015654983729731977,
+      "loss": 0.1278,
+      "step": 620
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "grad_norm": 0.08027515560388565,
+      "learning_rate": 0.00015477930668604916,
+      "loss": 0.117,
+      "step": 630
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "eval_loss": 0.11004864424467087,
+      "eval_runtime": 47.4023,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 4.852,
+      "step": 630
+    },
+    {
+      "epoch": 1.1724375143315753,
+      "grad_norm": 0.25526005029678345,
+      "learning_rate": 0.00015298389295275098,
+      "loss": 0.1179,
+      "step": 640
+    },
+    {
+      "epoch": 1.190781930749828,
+      "grad_norm": 0.2913426458835602,
+      "learning_rate": 0.00015116441165172328,
+      "loss": 0.1226,
+      "step": 650
+    },
+    {
+      "epoch": 1.2091263471680807,
+      "grad_norm": 0.12240047007799149,
+      "learning_rate": 0.00014932168926979074,
+      "loss": 0.1206,
+      "step": 660
+    },
+    {
+      "epoch": 1.2091263471680807,
+      "eval_loss": 0.11615979671478271,
+      "eval_runtime": 47.3821,
+      "eval_samples_per_second": 4.854,
+      "eval_steps_per_second": 4.854,
+      "step": 660
+    },
+    {
+      "epoch": 1.2274707635863333,
+      "grad_norm": 0.5275110602378845,
+      "learning_rate": 0.00014745656285087866,
+      "loss": 0.131,
+      "step": 670
+    },
+    {
+      "epoch": 1.245815180004586,
+      "grad_norm": 0.08649874478578568,
+      "learning_rate": 0.00014556987961579146,
+      "loss": 0.1273,
+      "step": 680
+    },
+    {
+      "epoch": 1.264159596422839,
+      "grad_norm": 0.21493305265903473,
+      "learning_rate": 0.00014366249657736866,
+      "loss": 0.1238,
+      "step": 690
+    },
+    {
+      "epoch": 1.264159596422839,
+      "eval_loss": 0.11726190149784088,
+      "eval_runtime": 47.4729,
+      "eval_samples_per_second": 4.845,
+      "eval_steps_per_second": 4.845,
+      "step": 690
+    },
+    {
+      "epoch": 1.2825040128410916,
+      "grad_norm": 0.2242494374513626,
+      "learning_rate": 0.00014173528015119246,
+      "loss": 0.1267,
+      "step": 700
+    },
+    {
+      "epoch": 1.3008484292593443,
+      "grad_norm": 0.1080465167760849,
+      "learning_rate": 0.0001397891057620247,
+      "loss": 0.1275,
+      "step": 710
+    },
+    {
+      "epoch": 1.319192845677597,
+      "grad_norm": 0.11881080269813538,
+      "learning_rate": 0.00013782485744615096,
+      "loss": 0.1265,
+      "step": 720
+    },
+    {
+      "epoch": 1.319192845677597,
+      "eval_loss": 0.11231047660112381,
+      "eval_runtime": 47.5156,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 720
+    },
+    {
+      "epoch": 1.3375372620958497,
+      "grad_norm": 0.11510378122329712,
+      "learning_rate": 0.0001358434274498134,
+      "loss": 0.118,
+      "step": 730
+    },
+    {
+      "epoch": 1.3558816785141024,
+      "grad_norm": 0.1533641517162323,
+      "learning_rate": 0.00013384571582391393,
+      "loss": 0.1239,
+      "step": 740
+    },
+    {
+      "epoch": 1.374226094932355,
+      "grad_norm": 0.09978242218494415,
+      "learning_rate": 0.00013183263001517224,
+      "loss": 0.1206,
+      "step": 750
+    },
+    {
+      "epoch": 1.374226094932355,
+      "eval_loss": 0.1097174733877182,
+      "eval_runtime": 47.3489,
+      "eval_samples_per_second": 4.858,
+      "eval_steps_per_second": 4.858,
+      "step": 750
+    },
+    {
+      "epoch": 1.3925705113506077,
+      "grad_norm": 0.10042322427034378,
+      "learning_rate": 0.0001298050844539246,
+      "loss": 0.1244,
+      "step": 760
+    },
+    {
+      "epoch": 1.4109149277688604,
+      "grad_norm": 0.09835106879472733,
