Yepes_2e-05_0404_ES6_strict_tok
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0967
- Precision: 0.6635
- Recall: 0.4192
- F1: 0.5138
- Accuracy: 0.9782
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
- training_steps: 2000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.9417 | 0.43 | 25 | 0.2323 | 0.0 | 0.0 | 0.0 | 0.9663 |
0.267 | 0.86 | 50 | 0.2162 | 0.0 | 0.0 | 0.0 | 0.9663 |
0.2155 | 1.29 | 75 | 0.1810 | 0.0 | 0.0 | 0.0 | 0.9663 |
0.2125 | 1.72 | 100 | 0.1474 | 0.0 | 0.0 | 0.0 | 0.9682 |
0.1642 | 2.16 | 125 | 0.1409 | 0.3333 | 0.0958 | 0.1488 | 0.9705 |
0.152 | 2.59 | 150 | 0.1251 | 0.3284 | 0.2006 | 0.2491 | 0.9729 |
0.1489 | 3.02 | 175 | 0.1130 | 0.3838 | 0.2275 | 0.2857 | 0.9741 |
0.1285 | 3.45 | 200 | 0.1114 | 0.6 | 0.2515 | 0.3544 | 0.9749 |
0.1214 | 3.88 | 225 | 0.1018 | 0.4064 | 0.3054 | 0.3487 | 0.9754 |
0.1576 | 4.31 | 250 | 0.0988 | 0.4760 | 0.3263 | 0.3872 | 0.9749 |
0.0958 | 4.74 | 275 | 0.0967 | 0.6270 | 0.3473 | 0.4470 | 0.9774 |
0.0952 | 5.17 | 300 | 0.0981 | 0.6686 | 0.3503 | 0.4597 | 0.9784 |
0.0852 | 5.6 | 325 | 0.0922 | 0.6649 | 0.3743 | 0.4789 | 0.9782 |
0.0817 | 6.03 | 350 | 0.0936 | 0.5865 | 0.4162 | 0.4869 | 0.9772 |
0.0755 | 6.47 | 375 | 0.0967 | 0.6635 | 0.4192 | 0.5138 | 0.9782 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 9