zinc10M_gpt2_SMILES_bpe_combined_step1
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5863
- Accuracy: 0.8085
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6819 | 1.0 | 10635 | 0.6556 | 0.7912 |
| 0.6466 | 2.0 | 21270 | 0.6256 | 0.7987 |
| 0.6299 | 3.0 | 31905 | 0.6115 | 0.8022 |
| 0.6199 | 4.0 | 42540 | 0.6028 | 0.8044 |
| 0.6132 | 5.0 | 53175 | 0.5972 | 0.8058 |
| 0.6079 | 6.0 | 63810 | 0.5932 | 0.8068 |
| 0.6043 | 7.0 | 74445 | 0.5902 | 0.8075 |
| 0.6019 | 8.0 | 85080 | 0.5885 | 0.8080 |
| 0.6002 | 9.0 | 95715 | 0.5870 | 0.8083 |
| 0.5989 | 10.0 | 106350 | 0.5863 | 0.8085 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0