+      "learning_rate": 0.00012776400013875006,
+      "loss": 0.1157,
+      "step": 770
+    },
+    {
+      "epoch": 1.429259344187113,
+      "grad_norm": 0.0930342748761177,
+      "learning_rate": 0.00012571030421811314,
+      "loss": 0.1236,
+      "step": 780
+    },
+    {
+      "epoch": 1.429259344187113,
+      "eval_loss": 0.11065001785755157,
+      "eval_runtime": 47.4754,
+      "eval_samples_per_second": 4.845,
+      "eval_steps_per_second": 4.845,
+      "step": 780
+    },
+    {
+      "epoch": 1.4476037606053658,
+      "grad_norm": 0.08919622749090195,
+      "learning_rate": 0.0001236449295692131,
+      "loss": 0.1261,
+      "step": 790
+    },
+    {
+      "epoch": 1.4659481770236185,
+      "grad_norm": 0.0871356800198555,
+      "learning_rate": 0.00012156881437423103,
+      "loss": 0.1215,
+      "step": 800
+    },
+    {
+      "epoch": 1.4842925934418711,
+      "grad_norm": 0.11698926240205765,
+      "learning_rate": 0.00011948290169416682,
+      "loss": 0.1269,
+      "step": 810
+    },
+    {
+      "epoch": 1.4842925934418711,
+      "eval_loss": 0.10887381434440613,
+      "eval_runtime": 47.4819,
+      "eval_samples_per_second": 4.844,
+      "eval_steps_per_second": 4.844,
+      "step": 810
+    },
+    {
+      "epoch": 1.5026370098601238,
+      "grad_norm": 0.06746023893356323,
+      "learning_rate": 0.00011738813904046044,
+      "loss": 0.1122,
+      "step": 820
+    },
+    {
+      "epoch": 1.5209814262783765,
+      "grad_norm": 0.09794127196073532,
+      "learning_rate": 0.00011528547794459128,
+      "loss": 0.1161,
+      "step": 830
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 0.15457604825496674,
+      "learning_rate": 0.00011317587352585157,
+      "loss": 0.1281,
+      "step": 840
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "eval_loss": 0.10888072103261948,
+      "eval_runtime": 47.3656,
+      "eval_samples_per_second": 4.856,
+      "eval_steps_per_second": 4.856,
+      "step": 840
+    },
+    {
+      "epoch": 1.5576702591148819,
+      "grad_norm": 0.08662489801645279,
+      "learning_rate": 0.00011106028405749005,
+      "loss": 0.1191,
+      "step": 850
+    },
+    {
+      "epoch": 1.5760146755331346,
+      "grad_norm": 0.08548998087644577,
+      "learning_rate": 0.00010893967053142296,
+      "loss": 0.1196,
+      "step": 860
+    },
+    {
+      "epoch": 1.5943590919513873,
+      "grad_norm": 0.10732567310333252,
+      "learning_rate": 0.00010681499622171005,
+      "loss": 0.1246,
+      "step": 870
+    },
+    {
+      "epoch": 1.5943590919513873,
+      "eval_loss": 0.10937893390655518,
+      "eval_runtime": 47.5072,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 870
+    },
+    {
+      "epoch": 1.61270350836964,
+      "grad_norm": 0.07822810858488083,
+      "learning_rate": 0.00010468722624699401,
+      "loss": 0.1121,
+      "step": 880
+    },
+    {
+      "epoch": 1.6310479247878926,
+      "grad_norm": 0.07400278747081757,
+      "learning_rate": 0.00010255732713210206,
+      "loss": 0.124,
+      "step": 890
+    },
+    {
+      "epoch": 1.6493923412061453,
+      "grad_norm": 0.0789525955915451,
+      "learning_rate": 0.00010042626636900856,
+      "loss": 0.1181,
+      "step": 900
+    },
+    {
+      "epoch": 1.6493923412061453,
+      "eval_loss": 0.10813174396753311,
+      "eval_runtime": 47.5685,
+      "eval_samples_per_second": 4.835,
+      "eval_steps_per_second": 4.835,
+      "step": 900
+    },
+    {
+      "epoch": 1.667736757624398,
+      "grad_norm": 0.07806720584630966,
+      "learning_rate": 9.829501197735866e-05,
+      "loss": 0.1172,
+      "step": 910
+    },
+    {
+      "epoch": 1.6860811740426507,
+      "grad_norm": 0.09959676861763,
