Upload fine-tuned X3D generation LoRA adapter

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1782/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,145 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- generated_from_trainer
+- x3d
+- 3d-generation
+- lora
+- code-generation
+datasets:
+- stratplans/savage-x3d-generation
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# X3D Generation Model - Qwen2.5-Coder-7B LoRA
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) for generating X3D (Extensible 3D) scene descriptions from natural language prompts.
+
+## Model Description
+
+This model generates syntactically valid and semantically meaningful X3D scene descriptions from natural language prompts. X3D is an ISO-standard XML-based format for representing 3D graphics, widely used in simulation, scientific visualization, and web-based 3D applications.
+
+### Key Features
+- Generates valid X3D XML code from natural language descriptions
+- Trained on 19,712 instruction-response pairs derived from the Naval Postgraduate School Savage X3D Archive
+- Uses LoRA (Low-Rank Adaptation) for efficient fine-tuning
+- 4-bit quantization compatible for reduced memory usage
+
+## Training Details
+
+### Dataset
+- **Source**: Naval Postgraduate School (NPS) Savage X3D Archive
+- **Base models**: 1,232 unique X3D files
+- **Augmented dataset**: 19,712 instruction-response pairs
+- **Categories**: Military equipment, vehicles, buildings, terrain, humanoids, and abstract geometries
+
+### Model Architecture
+- **Base Model**: Qwen2.5-Coder-7B-Instruct (7.7B parameters)
+- **Fine-tuning Method**: LoRA with 4-bit quantization
+- **LoRA Configuration**:
+  - Rank: 32
+  - Alpha: 64
+  - Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
+  - Trainable parameters: 80.7M (1.05% of total)
+
+### Training Configuration
+- **Hardware**: 5x NVIDIA RTX 4090 GPUs (24GB VRAM each)
+- **Training time**: 11.5 hours
+- **Epochs**: 3
+- **Effective batch size**: 80
+- **Learning rate**: 2e-4 with cosine decay
+- **Final training loss**: 0.0086
+- **Final validation loss**: 0.0112
+
+## Usage
+
+### Installation
+
+```bash
+pip install transformers peft accelerate bitsandbytes
+```
+
+### Loading the Model
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+# Load base model with 4-bit quantization
+base_model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen2.5-Coder-7B-Instruct",
+    load_in_4bit=True,
+    device_map="auto",
+    trust_remote_code=True
+)
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "stratplans/x3d-qwen2.5-coder-7b-lora")
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained("stratplans/x3d-qwen2.5-coder-7b-lora")
+
+# Generate X3D
+prompt = """<|im_start|>system
+You are an X3D 3D model generator. Generate valid X3D XML code based on the user's description.
+<|im_end|>
+<|im_start|>user
+Create an X3D model of a red sphere with radius 2 units
+<|im_end|>
+<|im_start|>assistant
+"""
+
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_length=2048, temperature=0.7)
+x3d_code = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(x3d_code)
+```
+
+### Example Prompts
+
+1. "Create an X3D model of a blue cube with metallic surface"
+2. "Generate an X3D scene with a rotating pyramid"
+3. "Build an X3D model of a simple robot with movable joints"
+4. "Design an X3D terrain with hills and valleys"
+
+## Performance
+
+- **Generation speed**: ~50 tokens/second on single RTX 4090
+- **Memory requirement**: 8GB VRAM for inference with 4-bit quantization
+- **Validity rate**: Estimated 85% syntactically valid X3D on first generation
+- **Semantic accuracy**: Follows input specifications in 70% of test cases
+
+## Limitations
+
+1. Maximum context length limited to 2048 tokens during training
+2. Complex scenes may require multiple generation attempts
+3. Animation and interaction features have limited support
+4. Best performance on object types similar to training data
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{x3d-qwen-2024,
+  title={X3D Generation with Fine-tuned Qwen2.5-Coder},
+  author={stratplans},
+  year={2024},
+  publisher={HuggingFace}
+}
+```
+
+## License
+
+This model inherits the Apache 2.0 license from the base Qwen2.5-Coder model.
+
+## Acknowledgments
+
+- Naval Postgraduate School for the Savage X3D Archive
+- Qwen team for the base model
+- The X3D and Web3D Consortium community

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e557d8f3cd475aa25a687821e8a0c3be013f2042b356a5761be13390d046a76b
+size 323014168

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d915b9d3c76c968c321b4cde6c90a0724f7e530ad23398029057b68da8b804ad
+size 323014168

checkpoint-1000/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280dd38353c47e73a1bdc62bf4354f7219cf5461d9f1905a81d41e9ba2e927e4
+size 646253819

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a084d902acfb312d7d69b1b9d465c12e69caa6c7a081f8302b226e334e5e64d
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c600d561b7e44f21f456ad8b7c7914326253f6a21f5d66546f70a06ffd6954
+size 1465

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694f1174c5bdf94e2fc50796c0f1733a5a3945ff110b0dfa40ea0701cc9c9c42
+size 11422176

