<!-- 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-MLM-scirepeval_fos_chemistry-tokenCLS-BATTERY
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0777
- Precision: 0.6676
- Recall: 0.7515
- F1: 0.7071
- Accuracy: 0.9725
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.3933 | 1.0 | 85 | 0.1556 | 0.4379 | 0.4755 | 0.4559 | 0.9568 |
0.1255 | 2.0 | 170 | 0.0980 | 0.6268 | 0.6595 | 0.6428 | 0.9665 |
0.0842 | 3.0 | 255 | 0.0846 | 0.6619 | 0.7147 | 0.6873 | 0.9695 |
0.0655 | 4.0 | 340 | 0.0812 | 0.6587 | 0.7577 | 0.7047 | 0.9715 |
0.058 | 5.0 | 425 | 0.0777 | 0.6676 | 0.7515 | 0.7071 | 0.9725 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2