+      "learning_rate": 9.616453206475179e-05,
+      "loss": 0.1214,
+      "step": 920
+    },
+    {
+      "epoch": 1.7044255904609034,
+      "grad_norm": 0.07471271604299545,
+      "learning_rate": 9.40357943869858e-05,
+      "loss": 0.1212,
+      "step": 930
+    },
+    {
+      "epoch": 1.7044255904609034,
+      "eval_loss": 0.1081625297665596,
+      "eval_runtime": 47.4204,
+      "eval_samples_per_second": 4.85,
+      "eval_steps_per_second": 4.85,
+      "step": 930
+    },
+    {
+      "epoch": 1.722770006879156,
+      "grad_norm": 0.0786692202091217,
+      "learning_rate": 9.190976590846027e-05,
+      "loss": 0.1187,
+      "step": 940
+    },
+    {
+      "epoch": 1.7411144232974087,
+      "grad_norm": 0.09310892224311829,
+      "learning_rate": 8.978741236293973e-05,
+      "loss": 0.115,
+      "step": 950
+    },
+    {
+      "epoch": 1.7594588397156614,
+      "grad_norm": 0.10510563850402832,
+      "learning_rate": 8.766969781487578e-05,
+      "loss": 0.1254,
+      "step": 960
+    },
+    {
+      "epoch": 1.7594588397156614,
+      "eval_loss": 0.10792473703622818,
+      "eval_runtime": 47.4662,
+      "eval_samples_per_second": 4.846,
+      "eval_steps_per_second": 4.846,
+      "step": 960
+    },
+    {
+      "epoch": 1.777803256133914,
+      "grad_norm": 0.07966180145740509,
+      "learning_rate": 8.555758422148745e-05,
+      "loss": 0.121,
+      "step": 970
+    },
+    {
+      "epoch": 1.7961476725521668,
+      "grad_norm": 0.08049053698778152,
+      "learning_rate": 8.345203099579874e-05,
+      "loss": 0.11,
+      "step": 980
+    },
+    {
+      "epoch": 1.8144920889704195,
+      "grad_norm": 0.06832806766033173,
+      "learning_rate": 8.13539945708319e-05,
+      "loss": 0.1236,
+      "step": 990
+    },
+    {
+      "epoch": 1.8144920889704195,
+      "eval_loss": 0.10886505246162415,
+      "eval_runtime": 47.5036,
+      "eval_samples_per_second": 4.842,
+      "eval_steps_per_second": 4.842,
+      "step": 990
+    },
+    {
+      "epoch": 1.8328365053886724,
+      "grad_norm": 0.08461681008338928,
+      "learning_rate": 7.926442796515429e-05,
+      "loss": 0.1341,
+      "step": 1000
+    },
+    {
+      "epoch": 1.851180921806925,
+      "grad_norm": 0.07851795107126236,
+      "learning_rate": 7.71842803499764e-05,
+      "loss": 0.1306,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8695253382251777,
+      "grad_norm": 0.0859571248292923,
+      "learning_rate": 7.51144966179972e-05,
+      "loss": 0.1155,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8695253382251777,
+      "eval_loss": 0.107667475938797,
+      "eval_runtime": 47.4797,
+      "eval_samples_per_second": 4.844,
+      "eval_steps_per_second": 4.844,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8878697546434304,
+      "grad_norm": 0.08879910409450531,
+      "learning_rate": 7.305601695419323e-05,
+      "loss": 0.1173,
+      "step": 1030
+    },
+    {
+      "epoch": 1.9062141710616831,
+      "grad_norm": 0.07893572747707367,
+      "learning_rate": 7.10097764087462e-05,
+      "loss": 0.1109,
+      "step": 1040
+    },
+    {
+      "epoch": 1.9245585874799358,
+      "grad_norm": 0.0726647600531578,
+      "learning_rate": 6.897670447230262e-05,
+      "loss": 0.1136,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9245585874799358,
+      "eval_loss": 0.10811686515808105,
+      "eval_runtime": 47.401,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 4.852,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9429030038981885,
+      "grad_norm": 0.08151935786008835,
+      "learning_rate": 6.69577246537593e-05,
+      "loss": 0.1145,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9612474203164412,
