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-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2493/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/sft_alfworld_trajectory_dataset
+- u-10bei/sft_alfworld_trajectory_dataset_v2
+- u-10bei/sft_alfworld_trajectory_dataset_v3
+- 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: 2048
+- 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": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2e40b92d02b9398ad80b68d3c3c85f8f9fce96dfd3baf909c4b75e98bf4174
+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-2400/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-2400/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": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49317395cf596a54314cb91f6bd8387451c3b989e5c0c15e85394da2d5af79ea
+size 528550256

checkpoint-2400/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-2400/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-2400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e4d14d8b4776456b914438a65c4483cebb59e71e14a46ab7a63189d5f7aaf3
+size 1057397963

checkpoint-2400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117a0508586480fca8b90740ecd3f53853a2ee86b2b67a320f0db428d54a1801
+size 14645

checkpoint-2400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae581bfd569d4ccb7dee5019d0aa180e6157d8c65f7133aded35afefd4fa2d5c
+size 1465

checkpoint-2400/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-2400/tokenizer.json

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

checkpoint-2400/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-2400/trainer_state.json

@@ -0,0 +1,2354 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.888888888888889,
+  "eval_steps": 30,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012044564890093345,
+      "grad_norm": 11.71904468536377,
+      "learning_rate": 7.2e-06,
+      "loss": 2.9594,
+      "step": 10
+    },
+    {
+      "epoch": 0.02408912978018669,
+      "grad_norm": 2.4383621215820312,
+      "learning_rate": 1.52e-05,
+      "loss": 1.5501,
+      "step": 20
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "grad_norm": 0.7187284231185913,
+      "learning_rate": 2.32e-05,
+      "loss": 0.7478,
+      "step": 30
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "eval_loss": 0.6954202651977539,
+      "eval_runtime": 81.243,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 30
+    },
+    {
+      "epoch": 0.04817825956037338,
+      "grad_norm": 0.9893588423728943,
+      "learning_rate": 3.12e-05,
+      "loss": 0.6087,
+      "step": 40
+    },
+    {
+      "epoch": 0.06022282445046673,
+      "grad_norm": 0.6181250214576721,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.4514,
+      "step": 50
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "grad_norm": 0.5894028544425964,
+      "learning_rate": 4.72e-05,
+      "loss": 0.3809,
+      "step": 60
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "eval_loss": 0.35219648480415344,
+      "eval_runtime": 80.7477,
+      "eval_samples_per_second": 4.334,
+      "eval_steps_per_second": 2.167,
+      "step": 60
+    },
+    {
+      "epoch": 0.08431195423065342,
+      "grad_norm": 3.429518222808838,
+      "learning_rate": 5.520000000000001e-05,
+      "loss": 0.2992,
+      "step": 70
+    },
+    {
+      "epoch": 0.09635651912074676,
+      "grad_norm": 0.6878916025161743,
+      "learning_rate": 6.32e-05,
+      "loss": 0.2921,
+      "step": 80
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "grad_norm": 0.5862188339233398,
+      "learning_rate": 7.12e-05,
+      "loss": 0.2483,
+      "step": 90
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "eval_loss": 0.22866909205913544,
+      "eval_runtime": 81.2164,
+      "eval_samples_per_second": 4.309,
+      "eval_steps_per_second": 2.155,
+      "step": 90
+    },
+    {
+      "epoch": 0.12044564890093346,
+      "grad_norm": 0.7386724948883057,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 0.2107,
+      "step": 100
+    },
+    {
+      "epoch": 0.1324902137910268,
+      "grad_norm": 0.6922011375427246,
+      "learning_rate": 8.72e-05,
+      "loss": 0.1962,
+      "step": 110
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "grad_norm": 0.4779876470565796,
+      "learning_rate": 9.52e-05,
+      "loss": 0.1741,
+      "step": 120
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "eval_loss": 0.18707558512687683,
+      "eval_runtime": 81.1016,
+      "eval_samples_per_second": 4.316,
+      "eval_steps_per_second": 2.158,
+      "step": 120
+    },
+    {
+      "epoch": 0.1565793435712135,
+      "grad_norm": 0.3711669445037842,
+      "learning_rate": 0.0001032,
+      "loss": 0.1775,
+      "step": 130
+    },
+    {
+      "epoch": 0.16862390846130684,
+      "grad_norm": 0.5507099032402039,
+      "learning_rate": 0.00011120000000000002,
+      "loss": 0.1663,
+      "step": 140
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "grad_norm": 0.6897018551826477,
+      "learning_rate": 0.0001192,
+      "loss": 0.162,
+      "step": 150
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "eval_loss": 0.1689070761203766,
+      "eval_runtime": 81.1763,
+      "eval_samples_per_second": 4.312,
+      "eval_steps_per_second": 2.156,
+      "step": 150
+    },
+    {
+      "epoch": 0.19271303824149352,
+      "grad_norm": 0.30447226762771606,
+      "learning_rate": 0.0001272,
+      "loss": 0.1654,
+      "step": 160
+    },
+    {
+      "epoch": 0.20475760313158686,
+      "grad_norm": 0.36739301681518555,
+      "learning_rate": 0.0001352,
+      "loss": 0.1692,
+      "step": 170
+    },
+    {
+      "epoch": 0.21680216802168023,
+      "grad_norm": 0.42459923028945923,
+      "learning_rate": 0.0001432,
+      "loss": 0.1479,
+      "step": 180
+    },
+    {
+      "epoch": 0.21680216802168023,
+      "eval_loss": 0.16287875175476074,
+      "eval_runtime": 81.3447,
+      "eval_samples_per_second": 4.303,
+      "eval_steps_per_second": 2.151,
+      "step": 180
+    },
+    {
+      "epoch": 0.22884673291177357,
+      "grad_norm": 0.24459399282932281,
+      "learning_rate": 0.00015120000000000002,
+      "loss": 0.1567,
+      "step": 190
+    },
+    {
+      "epoch": 0.2408912978018669,
+      "grad_norm": 0.29077818989753723,
+      "learning_rate": 0.00015920000000000002,
+      "loss": 0.1491,
+      "step": 200
+    },
+    {
+      "epoch": 0.2529358626919603,
+      "grad_norm": 0.3934674561023712,
+      "learning_rate": 0.0001672,
+      "loss": 0.1587,
+      "step": 210
+    },
+    {
+      "epoch": 0.2529358626919603,
+      "eval_loss": 0.1568612903356552,
+      "eval_runtime": 80.9345,
+      "eval_samples_per_second": 4.324,
+      "eval_steps_per_second": 2.162,
+      "step": 210
+    },
+    {
+      "epoch": 0.2649804275820536,
+      "grad_norm": 0.31920939683914185,
+      "learning_rate": 0.0001752,
+      "loss": 0.1622,
+      "step": 220
+    },
+    {
+      "epoch": 0.27702499247214696,
+      "grad_norm": 0.5031167268753052,
+      "learning_rate": 0.0001832,
+      "loss": 0.147,
+      "step": 230
+    },
+    {
+      "epoch": 0.28906955736224027,
+      "grad_norm": 0.2890608310699463,
+      "learning_rate": 0.0001912,
+      "loss": 0.1433,
+      "step": 240
+    },
+    {
+      "epoch": 0.28906955736224027,
+      "eval_loss": 0.15362557768821716,
+      "eval_runtime": 80.9234,
+      "eval_samples_per_second": 4.325,
+      "eval_steps_per_second": 2.163,
+      "step": 240
+    },
+    {
+      "epoch": 0.30111412225233364,
+      "grad_norm": 0.2849373519420624,
+      "learning_rate": 0.00019920000000000002,
+      "loss": 0.1471,
+      "step": 250
+    },
+    {
+      "epoch": 0.313158687142427,
+      "grad_norm": 0.263950914144516,
+      "learning_rate": 0.0001999920550627653,
+      "loss": 0.155,
+      "step": 260
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 0.31182682514190674,
+      "learning_rate": 0.00019996459270297992,
+      "loss": 0.138,
+      "step": 270
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "eval_loss": 0.15008553862571716,
+      "eval_runtime": 80.9483,
+      "eval_samples_per_second": 4.324,
+      "eval_steps_per_second": 2.162,
+      "step": 270
+    },
+    {
+      "epoch": 0.3372478169226137,
+      "grad_norm": 0.41790467500686646,
+      "learning_rate": 0.00019991752022102606,
+      "loss": 0.1472,
+      "step": 280
+    },
+    {
+      "epoch": 0.349292381812707,
+      "grad_norm": 0.29337936639785767,
+      "learning_rate": 0.0001998508468511445,
+      "loss": 0.152,
+      "step": 290
+    },
+    {
+      "epoch": 0.36133694670280037,
+      "grad_norm": 0.1533428430557251,
+      "learning_rate": 0.0001997645856726956,
+      "loss": 0.1427,
+      "step": 300
+    },
+    {
+      "epoch": 0.36133694670280037,
+      "eval_loss": 0.14941252768039703,
+      "eval_runtime": 81.0588,
+      "eval_samples_per_second": 4.318,
+      "eval_steps_per_second": 2.159,
+      "step": 300
+    },
+    {
+      "epoch": 0.37338151159289373,
+      "grad_norm": 0.3626411557197571,
+      "learning_rate": 0.0001996587536075934,
+      "loss": 0.1539,
+      "step": 310
+    },
+    {
+      "epoch": 0.38542607648298705,
+      "grad_norm": 0.3157321810722351,
+      "learning_rate": 0.00019953337141698617,
+      "loss": 0.1457,
+      "step": 320
+    },
+    {
+      "epoch": 0.3974706413730804,
+      "grad_norm": 0.18949578702449799,
+      "learning_rate": 0.00019938846369718348,
+      "loss": 0.1471,
+      "step": 330
+    },
+    {
+      "epoch": 0.3974706413730804,
+      "eval_loss": 0.14507745206356049,
+      "eval_runtime": 81.0028,
+      "eval_samples_per_second": 4.321,
+      "eval_steps_per_second": 2.16,
+      "step": 330
+    },
+    {
+      "epoch": 0.4095152062631737,
+      "grad_norm": 0.2189997136592865,
+      "learning_rate": 0.0001992240588748314,
+      "loss": 0.1423,
+      "step": 340
+    },
+    {
+      "epoch": 0.4215597711532671,
+      "grad_norm": 0.2674465775489807,
+      "learning_rate": 0.00019904018920133574,
+      "loss": 0.1397,
+      "step": 350
+    },
+    {
+      "epoch": 0.43360433604336046,
+      "grad_norm": 0.3467840552330017,
+      "learning_rate": 0.00019883689074653548,
+      "loss": 0.1486,
+      "step": 360
+    },
+    {
+      "epoch": 0.43360433604336046,
+      "eval_loss": 0.1380164623260498,
+      "eval_runtime": 81.2554,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.154,
+      "step": 360
+    },
+    {
+      "epoch": 0.4456489009334538,
+      "grad_norm": 0.22817489504814148,
+      "learning_rate": 0.00019861420339162682,
+      "loss": 0.1411,
+      "step": 370
+    },
+    {
+      "epoch": 0.45769346582354714,
+      "grad_norm": 0.1939237415790558,
+      "learning_rate": 0.0001983721708213397,
+      "loss": 0.1337,
+      "step": 380
+    },
+    {
+      "epoch": 0.46973803071364045,
+      "grad_norm": 0.20223841071128845,
+      "learning_rate": 0.00019811084051536812,
+      "loss": 0.147,
+      "step": 390
+    },
+    {
+      "epoch": 0.46973803071364045,
+      "eval_loss": 0.13835138082504272,
+      "eval_runtime": 81.2083,
+      "eval_samples_per_second": 4.31,
+      "eval_steps_per_second": 2.155,
+      "step": 390
+    },
+    {
+      "epoch": 0.4817825956037338,
+      "grad_norm": 0.16610513627529144,
+      "learning_rate": 0.00019783026373905603,
+      "loss": 0.1261,
+      "step": 400
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.13892178237438202,
+      "learning_rate": 0.0001975304955333405,
+      "loss": 0.1303,
+      "step": 410
+    },
+    {
+      "epoch": 0.5058717253839206,
+      "grad_norm": 0.17607590556144714,
+      "learning_rate": 0.00019721159470395446,
+      "loss": 0.1408,
+      "step": 420
+    },
+    {
+      "epoch": 0.5058717253839206,
+      "eval_loss": 0.13557562232017517,
+      "eval_runtime": 81.2501,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 420
+    },
+    {
+      "epoch": 0.5179162902740139,
+      "grad_norm": 0.2578093409538269,
+      "learning_rate": 0.0001968736238098906,
+      "loss": 0.1328,
+      "step": 430
+    },
+    {
+      "epoch": 0.5299608551641072,
+      "grad_norm": 0.5826597213745117,
+      "learning_rate": 0.00019651664915112913,
+      "loss": 0.1379,
+      "step": 440
+    },
+    {
+      "epoch": 0.5420054200542005,
+      "grad_norm": 0.2640504240989685,
+      "learning_rate": 0.00019614074075563178,
+      "loss": 0.1328,
+      "step": 450
+    },
+    {
+      "epoch": 0.5420054200542005,
+      "eval_loss": 0.13704629242420197,
+      "eval_runtime": 81.2461,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 450
+    },
+    {
+      "epoch": 0.5540499849442939,
+      "grad_norm": 0.25430986285209656,
+      "learning_rate": 0.00019574597236560428,
+      "loss": 0.1295,
+      "step": 460
+    },
+    {
+      "epoch": 0.5660945498343872,
+      "grad_norm": 0.2172861099243164,
+      "learning_rate": 0.00019533242142303028,
+      "loss": 0.1274,
+      "step": 470
+    },
+    {
+      "epoch": 0.5781391147244805,
+      "grad_norm": 0.18936924636363983,
+      "learning_rate": 0.00019490016905447958,
+      "loss": 0.131,
+      "step": 480
+    },
+    {
+      "epoch": 0.5781391147244805,
+      "eval_loss": 0.13753947615623474,
+      "eval_runtime": 81.0949,
+      "eval_samples_per_second": 4.316,
+      "eval_steps_per_second": 2.158,
+      "step": 480
+    },
+    {
+      "epoch": 0.590183679614574,
+      "grad_norm": 0.26435989141464233,
+      "learning_rate": 0.00019444930005519347,
+      "loss": 0.132,
+      "step": 490
+    },
+    {
+      "epoch": 0.6022282445046673,
+      "grad_norm": 0.23327338695526123,
+      "learning_rate": 0.00019397990287245027,
+      "loss": 0.1417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6142728093947606,
+      "grad_norm": 0.14256203174591064,
+      "learning_rate": 0.00019349206958821474,
+      "loss": 0.1392,
+      "step": 510
+    },
+    {
+      "epoch": 0.6142728093947606,
+      "eval_loss": 0.13641956448554993,
+      "eval_runtime": 81.0841,
+      "eval_samples_per_second": 4.317,
+      "eval_steps_per_second": 2.158,
+      "step": 510
+    },
+    {
+      "epoch": 0.626317374284854,
+      "grad_norm": 0.16011199355125427,
+      "learning_rate": 0.00019298589590107415,
+      "loss": 0.1406,
+      "step": 520
+    },
+    {
+      "epoch": 0.6383619391749473,
+      "grad_norm": 0.1269129067659378,
+      "learning_rate": 0.00019246148110746515,
+      "loss": 0.1346,
+      "step": 530
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 0.13770046830177307,
+      "learning_rate": 0.0001919189280821946,
+      "loss": 0.1315,
+      "step": 540
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "eval_loss": 0.1363556832075119,
+      "eval_runtime": 81.2186,
+      "eval_samples_per_second": 4.309,
+      "eval_steps_per_second": 2.155,
+      "step": 540
+    },
+    {
+      "epoch": 0.662451068955134,
+      "grad_norm": 0.18796966969966888,
+      "learning_rate": 0.00019135834325825868,
+      "loss": 0.13,
+      "step": 550
+    },
+    {
+      "epoch": 0.6744956338452274,
+      "grad_norm": 0.12326055020093918,
+      "learning_rate": 0.00019077983660596365,
+      "loss": 0.1339,
+      "step": 560
+    },
+    {
+      "epoch": 0.6865401987353207,
