<!-- 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. -->
tmvar_2e-05_0404_ES6_strict_tok1
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: 0.0330
- Precision: 0.8213
- Recall: 0.8629
- F1: 0.8416
- Accuracy: 0.9916
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 |
---|---|---|---|---|---|---|---|
0.7315 | 0.49 | 25 | 0.2102 | 0.0 | 0.0 | 0.0 | 0.9555 |
0.1371 | 0.98 | 50 | 0.1021 | 0.0 | 0.0 | 0.0 | 0.9698 |
0.0836 | 1.47 | 75 | 0.0960 | 0.0 | 0.0 | 0.0 | 0.9725 |
0.0666 | 1.96 | 100 | 0.0526 | 0.0 | 0.0 | 0.0 | 0.9804 |
0.0391 | 2.45 | 125 | 0.0521 | 0.7294 | 0.3147 | 0.4397 | 0.9843 |
0.0252 | 2.94 | 150 | 0.0382 | 0.8630 | 0.6396 | 0.7347 | 0.9899 |
0.016 | 3.43 | 175 | 0.0452 | 0.6496 | 0.7716 | 0.7053 | 0.9872 |
0.0145 | 3.92 | 200 | 0.0272 | 0.8730 | 0.8376 | 0.8549 | 0.9923 |
0.0082 | 4.41 | 225 | 0.0301 | 0.8804 | 0.8223 | 0.8504 | 0.9920 |
0.0058 | 4.9 | 250 | 0.0330 | 0.8213 | 0.8629 | 0.8416 | 0.9916 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3