初始化项目，由ModelHub XC社区提供模型
Model: AdaptLLM/food-Qwen2-VL-2B-Instruct Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz 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
|
||||||
|
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
129
README.md
Normal file
129
README.md
Normal file
@@ -0,0 +1,129 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen2-VL-2B-Instruct
|
||||||
|
tags:
|
||||||
|
- food
|
||||||
|
- recipe
|
||||||
|
---
|
||||||
|
# Adapting Multimodal Large Language Models to Domains via Post-Training (EMNLP 2025)
|
||||||
|
|
||||||
|
This repos contains the **food MLLM developed from Qwen-2-VL-2B-Instruct** in our paper: [On Domain-Specific Post-Training for Multimodal Large Language Models](https://huggingface.co/papers/2411.19930).
|
||||||
|
|
||||||
|
The main project page is: [Adapt-MLLM-to-Domains](https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains)
|
||||||
|
|
||||||
|
## 1. To Chat with AdaMLLM
|
||||||
|
|
||||||
|
Our model architecture aligns with the base model: Qwen-2-VL-Instruct. We provide a usage example below, and you may refer to the official [Qwen-2-VL-Instruct repository](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) for more advanced usage instructions.
|
||||||
|
|
||||||
|
**Note:** For AdaMLLM, always place the image at the beginning of the input instruction in the messages.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary> Click to expand </summary>
|
||||||
|
|
||||||
|
1. Set up
|
||||||
|
```bash
|
||||||
|
pip install qwen-vl-utils
|
||||||
|
```
|
||||||
|
2. Inference
|
||||||
|
```python
|
||||||
|
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
||||||
|
from qwen_vl_utils import process_vision_info
|
||||||
|
|
||||||
|
# default: Load the model on the available device(s)
|
||||||
|
model = Qwen2VLForConditionalGeneration.from_pretrained(
|
||||||
|
"AdaptLLM/food-Qwen2-VL-2B-Instruct", torch_dtype="auto", device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
|
||||||
|
# model = Qwen2VLForConditionalGeneration.from_pretrained(
|
||||||
|
# "AdaptLLM/food-Qwen2-VL-2B-Instruct",
|
||||||
|
# torch_dtype=torch.bfloat16,
|
||||||
|
# attn_implementation="flash_attention_2",
|
||||||
|
# device_map="auto",
|
||||||
|
# )
|
||||||
|
|
||||||
|
# default processer
|
||||||
|
processor = AutoProcessor.from_pretrained("AdaptLLM/food-Qwen2-VL-2B-Instruct")
|
||||||
|
|
||||||
|
# The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
|
||||||
|
# min_pixels = 256*28*28
|
||||||
|
# max_pixels = 1280*28*28
|
||||||
|
# processor = AutoProcessor.from_pretrained("AdaptLLM/food-Qwen2-VL-2B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
|
||||||
|
|
||||||
|
# NOTE: For AdaMLLM, always place the image at the beginning of the input instruction in the messages.
|
||||||
|
messages = [
|
||||||
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": [
|
||||||
|
{
|
||||||
|
"type": "image",
|
||||||
|
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
||||||
|
},
|
||||||
|
{"type": "text", "text": "Describe this image."},
|
||||||
|
],
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
||||||
|
# Preparation for inference
|
||||||
|
text = processor.apply_chat_template(
|
||||||
|
messages, tokenize=False, add_generation_prompt=True
|
||||||
|
)
|
||||||
|
image_inputs, video_inputs = process_vision_info(messages)
|
||||||
|
inputs = processor(
|
||||||
|
text=[text],
|
||||||
|
images=image_inputs,
|
||||||
|
videos=video_inputs,
|
||||||
|
padding=True,
|
||||||
|
return_tensors="pt",
|
||||||
|
)
|
||||||
|
inputs = inputs.to("cuda")
|
||||||
|
|
||||||
|
# Inference: Generation of the output
|
||||||
|
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
||||||
|
generated_ids_trimmed = [
|
||||||
|
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
||||||
|
]
|
||||||
|
output_text = processor.batch_decode(
|
||||||
|
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
||||||
|
)
|
||||||
|
print(output_text)
|
||||||
|
```
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## 2. To Evaluate Any MLLM on Domain-Specific Benchmarks
|
||||||
|
|
||||||
|
Refer to the [food-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/food-VQA-benchmark) to reproduce our results and evaluate many other MLLMs on domain-specific benchmarks.
|
||||||
|
|
||||||
|
## 3. To Reproduce this Domain-Adapted MLLM
|
||||||
|
|
||||||
|
See [Post-Train Guide](https://github.com/bigai-ai/QA-Synthesizer/blob/main/docs/Post_Train.md) to adapt MLLMs to domains.
|
||||||
|
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
If you find our work helpful, please cite us.
|
||||||
|
|
||||||
|
[Adapt MLLM to Domains](https://huggingface.co/papers/2411.19930) (EMNLP 2025 Findings)
|
||||||
|
```bibtex
|
||||||
|
@article{adamllm,
|
||||||
|
title={On Domain-Adaptive Post-Training for Multimodal Large Language Models},
|
||||||
|
author={Cheng, Daixuan and Huang, Shaohan and Zhu, Ziyu and Zhang, Xintong and Zhao, Wayne Xin and Luan, Zhongzhi and Dai, Bo and Zhang, Zhenliang},
|
||||||
|
journal={arXiv preprint arXiv:2411.19930},
|
||||||
|
year={2024}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
[Adapt LLM to Domains](https://huggingface.co/papers/2309.09530) (ICLR 2024)
|
||||||
|
```bibtex
|
||||||
|
@inproceedings{
|
||||||
|
cheng2024adapting,
|
||||||
|
title={Adapting Large Language Models via Reading Comprehension},
|
||||||
|
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
|
||||||
|
booktitle={The Twelfth International Conference on Learning Representations},
|
||||||
|
year={2024},
|
||||||
|
url={https://openreview.net/forum?id=y886UXPEZ0}
|
||||||
|
}
|
||||||
|
```
|
||||||
16
added_tokens.json
Normal file
16
added_tokens.json
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
{
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"total_flos": 1.3956152400113828e+18,
|
||||||
|
"train_loss": 1.210920991029758,
|
||||||
|
"train_runtime": 4090.7445,
|
||||||
|
"train_samples_per_second": 31.964,
|
||||||
|
"train_steps_per_second": 0.25
|
||||||
|
}
|
||||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
{
|
||||||
|
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||||
|
}
|
||||||
46
config.json
Normal file
46
config.json
Normal file
@@ -0,0 +1,46 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"image_token_id": 151655,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8960,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2_vl",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": {
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
],
|
||||||
|
"type": "mrope"
|
||||||
|
},