+      "grad_norm": 0.09550312161445618,
+      "learning_rate": 6.495375406076573e-05,
+      "loss": 0.1215,
+      "step": 1070
+    },
+    {
+      "epoch": 1.9795918367346939,
+      "grad_norm": 0.20997484028339386,
+      "learning_rate": 6.296570298313431e-05,
+      "loss": 0.1222,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9795918367346939,
+      "eval_loss": 0.1070978045463562,
+      "eval_runtime": 47.3536,
+      "eval_samples_per_second": 4.857,
+      "eval_steps_per_second": 4.857,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9979362531529465,
+      "grad_norm": 0.07865249365568161,
+      "learning_rate": 6.099447447934743e-05,
+      "loss": 0.1113,
+      "step": 1090
+    },
+    {
+      "epoch": 2.0146755331346022,
+      "grad_norm": 0.08859091252088547,
+      "learning_rate": 5.904096396634935e-05,
+      "loss": 0.1253,
+      "step": 1100
+    },
+    {
+      "epoch": 2.033019949552855,
+      "grad_norm": 0.08467495441436768,
+      "learning_rate": 5.710605881280939e-05,
+      "loss": 0.1168,
+      "step": 1110
+    },
+    {
+      "epoch": 2.033019949552855,
+      "eval_loss": 0.10781675577163696,
+      "eval_runtime": 47.5138,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 1110
+    },
+    {
+      "epoch": 2.0513643659711076,
+      "grad_norm": 0.07836291193962097,
+      "learning_rate": 5.519063793604067e-05,
+      "loss": 0.1138,
+      "step": 1120
+    },
+    {
+      "epoch": 2.0697087823893603,
+      "grad_norm": 0.10746737569570541,
+      "learning_rate": 5.329557140275801e-05,
+      "loss": 0.1146,
+      "step": 1130
+    },
+    {
+      "epoch": 2.088053198807613,
+      "grad_norm": 0.06803814321756363,
+      "learning_rate": 5.1421720033856216e-05,
+      "loss": 0.1148,
+      "step": 1140
+    },
+    {
+      "epoch": 2.088053198807613,
+      "eval_loss": 0.10701934248209,
+      "eval_runtime": 47.4053,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 4.852,
+      "step": 1140
+    },
+    {
+      "epoch": 2.1063976152258657,
+      "grad_norm": 0.08060242980718613,
+      "learning_rate": 4.9569935013388125e-05,
+      "loss": 0.1099,
+      "step": 1150
+    },
+    {
+      "epoch": 2.1247420316441183,
+      "grad_norm": 0.08353856205940247,
+      "learning_rate": 4.774105750192e-05,
+      "loss": 0.1203,
+      "step": 1160
+    },
+    {
+      "epoch": 2.143086448062371,
+      "grad_norm": 0.08800723403692245,
+      "learning_rate": 4.593591825444028e-05,
+      "loss": 0.112,
+      "step": 1170
+    },
+    {
+      "epoch": 2.143086448062371,
+      "eval_loss": 0.10760512948036194,
+      "eval_runtime": 47.4958,
+      "eval_samples_per_second": 4.843,
+      "eval_steps_per_second": 4.843,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1614308644806237,
+      "grad_norm": 0.07223484665155411,
+      "learning_rate": 4.415533724299471e-05,
+      "loss": 0.1221,
+      "step": 1180
+    },
+    {
+      "epoch": 2.1797752808988764,
+      "grad_norm": 0.07669170200824738,
+      "learning_rate": 4.240012328421997e-05,
+      "loss": 0.1088,
+      "step": 1190
+    },
+    {
+      "epoch": 2.198119697317129,
+      "grad_norm": 0.07591399550437927,
+      "learning_rate": 4.067107367194397e-05,
+      "loss": 0.1115,
+      "step": 1200
+    },
+    {
+      "epoch": 2.198119697317129,
+      "eval_loss": 0.1069360300898552,
+      "eval_runtime": 47.5987,
+      "eval_samples_per_second": 4.832,
+      "eval_steps_per_second": 4.832,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2164641137353818,
+      "grad_norm": 0.0850834846496582,
+      "learning_rate": 3.8968973815020806e-05,
+      "loss": 0.1149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.2348085301536345,
