<!-- 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. -->
chembert_cased-tokenCLS-CATALYST
This model is a fine-tuned version of jiangg/chembert_cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0542
- Precision: 0.7153
- Recall: 0.8377
- F1: 0.7717
- Accuracy: 0.9826
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0354 | 1.0 | 1114 | 0.0727 | 0.5774 | 0.8754 | 0.6959 | 0.9761 |
0.0328 | 2.0 | 2228 | 0.0679 | 0.6808 | 0.8406 | 0.7523 | 0.9821 |
0.0259 | 3.0 | 3342 | 0.0542 | 0.7153 | 0.8377 | 0.7717 | 0.9826 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3