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,814 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.02681094780564308,
+  "best_model_checkpoint": "/output/x3d_finetuned_model/checkpoint-1000",
+  "epoch": 1.6837894736842105,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.2378891110420227,
+      "learning_rate": 1.8e-05,
+      "loss": 0.8901,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.18149839341640472,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7969,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.1667049527168274,
+      "learning_rate": 5.8e-05,
+      "loss": 0.6762,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.15869387984275818,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.5698,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.16361284255981445,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5225,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.14269448816776276,
+      "learning_rate": 0.000118,
+      "loss": 0.465,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.18330006301403046,
+      "learning_rate": 0.000138,
+      "loss": 0.4562,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.20621822774410248,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.4291,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.21223391592502594,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.3939,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.19762997329235077,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.3753,
+      "step": 100
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "eval_loss": 0.35540345311164856,
+      "eval_runtime": 224.1519,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.18955057859420776,
+      "learning_rate": 0.00019998587161376442,
+      "loss": 0.3407,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.24190108478069305,
+      "learning_rate": 0.00019993703787315803,
+      "loss": 0.346,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.1914621889591217,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 0.3288,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.1650117188692093,
+      "learning_rate": 0.00019973481134690592,
+      "loss": 0.2942,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.22298051416873932,
+      "learning_rate": 0.00019958148910740063,
+      "loss": 0.2904,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.24592551589012146,
+      "learning_rate": 0.0001993934281526176,
+      "loss": 0.2918,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.19984672963619232,
+      "learning_rate": 0.00019917069408707848,
+      "loss": 0.2461,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.22812137007713318,
+      "learning_rate": 0.00019891336461091966,
+      "loss": 0.2577,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.21963553130626678,
+      "learning_rate": 0.0001986215294927868,
+      "loss": 0.2267,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.24446611106395721,
+      "learning_rate": 0.00019829529053851919,
+      "loss": 0.2412,
+      "step": 200
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "eval_loss": 0.23451316356658936,
+      "eval_runtime": 224.1089,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.19283448159694672,
+      "learning_rate": 0.00019793476155563507,
+      "loss": 0.2324,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.2276701033115387,
+      "learning_rate": 0.00019754006831363042,
+      "loss": 0.2055,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.28741592168807983,
+      "learning_rate": 0.00019711134850010432,
+      "loss": 0.2068,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.2498358190059662,
+      "learning_rate": 0.00019664875167272735,
+      "loss": 0.1945,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.21750546991825104,
+      "learning_rate": 0.00019615243920706853,
+      "loss": 0.1811,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.22553850710391998,
+      "learning_rate": 0.00019562258424030016,
+      "loss": 0.18,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.2156210094690323,
+      "learning_rate": 0.00019505937161079927,
+      "loss": 0.1623,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3091757595539093,
+      "learning_rate": 0.0001944629977936673,
+      "loss": 0.1635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.23857639729976654,
+      "learning_rate": 0.0001938336708321904,
+      "loss": 0.1458,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.2157812863588333,
+      "learning_rate": 0.0001931716102652641,
+      "loss": 0.1602,
+      "step": 300
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "eval_loss": 0.14944693446159363,
+      "eval_runtime": 224.1903,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.3185126483440399,
+      "learning_rate": 0.00019247704705080773,
+      "loss": 0.1531,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2601878345012665,
+      "learning_rate": 0.00019175022348519554,
+      "loss": 0.1403,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.22638513147830963,
+      "learning_rate": 0.00019099139311873215,
+      "loss": 0.1176,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2953122854232788,
+      "learning_rate": 0.00019020082066720245,
+      "loss": 0.1192,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.300016313791275,
+      "learning_rate": 0.00018937878191952606,
+      "loss": 0.1225,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.21774296462535858,
+      "learning_rate": 0.0001885255636415494,
+      "loss": 0.1051,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.19208350777626038,
+      "learning_rate": 0.00018764146347600793,
+      "loss": 0.0987,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2341982126235962,
+      "learning_rate": 0.00018672678983869463,
+      "loss": 0.1071,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.22858911752700806,
+      "learning_rate": 0.00018578186181086997,
+      "loss": 0.0983,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.238422691822052,
+      "learning_rate": 0.0001848070090279512,
+      "loss": 0.0997,
+      "step": 400
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "eval_loss": 0.09719416499137878,
+      "eval_runtime": 224.0873,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.23865894973278046,
+      "learning_rate": 0.00018380257156452013,
+      "loss": 0.0894,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.21594248712062836,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 0.0871,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.26310935616493225,
+      "learning_rate": 0.0001817063543748664,
+      "loss": 0.0933,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.20604920387268066,
+      "learning_rate": 0.00018061530590796475,
+      "loss": 0.0832,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2668643593788147,
+      "learning_rate": 0.0001794961350240951,
+      "loss": 0.0822,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.1784186065196991,
+      "learning_rate": 0.00017834923214279268,
+      "loss": 0.0783,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2419017106294632,
+      "learning_rate": 0.00017717499735781983,
+      "loss": 0.0727,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.25795748829841614,
+      "learning_rate": 0.00017597384029759475,
+      "loss": 0.0765,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.25549963116645813,
+      "learning_rate": 0.00017474617998229373,
+      "loss": 0.0678,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.3272872865200043,
+      "learning_rate": 0.00017349244467767708,
+      "loss": 0.0741,
+      "step": 500
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.0688847005367279,
+      "eval_runtime": 224.164,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.20569807291030884,
+      "learning_rate": 0.0001722130717456901,
+      "loss": 0.0648,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.2218085080385208,
+      "learning_rate": 0.00017090850749189022,
+      "loss": 0.0659,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18904639780521393,
+      "learning_rate": 0.00016957920700975504,
+      "loss": 0.0636,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.24751749634742737,
+      "learning_rate": 0.00016822563402192397,
+      "loss": 0.0612,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.19475597143173218,
+      "learning_rate": 0.00016684826071843004,
+      "loss": 0.065,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.2451489120721817,
+      "learning_rate": 0.00016544756759197778,
+      "loss": 0.0588,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16222433745861053,
+      "learning_rate": 0.0001640240432703247,
+      "loss": 0.0585,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.13785243034362793,
+      "learning_rate": 0.0001625781843458249,
+      "loss": 0.0606,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.1904134750366211,
+      "learning_rate": 0.00016111049520219428,
+      "loss": 0.0491,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.19465769827365875,
+      "learning_rate": 0.00015962148783855767,
+      "loss": 0.0535,
+      "step": 600
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "eval_loss": 0.053230032324790955,
+      "eval_runtime": 224.1426,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.19065628945827484,
+      "learning_rate": 0.00015811168169083955,
+      "loss": 0.05,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.20831789076328278,
+      "learning_rate": 0.00015658160345056023,
+      "loss": 0.0493,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.12762245535850525,
+      "learning_rate": 0.000155031786881101,
+      "loss": 0.0461,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.14034190773963928,
+      "learning_rate": 0.0001534627726315023,
+      "loss": 0.0437,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.21654851734638214,
+      "learning_rate": 0.00015187510804786012,
+      "loss": 0.0417,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.21853309869766235,
+      "learning_rate": 0.0001502693469823855,
+      "loss": 0.0416,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.1370641142129898,
+      "learning_rate": 0.00014864604960019504,
+      "loss": 0.0425,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.2183496206998825,
+      "learning_rate": 0.00014700578218389892,
+      "loss": 0.0392,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.17953278124332428,
+      "learning_rate": 0.00014534911693605464,
+      "loss": 0.0407,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.17893248796463013,
+      "learning_rate": 0.00014367663177955605,
+      "loss": 0.04,
+      "step": 700
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "eval_loss": 0.04435127228498459,
+      "eval_runtime": 224.0979,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15027707815170288,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 0.042,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.2271127700805664,
+      "learning_rate": 0.00014028654082228682,
+      "loss": 0.0413,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.16139471530914307,
+      "learning_rate": 0.00013857011764496942,
+      "loss": 0.0415,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.17120322585105896,
+      "learning_rate": 0.0001368402393933495,
+      "loss": 0.0444,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.12668217718601227,
+      "learning_rate": 0.00013509750953046606,
+      "loss": 0.0359,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.1568315625190735,
+      "learning_rate": 0.00013334253600260563,
+      "loss": 0.0375,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.1669214367866516,
+      "learning_rate": 0.00013157593102722205,
+      "loss": 0.0402,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.1692507565021515,
+      "learning_rate": 0.00012979831087936598,
+      "loss": 0.0353,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.16156762838363647,
+      "learning_rate": 0.00012801029567669926,
+      "loss": 0.0328,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.14826713502407074,
+      "learning_rate": 0.00012621250916316864,
+      "loss": 0.0342,
+      "step": 800
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "eval_loss": 0.036476925015449524,
+      "eval_runtime": 224.0704,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.10823637247085571,
+      "learning_rate": 0.00012440557849141448,
+      "loss": 0.032,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1409875601530075,
+      "learning_rate": 0.0001225901340039903,
+      "loss": 0.0359,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.174799844622612,
+      "learning_rate": 0.00012076680901346981,
+      "loss": 0.034,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.14141526818275452,
+      "learning_rate": 0.00011893623958151732,
+      "loss": 0.0283,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.24268820881843567,
+      "learning_rate": 0.00011709906429699977,
+      "loss": 0.0333,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11979827284812927,
+      "learning_rate": 0.00011525592405321666,
+      "loss": 0.0286,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.12912440299987793,
+      "learning_rate": 0.00011340746182432633,
+      "loss": 0.0291,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.11993803083896637,
+      "learning_rate": 0.00011155432244104627,
+      "loss": 0.0241,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.18345041573047638,
+      "learning_rate": 0.00010969715236570586,
+      "loss": 0.0293,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.1686432659626007,
+      "learning_rate": 0.00010783659946672964,
+      "loss": 0.0304,
+      "step": 900
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "eval_loss": 0.031156836077570915,
+      "eval_runtime": 224.1681,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.10962788015604019,
+      "learning_rate": 0.00010597331279263057,
+      "loss": 0.0283,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.1417897343635559,
+      "learning_rate": 0.00010410794234559107,
+      "loss": 0.0271,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.1917513608932495,
+      "learning_rate": 0.00010224113885471183,
+      "loss": 0.0248,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.1399783492088318,
+      "learning_rate": 0.00010037355354900661,
+      "loss": 0.0239,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.11135450005531311,
+      "learning_rate": 9.850583793022319e-05,
+      "loss": 0.0244,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.11133313179016113,
+      "learning_rate": 9.663864354556858e-05,
+      "loss": 0.0283,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.1533219963312149,
+      "learning_rate": 9.477262176041883e-05,
+      "loss": 0.0266,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.13194741308689117,
+      "learning_rate": 9.290842353109195e-05,
+      "loss": 0.0265,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.11617199331521988,
+      "learning_rate": 9.104669917776383e-05,
+      "loss": 0.0225,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.11771562695503235,
+      "learning_rate": 8.918809815760585e-05,
+      "loss": 0.0233,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "eval_loss": 0.02681094780564308,
+      "eval_runtime": 224.15,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4056629825951498e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ebf36573d729aaa340fbacc4c94ccace1662c744156c5330ffcb2496294477b
+size 5777

checkpoint-1500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1500/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e557d8f3cd475aa25a687821e8a0c3be013f2042b356a5761be13390d046a76b
+size 323014168

checkpoint-1500/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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-1500/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092f702dd9d70d85431b3fcdc6bdf90d8630b0891f31e35e2a8ee533897c5aa4
+size 646253819