+      "grad_norm": 0.1480596363544464,
+      "learning_rate": 0.00019018352161135317,
+      "loss": 0.1296,
+      "step": 570
+    },
+    {
+      "epoch": 0.6865401987353207,
+      "eval_loss": 0.13280269503593445,
+      "eval_runtime": 81.3546,
+      "eval_samples_per_second": 4.302,
+      "eval_steps_per_second": 2.151,
+      "step": 570
+    },
+    {
+      "epoch": 0.698584763625414,
+      "grad_norm": 0.15606318414211273,
+      "learning_rate": 0.0001895695152539455,
+      "loss": 0.1296,
+      "step": 580
+    },
+    {
+      "epoch": 0.7106293285155074,
+      "grad_norm": 0.09551403671503067,
+      "learning_rate": 0.00018893793798378553,
+      "loss": 0.1323,
+      "step": 590
+    },
+    {
+      "epoch": 0.7226738934056007,
+      "grad_norm": 0.11749322712421417,
+      "learning_rate": 0.00018828891369781605,
+      "loss": 0.1179,
+      "step": 600
+    },
+    {
+      "epoch": 0.7226738934056007,
+      "eval_loss": 0.12917345762252808,
+      "eval_runtime": 81.4843,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.148,
+      "step": 600
+    },
+    {
+      "epoch": 0.734718458295694,
+      "grad_norm": 0.11540284752845764,
+      "learning_rate": 0.0001876225697155729,
+      "loss": 0.1227,
+      "step": 610
+    },
+    {
+      "epoch": 0.7467630231857875,
+      "grad_norm": 0.3190910518169403,
+      "learning_rate": 0.00018693903675420846,
+      "loss": 0.1281,
+      "step": 620
+    },
+    {
+      "epoch": 0.7588075880758808,
+      "grad_norm": 0.11964758485555649,
+      "learning_rate": 0.00018623844890284884,
+      "loss": 0.1356,
+      "step": 630
+    },
+    {
+      "epoch": 0.7588075880758808,
+      "eval_loss": 0.12936915457248688,
+      "eval_runtime": 81.4409,
+      "eval_samples_per_second": 4.298,
+      "eval_steps_per_second": 2.149,
+      "step": 630
+    },
+    {
+      "epoch": 0.7708521529659741,
+      "grad_norm": 0.10809649527072906,
+      "learning_rate": 0.00018552094359628956,
+      "loss": 0.1337,
+      "step": 640
+    },
+    {
+      "epoch": 0.7828967178560674,
+      "grad_norm": 0.13179966807365417,
+      "learning_rate": 0.00018478666158803475,
+      "loss": 0.1213,
+      "step": 650
+    },
+    {
+      "epoch": 0.7949412827461608,
+      "grad_norm": 0.13050246238708496,
+      "learning_rate": 0.00018403574692268566,
+      "loss": 0.1274,
+      "step": 660
+    },
+    {
+      "epoch": 0.7949412827461608,
+      "eval_loss": 0.129548579454422,
+      "eval_runtime": 81.3854,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.15,
+      "step": 660
+    },
+    {
+      "epoch": 0.8069858476362541,
+      "grad_norm": 0.10548313707113266,
+      "learning_rate": 0.00018326834690768308,
+      "loss": 0.1266,
+      "step": 670
+    },
+    {
+      "epoch": 0.8190304125263475,
+      "grad_norm": 0.11163028329610825,
+      "learning_rate": 0.00018248461208441016,
+      "loss": 0.1275,
+      "step": 680
+    },
+    {
+      "epoch": 0.8310749774164409,
+      "grad_norm": 0.10246960818767548,
+      "learning_rate": 0.00018168469619866037,
+      "loss": 0.1262,
+      "step": 690
+    },
+    {
+      "epoch": 0.8310749774164409,
+      "eval_loss": 0.12998254597187042,
+      "eval_runtime": 81.2607,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.154,
+      "step": 690
+    },
+    {
+      "epoch": 0.8431195423065342,
+      "grad_norm": 0.16775400936603546,
+      "learning_rate": 0.00018086875617047738,
+      "loss": 0.128,
+      "step": 700
+    },
+    {
+      "epoch": 0.8551641071966275,
+      "grad_norm": 0.09823903441429138,
+      "learning_rate": 0.00018003695206337164,
+      "loss": 0.1186,
+      "step": 710
+    },
+    {
+      "epoch": 0.8672086720867209,
+      "grad_norm": 0.08154378831386566,
+      "learning_rate": 0.0001791894470529209,
+      "loss": 0.1304,
+      "step": 720
+    },
+    {
+      "epoch": 0.8672086720867209,
+      "eval_loss": 0.12851889431476593,
+      "eval_runtime": 81.3179,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 2.152,
+      "step": 720
+    },
+    {
+      "epoch": 0.8792532369768142,
+      "grad_norm": 0.13566914200782776,
+      "learning_rate": 0.00017832640739475964,
+      "loss": 0.1256,
+      "step": 730
+    },
+    {
+      "epoch": 0.8912978018669075,
+      "grad_norm": 0.21967343986034393,
+      "learning_rate": 0.00017744800239196485,
+      "loss": 0.1049,
+      "step": 740
+    },
+    {
+      "epoch": 0.9033423667570009,
+      "grad_norm": 0.12291447818279266,
+      "learning_rate": 0.00017655440436184361,
+      "loss": 0.1352,
+      "step": 750
+    },
+    {
+      "epoch": 0.9033423667570009,
+      "eval_loss": 0.12859711050987244,
+      "eval_runtime": 81.5112,
+      "eval_samples_per_second": 4.294,
+      "eval_steps_per_second": 2.147,
+      "step": 750
+    },
+    {
+      "epoch": 0.9153869316470943,
+      "grad_norm": 0.23631049692630768,
+      "learning_rate": 0.00017564578860212952,
+      "loss": 0.1236,
+      "step": 760
+    },
+    {
+      "epoch": 0.9274314965371876,
+      "grad_norm": 0.13145385682582855,
+      "learning_rate": 0.00017472233335659443,
+      "loss": 0.1235,
+      "step": 770
+    },
+    {
+      "epoch": 0.9394760614272809,
+      "grad_norm": 0.0923519879579544,
+      "learning_rate": 0.00017378421978008212,
+      "loss": 0.1224,
+      "step": 780
+    },
+    {
+      "epoch": 0.9394760614272809,
+      "eval_loss": 0.12813878059387207,
+      "eval_runtime": 81.2514,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 780
+    },
+    {
+      "epoch": 0.9515206263173743,
+      "grad_norm": 0.2052728235721588,
+      "learning_rate": 0.0001728316319029713,
+      "loss": 0.1189,
+      "step": 790
+    },
+    {
+      "epoch": 0.9635651912074676,
+      "grad_norm": 0.19939783215522766,
+      "learning_rate": 0.0001718647565950739,
+      "loss": 0.128,
+      "step": 800
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.11448610574007034,
+      "learning_rate": 0.00017088378352897703,
+      "loss": 0.1103,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "eval_loss": 0.12625984847545624,
+      "eval_runtime": 81.2673,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.153,
+      "step": 810
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.11135770380496979,
+      "learning_rate": 0.00016988890514283447,
+      "loss": 0.1281,
+      "step": 820
+    },
+    {
+      "epoch": 0.9996988858777477,
+      "grad_norm": 0.11028297245502472,
+      "learning_rate": 0.00016888031660261622,
+      "loss": 0.1225,
+      "step": 830
+    },
+    {
+      "epoch": 1.010840108401084,
+      "grad_norm": 0.11298307776451111,
+      "learning_rate": 0.00016785821576382245,
+      "loss": 0.1188,
+      "step": 840
+    },
+    {
+      "epoch": 1.010840108401084,
+      "eval_loss": 0.1276378333568573,
+      "eval_runtime": 81.1811,
+      "eval_samples_per_second": 4.311,
+      "eval_steps_per_second": 2.156,
+      "step": 840
+    },
+    {
+      "epoch": 1.0228846732911774,
+      "grad_norm": 0.09120020270347595,
+      "learning_rate": 0.0001668228031326702,
+      "loss": 0.1169,
+      "step": 850
+    },
+    {
+      "epoch": 1.0349292381812707,
+      "grad_norm": 0.11060494184494019,
+      "learning_rate": 0.00016577428182675973,
+      "loss": 0.1243,
+      "step": 860
+    },
+    {
+      "epoch": 1.046973803071364,
+      "grad_norm": 0.09636874496936798,
+      "learning_rate": 0.0001647128575352292,
+      "loss": 0.1187,
+      "step": 870
+    },
+    {
+      "epoch": 1.046973803071364,
+      "eval_loss": 0.12680906057357788,
+      "eval_runtime": 81.1164,
+      "eval_samples_per_second": 4.315,
+      "eval_steps_per_second": 2.157,
+      "step": 870
+    },
+    {
+      "epoch": 1.0590183679614573,
+      "grad_norm": 0.10281568765640259,
+      "learning_rate": 0.000163638738478404,
+      "loss": 0.133,
+      "step": 880
+    },
+    {
+      "epoch": 1.0710629328515506,
+      "grad_norm": 0.08682233840227127,
+      "learning_rate": 0.0001625521353669504,
+      "loss": 0.1171,
+      "step": 890
+    },
+    {
+      "epoch": 1.0831074977416442,
+      "grad_norm": 0.1339954435825348,
+      "learning_rate": 0.00016145326136054008,
+      "loss": 0.1257,
+      "step": 900
+    },
+    {
+      "epoch": 1.0831074977416442,
+      "eval_loss": 0.12813013792037964,
+      "eval_runtime": 81.4418,
+      "eval_samples_per_second": 4.298,
+      "eval_steps_per_second": 2.149,
+      "step": 900
+    },
+    {
+      "epoch": 1.0951520626317375,
+      "grad_norm": 0.09956265985965729,
+      "learning_rate": 0.00016034233202603463,
+      "loss": 0.1287,
+      "step": 910
+    },
+    {
+      "epoch": 1.1071966275218308,
+      "grad_norm": 0.07889163494110107,
+      "learning_rate": 0.00015921956529519747,
+      "loss": 0.1135,
+      "step": 920
+    },
+    {
+      "epoch": 1.119241192411924,
+      "grad_norm": 0.07798007130622864,
+      "learning_rate": 0.00015808518142194214,
+      "loss": 0.1128,
+      "step": 930
+    },
+    {
+      "epoch": 1.119241192411924,
+      "eval_loss": 0.12662966549396515,
+      "eval_runtime": 81.2769,
+      "eval_samples_per_second": 4.306,
+      "eval_steps_per_second": 2.153,
+      "step": 930
+    },
+    {
+      "epoch": 1.1312857573020174,
+      "grad_norm": 0.09110717475414276,
+      "learning_rate": 0.00015693940293912492,
+      "loss": 0.1161,
+      "step": 940
+    },
+    {
+      "epoch": 1.1433303221921107,
+      "grad_norm": 0.10704551637172699,
+      "learning_rate": 0.00015578245461489042,
+      "loss": 0.1237,
+      "step": 950
+    },
+    {
+      "epoch": 1.1553748870822043,
+      "grad_norm": 0.12007839977741241,
+      "learning_rate": 0.00015461456340857857,
+      "loss": 0.1246,
+      "step": 960
+    },
+    {
+      "epoch": 1.1553748870822043,
+      "eval_loss": 0.12597930431365967,
+      "eval_runtime": 81.2379,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 960
+    },
+    {
+      "epoch": 1.1674194519722976,
+      "grad_norm": 0.09195715934038162,
+      "learning_rate": 0.00015343595842620198,
+      "loss": 0.1179,
+      "step": 970
+    },
+    {
+      "epoch": 1.1794640168623909,
+      "grad_norm": 0.11327285319566727,
+      "learning_rate": 0.000152246870875502,
+      "loss": 0.1219,
+      "step": 980
+    },
+    {
+      "epoch": 1.1915085817524842,
+      "grad_norm": 0.12147443741559982,
+      "learning_rate": 0.00015104753402059252,
+      "loss": 0.1198,
+      "step": 990
+    },
+    {
+      "epoch": 1.1915085817524842,
+      "eval_loss": 0.12678198516368866,
+      "eval_runtime": 81.2272,
+      "eval_samples_per_second": 4.309,
+      "eval_steps_per_second": 2.154,
+      "step": 990
+    },
+    {
+      "epoch": 1.2035531466425775,
+      "grad_norm": 0.12530316412448883,
+      "learning_rate": 0.00014983818313620047,
+      "loss": 0.1215,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2155977115326708,
+      "grad_norm": 0.21503940224647522,
+      "learning_rate": 0.00014861905546151164,
+      "loss": 0.132,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2276422764227641,
+      "grad_norm": 0.09851568937301636,
+      "learning_rate": 0.00014739039015363155,
+      "loss": 0.1255,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2276422764227641,
+      "eval_loss": 0.1265084594488144,
+      "eval_runtime": 81.2978,
+      "eval_samples_per_second": 4.305,
+      "eval_steps_per_second": 2.153,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2396868413128577,
+      "grad_norm": 0.09794170409440994,
+      "learning_rate": 0.0001461524282406696,
+      "loss": 0.1203,
+      "step": 1030
+    },
+    {
+      "epoch": 1.251731406202951,
+      "grad_norm": 0.09283249080181122,
+      "learning_rate": 0.00014490541257445664,
+      "loss": 0.1241,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2637759710930443,
+      "grad_norm": 0.10757778584957123,
+      "learning_rate": 0.00014364958778290436,
+      "loss": 0.1263,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2637759710930443,
+      "eval_loss": 0.1275068074464798,
+      "eval_runtime": 81.3037,
+      "eval_samples_per_second": 4.305,
+      "eval_steps_per_second": 2.152,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2758205359831376,
+      "grad_norm": 0.08741755038499832,
+      "learning_rate": 0.00014238520022201665,
+      "loss": 0.1279,
+      "step": 1060
+    },
+    {
+      "epoch": 1.287865100873231,
+      "grad_norm": 0.09674480557441711,
+      "learning_rate": 0.00014111249792756164,
+      "loss": 0.1203,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2999096657633242,
+      "grad_norm": 0.18980656564235687,
+      "learning_rate": 0.00013983173056641437,
+      "loss": 0.1273,
+      "step": 1080
+    },
+    {
+      "epoch": 1.2999096657633242,
+      "eval_loss": 0.12540876865386963,
+      "eval_runtime": 81.3684,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.151,
+      "step": 1080
+    },
+    {
+      "epoch": 1.3119542306534178,
+      "grad_norm": 0.11260770261287689,
+      "learning_rate": 0.00013854314938757954,
+      "loss": 0.1209,
+      "step": 1090
+    },
+    {
+      "epoch": 1.323998795543511,
+      "grad_norm": 0.08883814513683319,
+      "learning_rate": 0.00013724700717290385,
+      "loss": 0.1307,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3360433604336044,
+      "grad_norm": 0.08555177599191666,
+      "learning_rate": 0.0001359435581874874,
+      "loss": 0.1187,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3360433604336044,
+      "eval_loss": 0.1246650293469429,
+      "eval_runtime": 81.3179,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 2.152,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3480879253236977,
+      "grad_norm": 0.09265279769897461,
+      "learning_rate": 0.0001346330581298046,
+      "loss": 0.1237,
+      "step": 1120
+    },
+    {
+      "epoch": 1.360132490213791,
+      "grad_norm": 0.07397205382585526,
+      "learning_rate": 0.0001333157640815434,
+      "loss": 0.1194,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3721770551038843,
+      "grad_norm": 0.10523436218500137,
+      "learning_rate": 0.00013199193445717362,
+      "loss": 0.1215,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3721770551038843,
+      "eval_loss": 0.12532441318035126,
+      "eval_runtime": 81.5003,
+      "eval_samples_per_second": 4.294,
+      "eval_steps_per_second": 2.147,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3842216199939776,
+      "grad_norm": 0.08104018867015839,
+      "learning_rate": 0.00013066182895325339,
+      "loss": 0.1276,
+      "step": 1150
+    },
+    {
+      "epoch": 1.396266184884071,
+      "grad_norm": 0.1049809381365776,
+      "learning_rate": 0.00012932570849748446,
+      "loss": 0.128,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4083107497741645,
+      "grad_norm": 0.10500895977020264,
+      "learning_rate": 0.00012798383519752577,
+      "loss": 0.1179,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4083107497741645,
+      "eval_loss": 0.12398175895214081,
+      "eval_runtime": 81.4012,
+      "eval_samples_per_second": 4.3,
+      "eval_steps_per_second": 2.15,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4203553146642578,
