metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: prot_bert_classification_finetuned_no_finetune
results: []
prot_bert_classification_finetuned_no_finetune
This model is a fine-tuned version of Rostlab/prot_bert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6212
- Accuracy: 0.6473
- F1: 0.6623
- Precision: 0.6201
- Recall: 0.7107
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 |
|---|---|---|---|---|---|---|---|
| 0.6494 | 1.0 | 3332 | 0.6479 | 0.6439 | 0.6679 | 0.6116 | 0.7357 |
| 0.5357 | 2.0 | 6664 | 0.6440 | 0.6148 | 0.6459 | 0.5845 | 0.7218 |
| 0.4661 | 3.0 | 9996 | 0.6265 | 0.6283 | 0.6414 | 0.6047 | 0.6829 |
| 0.506 | 4.0 | 13328 | 0.6192 | 0.6439 | 0.6567 | 0.6187 | 0.6996 |
| 0.4204 | 5.0 | 16660 | 0.6122 | 0.6567 | 0.6752 | 0.6259 | 0.7330 |
| 0.6071 | 6.0 | 19992 | 0.6212 | 0.6473 | 0.6623 | 0.6201 | 0.7107 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1