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.45.0.dev0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"video_token_id": 151656,
|
||||||
|
"vision_config": {
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"in_chans": 3,
|
||||||
|
"model_type": "qwen2_vl",
|
||||||
|
"spatial_patch_size": 14
|
||||||
|
},
|
||||||
|
"vision_end_token_id": 151653,
|
||||||
|
"vision_start_token_id": 151652,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.01,
|
||||||
|
"top_k": 1,
|
||||||
|
"top_p": 0.001,
|
||||||
|
"transformers_version": "4.45.0.dev0"
|
||||||
|
}
|
||||||
151387
merges.txt
Normal file
151387
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3a5540acea6a98e8f6a793911dd3d0287b1219a8ecc8597c5176e17dff5d0350
|
||||||
|
size 4884798456
|
||||||
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"do_convert_rgb": true,
|
||||||
|
"do_normalize": true,
|
||||||
|
"do_rescale": true,
|
||||||
|
"do_resize": true,
|
||||||
|
"image_mean": [
|
||||||
|
0.48145466,
|
||||||
|
0.4578275,
|
||||||
|
0.40821073
|
||||||
|
],
|
||||||
|
"image_processor_type": "Qwen2VLImageProcessor",
|
||||||
|
"image_std": [
|
||||||
|
0.26862954,
|
||||||
|
0.26130258,
|
||||||
|
0.27577711
|
||||||
|
],
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"merge_size": 2,
|
||||||
|
"min_pixels": 3136,
|
||||||
|
"patch_size": 14,
|
||||||
|
"processor_class": "Qwen2VLProcessor",
|
||||||
|
"resample": 3,
|
||||||
|
"rescale_factor": 0.00392156862745098,
|
||||||
|
"size": {
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"min_pixels": 3136
|
||||||
|
},
|
||||||
|
"temporal_patch_size": 2
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -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
|
||||||
|
}
|
||||||
|
}
|
||||||
303192
tokenizer.json
Normal file
303192
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
129
tokenizer_config.json
Normal file
129
tokenizer_config.json
Normal file
@@ -0,0 +1,129 @@
|
|||||||
|
{
|
||||||
|
"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
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"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,
|
||||||
|
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"errors": "replace",
|
||||||
|
"model_max_length": 32768,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"total_flos": 1.3956152400113828e+18,
|
||||||
|
"train_loss": 1.210920991029758,
|
||||||
|
"train_runtime": 4090.7445,
|
||||||
|
"train_samples_per_second": 31.964,
|
||||||
|
"train_steps_per_second": 0.25
|
||||||
|
}
|
||||||
103
trainer_log.jsonl
Normal file
103
trainer_log.jsonl
Normal file
@@ -0,0 +1,103 @@
|
|||||||
|
{"current_steps": 10, "total_steps": 1022, "loss": 1.7598, "learning_rate": 9.70873786407767e-07, "epoch": 0.009784735812133072, "percentage": 0.98, "elapsed_time": "0:00:44", "remaining_time": "1:15:12"}
|
||||||
|
{"current_steps": 20, "total_steps": 1022, "loss": 1.6964, "learning_rate": 1.941747572815534e-06, "epoch": 0.019569471624266144, "percentage": 1.96, "elapsed_time": "0:01:23", "remaining_time": "1:09:40"}
|
||||||
|
{"current_steps": 30, "total_steps": 1022, "loss": 1.611, "learning_rate": 2.912621359223301e-06, "epoch": 0.029354207436399216, "percentage": 2.94, "elapsed_time": "0:02:05", "remaining_time": "1:09:20"}
|
||||||
|
{"current_steps": 40, "total_steps": 1022, "loss": 1.4946, "learning_rate": 3.883495145631068e-06, "epoch": 0.03913894324853229, "percentage": 3.91, "elapsed_time": "0:02:48", "remaining_time": "1:08:55"}
|
||||||
|
{"current_steps": 50, "total_steps": 1022, "loss": 1.4397, "learning_rate": 4.854368932038836e-06, "epoch": 0.04892367906066536, "percentage": 4.89, "elapsed_time": "0:03:28", "remaining_time": "1:07:35"}
|
||||||
|
{"current_steps": 60, "total_steps": 1022, "loss": 1.3915, "learning_rate": 5.825242718446602e-06, "epoch": 0.05870841487279843, "percentage": 5.87, "elapsed_time": "0:04:09", "remaining_time": "1:06:42"}
|
||||||
|
{"current_steps": 70, "total_steps": 1022, "loss": 1.3412, "learning_rate": 6.79611650485437e-06, "epoch": 0.0684931506849315, "percentage": 6.85, "elapsed_time": "0:04:47", "remaining_time": "1:05:09"}
|
||||||
|
{"current_steps": 80, "total_steps": 1022, "loss": 1.3442, "learning_rate": 7.766990291262136e-06, "epoch": 0.07827788649706457, "percentage": 7.83, "elapsed_time": "0:05:26", "remaining_time": "1:04:03"}
|
||||||
|
{"current_steps": 90, "total_steps": 1022, "loss": 1.307, "learning_rate": 8.737864077669904e-06, "epoch": 0.08806262230919765, "percentage": 8.81, "elapsed_time": "0:06:11", "remaining_time": "1:04:04"}
|
||||||
|
{"current_steps": 100, "total_steps": 1022, "loss": 1.3041, "learning_rate": 9.708737864077671e-06, "epoch": 0.09784735812133072, "percentage": 9.78, "elapsed_time": "0:06:48", "remaining_time": "1:02:49"}
|
||||||
|
{"current_steps": 110, "total_steps": 1022, "loss": 1.2911, "learning_rate": 9.998568523945896e-06, "epoch": 0.10763209393346379, "percentage": 10.76, "elapsed_time": "0:07:26", "remaining_time": "1:01:40"}
|
||||||
|
{"current_steps": 120, "total_steps": 1022, "loss": 1.2871, "learning_rate": 9.991559185756013e-06, "epoch": 0.11741682974559686, "percentage": 11.74, "elapsed_time": "0:08:02", "remaining_time": "1:00:25"}
|
||||||
|
{"current_steps": 130, "total_steps": 1022, "loss": 1.261, "learning_rate": 9.978717241383576e-06, "epoch": 0.12720156555772993, "percentage": 12.72, "elapsed_time": "0:08:42", "remaining_time": "0:59:44"}
|
||||||
|
{"current_steps": 140, "total_steps": 1022, "loss": 1.2554, "learning_rate": 9.960057696561538e-06, "epoch": 0.136986301369863, "percentage": 13.7, "elapsed_time": "0:09:24", "remaining_time": "0:59:17"}
|
||||||
|
{"current_steps": 150, "total_steps": 1022, "loss": 1.2542, "learning_rate": 9.935602354853163e-06, "epoch": 0.14677103718199608, "percentage": 14.68, "elapsed_time": "0:10:03", "remaining_time": "0:58:26"}
|
||||||
|
{"current_steps": 160, "total_steps": 1022, "loss": 1.2521, "learning_rate": 9.905379792174697e-06, "epoch": 0.15655577299412915, "percentage": 15.66, "elapsed_time": "0:10:39", "remaining_time": "0:57:24"}
|
||||||
|
{"current_steps": 170, "total_steps": 1022, "loss": 1.2677, "learning_rate": 9.869425323404593e-06, "epoch": 0.16634050880626222, "percentage": 16.63, "elapsed_time": "0:11:19", "remaining_time": "0:56:44"}
|
||||||
|
{"current_steps": 180, "total_steps": 1022, "loss": 1.2511, "learning_rate": 9.82778096111829e-06, "epoch": 0.1761252446183953, "percentage": 17.61, "elapsed_time": "0:11:57", "remaining_time": "0:55:58"}
|
||||||
|
{"current_steps": 190, "total_steps": 1022, "loss": 1.2446, "learning_rate": 9.780495366496772e-06, "epoch": 0.18590998043052837, "percentage": 18.59, "elapsed_time": "0:12:34", "remaining_time": "0:55:06"}