+      "grad_norm": 0.08427383005619049,
+      "learning_rate": 0.00012663647228957562,
+      "loss": 0.1145,
+      "step": 1180
+    },
+    {
+      "epoch": 1.432399879554351,
+      "grad_norm": 0.08236031979322433,
+      "learning_rate": 0.0001252838840867324,
+      "loss": 0.1216,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.08572593331336975,
+      "learning_rate": 0.00012392633592714423,
+      "loss": 0.128,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "eval_loss": 0.1240333542227745,
+      "eval_runtime": 81.3808,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.15,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4564890093345377,
+      "grad_norm": 0.08900213986635208,
+      "learning_rate": 0.00012256409412195727,
+      "loss": 0.1171,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4685335742246313,
+      "grad_norm": 0.09740438312292099,
+      "learning_rate": 0.0001211974259030733,
+      "loss": 0.1316,
+      "step": 1220
+    },
+    {
+      "epoch": 1.4805781391147246,
+      "grad_norm": 0.07978689670562744,
+      "learning_rate": 0.00011982659937072677,
+      "loss": 0.1219,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4805781391147246,
+      "eval_loss": 0.12412716448307037,
+      "eval_runtime": 81.2608,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.154,
+      "step": 1230
+    },
+    {
+      "epoch": 1.492622704004818,
+      "grad_norm": 0.08000902086496353,
+      "learning_rate": 0.00011845188344089126,
+      "loss": 0.1135,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5046672688949112,
+      "grad_norm": 0.07367110252380371,
+      "learning_rate": 0.00011707354779252612,
+      "loss": 0.1206,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5167118337850045,
+      "grad_norm": 0.07485098391771317,
+      "learning_rate": 0.00011569186281467335,
+      "loss": 0.1138,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5167118337850045,
+      "eval_loss": 0.1249684989452362,
+      "eval_runtime": 81.6234,
+      "eval_samples_per_second": 4.288,
+      "eval_steps_per_second": 2.144,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5287563986750978,
+      "grad_norm": 0.11146491765975952,
+      "learning_rate": 0.00011430709955341514,
+      "loss": 0.1272,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5408009635651911,
+      "grad_norm": 0.08664289861917496,
+      "learning_rate": 0.00011291952965870269,
+      "loss": 0.1147,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5528455284552845,
+      "grad_norm": 0.09051596373319626,
+      "learning_rate": 0.00011152942533106638,
+      "loss": 0.1161,
+      "step": 1290
+    },
+    {
+      "epoch": 1.5528455284552845,
+      "eval_loss": 0.12454230338335037,
+      "eval_runtime": 81.4318,
+      "eval_samples_per_second": 4.298,
+      "eval_steps_per_second": 2.149,
+      "step": 1290
+    },
+    {
+      "epoch": 1.5648900933453778,
+      "grad_norm": 0.06956392526626587,
+      "learning_rate": 0.000110137059268218,
+      "loss": 0.1077,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5769346582354713,
+      "grad_norm": 0.07337108254432678,
+      "learning_rate": 0.00010874270461155554,
+      "loss": 0.124,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5889792231255646,
+      "grad_norm": 0.08082354068756104,
+      "learning_rate": 0.0001073466348925807,
+      "loss": 0.1108,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5889792231255646,
+      "eval_loss": 0.12420380860567093,
+      "eval_runtime": 81.6866,
+      "eval_samples_per_second": 4.285,
+      "eval_steps_per_second": 2.142,
+      "step": 1320
+    },
+    {
+      "epoch": 1.601023788015658,
+      "grad_norm": 0.07141824066638947,
+      "learning_rate": 0.00010594912397924018,
+      "loss": 0.1112,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6130683529057512,
+      "grad_norm": 0.09476039558649063,
+      "learning_rate": 0.00010455044602220076,
+      "loss": 0.1257,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6251129177958448,
+      "grad_norm": 0.06789754331111908,
+      "learning_rate": 0.00010315087540106894,
+      "loss": 0.1167,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6251129177958448,
+      "eval_loss": 0.12411510944366455,
+      "eval_runtime": 81.5821,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 1350
+    },
+    {
+      "epoch": 1.637157482685938,
+      "grad_norm": 0.08458850532770157,
+      "learning_rate": 0.00010175068667056578,
+      "loss": 0.1215,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6492020475760314,
+      "grad_norm": 0.0818653479218483,
+      "learning_rate": 0.00010035015450666723,
+      "loss": 0.1193,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6612466124661247,
+      "grad_norm": 0.060270510613918304,
+      "learning_rate": 9.894955365272087e-05,
+      "loss": 0.1094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6612466124661247,
+      "eval_loss": 0.12342710047960281,
+      "eval_runtime": 81.3723,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.151,
+      "step": 1380
+    },
+    {
+      "epoch": 1.673291177356218,
+      "grad_norm": 0.08454828709363937,
+      "learning_rate": 9.75491588655492e-05,
+      "loss": 0.1205,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6853357422463113,
+      "grad_norm": 0.06156294047832489,
+      "learning_rate": 9.614924486155047e-05,
+      "loss": 0.1111,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6973803071364046,
+      "grad_norm": 0.08005426079034805,
+      "learning_rate": 9.475008626280739e-05,
+      "loss": 0.1077,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6973803071364046,
+      "eval_loss": 0.12282679229974747,
+      "eval_runtime": 81.2841,
+      "eval_samples_per_second": 4.306,
+      "eval_steps_per_second": 2.153,
+      "step": 1410
+    },
+    {
+      "epoch": 1.709424872026498,
+      "grad_norm": 0.08515966683626175,
+      "learning_rate": 9.335195754321427e-05,
+      "loss": 0.1226,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7214694369165913,
+      "grad_norm": 0.08117437362670898,
+      "learning_rate": 9.195513297463339e-05,
+      "loss": 0.1158,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7335140018066846,
+      "grad_norm": 0.0748409777879715,
+      "learning_rate": 9.055988657309075e-05,
+      "loss": 0.1152,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7335140018066846,
+      "eval_loss": 0.12351047992706299,
+      "eval_runtime": 81.3284,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 2.152,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7455585666967781,
+      "grad_norm": 0.08821168541908264,
+      "learning_rate": 8.916649204502231e-05,
+      "loss": 0.1231,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7576031315868714,
+      "grad_norm": 0.06368843466043472,
+      "learning_rate": 8.777522273358076e-05,
+      "loss": 0.1144,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7696476964769647,
+      "grad_norm": 0.08906359225511551,
+      "learning_rate": 8.638635156501353e-05,
+      "loss": 0.1278,
+      "step": 1470
+    },
+    {
+      "epoch": 1.7696476964769647,
+      "eval_loss": 0.12412309646606445,
+      "eval_runtime": 81.4647,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 2.148,
+      "step": 1470
+    },
+    {
+      "epoch": 1.7816922613670583,
+      "grad_norm": 0.13860240578651428,
+      "learning_rate": 8.500015099512282e-05,
+      "loss": 0.1135,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7937368262571516,
+      "grad_norm": 0.08925935626029968,
+      "learning_rate": 8.361689295581759e-05,
+      "loss": 0.1274,
+      "step": 1490
+    },
+    {
+      "epoch": 1.805781391147245,
+      "grad_norm": 0.2061154991388321,
+      "learning_rate": 8.223684880176861e-05,
+      "loss": 0.1245,
+      "step": 1500
+    },
+    {
+      "epoch": 1.805781391147245,
+      "eval_loss": 0.12294992804527283,
+      "eval_runtime": 81.5386,
+      "eval_samples_per_second": 4.292,
+      "eval_steps_per_second": 2.146,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8178259560373382,
+      "grad_norm": 0.07016266882419586,
+      "learning_rate": 8.086028925717661e-05,
+      "loss": 0.1215,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8298705209274315,
+      "grad_norm": 0.19503405690193176,
+      "learning_rate": 7.948748436266409e-05,
+      "loss": 0.1169,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8419150858175248,
+      "grad_norm": 0.07560829073190689,
+      "learning_rate": 7.811870342230127e-05,
+      "loss": 0.1219,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8419150858175248,
+      "eval_loss": 0.12353645265102386,
+      "eval_runtime": 81.5233,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.147,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8539596507076181,
+      "grad_norm": 0.06638047844171524,
+      "learning_rate": 7.675421495077657e-05,
+      "loss": 0.1174,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8660042155977115,
+      "grad_norm": 0.07245375961065292,
+      "learning_rate": 7.539428662072188e-05,
+      "loss": 0.1263,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8780487804878048,
+      "grad_norm": 0.08080323040485382,
+      "learning_rate": 7.403918521020305e-05,
+      "loss": 0.1261,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8780487804878048,
+      "eval_loss": 0.12283791601657867,
+      "eval_runtime": 81.5734,
+      "eval_samples_per_second": 4.291,
+      "eval_steps_per_second": 2.145,
+      "step": 1560
+    },
+    {
+      "epoch": 1.890093345377898,
+      "grad_norm": 0.06938530504703522,
+      "learning_rate": 7.268917655038581e-05,
+      "loss": 0.1167,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9021379102679916,
+      "grad_norm": 0.07764075696468353,
+      "learning_rate": 7.134452547338753e-05,
+      "loss": 0.1191,
+      "step": 1580
+    },
+    {
+      "epoch": 1.914182475158085,
+      "grad_norm": 0.10729371011257172,
+      "learning_rate": 7.000549576032489e-05,
+      "loss": 0.1175,
+      "step": 1590
+    },
+    {
+      "epoch": 1.914182475158085,
+      "eval_loss": 0.12257985025644302,
+      "eval_runtime": 81.3844,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.15,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9262270400481782,
+      "grad_norm": 0.06268001347780228,
+      "learning_rate": 6.867235008956783e-05,
+      "loss": 0.1203,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9382716049382716,
+      "grad_norm": 0.059695664793252945,
+      "learning_rate": 6.734534998520969e-05,
+      "loss": 0.1147,
+      "step": 1610
+    },
+    {
+      "epoch": 1.950316169828365,
+      "grad_norm": 0.07781612873077393,
+      "learning_rate": 6.602475576576383e-05,
+      "loss": 0.1191,
+      "step": 1620
+    },
+    {
+      "epoch": 1.950316169828365,
+      "eval_loss": 0.1225815936923027,
+      "eval_runtime": 81.7725,
+      "eval_samples_per_second": 4.28,
+      "eval_steps_per_second": 2.14,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9623607347184584,
+      "grad_norm": 0.06548433750867844,
+      "learning_rate": 6.471082649309686e-05,
+      "loss": 0.1181,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9744052996085517,
+      "grad_norm": 0.0688992366194725,
+      "learning_rate": 6.34038199216082e-05,
+      "loss": 0.1139,
+      "step": 1640
+    },
+    {
+      "epoch": 1.986449864498645,
+      "grad_norm": 0.07544533908367157,
+      "learning_rate": 6.210399244766632e-05,
+      "loss": 0.1194,
+      "step": 1650
+    },
+    {
+      "epoch": 1.986449864498645,
+      "eval_loss": 0.12259992212057114,
+      "eval_runtime": 81.5949,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.145,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9984944293887383,
+      "grad_norm": 0.13208015263080597,
+      "learning_rate": 6.0811599059311195e-05,
+      "loss": 0.1185,
+      "step": 1660
+    },
+    {
+      "epoch": 2.009635651912075,
+      "grad_norm": 0.08133638650178909,
+      "learning_rate": 5.952689328623321e-05,
+      "loss": 0.1264,
+      "step": 1670
+    },
+    {
+      "epoch": 2.021680216802168,
+      "grad_norm": 0.08000742644071579,
+      "learning_rate": 5.8250127150038016e-05,
+      "loss": 0.1108,
+      "step": 1680
+    },
+    {
+      "epoch": 2.021680216802168,
+      "eval_loss": 0.12281496077775955,
+      "eval_runtime": 81.5447,
+      "eval_samples_per_second": 4.292,
+      "eval_steps_per_second": 2.146,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0337247816922615,
+      "grad_norm": 0.06525713950395584,
+      "learning_rate": 5.698155111480722e-05,
+      "loss": 0.1141,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0457693465823548,
+      "grad_norm": 0.06997241824865341,
+      "learning_rate": 5.57214140379649e-05,
+      "loss": 0.1146,
+      "step": 1700
+    },
+    {
+      "epoch": 2.057813911472448,
+      "grad_norm": 0.07603967189788818,
+      "learning_rate": 5.4469963121458776e-05,
+      "loss": 0.1169,
+      "step": 1710
+    },
+    {
+      "epoch": 2.057813911472448,
+      "eval_loss": 0.12317664176225662,
+      "eval_runtime": 81.5005,
+      "eval_samples_per_second": 4.294,
+      "eval_steps_per_second": 2.147,
+      "step": 1710
+    },
+    {
+      "epoch": 2.0698584763625414,
+      "grad_norm": 0.09060684591531754,
+      "learning_rate": 5.322744386326675e-05,
+      "loss": 0.1139,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0819030412526347,
+      "grad_norm": 0.09253629297018051,
+      "learning_rate": 5.1994100009237e-05,
+      "loss": 0.1174,
+      "step": 1730
+    },
+    {
+      "epoch": 2.093947606142728,
+      "grad_norm": 0.0707191526889801,
+      "learning_rate": 5.077017350527269e-05,
+      "loss": 0.1138,
+      "step": 1740
+    },
+    {
+      "epoch": 2.093947606142728,
+      "eval_loss": 0.1225883737206459,
+      "eval_runtime": 81.4669,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 2.148,
+      "step": 1740
+    },
+    {
+      "epoch": 2.1059921710328213,
+      "grad_norm": 0.06803560256958008,
+      "learning_rate": 4.9555904449868795e-05,
+      "loss": 0.1196,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1180367359229146,
+      "grad_norm": 0.08914126455783844,
+      "learning_rate": 4.835153104701221e-05,
+      "loss": 0.1129,
+      "step": 1760
+    },
+    {
+      "epoch": 2.130081300813008,
+      "grad_norm": 0.08918345719575882,
+      "learning_rate": 4.71572895594528e-05,
+      "loss": 0.1183,
+      "step": 1770
+    },
+    {
+      "epoch": 2.130081300813008,
+      "eval_loss": 0.12287717312574387,
+      "eval_runtime": 81.4917,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.147,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1421258657031013,
+      "grad_norm": 0.07838484644889832,
+      "learning_rate": 4.5973414262355785e-05,
+      "loss": 0.1141,
+      "step": 1780
+    },
+    {
+      "epoch": 2.154170430593195,
+      "grad_norm": 0.11005687713623047,
+      "learning_rate": 4.480013739734368e-05,
+      "loss": 0.1223,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1662149954832883,
+      "grad_norm": 0.08749410510063171,
+      "learning_rate": 4.363768912693749e-05,
