bert_base_mimic_iii_token_classification_top15_DEF_2
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8977
- Precision Macro: 0.1807
- Recall Macro: 0.1701
- F1 Macro: 0.1700
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision Macro | Recall Macro | F1 Macro |
|---|---|---|---|---|---|---|
| 0.8814 | 1.0 | 1065 | 0.7602 | 0.5675 | 0.0648 | 0.0404 |
| 0.7083 | 2.0 | 2130 | 0.6557 | 0.5553 | 0.1024 | 0.0923 |
| 0.6707 | 3.0 | 3195 | 0.6360 | 0.3861 | 0.1243 | 0.1187 |
| 0.6561 | 4.0 | 4260 | 0.6275 | 0.3424 | 0.1449 | 0.1426 |
| 0.6443 | 5.0 | 5325 | 0.6251 | 0.3082 | 0.1401 | 0.1429 |
| 0.6059 | 6.0 | 6390 | 0.6457 | 0.3239 | 0.1630 | 0.1557 |
| 0.5489 | 7.0 | 7455 | 0.6658 | 0.3197 | 0.1281 | 0.1269 |
| 0.4992 | 8.0 | 8520 | 0.7151 | 0.2011 | 0.1699 | 0.1599 |
| 0.4778 | 9.0 | 9585 | 0.7378 | 0.1996 | 0.1855 | 0.1787 |
| 0.4423 | 10.0 | 10650 | 0.7876 | 0.1956 | 0.1676 | 0.1673 |
| 0.3968 | 11.0 | 11715 | 0.8177 | 0.1755 | 0.1796 | 0.1733 |
| 0.3505 | 12.0 | 12780 | 0.8406 | 0.1823 | 0.1792 | 0.1756 |
| 0.3229 | 13.0 | 13845 | 0.8747 | 0.1708 | 0.1826 | 0.1726 |
| 0.3141 | 14.0 | 14910 | 0.8977 | 0.1807 | 0.1701 | 0.1700 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.14.0