<!-- 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-papernew5
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0864
- Precision: 0.7835
- Recall: 0.8144
- F1: 0.7986
- Accuracy: 0.9742
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | 0.1872 | 0.6657 | 0.5174 | 0.5822 | 0.9511 |
| No log | 2.0 | 162 | 0.1321 | 0.6189 | 0.7912 | 0.6945 | 0.9585 |
| No log | 3.0 | 243 | 0.0864 | 0.7835 | 0.8144 | 0.7986 | 0.9742 |
| No log | 4.0 | 324 | 0.0891 | 0.7532 | 0.8144 | 0.7826 | 0.9723 |
| No log | 5.0 | 405 | 0.1004 | 0.7542 | 0.8399 | 0.7947 | 0.9723 |
| No log | 6.0 | 486 | 0.1197 | 0.7267 | 0.8515 | 0.7842 | 0.9677 |
| 0.1476 | 7.0 | 567 | 0.1237 | 0.7605 | 0.8399 | 0.7982 | 0.9709 |
| 0.1476 | 8.0 | 648 | 0.1104 | 0.7383 | 0.8445 | 0.7879 | 0.9728 |
| 0.1476 | 9.0 | 729 | 0.1179 | 0.7863 | 0.8283 | 0.8068 | 0.9742 |
| 0.1476 | 10.0 | 810 | 0.1150 | 0.7811 | 0.8608 | 0.8190 | 0.9752 |
| 0.1476 | 11.0 | 891 | 0.1273 | 0.7602 | 0.8608 | 0.8074 | 0.9728 |
| 0.1476 | 12.0 | 972 | 0.1230 | 0.7711 | 0.8677 | 0.8166 | 0.9751 |
| 0.014 | 13.0 | 1053 | 0.1280 | 0.7815 | 0.8631 | 0.8203 | 0.9753 |
| 0.014 | 14.0 | 1134 | 0.1285 | 0.7755 | 0.8654 | 0.8180 | 0.9753 |
| 0.014 | 15.0 | 1215 | 0.1336 | 0.7639 | 0.8631 | 0.8105 | 0.9740 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