|
||||||
|
{"current_steps": 200, "total_steps": 1022, "loss": 1.2314, "learning_rate": 9.727623792466285e-06, "epoch": 0.19569471624266144, "percentage": 19.57, "elapsed_time": "0:13:15", "remaining_time": "0:54:28"}
|
||||||
|
{"current_steps": 210, "total_steps": 1022, "loss": 1.2458, "learning_rate": 9.669228019135625e-06, "epoch": 0.2054794520547945, "percentage": 20.55, "elapsed_time": "0:13:52", "remaining_time": "0:53:39"}
|
||||||
|
{"current_steps": 220, "total_steps": 1022, "loss": 1.2237, "learning_rate": 9.605376281606472e-06, "epoch": 0.21526418786692758, "percentage": 21.53, "elapsed_time": "0:14:33", "remaining_time": "0:53:02"}
|
||||||
|
{"current_steps": 230, "total_steps": 1022, "loss": 1.2146, "learning_rate": 9.53614319024108e-06, "epoch": 0.22504892367906065, "percentage": 22.5, "elapsed_time": "0:15:12", "remaining_time": "0:52:21"}
|
||||||
|
{"current_steps": 240, "total_steps": 1022, "loss": 1.2138, "learning_rate": 9.461609643480541e-06, "epoch": 0.23483365949119372, "percentage": 23.48, "elapsed_time": "0:15:55", "remaining_time": "0:51:52"}
|
||||||
|
{"current_steps": 250, "total_steps": 1022, "loss": 1.2111, "learning_rate": 9.381862733315444e-06, "epoch": 0.2446183953033268, "percentage": 24.46, "elapsed_time": "0:16:33", "remaining_time": "0:51:07"}
|
||||||
|
{"current_steps": 260, "total_steps": 1022, "loss": 1.2127, "learning_rate": 9.296995643519432e-06, "epoch": 0.25440313111545987, "percentage": 25.44, "elapsed_time": "0:17:11", "remaining_time": "0:50:22"}
|
||||||
|
{"current_steps": 270, "total_steps": 1022, "loss": 1.2338, "learning_rate": 9.207107540764519e-06, "epoch": 0.26418786692759294, "percentage": 26.42, "elapsed_time": "0:17:50", "remaining_time": "0:49:41"}
|
||||||
|
{"current_steps": 280, "total_steps": 1022, "loss": 1.2054, "learning_rate": 9.112303458745462e-06, "epoch": 0.273972602739726, "percentage": 27.4, "elapsed_time": "0:18:27", "remaining_time": "0:48:54"}
|
||||||
|
{"current_steps": 290, "total_steps": 1022, "loss": 1.2223, "learning_rate": 9.012694175448526e-06, "epoch": 0.2837573385518591, "percentage": 28.38, "elapsed_time": "0:19:07", "remaining_time": "0:48:16"}
|
||||||
|
{"current_steps": 300, "total_steps": 1022, "loss": 1.2137, "learning_rate": 8.90839608370809e-06, "epoch": 0.29354207436399216, "percentage": 29.35, "elapsed_time": "0:19:43", "remaining_time": "0:47:29"}
|
||||||
|
{"current_steps": 310, "total_steps": 1022, "loss": 1.2021, "learning_rate": 8.799531055202332e-06, "epoch": 0.30332681017612523, "percentage": 30.33, "elapsed_time": "0:20:20", "remaining_time": "0:46:43"}
|
||||||
|
{"current_steps": 320, "total_steps": 1022, "loss": 1.2107, "learning_rate": 8.686226298046938e-06, "epoch": 0.3131115459882583, "percentage": 31.31, "elapsed_time": "0:20:58", "remaining_time": "0:46:00"}
|
||||||
|
{"current_steps": 330, "total_steps": 1022, "loss": 1.2051, "learning_rate": 8.568614208153181e-06, "epoch": 0.32289628180039137, "percentage": 32.29, "elapsed_time": "0:21:36", "remaining_time": "0:45:17"}
|
||||||
|
{"current_steps": 340, "total_steps": 1022, "loss": 1.1906, "learning_rate": 8.446832214524132e-06, "epoch": 0.33268101761252444, "percentage": 33.27, "elapsed_time": "0:22:13", "remaining_time": "0:44:33"}
|
||||||
|
{"current_steps": 350, "total_steps": 1022, "loss": 1.2189, "learning_rate": 8.321022618669706e-06, "epoch": 0.3424657534246575, "percentage": 34.25, "elapsed_time": "0:22:49", "remaining_time": "0:43:49"}
|
||||||
|
{"current_steps": 360, "total_steps": 1022, "loss": 1.2056, "learning_rate": 8.191332428328227e-06, "epoch": 0.3522504892367906, "percentage": 35.23, "elapsed_time": "0:23:26", "remaining_time": "0:43:06"}
|
||||||
|
{"current_steps": 370, "total_steps": 1022, "loss": 1.2058, "learning_rate": 8.057913185688789e-06, "epoch": 0.36203522504892366, "percentage": 36.2, "elapsed_time": "0:24:05", "remaining_time": "0:42:26"}
|
||||||
|
{"current_steps": 380, "total_steps": 1022, "loss": 1.1787, "learning_rate": 7.920920790315139e-06, "epoch": 0.37181996086105673, "percentage": 37.18, "elapsed_time": "0:24:44", "remaining_time": "0:41:47"}
|
||||||
|
{"current_steps": 390, "total_steps": 1022, "loss": 1.1868, "learning_rate": 7.780515316978003e-06, "epoch": 0.3816046966731898, "percentage": 38.16, "elapsed_time": "0:25:24", "remaining_time": "0:41:09"}
|
||||||
|
{"current_steps": 400, "total_steps": 1022, "loss": 1.1945, "learning_rate": 7.6368608286087e-06, "epoch": 0.3913894324853229, "percentage": 39.14, "elapsed_time": "0:26:01", "remaining_time": "0:40:28"}
|
||||||
|
{"current_steps": 410, "total_steps": 1022, "loss": 1.1813, "learning_rate": 7.490125184592607e-06, "epoch": 0.40117416829745595, "percentage": 40.12, "elapsed_time": "0:26:38", "remaining_time": "0:39:46"}
|
||||||
|
{"current_steps": 420, "total_steps": 1022, "loss": 1.1996, "learning_rate": 7.340479844626516e-06, "epoch": 0.410958904109589, "percentage": 41.1, "elapsed_time": "0:27:17", "remaining_time": "0:39:07"}
|
||||||
|
{"current_steps": 430, "total_steps": 1022, "loss": 1.193, "learning_rate": 7.188099668369015e-06, "epoch": 0.4207436399217221, "percentage": 42.07, "elapsed_time": "0:27:55", "remaining_time": "0:38:26"}
|
||||||
|
{"current_steps": 440, "total_steps": 1022, "loss": 1.182, "learning_rate": 7.033162711118077e-06, "epoch": 0.43052837573385516, "percentage": 43.05, "elapsed_time": "0:28:34", "remaining_time": "0:37:47"}
|
||||||
|
{"current_steps": 450, "total_steps": 1022, "loss": 1.1781, "learning_rate": 6.8758500157545185e-06, "epoch": 0.44031311154598823, "percentage": 44.03, "elapsed_time": "0:29:15", "remaining_time": "0:37:12"}
|
||||||
|
{"current_steps": 460, "total_steps": 1022, "loss": 1.1613, "learning_rate": 6.716345401194519e-06, "epoch": 0.4500978473581213, "percentage": 45.01, "elapsed_time": "0:29:56", "remaining_time": "0:36:35"}
|
||||||
|
{"current_steps": 470, "total_steps": 1022, "loss": 1.1798, "learning_rate": 6.554835247598347e-06, "epoch": 0.4598825831702544, "percentage": 45.99, "elapsed_time": "0:30:38", "remaining_time": "0:35:59"}
|
||||||
|
{"current_steps": 480, "total_steps": 1022, "loss": 1.181, "learning_rate": 6.391508278586287e-06, "epoch": 0.46966731898238745, "percentage": 46.97, "elapsed_time": "0:31:18", "remaining_time": "0:35:20"}
|
||||||
|
{"current_steps": 490, "total_steps": 1022, "loss": 1.1887, "learning_rate": 6.226555340716258e-06, "epoch": 0.4794520547945205, "percentage": 47.95, "elapsed_time": "0:31:58", "remaining_time": "0:34:43"}
|
||||||
|