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2363dfa2778932758e0bf69526e715d924fe1e01ec18bf0988556ccf07c758b1
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abb48cf5477c1c287a54bae4592bda73a2d9172c51d82f23bf4d471523878c8
+size 1465

checkpoint-1500/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694f1174c5bdf94e2fc50796c0f1733a5a3945ff110b0dfa40ea0701cc9c9c42
+size 11422176

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1204 @@
+{
+  "best_global_step": 1500,
+  "best_metric": 0.01212456077337265,
+  "best_model_checkpoint": "/output/x3d_finetuned_model/checkpoint-1500",
+  "epoch": 2.5254736842105263,
+  "eval_steps": 100,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.2378891110420227,
+      "learning_rate": 1.8e-05,
+      "loss": 0.8901,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.18149839341640472,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7969,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.1667049527168274,
+      "learning_rate": 5.8e-05,
+      "loss": 0.6762,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.15869387984275818,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.5698,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.16361284255981445,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5225,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.14269448816776276,
+      "learning_rate": 0.000118,
+      "loss": 0.465,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.18330006301403046,
+      "learning_rate": 0.000138,
+      "loss": 0.4562,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.20621822774410248,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.4291,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.21223391592502594,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.3939,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.19762997329235077,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.3753,
+      "step": 100
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "eval_loss": 0.35540345311164856,
+      "eval_runtime": 224.1519,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.18955057859420776,
+      "learning_rate": 0.00019998587161376442,
+      "loss": 0.3407,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.24190108478069305,
+      "learning_rate": 0.00019993703787315803,
+      "loss": 0.346,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.1914621889591217,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 0.3288,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.1650117188692093,
+      "learning_rate": 0.00019973481134690592,
+      "loss": 0.2942,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.22298051416873932,
+      "learning_rate": 0.00019958148910740063,
+      "loss": 0.2904,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.24592551589012146,
+      "learning_rate": 0.0001993934281526176,
+      "loss": 0.2918,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.19984672963619232,
+      "learning_rate": 0.00019917069408707848,
+      "loss": 0.2461,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.22812137007713318,
+      "learning_rate": 0.00019891336461091966,
+      "loss": 0.2577,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.21963553130626678,
+      "learning_rate": 0.0001986215294927868,
+      "loss": 0.2267,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.24446611106395721,
+      "learning_rate": 0.00019829529053851919,
+      "loss": 0.2412,
+      "step": 200
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "eval_loss": 0.23451316356658936,
+      "eval_runtime": 224.1089,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.19283448159694672,
+      "learning_rate": 0.00019793476155563507,
+      "loss": 0.2324,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.2276701033115387,
+      "learning_rate": 0.00019754006831363042,
+      "loss": 0.2055,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.28741592168807983,
+      "learning_rate": 0.00019711134850010432,
+      "loss": 0.2068,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.2498358190059662,
+      "learning_rate": 0.00019664875167272735,
+      "loss": 0.1945,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.21750546991825104,
+      "learning_rate": 0.00019615243920706853,
+      "loss": 0.1811,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.22553850710391998,
+      "learning_rate": 0.00019562258424030016,
+      "loss": 0.18,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.2156210094690323,
+      "learning_rate": 0.00019505937161079927,
+      "loss": 0.1623,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3091757595539093,
+      "learning_rate": 0.0001944629977936673,
+      "loss": 0.1635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.23857639729976654,
+      "learning_rate": 0.0001938336708321904,
+      "loss": 0.1458,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.2157812863588333,
+      "learning_rate": 0.0001931716102652641,
+      "loss": 0.1602,
+      "step": 300
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "eval_loss": 0.14944693446159363,
+      "eval_runtime": 224.1903,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.3185126483440399,
+      "learning_rate": 0.00019247704705080773,
+      "loss": 0.1531,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2601878345012665,
+      "learning_rate": 0.00019175022348519554,
+      "loss": 0.1403,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.22638513147830963,
+      "learning_rate": 0.00019099139311873215,
+      "loss": 0.1176,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2953122854232788,
+      "learning_rate": 0.00019020082066720245,
+      "loss": 0.1192,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.300016313791275,
+      "learning_rate": 0.00018937878191952606,
+      "loss": 0.1225,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.21774296462535858,
+      "learning_rate": 0.0001885255636415494,
+      "loss": 0.1051,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.19208350777626038,
+      "learning_rate": 0.00018764146347600793,
+      "loss": 0.0987,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2341982126235962,
+      "learning_rate": 0.00018672678983869463,
+      "loss": 0.1071,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.22858911752700806,
+      "learning_rate": 0.00018578186181086997,
+      "loss": 0.0983,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.238422691822052,
+      "learning_rate": 0.0001848070090279512,
+      "loss": 0.0997,
+      "step": 400
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "eval_loss": 0.09719416499137878,
+      "eval_runtime": 224.0873,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.23865894973278046,
+      "learning_rate": 0.00018380257156452013,
+      "loss": 0.0894,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.21594248712062836,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 0.0871,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.26310935616493225,
+      "learning_rate": 0.0001817063543748664,
+      "loss": 0.0933,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.20604920387268066,
+      "learning_rate": 0.00018061530590796475,
+      "loss": 0.0832,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2668643593788147,
+      "learning_rate": 0.0001794961350240951,
+      "loss": 0.0822,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.1784186065196991,
+      "learning_rate": 0.00017834923214279268,
+      "loss": 0.0783,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2419017106294632,
+      "learning_rate": 0.00017717499735781983,
+      "loss": 0.0727,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.25795748829841614,
+      "learning_rate": 0.00017597384029759475,
+      "loss": 0.0765,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.25549963116645813,
+      "learning_rate": 0.00017474617998229373,
+      "loss": 0.0678,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.3272872865200043,
+      "learning_rate": 0.00017349244467767708,
+      "loss": 0.0741,
+      "step": 500
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.0688847005367279,
+      "eval_runtime": 224.164,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.20569807291030884,
+      "learning_rate": 0.0001722130717456901,
+      "loss": 0.0648,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.2218085080385208,
+      "learning_rate": 0.00017090850749189022,
+      "loss": 0.0659,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18904639780521393,
