|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: runs |
|
|
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. --> |
|
|
|
|
|
# runs |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.1137 |
|
|
- Accuracy: 0.0000 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 48 |
|
|
- seed: 444 |
|
|
- gradient_accumulation_steps: 3 |
|
|
- total_train_batch_size: 48 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine_with_restarts |
|
|
- lr_scheduler_warmup_ratio: 0.3 |
|
|
- training_steps: 100 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| No log | 0.03 | 10 | 4.7890 | 0.1380 | |
|
|
| 4.9326 | 0.05 | 20 | 4.4600 | 0.1310 | |
|
|
| 4.9326 | 0.08 | 30 | 4.1364 | 0.0172 | |
|
|
| 4.1299 | 0.11 | 40 | 3.7156 | 0.0010 | |
|
|
| 4.1299 | 0.13 | 50 | 3.3965 | 0.0002 | |
|
|
| 3.4428 | 0.16 | 60 | 3.2530 | 0.0002 | |
|
|
| 3.4428 | 0.19 | 70 | 3.1727 | 0.0000 | |
|
|
| 3.1873 | 0.21 | 80 | 3.1316 | 0.0000 | |
|
|
| 3.1873 | 0.24 | 90 | 3.1165 | 0.0000 | |
|
|
| 3.1176 | 0.26 | 100 | 3.1137 | 0.0000 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.37.2 |
|
|
- Pytorch 2.2.0+cu121 |
|
|
- Datasets 2.17.0 |
|
|
- Tokenizers 0.15.1 |
|
|
|
