<!-- 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_ner_model_mimic
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: 0.7676
- Precision Macro: 0.1480
- Recall Macro: 0.1723
- F1 Macro: 0.1554
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: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Precision Macro | Recall Macro | F1 Macro |
---|---|---|---|---|---|---|
0.7391 | 1.0 | 1925 | 0.6420 | 0.2610 | 0.0981 | 0.0713 |
0.6701 | 2.0 | 3850 | 0.6048 | 0.3197 | 0.1168 | 0.1022 |
0.6254 | 3.0 | 5775 | 0.6194 | 0.2210 | 0.1195 | 0.1106 |
0.616 | 4.0 | 7700 | 0.5983 | 0.3199 | 0.1286 | 0.1208 |
0.5441 | 5.0 | 9625 | 0.6234 | 0.1878 | 0.1467 | 0.1365 |
0.5 | 6.0 | 11550 | 0.6900 | 0.1285 | 0.1418 | 0.1298 |
0.4265 | 7.0 | 13475 | 0.7442 | 0.1558 | 0.1571 | 0.1470 |
0.384 | 8.0 | 15400 | 0.7676 | 0.1480 | 0.1723 | 0.1554 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.14.0