Regression_albert_3
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: 0.7092
- Mse: 0.7092
- Mae: 0.6931
- R2: -0.3058
- Accuracy: 0.4737
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 | 0.3632 | 0.3632 | 0.5672 | -0.0851 | 0.2703 |
| No log | 2.0 | 66 | 0.3855 | 0.3855 | 0.5860 | -0.1518 | 0.2703 |
| No log | 3.0 | 99 | 0.4619 | 0.4619 | 0.5229 | -0.3801 | 0.5405 |
| No log | 4.0 | 132 | 0.4573 | 0.4573 | 0.5791 | -0.3665 | 0.4324 |
| No log | 5.0 | 165 | 0.3254 | 0.3254 | 0.4284 | 0.0277 | 0.7297 |
| No log | 6.0 | 198 | 0.3139 | 0.3139 | 0.4078 | 0.0622 | 0.6757 |
| No log | 7.0 | 231 | 0.3489 | 0.3489 | 0.4370 | -0.0424 | 0.5946 |
| No log | 8.0 | 264 | 0.3933 | 0.3933 | 0.4113 | -0.1753 | 0.6757 |
| No log | 9.0 | 297 | 0.3219 | 0.3219 | 0.3611 | 0.0381 | 0.7027 |
| No log | 10.0 | 330 | 0.3228 | 0.3228 | 0.3423 | 0.0356 | 0.7568 |
| No log | 11.0 | 363 | 0.3289 | 0.3289 | 0.3964 | 0.0173 | 0.6757 |
| No log | 12.0 | 396 | 0.3717 | 0.3717 | 0.3917 | -0.1107 | 0.6757 |
| No log | 13.0 | 429 | 0.4160 | 0.4160 | 0.4238 | -0.2430 | 0.6486 |
| No log | 14.0 | 462 | 0.3691 | 0.3691 | 0.3781 | -0.1027 | 0.6486 |
| No log | 15.0 | 495 | 0.4483 | 0.4483 | 0.4233 | -0.3394 | 0.7027 |
| 0.1519 | 16.0 | 528 | 0.4205 | 0.4205 | 0.3878 | -0.2563 | 0.7027 |
| 0.1519 | 17.0 | 561 | 0.3750 | 0.3750 | 0.4112 | -0.1205 | 0.6216 |
| 0.1519 | 18.0 | 594 | 0.3895 | 0.3895 | 0.4010 | -0.1639 | 0.6486 |
| 0.1519 | 19.0 | 627 | 0.3884 | 0.3884 | 0.3933 | -0.1605 | 0.6757 |
| 0.1519 | 20.0 | 660 | 0.3907 | 0.3907 | 0.3871 | -0.1674 | 0.6757 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2