metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: prot_bert_classification_finetuned
results: []
prot_bert_classification_finetuned
This model is a fine-tuned version of nepp1d0/prot_bert-finetuned-smiles-bindingDB on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5675
- Accuracy: 0.7299
- F1: 0.7377
- Precision: 0.6995
- Recall: 0.7803
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: 1e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 3
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4221 | 1.0 | 3332 | 0.6152 | 0.6615 | 0.6711 | 0.6367 | 0.7093 |
| 0.4133 | 2.0 | 6664 | 0.5840 | 0.6845 | 0.6718 | 0.6805 | 0.6634 |
| 0.4293 | 3.0 | 9996 | 0.5727 | 0.7116 | 0.7094 | 0.6961 | 0.7232 |
| 0.3098 | 4.0 | 13328 | 0.5636 | 0.7163 | 0.7220 | 0.6904 | 0.7566 |
| 0.3881 | 5.0 | 16660 | 0.5629 | 0.7265 | 0.7377 | 0.6918 | 0.7900 |
| 0.4943 | 6.0 | 19992 | 0.5675 | 0.7299 | 0.7377 | 0.6995 | 0.7803 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1