初始化项目，由ModelHub XC社区提供模型
Model: AdaptLLM/remote-sensing-Qwen2-VL-2B-Instruct Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 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
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack 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
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* 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
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
130
README.md
Normal file
130
README.md
Normal file
@@ -0,0 +1,130 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen2-VL-2B-Instruct
|
||||||
|
tags:
|
||||||
|
- remote-sensing
|
||||||
|
datasets:
|
||||||
|
- AdaptLLM/remote-sensing-visual-instructions
|
||||||
|
---
|
||||||
|
# Adapting Multimodal Large Language Models to Domains via Post-Training (EMNLP 2025)
|
||||||
|
|
||||||
|
This repos contains the **remote sensing 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 correspoding training dataset is in [remote-sensing-visual-instructions](https://huggingface.co/datasets/AdaptLLM/remote-sensing-visual-instructions).
|
||||||
|
|
||||||
|
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/remote-sensing-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/remote-sensing-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 [remote-sensing-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/remote-sensing-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": 1.4819175628485427e+17,
|
||||||
|
"train_loss": 0.8990087810315583,
|
||||||
|
"train_runtime": 350.8438,
|
||||||
|
"train_samples_per_second": 103.861,
|
||||||
|
"train_steps_per_second": 0.812
|
||||||
|
}
|
||||||
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 sha256:7901956be7ababfff6d313d6d1df43d13863ff62df6af2f2d07401782307e143
|
||||||
|
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
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cb63a0a23eef3d5b01063a9880a1925a65aaf4d1591d519910ee3527852950a0
|
||||||
|
size 7029741
|
||||||
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": 1.4819175628485427e+17,
|
||||||
|
"train_loss": 0.8990087810315583,
|
||||||
|
"train_runtime": 350.8438,
|
||||||
|
"train_samples_per_second": 103.861,
|
||||||
|
"train_steps_per_second": 0.812
|
||||||
|
}
|
||||||
29
trainer_log.jsonl
Normal file
29
trainer_log.jsonl
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{"current_steps": 10, "total_steps": 285, "loss": 1.8558, "learning_rate": 3.448275862068966e-06, "epoch": 0.03508771929824561, "percentage": 3.51, "elapsed_time": "0:00:13", "remaining_time": "0:06:18"}
|
||||||
|
{"current_steps": 20, "total_steps": 285, "loss": 1.4458, "learning_rate": 6.896551724137932e-06, "epoch": 0.07017543859649122, "percentage": 7.02, "elapsed_time": "0:00:25", "remaining_time": "0:05:40"}
|
||||||
|
{"current_steps": 30, "total_steps": 285, "loss": 1.2409, "learning_rate": 9.999623509195724e-06, "epoch": 0.10526315789473684, "percentage": 10.53, "elapsed_time": "0:00:37", "remaining_time": "0:05:18"}
|
||||||
|
{"current_steps": 40, "total_steps": 285, "loss": 1.1153, "learning_rate": 9.9545131771389e-06, "epoch": 0.14035087719298245, "percentage": 14.04, "elapsed_time": "0:00:49", "remaining_time": "0:05:01"}
|
||||||
|
{"current_steps": 50, "total_steps": 285, "loss": 1.0284, "learning_rate": 9.834882355224261e-06, "epoch": 0.17543859649122806, "percentage": 17.54, "elapsed_time": "0:01:00", "remaining_time": "0:04:44"}
|
||||||
|
{"current_steps": 60, "total_steps": 285, "loss": 0.9903, "learning_rate": 9.64253040236608e-06, "epoch": 0.21052631578947367, "percentage": 21.05, "elapsed_time": "0:01:12", "remaining_time": "0:04:31"}
|
||||||
|
