ec-biogpt-noised-pubmed-v4
This model is a fine-tuned version of microsoft/biogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8204
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
- lr_scheduler_warmup_steps: 10
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7942 | 0.11 | 500 | 1.8358 |
| 1.9793 | 0.21 | 1000 | 1.8000 |
| 1.9244 | 0.32 | 1500 | 1.7763 |
| 1.8871 | 0.43 | 2000 | 1.7623 |
| 1.6525 | 0.54 | 2500 | 1.7511 |
| 1.6871 | 0.64 | 3000 | 1.7401 |
| 1.5771 | 0.75 | 3500 | 1.7315 |
| 1.732 | 0.86 | 4000 | 1.7278 |
| 1.9909 | 0.96 | 4500 | 1.7196 |
| 1.5173 | 1.07 | 5000 | 1.7204 |
| 1.6015 | 1.18 | 5500 | 1.7206 |
| 1.6817 | 1.28 | 6000 | 1.7183 |
| 1.6475 | 1.39 | 6500 | 1.7161 |
| 1.7425 | 1.5 | 7000 | 1.7114 |
| 1.4702 | 1.61 | 7500 | 1.7067 |
| 1.5635 | 1.71 | 8000 | 1.7078 |
| 1.574 | 1.82 | 8500 | 1.7020 |
| 1.6691 | 1.93 | 9000 | 1.6985 |
| 1.4796 | 2.03 | 9500 | 1.7339 |
| 1.472 | 2.14 | 10000 | 1.7354 |
| 1.4476 | 2.25 | 10500 | 1.7331 |
| 1.4402 | 2.35 | 11000 | 1.7327 |
| 1.5988 | 2.46 | 11500 | 1.7328 |
| 1.3682 | 2.57 | 12000 | 1.7299 |
| 1.4988 | 2.68 | 12500 | 1.7281 |
| 1.4514 | 2.78 | 13000 | 1.7257 |
| 1.6356 | 2.89 | 13500 | 1.7264 |
| 1.6653 | 3.0 | 14000 | 1.7240 |
| 1.2013 | 3.1 | 14500 | 1.7782 |
| 1.2864 | 3.21 | 15000 | 1.7770 |
| 1.4638 | 3.32 | 15500 | 1.7817 |
| 1.2501 | 3.43 | 16000 | 1.7787 |
| 1.4613 | 3.53 | 16500 | 1.7791 |
| 1.1816 | 3.64 | 17000 | 1.7767 |
| 1.1841 | 3.75 | 17500 | 1.7786 |
| 1.2382 | 3.85 | 18000 | 1.7743 |
| 1.2868 | 3.96 | 18500 | 1.7749 |
| 1.2074 | 4.07 | 19000 | 1.8167 |
| 1.1657 | 4.17 | 19500 | 1.8224 |
| 1.1851 | 4.28 | 20000 | 1.8197 |
| 1.1141 | 4.39 | 20500 | 1.8225 |
| 1.0628 | 4.5 | 21000 | 1.8202 |
| 1.0946 | 4.6 | 21500 | 1.8209 |
| 1.037 | 4.71 | 22000 | 1.8201 |
| 1.1277 | 4.82 | 22500 | 1.8206 |
| 1.2766 | 4.92 | 23000 | 1.8204 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3