+      "loss": 0.1117,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1662149954832883,
+      "eval_loss": 0.12259072810411453,
+      "eval_runtime": 81.4558,
+      "eval_samples_per_second": 4.297,
+      "eval_steps_per_second": 2.148,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1782595603733816,
+      "grad_norm": 0.08549398928880692,
+      "learning_rate": 4.24862974894053e-05,
+      "loss": 0.1088,
+      "step": 1810
+    },
+    {
+      "epoch": 2.190304125263475,
+      "grad_norm": 0.05755528435111046,
+      "learning_rate": 4.134618835402816e-05,
+      "loss": 0.1063,
+      "step": 1820
+    },
+    {
+      "epoch": 2.2023486901535683,
+      "grad_norm": 0.07486403733491898,
+      "learning_rate": 4.0217585376790834e-05,
+      "loss": 0.1183,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2023486901535683,
+      "eval_loss": 0.12217788398265839,
+      "eval_runtime": 81.8011,
+      "eval_samples_per_second": 4.279,
+      "eval_steps_per_second": 2.139,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2143932550436616,
+      "grad_norm": 0.08609265834093094,
+      "learning_rate": 3.9100709956507356e-05,
+      "loss": 0.1254,
+      "step": 1840
+    },
+    {
+      "epoch": 2.226437819933755,
+      "grad_norm": 0.0692862719297409,
+      "learning_rate": 3.79957811913888e-05,
+      "loss": 0.1121,
+      "step": 1850
+    },
+    {
+      "epoch": 2.238482384823848,
+      "grad_norm": 0.08547110855579376,
+      "learning_rate": 3.6903015836062905e-05,
+      "loss": 0.1097,
+      "step": 1860
+    },
+    {
+      "epoch": 2.238482384823848,
+      "eval_loss": 0.12183844298124313,
+      "eval_runtime": 81.5286,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.146,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2505269497139415,
+      "grad_norm": 0.08573822677135468,
+      "learning_rate": 3.5822628259052906e-05,
+      "loss": 0.1174,
+      "step": 1870
+    },
+    {
+      "epoch": 2.262571514604035,
+      "grad_norm": 0.08069294691085815,
+      "learning_rate": 3.475483040072495e-05,
+      "loss": 0.1198,
+      "step": 1880
+    },
+    {
+      "epoch": 2.274616079494128,
+      "grad_norm": 0.08202630281448364,
+      "learning_rate": 3.369983173171141e-05,
+      "loss": 0.1132,
+      "step": 1890
+    },
+    {
+      "epoch": 2.274616079494128,
+      "eval_loss": 0.12189455330371857,
+      "eval_runtime": 81.6511,
+      "eval_samples_per_second": 4.287,
+      "eval_steps_per_second": 2.143,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2866606443842215,
+      "grad_norm": 0.08111971616744995,
+      "learning_rate": 3.2657839211819085e-05,
+      "loss": 0.1086,
+      "step": 1900
+    },
+    {
+      "epoch": 2.298705209274315,
+      "grad_norm": 0.07577092200517654,
+      "learning_rate": 3.1629057249429527e-05,
+      "loss": 0.1205,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3107497741644085,
+      "grad_norm": 0.0689835473895073,
+      "learning_rate": 3.0613687661400384e-05,
+      "loss": 0.1133,
+      "step": 1920
+    },
+    {
+      "epoch": 2.3107497741644085,
+      "eval_loss": 0.12182266265153885,
+      "eval_runtime": 81.5792,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 1920
+    },
+    {
+      "epoch": 2.322794339054502,
+      "grad_norm": 0.09697998315095901,
+      "learning_rate": 2.9611929633474555e-05,
+      "loss": 0.1214,
+      "step": 1930
+    },
+    {
+      "epoch": 2.334838903944595,
+      "grad_norm": 0.07920137792825699,
+      "learning_rate": 2.8623979681206002e-05,
+      "loss": 0.1108,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3468834688346885,
+      "grad_norm": 0.07563956826925278,
+      "learning_rate": 2.765003161140911e-05,
+      "loss": 0.1213,
+      "step": 1950
+    },
+    {
+      "epoch": 2.3468834688346885,
+      "eval_loss": 0.12195436656475067,
+      "eval_runtime": 81.5329,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.146,
+      "step": 1950
+    },
+    {
+      "epoch": 2.3589280337247818,
+      "grad_norm": 0.08294857293367386,
+      "learning_rate": 2.66902764841394e-05,
+      "loss": 0.1186,
+      "step": 1960
+    },
+    {
+      "epoch": 2.370972598614875,
+      "grad_norm": 0.0806855708360672,
+      "learning_rate": 2.5744902575213248e-05,
+      "loss": 0.1127,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3830171635049684,
+      "grad_norm": 0.1039934828877449,
+      "learning_rate": 2.481409533927358e-05,
+      "loss": 0.1188,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3830171635049684,
+      "eval_loss": 0.12177734076976776,
+      "eval_runtime": 81.5272,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.147,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3950617283950617,
+      "grad_norm": 0.09341799467802048,
+      "learning_rate": 2.3898037373409276e-05,
+      "loss": 0.1173,
+      "step": 1990
+    },
+    {
+      "epoch": 2.407106293285155,
+      "grad_norm": 0.08933733403682709,
+      "learning_rate": 2.2996908381334736e-05,
+      "loss": 0.1148,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4191508581752483,
+      "grad_norm": 0.08493391424417496,
+      "learning_rate": 2.211088513813754e-05,
+      "loss": 0.1121,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4191508581752483,
+      "eval_loss": 0.12171091139316559,
+      "eval_runtime": 81.5846,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4311954230653416,
+      "grad_norm": 0.1086319163441658,
+      "learning_rate": 2.1240141455600116e-05,
+      "loss": 0.1145,
+      "step": 2020
+    },
+    {
+      "epoch": 2.443239987955435,
+      "grad_norm": 0.09176024794578552,
+      "learning_rate": 2.0384848148103196e-05,
+      "loss": 0.1092,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4552845528455283,
+      "grad_norm": 0.1033325344324112,
+      "learning_rate": 1.9545172999116812e-05,
+      "loss": 0.1055,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4552845528455283,
+      "eval_loss": 0.12144716829061508,
+      "eval_runtime": 81.758,
+      "eval_samples_per_second": 4.281,
+      "eval_steps_per_second": 2.14,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4673291177356216,
+      "grad_norm": 0.07238776981830597,
+      "learning_rate": 1.872128072828634e-05,
+      "loss": 0.1105,
+      "step": 2050
+    },
+    {
+      "epoch": 2.4793736826257153,
+      "grad_norm": 0.06941673159599304,
+      "learning_rate": 1.791333295911909e-05,
+      "loss": 0.1118,
+      "step": 2060
+    },
+    {
+      "epoch": 2.4914182475158086,
+      "grad_norm": 0.08462639153003693,
+      "learning_rate": 1.7121488187278713e-05,
+      "loss": 0.1082,
+      "step": 2070
+    },
+    {
+      "epoch": 2.4914182475158086,
+      "eval_loss": 0.12135373055934906,
+      "eval_runtime": 81.6101,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.144,
+      "step": 2070
+    },
+    {
+      "epoch": 2.503462812405902,
+      "grad_norm": 0.09350676834583282,
+      "learning_rate": 1.6345901749492887e-05,
+      "loss": 0.1121,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5155073772959953,
+      "grad_norm": 0.08438068628311157,
+      "learning_rate": 1.5586725793080814e-05,
+      "loss": 0.1146,
+      "step": 2090
+    },
+    {
+      "epoch": 2.5275519421860886,
+      "grad_norm": 0.10219820588827133,
+      "learning_rate": 1.484410924610642e-05,
+      "loss": 0.1179,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5275519421860886,
+      "eval_loss": 0.12126310169696808,
+      "eval_runtime": 81.4438,
+      "eval_samples_per_second": 4.297,
+      "eval_steps_per_second": 2.149,
+      "step": 2100
+    },
+    {
+      "epoch": 2.539596507076182,
+      "grad_norm": 0.0966809093952179,
+      "learning_rate": 1.4118197788163056e-05,
+      "loss": 0.1186,
+      "step": 2110
+    },
+    {
+      "epoch": 2.551641071966275,
+      "grad_norm": 0.1106065958738327,
+      "learning_rate": 1.3409133821795306e-05,
+      "loss": 0.1112,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5636856368563685,
+      "grad_norm": 0.09320900589227676,
+      "learning_rate": 1.2717056444563957e-05,
+      "loss": 0.1148,
+      "step": 2130
+    },
+    {
+      "epoch": 2.5636856368563685,
+      "eval_loss": 0.12110390514135361,
+      "eval_runtime": 81.8244,
+      "eval_samples_per_second": 4.277,
+      "eval_steps_per_second": 2.139,
+      "step": 2130
+    },
+    {
+      "epoch": 2.575730201746462,
+      "grad_norm": 0.09060157835483551,
+      "learning_rate": 1.2042101421758955e-05,
+      "loss": 0.1219,
+      "step": 2140
+    },
+    {
+      "epoch": 2.587774766636555,
+      "grad_norm": 0.09531334787607193,
+      "learning_rate": 1.1384401159766433e-05,
+      "loss": 0.1136,
+      "step": 2150
+    },
+    {
+      "epoch": 2.5998193315266485,
+      "grad_norm": 0.07259315997362137,
+      "learning_rate": 1.0744084680094246e-05,
+      "loss": 0.1062,
+      "step": 2160
+    },
+    {
+      "epoch": 2.5998193315266485,
+      "eval_loss": 0.12105338275432587,
+      "eval_runtime": 81.5762,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 2160
+    },
+    {
+      "epoch": 2.611863896416742,
+      "grad_norm": 0.07185359299182892,
+      "learning_rate": 1.0121277594061939e-05,
+      "loss": 0.1184,
+      "step": 2170
+    },
+    {
+      "epoch": 2.6239084613068355,
+      "grad_norm": 0.0885002538561821,
+      "learning_rate": 9.516102078159317e-06,
+      "loss": 0.1243,
+      "step": 2180
+    },
+    {
+      "epoch": 2.635953026196929,
+      "grad_norm": 0.10129860043525696,
+      "learning_rate": 8.928676850079133e-06,
+      "loss": 0.1249,
+      "step": 2190
+    },
+    {
+      "epoch": 2.635953026196929,
+      "eval_loss": 0.1209418997168541,
+      "eval_runtime": 81.4691,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 2.148,
+      "step": 2190
+    },
+    {
+      "epoch": 2.647997591087022,
+      "grad_norm": 0.08937793970108032,
+      "learning_rate": 8.359117145428053e-06,
+      "loss": 0.1188,
+      "step": 2200
+    },
+    {
+      "epoch": 2.6600421559771155,
+      "grad_norm": 0.08618754148483276,
+      "learning_rate": 7.807534695120911e-06,
+      "loss": 0.1193,
+      "step": 2210
+    },
+    {
+      "epoch": 2.6720867208672088,
+      "grad_norm": 0.0760350152850151,
+      "learning_rate": 7.274037703462244e-06,
+      "loss": 0.107,
+      "step": 2220
+    },
+    {
+      "epoch": 2.6720867208672088,
+      "eval_loss": 0.12113867700099945,
+      "eval_runtime": 81.609,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.144,
+      "step": 2220
+    },
+    {
+      "epoch": 2.684131285757302,
+      "grad_norm": 0.08701752126216888,
+      "learning_rate": 6.7587308269199786e-06,
+      "loss": 0.1042,
+      "step": 2230
+    },
+    {
+      "epoch": 2.6961758506473954,
+      "grad_norm": 0.08244354277849197,
+      "learning_rate": 6.261715153594627e-06,
+      "loss": 0.1156,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7082204155374887,
+      "grad_norm": 0.14877063035964966,
+      "learning_rate": 5.783088183389062e-06,
+      "loss": 0.1076,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7082204155374887,
+      "eval_loss": 0.12096786499023438,
+      "eval_runtime": 81.6046,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.144,
+      "step": 2250
+    },
+    {
+      "epoch": 2.720264980427582,
+      "grad_norm": 0.09160082787275314,
+      "learning_rate": 5.322943808881675e-06,
+      "loss": 0.1188,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7323095453176753,
+      "grad_norm": 0.08697830885648727,
+      "learning_rate": 4.881372296907516e-06,
+      "loss": 0.1082,
+      "step": 2270
+    },
+    {
+      "epoch": 2.7443541102077686,
+      "grad_norm": 0.09075489640235901,
+      "learning_rate": 4.4584602708505285e-06,
+      "loss": 0.118,
+      "step": 2280
+    },
+    {
+      "epoch": 2.7443541102077686,
+      "eval_loss": 0.12092573195695877,
+      "eval_runtime": 81.6503,
+      "eval_samples_per_second": 4.287,
+      "eval_steps_per_second": 2.143,
+      "step": 2280
+    },
+    {
+      "epoch": 2.756398675097862,
+      "grad_norm": 0.0934319868683815,
+      "learning_rate": 4.054290693650642e-06,
+      "loss": 0.1091,
+      "step": 2290
+    },
+    {
+      "epoch": 2.7684432399879553,
+      "grad_norm": 0.08008915930986404,
+      "learning_rate": 3.6689428515288004e-06,
+      "loss": 0.1103,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7804878048780486,
+      "grad_norm": 0.07896912097930908,
+      "learning_rate": 3.3024923384334163e-06,
+      "loss": 0.1087,
+      "step": 2310
+    },
+    {
+      "epoch": 2.7804878048780486,
+      "eval_loss": 0.12093985080718994,
+      "eval_runtime": 81.4605,
+      "eval_samples_per_second": 4.297,
+      "eval_steps_per_second": 2.148,
+      "step": 2310
+    },
+    {
+      "epoch": 2.792532369768142,
+      "grad_norm": 0.08136588335037231,
+      "learning_rate": 2.9550110412109534e-06,
+      "loss": 0.1106,
+      "step": 2320
+    },
+    {
+      "epoch": 2.804576934658235,
+      "grad_norm": 0.07197284698486328,
+      "learning_rate": 2.6265671255039537e-06,
+      "loss": 0.1265,
+      "step": 2330
+    },
+    {
+      "epoch": 2.816621499548329,
+      "grad_norm": 0.09639979153871536,
+      "learning_rate": 2.3172250223787994e-06,
+      "loss": 0.1168,
+      "step": 2340
+    },
+    {
+      "epoch": 2.816621499548329,
+      "eval_loss": 0.12088128179311752,
+      "eval_runtime": 81.8851,
+      "eval_samples_per_second": 4.274,
+      "eval_steps_per_second": 2.137,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8286660644384223,
+      "grad_norm": 0.09752853214740753,
+      "learning_rate": 2.0270454156863905e-06,
+      "loss": 0.1209,
+      "step": 2350
+    },
+    {
+      "epoch": 2.8407106293285156,
+      "grad_norm": 0.08983393758535385,
+      "learning_rate": 1.7560852301575892e-06,
+      "loss": 0.1185,
+      "step": 2360
+    },
+    {
+      "epoch": 2.852755194218609,
+      "grad_norm": 0.09476975351572037,
+      "learning_rate": 1.5043976202363641e-06,
+      "loss": 0.1172,
+      "step": 2370
+    },
+    {
+      "epoch": 2.852755194218609,
+      "eval_loss": 0.1208338588476181,
+      "eval_runtime": 81.5048,
+      "eval_samples_per_second": 4.294,
+      "eval_steps_per_second": 2.147,
+      "step": 2370
+    },
+    {
+      "epoch": 2.864799759108702,
+      "grad_norm": 0.06642317026853561,
+      "learning_rate": 1.2720319596523977e-06,
+      "loss": 0.116,
+      "step": 2380
+    },
+    {
+      "epoch": 2.8768443239987955,
+      "grad_norm": 0.10626640915870667,
+      "learning_rate": 1.0590338317354454e-06,
+      "loss": 0.112,
+      "step": 2390
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.07917091995477676,
+      "learning_rate": 8.654450204731768e-07,
+      "loss": 0.1092,
+      "step": 2400
+    },
+    {
+      "epoch": 2.888888888888889,
+      "eval_loss": 0.12085919827222824,
+      "eval_runtime": 81.5821,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2493,
+  "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": 4.360791333022802e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cb9e0c5da29bc408e28b78229d144492041698a4b4939d9177cfe475720f63
+size 5777