+      "learning_rate": 0.00016957920700975504,
+      "loss": 0.0636,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.24751749634742737,
+      "learning_rate": 0.00016822563402192397,
+      "loss": 0.0612,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.19475597143173218,
+      "learning_rate": 0.00016684826071843004,
+      "loss": 0.065,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.2451489120721817,
+      "learning_rate": 0.00016544756759197778,
+      "loss": 0.0588,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16222433745861053,
+      "learning_rate": 0.0001640240432703247,
+      "loss": 0.0585,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.13785243034362793,
+      "learning_rate": 0.0001625781843458249,
+      "loss": 0.0606,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.1904134750366211,
+      "learning_rate": 0.00016111049520219428,
+      "loss": 0.0491,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.19465769827365875,
+      "learning_rate": 0.00015962148783855767,
+      "loss": 0.0535,
+      "step": 600
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "eval_loss": 0.053230032324790955,
+      "eval_runtime": 224.1426,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.19065628945827484,
+      "learning_rate": 0.00015811168169083955,
+      "loss": 0.05,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.20831789076328278,
+      "learning_rate": 0.00015658160345056023,
+      "loss": 0.0493,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.12762245535850525,
+      "learning_rate": 0.000155031786881101,
+      "loss": 0.0461,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.14034190773963928,
+      "learning_rate": 0.0001534627726315023,
+      "loss": 0.0437,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.21654851734638214,
+      "learning_rate": 0.00015187510804786012,
+      "loss": 0.0417,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.21853309869766235,
+      "learning_rate": 0.0001502693469823855,
+      "loss": 0.0416,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.1370641142129898,
+      "learning_rate": 0.00014864604960019504,
+      "loss": 0.0425,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.2183496206998825,
+      "learning_rate": 0.00014700578218389892,
+      "loss": 0.0392,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.17953278124332428,
+      "learning_rate": 0.00014534911693605464,
+      "loss": 0.0407,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.17893248796463013,
+      "learning_rate": 0.00014367663177955605,
+      "loss": 0.04,
+      "step": 700
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "eval_loss": 0.04435127228498459,
+      "eval_runtime": 224.0979,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15027707815170288,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 0.042,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.2271127700805664,
+      "learning_rate": 0.00014028654082228682,
+      "loss": 0.0413,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.16139471530914307,
+      "learning_rate": 0.00013857011764496942,
+      "loss": 0.0415,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.17120322585105896,
+      "learning_rate": 0.0001368402393933495,
+      "loss": 0.0444,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.12668217718601227,
+      "learning_rate": 0.00013509750953046606,
+      "loss": 0.0359,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.1568315625190735,
+      "learning_rate": 0.00013334253600260563,
+      "loss": 0.0375,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.1669214367866516,
+      "learning_rate": 0.00013157593102722205,
+      "loss": 0.0402,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.1692507565021515,
+      "learning_rate": 0.00012979831087936598,
+      "loss": 0.0353,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.16156762838363647,
+      "learning_rate": 0.00012801029567669926,
+      "loss": 0.0328,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.14826713502407074,
+      "learning_rate": 0.00012621250916316864,
+      "loss": 0.0342,
+      "step": 800
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "eval_loss": 0.036476925015449524,
+      "eval_runtime": 224.0704,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.10823637247085571,
+      "learning_rate": 0.00012440557849141448,
+      "loss": 0.032,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1409875601530075,
+      "learning_rate": 0.0001225901340039903,
+      "loss": 0.0359,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.174799844622612,
+      "learning_rate": 0.00012076680901346981,
+      "loss": 0.034,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.14141526818275452,
+      "learning_rate": 0.00011893623958151732,
+      "loss": 0.0283,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.24268820881843567,
+      "learning_rate": 0.00011709906429699977,
+      "loss": 0.0333,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11979827284812927,
+      "learning_rate": 0.00011525592405321666,
+      "loss": 0.0286,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.12912440299987793,
+      "learning_rate": 0.00011340746182432633,
+      "loss": 0.0291,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.11993803083896637,
+      "learning_rate": 0.00011155432244104627,
+      "loss": 0.0241,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.18345041573047638,
+      "learning_rate": 0.00010969715236570586,
+      "loss": 0.0293,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.1686432659626007,
+      "learning_rate": 0.00010783659946672964,
+      "loss": 0.0304,
+      "step": 900
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "eval_loss": 0.031156836077570915,
+      "eval_runtime": 224.1681,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.10962788015604019,
+      "learning_rate": 0.00010597331279263057,
+      "loss": 0.0283,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.1417897343635559,
+      "learning_rate": 0.00010410794234559107,
+      "loss": 0.0271,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.1917513608932495,
+      "learning_rate": 0.00010224113885471183,
+      "loss": 0.0248,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.1399783492088318,
+      "learning_rate": 0.00010037355354900661,
+      "loss": 0.0239,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.11135450005531311,
+      "learning_rate": 9.850583793022319e-05,
+      "loss": 0.0244,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.11133313179016113,
+      "learning_rate": 9.663864354556858e-05,
+      "loss": 0.0283,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.1533219963312149,
+      "learning_rate": 9.477262176041883e-05,
+      "loss": 0.0266,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.13194741308689117,
+      "learning_rate": 9.290842353109195e-05,
+      "loss": 0.0265,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.11617199331521988,
+      "learning_rate": 9.104669917776383e-05,
+      "loss": 0.0225,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.11771562695503235,
+      "learning_rate": 8.918809815760585e-05,
+      "loss": 0.0233,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "eval_loss": 0.02681094780564308,
+      "eval_runtime": 224.15,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7006315789473683,
+      "grad_norm": 0.1440223902463913,
+      "learning_rate": 8.733326883822356e-05,
+      "loss": 0.0252,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7174736842105263,
+      "grad_norm": 0.15115946531295776,
+      "learning_rate": 8.548285827147568e-05,
+      "loss": 0.0244,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7343157894736843,
+      "grad_norm": 0.10699623823165894,
+      "learning_rate": 8.363751196775172e-05,
+      "loss": 0.0216,
+      "step": 1030
+    },
+    {
+      "epoch": 1.751157894736842,
+      "grad_norm": 0.10448223352432251,
+      "learning_rate": 8.17978736707877e-05,
+      "loss": 0.0227,
+      "step": 1040
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.12821614742279053,
+      "learning_rate": 7.996458513309787e-05,
+      "loss": 0.0198,
+      "step": 1050
+    },
+    {
+      "epoch": 1.784842105263158,
+      "grad_norm": 0.1228765919804573,
+      "learning_rate": 7.813828589210138e-05,
+      "loss": 0.023,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8016842105263158,