{"current_steps": 70, "total_steps": 285, "loss": 0.9464, "learning_rate": 9.380350470977033e-06, "epoch": 0.24561403508771928, "percentage": 24.56, "elapsed_time": "0:01:24", "remaining_time": "0:04:20"}
|
||||||
|
{"current_steps": 80, "total_steps": 285, "loss": 0.9232, "learning_rate": 9.052285991262975e-06, "epoch": 0.2807017543859649, "percentage": 28.07, "elapsed_time": "0:01:37", "remaining_time": "0:04:08"}
|
||||||
|
{"current_steps": 90, "total_steps": 285, "loss": 0.8927, "learning_rate": 8.663271358362064e-06, "epoch": 0.3157894736842105, "percentage": 31.58, "elapsed_time": "0:01:49", "remaining_time": "0:03:56"}
|
||||||
|
{"current_steps": 100, "total_steps": 285, "loss": 0.8748, "learning_rate": 8.219157714448957e-06, "epoch": 0.3508771929824561, "percentage": 35.09, "elapsed_time": "0:02:00", "remaining_time": "0:03:42"}
|
||||||
|
{"current_steps": 110, "total_steps": 285, "loss": 0.8712, "learning_rate": 7.726624942110233e-06, "epoch": 0.38596491228070173, "percentage": 38.6, "elapsed_time": "0:02:11", "remaining_time": "0:03:29"}
|
||||||
|
{"current_steps": 120, "total_steps": 285, "loss": 0.8413, "learning_rate": 7.193081192692639e-06, "epoch": 0.42105263157894735, "percentage": 42.11, "elapsed_time": "0:02:24", "remaining_time": "0:03:18"}
|
||||||
|
{"current_steps": 130, "total_steps": 285, "loss": 0.8245, "learning_rate": 6.626551460811316e-06, "epoch": 0.45614035087719296, "percentage": 45.61, "elapsed_time": "0:02:35", "remaining_time": "0:03:05"}
|
||||||
|
{"current_steps": 140, "total_steps": 285, "loss": 0.7995, "learning_rate": 6.035556880961093e-06, "epoch": 0.49122807017543857, "percentage": 49.12, "elapsed_time": "0:02:48", "remaining_time": "0:02:54"}
|
||||||
|
{"current_steps": 150, "total_steps": 285, "loss": 0.7919, "learning_rate": 5.4289865617222005e-06, "epoch": 0.5263157894736842, "percentage": 52.63, "elapsed_time": "0:02:59", "remaining_time": "0:02:41"}
|
||||||
|
{"current_steps": 160, "total_steps": 285, "loss": 0.794, "learning_rate": 4.815963885293206e-06, "epoch": 0.5614035087719298, "percentage": 56.14, "elapsed_time": "0:03:10", "remaining_time": "0:02:28"}
|
||||||
|
{"current_steps": 170, "total_steps": 285, "loss": 0.7713, "learning_rate": 4.205709283330694e-06, "epoch": 0.5964912280701754, "percentage": 59.65, "elapsed_time": "0:03:22", "remaining_time": "0:02:16"}
|
||||||
|
{"current_steps": 180, "total_steps": 285, "loss": 0.7775, "learning_rate": 3.6074015530747354e-06, "epoch": 0.631578947368421, "percentage": 63.16, "elapsed_time": "0:03:34", "remaining_time": "0:02:05"}
|
||||||
|
{"current_steps": 190, "total_steps": 285, "loss": 0.7515, "learning_rate": 3.0300397996947604e-06, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:03:46", "remaining_time": "0:01:53"}
|
||||||
|
{"current_steps": 200, "total_steps": 285, "loss": 0.765, "learning_rate": 2.482308081371413e-06, "epoch": 0.7017543859649122, "percentage": 70.18, "elapsed_time": "0:03:57", "remaining_time": "0:01:41"}
|
||||||
|
{"current_steps": 210, "total_steps": 285, "loss": 0.7528, "learning_rate": 1.972444792978373e-06, "epoch": 0.7368421052631579, "percentage": 73.68, "elapsed_time": "0:04:09", "remaining_time": "0:01:28"}
|
||||||
|
{"current_steps": 220, "total_steps": 285, "loss": 0.7396, "learning_rate": 1.508118752955136e-06, "epoch": 0.7719298245614035, "percentage": 77.19, "elapsed_time": "0:04:20", "remaining_time": "0:01:16"}
|
||||||
|
{"current_steps": 230, "total_steps": 285, "loss": 0.7408, "learning_rate": 1.0963138571395277e-06, "epoch": 0.8070175438596491, "percentage": 80.7, "elapsed_time": "0:04:32", "remaining_time": "0:01:05"}
|
||||||
|
{"current_steps": 240, "total_steps": 285, "loss": 0.7486, "learning_rate": 7.43224034473674e-07, "epoch": 0.8421052631578947, "percentage": 84.21, "elapsed_time": "0:04:44", "remaining_time": "0:00:53"}
