<!-- 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. -->
bert_large_mimic_iii_token_classification_12ep_top5
This model is a fine-tuned version of bert-large-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8545
- Precision Macro: 0.2731
- Recall Macro: 0.2807
- F1 Macro: 0.2765
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: 4
- 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: 12
Training results
Training Loss | Epoch | Step | Validation Loss | Precision Macro | Recall Macro | F1 Macro |
---|---|---|---|---|---|---|
0.5697 | 1.0 | 1549 | 0.4916 | 0.1175 | 0.1506 | 0.1315 |
0.4627 | 2.0 | 3098 | 0.4687 | 0.2314 | 0.1996 | 0.2142 |
0.4697 | 3.0 | 4647 | 0.4434 | 0.2726 | 0.2398 | 0.2512 |
0.4566 | 4.0 | 6196 | 0.4385 | 0.2204 | 0.2028 | 0.2071 |
0.422 | 5.0 | 7745 | 0.4470 | 0.2051 | 0.2278 | 0.2048 |
0.3656 | 6.0 | 9294 | 0.4861 | 0.2949 | 0.2646 | 0.2744 |
0.3372 | 7.0 | 10843 | 0.5425 | 0.2695 | 0.2488 | 0.2506 |
0.2773 | 8.0 | 12392 | 0.5894 | 0.2419 | 0.2598 | 0.2473 |
0.2363 | 9.0 | 13941 | 0.7030 | 0.2419 | 0.2643 | 0.2508 |
0.1938 | 10.0 | 15490 | 0.7220 | 0.2521 | 0.2800 | 0.2643 |
0.1853 | 11.0 | 17039 | 0.8021 | 0.2719 | 0.2793 | 0.2746 |
0.1449 | 12.0 | 18588 | 0.8545 | 0.2731 | 0.2807 | 0.2765 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.14.0