+      "grad_norm": 0.1160237044095993,
+      "learning_rate": 7.631961304702124e-05,
+      "loss": 0.0235,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8185263157894735,
+      "grad_norm": 0.097357377409935,
+      "learning_rate": 7.450920103663443e-05,
+      "loss": 0.0219,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8353684210526315,
+      "grad_norm": 0.169428288936615,
+      "learning_rate": 7.270768141794942e-05,
+      "loss": 0.0207,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "grad_norm": 0.12443847209215164,
+      "learning_rate": 7.091568264588952e-05,
+      "loss": 0.0195,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "eval_loss": 0.02066013775765896,
+      "eval_runtime": 224.1852,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8690526315789473,
+      "grad_norm": 0.11752050369977951,
+      "learning_rate": 6.913382985405814e-05,
+      "loss": 0.0186,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8858947368421053,
+      "grad_norm": 0.12359823286533356,
+      "learning_rate": 6.736274463666283e-05,
+      "loss": 0.0193,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9027368421052633,
+      "grad_norm": 0.10313016176223755,
+      "learning_rate": 6.560304483167368e-05,
+      "loss": 0.0191,
+      "step": 1130
+    },
+    {
+      "epoch": 1.919578947368421,
+      "grad_norm": 0.12194198369979858,
+      "learning_rate": 6.385534430529275e-05,
+      "loss": 0.0189,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9364210526315788,
+      "grad_norm": 0.1172875314950943,
+      "learning_rate": 6.212025273780815e-05,
+      "loss": 0.0155,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9532631578947368,
+      "grad_norm": 0.09735918790102005,
+      "learning_rate": 6.039837541090913e-05,
+      "loss": 0.0169,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9701052631578948,
+      "grad_norm": 0.09256832301616669,
+      "learning_rate": 5.869031299653518e-05,
+      "loss": 0.0174,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9869473684210526,
+      "grad_norm": 0.10335566103458405,
+      "learning_rate": 5.699666134733349e-05,
+      "loss": 0.0171,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0033684210526315,
+      "grad_norm": 0.10647857934236526,
+      "learning_rate": 5.5318011288797237e-05,
+      "loss": 0.0158,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "grad_norm": 0.12479748576879501,
+      "learning_rate": 5.365494841315808e-05,
+      "loss": 0.0136,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "eval_loss": 0.017488960176706314,
+      "eval_runtime": 224.1495,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0370526315789474,
+      "grad_norm": 0.09349500387907028,
+      "learning_rate": 5.2008052875103886e-05,
+      "loss": 0.0137,
+      "step": 1210
+    },
+    {
+      "epoch": 2.053894736842105,
+      "grad_norm": 0.06680870801210403,
+      "learning_rate": 5.037789918939335e-05,
+      "loss": 0.0126,
+      "step": 1220
+    },
+    {
+      "epoch": 2.070736842105263,
+      "grad_norm": 0.09055491536855698,
+      "learning_rate": 4.876505603043826e-05,
+      "loss": 0.0128,
+      "step": 1230
+    },
+    {
+      "epoch": 2.087578947368421,
+      "grad_norm": 0.12399008870124817,
+      "learning_rate": 4.717008603392318e-05,
+      "loss": 0.0131,
+      "step": 1240
+    },
+    {
+      "epoch": 2.104421052631579,
+      "grad_norm": 0.09043820202350616,
+      "learning_rate": 4.559354560053135e-05,
+      "loss": 0.0118,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1212631578947367,
+      "grad_norm": 0.07968771457672119,
+      "learning_rate": 4.4035984701846234e-05,
+      "loss": 0.0122,
+      "step": 1260
+    },
+    {
+      "epoch": 2.138105263157895,
+      "grad_norm": 0.07125072926282883,
+      "learning_rate": 4.2497946688495184e-05,
+      "loss": 0.0117,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1549473684210527,
+      "grad_norm": 0.07947332412004471,
+      "learning_rate": 4.097996810060346e-05,
+      "loss": 0.0112,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1717894736842105,
+      "grad_norm": 0.06901393830776215,
+      "learning_rate": 3.948257848062351e-05,
+      "loss": 0.0119,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "grad_norm": 0.07422488927841187,
+      "learning_rate": 3.8006300188605705e-05,
+      "loss": 0.0111,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "eval_loss": 0.015334118157625198,
+      "eval_runtime": 224.1161,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2054736842105265,
+      "grad_norm": 0.10787979513406754,
+      "learning_rate": 3.655164821997451e-05,
+      "loss": 0.0123,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2223157894736842,
+      "grad_norm": 0.07865067571401596,
+      "learning_rate": 3.5119130025874034e-05,
+      "loss": 0.0107,
+      "step": 1320
+    },
+    {
+      "epoch": 2.239157894736842,
+      "grad_norm": 0.07730992138385773,
+      "learning_rate": 3.3709245336144777e-05,
+      "loss": 0.0112,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.0723709836602211,
+      "learning_rate": 3.232248598499459e-05,
+      "loss": 0.0114,
+      "step": 1340
+    },
+    {
+      "epoch": 2.272842105263158,
+      "grad_norm": 0.08348905295133591,
+      "learning_rate": 3.09593357394236e-05,
+      "loss": 0.01,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2896842105263158,
+      "grad_norm": 0.07650898396968842,
+      "learning_rate": 2.9620270130463667e-05,
+      "loss": 0.0109,
+      "step": 1360
+    },
+    {
+      "epoch": 2.3065263157894735,
+      "grad_norm": 0.06670452654361725,
+      "learning_rate": 2.8305756287290484e-05,
+      "loss": 0.0114,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3233684210526317,
+      "grad_norm": 0.07205783575773239,
+      "learning_rate": 2.7016252774267192e-05,
+      "loss": 0.0109,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3402105263157895,
+      "grad_norm": 0.07499977201223373,
+      "learning_rate": 2.575220943097526e-05,
+      "loss": 0.0113,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "grad_norm": 0.07749755680561066,
+      "learning_rate": 2.4514067215289503e-05,
+      "loss": 0.0102,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "eval_loss": 0.013460199348628521,
+      "eval_runtime": 224.1893,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3738947368421055,
+      "grad_norm": 0.07490992546081543,
+      "learning_rate": 2.3302258049550974e-05,
+      "loss": 0.0103,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3907368421052633,
+      "grad_norm": 0.07824037969112396,
+      "learning_rate": 2.2117204669892198e-05,
+      "loss": 0.0104,
+      "step": 1420
+    },
+    {
+      "epoch": 2.407578947368421,
+      "grad_norm": 0.07291096448898315,
+      "learning_rate": 2.0959320478766965e-05,
+      "loss": 0.0101,
+      "step": 1430
+    },
+    {
+      "epoch": 2.424421052631579,
+      "grad_norm": 0.09640032798051834,
+      "learning_rate": 1.9829009400735977e-05,
+      "loss": 0.011,
+      "step": 1440
+    },
+    {
+      "epoch": 2.441263157894737,
+      "grad_norm": 0.07188956439495087,
+      "learning_rate": 1.8726665741558923e-05,
+      "loss": 0.0105,
+      "step": 1450
+    },
+    {
+      "epoch": 2.458105263157895,
+      "grad_norm": 0.0596754252910614,
+      "learning_rate": 1.765267405064206e-05,
+      "loss": 0.009,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4749473684210526,
+      "grad_norm": 0.0846128836274147,
+      "learning_rate": 1.6607408986889384e-05,
+      "loss": 0.0096,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4917894736842103,
+      "grad_norm": 0.10189133137464523,
+      "learning_rate": 1.559123518800376e-05,
+      "loss": 0.0105,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5086315789473685,
+      "grad_norm": 0.06304220855236053,
+      "learning_rate": 1.460450714328423e-05,
+      "loss": 0.0104,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "grad_norm": 0.06267323344945908,
+      "learning_rate": 1.364756906996345e-05,
+      "loss": 0.0095,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "eval_loss": 0.01212456077337265,
+      "eval_runtime": 224.2724,
+      "eval_samples_per_second": 2.229,
+      "eval_steps_per_second": 2.229,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1083187220819476e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ebf36573d729aaa340fbacc4c94ccace1662c744156c5330ffcb2496294477b
+size 5777