{"current_steps": 500, "total_steps": 1022, "loss": 1.1714, "learning_rate": 6.060169180480776e-06, "epoch": 0.4892367906066536, "percentage": 48.92, "elapsed_time": "0:32:44", "remaining_time": "0:34:10"}
|
||||||
|
{"current_steps": 510, "total_steps": 1022, "loss": 1.1818, "learning_rate": 5.8925442190838735e-06, "epoch": 0.49902152641878667, "percentage": 49.9, "elapsed_time": "0:33:23", "remaining_time": "0:33:31"}
|
||||||
|
{"current_steps": 520, "total_steps": 1022, "loss": 1.1766, "learning_rate": 5.723876325261109e-06, "epoch": 0.5088062622309197, "percentage": 50.88, "elapsed_time": "0:34:03", "remaining_time": "0:32:53"}
|
||||||
|
{"current_steps": 530, "total_steps": 1022, "loss": 1.188, "learning_rate": 5.554362586408164e-06, "epoch": 0.5185909980430529, "percentage": 51.86, "elapsed_time": "0:34:42", "remaining_time": "0:32:13"}
|
||||||
|
{"current_steps": 540, "total_steps": 1022, "loss": 1.1793, "learning_rate": 5.3842010782854306e-06, "epoch": 0.5283757338551859, "percentage": 52.84, "elapsed_time": "0:35:25", "remaining_time": "0:31:36"}
|
||||||
|
{"current_steps": 550, "total_steps": 1022, "loss": 1.1734, "learning_rate": 5.2135906335677075e-06, "epoch": 0.538160469667319, "percentage": 53.82, "elapsed_time": "0:36:02", "remaining_time": "0:30:55"}
|
||||||
|
{"current_steps": 560, "total_steps": 1022, "loss": 1.169, "learning_rate": 5.0427306095094365e-06, "epoch": 0.547945205479452, "percentage": 54.79, "elapsed_time": "0:36:39", "remaining_time": "0:30:14"}
|
||||||
|
{"current_steps": 570, "total_steps": 1022, "loss": 1.1856, "learning_rate": 4.871820654996985e-06, "epoch": 0.5577299412915852, "percentage": 55.77, "elapsed_time": "0:37:19", "remaining_time": "0:29:35"}
|
||||||
|
{"current_steps": 580, "total_steps": 1022, "loss": 1.1662, "learning_rate": 4.701060477260152e-06, "epoch": 0.5675146771037182, "percentage": 56.75, "elapsed_time": "0:37:56", "remaining_time": "0:28:54"}
|
||||||
|
{"current_steps": 590, "total_steps": 1022, "loss": 1.1786, "learning_rate": 4.5306496085154905e-06, "epoch": 0.5772994129158513, "percentage": 57.73, "elapsed_time": "0:38:36", "remaining_time": "0:28:16"}
|
||||||
|
{"current_steps": 600, "total_steps": 1022, "loss": 1.1516, "learning_rate": 4.360787172814148e-06, "epoch": 0.5870841487279843, "percentage": 58.71, "elapsed_time": "0:39:14", "remaining_time": "0:27:36"}
|
||||||
|
{"current_steps": 610, "total_steps": 1022, "loss": 1.175, "learning_rate": 4.191671653366638e-06, "epoch": 0.5968688845401174, "percentage": 59.69, "elapsed_time": "0:39:51", "remaining_time": "0:26:55"}
|
||||||
|
{"current_steps": 620, "total_steps": 1022, "loss": 1.1656, "learning_rate": 4.02350066061643e-06, "epoch": 0.6066536203522505, "percentage": 60.67, "elapsed_time": "0:40:29", "remaining_time": "0:26:15"}
|
||||||
|
{"current_steps": 630, "total_steps": 1022, "loss": 1.1655, "learning_rate": 3.85647070133336e-06, "epoch": 0.6164383561643836, "percentage": 61.64, "elapsed_time": "0:41:06", "remaining_time": "0:25:34"}
|
||||||
|
{"current_steps": 640, "total_steps": 1022, "loss": 1.1572, "learning_rate": 3.69077694899668e-06, "epoch": 0.6262230919765166, "percentage": 62.62, "elapsed_time": "0:41:42", "remaining_time": "0:24:53"}
|
||||||
|
{"current_steps": 650, "total_steps": 1022, "loss": 1.1707, "learning_rate": 3.5266130157360557e-06, "epoch": 0.6360078277886497, "percentage": 63.6, "elapsed_time": "0:42:21", "remaining_time": "0:24:14"}
|
||||||
|
{"current_steps": 660, "total_steps": 1022, "loss": 1.1619, "learning_rate": 3.3641707260969724e-06, "epoch": 0.6457925636007827, "percentage": 64.58, "elapsed_time": "0:42:59", "remaining_time": "0:23:34"}
|
||||||
|
{"current_steps": 670, "total_steps": 1022, "loss": 1.1681, "learning_rate": 3.2036398928949475e-06, "epoch": 0.6555772994129159, "percentage": 65.56, "elapsed_time": "0:43:38", "remaining_time": "0:22:55"}
|
||||||
|
{"current_steps": 680, "total_steps": 1022, "loss": 1.1578, "learning_rate": 3.0452080954204133e-06, "epoch": 0.6653620352250489, "percentage": 66.54, "elapsed_time": "0:44:16", "remaining_time": "0:22:16"}
|
||||||
|
{"current_steps": 690, "total_steps": 1022, "loss": 1.166, "learning_rate": 2.8890604602534777e-06, "epoch": 0.675146771037182, "percentage": 67.51, "elapsed_time": "0:44:54", "remaining_time": "0:21:36"}
|
||||||
|
{"current_steps": 700, "total_steps": 1022, "loss": 1.156, "learning_rate": 2.735379444944655e-06, "epoch": 0.684931506849315, "percentage": 68.49, "elapsed_time": "0:45:32", "remaining_time": "0:20:56"}
|
||||||
|
{"current_steps": 710, "total_steps": 1022, "loss": 1.1498, "learning_rate": 2.5843446248143308e-06, "epoch": 0.6947162426614482, "percentage": 69.47, "elapsed_time": "0:46:09", "remaining_time": "0:20:17"}
|
||||||
|
{"current_steps": 720, "total_steps": 1022, "loss": 1.1414, "learning_rate": 2.436132483120121e-06, "epoch": 0.7045009784735812, "percentage": 70.45, "elapsed_time": "0:46:44", "remaining_time": "0:19:36"}
|
||||||
|
{"current_steps": 730, "total_steps": 1022, "loss": 1.1494, "learning_rate": 2.290916204837262e-06, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:47:22", "remaining_time": "0:18:57"}
|
||||||
|
{"current_steps": 740, "total_steps": 1022, "loss": 1.1532, "learning_rate": 2.148865474293036e-06, "epoch": 0.7240704500978473, "percentage": 72.41, "elapsed_time": "0:48:02", "remaining_time": "0:18:18"}
|
||||||
|
{"current_steps": 750, "total_steps": 1022, "loss": 1.1524, "learning_rate": 2.010146276891675e-06, "epoch": 0.7338551859099804, "percentage": 73.39, "elapsed_time": "0:48:40", "remaining_time": "0:17:39"}
|
||||||
|
{"current_steps": 760, "total_steps": 1022, "loss": 1.1553, "learning_rate": 1.8749207051614448e-06, "epoch": 0.7436399217221135, "percentage": 74.36, "elapsed_time": "0:49:19", "remaining_time": "0:17:00"}
|
||||||
|
{"current_steps": 770, "total_steps": 1022, "loss": 1.1493, "learning_rate": 1.743346769350519e-06, "epoch": 0.7534246575342466, "percentage": 75.34, "elapsed_time": "0:49:56", "remaining_time": "0:16:20"}
|
||||||
|
{"current_steps": 780, "total_steps": 1022, "loss": 1.1544, "learning_rate": 1.6155782127929787e-06, "epoch": 0.7632093933463796, "percentage": 76.32, "elapsed_time": "0:50:37", "remaining_time": "0:15:42"}
|
||||||
|
{"current_steps": 790, "total_steps": 1022, "loss": 1.169, "learning_rate": 1.4917643322606668e-06, "epoch": 0.7729941291585127, "percentage": 77.3, "elapsed_time": "0:51:13", "remaining_time": "0:15:02"}
|
||||||
|
{"current_steps": 800, "total_steps": 1022, "loss": 1.1406, "learning_rate": 1.3720498035108393e-06, "epoch": 0.7827788649706457, "percentage": 78.28, "elapsed_time": "0:51:51", "remaining_time": "0:14:23"}
|
||||||
|
