<!-- 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. -->
distilbert-base-cased-finetuned-paper3
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1966
- Precision: 0.6773
- Recall: 0.7350
- F1: 0.7050
- Accuracy: 0.9687
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 | 0.1851 | 0.4383 | 0.4479 | 0.4431 | 0.9434 |
| No log | 2.0 | 146 | 0.1473 | 0.5455 | 0.5678 | 0.5564 | 0.9593 |
| No log | 3.0 | 219 | 0.1391 | 0.6509 | 0.6530 | 0.6520 | 0.9646 |
| No log | 4.0 | 292 | 0.1236 | 0.6552 | 0.7192 | 0.6857 | 0.9702 |
| No log | 5.0 | 365 | 0.1352 | 0.6724 | 0.7382 | 0.7038 | 0.9693 |
| No log | 6.0 | 438 | 0.1594 | 0.6746 | 0.7129 | 0.6933 | 0.9673 |
| 0.0969 | 7.0 | 511 | 0.1693 | 0.6705 | 0.7382 | 0.7027 | 0.9683 |
| 0.0969 | 8.0 | 584 | 0.1806 | 0.6923 | 0.7382 | 0.7145 | 0.9692 |
| 0.0969 | 9.0 | 657 | 0.1594 | 0.6359 | 0.7603 | 0.6925 | 0.9687 |
| 0.0969 | 10.0 | 730 | 0.1740 | 0.6946 | 0.7319 | 0.7127 | 0.9683 |
| 0.0969 | 11.0 | 803 | 0.1881 | 0.6735 | 0.7287 | 0.7 | 0.9677 |
| 0.0969 | 12.0 | 876 | 0.1932 | 0.7064 | 0.7287 | 0.7174 | 0.9692 |
| 0.0969 | 13.0 | 949 | 0.1890 | 0.6907 | 0.7256 | 0.7077 | 0.9689 |
| 0.0025 | 14.0 | 1022 | 0.1860 | 0.6705 | 0.7445 | 0.7055 | 0.9696 |
| 0.0025 | 15.0 | 1095 | 0.1951 | 0.6706 | 0.7256 | 0.6970 | 0.9688 |
| 0.0025 | 16.0 | 1168 | 0.1936 | 0.6648 | 0.7319 | 0.6967 | 0.9681 |
| 0.0025 | 17.0 | 1241 | 0.1969 | 0.6725 | 0.7319 | 0.7009 | 0.9686 |
| 0.0025 | 18.0 | 1314 | 0.1953 | 0.6792 | 0.7413 | 0.7089 | 0.9692 |
| 0.0025 | 19.0 | 1387 | 0.1960 | 0.6754 | 0.7350 | 0.7039 | 0.9687 |
| 0.0025 | 20.0 | 1460 | 0.1966 | 0.6773 | 0.7350 | 0.7050 | 0.9687 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