checkpoint-2493/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-2493/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": [
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2493/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2e40b92d02b9398ad80b68d3c3c85f8f9fce96dfd3baf909c4b75e98bf4174
+size 528550256

checkpoint-2493/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-2493/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-2493/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e8a667b1136c5dbbe0177d569635569e11d2f4098ef3b8c57859269bc5028f
+size 1057397963

checkpoint-2493/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db67b920a6805fc9f84cd85126efa573cb5585230d023b3aa66f0c681049f9de
+size 14645

checkpoint-2493/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e9ee5fc9696cf6dfb42f739400a1ac79c89467317c5571df622e42a35adb72a
+size 1465

checkpoint-2493/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-2493/tokenizer.json

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

checkpoint-2493/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-2493/trainer_state.json

@@ -0,0 +1,2441 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 30,
+  "global_step": 2493,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012044564890093345,
+      "grad_norm": 11.71904468536377,
+      "learning_rate": 7.2e-06,
+      "loss": 2.9594,
+      "step": 10
+    },
+    {
+      "epoch": 0.02408912978018669,
+      "grad_norm": 2.4383621215820312,
+      "learning_rate": 1.52e-05,
+      "loss": 1.5501,
+      "step": 20
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "grad_norm": 0.7187284231185913,
+      "learning_rate": 2.32e-05,
+      "loss": 0.7478,
+      "step": 30
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "eval_loss": 0.6954202651977539,
+      "eval_runtime": 81.243,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 30
+    },
+    {
+      "epoch": 0.04817825956037338,
+      "grad_norm": 0.9893588423728943,
+      "learning_rate": 3.12e-05,
+      "loss": 0.6087,
+      "step": 40
+    },
+    {
+      "epoch": 0.06022282445046673,
+      "grad_norm": 0.6181250214576721,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.4514,
+      "step": 50
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "grad_norm": 0.5894028544425964,
+      "learning_rate": 4.72e-05,
+      "loss": 0.3809,
+      "step": 60
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "eval_loss": 0.35219648480415344,
+      "eval_runtime": 80.7477,
+      "eval_samples_per_second": 4.334,
+      "eval_steps_per_second": 2.167,
+      "step": 60
+    },
+    {
+      "epoch": 0.08431195423065342,
+      "grad_norm": 3.429518222808838,
+      "learning_rate": 5.520000000000001e-05,
+      "loss": 0.2992,
+      "step": 70
+    },
+    {
+      "epoch": 0.09635651912074676,
+      "grad_norm": 0.6878916025161743,
+      "learning_rate": 6.32e-05,
+      "loss": 0.2921,
+      "step": 80
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "grad_norm": 0.5862188339233398,
+      "learning_rate": 7.12e-05,
+      "loss": 0.2483,
+      "step": 90
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "eval_loss": 0.22866909205913544,
+      "eval_runtime": 81.2164,
+      "eval_samples_per_second": 4.309,
+      "eval_steps_per_second": 2.155,
+      "step": 90
+    },
+    {
+      "epoch": 0.12044564890093346,
+      "grad_norm": 0.7386724948883057,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 0.2107,
+      "step": 100
+    },
+    {
+      "epoch": 0.1324902137910268,
+      "grad_norm": 0.6922011375427246,
+      "learning_rate": 8.72e-05,
+      "loss": 0.1962,
+      "step": 110
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "grad_norm": 0.4779876470565796,
+      "learning_rate": 9.52e-05,
+      "loss": 0.1741,
+      "step": 120
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "eval_loss": 0.18707558512687683,
+      "eval_runtime": 81.1016,
+      "eval_samples_per_second": 4.316,
+      "eval_steps_per_second": 2.158,
+      "step": 120
+    },
+    {
+      "epoch": 0.1565793435712135,
+      "grad_norm": 0.3711669445037842,
+      "learning_rate": 0.0001032,
+      "loss": 0.1775,
+      "step": 130
+    },
+    {
+      "epoch": 0.16862390846130684,
+      "grad_norm": 0.5507099032402039,
+      "learning_rate": 0.00011120000000000002,
+      "loss": 0.1663,
+      "step": 140
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "grad_norm": 0.6897018551826477,
+      "learning_rate": 0.0001192,
+      "loss": 0.162,
+      "step": 150
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "eval_loss": 0.1689070761203766,
+      "eval_runtime": 81.1763,
+      "eval_samples_per_second": 4.312,
+      "eval_steps_per_second": 2.156,
+      "step": 150
+    },
+    {
+      "epoch": 0.19271303824149352,
+      "grad_norm": 0.30447226762771606,
+      "learning_rate": 0.0001272,
+      "loss": 0.1654,
+      "step": 160
+    },
+    {
+      "epoch": 0.20475760313158686,
+      "grad_norm": 0.36739301681518555,
+      "learning_rate": 0.0001352,
+      "loss": 0.1692,
+      "step": 170
+    },
+    {
+      "epoch": 0.21680216802168023,
+      "grad_norm": 0.42459923028945923,
+      "learning_rate": 0.0001432,
+      "loss": 0.1479,
+      "step": 180
+    },
+    {
+      "epoch": 0.21680216802168023,
+      "eval_loss": 0.16287875175476074,
+      "eval_runtime": 81.3447,
+      "eval_samples_per_second": 4.303,
+      "eval_steps_per_second": 2.151,
+      "step": 180
+    },
+    {
+      "epoch": 0.22884673291177357,
+      "grad_norm": 0.24459399282932281,
+      "learning_rate": 0.00015120000000000002,
+      "loss": 0.1567,
+      "step": 190
+    },
+    {
+      "epoch": 0.2408912978018669,
+      "grad_norm": 0.29077818989753723,
+      "learning_rate": 0.00015920000000000002,
+      "loss": 0.1491,
+      "step": 200
+    },
+    {
+      "epoch": 0.2529358626919603,
+      "grad_norm": 0.3934674561023712,
+      "learning_rate": 0.0001672,
+      "loss": 0.1587,
+      "step": 210
+    },
+    {
+      "epoch": 0.2529358626919603,
+      "eval_loss": 0.1568612903356552,
+      "eval_runtime": 80.9345,
+      "eval_samples_per_second": 4.324,
+      "eval_steps_per_second": 2.162,
+      "step": 210
+    },
+    {
+      "epoch": 0.2649804275820536,
+      "grad_norm": 0.31920939683914185,
+      "learning_rate": 0.0001752,
+      "loss": 0.1622,
+      "step": 220
+    },
+    {
+      "epoch": 0.27702499247214696,
+      "grad_norm": 0.5031167268753052,
+      "learning_rate": 0.0001832,
+      "loss": 0.147,
+      "step": 230
+    },
+    {
+      "epoch": 0.28906955736224027,
+      "grad_norm": 0.2890608310699463,
+      "learning_rate": 0.0001912,
+      "loss": 0.1433,
+      "step": 240
+    },
+    {
+      "epoch": 0.28906955736224027,
+      "eval_loss": 0.15362557768821716,
+      "eval_runtime": 80.9234,
+      "eval_samples_per_second": 4.325,
+      "eval_steps_per_second": 2.163,
+      "step": 240
+    },
+    {
+      "epoch": 0.30111412225233364,
+      "grad_norm": 0.2849373519420624,
+      "learning_rate": 0.00019920000000000002,
+      "loss": 0.1471,
+      "step": 250
+    },
+    {
+      "epoch": 0.313158687142427,
+      "grad_norm": 0.263950914144516,
+      "learning_rate": 0.0001999920550627653,
+      "loss": 0.155,
+      "step": 260
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 0.31182682514190674,
+      "learning_rate": 0.00019996459270297992,
+      "loss": 0.138,
+      "step": 270
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "eval_loss": 0.15008553862571716,
+      "eval_runtime": 80.9483,
+      "eval_samples_per_second": 4.324,
+      "eval_steps_per_second": 2.162,
+      "step": 270
+    },
+    {
+      "epoch": 0.3372478169226137,
+      "grad_norm": 0.41790467500686646,
+      "learning_rate": 0.00019991752022102606,
+      "loss": 0.1472,
+      "step": 280
+    },
+    {
+      "epoch": 0.349292381812707,
+      "grad_norm": 0.29337936639785767,
+      "learning_rate": 0.0001998508468511445,
+      "loss": 0.152,
+      "step": 290
+    },
+    {
+      "epoch": 0.36133694670280037,
+      "grad_norm": 0.1533428430557251,
+      "learning_rate": 0.0001997645856726956,
+      "loss": 0.1427,
+      "step": 300
+    },
+    {
+      "epoch": 0.36133694670280037,
+      "eval_loss": 0.14941252768039703,
+      "eval_runtime": 81.0588,
+      "eval_samples_per_second": 4.318,
+      "eval_steps_per_second": 2.159,
+      "step": 300
+    },
+    {
+      "epoch": 0.37338151159289373,
+      "grad_norm": 0.3626411557197571,
+      "learning_rate": 0.0001996587536075934,
+      "loss": 0.1539,
+      "step": 310
+    },
+    {
+      "epoch": 0.38542607648298705,
+      "grad_norm": 0.3157321810722351,
+      "learning_rate": 0.00019953337141698617,
+      "loss": 0.1457,
+      "step": 320
+    },
+    {
+      "epoch": 0.3974706413730804,
+      "grad_norm": 0.18949578702449799,
+      "learning_rate": 0.00019938846369718348,
+      "loss": 0.1471,
+      "step": 330
+    },
+    {
+      "epoch": 0.3974706413730804,
+      "eval_loss": 0.14507745206356049,
+      "eval_runtime": 81.0028,
+      "eval_samples_per_second": 4.321,
+      "eval_steps_per_second": 2.16,
+      "step": 330
+    },
+    {
+      "epoch": 0.4095152062631737,
+      "grad_norm": 0.2189997136592865,
+      "learning_rate": 0.0001992240588748314,
+      "loss": 0.1423,
+      "step": 340
+    },
+    {
+      "epoch": 0.4215597711532671,
+      "grad_norm": 0.2674465775489807,
+      "learning_rate": 0.00019904018920133574,
+      "loss": 0.1397,
+      "step": 350
+    },
+    {
+      "epoch": 0.43360433604336046,
+      "grad_norm": 0.3467840552330017,
+      "learning_rate": 0.00019883689074653548,
+      "loss": 0.1486,
+      "step": 360
+    },
+    {
+      "epoch": 0.43360433604336046,
+      "eval_loss": 0.1380164623260498,
+      "eval_runtime": 81.2554,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.154,
+      "step": 360
+    },
+    {
+      "epoch": 0.4456489009334538,
+      "grad_norm": 0.22817489504814148,
+      "learning_rate": 0.00019861420339162682,
+      "loss": 0.1411,
+      "step": 370
+    },
+    {
+      "epoch": 0.45769346582354714,
+      "grad_norm": 0.1939237415790558,
+      "learning_rate": 0.0001983721708213397,
+      "loss": 0.1337,
+      "step": 380
+    },
+    {
+      "epoch": 0.46973803071364045,
+      "grad_norm": 0.20223841071128845,
+      "learning_rate": 0.00019811084051536812,
+      "loss": 0.147,
+      "step": 390
+    },
+    {
+      "epoch": 0.46973803071364045,
+      "eval_loss": 0.13835138082504272,
+      "eval_runtime": 81.2083,
+      "eval_samples_per_second": 4.31,
+      "eval_steps_per_second": 2.155,
+      "step": 390
+    },
+    {
+      "epoch": 0.4817825956037338,
+      "grad_norm": 0.16610513627529144,
+      "learning_rate": 0.00019783026373905603,
+      "loss": 0.1261,
+      "step": 400
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.13892178237438202,
+      "learning_rate": 0.0001975304955333405,
+      "loss": 0.1303,
+      "step": 410
+    },
+    {
+      "epoch": 0.5058717253839206,
+      "grad_norm": 0.17607590556144714,
+      "learning_rate": 0.00019721159470395446,
+      "loss": 0.1408,
+      "step": 420
+    },
+    {
+      "epoch": 0.5058717253839206,
+      "eval_loss": 0.13557562232017517,
+      "eval_runtime": 81.2501,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 420
+    },
+    {
+      "epoch": 0.5179162902740139,
+      "grad_norm": 0.2578093409538269,
+      "learning_rate": 0.0001968736238098906,
+      "loss": 0.1328,
+      "step": 430
+    },
+    {
+      "epoch": 0.5299608551641072,
+      "grad_norm": 0.5826597213745117,
+      "learning_rate": 0.00019651664915112913,
+      "loss": 0.1379,
+      "step": 440
+    },
+    {
+      "epoch": 0.5420054200542005,
+      "grad_norm": 0.2640504240989685,
+      "learning_rate": 0.00019614074075563178,
+      "loss": 0.1328,
+      "step": 450
+    },
+    {
+      "epoch": 0.5420054200542005,
+      "eval_loss": 0.13704629242420197,
+      "eval_runtime": 81.2461,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 450
+    },
+    {
+      "epoch": 0.5540499849442939,
+      "grad_norm": 0.25430986285209656,
+      "learning_rate": 0.00019574597236560428,
+      "loss": 0.1295,
+      "step": 460
+    },
+    {
+      "epoch": 0.5660945498343872,
+      "grad_norm": 0.2172861099243164,
+      "learning_rate": 0.00019533242142303028,
+      "loss": 0.1274,
+      "step": 470
+    },
+    {
+      "epoch": 0.5781391147244805,
+      "grad_norm": 0.18936924636363983,
+      "learning_rate": 0.00019490016905447958,
+      "loss": 0.131,
+      "step": 480
+    },
+    {
+      "epoch": 0.5781391147244805,
+      "eval_loss": 0.13753947615623474,
+      "eval_runtime": 81.0949,
+      "eval_samples_per_second": 4.316,
+      "eval_steps_per_second": 2.158,
+      "step": 480
+    },
+    {
+      "epoch": 0.590183679614574,
+      "grad_norm": 0.26435989141464233,
+      "learning_rate": 0.00019444930005519347,
+      "loss": 0.132,
+      "step": 490
+    },
+    {
+      "epoch": 0.6022282445046673,
+      "grad_norm": 0.23327338695526123,
+      "learning_rate": 0.00019397990287245027,
+      "loss": 0.1417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6142728093947606,
+      "grad_norm": 0.14256203174591064,
+      "learning_rate": 0.00019349206958821474,
+      "loss": 0.1392,
+      "step": 510
+    },
+    {
+      "epoch": 0.6142728093947606,
+      "eval_loss": 0.13641956448554993,
+      "eval_runtime": 81.0841,
+      "eval_samples_per_second": 4.317,
+      "eval_steps_per_second": 2.158,
+      "step": 510
+    },
+    {
+      "epoch": 0.626317374284854,
+      "grad_norm": 0.16011199355125427,
+      "learning_rate": 0.00019298589590107415,
+      "loss": 0.1406,
+      "step": 520
+    },
+    {
+      "epoch": 0.6383619391749473,
+      "grad_norm": 0.1269129067659378,
+      "learning_rate": 0.00019246148110746515,
+      "loss": 0.1346,
+      "step": 530
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 0.13770046830177307,
+      "learning_rate": 0.0001919189280821946,
+      "loss": 0.1315,
+      "step": 540
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "eval_loss": 0.1363556832075119,
+      "eval_runtime": 81.2186,
+      "eval_samples_per_second": 4.309,
+      "eval_steps_per_second": 2.155,
+      "step": 540
+    },
+    {
+      "epoch": 0.662451068955134,
+      "grad_norm": 0.18796966969966888,
+      "learning_rate": 0.00019135834325825868,
+      "loss": 0.13,
+      "step": 550
+    },
+    {
+      "epoch": 0.6744956338452274,
+      "grad_norm": 0.12326055020093918,
+      "learning_rate": 0.00019077983660596365,
+      "loss": 0.1339,
+      "step": 560
+    },
+    {
+      "epoch": 0.6865401987353207,
+      "grad_norm": 0.1480596363544464,
+      "learning_rate": 0.00019018352161135317,
+      "loss": 0.1296,
+      "step": 570
+    },
+    {
+      "epoch": 0.6865401987353207,
+      "eval_loss": 0.13280269503593445,
+      "eval_runtime": 81.3546,
+      "eval_samples_per_second": 4.302,
+      "eval_steps_per_second": 2.151,
+      "step": 570
+    },
+    {
+      "epoch": 0.698584763625414,
+      "grad_norm": 0.15606318414211273,
+      "learning_rate": 0.0001895695152539455,
+      "loss": 0.1296,
+      "step": 580
+    },
+    {
+      "epoch": 0.7106293285155074,
+      "grad_norm": 0.09551403671503067,
+      "learning_rate": 0.00018893793798378553,
+      "loss": 0.1323,
+      "step": 590
+    },
+    {
+      "epoch": 0.7226738934056007,
+      "grad_norm": 0.11749322712421417,
+      "learning_rate": 0.00018828891369781605,
+      "loss": 0.1179,
+      "step": 600
+    },
+    {
+      "epoch": 0.7226738934056007,
+      "eval_loss": 0.12917345762252808,
+      "eval_runtime": 81.4843,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.148,
+      "step": 600
