<!-- 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. -->
roberta_large_ner_model_mimic_top10
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7754
- Precision Macro: 0.1399
- Recall Macro: 0.1605
- F1 Macro: 0.1477
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: 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_ratio: 0.3
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision Macro | Recall Macro | F1 Macro |
|---|---|---|---|---|---|---|
| No log | 1.0 | 482 | 0.7678 | 0.8470 | 0.0584 | 0.0521 |
| 1.6117 | 2.0 | 964 | 0.6483 | 0.3520 | 0.0792 | 0.0626 |
| 0.6944 | 3.0 | 1446 | 0.6060 | 0.3800 | 0.0967 | 0.0847 |
| 0.6081 | 4.0 | 1928 | 0.5901 | 0.3978 | 0.0940 | 0.0918 |
| 0.5853 | 5.0 | 2410 | 0.5970 | 0.3109 | 0.1063 | 0.0987 |
| 0.5549 | 6.0 | 2892 | 0.5972 | 0.2083 | 0.1091 | 0.1011 |
| 0.534 | 7.0 | 3374 | 0.5885 | 0.2279 | 0.1297 | 0.1230 |
| 0.5077 | 8.0 | 3856 | 0.6130 | 0.1660 | 0.1304 | 0.1210 |
| 0.4798 | 9.0 | 4338 | 0.6162 | 0.1885 | 0.1533 | 0.1394 |
| 0.4397 | 10.0 | 4820 | 0.6235 | 0.2409 | 0.1448 | 0.1381 |
| 0.4092 | 11.0 | 5302 | 0.6498 | 0.2327 | 0.1453 | 0.1339 |
| 0.3933 | 12.0 | 5784 | 0.6631 | 0.1589 | 0.1590 | 0.1444 |
| 0.3544 | 13.0 | 6266 | 0.6909 | 0.1441 | 0.1613 | 0.1466 |
| 0.3384 | 14.0 | 6748 | 0.7096 | 0.1429 | 0.1584 | 0.1455 |
| 0.3178 | 15.0 | 7230 | 0.7355 | 0.1425 | 0.1571 | 0.1466 |
| 0.297 | 16.0 | 7712 | 0.7348 | 0.1482 | 0.1618 | 0.1498 |
| 0.2803 | 17.0 | 8194 | 0.7569 | 0.1473 | 0.1633 | 0.1516 |
| 0.2633 | 18.0 | 8676 | 0.7645 | 0.1423 | 0.1642 | 0.1511 |
| 0.2586 | 19.0 | 9158 | 0.7731 | 0.1479 | 0.1619 | 0.1523 |
| 0.2516 | 20.0 | 9640 | 0.7754 | 0.1399 | 0.1605 | 0.1477 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.14.0