{"current_steps": 810, "total_steps": 1022, "loss": 1.1464, "learning_rate": 1.256574512233426e-06, "epoch": 0.7925636007827789, "percentage": 79.26, "elapsed_time": "0:52:30", "remaining_time": "0:13:44"}
|
||||||
|
{"current_steps": 820, "total_steps": 1022, "loss": 1.1682, "learning_rate": 1.1454733905954679e-06, "epoch": 0.8023483365949119, "percentage": 80.23, "elapsed_time": "0:53:09", "remaining_time": "0:13:05"}
|
||||||
|
{"current_steps": 830, "total_steps": 1022, "loss": 1.1514, "learning_rate": 1.0388762595737012e-06, "epoch": 0.812133072407045, "percentage": 81.21, "elapsed_time": "0:53:45", "remaining_time": "0:12:26"}
|
||||||
|
{"current_steps": 840, "total_steps": 1022, "loss": 1.1381, "learning_rate": 9.36907677259562e-07, "epoch": 0.821917808219178, "percentage": 82.19, "elapsed_time": "0:54:23", "remaining_time": "0:11:47"}
|
||||||
|
{"current_steps": 850, "total_steps": 1022, "loss": 1.1544, "learning_rate": 8.396867933138031e-07, "epoch": 0.8317025440313112, "percentage": 83.17, "elapsed_time": "0:55:03", "remaining_time": "0:11:08"}
|
||||||
|
{"current_steps": 860, "total_steps": 1022, "loss": 1.1572, "learning_rate": 7.473272097408657e-07, "epoch": 0.8414872798434442, "percentage": 84.15, "elapsed_time": "0:55:41", "remaining_time": "0:10:29"}
|
||||||
|
{"current_steps": 870, "total_steps": 1022, "loss": 1.1645, "learning_rate": 6.599368481456237e-07, "epoch": 0.8512720156555773, "percentage": 85.13, "elapsed_time": "0:56:19", "remaining_time": "0:09:50"}
|
||||||
|
{"current_steps": 880, "total_steps": 1022, "loss": 1.1402, "learning_rate": 5.776178236276642e-07, "epoch": 0.8610567514677103, "percentage": 86.11, "elapsed_time": "0:56:56", "remaining_time": "0:09:11"}
|
||||||
|
{"current_steps": 890, "total_steps": 1022, "loss": 1.1434, "learning_rate": 5.004663254604125e-07, "epoch": 0.8708414872798435, "percentage": 87.08, "elapsed_time": "0:57:32", "remaining_time": "0:08:31"}
|
||||||
|
{"current_steps": 900, "total_steps": 1022, "loss": 1.1404, "learning_rate": 4.28572504694566e-07, "epoch": 0.8806262230919765, "percentage": 88.06, "elapsed_time": "0:58:09", "remaining_time": "0:07:53"}
|
||||||
|
{"current_steps": 910, "total_steps": 1022, "loss": 1.1577, "learning_rate": 3.620203688171381e-07, "epoch": 0.8904109589041096, "percentage": 89.04, "elapsed_time": "0:58:48", "remaining_time": "0:07:14"}
|
||||||
|
{"current_steps": 920, "total_steps": 1022, "loss": 1.1427, "learning_rate": 3.0088768358923545e-07, "epoch": 0.9001956947162426, "percentage": 90.02, "elapsed_time": "0:59:26", "remaining_time": "0:06:35"}
|
||||||
|
{"current_steps": 930, "total_steps": 1022, "loss": 1.1373, "learning_rate": 2.4524588217723746e-07, "epoch": 0.9099804305283757, "percentage": 91.0, "elapsed_time": "1:00:04", "remaining_time": "0:05:56"}
|
||||||
|
{"current_steps": 940, "total_steps": 1022, "loss": 1.1565, "learning_rate": 1.9515998168358809e-07, "epoch": 0.9197651663405088, "percentage": 91.98, "elapsed_time": "1:00:42", "remaining_time": "0:05:17"}
|
||||||
|
{"current_steps": 950, "total_steps": 1022, "loss": 1.1409, "learning_rate": 1.506885071747033e-07, "epoch": 0.9295499021526419, "percentage": 92.95, "elapsed_time": "1:01:22", "remaining_time": "0:04:39"}
|
||||||
|
{"current_steps": 960, "total_steps": 1022, "loss": 1.1592, "learning_rate": 1.1188342329479962e-07, "epoch": 0.9393346379647749, "percentage": 93.93, "elapsed_time": "1:01:59", "remaining_time": "0:04:00"}
|
||||||
|
{"current_steps": 970, "total_steps": 1022, "loss": 1.1331, "learning_rate": 7.879007354552271e-08, "epoch": 0.949119373776908, "percentage": 94.91, "elapsed_time": "1:02:37", "remaining_time": "0:03:21"}
|
||||||
|
{"current_steps": 980, "total_steps": 1022, "loss": 1.1588, "learning_rate": 5.14471273023448e-08, "epoch": 0.958904109589041, "percentage": 95.89, "elapsed_time": "1:03:16", "remaining_time": "0:02:42"}
|
||||||
|
{"current_steps": 990, "total_steps": 1022, "loss": 1.1482, "learning_rate": 2.9886534629638975e-08, "epoch": 0.9686888454011742, "percentage": 96.87, "elapsed_time": "1:03:50", "remaining_time": "0:02:03"}
|
||||||
|
{"current_steps": 1000, "total_steps": 1022, "loss": 1.17, "learning_rate": 1.4133488947225548e-08, "epoch": 0.9784735812133072, "percentage": 97.85, "elapsed_time": "1:04:29", "remaining_time": "0:01:25"}
|
||||||
|
{"current_steps": 1010, "total_steps": 1022, "loss": 1.155, "learning_rate": 4.2063975920153545e-09, "epoch": 0.9882583170254403, "percentage": 98.83, "elapsed_time": "1:06:16", "remaining_time": "0:00:47"}
|
||||||
|
{"current_steps": 1020, "total_steps": 1022, "loss": 1.1449, "learning_rate": 1.168603091489251e-10, "epoch": 0.9980430528375733, "percentage": 99.8, "elapsed_time": "1:06:54", "remaining_time": "0:00:07"}
|
||||||
|
{"current_steps": 1022, "total_steps": 1022, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:08:10", "remaining_time": "0:00:00"}
|
||||||
756
trainer_state.json
Normal file
756
trainer_state.json
Normal file
@@ -0,0 +1,756 @@
|
|||||||
|
{
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 1022,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.009784735812133072,
|
||||||
|
"grad_norm": 4.04649150142379,
|
||||||
|
"learning_rate": 9.70873786407767e-07,
|
||||||
|
"loss": 1.7598,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.019569471624266144,
|
||||||
|
"grad_norm": 1.8898281767230303,
|
||||||
|
"learning_rate": 1.941747572815534e-06,
|
||||||
|
"loss": 1.6964,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.029354207436399216,
|
||||||
|
"grad_norm": 1.483970324647816,
|
||||||
|
"learning_rate": 2.912621359223301e-06,
|
||||||
|
"loss": 1.611,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.03913894324853229,
|
||||||
|
"grad_norm": 1.3044067583298566,
|
||||||
|
"learning_rate": 3.883495145631068e-06,
|
||||||
|
"loss": 1.4946,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.04892367906066536,
|
||||||
|
"grad_norm": 1.1307579978177575,
|
||||||
|
"learning_rate": 4.854368932038836e-06,
|
||||||
|
"loss": 1.4397,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.05870841487279843,
|
||||||
|
"grad_norm": 1.1230632491576633,
|
||||||
|
"learning_rate": 5.825242718446602e-06,
|
||||||
|
"loss": 1.3915,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.0684931506849315,
|
||||||
|
"grad_norm": 1.2171487481951635,
|
||||||
|
"learning_rate": 6.79611650485437e-06,
|
||||||
|
"loss": 1.3412,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.07827788649706457,
|
||||||
|
"grad_norm": 1.1602684245071337,
|
||||||
|
"learning_rate": 7.766990291262136e-06,
|
||||||
|
"loss": 1.3442,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.08806262230919765,
