metadata
library_name: transformers
base_model: allenai/biomed_roberta_base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BioMedRoBERTa-finetuned-valid-testing-0.0002-32
results: []
BioMedRoBERTa-finetuned-valid-testing-0.0002-32
This model is a fine-tuned version of allenai/biomed_roberta_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0879
- Precision: 0.8178
- Recall: 0.8292
- F1: 0.8235
- Accuracy: 0.9763
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: 0.0002
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 209 | 0.1001 | 0.7504 | 0.7779 | 0.7639 | 0.9695 |
| No log | 2.0 | 418 | 0.0776 | 0.8208 | 0.8153 | 0.8180 | 0.9771 |
| 0.2051 | 3.0 | 627 | 0.0812 | 0.8026 | 0.8140 | 0.8083 | 0.9725 |
| 0.2051 | 4.0 | 836 | 0.0850 | 0.7953 | 0.8254 | 0.8101 | 0.9758 |
| 0.0355 | 5.0 | 1045 | 0.0879 | 0.8178 | 0.8292 | 0.8235 | 0.9763 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1