+    },
+    {
+      "epoch": 0.734718458295694,
+      "grad_norm": 0.11540284752845764,
+      "learning_rate": 0.0001876225697155729,
+      "loss": 0.1227,
+      "step": 610
+    },
+    {
+      "epoch": 0.7467630231857875,
+      "grad_norm": 0.3190910518169403,
+      "learning_rate": 0.00018693903675420846,
+      "loss": 0.1281,
+      "step": 620
+    },
+    {
+      "epoch": 0.7588075880758808,
+      "grad_norm": 0.11964758485555649,
+      "learning_rate": 0.00018623844890284884,
+      "loss": 0.1356,
+      "step": 630
+    },
+    {
+      "epoch": 0.7588075880758808,
+      "eval_loss": 0.12936915457248688,
+      "eval_runtime": 81.4409,
+      "eval_samples_per_second": 4.298,
+      "eval_steps_per_second": 2.149,
+      "step": 630
+    },
+    {
+      "epoch": 0.7708521529659741,
+      "grad_norm": 0.10809649527072906,
+      "learning_rate": 0.00018552094359628956,
+      "loss": 0.1337,
+      "step": 640
+    },
+    {
+      "epoch": 0.7828967178560674,
+      "grad_norm": 0.13179966807365417,
+      "learning_rate": 0.00018478666158803475,
+      "loss": 0.1213,
+      "step": 650
+    },
+    {
+      "epoch": 0.7949412827461608,
+      "grad_norm": 0.13050246238708496,
+      "learning_rate": 0.00018403574692268566,
+      "loss": 0.1274,
+      "step": 660
+    },
+    {
+      "epoch": 0.7949412827461608,
+      "eval_loss": 0.129548579454422,
+      "eval_runtime": 81.3854,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.15,
+      "step": 660
+    },
+    {
+      "epoch": 0.8069858476362541,
+      "grad_norm": 0.10548313707113266,
+      "learning_rate": 0.00018326834690768308,
+      "loss": 0.1266,
+      "step": 670
+    },
+    {
+      "epoch": 0.8190304125263475,
+      "grad_norm": 0.11163028329610825,
+      "learning_rate": 0.00018248461208441016,
+      "loss": 0.1275,
+      "step": 680
+    },
+    {
+      "epoch": 0.8310749774164409,
+      "grad_norm": 0.10246960818767548,
+      "learning_rate": 0.00018168469619866037,
+      "loss": 0.1262,
+      "step": 690
+    },
+    {
+      "epoch": 0.8310749774164409,
+      "eval_loss": 0.12998254597187042,
+      "eval_runtime": 81.2607,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.154,
+      "step": 690
+    },
+    {
+      "epoch": 0.8431195423065342,
+      "grad_norm": 0.16775400936603546,
+      "learning_rate": 0.00018086875617047738,
+      "loss": 0.128,
+      "step": 700
+    },
+    {
+      "epoch": 0.8551641071966275,
+      "grad_norm": 0.09823903441429138,
+      "learning_rate": 0.00018003695206337164,
+      "loss": 0.1186,
+      "step": 710
+    },
+    {
+      "epoch": 0.8672086720867209,
+      "grad_norm": 0.08154378831386566,
+      "learning_rate": 0.0001791894470529209,
+      "loss": 0.1304,
+      "step": 720
+    },
+    {
+      "epoch": 0.8672086720867209,
+      "eval_loss": 0.12851889431476593,
+      "eval_runtime": 81.3179,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 2.152,
+      "step": 720
+    },
+    {
+      "epoch": 0.8792532369768142,
+      "grad_norm": 0.13566914200782776,
+      "learning_rate": 0.00017832640739475964,
+      "loss": 0.1256,
+      "step": 730
+    },
+    {
+      "epoch": 0.8912978018669075,
+      "grad_norm": 0.21967343986034393,
+      "learning_rate": 0.00017744800239196485,
+      "loss": 0.1049,
+      "step": 740
+    },
+    {
+      "epoch": 0.9033423667570009,
+      "grad_norm": 0.12291447818279266,
+      "learning_rate": 0.00017655440436184361,
+      "loss": 0.1352,
+      "step": 750
+    },
+    {
+      "epoch": 0.9033423667570009,
+      "eval_loss": 0.12859711050987244,
+      "eval_runtime": 81.5112,
+      "eval_samples_per_second": 4.294,
+      "eval_steps_per_second": 2.147,
+      "step": 750
+    },
+    {
+      "epoch": 0.9153869316470943,
+      "grad_norm": 0.23631049692630768,
+      "learning_rate": 0.00017564578860212952,
+      "loss": 0.1236,
+      "step": 760
+    },
+    {
+      "epoch": 0.9274314965371876,
+      "grad_norm": 0.13145385682582855,
+      "learning_rate": 0.00017472233335659443,
+      "loss": 0.1235,
+      "step": 770
+    },
+    {
+      "epoch": 0.9394760614272809,
+      "grad_norm": 0.0923519879579544,
+      "learning_rate": 0.00017378421978008212,
+      "loss": 0.1224,
+      "step": 780
+    },
+    {
+      "epoch": 0.9394760614272809,
+      "eval_loss": 0.12813878059387207,
+      "eval_runtime": 81.2514,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 780
+    },
+    {
+      "epoch": 0.9515206263173743,
+      "grad_norm": 0.2052728235721588,
+      "learning_rate": 0.0001728316319029713,
+      "loss": 0.1189,
+      "step": 790
+    },
+    {
+      "epoch": 0.9635651912074676,
+      "grad_norm": 0.19939783215522766,
+      "learning_rate": 0.0001718647565950739,
+      "loss": 0.128,
+      "step": 800
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.11448610574007034,
+      "learning_rate": 0.00017088378352897703,
+      "loss": 0.1103,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "eval_loss": 0.12625984847545624,
+      "eval_runtime": 81.2673,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.153,
+      "step": 810
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.11135770380496979,
+      "learning_rate": 0.00016988890514283447,
+      "loss": 0.1281,
+      "step": 820
+    },
+    {
+      "epoch": 0.9996988858777477,
+      "grad_norm": 0.11028297245502472,
+      "learning_rate": 0.00016888031660261622,
+      "loss": 0.1225,
+      "step": 830
+    },
+    {
+      "epoch": 1.010840108401084,
+      "grad_norm": 0.11298307776451111,
+      "learning_rate": 0.00016785821576382245,
+      "loss": 0.1188,
+      "step": 840
+    },
+    {
+      "epoch": 1.010840108401084,
+      "eval_loss": 0.1276378333568573,
+      "eval_runtime": 81.1811,
+      "eval_samples_per_second": 4.311,
+      "eval_steps_per_second": 2.156,
+      "step": 840
+    },
+    {
+      "epoch": 1.0228846732911774,
+      "grad_norm": 0.09120020270347595,
+      "learning_rate": 0.0001668228031326702,
+      "loss": 0.1169,
+      "step": 850
+    },
+    {
+      "epoch": 1.0349292381812707,
+      "grad_norm": 0.11060494184494019,
+      "learning_rate": 0.00016577428182675973,
+      "loss": 0.1243,
+      "step": 860
+    },
+    {
+      "epoch": 1.046973803071364,
+      "grad_norm": 0.09636874496936798,
+      "learning_rate": 0.0001647128575352292,
+      "loss": 0.1187,
+      "step": 870
+    },
+    {
+      "epoch": 1.046973803071364,
+      "eval_loss": 0.12680906057357788,
+      "eval_runtime": 81.1164,
+      "eval_samples_per_second": 4.315,
+      "eval_steps_per_second": 2.157,
+      "step": 870
+    },
+    {
+      "epoch": 1.0590183679614573,
+      "grad_norm": 0.10281568765640259,
+      "learning_rate": 0.000163638738478404,
+      "loss": 0.133,
+      "step": 880
+    },
+    {
+      "epoch": 1.0710629328515506,
+      "grad_norm": 0.08682233840227127,
+      "learning_rate": 0.0001625521353669504,
+      "loss": 0.1171,
+      "step": 890
+    },
+    {
+      "epoch": 1.0831074977416442,
+      "grad_norm": 0.1339954435825348,
+      "learning_rate": 0.00016145326136054008,
+      "loss": 0.1257,
+      "step": 900
+    },
+    {
+      "epoch": 1.0831074977416442,
+      "eval_loss": 0.12813013792037964,
+      "eval_runtime": 81.4418,
+      "eval_samples_per_second": 4.298,
+      "eval_steps_per_second": 2.149,
+      "step": 900
+    },
+    {
+      "epoch": 1.0951520626317375,
+      "grad_norm": 0.09956265985965729,
+      "learning_rate": 0.00016034233202603463,
+      "loss": 0.1287,
+      "step": 910
+    },
+    {
+      "epoch": 1.1071966275218308,
+      "grad_norm": 0.07889163494110107,
+      "learning_rate": 0.00015921956529519747,
+      "loss": 0.1135,
+      "step": 920
+    },
+    {
+      "epoch": 1.119241192411924,
+      "grad_norm": 0.07798007130622864,
+      "learning_rate": 0.00015808518142194214,
+      "loss": 0.1128,
+      "step": 930
+    },
+    {
+      "epoch": 1.119241192411924,
+      "eval_loss": 0.12662966549396515,
+      "eval_runtime": 81.2769,
+      "eval_samples_per_second": 4.306,
+      "eval_steps_per_second": 2.153,
+      "step": 930
+    },
+    {
+      "epoch": 1.1312857573020174,
+      "grad_norm": 0.09110717475414276,
+      "learning_rate": 0.00015693940293912492,
+      "loss": 0.1161,
+      "step": 940
+    },
+    {
+      "epoch": 1.1433303221921107,
+      "grad_norm": 0.10704551637172699,
+      "learning_rate": 0.00015578245461489042,
+      "loss": 0.1237,
+      "step": 950
+    },
+    {
+      "epoch": 1.1553748870822043,
+      "grad_norm": 0.12007839977741241,
+      "learning_rate": 0.00015461456340857857,
+      "loss": 0.1246,
+      "step": 960
+    },
+    {
+      "epoch": 1.1553748870822043,
+      "eval_loss": 0.12597930431365967,
+      "eval_runtime": 81.2379,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 2.154,
+      "step": 960
+    },
+    {
+      "epoch": 1.1674194519722976,
+      "grad_norm": 0.09195715934038162,
+      "learning_rate": 0.00015343595842620198,
+      "loss": 0.1179,
+      "step": 970
+    },
+    {
+      "epoch": 1.1794640168623909,
+      "grad_norm": 0.11327285319566727,
+      "learning_rate": 0.000152246870875502,
+      "loss": 0.1219,
+      "step": 980
+    },
+    {
+      "epoch": 1.1915085817524842,
+      "grad_norm": 0.12147443741559982,
+      "learning_rate": 0.00015104753402059252,
+      "loss": 0.1198,
+      "step": 990
+    },
+    {
+      "epoch": 1.1915085817524842,
+      "eval_loss": 0.12678198516368866,
+      "eval_runtime": 81.2272,
+      "eval_samples_per_second": 4.309,
+      "eval_steps_per_second": 2.154,
+      "step": 990
+    },
+    {
+      "epoch": 1.2035531466425775,
+      "grad_norm": 0.12530316412448883,
+      "learning_rate": 0.00014983818313620047,
+      "loss": 0.1215,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2155977115326708,
+      "grad_norm": 0.21503940224647522,
+      "learning_rate": 0.00014861905546151164,
+      "loss": 0.132,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2276422764227641,
+      "grad_norm": 0.09851568937301636,
+      "learning_rate": 0.00014739039015363155,
+      "loss": 0.1255,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2276422764227641,
+      "eval_loss": 0.1265084594488144,
+      "eval_runtime": 81.2978,
+      "eval_samples_per_second": 4.305,
+      "eval_steps_per_second": 2.153,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2396868413128577,
+      "grad_norm": 0.09794170409440994,
+      "learning_rate": 0.0001461524282406696,
+      "loss": 0.1203,
+      "step": 1030
+    },
+    {
+      "epoch": 1.251731406202951,
+      "grad_norm": 0.09283249080181122,
+      "learning_rate": 0.00014490541257445664,
+      "loss": 0.1241,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2637759710930443,
+      "grad_norm": 0.10757778584957123,
+      "learning_rate": 0.00014364958778290436,
+      "loss": 0.1263,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2637759710930443,
+      "eval_loss": 0.1275068074464798,
+      "eval_runtime": 81.3037,
+      "eval_samples_per_second": 4.305,
+      "eval_steps_per_second": 2.152,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2758205359831376,
+      "grad_norm": 0.08741755038499832,
+      "learning_rate": 0.00014238520022201665,
+      "loss": 0.1279,
+      "step": 1060
+    },
+    {
+      "epoch": 1.287865100873231,
+      "grad_norm": 0.09674480557441711,
+      "learning_rate": 0.00014111249792756164,
+      "loss": 0.1203,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2999096657633242,
+      "grad_norm": 0.18980656564235687,
+      "learning_rate": 0.00013983173056641437,
+      "loss": 0.1273,
+      "step": 1080
+    },
+    {
+      "epoch": 1.2999096657633242,
+      "eval_loss": 0.12540876865386963,
+      "eval_runtime": 81.3684,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.151,
+      "step": 1080
+    },
+    {
+      "epoch": 1.3119542306534178,
+      "grad_norm": 0.11260770261287689,
+      "learning_rate": 0.00013854314938757954,
+      "loss": 0.1209,
+      "step": 1090
+    },
+    {
+      "epoch": 1.323998795543511,
+      "grad_norm": 0.08883814513683319,
+      "learning_rate": 0.00013724700717290385,
+      "loss": 0.1307,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3360433604336044,
+      "grad_norm": 0.08555177599191666,
+      "learning_rate": 0.0001359435581874874,
+      "loss": 0.1187,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3360433604336044,
+      "eval_loss": 0.1246650293469429,
+      "eval_runtime": 81.3179,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 2.152,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3480879253236977,
+      "grad_norm": 0.09265279769897461,
+      "learning_rate": 0.0001346330581298046,
+      "loss": 0.1237,
+      "step": 1120
+    },
+    {
+      "epoch": 1.360132490213791,
+      "grad_norm": 0.07397205382585526,
+      "learning_rate": 0.0001333157640815434,
+      "loss": 0.1194,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3721770551038843,
+      "grad_norm": 0.10523436218500137,
+      "learning_rate": 0.00013199193445717362,
+      "loss": 0.1215,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3721770551038843,
+      "eval_loss": 0.12532441318035126,
+      "eval_runtime": 81.5003,
+      "eval_samples_per_second": 4.294,
+      "eval_steps_per_second": 2.147,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3842216199939776,
+      "grad_norm": 0.08104018867015839,
+      "learning_rate": 0.00013066182895325339,
+      "loss": 0.1276,
+      "step": 1150
+    },
+    {
+      "epoch": 1.396266184884071,
+      "grad_norm": 0.1049809381365776,
+      "learning_rate": 0.00012932570849748446,
+      "loss": 0.128,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4083107497741645,
+      "grad_norm": 0.10500895977020264,
+      "learning_rate": 0.00012798383519752577,
+      "loss": 0.1179,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4083107497741645,
+      "eval_loss": 0.12398175895214081,
+      "eval_runtime": 81.4012,
+      "eval_samples_per_second": 4.3,
+      "eval_steps_per_second": 2.15,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4203553146642578,
+      "grad_norm": 0.08427383005619049,
+      "learning_rate": 0.00012663647228957562,
+      "loss": 0.1145,
+      "step": 1180
+    },
+    {
+      "epoch": 1.432399879554351,
+      "grad_norm": 0.08236031979322433,
+      "learning_rate": 0.0001252838840867324,
+      "loss": 0.1216,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.08572593331336975,
+      "learning_rate": 0.00012392633592714423,
+      "loss": 0.128,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "eval_loss": 0.1240333542227745,
+      "eval_runtime": 81.3808,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.15,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4564890093345377,
+      "grad_norm": 0.08900213986635208,
+      "learning_rate": 0.00012256409412195727,
+      "loss": 0.1171,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4685335742246313,
+      "grad_norm": 0.09740438312292099,
+      "learning_rate": 0.0001211974259030733,
+      "loss": 0.1316,
+      "step": 1220
+    },
+    {
+      "epoch": 1.4805781391147246,
+      "grad_norm": 0.07978689670562744,
+      "learning_rate": 0.00011982659937072677,
+      "loss": 0.1219,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4805781391147246,
+      "eval_loss": 0.12412716448307037,
+      "eval_runtime": 81.2608,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.154,
+      "step": 1230
+    },
+    {
+      "epoch": 1.492622704004818,
+      "grad_norm": 0.08000902086496353,
+      "learning_rate": 0.00011845188344089126,
+      "loss": 0.1135,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5046672688949112,
+      "grad_norm": 0.07367110252380371,
