<!-- 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. -->
biobert-finetuned-ner
This model is a fine-tuned version of dmis-lab/biobert-v1.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0280
- Precision: 0.9316
- Recall: 0.9303
- F1: 0.9310
- Accuracy: 0.9953
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0311 | 1.0 | 6070 | 0.0278 | 0.8892 | 0.9098 | 0.8994 | 0.9939 |
0.0213 | 2.0 | 12140 | 0.0330 | 0.9133 | 0.9071 | 0.9102 | 0.9934 |
0.0132 | 3.0 | 18210 | 0.0224 | 0.9283 | 0.9194 | 0.9238 | 0.9952 |
0.0078 | 4.0 | 24280 | 0.0243 | 0.9231 | 0.9180 | 0.9205 | 0.9949 |
0.0068 | 5.0 | 30350 | 0.0222 | 0.9253 | 0.9303 | 0.9278 | 0.9957 |
0.0035 | 6.0 | 36420 | 0.0245 | 0.9243 | 0.9344 | 0.9293 | 0.9955 |
0.0039 | 7.0 | 42490 | 0.0282 | 0.9283 | 0.9372 | 0.9327 | 0.9954 |
0.0008 | 8.0 | 48560 | 0.0280 | 0.9316 | 0.9303 | 0.9310 | 0.9953 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2