|
||||||
|
"grad_norm": 1.1297981589874249,
|
||||||
|
"learning_rate": 8.737864077669904e-06,
|
||||||
|
"loss": 1.307,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.09784735812133072,
|
||||||
|
"grad_norm": 1.1989099168675559,
|
||||||
|
"learning_rate": 9.708737864077671e-06,
|
||||||
|
"loss": 1.3041,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10763209393346379,
|
||||||
|
"grad_norm": 1.0923068630227757,
|
||||||
|
"learning_rate": 9.998568523945896e-06,
|
||||||
|
"loss": 1.2911,
|
||||||
|
"step": 110
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.11741682974559686,
|
||||||
|
"grad_norm": 1.2597514623600858,
|
||||||
|
"learning_rate": 9.991559185756013e-06,
|
||||||
|
"loss": 1.2871,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.12720156555772993,
|
||||||
|
"grad_norm": 1.137541898001787,
|
||||||
|
"learning_rate": 9.978717241383576e-06,
|
||||||
|
"loss": 1.261,
|
||||||
|
"step": 130
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.136986301369863,
|
||||||
|
"grad_norm": 1.1658887896761427,
|
||||||
|
"learning_rate": 9.960057696561538e-06,
|
||||||
|
"loss": 1.2554,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.14677103718199608,
|
||||||
|
"grad_norm": 1.2229261479256421,
|
||||||
|
"learning_rate": 9.935602354853163e-06,
|
||||||
|
"loss": 1.2542,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.15655577299412915,
|
||||||
|
"grad_norm": 1.1243006143779628,
|
||||||
|
"learning_rate": 9.905379792174697e-06,
|
||||||
|
"loss": 1.2521,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16634050880626222,
|
||||||
|
"grad_norm": 1.0968643854275186,
|
||||||
|
"learning_rate": 9.869425323404593e-06,
|
||||||
|
"loss": 1.2677,
|
||||||
|
"step": 170
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1761252446183953,
|
||||||
|
"grad_norm": 1.1045669372583213,
|
||||||
|
"learning_rate": 9.82778096111829e-06,
|
||||||
|
"loss": 1.2511,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.18590998043052837,
|
||||||
|
"grad_norm": 1.1112118778947822,
|
||||||
|
"learning_rate": 9.780495366496772e-06,
|
||||||
|
"loss": 1.2446,
|
||||||
|
"step": 190
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.19569471624266144,
|
||||||
|
"grad_norm": 1.0826613870591981,
|
||||||
|
"learning_rate": 9.727623792466285e-06,
|
||||||
|
"loss": 1.2314,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2054794520547945,
|
||||||
|
"grad_norm": 1.098249884945961,
|
||||||
|
"learning_rate": 9.669228019135625e-06,
|
||||||
|
"loss": 1.2458,
|
||||||
|
"step": 210
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.21526418786692758,
|
||||||
|
"grad_norm": 1.1612733633383774,
|
||||||
|
"learning_rate": 9.605376281606472e-06,
|
||||||
|
"loss": 1.2237,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.22504892367906065,
|
||||||
|
"grad_norm": 1.125936251992049,
|
||||||
|
"learning_rate": 9.53614319024108e-06,
|
||||||
|
"loss": 1.2146,
|
||||||
|
"step": 230
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.23483365949119372,
|
||||||
|
"grad_norm": 1.1467535473229693,
|
||||||
|
"learning_rate": 9.461609643480541e-06,
|
||||||
|
"loss": 1.2138,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2446183953033268,
|
||||||
|
"grad_norm": 1.0542912347811166,
|
||||||
|
"learning_rate": 9.381862733315444e-06,
|
||||||
|
"loss": 1.2111,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.25440313111545987,
|
||||||
|
"grad_norm": 1.149152919711082,
|
||||||
|
"learning_rate": 9.296995643519432e-06,
|
||||||
|
"loss": 1.2127,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.26418786692759294,
|
||||||
|
"grad_norm": 1.0920081819134964,
|
||||||
|
"learning_rate": 9.207107540764519e-06,
|
||||||
|
"loss": 1.2338,
|
||||||
|
"step": 270
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.273972602739726,
|
||||||
|
"grad_norm": 1.1780253225746746,
|
||||||
|
"learning_rate": 9.112303458745462e-06,
|
||||||
|
"loss": 1.2054,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2837573385518591,
|
||||||
|
"grad_norm": 1.0205557268076189,
|
||||||
|
"learning_rate": 9.012694175448526e-06,
|
||||||
|
"loss": 1.2223,
|
||||||
|
"step": 290
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.29354207436399216,
|
||||||
|
"grad_norm": 1.182238809951801,
|
||||||
|
"learning_rate": 8.90839608370809e-06,
|
||||||
|
"loss": 1.2137,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.30332681017612523,
|
||||||
|
"grad_norm": 1.0623824819302699,
|
||||||
|
"learning_rate": 8.799531055202332e-06,
|
||||||
|
"loss": 1.2021,
|
||||||
|
"step": 310
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3131115459882583,
|
||||||
|
"grad_norm": 1.103614217675967,
|
||||||
|
"learning_rate": 8.686226298046938e-06,
|
||||||
|
"loss": 1.2107,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.32289628180039137,
|
||||||
|
"grad_norm": 1.0562421868073395,
|
||||||
|
"learning_rate": 8.568614208153181e-06,
|
||||||
|
"loss": 1.2051,
|
||||||
|
"step": 330
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.33268101761252444,
|
||||||
|
"grad_norm": 1.061840954937612,
|
||||||
|
"learning_rate": 8.446832214524132e-06,
|
||||||
|
"loss": 1.1906,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3424657534246575,
|
||||||
|
"grad_norm": 1.1618629276892396,
|
||||||
|
"learning_rate": 8.321022618669706e-06,
|
||||||
|
"loss": 1.2189,
|
||||||
|
"step": 350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3522504892367906,
|
||||||
|
"grad_norm": 0.9952732308566709,
|
||||||
|
"learning_rate": 8.191332428328227e-06,
|
||||||
|
"loss": 1.2056,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.36203522504892366,
|
||||||
|
"grad_norm": 1.08417836514905,
|
||||||
|
"learning_rate": 8.057913185688789e-06,
|
||||||
|
"loss": 1.2058,
|
||||||
|
"step": 370
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.37181996086105673,
|
||||||
|
"grad_norm": 1.0664180337103972,
|
||||||
|
"learning_rate": 7.920920790315139e-06,
|
||||||
|
"loss": 1.1787,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3816046966731898,
|
||||||
|
"grad_norm": 1.0237212990645388,
|
||||||
|
"learning_rate": 7.780515316978003e-06,
|
||||||
|
"loss": 1.1868,
|
||||||
|
"step": 390
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3913894324853229,
|
||||||
|
"grad_norm": 1.0196131058576328,
|
||||||
|
"learning_rate": 7.6368608286087e-06,
|
||||||
|
"loss": 1.1945,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.40117416829745595,
|
||||||
|
"grad_norm": 1.095727756369159,
|
||||||
|
"learning_rate": 7.490125184592607e-06,
|
||||||
|
"loss": 1.1813,
|
||||||
|
"step": 410
