rel-cl2-transformer-4
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8723
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: 32
- eval_batch_size: 32
- seed: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.2396 | 0.03 | 76320 | 4.2054 |
| 4.0324 | 1.03 | 152640 | 4.0344 |
| 3.9268 | 0.03 | 228960 | 3.9612 |
| 3.858 | 1.03 | 305280 | 3.9191 |
| 3.8054 | 0.03 | 381600 | 3.8933 |
| 3.7659 | 1.03 | 457920 | 3.8774 |
| 3.7299 | 0.03 | 534240 | 3.8676 |
| 3.6983 | 1.03 | 610560 | 3.8601 |
| 3.6681 | 0.03 | 686880 | 3.8566 |
| 3.6432 | 1.03 | 763200 | 3.8536 |
| 3.6169 | 0.03 | 839520 | 3.8521 |
| 3.596 | 1.03 | 915840 | 3.8518 |
| 3.5764 | 0.03 | 992160 | 3.8511 |
| 3.5594 | 1.03 | 1068480 | 3.8525 |
| 3.5453 | 0.03 | 1144800 | 3.8519 |
| 3.5375 | 1.03 | 1221120 | 3.8525 |
| 3.5204 | 0.03 | 1297440 | 3.8539 |
| 3.5061 | 1.03 | 1373760 | 3.8566 |
| 3.494 | 0.03 | 1450080 | 3.8576 |
| 3.483 | 1.03 | 1526400 | 3.8582 |
| 3.4723 | 0.03 | 1602720 | 3.8598 |
| 3.4649 | 1.03 | 1679040 | 3.8618 |
| 3.4552 | 0.03 | 1755360 | 3.8638 |
| 3.4422 | 0.03 | 1831680 | 3.8636 |
| 3.4279 | 1.03 | 1908000 | 3.8664 |
| 3.4158 | 0.03 | 1984320 | 3.8670 |
| 3.4032 | 1.03 | 2060640 | 3.8694 |
| 3.392 | 0.03 | 2136960 | 3.8695 |
| 3.3802 | 1.03 | 2213280 | 3.8707 |
| 3.3686 | 0.03 | 2289600 | 3.8726 |
| 3.3611 | 1.03 | 2365920 | 3.8729 |
| 3.359 | 0.03 | 2442240 | 3.8727 |
| 3.3459 | 1.03 | 2518560 | 3.8743 |
| 3.3369 | 0.03 | 2594880 | 3.8742 |
| 3.328 | 0.03 | 2671200 | 3.8751 |
| 3.3197 | 1.03 | 2747520 | 3.8751 |
| 3.3156 | 0.03 | 2823840 | 3.8752 |
| 3.3092 | 1.03 | 2900160 | 3.8751 |
| 3.3014 | 0.03 | 2976480 | 3.8737 |
| 3.2948 | 1.02 | 3052726 | 3.8723 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3