checkpoint-1782/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1782/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1782/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6b50b6bfc1c5e7d4d843e620fd2dd98fd3b8a416a439f46b5f8440fa6d14aa
+size 323014168

checkpoint-1782/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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-1782/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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-1782/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f5eb9d9552fdf24306ebe4697c2bf2f379632e5d7de2c5717fc2f39fee30cd
+size 646253819

checkpoint-1782/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030bf98ea15bfaa2df571d5881050f473c0d742d9d7778e1c59e152451a57a8
+size 14645

checkpoint-1782/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b90582241be69f16130e8995724321b1bd92ffb986e87dad86a9611772b165
+size 1465

checkpoint-1782/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1782/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694f1174c5bdf94e2fc50796c0f1733a5a3945ff110b0dfa40ea0701cc9c9c42
+size 11422176

checkpoint-1782/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1782/trainer_state.json

@@ -0,0 +1,1416 @@
+{
+  "best_global_step": 1700,
+  "best_metric": 0.011158278211951256,
+  "best_model_checkpoint": "/output/x3d_finetuned_model/checkpoint-1500",
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 1782,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.2378891110420227,
+      "learning_rate": 1.8e-05,
+      "loss": 0.8901,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.18149839341640472,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7969,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.1667049527168274,
+      "learning_rate": 5.8e-05,
+      "loss": 0.6762,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.15869387984275818,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.5698,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.16361284255981445,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5225,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.14269448816776276,
+      "learning_rate": 0.000118,
+      "loss": 0.465,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.18330006301403046,
+      "learning_rate": 0.000138,
+      "loss": 0.4562,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.20621822774410248,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.4291,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.21223391592502594,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.3939,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.19762997329235077,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.3753,
+      "step": 100
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "eval_loss": 0.35540345311164856,
+      "eval_runtime": 224.1519,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.18955057859420776,
+      "learning_rate": 0.00019998587161376442,
+      "loss": 0.3407,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.24190108478069305,
+      "learning_rate": 0.00019993703787315803,
+      "loss": 0.346,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.1914621889591217,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 0.3288,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.1650117188692093,
+      "learning_rate": 0.00019973481134690592,
+      "loss": 0.2942,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.22298051416873932,
+      "learning_rate": 0.00019958148910740063,
+      "loss": 0.2904,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.24592551589012146,
+      "learning_rate": 0.0001993934281526176,
+      "loss": 0.2918,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.19984672963619232,
+      "learning_rate": 0.00019917069408707848,
+      "loss": 0.2461,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.22812137007713318,
+      "learning_rate": 0.00019891336461091966,
+      "loss": 0.2577,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.21963553130626678,
+      "learning_rate": 0.0001986215294927868,
+      "loss": 0.2267,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.24446611106395721,
+      "learning_rate": 0.00019829529053851919,
+      "loss": 0.2412,
+      "step": 200
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "eval_loss": 0.23451316356658936,
+      "eval_runtime": 224.1089,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.19283448159694672,
+      "learning_rate": 0.00019793476155563507,
+      "loss": 0.2324,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.2276701033115387,
+      "learning_rate": 0.00019754006831363042,
+      "loss": 0.2055,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.28741592168807983,
+      "learning_rate": 0.00019711134850010432,
+      "loss": 0.2068,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.2498358190059662,
+      "learning_rate": 0.00019664875167272735,
+      "loss": 0.1945,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.21750546991825104,
+      "learning_rate": 0.00019615243920706853,
+      "loss": 0.1811,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.22553850710391998,
+      "learning_rate": 0.00019562258424030016,
+      "loss": 0.18,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.2156210094690323,
+      "learning_rate": 0.00019505937161079927,
+      "loss": 0.1623,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3091757595539093,
+      "learning_rate": 0.0001944629977936673,
+      "loss": 0.1635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.23857639729976654,
+      "learning_rate": 0.0001938336708321904,
+      "loss": 0.1458,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.2157812863588333,
+      "learning_rate": 0.0001931716102652641,
+      "loss": 0.1602,
+      "step": 300
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "eval_loss": 0.14944693446159363,
+      "eval_runtime": 224.1903,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.3185126483440399,
+      "learning_rate": 0.00019247704705080773,
+      "loss": 0.1531,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2601878345012665,
+      "learning_rate": 0.00019175022348519554,
+      "loss": 0.1403,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.22638513147830963,
+      "learning_rate": 0.00019099139311873215,
+      "loss": 0.1176,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2953122854232788,
+      "learning_rate": 0.00019020082066720245,
+      "loss": 0.1192,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.300016313791275,
+      "learning_rate": 0.00018937878191952606,
+      "loss": 0.1225,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.21774296462535858,
+      "learning_rate": 0.0001885255636415494,
+      "loss": 0.1051,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.19208350777626038,
+      "learning_rate": 0.00018764146347600793,
+      "loss": 0.0987,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2341982126235962,
+      "learning_rate": 0.00018672678983869463,
+      "loss": 0.1071,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.22858911752700806,
+      "learning_rate": 0.00018578186181086997,
+      "loss": 0.0983,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.238422691822052,
+      "learning_rate": 0.0001848070090279512,
+      "loss": 0.0997,
+      "step": 400
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "eval_loss": 0.09719416499137878,
+      "eval_runtime": 224.0873,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.23865894973278046,
+      "learning_rate": 0.00018380257156452013,
+      "loss": 0.0894,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.21594248712062836,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 0.0871,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.26310935616493225,
+      "learning_rate": 0.0001817063543748664,
+      "loss": 0.0933,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.20604920387268066,
+      "learning_rate": 0.00018061530590796475,
+      "loss": 0.0832,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2668643593788147,
+      "learning_rate": 0.0001794961350240951,
+      "loss": 0.0822,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.1784186065196991,
+      "learning_rate": 0.00017834923214279268,
+      "loss": 0.0783,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2419017106294632,
+      "learning_rate": 0.00017717499735781983,
+      "loss": 0.0727,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.25795748829841614,
+      "learning_rate": 0.00017597384029759475,
+      "loss": 0.0765,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.25549963116645813,
+      "learning_rate": 0.00017474617998229373,
+      "loss": 0.0678,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.3272872865200043,
+      "learning_rate": 0.00017349244467767708,
+      "loss": 0.0741,
+      "step": 500
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.0688847005367279,
+      "eval_runtime": 224.164,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.20569807291030884,
+      "learning_rate": 0.0001722130717456901,
+      "loss": 0.0648,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.2218085080385208,
+      "learning_rate": 0.00017090850749189022,
+      "loss": 0.0659,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18904639780521393,
+      "learning_rate": 0.00016957920700975504,
+      "loss": 0.0636,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.24751749634742737,
+      "learning_rate": 0.00016822563402192397,
+      "loss": 0.0612,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.19475597143173218,
+      "learning_rate": 0.00016684826071843004,
+      "loss": 0.065,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.2451489120721817,
+      "learning_rate": 0.00016544756759197778,
+      "loss": 0.0588,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16222433745861053,
+      "learning_rate": 0.0001640240432703247,
+      "loss": 0.0585,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.13785243034362793,
+      "learning_rate": 0.0001625781843458249,
+      "loss": 0.0606,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.1904134750366211,
+      "learning_rate": 0.00016111049520219428,
+      "loss": 0.0491,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.19465769827365875,
+      "learning_rate": 0.00015962148783855767,
+      "loss": 0.0535,
+      "step": 600
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "eval_loss": 0.053230032324790955,
+      "eval_runtime": 224.1426,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.19065628945827484,
