tmvar_5e-05_250
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: 0.0104
- Precision: 0.8718
- Recall: 0.9189
- F1: 0.8947
- Accuracy: 0.9977
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: 5e-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: 500
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2897 | 1.0 | 25 | 0.0896 | 0.0 | 0.0 | 0.0 | 0.9858 |
0.0759 | 2.0 | 50 | 0.0302 | 0.5522 | 0.4 | 0.4639 | 0.9898 |
0.0347 | 3.0 | 75 | 0.0175 | 0.6789 | 0.6973 | 0.688 | 0.9945 |
0.0174 | 4.0 | 100 | 0.0133 | 0.76 | 0.8216 | 0.7896 | 0.9962 |
0.0084 | 5.0 | 125 | 0.0125 | 0.805 | 0.8703 | 0.8364 | 0.9967 |
0.0048 | 6.0 | 150 | 0.0090 | 0.8859 | 0.8811 | 0.8835 | 0.9977 |
0.0025 | 7.0 | 175 | 0.0097 | 0.8382 | 0.9243 | 0.8792 | 0.9977 |
0.0017 | 8.0 | 200 | 0.0089 | 0.8529 | 0.9405 | 0.8946 | 0.9980 |
0.0015 | 9.0 | 225 | 0.0099 | 0.8357 | 0.9351 | 0.8827 | 0.9979 |
0.0012 | 10.0 | 250 | 0.0104 | 0.8522 | 0.9351 | 0.8918 | 0.9979 |
0.0011 | 11.0 | 275 | 0.0104 | 0.8798 | 0.8703 | 0.875 | 0.9972 |
0.0009 | 12.0 | 300 | 0.0098 | 0.8718 | 0.9189 | 0.8947 | 0.9977 |
0.0007 | 13.0 | 325 | 0.0100 | 0.8718 | 0.9189 | 0.8947 | 0.9977 |
0.0006 | 14.0 | 350 | 0.0104 | 0.8718 | 0.9189 | 0.8947 | 0.9977 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
- Downloads last month
- 5
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.