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.410958904109589,
|
||||||
|
"grad_norm": 1.0260192699123412,
|
||||||
|
"learning_rate": 7.340479844626516e-06,
|
||||||
|
"loss": 1.1996,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4207436399217221,
|
||||||
|
"grad_norm": 1.0159524740262653,
|
||||||
|
"learning_rate": 7.188099668369015e-06,
|
||||||
|
"loss": 1.193,
|
||||||
|
"step": 430
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.43052837573385516,
|
||||||
|
"grad_norm": 1.1094365729981088,
|
||||||
|
"learning_rate": 7.033162711118077e-06,
|
||||||
|
"loss": 1.182,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.44031311154598823,
|
||||||
|
"grad_norm": 1.0230643234668957,
|
||||||
|
"learning_rate": 6.8758500157545185e-06,
|
||||||
|
"loss": 1.1781,
|
||||||
|
"step": 450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4500978473581213,
|
||||||
|
"grad_norm": 1.0282046095119801,
|
||||||
|
"learning_rate": 6.716345401194519e-06,
|
||||||
|
"loss": 1.1613,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4598825831702544,
|
||||||
|
"grad_norm": 1.0383674282070607,
|
||||||
|
"learning_rate": 6.554835247598347e-06,
|
||||||
|
"loss": 1.1798,
|
||||||
|
"step": 470
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.46966731898238745,
|
||||||
|
"grad_norm": 0.9837704553579479,
|
||||||
|
"learning_rate": 6.391508278586287e-06,
|
||||||
|
"loss": 1.181,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4794520547945205,
|
||||||
|
"grad_norm": 1.0580246864370755,
|
||||||
|
"learning_rate": 6.226555340716258e-06,
|
||||||
|
"loss": 1.1887,
|
||||||
|
"step": 490
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4892367906066536,
|
||||||
|
"grad_norm": 1.017013165650618,
|
||||||
|
"learning_rate": 6.060169180480776e-06,
|
||||||
|
"loss": 1.1714,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.49902152641878667,
|
||||||
|
"grad_norm": 1.0072748086969616,
|
||||||
|
"learning_rate": 5.8925442190838735e-06,
|
||||||
|
"loss": 1.1818,
|
||||||
|
"step": 510
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5088062622309197,
|
||||||
|
"grad_norm": 1.0791337064960191,
|
||||||
|
"learning_rate": 5.723876325261109e-06,
|
||||||
|
"loss": 1.1766,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5185909980430529,
|
||||||
|
"grad_norm": 1.0401219276204419,
|
||||||
|
"learning_rate": 5.554362586408164e-06,
|
||||||
|
"loss": 1.188,
|
||||||
|
"step": 530
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5283757338551859,
|
||||||
|
"grad_norm": 1.04026227937617,
|
||||||
|
"learning_rate": 5.3842010782854306e-06,
|
||||||
|
"loss": 1.1793,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.538160469667319,
|
||||||
|
"grad_norm": 1.17417294090351,
|
||||||
|
"learning_rate": 5.2135906335677075e-06,
|
||||||
|
"loss": 1.1734,
|
||||||
|
"step": 550
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.547945205479452,
|
||||||
|
"grad_norm": 1.014702815772571,
|
||||||
|
"learning_rate": 5.0427306095094365e-06,
|
||||||
|
"loss": 1.169,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5577299412915852,
|
||||||
|
"grad_norm": 1.0275982848917589,
|
||||||
|
"learning_rate": 4.871820654996985e-06,
|
||||||
|
"loss": 1.1856,
|
||||||
|
"step": 570
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5675146771037182,
|
||||||
|
"grad_norm": 1.0530785296526888,
|
||||||
|
"learning_rate": 4.701060477260152e-06,
|
||||||
|
"loss": 1.1662,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5772994129158513,
|
||||||
|
"grad_norm": 1.023986668412493,
|
||||||
|
"learning_rate": 4.5306496085154905e-06,
|
||||||
|
"loss": 1.1786,
|
||||||
|
"step": 590
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5870841487279843,
|
||||||
|
"grad_norm": 1.0639406354816834,
|
||||||
|
"learning_rate": 4.360787172814148e-06,
|
||||||
|
"loss": 1.1516,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5968688845401174,
|
||||||
|
"grad_norm": 0.9500520632946152,
|
||||||
|
"learning_rate": 4.191671653366638e-06,
|
||||||
|
"loss": 1.175,
|
||||||
|
"step": 610
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6066536203522505,
|
||||||
|
"grad_norm": 0.984391446028831,
|
||||||
|
"learning_rate": 4.02350066061643e-06,
|
||||||
|
"loss": 1.1656,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6164383561643836,
|
||||||
|
"grad_norm": 1.005147372886877,
|
||||||
|
"learning_rate": 3.85647070133336e-06,
|
||||||
|
"loss": 1.1655,
|
||||||
|
"step": 630
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6262230919765166,
|
||||||
|
"grad_norm": 1.015642402945713,
|
||||||
|
"learning_rate": 3.69077694899668e-06,
|
||||||
|
"loss": 1.1572,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6360078277886497,
|
||||||
|
"grad_norm": 1.0201007215429072,
|
||||||
|
"learning_rate": 3.5266130157360557e-06,
|
||||||
|
"loss": 1.1707,
|
||||||
|
"step": 650
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6457925636007827,
|
||||||
|
"grad_norm": 0.9956935095703923,
|
||||||
|
"learning_rate": 3.3641707260969724e-06,
|
||||||
|
"loss": 1.1619,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6555772994129159,
|
||||||
|
"grad_norm": 0.9644023257276766,
|
||||||
|
"learning_rate": 3.2036398928949475e-06,
|
||||||
|
"loss": 1.1681,
|
||||||
|
"step": 670
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6653620352250489,
|
||||||
|
"grad_norm": 1.029502516764066,
|
||||||
|
"learning_rate": 3.0452080954204133e-06,
|
||||||
|
"loss": 1.1578,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.675146771037182,
|
||||||
|
"grad_norm": 0.9452739847782414,
|
||||||
|
"learning_rate": 2.8890604602534777e-06,
|
||||||
|
"loss": 1.166,
|
||||||
|
"step": 690
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.684931506849315,
|
||||||
|
"grad_norm": 0.9549493201312858,
|
||||||
|
"learning_rate": 2.735379444944655e-06,
|
||||||
|
"loss": 1.156,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6947162426614482,
|
||||||
|
"grad_norm": 0.9808822395078565,
|
||||||
|
"learning_rate": 2.5843446248143308e-06,
|
||||||
|
"loss": 1.1498,
|
||||||
|
"step": 710
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7045009784735812,
|
||||||
|
"grad_norm": 0.9725284687123298,
|
||||||
|
"learning_rate": 2.436132483120121e-06,
|
||||||
|
"loss": 1.1414,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7142857142857143,
|
||||||
|
"grad_norm": 1.0146025684804074,
|
||||||
|
"learning_rate": 2.290916204837262e-06,
|
||||||
|
"loss": 1.1494,
|
||||||
|
"step": 730
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7240704500978473,
|
||||||
|
"grad_norm": 0.9942038199138818,
|
||||||
|
