metadata
base_model: jarod0411/zinc10M_gpt2_SMILES_bpe_combined_step1
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: stage1
results: []
stage1
This model is a fine-tuned version of jarod0411/zinc10M_gpt2_SMILES_bpe_combined_step1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3311
- Accuracy: 0.8936
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: 24
- eval_batch_size: 24
- seed: 1
- distributed_type: multi-GPU
- num_devices: 6
- total_train_batch_size: 144
- total_eval_batch_size: 144
- 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 |
|---|---|---|---|---|
| 0.375 | 1.0 | 23931 | 0.3615 | 0.8853 |
| 0.3609 | 2.0 | 47862 | 0.3494 | 0.8887 |
| 0.3533 | 3.0 | 71793 | 0.3432 | 0.8904 |
| 0.3486 | 4.0 | 95724 | 0.3394 | 0.8914 |
| 0.3456 | 5.0 | 119655 | 0.3367 | 0.8921 |
| 0.3432 | 6.0 | 143586 | 0.3346 | 0.8927 |
| 0.3412 | 7.0 | 167517 | 0.3333 | 0.8930 |
| 0.3397 | 8.0 | 191448 | 0.3322 | 0.8933 |
| 0.339 | 9.0 | 215379 | 0.3314 | 0.8935 |
| 0.3383 | 10.0 | 239310 | 0.3311 | 0.8936 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2