<!-- 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. -->
saransh_biogpt
This model is a fine-tuned version of microsoft/biogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2022
- Precision: 0.3780
- Recall: 0.4015
- F1: 0.3894
- Accuracy: 0.9409
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.3116 | 1.0 | 679 | 0.2155 | 0.2667 | 0.3139 | 0.2884 | 0.9330 |
0.2212 | 2.0 | 1358 | 0.1951 | 0.3385 | 0.3355 | 0.3369 | 0.9396 |
0.1687 | 3.0 | 2037 | 0.2022 | 0.3780 | 0.4015 | 0.3894 | 0.9409 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3