<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
labse-finetuning-unhealthyConv-dropout005-epochs-best-loss
This model is a fine-tuned version of old_models/LaBSE/0_Transformer on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3243
- Mse: 0.3243
- Rmse: 0.5694
- Mae: 0.2417
- R2: 0.9417
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Rmse | Mae | R2 |
|---|---|---|---|---|---|---|---|
| 1.1897 | 1.0 | 6778 | 1.0972 | 1.0972 | 1.0475 | 0.7271 | 0.8107 |
| 0.8642 | 2.0 | 13556 | 0.9204 | 0.9204 | 0.9594 | 0.6268 | 0.8412 |
| 0.6139 | 3.0 | 20334 | 0.7241 | 0.7241 | 0.8509 | 0.5418 | 0.8751 |
| 0.4295 | 4.0 | 27112 | 0.6779 | 0.6779 | 0.8233 | 0.5333 | 0.8830 |
| 0.3535 | 5.0 | 33890 | 0.5362 | 0.5362 | 0.7323 | 0.4403 | 0.9075 |
| 0.2717 | 6.0 | 40668 | 0.5005 | 0.5005 | 0.7074 | 0.4029 | 0.9136 |
| 0.223 | 7.0 | 47446 | 0.4659 | 0.4659 | 0.6826 | 0.3750 | 0.9196 |
| 0.185 | 8.0 | 54224 | 0.4401 | 0.4401 | 0.6634 | 0.3600 | 0.9241 |
| 0.148 | 9.0 | 61002 | 0.4137 | 0.4137 | 0.6432 | 0.3352 | 0.9286 |
| 0.1258 | 10.0 | 67780 | 0.4061 | 0.4061 | 0.6373 | 0.3364 | 0.9299 |
| 0.1084 | 11.0 | 74558 | 0.3964 | 0.3964 | 0.6296 | 0.3122 | 0.9316 |
| 0.0856 | 12.0 | 81336 | 0.3874 | 0.3874 | 0.6224 | 0.2991 | 0.9332 |
| 0.0795 | 13.0 | 88114 | 0.3791 | 0.3791 | 0.6157 | 0.3031 | 0.9346 |
| 0.0657 | 14.0 | 94892 | 0.3870 | 0.3870 | 0.6221 | 0.3010 | 0.9332 |
| 0.06 | 15.0 | 101670 | 0.3604 | 0.3604 | 0.6004 | 0.2571 | 0.9378 |
| 0.0544 | 16.0 | 108448 | 0.3635 | 0.3635 | 0.6029 | 0.2660 | 0.9373 |
| 0.0418 | 17.0 | 115226 | 0.3628 | 0.3628 | 0.6024 | 0.2781 | 0.9374 |
| 0.0387 | 18.0 | 122004 | 0.3499 | 0.3499 | 0.5915 | 0.2536 | 0.9396 |
| 0.0356 | 19.0 | 128782 | 0.3534 | 0.3534 | 0.5945 | 0.2587 | 0.9390 |
| 0.0327 | 20.0 | 135560 | 0.3583 | 0.3583 | 0.5985 | 0.2598 | 0.9382 |
| 0.0295 | 21.0 | 142338 | 0.3513 | 0.3513 | 0.5927 | 0.2493 | 0.9394 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