+      "grad_norm": 0.08643563091754913,
+      "learning_rate": 3.729459688056427e-05,
+      "loss": 0.1125,
+      "step": 1220
+    },
+    {
+      "epoch": 2.253152946571887,
+      "grad_norm": 0.07351703196763992,
+      "learning_rate": 3.564870344274185e-05,
+      "loss": 0.1099,
+      "step": 1230
+    },
+    {
+      "epoch": 2.253152946571887,
+      "eval_loss": 0.10722808539867401,
+      "eval_runtime": 47.5417,
+      "eval_samples_per_second": 4.838,
+      "eval_steps_per_second": 4.838,
+      "step": 1230
+    },
+    {
+      "epoch": 2.27149736299014,
+      "grad_norm": 0.09461668133735657,
+      "learning_rate": 3.403204113728933e-05,
+      "loss": 0.1189,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2898417794083925,
+      "grad_norm": 0.09557740390300751,
+      "learning_rate": 3.244534432190225e-05,
+      "loss": 0.1219,
+      "step": 1250
+    },
+    {
+      "epoch": 2.308186195826645,
+      "grad_norm": 0.09171107411384583,
+      "learning_rate": 3.088933374265919e-05,
+      "loss": 0.1199,
+      "step": 1260
+    },
+    {
+      "epoch": 2.308186195826645,
+      "eval_loss": 0.10666479170322418,
+      "eval_runtime": 47.7241,
+      "eval_samples_per_second": 4.819,
+      "eval_steps_per_second": 4.819,
+      "step": 1260
+    },
+    {
+      "epoch": 2.326530612244898,
+      "grad_norm": 0.09569697827100754,
+      "learning_rate": 2.936471620662763e-05,
+      "loss": 0.1018,
+      "step": 1270
+    },
+    {
+      "epoch": 2.3448750286631506,
+      "grad_norm": 0.10778363794088364,
+      "learning_rate": 2.7872184260801838e-05,
+      "loss": 0.1156,
+      "step": 1280
+    },
+    {
+      "epoch": 2.3632194450814032,
+      "grad_norm": 0.07144766300916672,
+      "learning_rate": 2.6412415877518238e-05,
+      "loss": 0.1171,
+      "step": 1290
+    },
+    {
+      "epoch": 2.3632194450814032,
+      "eval_loss": 0.10628043115139008,
+      "eval_runtime": 47.8715,
+      "eval_samples_per_second": 4.805,
+      "eval_steps_per_second": 4.805,
+      "step": 1290
+    },
+    {
+      "epoch": 2.381563861499656,
+      "grad_norm": 0.10883186757564545,
+      "learning_rate": 2.4986074146490967e-05,
+      "loss": 0.115,
+      "step": 1300
+    },
+    {
+      "epoch": 2.3999082779179086,
+      "grad_norm": 0.08375997096300125,
+      "learning_rate": 2.35938069736081e-05,
+      "loss": 0.1134,
+      "step": 1310
+    },
+    {
+      "epoch": 2.4182526943361613,
+      "grad_norm": 0.09004294127225876,
+      "learning_rate": 2.2236246786624792e-05,
+      "loss": 0.1067,
+      "step": 1320
+    },
+    {
+      "epoch": 2.4182526943361613,
+      "eval_loss": 0.10667029023170471,
+      "eval_runtime": 47.8027,
+      "eval_samples_per_second": 4.811,
+      "eval_steps_per_second": 4.811,
+      "step": 1320
+    },
+    {
+      "epoch": 2.436597110754414,
+      "grad_norm": 0.08431920409202576,
+      "learning_rate": 2.091401024788745e-05,
+      "loss": 0.1175,
+      "step": 1330
+    },
+    {
+      "epoch": 2.4549415271726667,
+      "grad_norm": 0.06736938655376434,
+      "learning_rate": 1.962769797421895e-05,
+      "loss": 0.1081,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4732859435909194,
+      "grad_norm": 0.0825665220618248,
+      "learning_rate": 1.83778942640927e-05,
+      "loss": 0.1144,
+      "step": 1350
+    },
+    {
+      "epoch": 2.4732859435909194,
+      "eval_loss": 0.10638684034347534,
+      "eval_runtime": 47.5125,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 1350
+    },
+    {
+      "epoch": 2.491630360009172,
+      "grad_norm": 0.09597857296466827,
+      "learning_rate": 1.716516683221906e-05,
+      "loss": 0.1174,
