|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: RADME_fine_f4 |
|
|
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. --> |
|
|
|
|
|
# RADME_fine_f4 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3141 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 3 |
|
|
- num_epochs: 15 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 0.3477 | 0.95 | 5000 | 0.3100 | |
|
|
| 0.3067 | 1.91 | 10000 | 0.2889 | |
|
|
| 0.2787 | 2.86 | 15000 | 0.2791 | |
|
|
| 0.2573 | 3.81 | 20000 | 0.2767 | |
|
|
| 0.2434 | 4.77 | 25000 | 0.2740 | |
|
|
| 0.2256 | 5.72 | 30000 | 0.2772 | |
|
|
| 0.2152 | 6.67 | 35000 | 0.2799 | |
|
|
| 0.2026 | 7.63 | 40000 | 0.2833 | |
|
|
| 0.1925 | 8.58 | 45000 | 0.2884 | |
|
|
| 0.1838 | 9.53 | 50000 | 0.2926 | |
|
|
| 0.1744 | 10.49 | 55000 | 0.2979 | |
|
|
| 0.1669 | 11.44 | 60000 | 0.3034 | |
|
|
| 0.1612 | 12.39 | 65000 | 0.3087 | |
|
|
| 0.1548 | 13.35 | 70000 | 0.3127 | |
|
|
| 0.1529 | 14.3 | 75000 | 0.3141 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.32.1 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.14.4 |
|
|
- Tokenizers 0.13.3 |
|
|
|
