<!-- 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-paper
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1620
- Precision: 0.7605
- Recall: 0.8141
- F1: 0.7864
- Accuracy: 0.9765
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: 5e-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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 73 | 0.1575 | 0.6484 | 0.5673 | 0.6051 | 0.9591 |
No log | 2.0 | 146 | 0.0964 | 0.6723 | 0.7628 | 0.7147 | 0.9718 |
No log | 3.0 | 219 | 0.1233 | 0.6447 | 0.7853 | 0.7081 | 0.9655 |
No log | 4.0 | 292 | 0.1153 | 0.7563 | 0.7660 | 0.7611 | 0.9737 |
No log | 5.0 | 365 | 0.1194 | 0.7265 | 0.8173 | 0.7692 | 0.9727 |
No log | 6.0 | 438 | 0.1243 | 0.7286 | 0.8173 | 0.7704 | 0.9722 |
0.0974 | 7.0 | 511 | 0.1406 | 0.7202 | 0.7756 | 0.7469 | 0.9732 |
0.0974 | 8.0 | 584 | 0.1436 | 0.7406 | 0.7596 | 0.7500 | 0.9706 |
0.0974 | 9.0 | 657 | 0.1687 | 0.7524 | 0.7596 | 0.7560 | 0.9738 |
0.0974 | 10.0 | 730 | 0.1591 | 0.7394 | 0.7821 | 0.7601 | 0.9743 |
0.0974 | 11.0 | 803 | 0.1431 | 0.7619 | 0.8205 | 0.7901 | 0.9754 |
0.0974 | 12.0 | 876 | 0.1487 | 0.7477 | 0.7981 | 0.7721 | 0.9745 |
0.0974 | 13.0 | 949 | 0.1512 | 0.7764 | 0.8013 | 0.7886 | 0.9763 |
0.0043 | 14.0 | 1022 | 0.1532 | 0.7645 | 0.8013 | 0.7825 | 0.9754 |
0.0043 | 15.0 | 1095 | 0.1531 | 0.7720 | 0.8141 | 0.7925 | 0.9761 |
0.0043 | 16.0 | 1168 | 0.1590 | 0.7635 | 0.8173 | 0.7895 | 0.9756 |
0.0043 | 17.0 | 1241 | 0.1615 | 0.7559 | 0.8237 | 0.7883 | 0.9754 |
0.0043 | 18.0 | 1314 | 0.1624 | 0.7612 | 0.8173 | 0.7883 | 0.9759 |
0.0043 | 19.0 | 1387 | 0.1622 | 0.7574 | 0.8205 | 0.7877 | 0.9763 |
0.0043 | 20.0 | 1460 | 0.1620 | 0.7605 | 0.8141 | 0.7864 | 0.9765 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2