metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: tmvar_0.0001_ES12
results: []
tmvar_0.0001_ES12
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: 0.0194
- Precision: 0.8877
- Recall: 0.8973
- F1: 0.8925
- Accuracy: 0.9968
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: 1000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2263 | 1.47 | 25 | 0.0788 | 0.0 | 0.0 | 0.0 | 0.9843 |
0.0492 | 2.94 | 50 | 0.0355 | 0.2576 | 0.3676 | 0.3029 | 0.9863 |
0.0258 | 4.41 | 75 | 0.0224 | 0.6 | 0.6811 | 0.6380 | 0.9933 |
0.013 | 5.88 | 100 | 0.0141 | 0.8267 | 0.9027 | 0.8630 | 0.9969 |
0.0031 | 7.35 | 125 | 0.0162 | 0.8218 | 0.8973 | 0.8579 | 0.9971 |
0.0028 | 8.82 | 150 | 0.0187 | 0.8449 | 0.8541 | 0.8495 | 0.9961 |
0.0024 | 10.29 | 175 | 0.0154 | 0.8267 | 0.9027 | 0.8630 | 0.9965 |
0.0014 | 11.76 | 200 | 0.0159 | 0.8221 | 0.9243 | 0.8702 | 0.9966 |
0.0013 | 13.24 | 225 | 0.0179 | 0.8579 | 0.8811 | 0.8693 | 0.9971 |
0.0009 | 14.71 | 250 | 0.0165 | 0.8807 | 0.8378 | 0.8587 | 0.9964 |
0.0005 | 16.18 | 275 | 0.0184 | 0.8549 | 0.8919 | 0.8730 | 0.9966 |
0.0003 | 17.65 | 300 | 0.0188 | 0.8777 | 0.8919 | 0.8847 | 0.9967 |
0.0002 | 19.12 | 325 | 0.0195 | 0.8474 | 0.8703 | 0.8587 | 0.9964 |
0.0002 | 20.59 | 350 | 0.0192 | 0.8836 | 0.9027 | 0.8930 | 0.9969 |
0.0003 | 22.06 | 375 | 0.0191 | 0.8889 | 0.9081 | 0.8984 | 0.9969 |
0.0002 | 23.53 | 400 | 0.0194 | 0.8877 | 0.8973 | 0.8925 | 0.9968 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2