<!-- 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. -->
bert_labse-finetuning-unhealthyConv-dropout005-epochs-10
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: 0.7708
- Mse: 0.7708
- Rmse: 0.8779
- Mae: 0.4977
- R2: 0.8607
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Rmse | Mae | R2 |
|---|---|---|---|---|---|---|---|
| 1.54 | 1.0 | 3389 | 1.2501 | 1.2501 | 1.1181 | 0.7744 | 0.7741 |
| 1.0093 | 2.0 | 6778 | 1.3221 | 1.3221 | 1.1498 | 0.8026 | 0.7611 |
| 0.7994 | 3.0 | 10167 | 1.0421 | 1.0421 | 1.0209 | 0.6981 | 0.8117 |
| 0.6243 | 4.0 | 13556 | 0.8910 | 0.8910 | 0.9439 | 0.6020 | 0.8390 |
| 0.5119 | 5.0 | 16945 | 0.8391 | 0.8391 | 0.9160 | 0.5694 | 0.8484 |
| 0.3935 | 6.0 | 20334 | 0.8609 | 0.8609 | 0.9278 | 0.5658 | 0.8445 |
| 0.3394 | 7.0 | 23723 | 0.8093 | 0.8093 | 0.8996 | 0.5317 | 0.8538 |
| 0.295 | 8.0 | 27112 | 0.7712 | 0.7712 | 0.8782 | 0.5165 | 0.8607 |
| 0.2338 | 9.0 | 30501 | 0.7831 | 0.7831 | 0.8849 | 0.5154 | 0.8585 |
| 0.2119 | 10.0 | 33890 | 0.7708 | 0.7708 | 0.8779 | 0.4977 | 0.8607 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
