full-lstm-4
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9704
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 |
|---|---|---|---|
| 4.8004 | 0.03 | 76319 | 4.7641 |
| 4.5121 | 0.03 | 152638 | 4.4806 |
| 4.3684 | 1.03 | 228957 | 4.3448 |
| 4.2765 | 0.03 | 305276 | 4.2616 |
| 4.2121 | 1.03 | 381595 | 4.2050 |
| 4.1608 | 0.03 | 457914 | 4.1635 |
| 4.1255 | 1.03 | 534233 | 4.1324 |
| 4.0959 | 0.03 | 610552 | 4.1078 |
| 4.0666 | 0.03 | 686871 | 4.0883 |
| 4.0436 | 1.03 | 763190 | 4.0722 |
| 4.0239 | 0.03 | 839509 | 4.0580 |
| 4.0089 | 1.03 | 915828 | 4.0473 |
| 3.9888 | 0.03 | 992148 | 4.0371 |
| 3.9758 | 1.03 | 1068468 | 4.0294 |
| 3.9699 | 0.03 | 1144788 | 4.0218 |
| 3.9587 | 1.03 | 1221108 | 4.0161 |
| 3.9389 | 0.03 | 1297428 | 4.0109 |
| 3.931 | 1.03 | 1373748 | 4.0059 |
| 3.9193 | 0.03 | 1450068 | 4.0013 |
| 3.9126 | 1.03 | 1526388 | 3.9978 |
| 3.9121 | 0.03 | 1602708 | 3.9949 |
| 3.9067 | 1.03 | 1679028 | 3.9922 |
| 3.9079 | 0.03 | 1755348 | 3.9896 |
| 3.904 | 1.03 | 1831668 | 3.9874 |
| 3.897 | 0.03 | 1907988 | 3.9856 |
| 3.8901 | 1.03 | 1984308 | 3.9840 |
| 3.8877 | 0.03 | 2060628 | 3.9821 |
| 3.8779 | 1.03 | 2136948 | 3.9806 |
| 3.8775 | 0.03 | 2213268 | 3.9794 |
| 3.8691 | 0.03 | 2289588 | 3.9782 |
| 3.8627 | 0.03 | 2365908 | 3.9771 |
| 3.8616 | 1.03 | 2442228 | 3.9761 |
| 3.8491 | 0.03 | 2518548 | 3.9749 |
| 3.848 | 1.03 | 2594868 | 3.9738 |
| 3.8413 | 0.03 | 2671188 | 3.9730 |
| 3.842 | 1.03 | 2747508 | 3.9721 |
| 3.8472 | 0.03 | 2823828 | 3.9715 |
| 3.8438 | 1.03 | 2900148 | 3.9710 |
| 3.85 | 0.03 | 2976468 | 3.9706 |
| 3.8505 | 0.02 | 3052726 | 3.9704 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 11