metadata
tags:
- generated_from_trainer
model-index:
- name: RADME_fine_f0
results: []
RADME_fine_f0
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3180
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 |
|---|---|---|---|
| 0.3415 | 0.95 | 5000 | 0.3092 |
| 0.3072 | 1.91 | 10000 | 0.2882 |
| 0.2776 | 2.86 | 15000 | 0.2789 |
| 0.2571 | 3.82 | 20000 | 0.2754 |
| 0.2403 | 4.77 | 25000 | 0.2751 |
| 0.226 | 5.72 | 30000 | 0.2763 |
| 0.2111 | 6.68 | 35000 | 0.2812 |
| 0.2021 | 7.63 | 40000 | 0.2852 |
| 0.1897 | 8.58 | 45000 | 0.2908 |
| 0.1789 | 9.54 | 50000 | 0.2950 |
| 0.171 | 10.49 | 55000 | 0.3001 |
| 0.1646 | 11.45 | 60000 | 0.3062 |
| 0.1577 | 12.4 | 65000 | 0.3105 |
| 0.1528 | 13.35 | 70000 | 0.3154 |
| 0.1499 | 14.31 | 75000 | 0.3180 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3