roberta-base-finetuned-papernew
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1716
- Precision: 0.7586
- Recall: 0.8056
- F1: 0.7814
- Accuracy: 0.9734
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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 81 | 0.1846 | 0.6825 | 0.4845 | 0.5667 | 0.9497 |
No log | 2.0 | 162 | 0.1238 | 0.6952 | 0.6873 | 0.6912 | 0.9671 |
No log | 3.0 | 243 | 0.1032 | 0.7351 | 0.7662 | 0.7503 | 0.9711 |
No log | 4.0 | 324 | 0.1060 | 0.8169 | 0.7915 | 0.8040 | 0.9767 |
No log | 5.0 | 405 | 0.1144 | 0.7892 | 0.7803 | 0.7847 | 0.9743 |
No log | 6.0 | 486 | 0.1257 | 0.7378 | 0.8085 | 0.7715 | 0.9706 |
0.1393 | 7.0 | 567 | 0.1392 | 0.7379 | 0.8169 | 0.7754 | 0.9705 |
0.1393 | 8.0 | 648 | 0.1333 | 0.7304 | 0.7859 | 0.7571 | 0.9709 |
0.1393 | 9.0 | 729 | 0.1419 | 0.7539 | 0.8113 | 0.7815 | 0.9725 |
0.1393 | 10.0 | 810 | 0.1570 | 0.7385 | 0.8113 | 0.7732 | 0.9712 |
0.1393 | 11.0 | 891 | 0.1645 | 0.7318 | 0.7915 | 0.7605 | 0.9704 |
0.1393 | 12.0 | 972 | 0.1586 | 0.7506 | 0.8141 | 0.7811 | 0.9733 |
0.0126 | 13.0 | 1053 | 0.1589 | 0.7474 | 0.8169 | 0.7806 | 0.9747 |
0.0126 | 14.0 | 1134 | 0.1616 | 0.7527 | 0.7972 | 0.7743 | 0.9737 |
0.0126 | 15.0 | 1215 | 0.1642 | 0.7410 | 0.8141 | 0.7758 | 0.9736 |
0.0126 | 16.0 | 1296 | 0.1725 | 0.7429 | 0.8056 | 0.7730 | 0.9726 |
0.0126 | 17.0 | 1377 | 0.1686 | 0.7487 | 0.8056 | 0.7761 | 0.9737 |
0.0126 | 18.0 | 1458 | 0.1657 | 0.7533 | 0.8 | 0.7760 | 0.9740 |
0.0034 | 19.0 | 1539 | 0.1716 | 0.7493 | 0.8085 | 0.7778 | 0.9738 |
0.0034 | 20.0 | 1620 | 0.1716 | 0.7586 | 0.8056 | 0.7814 | 0.9734 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.