results_G1
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2389
- Treatment: 0.9038
- Chronic: 0.9179
- Cancer: 0.9009
- Allergy: 0.8278
- Other: 0.9482
- Weighted Avg: 0.9309
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Treatment | Chronic | Cancer | Allergy | Other | Weighted Avg |
|---|---|---|---|---|---|---|---|---|---|
| 1.1562 | 0.2717 | 100 | 0.6532 | 0.6522 | 0.6504 | 0.1040 | 0.0 | 0.8459 | 0.7235 |
| 0.4683 | 0.5435 | 200 | 0.3505 | 0.8375 | 0.8724 | 0.7987 | 0.0 | 0.9169 | 0.8794 |
| 0.329 | 0.8152 | 300 | 0.2931 | 0.8642 | 0.8808 | 0.8561 | 0.6707 | 0.9307 | 0.9030 |
| 0.2747 | 1.0870 | 400 | 0.3256 | 0.8618 | 0.9007 | 0.8671 | 0.7720 | 0.9269 | 0.9055 |
| 0.2343 | 1.3587 | 500 | 0.2949 | 0.8779 | 0.8882 | 0.8597 | 0.7990 | 0.9353 | 0.9108 |
| 0.229 | 1.6304 | 600 | 0.2585 | 0.8864 | 0.9017 | 0.8653 | 0.8235 | 0.9385 | 0.9171 |
| 0.1988 | 1.9022 | 700 | 0.2474 | 0.8793 | 0.9128 | 0.8916 | 0.8265 | 0.9427 | 0.9218 |
| 0.1591 | 2.1739 | 800 | 0.2588 | 0.8928 | 0.9111 | 0.8853 | 0.8040 | 0.9429 | 0.9235 |
| 0.1281 | 2.4457 | 900 | 0.2682 | 0.8952 | 0.9121 | 0.8966 | 0.815 | 0.9407 | 0.9236 |
| 0.1298 | 2.7174 | 1000 | 0.2450 | 0.9015 | 0.9155 | 0.8937 | 0.8152 | 0.9478 | 0.9292 |
| 0.1053 | 2.9891 | 1100 | 0.2389 | 0.9038 | 0.9179 | 0.9009 | 0.8278 | 0.9482 | 0.9309 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1