metadata
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: nepp1d0/ChemBERTa_drug_state_classification
model-index:
- name: ChemBERTa_drug_state_classification
results: []
ChemBERTa_drug_state_classification
This model is a fine-tuned version of nepp1d0/ChemBERTa_drug_state_classification on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0463
- Accuracy: 0.9870
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5063 | 1.0 | 240 | 0.3069 | 0.9160 |
| 0.3683 | 2.0 | 480 | 0.2135 | 0.9431 |
| 0.2633 | 3.0 | 720 | 0.1324 | 0.9577 |
| 0.1692 | 4.0 | 960 | 0.0647 | 0.9802 |
| 0.1109 | 5.0 | 1200 | 0.0463 | 0.9870 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.12.1