+      "step": 1360
+    },
+    {
+      "epoch": 2.509974776427425,
+      "grad_norm": 0.087304025888443,
+      "learning_rate": 1.5990066551664906e-05,
+      "loss": 0.1217,
+      "step": 1370
+    },
+    {
+      "epoch": 2.528319192845678,
+      "grad_norm": 0.1020963117480278,
+      "learning_rate": 1.4853127203623252e-05,
+      "loss": 0.1206,
+      "step": 1380
+    },
+    {
+      "epoch": 2.528319192845678,
+      "eval_loss": 0.10611271858215332,
+      "eval_runtime": 47.5951,
+      "eval_samples_per_second": 4.832,
+      "eval_steps_per_second": 4.832,
+      "step": 1380
+    },
+    {
+      "epoch": 2.5466636092639305,
+      "grad_norm": 0.09987211227416992,
+      "learning_rate": 1.3754865234946835e-05,
+      "loss": 0.1237,
+      "step": 1390
+    },
+    {
+      "epoch": 2.5650080256821832,
+      "grad_norm": 0.09537294507026672,
+      "learning_rate": 1.2695779523555829e-05,
+      "loss": 0.1074,
+      "step": 1400
+    },
+    {
+      "epoch": 2.583352442100436,
+      "grad_norm": 0.06951133906841278,
+      "learning_rate": 1.1676351151825804e-05,
+      "loss": 0.1113,
+      "step": 1410
+    },
+    {
+      "epoch": 2.583352442100436,
+      "eval_loss": 0.10620437562465668,
+      "eval_runtime": 47.5731,
+      "eval_samples_per_second": 4.835,
+      "eval_steps_per_second": 4.835,
+      "step": 1410
+    },
+    {
+      "epoch": 2.6016968585186886,
+      "grad_norm": 0.08393154293298721,
+      "learning_rate": 1.0697043188059475e-05,
+      "loss": 0.1082,
+      "step": 1420
+    },
+    {
+      "epoch": 2.6200412749369413,
+      "grad_norm": 0.08919060230255127,
+      "learning_rate": 9.75830047614117e-06,
+      "loss": 0.1129,
+      "step": 1430
+    },
+    {
+      "epoch": 2.638385691355194,
+      "grad_norm": 0.08663026988506317,
+      "learning_rate": 8.860549433469444e-06,
+      "loss": 0.1151,
+      "step": 1440
+    },
+    {
+      "epoch": 2.638385691355194,
+      "eval_loss": 0.10626456141471863,
+      "eval_runtime": 47.3921,
+      "eval_samples_per_second": 4.853,
+      "eval_steps_per_second": 4.853,
+      "step": 1440
+    },
+    {
+      "epoch": 2.6567301077734466,
+      "grad_norm": 0.09450593590736389,
+      "learning_rate": 8.004197857260042e-06,
+      "loss": 0.1154,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6750745241916993,
+      "grad_norm": 0.08700842410326004,
+      "learning_rate": 7.189634739306705e-06,
+      "loss": 0.1113,
+      "step": 1460
+    },
+    {
+      "epoch": 2.693418940609952,
+      "grad_norm": 0.08897579461336136,
+      "learning_rate": 6.4172300892844425e-06,
+      "loss": 0.1068,
+      "step": 1470
+    },
+    {
+      "epoch": 2.693418940609952,
+      "eval_loss": 0.10611724108457565,
+      "eval_runtime": 47.6236,
+      "eval_samples_per_second": 4.83,
+      "eval_steps_per_second": 4.83,
+      "step": 1470
+    },
+    {
+      "epoch": 2.7117633570282047,
+      "grad_norm": 0.08531934022903442,
+      "learning_rate": 5.687334766675123e-06,
+      "loss": 0.1057,
+      "step": 1480
+    },
+    {
+      "epoch": 2.7301077734464574,
+      "grad_norm": 0.08912410587072372,
+      "learning_rate": 5.000280321392004e-06,
+      "loss": 0.1179,
+      "step": 1490
+    },
+    {
+      "epoch": 2.74845218986471,
+      "grad_norm": 0.0903608500957489,
+      "learning_rate": 4.356378843175446e-06,
+      "loss": 0.1137,
+      "step": 1500
+    },
+    {
+      "epoch": 2.74845218986471,
+      "eval_loss": 0.10605704039335251,
+      "eval_runtime": 47.5904,
+      "eval_samples_per_second": 4.833,
+      "eval_steps_per_second": 4.833,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7667966062829628,
+      "grad_norm": 0.08206541836261749,
