full-transformer-3
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8587
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 |
---|---|---|---|
4.2233 | 0.03 | 76319 | 4.1904 |
4.0164 | 0.03 | 152638 | 4.0214 |
3.9108 | 0.03 | 228957 | 3.9470 |
3.8387 | 0.03 | 305276 | 3.9060 |
3.7867 | 0.03 | 381595 | 3.8814 |
3.7413 | 0.03 | 457914 | 3.8656 |
3.7107 | 0.03 | 534233 | 3.8556 |
3.6837 | 0.03 | 610552 | 3.8487 |
3.6531 | 0.03 | 686871 | 3.8448 |
3.6291 | 0.03 | 763190 | 3.8420 |
3.6101 | 1.03 | 839509 | 3.8409 |
3.5963 | 0.03 | 915829 | 3.8363 |
3.5791 | 1.03 | 992149 | 3.8367 |
3.5582 | 0.03 | 1068469 | 3.8382 |
3.5416 | 1.03 | 1144789 | 3.8380 |
3.5288 | 0.03 | 1221109 | 3.8402 |
3.5067 | 1.03 | 1297429 | 3.8410 |
3.4946 | 0.03 | 1373749 | 3.8431 |
3.4805 | 0.03 | 1450069 | 3.8431 |
3.4665 | 1.03 | 1526389 | 3.8470 |
3.4615 | 0.03 | 1602709 | 3.8478 |
3.4538 | 1.03 | 1679029 | 3.8471 |
3.448 | 0.03 | 1755349 | 3.8479 |
3.4378 | 1.03 | 1831669 | 3.8503 |
3.4252 | 0.03 | 1907989 | 3.8518 |
3.4161 | 1.03 | 1984309 | 3.8544 |
3.4041 | 0.03 | 2060629 | 3.8546 |
3.3914 | 0.03 | 2136949 | 3.8557 |
3.3834 | 1.03 | 2213269 | 3.8566 |
3.3716 | 0.03 | 2289589 | 3.8571 |
3.3606 | 0.03 | 2365909 | 3.8585 |
3.3526 | 0.03 | 2442229 | 3.8595 |
3.3358 | 0.03 | 2518549 | 3.8594 |
3.327 | 0.03 | 2594869 | 3.8601 |
3.3165 | 0.03 | 2671189 | 3.8611 |
3.3069 | 0.03 | 2747509 | 3.8615 |
3.3062 | 1.03 | 2823829 | 3.8609 |
3.2995 | 0.03 | 2900149 | 3.8612 |
3.2968 | 1.03 | 2976469 | 3.8606 |
3.2924 | 0.02 | 3052726 | 3.8587 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1