MultiCorp_norm_label_2e-05_0404_ES2_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: 0.0410
- Precision: 0.5775
- Recall: 0.6445
- F1: 0.6091
- Accuracy: 0.9845
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 |
---|---|---|---|---|---|---|---|
0.4669 | 0.08 | 25 | 0.1415 | 0.0 | 0.0 | 0.0 | 0.9734 |
0.1519 | 0.15 | 50 | 0.1264 | 0.0 | 0.0 | 0.0 | 0.9734 |
0.1363 | 0.23 | 75 | 0.1108 | 0.0 | 0.0 | 0.0 | 0.9734 |
0.1097 | 0.31 | 100 | 0.0915 | 0.0 | 0.0 | 0.0 | 0.9734 |
0.1037 | 0.39 | 125 | 0.0883 | 0.0 | 0.0 | 0.0 | 0.9734 |
0.0746 | 0.46 | 150 | 0.0736 | 0.0 | 0.0 | 0.0 | 0.9750 |
0.0846 | 0.54 | 175 | 0.0683 | 0.0 | 0.0 | 0.0 | 0.9742 |
0.0764 | 0.62 | 200 | 0.0671 | 0.0 | 0.0 | 0.0 | 0.9751 |
0.0767 | 0.7 | 225 | 0.0659 | 0.64 | 0.0479 | 0.0891 | 0.9778 |
0.0689 | 0.77 | 250 | 0.0746 | 0.5244 | 0.1527 | 0.2365 | 0.9703 |
0.0718 | 0.85 | 275 | 0.0618 | 0.5739 | 0.1220 | 0.2012 | 0.9760 |
0.0696 | 0.93 | 300 | 0.0511 | 0.6404 | 0.2799 | 0.3896 | 0.9808 |
0.0633 | 1.01 | 325 | 0.0498 | 0.6383 | 0.4371 | 0.5189 | 0.9812 |
0.0358 | 1.08 | 350 | 0.0482 | 0.5319 | 0.5052 | 0.5182 | 0.9825 |
0.0575 | 1.16 | 375 | 0.0430 | 0.6702 | 0.4775 | 0.5577 | 0.9838 |
0.0432 | 1.24 | 400 | 0.0439 | 0.6302 | 0.5524 | 0.5888 | 0.9828 |
0.0415 | 1.32 | 425 | 0.0426 | 0.6299 | 0.5681 | 0.5974 | 0.9833 |
0.0454 | 1.39 | 450 | 0.0404 | 0.6263 | 0.5269 | 0.5724 | 0.9847 |
0.0421 | 1.47 | 475 | 0.0416 | 0.5990 | 0.6587 | 0.6275 | 0.9836 |
0.0487 | 1.55 | 500 | 0.0410 | 0.5775 | 0.6445 | 0.6091 | 0.9845 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.