+      "learning_rate": 0.00011707354779252612,
+      "loss": 0.1206,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5167118337850045,
+      "grad_norm": 0.07485098391771317,
+      "learning_rate": 0.00011569186281467335,
+      "loss": 0.1138,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5167118337850045,
+      "eval_loss": 0.1249684989452362,
+      "eval_runtime": 81.6234,
+      "eval_samples_per_second": 4.288,
+      "eval_steps_per_second": 2.144,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5287563986750978,
+      "grad_norm": 0.11146491765975952,
+      "learning_rate": 0.00011430709955341514,
+      "loss": 0.1272,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5408009635651911,
+      "grad_norm": 0.08664289861917496,
+      "learning_rate": 0.00011291952965870269,
+      "loss": 0.1147,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5528455284552845,
+      "grad_norm": 0.09051596373319626,
+      "learning_rate": 0.00011152942533106638,
+      "loss": 0.1161,
+      "step": 1290
+    },
+    {
+      "epoch": 1.5528455284552845,
+      "eval_loss": 0.12454230338335037,
+      "eval_runtime": 81.4318,
+      "eval_samples_per_second": 4.298,
+      "eval_steps_per_second": 2.149,
+      "step": 1290
+    },
+    {
+      "epoch": 1.5648900933453778,
+      "grad_norm": 0.06956392526626587,
+      "learning_rate": 0.000110137059268218,
+      "loss": 0.1077,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5769346582354713,
+      "grad_norm": 0.07337108254432678,
+      "learning_rate": 0.00010874270461155554,
+      "loss": 0.124,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5889792231255646,
+      "grad_norm": 0.08082354068756104,
+      "learning_rate": 0.0001073466348925807,
+      "loss": 0.1108,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5889792231255646,
+      "eval_loss": 0.12420380860567093,
+      "eval_runtime": 81.6866,
+      "eval_samples_per_second": 4.285,
+      "eval_steps_per_second": 2.142,
+      "step": 1320
+    },
+    {
+      "epoch": 1.601023788015658,
+      "grad_norm": 0.07141824066638947,
+      "learning_rate": 0.00010594912397924018,
+      "loss": 0.1112,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6130683529057512,
+      "grad_norm": 0.09476039558649063,
+      "learning_rate": 0.00010455044602220076,
+      "loss": 0.1257,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6251129177958448,
+      "grad_norm": 0.06789754331111908,
+      "learning_rate": 0.00010315087540106894,
+      "loss": 0.1167,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6251129177958448,
+      "eval_loss": 0.12411510944366455,
+      "eval_runtime": 81.5821,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 1350
+    },
+    {
+      "epoch": 1.637157482685938,
+      "grad_norm": 0.08458850532770157,
+      "learning_rate": 0.00010175068667056578,
+      "loss": 0.1215,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6492020475760314,
+      "grad_norm": 0.0818653479218483,
+      "learning_rate": 0.00010035015450666723,
+      "loss": 0.1193,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6612466124661247,
+      "grad_norm": 0.060270510613918304,
+      "learning_rate": 9.894955365272087e-05,
+      "loss": 0.1094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6612466124661247,
+      "eval_loss": 0.12342710047960281,
+      "eval_runtime": 81.3723,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.151,
+      "step": 1380
+    },
+    {
+      "epoch": 1.673291177356218,
+      "grad_norm": 0.08454828709363937,
+      "learning_rate": 9.75491588655492e-05,
+      "loss": 0.1205,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6853357422463113,
+      "grad_norm": 0.06156294047832489,
+      "learning_rate": 9.614924486155047e-05,
+      "loss": 0.1111,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6973803071364046,
+      "grad_norm": 0.08005426079034805,
+      "learning_rate": 9.475008626280739e-05,
+      "loss": 0.1077,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6973803071364046,
+      "eval_loss": 0.12282679229974747,
+      "eval_runtime": 81.2841,
+      "eval_samples_per_second": 4.306,
+      "eval_steps_per_second": 2.153,
+      "step": 1410
+    },
+    {
+      "epoch": 1.709424872026498,
+      "grad_norm": 0.08515966683626175,
+      "learning_rate": 9.335195754321427e-05,
+      "loss": 0.1226,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7214694369165913,
+      "grad_norm": 0.08117437362670898,
+      "learning_rate": 9.195513297463339e-05,
+      "loss": 0.1158,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7335140018066846,
+      "grad_norm": 0.0748409777879715,
+      "learning_rate": 9.055988657309075e-05,
+      "loss": 0.1152,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7335140018066846,
+      "eval_loss": 0.12351047992706299,
+      "eval_runtime": 81.3284,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 2.152,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7455585666967781,
+      "grad_norm": 0.08821168541908264,
+      "learning_rate": 8.916649204502231e-05,
+      "loss": 0.1231,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7576031315868714,
+      "grad_norm": 0.06368843466043472,
+      "learning_rate": 8.777522273358076e-05,
+      "loss": 0.1144,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7696476964769647,
+      "grad_norm": 0.08906359225511551,
+      "learning_rate": 8.638635156501353e-05,
+      "loss": 0.1278,
+      "step": 1470
+    },
+    {
+      "epoch": 1.7696476964769647,
+      "eval_loss": 0.12412309646606445,
+      "eval_runtime": 81.4647,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 2.148,
+      "step": 1470
+    },
+    {
+      "epoch": 1.7816922613670583,
+      "grad_norm": 0.13860240578651428,
+      "learning_rate": 8.500015099512282e-05,
+      "loss": 0.1135,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7937368262571516,
+      "grad_norm": 0.08925935626029968,
+      "learning_rate": 8.361689295581759e-05,
+      "loss": 0.1274,
+      "step": 1490
+    },
+    {
+      "epoch": 1.805781391147245,
+      "grad_norm": 0.2061154991388321,
+      "learning_rate": 8.223684880176861e-05,
+      "loss": 0.1245,
+      "step": 1500
+    },
+    {
+      "epoch": 1.805781391147245,
+      "eval_loss": 0.12294992804527283,
+      "eval_runtime": 81.5386,
+      "eval_samples_per_second": 4.292,
+      "eval_steps_per_second": 2.146,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8178259560373382,
+      "grad_norm": 0.07016266882419586,
+      "learning_rate": 8.086028925717661e-05,
+      "loss": 0.1215,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8298705209274315,
+      "grad_norm": 0.19503405690193176,
+      "learning_rate": 7.948748436266409e-05,
+      "loss": 0.1169,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8419150858175248,
+      "grad_norm": 0.07560829073190689,
+      "learning_rate": 7.811870342230127e-05,
+      "loss": 0.1219,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8419150858175248,
+      "eval_loss": 0.12353645265102386,
+      "eval_runtime": 81.5233,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.147,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8539596507076181,
+      "grad_norm": 0.06638047844171524,
+      "learning_rate": 7.675421495077657e-05,
+      "loss": 0.1174,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8660042155977115,
+      "grad_norm": 0.07245375961065292,
+      "learning_rate": 7.539428662072188e-05,
+      "loss": 0.1263,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8780487804878048,
+      "grad_norm": 0.08080323040485382,
+      "learning_rate": 7.403918521020305e-05,
+      "loss": 0.1261,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8780487804878048,
+      "eval_loss": 0.12283791601657867,
+      "eval_runtime": 81.5734,
+      "eval_samples_per_second": 4.291,
+      "eval_steps_per_second": 2.145,
+      "step": 1560
+    },
+    {
+      "epoch": 1.890093345377898,
+      "grad_norm": 0.06938530504703522,
+      "learning_rate": 7.268917655038581e-05,
+      "loss": 0.1167,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9021379102679916,
+      "grad_norm": 0.07764075696468353,
+      "learning_rate": 7.134452547338753e-05,
+      "loss": 0.1191,
+      "step": 1580
+    },
+    {
+      "epoch": 1.914182475158085,
+      "grad_norm": 0.10729371011257172,
+      "learning_rate": 7.000549576032489e-05,
+      "loss": 0.1175,
+      "step": 1590
+    },
+    {
+      "epoch": 1.914182475158085,
+      "eval_loss": 0.12257985025644302,
+      "eval_runtime": 81.3844,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 2.15,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9262270400481782,
+      "grad_norm": 0.06268001347780228,
+      "learning_rate": 6.867235008956783e-05,
+      "loss": 0.1203,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9382716049382716,
+      "grad_norm": 0.059695664793252945,
+      "learning_rate": 6.734534998520969e-05,
+      "loss": 0.1147,
+      "step": 1610
+    },
+    {
+      "epoch": 1.950316169828365,
+      "grad_norm": 0.07781612873077393,
+      "learning_rate": 6.602475576576383e-05,
+      "loss": 0.1191,
+      "step": 1620
+    },
+    {
+      "epoch": 1.950316169828365,
+      "eval_loss": 0.1225815936923027,
+      "eval_runtime": 81.7725,
+      "eval_samples_per_second": 4.28,
+      "eval_steps_per_second": 2.14,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9623607347184584,
+      "grad_norm": 0.06548433750867844,
+      "learning_rate": 6.471082649309686e-05,
+      "loss": 0.1181,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9744052996085517,
+      "grad_norm": 0.0688992366194725,
+      "learning_rate": 6.34038199216082e-05,
+      "loss": 0.1139,
+      "step": 1640
+    },
+    {
+      "epoch": 1.986449864498645,
+      "grad_norm": 0.07544533908367157,
+      "learning_rate": 6.210399244766632e-05,
+      "loss": 0.1194,
+      "step": 1650
+    },
+    {
+      "epoch": 1.986449864498645,
+      "eval_loss": 0.12259992212057114,
+      "eval_runtime": 81.5949,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.145,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9984944293887383,
+      "grad_norm": 0.13208015263080597,
+      "learning_rate": 6.0811599059311195e-05,
+      "loss": 0.1185,
+      "step": 1660
+    },
+    {
+      "epoch": 2.009635651912075,
+      "grad_norm": 0.08133638650178909,
+      "learning_rate": 5.952689328623321e-05,
+      "loss": 0.1264,
+      "step": 1670
+    },
+    {
+      "epoch": 2.021680216802168,
+      "grad_norm": 0.08000742644071579,
+      "learning_rate": 5.8250127150038016e-05,
+      "loss": 0.1108,
+      "step": 1680
+    },
+    {
+      "epoch": 2.021680216802168,
+      "eval_loss": 0.12281496077775955,
+      "eval_runtime": 81.5447,
+      "eval_samples_per_second": 4.292,
+      "eval_steps_per_second": 2.146,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0337247816922615,
+      "grad_norm": 0.06525713950395584,
+      "learning_rate": 5.698155111480722e-05,
+      "loss": 0.1141,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0457693465823548,
+      "grad_norm": 0.06997241824865341,
+      "learning_rate": 5.57214140379649e-05,
+      "loss": 0.1146,
+      "step": 1700
+    },
+    {
+      "epoch": 2.057813911472448,
+      "grad_norm": 0.07603967189788818,
+      "learning_rate": 5.4469963121458776e-05,
+      "loss": 0.1169,
+      "step": 1710
+    },
+    {
+      "epoch": 2.057813911472448,
+      "eval_loss": 0.12317664176225662,
+      "eval_runtime": 81.5005,
+      "eval_samples_per_second": 4.294,
+      "eval_steps_per_second": 2.147,
+      "step": 1710
+    },
+    {
+      "epoch": 2.0698584763625414,
+      "grad_norm": 0.09060684591531754,
+      "learning_rate": 5.322744386326675e-05,
+      "loss": 0.1139,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0819030412526347,
+      "grad_norm": 0.09253629297018051,
+      "learning_rate": 5.1994100009237e-05,
+      "loss": 0.1174,
+      "step": 1730
+    },
+    {
+      "epoch": 2.093947606142728,
+      "grad_norm": 0.0707191526889801,
+      "learning_rate": 5.077017350527269e-05,
+      "loss": 0.1138,
+      "step": 1740
+    },
+    {
+      "epoch": 2.093947606142728,
+      "eval_loss": 0.1225883737206459,
+      "eval_runtime": 81.4669,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 2.148,
+      "step": 1740
+    },
+    {
+      "epoch": 2.1059921710328213,
+      "grad_norm": 0.06803560256958008,
+      "learning_rate": 4.9555904449868795e-05,
+      "loss": 0.1196,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1180367359229146,
+      "grad_norm": 0.08914126455783844,
+      "learning_rate": 4.835153104701221e-05,
+      "loss": 0.1129,
+      "step": 1760
+    },
+    {
+      "epoch": 2.130081300813008,
+      "grad_norm": 0.08918345719575882,
+      "learning_rate": 4.71572895594528e-05,
+      "loss": 0.1183,
+      "step": 1770
+    },
+    {
+      "epoch": 2.130081300813008,
+      "eval_loss": 0.12287717312574387,
+      "eval_runtime": 81.4917,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.147,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1421258657031013,
+      "grad_norm": 0.07838484644889832,
+      "learning_rate": 4.5973414262355785e-05,
+      "loss": 0.1141,
+      "step": 1780
+    },
+    {
+      "epoch": 2.154170430593195,
+      "grad_norm": 0.11005687713623047,
+      "learning_rate": 4.480013739734368e-05,
+      "loss": 0.1223,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1662149954832883,
+      "grad_norm": 0.08749410510063171,
+      "learning_rate": 4.363768912693749e-05,
+      "loss": 0.1117,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1662149954832883,
+      "eval_loss": 0.12259072810411453,
+      "eval_runtime": 81.4558,
+      "eval_samples_per_second": 4.297,
+      "eval_steps_per_second": 2.148,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1782595603733816,
+      "grad_norm": 0.08549398928880692,
+      "learning_rate": 4.24862974894053e-05,
+      "loss": 0.1088,
+      "step": 1810
+    },
+    {
+      "epoch": 2.190304125263475,
+      "grad_norm": 0.05755528435111046,
+      "learning_rate": 4.134618835402816e-05,
+      "loss": 0.1063,
+      "step": 1820
+    },
+    {
+      "epoch": 2.2023486901535683,
+      "grad_norm": 0.07486403733491898,
+      "learning_rate": 4.0217585376790834e-05,
+      "loss": 0.1183,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2023486901535683,
+      "eval_loss": 0.12217788398265839,
+      "eval_runtime": 81.8011,
+      "eval_samples_per_second": 4.279,
+      "eval_steps_per_second": 2.139,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2143932550436616,
+      "grad_norm": 0.08609265834093094,
+      "learning_rate": 3.9100709956507356e-05,
+      "loss": 0.1254,
+      "step": 1840
+    },
+    {
+      "epoch": 2.226437819933755,
+      "grad_norm": 0.0692862719297409,
+      "learning_rate": 3.79957811913888e-05,
+      "loss": 0.1121,
+      "step": 1850
+    },
+    {
+      "epoch": 2.238482384823848,
+      "grad_norm": 0.08547110855579376,
+      "learning_rate": 3.6903015836062905e-05,
+      "loss": 0.1097,
+      "step": 1860
+    },
+    {
+      "epoch": 2.238482384823848,
+      "eval_loss": 0.12183844298124313,
+      "eval_runtime": 81.5286,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.146,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2505269497139415,
+      "grad_norm": 0.08573822677135468,
+      "learning_rate": 3.5822628259052906e-05,
+      "loss": 0.1174,
+      "step": 1870
+    },
+    {
+      "epoch": 2.262571514604035,
+      "grad_norm": 0.08069294691085815,
+      "learning_rate": 3.475483040072495e-05,
+      "loss": 0.1198,
+      "step": 1880
+    },
+    {
+      "epoch": 2.274616079494128,
+      "grad_norm": 0.08202630281448364,