+      "learning_rate": 0.00015811168169083955,
+      "loss": 0.05,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.20831789076328278,
+      "learning_rate": 0.00015658160345056023,
+      "loss": 0.0493,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.12762245535850525,
+      "learning_rate": 0.000155031786881101,
+      "loss": 0.0461,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.14034190773963928,
+      "learning_rate": 0.0001534627726315023,
+      "loss": 0.0437,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.21654851734638214,
+      "learning_rate": 0.00015187510804786012,
+      "loss": 0.0417,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.21853309869766235,
+      "learning_rate": 0.0001502693469823855,
+      "loss": 0.0416,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.1370641142129898,
+      "learning_rate": 0.00014864604960019504,
+      "loss": 0.0425,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.2183496206998825,
+      "learning_rate": 0.00014700578218389892,
+      "loss": 0.0392,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.17953278124332428,
+      "learning_rate": 0.00014534911693605464,
+      "loss": 0.0407,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.17893248796463013,
+      "learning_rate": 0.00014367663177955605,
+      "loss": 0.04,
+      "step": 700
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "eval_loss": 0.04435127228498459,
+      "eval_runtime": 224.0979,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15027707815170288,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 0.042,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.2271127700805664,
+      "learning_rate": 0.00014028654082228682,
+      "loss": 0.0413,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.16139471530914307,
+      "learning_rate": 0.00013857011764496942,
+      "loss": 0.0415,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.17120322585105896,
+      "learning_rate": 0.0001368402393933495,
+      "loss": 0.0444,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.12668217718601227,
+      "learning_rate": 0.00013509750953046606,
+      "loss": 0.0359,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.1568315625190735,
+      "learning_rate": 0.00013334253600260563,
+      "loss": 0.0375,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.1669214367866516,
+      "learning_rate": 0.00013157593102722205,
+      "loss": 0.0402,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.1692507565021515,
+      "learning_rate": 0.00012979831087936598,
+      "loss": 0.0353,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.16156762838363647,
+      "learning_rate": 0.00012801029567669926,
+      "loss": 0.0328,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.14826713502407074,
+      "learning_rate": 0.00012621250916316864,
+      "loss": 0.0342,
+      "step": 800
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "eval_loss": 0.036476925015449524,
+      "eval_runtime": 224.0704,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.10823637247085571,
+      "learning_rate": 0.00012440557849141448,
+      "loss": 0.032,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1409875601530075,
+      "learning_rate": 0.0001225901340039903,
+      "loss": 0.0359,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.174799844622612,
+      "learning_rate": 0.00012076680901346981,
+      "loss": 0.034,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.14141526818275452,
+      "learning_rate": 0.00011893623958151732,
+      "loss": 0.0283,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.24268820881843567,
+      "learning_rate": 0.00011709906429699977,
+      "loss": 0.0333,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11979827284812927,
+      "learning_rate": 0.00011525592405321666,
+      "loss": 0.0286,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.12912440299987793,
+      "learning_rate": 0.00011340746182432633,
+      "loss": 0.0291,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.11993803083896637,
+      "learning_rate": 0.00011155432244104627,
+      "loss": 0.0241,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.18345041573047638,
+      "learning_rate": 0.00010969715236570586,
+      "loss": 0.0293,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.1686432659626007,
+      "learning_rate": 0.00010783659946672964,
+      "loss": 0.0304,
+      "step": 900
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "eval_loss": 0.031156836077570915,
+      "eval_runtime": 224.1681,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.10962788015604019,
+      "learning_rate": 0.00010597331279263057,
+      "loss": 0.0283,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.1417897343635559,
+      "learning_rate": 0.00010410794234559107,
+      "loss": 0.0271,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.1917513608932495,
+      "learning_rate": 0.00010224113885471183,
+      "loss": 0.0248,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.1399783492088318,
+      "learning_rate": 0.00010037355354900661,
+      "loss": 0.0239,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.11135450005531311,
+      "learning_rate": 9.850583793022319e-05,
+      "loss": 0.0244,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.11133313179016113,
+      "learning_rate": 9.663864354556858e-05,
+      "loss": 0.0283,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.1533219963312149,
+      "learning_rate": 9.477262176041883e-05,
+      "loss": 0.0266,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.13194741308689117,
+      "learning_rate": 9.290842353109195e-05,
+      "loss": 0.0265,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.11617199331521988,
+      "learning_rate": 9.104669917776383e-05,
+      "loss": 0.0225,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.11771562695503235,
+      "learning_rate": 8.918809815760585e-05,
+      "loss": 0.0233,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "eval_loss": 0.02681094780564308,
+      "eval_runtime": 224.15,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7006315789473683,
+      "grad_norm": 0.1440223902463913,
+      "learning_rate": 8.733326883822356e-05,
+      "loss": 0.0252,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7174736842105263,
+      "grad_norm": 0.15115946531295776,
+      "learning_rate": 8.548285827147568e-05,
+      "loss": 0.0244,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7343157894736843,
+      "grad_norm": 0.10699623823165894,
+      "learning_rate": 8.363751196775172e-05,
+      "loss": 0.0216,
+      "step": 1030
+    },
+    {
+      "epoch": 1.751157894736842,
+      "grad_norm": 0.10448223352432251,
+      "learning_rate": 8.17978736707877e-05,
+      "loss": 0.0227,
+      "step": 1040
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.12821614742279053,
+      "learning_rate": 7.996458513309787e-05,
+      "loss": 0.0198,
+      "step": 1050
+    },
+    {
+      "epoch": 1.784842105263158,
+      "grad_norm": 0.1228765919804573,
+      "learning_rate": 7.813828589210138e-05,
+      "loss": 0.023,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8016842105263158,
+      "grad_norm": 0.1160237044095993,
+      "learning_rate": 7.631961304702124e-05,
+      "loss": 0.0235,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8185263157894735,
+      "grad_norm": 0.097357377409935,
+      "learning_rate": 7.450920103663443e-05,
+      "loss": 0.0219,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8353684210526315,
+      "grad_norm": 0.169428288936615,
+      "learning_rate": 7.270768141794942e-05,
+      "loss": 0.0207,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "grad_norm": 0.12443847209215164,
+      "learning_rate": 7.091568264588952e-05,
+      "loss": 0.0195,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "eval_loss": 0.02066013775765896,
+      "eval_runtime": 224.1852,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8690526315789473,
+      "grad_norm": 0.11752050369977951,
+      "learning_rate": 6.913382985405814e-05,
+      "loss": 0.0186,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8858947368421053,
+      "grad_norm": 0.12359823286533356,
+      "learning_rate": 6.736274463666283e-05,
+      "loss": 0.0193,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9027368421052633,
+      "grad_norm": 0.10313016176223755,
+      "learning_rate": 6.560304483167368e-05,
+      "loss": 0.0191,
+      "step": 1130
+    },
+    {
+      "epoch": 1.919578947368421,
+      "grad_norm": 0.12194198369979858,
+      "learning_rate": 6.385534430529275e-05,
+      "loss": 0.0189,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9364210526315788,
+      "grad_norm": 0.1172875314950943,
+      "learning_rate": 6.212025273780815e-05,
+      "loss": 0.0155,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9532631578947368,
+      "grad_norm": 0.09735918790102005,
+      "learning_rate": 6.039837541090913e-05,
+      "loss": 0.0169,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9701052631578948,
+      "grad_norm": 0.09256832301616669,
+      "learning_rate": 5.869031299653518e-05,
+      "loss": 0.0174,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9869473684210526,
+      "grad_norm": 0.10335566103458405,
+      "learning_rate": 5.699666134733349e-05,
+      "loss": 0.0171,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0033684210526315,
+      "grad_norm": 0.10647857934236526,
+      "learning_rate": 5.5318011288797237e-05,
+      "loss": 0.0158,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "grad_norm": 0.12479748576879501,
+      "learning_rate": 5.365494841315808e-05,
+      "loss": 0.0136,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "eval_loss": 0.017488960176706314,
+      "eval_runtime": 224.1495,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0370526315789474,
+      "grad_norm": 0.09349500387907028,
+      "learning_rate": 5.2008052875103886e-05,
+      "loss": 0.0137,
+      "step": 1210
+    },
+    {
+      "epoch": 2.053894736842105,
+      "grad_norm": 0.06680870801210403,
+      "learning_rate": 5.037789918939335e-05,
+      "loss": 0.0126,
+      "step": 1220
+    },
+    {
+      "epoch": 2.070736842105263,
+      "grad_norm": 0.09055491536855698,
+      "learning_rate": 4.876505603043826e-05,
+      "loss": 0.0128,
+      "step": 1230
+    },
+    {
+      "epoch": 2.087578947368421,
+      "grad_norm": 0.12399008870124817,
+      "learning_rate": 4.717008603392318e-05,
+      "loss": 0.0131,
+      "step": 1240
+    },
+    {
+      "epoch": 2.104421052631579,
