|
|
--- |
|
|
library_name: peft |
|
|
license: apache-2.0 |
|
|
base_model: Qwen/Qwen3-0.6B |
|
|
tags: |
|
|
- llama-factory |
|
|
- lora |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Extractor_Adaptor_Qwen3_Final |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# Extractor_Adaptor_Qwen3_Final |
|
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on the web_finetune_train dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2849 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 1.7e-05 |
|
|
- train_batch_size: 2 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 2 |
|
|
- gradient_accumulation_steps: 8 |
|
|
- total_train_batch_size: 32 |
|
|
- total_eval_batch_size: 4 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 2.0 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.2465 | 0.1180 | 50 | 0.3812 | |
|
|
| 0.2805 | 0.2360 | 100 | 0.3440 | |
|
|
| 0.2016 | 0.3540 | 150 | 0.3299 | |
|
|
| 0.3261 | 0.4720 | 200 | 0.3187 | |
|
|
| 0.2523 | 0.5900 | 250 | 0.3116 | |
|
|
| 0.2505 | 0.7080 | 300 | 0.3049 | |
|
|
| 0.2371 | 0.8260 | 350 | 0.2978 | |
|
|
| 0.2177 | 0.9440 | 400 | 0.2940 | |
|
|
| 0.1686 | 1.0614 | 450 | 0.2935 | |
|
|
| 0.1189 | 1.1794 | 500 | 0.2935 | |
|
|
| 0.1955 | 1.2973 | 550 | 0.2907 | |
|
|
| 0.1341 | 1.4153 | 600 | 0.2885 | |
|
|
| 0.1591 | 1.5333 | 650 | 0.2874 | |
|
|
| 0.1594 | 1.6513 | 700 | 0.2859 | |
|
|
| 0.1452 | 1.7693 | 750 | 0.2850 | |
|
|
| 0.1845 | 1.8873 | 800 | 0.2849 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.15.2 |
|
|
- Transformers 4.57.1 |
|
|
- Pytorch 2.9.0+cu128 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.22.1 |