+      "learning_rate": 3.75592281982835e-06,
+      "loss": 0.121,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7851410227012154,
+      "grad_norm": 0.08107905834913254,
+      "learning_rate": 3.1991850043555425e-06,
+      "loss": 0.1141,
+      "step": 1520
+    },
+    {
+      "epoch": 2.803485439119468,
+      "grad_norm": 0.09001165628433228,
+      "learning_rate": 2.6864182910676273e-06,
+      "loss": 0.1135,
+      "step": 1530
+    },
+    {
+      "epoch": 2.803485439119468,
+      "eval_loss": 0.10597212612628937,
+      "eval_runtime": 47.6034,
+      "eval_samples_per_second": 4.832,
+      "eval_steps_per_second": 4.832,
+      "step": 1530
+    },
+    {
+      "epoch": 2.821829855537721,
+      "grad_norm": 0.08551483601331711,
+      "learning_rate": 2.2178556007054872e-06,
+      "loss": 0.1209,
+      "step": 1540
+    },
+    {
+      "epoch": 2.8401742719559735,
+      "grad_norm": 0.09350485354661942,
+      "learning_rate": 1.793709774637653e-06,
+      "loss": 0.1174,
+      "step": 1550
+    },
+    {
+      "epoch": 2.858518688374226,
+      "grad_norm": 0.08843007683753967,
+      "learning_rate": 1.41417347817856e-06,
+      "loss": 0.1146,
+      "step": 1560
+    },
+    {
+      "epoch": 2.858518688374226,
+      "eval_loss": 0.10600461810827255,
+      "eval_runtime": 47.5109,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 1560
+    },
+    {
+      "epoch": 2.876863104792479,
+      "grad_norm": 0.0968756377696991,
+      "learning_rate": 1.079419113071678e-06,
+      "loss": 0.1239,
+      "step": 1570
+    },
+    {
+      "epoch": 2.8952075212107315,
+      "grad_norm": 0.09828708320856094,
+      "learning_rate": 7.895987391771997e-07,
+      "loss": 0.1206,
+      "step": 1580
+    },
+    {
+      "epoch": 2.9135519376289842,
+      "grad_norm": 0.09327838569879532,
+      "learning_rate": 5.448440053999137e-07,
+      "loss": 0.1173,
+      "step": 1590
+    },
+    {
+      "epoch": 2.9135519376289842,
+      "eval_loss": 0.10602891445159912,
+      "eval_runtime": 47.5894,
+      "eval_samples_per_second": 4.833,
+      "eval_steps_per_second": 4.833,
+      "step": 1590
+    },
+    {
+      "epoch": 2.931896354047237,
+      "grad_norm": 0.07366887480020523,
+      "learning_rate": 3.45266089888574e-07,
+      "loss": 0.1076,
+      "step": 1600
+    },
+    {
+      "epoch": 2.9502407704654896,
+      "grad_norm": 0.15931493043899536,
+      "learning_rate": 1.9095564953398593e-07,
+      "loss": 0.1141,
+      "step": 1610
+    },
+    {
+      "epoch": 2.9685851868837423,
+      "grad_norm": 0.08528278023004532,
+      "learning_rate": 8.198277878879168e-08,
+      "loss": 0.1193,
+      "step": 1620
+    },
+    {
+      "epoch": 2.9685851868837423,
+      "eval_loss": 0.10595094412565231,
+      "eval_runtime": 47.6302,
+      "eval_samples_per_second": 4.829,
+      "eval_steps_per_second": 4.829,
+      "step": 1620
+    },
+    {
+      "epoch": 2.986929603301995,
+      "grad_norm": 0.09704465419054031,
+      "learning_rate": 1.8396977827495056e-08,
+      "loss": 0.1112,
+      "step": 1630
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1638,
+  "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": 2.273671664148695e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1638/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb94d765a48e318252257e53de978a3a40e6c28abef27316e8b307b4e3c5023
+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 sha256:55938193609635c9725a9510a60821d086b7be71f75596b8ba5248631091d3e4
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc32479309db8b1c1600b1fefa12cfe8054e23c576ae2091d08d6ef31a4427c
+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
+}