<!-- 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. -->
roberta-base-finetuned-scientific-eval
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1154
- Precision: 0.7165
- Recall: 0.8063
- F1: 0.7587
- Accuracy: 0.9626
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 | 71 | 0.2567 | 0.3762 | 0.3333 | 0.3535 | 0.9314 |
No log | 2.0 | 142 | 0.1597 | 0.6677 | 0.6011 | 0.6327 | 0.9529 |
No log | 3.0 | 213 | 0.1222 | 0.6995 | 0.7293 | 0.7141 | 0.9622 |
No log | 4.0 | 284 | 0.1154 | 0.7165 | 0.8063 | 0.7587 | 0.9626 |
No log | 5.0 | 355 | 0.1310 | 0.6988 | 0.8063 | 0.7487 | 0.9651 |
No log | 6.0 | 426 | 0.1366 | 0.7101 | 0.8234 | 0.7625 | 0.9641 |
No log | 7.0 | 497 | 0.1453 | 0.7125 | 0.8262 | 0.7652 | 0.9632 |
0.1453 | 8.0 | 568 | 0.1388 | 0.7612 | 0.8262 | 0.7923 | 0.9672 |
0.1453 | 9.0 | 639 | 0.1455 | 0.7494 | 0.8433 | 0.7936 | 0.9669 |
0.1453 | 10.0 | 710 | 0.1441 | 0.745 | 0.8490 | 0.7936 | 0.9682 |
Framework versions
- Transformers 4.27.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3