roberta-base-finetuned-scientific-exp
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1255
- Precision: 0.7662
- Recall: 0.7484
- F1: 0.7572
- Accuracy: 0.9674
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | 0.2172 | 0.6049 | 0.5180 | 0.5581 | 0.9433 |
| No log | 2.0 | 162 | 0.1470 | 0.7556 | 0.6469 | 0.6970 | 0.9582 |
| No log | 3.0 | 243 | 0.1255 | 0.7662 | 0.7484 | 0.7572 | 0.9674 |
| No log | 4.0 | 324 | 0.1261 | 0.7546 | 0.7738 | 0.7641 | 0.9666 |
| No log | 5.0 | 405 | 0.1339 | 0.7184 | 0.8414 | 0.7751 | 0.9635 |
| No log | 6.0 | 486 | 0.1350 | 0.7112 | 0.8330 | 0.7673 | 0.9627 |
| 0.1498 | 7.0 | 567 | 0.1362 | 0.7471 | 0.8309 | 0.7868 | 0.9693 |
| 0.1498 | 8.0 | 648 | 0.1530 | 0.7174 | 0.8266 | 0.7682 | 0.9644 |
| 0.1498 | 9.0 | 729 | 0.1587 | 0.7392 | 0.8330 | 0.7833 | 0.9655 |
| 0.1498 | 10.0 | 810 | 0.1610 | 0.7416 | 0.8372 | 0.7865 | 0.9651 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3