Regression_albert_12_NO_aug
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6997
- Mse: 0.6997
- Mae: 0.7013
- R2: -0.2883
- Accuracy: 0.4211
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 33 | 0.3797 | 0.3797 | 0.5648 | -0.1345 | 0.3514 |
| No log | 2.0 | 66 | 0.4018 | 0.4018 | 0.5029 | -0.2005 | 0.4865 |
| No log | 3.0 | 99 | 0.4384 | 0.4384 | 0.5738 | -0.3100 | 0.4054 |
| No log | 4.0 | 132 | 0.6817 | 0.6817 | 0.6523 | -1.0370 | 0.5405 |
| No log | 5.0 | 165 | 0.4155 | 0.4155 | 0.4750 | -0.2415 | 0.5676 |
| No log | 6.0 | 198 | 0.5695 | 0.5695 | 0.5599 | -0.7017 | 0.5405 |
| No log | 7.0 | 231 | 0.5646 | 0.5646 | 0.5588 | -0.6869 | 0.5405 |
| No log | 8.0 | 264 | 0.5240 | 0.5240 | 0.5330 | -0.5656 | 0.5676 |
| No log | 9.0 | 297 | 0.4613 | 0.4613 | 0.4798 | -0.3783 | 0.5676 |
| No log | 10.0 | 330 | 0.6285 | 0.6285 | 0.6172 | -0.8778 | 0.5135 |
| No log | 11.0 | 363 | 0.6012 | 0.6012 | 0.5600 | -0.7964 | 0.5676 |
| No log | 12.0 | 396 | 0.4417 | 0.4417 | 0.4767 | -0.3198 | 0.5405 |
| No log | 13.0 | 429 | 0.5486 | 0.5486 | 0.5349 | -0.6392 | 0.5676 |
| No log | 14.0 | 462 | 0.5328 | 0.5328 | 0.5174 | -0.5919 | 0.5676 |
| No log | 15.0 | 495 | 0.5442 | 0.5442 | 0.5165 | -0.6259 | 0.5405 |
| 0.2088 | 16.0 | 528 | 0.4587 | 0.4587 | 0.4619 | -0.3705 | 0.5405 |
| 0.2088 | 17.0 | 561 | 0.5056 | 0.5056 | 0.4970 | -0.5107 | 0.5405 |
| 0.2088 | 18.0 | 594 | 0.4787 | 0.4787 | 0.4744 | -0.4304 | 0.5405 |
| 0.2088 | 19.0 | 627 | 0.4349 | 0.4349 | 0.4531 | -0.2995 | 0.5676 |
| 0.2088 | 20.0 | 660 | 0.4605 | 0.4605 | 0.4642 | -0.3759 | 0.5676 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3