|
||||||
|
{"current_steps": 250, "total_steps": 285, "loss": 0.7359, "learning_rate": 4.5416008454738813e-07, "epoch": 0.8771929824561403, "percentage": 87.72, "elapsed_time": "0:04:56", "remaining_time": "0:00:41"}
|
||||||
|
{"current_steps": 260, "total_steps": 285, "loss": 0.7375, "learning_rate": 2.3346979822903071e-07, "epoch": 0.9122807017543859, "percentage": 91.23, "elapsed_time": "0:05:08", "remaining_time": "0:00:29"}
|
||||||
|
{"current_steps": 270, "total_steps": 285, "loss": 0.7245, "learning_rate": 8.447256284391858e-08, "epoch": 0.9473684210526315, "percentage": 94.74, "elapsed_time": "0:05:19", "remaining_time": "0:00:17"}
|
||||||
|
{"current_steps": 280, "total_steps": 285, "loss": 0.7378, "learning_rate": 9.409435499254105e-09, "epoch": 0.9824561403508771, "percentage": 98.25, "elapsed_time": "0:05:32", "remaining_time": "0:00:05"}
|
||||||
|
{"current_steps": 285, "total_steps": 285, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:05:50", "remaining_time": "0:00:00"}
|
||||||
238
trainer_state.json
Normal file
238
trainer_state.json
Normal file
@@ -0,0 +1,238 @@
|
|||||||
|
{
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 285,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.03508771929824561,
|
||||||
|
"grad_norm": 6.543553342182306,
|
||||||
|
"learning_rate": 3.448275862068966e-06,
|
||||||
|
"loss": 1.8558,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.07017543859649122,
|
||||||
|
"grad_norm": 3.5154288610740023,
|
||||||
|
"learning_rate": 6.896551724137932e-06,
|
||||||
|
"loss": 1.4458,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10526315789473684,
|
||||||
|
"grad_norm": 2.778543537236469,
|
||||||
|
"learning_rate": 9.999623509195724e-06,
|
||||||
|
"loss": 1.2409,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.14035087719298245,
|
||||||
|
"grad_norm": 2.5059789149316045,
|
||||||
|
"learning_rate": 9.9545131771389e-06,
|
||||||
|
"loss": 1.1153,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.17543859649122806,
|
||||||
|
"grad_norm": 2.33426924896289,
|
||||||
|
"learning_rate": 9.834882355224261e-06,
|
||||||
|
"loss": 1.0284,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.21052631578947367,
|
||||||
|
"grad_norm": 2.238033736817208,
|
||||||
|
"learning_rate": 9.64253040236608e-06,
|
||||||
|
"loss": 0.9903,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24561403508771928,
|
||||||
|
"grad_norm": 2.172103858227053,
|
||||||
|
"learning_rate": 9.380350470977033e-06,
|
||||||
|
"loss": 0.9464,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2807017543859649,
|
||||||
|
"grad_norm": 2.0775067726943957,
|
||||||
|
"learning_rate": 9.052285991262975e-06,
|
||||||
|
"loss": 0.9232,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3157894736842105,
|
||||||
|
"grad_norm": 2.036467828021783,
|
||||||
|
"learning_rate": 8.663271358362064e-06,
|
||||||
|
"loss": 0.8927,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3508771929824561,
|
||||||
|
"grad_norm": 2.092139892865783,
|
||||||
|
"learning_rate": 8.219157714448957e-06,
|
||||||
|
"loss": 0.8748,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.38596491228070173,
|
||||||
|
"grad_norm": 2.354936030454241,
|
||||||
|
"learning_rate": 7.726624942110233e-06,
|
||||||
|
"loss": 0.8712,
|
||||||
|
"step": 110
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.42105263157894735,
|
||||||
|
"grad_norm": 2.4480552576537313,
|
||||||
|
"learning_rate": 7.193081192692639e-06,
|
||||||
|
"loss": 0.8413,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.45614035087719296,
|
||||||
|
"grad_norm": 2.225961040994733,
|
||||||
|
"learning_rate": 6.626551460811316e-06,
|
||||||
|
"loss": 0.8245,