"learning_rate": 2.148865474293036e-06,
|
||||||
|
"loss": 1.1532,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7338551859099804,
|
||||||
|
"grad_norm": 0.9634937304590753,
|
||||||
|
"learning_rate": 2.010146276891675e-06,
|
||||||
|
"loss": 1.1524,
|
||||||
|
"step": 750
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7436399217221135,
|
||||||
|
"grad_norm": 0.9646041486253625,
|
||||||
|
"learning_rate": 1.8749207051614448e-06,
|
||||||
|
"loss": 1.1553,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7534246575342466,
|
||||||
|
"grad_norm": 0.9645946065696461,
|
||||||
|
"learning_rate": 1.743346769350519e-06,
|
||||||
|
"loss": 1.1493,
|
||||||
|
"step": 770
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7632093933463796,
|
||||||
|
"grad_norm": 0.9987538300542498,
|
||||||
|
"learning_rate": 1.6155782127929787e-06,
|
||||||
|
"loss": 1.1544,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7729941291585127,
|
||||||
|
"grad_norm": 0.9706627230186383,
|
||||||
|
"learning_rate": 1.4917643322606668e-06,
|
||||||
|
"loss": 1.169,
|
||||||
|
"step": 790
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7827788649706457,
|
||||||
|
"grad_norm": 0.995763457209775,
|
||||||
|
"learning_rate": 1.3720498035108393e-06,
|
||||||
|
"loss": 1.1406,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7925636007827789,
|
||||||
|
"grad_norm": 0.9780490169698375,
|
||||||
|
"learning_rate": 1.256574512233426e-06,
|
||||||
|
"loss": 1.1464,
|
||||||
|
"step": 810
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8023483365949119,
|
||||||
|
"grad_norm": 1.058131773284045,
|
||||||
|
"learning_rate": 1.1454733905954679e-06,
|
||||||
|
"loss": 1.1682,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.812133072407045,
|
||||||
|
"grad_norm": 0.9663337521771117,
|
||||||
|
"learning_rate": 1.0388762595737012e-06,
|
||||||
|
"loss": 1.1514,
|
||||||
|
"step": 830
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.821917808219178,
|
||||||
|
"grad_norm": 1.0060251032305096,
|
||||||
|
"learning_rate": 9.36907677259562e-07,
|
||||||
|
"loss": 1.1381,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8317025440313112,
|
||||||
|
"grad_norm": 1.0006702241602894,
|
||||||
|
"learning_rate": 8.396867933138031e-07,
|
||||||
|
"loss": 1.1544,
|
||||||
|
"step": 850
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8414872798434442,
|
||||||
|
"grad_norm": 0.9655200991402652,
|
||||||
|
"learning_rate": 7.473272097408657e-07,
|
||||||
|
"loss": 1.1572,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8512720156555773,
|
||||||
|
"grad_norm": 1.0010147904810007,
|
||||||
|
"learning_rate": 6.599368481456237e-07,
|
||||||
|
"loss": 1.1645,
|
||||||
|
"step": 870
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8610567514677103,
|
||||||
|
"grad_norm": 0.9615849194888773,
|
||||||
|
"learning_rate": 5.776178236276642e-07,
|
||||||
|
"loss": 1.1402,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8708414872798435,
|
||||||
|
"grad_norm": 0.9899952335825283,
|
||||||
|
"learning_rate": 5.004663254604125e-07,
|
||||||
|
"loss": 1.1434,
|
||||||
|
"step": 890
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8806262230919765,
|
||||||
|
"grad_norm": 0.9522480445427419,
|
||||||
|
"learning_rate": 4.28572504694566e-07,
|
||||||
|
"loss": 1.1404,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8904109589041096,
|
||||||
|
"grad_norm": 0.974551459961046,
|
||||||
|
"learning_rate": 3.620203688171381e-07,
|
||||||
|
"loss": 1.1577,
|
||||||
|
"step": 910
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9001956947162426,
|
||||||
|
"grad_norm": 0.9668235111962397,
|
||||||
|
"learning_rate": 3.0088768358923545e-07,
|
||||||
|
"loss": 1.1427,
|
||||||
|
"step": 920
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9099804305283757,
|
||||||
|
"grad_norm": 1.0319353813022967,
|
||||||
|
"learning_rate": 2.4524588217723746e-07,
|
||||||
|
"loss": 1.1373,
|
||||||
|
"step": 930
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9197651663405088,
|
||||||
|
"grad_norm": 1.029861953702673,
|
||||||
|
"learning_rate": 1.9515998168358809e-07,
|
||||||
|
"loss": 1.1565,
|
||||||
|
"step": 940
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9295499021526419,
|
||||||
|
"grad_norm": 0.950517130129004,
|
||||||
|
"learning_rate": 1.506885071747033e-07,
|
||||||
|
"loss": 1.1409,
|
||||||
|
"step": 950
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9393346379647749,
|
||||||
|
"grad_norm": 0.9918632320485316,
|
||||||
|
"learning_rate": 1.1188342329479962e-07,
|
||||||
|
"loss": 1.1592,
|
||||||
|
"step": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.949119373776908,
|
||||||
|
"grad_norm": 0.9513450607234911,
|
||||||
|
"learning_rate": 7.879007354552271e-08,
|
||||||
|
"loss": 1.1331,
|
||||||
|
"step": 970
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.958904109589041,
|
||||||
|
"grad_norm": 0.9860328317263265,
|
||||||
|
"learning_rate": 5.14471273023448e-08,
|
||||||
|
"loss": 1.1588,
|
||||||
|
"step": 980
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9686888454011742,
|
||||||
|
"grad_norm": 0.9557954337884952,
|
||||||
|
"learning_rate": 2.9886534629638975e-08,
|
||||||
|
"loss": 1.1482,
|
||||||
|
"step": 990
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9784735812133072,
|
||||||
|
"grad_norm": 0.982073690453174,
|
||||||
|
"learning_rate": 1.4133488947225548e-08,
|
||||||
|
"loss": 1.17,
|
||||||
|
"step": 1000
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9882583170254403,
|
||||||
|
"grad_norm": 0.9769182862134684,
|
||||||
|
"learning_rate": 4.2063975920153545e-09,
|
||||||
|
"loss": 1.155,
|
||||||
|
"step": 1010
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9980430528375733,
|
||||||
|
"grad_norm": 0.9371852604717477,
|
||||||
|
"learning_rate": 1.168603091489251e-10,
|
||||||
|
"loss": 1.1449,
|
||||||
|
"step": 1020
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"step": 1022,
|
||||||
|
"total_flos": 1.3956152400113828e+18,
|
||||||
|
"train_loss": 1.210920991029758,
|
||||||
|
"train_runtime": 4090.7445,
|
||||||
|
"train_samples_per_second": 31.964,
|
||||||
|
"train_steps_per_second": 0.25
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 10,
|
||||||
|
"max_steps": 1022,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"save_steps": 1000,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 1.3956152400113828e+18,
|
||||||
|
"train_batch_size": 8,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2d0d3039a79154d69623c316fa5d2a313260013245a82d15fd3ccd5b0290bbca
|
||||||
|
size 6712
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user