+      "learning_rate": 3.369983173171141e-05,
+      "loss": 0.1132,
+      "step": 1890
+    },
+    {
+      "epoch": 2.274616079494128,
+      "eval_loss": 0.12189455330371857,
+      "eval_runtime": 81.6511,
+      "eval_samples_per_second": 4.287,
+      "eval_steps_per_second": 2.143,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2866606443842215,
+      "grad_norm": 0.08111971616744995,
+      "learning_rate": 3.2657839211819085e-05,
+      "loss": 0.1086,
+      "step": 1900
+    },
+    {
+      "epoch": 2.298705209274315,
+      "grad_norm": 0.07577092200517654,
+      "learning_rate": 3.1629057249429527e-05,
+      "loss": 0.1205,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3107497741644085,
+      "grad_norm": 0.0689835473895073,
+      "learning_rate": 3.0613687661400384e-05,
+      "loss": 0.1133,
+      "step": 1920
+    },
+    {
+      "epoch": 2.3107497741644085,
+      "eval_loss": 0.12182266265153885,
+      "eval_runtime": 81.5792,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 1920
+    },
+    {
+      "epoch": 2.322794339054502,
+      "grad_norm": 0.09697998315095901,
+      "learning_rate": 2.9611929633474555e-05,
+      "loss": 0.1214,
+      "step": 1930
+    },
+    {
+      "epoch": 2.334838903944595,
+      "grad_norm": 0.07920137792825699,
+      "learning_rate": 2.8623979681206002e-05,
+      "loss": 0.1108,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3468834688346885,
+      "grad_norm": 0.07563956826925278,
+      "learning_rate": 2.765003161140911e-05,
+      "loss": 0.1213,
+      "step": 1950
+    },
+    {
+      "epoch": 2.3468834688346885,
+      "eval_loss": 0.12195436656475067,
+      "eval_runtime": 81.5329,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.146,
+      "step": 1950
+    },
+    {
+      "epoch": 2.3589280337247818,
+      "grad_norm": 0.08294857293367386,
+      "learning_rate": 2.66902764841394e-05,
+      "loss": 0.1186,
+      "step": 1960
+    },
+    {
+      "epoch": 2.370972598614875,
+      "grad_norm": 0.0806855708360672,
+      "learning_rate": 2.5744902575213248e-05,
+      "loss": 0.1127,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3830171635049684,
+      "grad_norm": 0.1039934828877449,
+      "learning_rate": 2.481409533927358e-05,
+      "loss": 0.1188,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3830171635049684,
+      "eval_loss": 0.12177734076976776,
+      "eval_runtime": 81.5272,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.147,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3950617283950617,
+      "grad_norm": 0.09341799467802048,
+      "learning_rate": 2.3898037373409276e-05,
+      "loss": 0.1173,
+      "step": 1990
+    },
+    {
+      "epoch": 2.407106293285155,
+      "grad_norm": 0.08933733403682709,
+      "learning_rate": 2.2996908381334736e-05,
+      "loss": 0.1148,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4191508581752483,
+      "grad_norm": 0.08493391424417496,
+      "learning_rate": 2.211088513813754e-05,
+      "loss": 0.1121,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4191508581752483,
+      "eval_loss": 0.12171091139316559,
+      "eval_runtime": 81.5846,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4311954230653416,
+      "grad_norm": 0.1086319163441658,
+      "learning_rate": 2.1240141455600116e-05,
+      "loss": 0.1145,
+      "step": 2020
+    },
+    {
+      "epoch": 2.443239987955435,
+      "grad_norm": 0.09176024794578552,
+      "learning_rate": 2.0384848148103196e-05,
+      "loss": 0.1092,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4552845528455283,
+      "grad_norm": 0.1033325344324112,
+      "learning_rate": 1.9545172999116812e-05,
+      "loss": 0.1055,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4552845528455283,
+      "eval_loss": 0.12144716829061508,
+      "eval_runtime": 81.758,
+      "eval_samples_per_second": 4.281,
+      "eval_steps_per_second": 2.14,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4673291177356216,
+      "grad_norm": 0.07238776981830597,
+      "learning_rate": 1.872128072828634e-05,
+      "loss": 0.1105,
+      "step": 2050
+    },
+    {
+      "epoch": 2.4793736826257153,
+      "grad_norm": 0.06941673159599304,
+      "learning_rate": 1.791333295911909e-05,
+      "loss": 0.1118,
+      "step": 2060
+    },
+    {
+      "epoch": 2.4914182475158086,
+      "grad_norm": 0.08462639153003693,
+      "learning_rate": 1.7121488187278713e-05,
+      "loss": 0.1082,
+      "step": 2070
+    },
+    {
+      "epoch": 2.4914182475158086,
+      "eval_loss": 0.12135373055934906,
+      "eval_runtime": 81.6101,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.144,
+      "step": 2070
+    },
+    {
+      "epoch": 2.503462812405902,
+      "grad_norm": 0.09350676834583282,
+      "learning_rate": 1.6345901749492887e-05,
+      "loss": 0.1121,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5155073772959953,
+      "grad_norm": 0.08438068628311157,
+      "learning_rate": 1.5586725793080814e-05,
+      "loss": 0.1146,
+      "step": 2090
+    },
+    {
+      "epoch": 2.5275519421860886,
+      "grad_norm": 0.10219820588827133,
+      "learning_rate": 1.484410924610642e-05,
+      "loss": 0.1179,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5275519421860886,
+      "eval_loss": 0.12126310169696808,
+      "eval_runtime": 81.4438,
+      "eval_samples_per_second": 4.297,
+      "eval_steps_per_second": 2.149,
+      "step": 2100
+    },
+    {
+      "epoch": 2.539596507076182,
+      "grad_norm": 0.0966809093952179,
+      "learning_rate": 1.4118197788163056e-05,
+      "loss": 0.1186,
+      "step": 2110
+    },
+    {
+      "epoch": 2.551641071966275,
+      "grad_norm": 0.1106065958738327,
+      "learning_rate": 1.3409133821795306e-05,
+      "loss": 0.1112,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5636856368563685,
+      "grad_norm": 0.09320900589227676,
+      "learning_rate": 1.2717056444563957e-05,
+      "loss": 0.1148,
+      "step": 2130
+    },
+    {
+      "epoch": 2.5636856368563685,
+      "eval_loss": 0.12110390514135361,
+      "eval_runtime": 81.8244,
+      "eval_samples_per_second": 4.277,
+      "eval_steps_per_second": 2.139,
+      "step": 2130
+    },
+    {
+      "epoch": 2.575730201746462,
+      "grad_norm": 0.09060157835483551,
+      "learning_rate": 1.2042101421758955e-05,
+      "loss": 0.1219,
+      "step": 2140
+    },
+    {
+      "epoch": 2.587774766636555,
+      "grad_norm": 0.09531334787607193,
+      "learning_rate": 1.1384401159766433e-05,
+      "loss": 0.1136,
+      "step": 2150
+    },
+    {
+      "epoch": 2.5998193315266485,
+      "grad_norm": 0.07259315997362137,
+      "learning_rate": 1.0744084680094246e-05,
+      "loss": 0.1062,
+      "step": 2160
+    },
+    {
+      "epoch": 2.5998193315266485,
+      "eval_loss": 0.12105338275432587,
+      "eval_runtime": 81.5762,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 2160
+    },
+    {
+      "epoch": 2.611863896416742,
+      "grad_norm": 0.07185359299182892,
+      "learning_rate": 1.0121277594061939e-05,
+      "loss": 0.1184,
+      "step": 2170
+    },
+    {
+      "epoch": 2.6239084613068355,
+      "grad_norm": 0.0885002538561821,
+      "learning_rate": 9.516102078159317e-06,
+      "loss": 0.1243,
+      "step": 2180
+    },
+    {
+      "epoch": 2.635953026196929,
+      "grad_norm": 0.10129860043525696,
+      "learning_rate": 8.928676850079133e-06,
+      "loss": 0.1249,
+      "step": 2190
+    },
+    {
+      "epoch": 2.635953026196929,
+      "eval_loss": 0.1209418997168541,
+      "eval_runtime": 81.4691,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 2.148,
+      "step": 2190
+    },
+    {
+      "epoch": 2.647997591087022,
+      "grad_norm": 0.08937793970108032,
+      "learning_rate": 8.359117145428053e-06,
+      "loss": 0.1188,
+      "step": 2200
+    },
+    {
+      "epoch": 2.6600421559771155,
+      "grad_norm": 0.08618754148483276,
+      "learning_rate": 7.807534695120911e-06,
+      "loss": 0.1193,
+      "step": 2210
+    },
+    {
+      "epoch": 2.6720867208672088,
+      "grad_norm": 0.0760350152850151,
+      "learning_rate": 7.274037703462244e-06,
+      "loss": 0.107,
+      "step": 2220
+    },
+    {
+      "epoch": 2.6720867208672088,
+      "eval_loss": 0.12113867700099945,
+      "eval_runtime": 81.609,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.144,
+      "step": 2220
+    },
+    {
+      "epoch": 2.684131285757302,
+      "grad_norm": 0.08701752126216888,
+      "learning_rate": 6.7587308269199786e-06,
+      "loss": 0.1042,
+      "step": 2230
+    },
+    {
+      "epoch": 2.6961758506473954,
+      "grad_norm": 0.08244354277849197,
+      "learning_rate": 6.261715153594627e-06,
+      "loss": 0.1156,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7082204155374887,
+      "grad_norm": 0.14877063035964966,
+      "learning_rate": 5.783088183389062e-06,
+      "loss": 0.1076,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7082204155374887,
+      "eval_loss": 0.12096786499023438,
+      "eval_runtime": 81.6046,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.144,
+      "step": 2250
+    },
+    {
+      "epoch": 2.720264980427582,
+      "grad_norm": 0.09160082787275314,
+      "learning_rate": 5.322943808881675e-06,
+      "loss": 0.1188,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7323095453176753,
+      "grad_norm": 0.08697830885648727,
+      "learning_rate": 4.881372296907516e-06,
+      "loss": 0.1082,
+      "step": 2270
+    },
+    {
+      "epoch": 2.7443541102077686,
+      "grad_norm": 0.09075489640235901,
+      "learning_rate": 4.4584602708505285e-06,
+      "loss": 0.118,
+      "step": 2280
+    },
+    {
+      "epoch": 2.7443541102077686,
+      "eval_loss": 0.12092573195695877,
+      "eval_runtime": 81.6503,
+      "eval_samples_per_second": 4.287,
+      "eval_steps_per_second": 2.143,
+      "step": 2280
+    },
+    {
+      "epoch": 2.756398675097862,
+      "grad_norm": 0.0934319868683815,
+      "learning_rate": 4.054290693650642e-06,
+      "loss": 0.1091,
+      "step": 2290
+    },
+    {
+      "epoch": 2.7684432399879553,
+      "grad_norm": 0.08008915930986404,
+      "learning_rate": 3.6689428515288004e-06,
+      "loss": 0.1103,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7804878048780486,
+      "grad_norm": 0.07896912097930908,
+      "learning_rate": 3.3024923384334163e-06,
+      "loss": 0.1087,
+      "step": 2310
+    },
+    {
+      "epoch": 2.7804878048780486,
+      "eval_loss": 0.12093985080718994,
+      "eval_runtime": 81.4605,
+      "eval_samples_per_second": 4.297,
+      "eval_steps_per_second": 2.148,
+      "step": 2310
+    },
+    {
+      "epoch": 2.792532369768142,
+      "grad_norm": 0.08136588335037231,
+      "learning_rate": 2.9550110412109534e-06,
+      "loss": 0.1106,
+      "step": 2320
+    },
+    {
+      "epoch": 2.804576934658235,
+      "grad_norm": 0.07197284698486328,
+      "learning_rate": 2.6265671255039537e-06,
+      "loss": 0.1265,
+      "step": 2330
+    },
+    {
+      "epoch": 2.816621499548329,
+      "grad_norm": 0.09639979153871536,
+      "learning_rate": 2.3172250223787994e-06,
+      "loss": 0.1168,
+      "step": 2340
+    },
+    {
+      "epoch": 2.816621499548329,
+      "eval_loss": 0.12088128179311752,
+      "eval_runtime": 81.8851,
+      "eval_samples_per_second": 4.274,
+      "eval_steps_per_second": 2.137,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8286660644384223,
+      "grad_norm": 0.09752853214740753,
+      "learning_rate": 2.0270454156863905e-06,
+      "loss": 0.1209,
+      "step": 2350
+    },
+    {
+      "epoch": 2.8407106293285156,
+      "grad_norm": 0.08983393758535385,
+      "learning_rate": 1.7560852301575892e-06,
+      "loss": 0.1185,
+      "step": 2360
+    },
+    {
+      "epoch": 2.852755194218609,
+      "grad_norm": 0.09476975351572037,
+      "learning_rate": 1.5043976202363641e-06,
+      "loss": 0.1172,
+      "step": 2370
+    },
+    {
+      "epoch": 2.852755194218609,
+      "eval_loss": 0.1208338588476181,
+      "eval_runtime": 81.5048,
+      "eval_samples_per_second": 4.294,
+      "eval_steps_per_second": 2.147,
+      "step": 2370
+    },
+    {
+      "epoch": 2.864799759108702,
+      "grad_norm": 0.06642317026853561,
+      "learning_rate": 1.2720319596523977e-06,
+      "loss": 0.116,
+      "step": 2380
+    },
+    {
+      "epoch": 2.8768443239987955,
+      "grad_norm": 0.10626640915870667,
+      "learning_rate": 1.0590338317354454e-06,
+      "loss": 0.112,
+      "step": 2390
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.07917091995477676,
+      "learning_rate": 8.654450204731768e-07,
+      "loss": 0.1092,
+      "step": 2400
+    },
+    {
+      "epoch": 2.888888888888889,
+      "eval_loss": 0.12085919827222824,
+      "eval_runtime": 81.5821,
+      "eval_samples_per_second": 4.29,
+      "eval_steps_per_second": 2.145,
+      "step": 2400
+    },
+    {
+      "epoch": 2.900933453778982,
+      "grad_norm": 0.09295058250427246,
+      "learning_rate": 6.913035023144443e-07,
+      "loss": 0.1137,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9129780186690755,
+      "grad_norm": 0.10089948773384094,
+      "learning_rate": 5.366434387193198e-07,
+      "loss": 0.1176,
+      "step": 2420
+    },
+    {
+      "epoch": 2.9250225835591688,
+      "grad_norm": 0.10267487913370132,
+      "learning_rate": 4.014951694577329e-07,
+      "loss": 0.1111,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9250225835591688,
+      "eval_loss": 0.12082531303167343,
+      "eval_runtime": 81.5548,
+      "eval_samples_per_second": 4.292,
+      "eval_steps_per_second": 2.146,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9370671484492625,
+      "grad_norm": 0.08494390547275543,
+      "learning_rate": 2.858852066576212e-07,
+      "loss": 0.1002,
+      "step": 2440
+    },
+    {
+      "epoch": 2.949111713339356,
+      "grad_norm": 0.10927818715572357,
+      "learning_rate": 1.8983622960404568e-07,
+      "loss": 0.1239,
+      "step": 2450
+    },
+    {
+      "epoch": 2.961156278229449,
+      "grad_norm": 0.11693628132343292,
+      "learning_rate": 1.1336708029019427e-07,
+      "loss": 0.1212,
+      "step": 2460
+    },
+    {
+      "epoch": 2.961156278229449,
+      "eval_loss": 0.1208575889468193,
+      "eval_runtime": 81.4992,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.147,
+      "step": 2460
+    },
+    {
+      "epoch": 2.9732008431195425,
+      "grad_norm": 0.07127541303634644,
+      "learning_rate": 5.6492759721116227e-08,
+      "loss": 0.1111,
+      "step": 2470
+    },
+    {
+      "epoch": 2.985245408009636,
+      "grad_norm": 0.12955011427402496,
+      "learning_rate": 1.9224424970964995e-08,
+      "loss": 0.1084,
+      "step": 2480
+    },
+    {
+      "epoch": 2.997289972899729,
+      "grad_norm": 0.061590053141117096,
+      "learning_rate": 1.5693869943489425e-09,
+      "loss": 0.1087,
+      "step": 2490
+    },
+    {
+      "epoch": 2.997289972899729,
+      "eval_loss": 0.12081737071275711,
+      "eval_runtime": 81.6055,
+      "eval_samples_per_second": 4.289,
+      "eval_steps_per_second": 2.144,
+      "step": 2490
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2493,
+  "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": 4.527283427342715e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2493/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cb9e0c5da29bc408e28b78229d144492041698a4b4939d9177cfe475720f63
+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 sha256:25b7ae99a559b5ee0a027c492d4ba35bf922fe872bd3886f76c1879f79c08c98
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de91bd8f3577780d81af124f2b9c5f6d97484e808267430d3dd77536d131d371
+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": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}