<!-- 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-uncased-finetuned-scientific-exp
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1314
- Precision: 0.6519
- Recall: 0.7167
- F1: 0.6828
- Accuracy: 0.9631
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 | 81 | 0.3013 | 0.3445 | 0.2600 | 0.2964 | 0.9177 |
No log | 2.0 | 162 | 0.2062 | 0.5736 | 0.4038 | 0.4739 | 0.9378 |
No log | 3.0 | 243 | 0.1553 | 0.6575 | 0.6089 | 0.6323 | 0.9571 |
No log | 4.0 | 324 | 0.1360 | 0.6427 | 0.6617 | 0.6521 | 0.9627 |
No log | 5.0 | 405 | 0.1314 | 0.6519 | 0.7167 | 0.6828 | 0.9631 |
No log | 6.0 | 486 | 0.1341 | 0.6485 | 0.7294 | 0.6866 | 0.9625 |
0.2011 | 7.0 | 567 | 0.1357 | 0.6564 | 0.7230 | 0.6881 | 0.9639 |
0.2011 | 8.0 | 648 | 0.1409 | 0.6559 | 0.7294 | 0.6907 | 0.9644 |
0.2011 | 9.0 | 729 | 0.1447 | 0.6591 | 0.7400 | 0.6972 | 0.9638 |
0.2011 | 10.0 | 810 | 0.1447 | 0.6597 | 0.7378 | 0.6966 | 0.9642 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3