|
||||||
|
"step": 130
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.49122807017543857,
|
||||||
|
"grad_norm": 2.2280118933835227,
|
||||||
|
"learning_rate": 6.035556880961093e-06,
|
||||||
|
"loss": 0.7995,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5263157894736842,
|
||||||
|
"grad_norm": 2.1092585894132694,
|
||||||
|
"learning_rate": 5.4289865617222005e-06,
|
||||||
|
"loss": 0.7919,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5614035087719298,
|
||||||
|
"grad_norm": 2.2317869413724947,
|
||||||
|
"learning_rate": 4.815963885293206e-06,
|
||||||
|
"loss": 0.794,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5964912280701754,
|
||||||
|
"grad_norm": 2.1555810331504976,
|
||||||
|
"learning_rate": 4.205709283330694e-06,
|
||||||
|
"loss": 0.7713,
|
||||||
|
"step": 170
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.631578947368421,
|
||||||
|
"grad_norm": 2.0442009159494785,
|
||||||
|
"learning_rate": 3.6074015530747354e-06,
|
||||||
|
"loss": 0.7775,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6666666666666666,
|
||||||
|
"grad_norm": 2.113365321780909,
|
||||||
|
"learning_rate": 3.0300397996947604e-06,
|
||||||
|
"loss": 0.7515,
|
||||||
|
"step": 190
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7017543859649122,
|
||||||
|
"grad_norm": 2.1674953587420838,
|
||||||
|
"learning_rate": 2.482308081371413e-06,
|
||||||
|
"loss": 0.765,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7368421052631579,
|
||||||
|
"grad_norm": 2.2304080548395917,
|
||||||
|
"learning_rate": 1.972444792978373e-06,
|
||||||
|
"loss": 0.7528,
|
||||||
|
"step": 210
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7719298245614035,
|
||||||
|
"grad_norm": 2.40752310761597,
|
||||||
|
"learning_rate": 1.508118752955136e-06,
|
||||||
|
"loss": 0.7396,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8070175438596491,
|
||||||
|
"grad_norm": 2.117568701663915,
|
||||||
|
"learning_rate": 1.0963138571395277e-06,
|
||||||
|
"loss": 0.7408,
|
||||||
|
"step": 230
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8421052631578947,
|
||||||
|
"grad_norm": 2.919503306825211,
|
||||||
|
"learning_rate": 7.43224034473674e-07,
|
||||||
|
"loss": 0.7486,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8771929824561403,
|
||||||
|
"grad_norm": 2.125280125804679,
|
||||||
|
"learning_rate": 4.5416008454738813e-07,
|
||||||
|
"loss": 0.7359,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9122807017543859,
|
||||||
|
"grad_norm": 2.066124288511879,
|
||||||
|
"learning_rate": 2.3346979822903071e-07,
|
||||||
|
"loss": 0.7375,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9473684210526315,
|
||||||
|
"grad_norm": 1.9772889405004763,
|
||||||
|
"learning_rate": 8.447256284391858e-08,
|
||||||
|
"loss": 0.7245,
|
||||||
|
"step": 270
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9824561403508771,
|
||||||
|
"grad_norm": 1.9570228116416033,
|
||||||
|
"learning_rate": 9.409435499254105e-09,
|
||||||
|
"loss": 0.7378,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"step": 285,
|
||||||
|
"total_flos": 1.4819175628485427e+17,
|
||||||
|
"train_loss": 0.8990087810315583,
|
||||||
|
"train_runtime": 350.8438,
|
||||||
|
"train_samples_per_second": 103.861,
|
||||||
|
"train_steps_per_second": 0.812
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 10,
|
||||||
|
"max_steps": 285,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"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": 1.4819175628485427e+17,
|
||||||
|
"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 sha256:917afe976f6d4c3b709d5fd40b3a87a682f30c20237b75ae8eedc3ae7fb4f468
|
||||||
|
size 6776
|
||||||
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