metadata
tags:
- generated_from_trainer
model-index:
- name: RADME_fine_f1
results: []
RADME_fine_f1
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3187
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 |
|---|---|---|---|
| 0.3491 | 0.95 | 5000 | 0.3109 |
| 0.3082 | 1.91 | 10000 | 0.2880 |
| 0.2772 | 2.86 | 15000 | 0.2798 |
| 0.2553 | 3.82 | 20000 | 0.2766 |
| 0.2424 | 4.77 | 25000 | 0.2758 |
| 0.2292 | 5.72 | 30000 | 0.2785 |
| 0.2134 | 6.68 | 35000 | 0.2799 |
| 0.2021 | 7.63 | 40000 | 0.2853 |
| 0.1912 | 8.59 | 45000 | 0.2893 |
| 0.182 | 9.54 | 50000 | 0.2959 |
| 0.1734 | 10.49 | 55000 | 0.3005 |
| 0.1647 | 11.45 | 60000 | 0.3069 |
| 0.1581 | 12.4 | 65000 | 0.3123 |
| 0.1538 | 13.36 | 70000 | 0.3147 |
| 0.1505 | 14.31 | 75000 | 0.3187 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3