|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: result_2 |
|
|
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. --> |
|
|
|
|
|
# result_2 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 10.7026 |
|
|
- Accuracy: 0.4058 |
|
|
|
|
|
## 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: 3e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 64 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- training_steps: 1000 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Accuracy | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:--------:|:---------------:| |
|
|
| 0.19 | 1.0 | 90 | 0.9620 | 0.1504 | |
|
|
| 0.1041 | 1.99 | 180 | 0.9744 | 0.0753 | |
|
|
| 0.0463 | 2.99 | 270 | 0.9972 | 0.0106 | |
|
|
| 0.0003 | 4.0 | 361 | 0.9965 | 0.0354 | |
|
|
| 0.0 | 5.0 | 451 | 0.9910 | 0.1336 | |
|
|
| 0.0 | 5.99 | 541 | 0.9959 | 0.0548 | |
|
|
| 0.0654 | 6.99 | 631 | 0.9952 | 0.0685 | |
|
|
| 0.0617 | 8.0 | 722 | 0.9972 | 0.0307 | |
|
|
| 0.0 | 9.0 | 812 | 0.9959 | 0.0454 | |
|
|
| 0.0 | 9.99 | 902 | 0.9972 | 0.0382 | |
|
|
| 0.0 | 10.99 | 992 | 0.9979 | 0.0365 | |
|
|
| 0.0 | 11.12 | 1001 | 10.7026 | 0.4058 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1+cu117 |
|
|
- Datasets 2.14.5 |
|
|
- Tokenizers 0.13.3 |
|
|
|