+      "grad_norm": 0.09043820202350616,
+      "learning_rate": 4.559354560053135e-05,
+      "loss": 0.0118,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1212631578947367,
+      "grad_norm": 0.07968771457672119,
+      "learning_rate": 4.4035984701846234e-05,
+      "loss": 0.0122,
+      "step": 1260
+    },
+    {
+      "epoch": 2.138105263157895,
+      "grad_norm": 0.07125072926282883,
+      "learning_rate": 4.2497946688495184e-05,
+      "loss": 0.0117,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1549473684210527,
+      "grad_norm": 0.07947332412004471,
+      "learning_rate": 4.097996810060346e-05,
+      "loss": 0.0112,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1717894736842105,
+      "grad_norm": 0.06901393830776215,
+      "learning_rate": 3.948257848062351e-05,
+      "loss": 0.0119,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "grad_norm": 0.07422488927841187,
+      "learning_rate": 3.8006300188605705e-05,
+      "loss": 0.0111,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "eval_loss": 0.015334118157625198,
+      "eval_runtime": 224.1161,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2054736842105265,
+      "grad_norm": 0.10787979513406754,
+      "learning_rate": 3.655164821997451e-05,
+      "loss": 0.0123,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2223157894736842,
+      "grad_norm": 0.07865067571401596,
+      "learning_rate": 3.5119130025874034e-05,
+      "loss": 0.0107,
+      "step": 1320
+    },
+    {
+      "epoch": 2.239157894736842,
+      "grad_norm": 0.07730992138385773,
+      "learning_rate": 3.3709245336144777e-05,
+      "loss": 0.0112,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.0723709836602211,
+      "learning_rate": 3.232248598499459e-05,
+      "loss": 0.0114,
+      "step": 1340
+    },
+    {
+      "epoch": 2.272842105263158,
+      "grad_norm": 0.08348905295133591,
+      "learning_rate": 3.09593357394236e-05,
+      "loss": 0.01,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2896842105263158,
+      "grad_norm": 0.07650898396968842,
+      "learning_rate": 2.9620270130463667e-05,
+      "loss": 0.0109,
+      "step": 1360
+    },
+    {
+      "epoch": 2.3065263157894735,
+      "grad_norm": 0.06670452654361725,
+      "learning_rate": 2.8305756287290484e-05,
+      "loss": 0.0114,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3233684210526317,
+      "grad_norm": 0.07205783575773239,
+      "learning_rate": 2.7016252774267192e-05,
+      "loss": 0.0109,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3402105263157895,
+      "grad_norm": 0.07499977201223373,
+      "learning_rate": 2.575220943097526e-05,
+      "loss": 0.0113,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "grad_norm": 0.07749755680561066,
+      "learning_rate": 2.4514067215289503e-05,
+      "loss": 0.0102,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "eval_loss": 0.013460199348628521,
+      "eval_runtime": 224.1893,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3738947368421055,
+      "grad_norm": 0.07490992546081543,
+      "learning_rate": 2.3302258049550974e-05,
+      "loss": 0.0103,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3907368421052633,
+      "grad_norm": 0.07824037969112396,
+      "learning_rate": 2.2117204669892198e-05,
+      "loss": 0.0104,
+      "step": 1420
+    },
+    {
+      "epoch": 2.407578947368421,
+      "grad_norm": 0.07291096448898315,
+      "learning_rate": 2.0959320478766965e-05,
+      "loss": 0.0101,
+      "step": 1430
+    },
+    {
+      "epoch": 2.424421052631579,
+      "grad_norm": 0.09640032798051834,
+      "learning_rate": 1.9829009400735977e-05,
+      "loss": 0.011,
+      "step": 1440
+    },
+    {
+      "epoch": 2.441263157894737,
+      "grad_norm": 0.07188956439495087,
+      "learning_rate": 1.8726665741558923e-05,
+      "loss": 0.0105,
+      "step": 1450
+    },
+    {
+      "epoch": 2.458105263157895,
+      "grad_norm": 0.0596754252910614,
+      "learning_rate": 1.765267405064206e-05,
+      "loss": 0.009,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4749473684210526,
+      "grad_norm": 0.0846128836274147,
+      "learning_rate": 1.6607408986889384e-05,
+      "loss": 0.0096,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4917894736842103,
+      "grad_norm": 0.10189133137464523,
+      "learning_rate": 1.559123518800376e-05,
+      "loss": 0.0105,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5086315789473685,
+      "grad_norm": 0.06304220855236053,
+      "learning_rate": 1.460450714328423e-05,
+      "loss": 0.0104,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "grad_norm": 0.06267323344945908,
+      "learning_rate": 1.364756906996345e-05,
+      "loss": 0.0095,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "eval_loss": 0.01212456077337265,
+      "eval_runtime": 224.2724,
+      "eval_samples_per_second": 2.229,
+      "eval_steps_per_second": 2.229,
+      "step": 1500
+    },
+    {
+      "epoch": 2.542315789473684,
+      "grad_norm": 0.09089558571577072,
+      "learning_rate": 1.2720754793128464e-05,
+      "loss": 0.0096,
+      "step": 1510
+    },
+    {
+      "epoch": 2.559157894736842,
+      "grad_norm": 0.0663435310125351,
+      "learning_rate": 1.1824387629266742e-05,
+      "loss": 0.0094,
+      "step": 1520
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.06648425757884979,
+      "learning_rate": 1.0958780273478253e-05,
+      "loss": 0.0095,
+      "step": 1530
+    },
+    {
+      "epoch": 2.592842105263158,
+      "grad_norm": 0.09527198225259781,
+      "learning_rate": 1.0124234690392586e-05,
+      "loss": 0.0098,
+      "step": 1540
+    },
+    {
+      "epoch": 2.609684210526316,
+      "grad_norm": 0.08171885460615158,
+      "learning_rate": 9.321042008829562e-06,
+      "loss": 0.0095,
+      "step": 1550
+    },
+    {
+      "epoch": 2.626526315789474,
+      "grad_norm": 0.06150711327791214,
+      "learning_rate": 8.549482420239707e-06,
+      "loss": 0.0098,
+      "step": 1560
+    },
+    {
+      "epoch": 2.6433684210526316,
+      "grad_norm": 0.058401718735694885,
+      "learning_rate": 7.809825080960276e-06,
+      "loss": 0.0096,
+      "step": 1570
+    },
+    {
+      "epoch": 2.6602105263157894,
+      "grad_norm": 0.0481596402823925,
+      "learning_rate": 7.102328018320858e-06,
+      "loss": 0.0096,
+      "step": 1580
+    },
+    {
+      "epoch": 2.677052631578947,
+      "grad_norm": 0.07530257105827332,
+      "learning_rate": 6.4272380406313334e-06,
+      "loss": 0.0091,
+      "step": 1590
+    },
+    {
+      "epoch": 2.6938947368421053,
+      "grad_norm": 0.062257252633571625,
+      "learning_rate": 5.784790651083405e-06,
+      "loss": 0.0097,
+      "step": 1600
+    },
+    {
+      "epoch": 2.6938947368421053,
+      "eval_loss": 0.011450879275798798,
+      "eval_runtime": 224.0976,
+      "eval_samples_per_second": 2.231,
+      "eval_steps_per_second": 2.231,
+      "step": 1600
+    },
+    {
+      "epoch": 2.710736842105263,
+      "grad_norm": 0.0579669252038002,
+      "learning_rate": 5.175209965596084e-06,
+      "loss": 0.0094,
+      "step": 1610
+    },
+    {
+      "epoch": 2.7275789473684213,
+      "grad_norm": 0.06278079748153687,
+      "learning_rate": 4.598708634633442e-06,
+      "loss": 0.009,
+      "step": 1620
+    },
+    {
+      "epoch": 2.744421052631579,
+      "grad_norm": 0.05131611227989197,
+      "learning_rate": 4.055487769022137e-06,
+      "loss": 0.0095,
+      "step": 1630
+    },
+    {
+      "epoch": 2.761263157894737,
+      "grad_norm": 0.05207466334104538,
+      "learning_rate": 3.545736869794458e-06,
+      "loss": 0.0092,
+      "step": 1640
+    },
+    {
+      "epoch": 2.7781052631578946,
+      "grad_norm": 0.06517709046602249,
+      "learning_rate": 3.0696337620814364e-06,
+      "loss": 0.0091,
+      "step": 1650
+    },
+    {
+      "epoch": 2.7949473684210524,
+      "grad_norm": 0.06492120027542114,
+      "learning_rate": 2.6273445330791234e-06,
+      "loss": 0.0093,
+      "step": 1660
+    },
+    {
+      "epoch": 2.8117894736842106,
+      "grad_norm": 0.06431007385253906,
+      "learning_rate": 2.219023474109483e-06,
+      "loss": 0.0091,
+      "step": 1670
+    },
+    {
+      "epoch": 2.8286315789473684,
+      "grad_norm": 0.05567321926355362,
+      "learning_rate": 1.8448130267962992e-06,
+      "loss": 0.0087,
+      "step": 1680
+    },
+    {
+      "epoch": 2.845473684210526,
+      "grad_norm": 0.08136210590600967,
+      "learning_rate": 1.5048437333748833e-06,
+      "loss": 0.0094,
+      "step": 1690
+    },
+    {
+      "epoch": 2.8623157894736844,
+      "grad_norm": 0.08303703367710114,
+      "learning_rate": 1.1992341911527649e-06,
+      "loss": 0.0085,
+      "step": 1700
+    },
+    {
+      "epoch": 2.8623157894736844,
+      "eval_loss": 0.011158278211951256,
+      "eval_runtime": 224.1949,
+      "eval_samples_per_second": 2.23,
+      "eval_steps_per_second": 2.23,
+      "step": 1700
+    },
+    {
+      "epoch": 2.879157894736842,
+      "grad_norm": 0.05584060773253441,
+      "learning_rate": 9.280910111373553e-07,
+      "loss": 0.0083,
+      "step": 1710
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.060032352805137634,
+      "learning_rate": 6.91508780844996e-07,
+      "loss": 0.0093,
+      "step": 1720
+    },
+    {
+      "epoch": 2.9128421052631577,
+      "grad_norm": 0.054556239396333694,
+      "learning_rate": 4.895700313044315e-07,
+      "loss": 0.0091,
+      "step": 1730
+    },
+    {
+      "epoch": 2.929684210526316,
+      "grad_norm": 0.05352412536740303,
+      "learning_rate": 3.223452082660394e-07,
+      "loss": 0.0089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.9465263157894737,
+      "grad_norm": 0.0548105351626873,
+      "learning_rate": 1.898926476270546e-07,
+      "loss": 0.0083,
+      "step": 1750
+    },
+    {
+      "epoch": 2.9633684210526314,
+      "grad_norm": 0.0906362310051918,
+      "learning_rate": 9.225855508123715e-08,
+      "loss": 0.009,
+      "step": 1760
+    },
+    {
+      "epoch": 2.9802105263157896,
+      "grad_norm": 0.053922925144433975,
+      "learning_rate": 2.947699000021009e-08,
+      "loss": 0.0091,
+      "step": 1770
+    },
+    {
+      "epoch": 2.9970526315789474,
+      "grad_norm": 0.08347595483064651,
+      "learning_rate": 1.5698535518748892e-09,
+      "loss": 0.0086,
+      "step": 1780
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.504463303573504e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1782/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ebf36573d729aaa340fbacc4c94ccace1662c744156c5330ffcb2496294477b
+size 5777