rel-cl2-transformer-3
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8752
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: 3
- 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 |
|---|---|---|---|
| 4.238 | 0.03 | 76320 | 4.2068 |
| 4.0326 | 1.03 | 152640 | 4.0352 |
| 3.9254 | 0.03 | 228960 | 3.9594 |
| 3.8541 | 1.03 | 305280 | 3.9177 |
| 3.8051 | 0.03 | 381600 | 3.8928 |
| 3.7636 | 0.03 | 457920 | 3.8770 |
| 3.7283 | 1.03 | 534240 | 3.8664 |
| 3.6974 | 0.03 | 610560 | 3.8598 |
| 3.6665 | 1.03 | 686880 | 3.8546 |
| 3.6435 | 0.03 | 763200 | 3.8530 |
| 3.6178 | 1.03 | 839520 | 3.8508 |
| 3.5986 | 0.03 | 915840 | 3.8514 |
| 3.5791 | 1.03 | 992160 | 3.8509 |
| 3.5621 | 0.03 | 1068480 | 3.8518 |
| 3.5498 | 1.03 | 1144800 | 3.8527 |
| 3.5345 | 0.03 | 1221120 | 3.8540 |
| 3.5205 | 1.03 | 1297440 | 3.8551 |
| 3.5063 | 0.03 | 1373760 | 3.8565 |
| 3.4944 | 1.03 | 1450080 | 3.8590 |
| 3.4828 | 0.03 | 1526400 | 3.8615 |
| 3.4734 | 0.03 | 1602720 | 3.8611 |
| 3.465 | 1.03 | 1679040 | 3.8627 |
| 3.4547 | 0.03 | 1755360 | 3.8664 |
| 3.4431 | 1.03 | 1831680 | 3.8674 |
| 3.4279 | 0.03 | 1908000 | 3.8686 |
| 3.4188 | 1.03 | 1984320 | 3.8693 |
| 3.4056 | 0.03 | 2060640 | 3.8711 |
| 3.3942 | 1.03 | 2136960 | 3.8723 |
| 3.3836 | 0.03 | 2213280 | 3.8747 |
| 3.3698 | 1.03 | 2289600 | 3.8753 |
| 3.3635 | 0.03 | 2365920 | 3.8765 |
| 3.3565 | 1.03 | 2442240 | 3.8772 |
| 3.347 | 0.03 | 2518560 | 3.8770 |
| 3.3347 | 1.03 | 2594880 | 3.8784 |
| 3.3296 | 0.03 | 2671200 | 3.8782 |
| 3.3223 | 0.03 | 2747520 | 3.8780 |
| 3.3144 | 1.03 | 2823840 | 3.8785 |
| 3.3108 | 0.03 | 2900160 | 3.8772 |
| 3.3033 | 1.03 | 2976480 | 3.8761 |
| 3.2948 | 0.02 | 3052726 | 3.8752 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3