Regression_roberta_2
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.4601
- Mse: 4.4601
- Mae: 1.5854
- R2: -1.3013
- Accuracy: 0.4286
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 3.5793 | 3.5793 | 1.5863 | -2.3584 | 0.2857 |
| No log | 2.0 | 2 | 3.3920 | 3.3920 | 1.5228 | -2.1826 | 0.2857 |
| No log | 3.0 | 3 | 3.2161 | 3.2161 | 1.4599 | -2.0176 | 0.2857 |
| No log | 4.0 | 4 | 3.0482 | 3.0482 | 1.3958 | -1.8601 | 0.4286 |
| No log | 5.0 | 5 | 2.8803 | 2.8803 | 1.3393 | -1.7026 | 0.4286 |
| No log | 6.0 | 6 | 2.7157 | 2.7157 | 1.2996 | -1.5481 | 0.4286 |
| No log | 7.0 | 7 | 2.5511 | 2.5511 | 1.2760 | -1.3937 | 0.4286 |
| No log | 8.0 | 8 | 2.3882 | 2.3882 | 1.2524 | -1.2408 | 0.4286 |
| No log | 9.0 | 9 | 2.2328 | 2.2328 | 1.2424 | -1.0950 | 0.2857 |
| No log | 10.0 | 10 | 2.0956 | 2.0956 | 1.2608 | -0.9662 | 0.1429 |
| No log | 11.0 | 11 | 1.9947 | 1.9947 | 1.2837 | -0.8716 | 0.1429 |
| No log | 12.0 | 12 | 1.9404 | 1.9404 | 1.3073 | -0.8206 | 0.0 |
| No log | 13.0 | 13 | 1.9271 | 1.9271 | 1.3254 | -0.8082 | 0.0 |
| No log | 14.0 | 14 | 1.9439 | 1.9439 | 1.3369 | -0.8239 | 0.0 |
| No log | 15.0 | 15 | 1.9740 | 1.9740 | 1.3394 | -0.8522 | 0.0 |
| No log | 16.0 | 16 | 2.0039 | 2.0039 | 1.3338 | -0.8802 | 0.0 |
| No log | 17.0 | 17 | 2.0291 | 2.0291 | 1.3237 | -0.9039 | 0.1429 |
| No log | 18.0 | 18 | 2.0540 | 2.0540 | 1.3152 | -0.9273 | 0.1429 |
| No log | 19.0 | 19 | 2.0721 | 2.0721 | 1.3080 | -0.9442 | 0.1429 |
| No log | 20.0 | 20 | 2.0814 | 2.0814 | 1.3037 | -0.9529 | 0.1429 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2