tmvar_0.0001_0404_ES6
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: 0.1174
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.9822
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: 0.0001
- 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 |
---|---|---|---|---|---|---|---|
0.2308 | 0.49 | 25 | 0.1155 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.0985 | 0.98 | 50 | 0.1247 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.1077 | 1.47 | 75 | 0.1174 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.0969 | 1.96 | 100 | 0.1170 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.0964 | 2.45 | 125 | 0.1173 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.1034 | 2.94 | 150 | 0.1145 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.0936 | 3.43 | 175 | 0.1195 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.1066 | 3.92 | 200 | 0.1175 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.0929 | 4.41 | 225 | 0.1171 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.1015 | 4.9 | 250 | 0.1170 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.1154 | 5.39 | 275 | 0.1142 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.0905 | 5.88 | 300 | 0.1188 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.0883 | 6.37 | 325 | 0.1190 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.097 | 6.86 | 350 | 0.1161 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.111 | 7.35 | 375 | 0.1166 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.1029 | 7.84 | 400 | 0.1151 | 0.0 | 0.0 | 0.0 | 0.9822 |
0.091 | 8.33 | 425 | 0.1174 | 0.0 | 0.0 | 0.0 | 0.9822 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2
- Downloads last month
- 4
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.