|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: Qwen/Qwen1.5-7B |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: amazon_attrprompt |
|
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. --> |
|
|
|
# amazon_attrprompt |
|
|
|
This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4250 |
|
- Accuracy: 0.8709 |
|
- F1 Macro: 0.8541 |
|
- F1 Micro: 0.8709 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 32 |
|
- total_eval_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.6833 | 0.13 | 50 | 1.2279 | 0.6640 | 0.5879 | 0.6640 | |
|
| 0.6531 | 0.26 | 100 | 0.6578 | 0.8155 | 0.7767 | 0.8155 | |
|
| 0.6075 | 0.39 | 150 | 0.5935 | 0.8327 | 0.8113 | 0.8327 | |
|
| 0.5646 | 0.53 | 200 | 0.5660 | 0.8379 | 0.8194 | 0.8379 | |
|
| 0.6148 | 0.66 | 250 | 0.5318 | 0.8426 | 0.8319 | 0.8426 | |
|
| 0.4047 | 0.79 | 300 | 0.4546 | 0.8650 | 0.8467 | 0.8650 | |
|
| 0.568 | 0.92 | 350 | 0.4250 | 0.8709 | 0.8541 | 0.8709 | |
|
| 0.2395 | 1.05 | 400 | 0.4570 | 0.8762 | 0.8611 | 0.8762 | |
|
| 0.2213 | 1.18 | 450 | 0.4524 | 0.8775 | 0.8631 | 0.8775 | |
|
| 0.1778 | 1.32 | 500 | 0.4649 | 0.8748 | 0.8508 | 0.8748 | |
|
| 0.1738 | 1.45 | 550 | 0.4853 | 0.8794 | 0.8617 | 0.8794 | |
|
| 0.2643 | 1.58 | 600 | 0.4302 | 0.8827 | 0.8676 | 0.8827 | |
|
| 0.3357 | 1.71 | 650 | 0.4388 | 0.8827 | 0.8673 | 0.8827 | |
|
| 0.3029 | 1.84 | 700 | 0.4431 | 0.8827 | 0.8656 | 0.8827 | |
|
| 0.1809 | 1.97 | 750 | 0.4266 | 0.8900 | 0.8742 | 0.8900 | |
|
| 0.0589 | 2.11 | 800 | 0.4499 | 0.8946 | 0.8815 | 0.8946 | |
|
| 0.0531 | 2.24 | 850 | 0.4758 | 0.8920 | 0.8758 | 0.8920 | |
|
| 0.0234 | 2.37 | 900 | 0.4788 | 0.8953 | 0.8804 | 0.8953 | |
|
| 0.0145 | 2.5 | 950 | 0.4976 | 0.8939 | 0.8779 | 0.8939 | |
|
| 0.058 | 2.63 | 1000 | 0.4967 | 0.8992 | 0.8816 | 0.8992 | |
|
| 0.05 | 2.76 | 1050 | 0.5113 | 0.8933 | 0.8753 | 0.8933 | |
|
| 0.0556 | 2.89 | 1100 | 0.5024 | 0.8966 | 0.8803 | 0.8966 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |