metadata
license: mit
base_model: austin/Austin-MeDeBERTa
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fold_0
results: []
fold_0
This model is a fine-tuned version of austin/Austin-MeDeBERTa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0091
- Precision: 0.7601
- Recall: 0.7219
- F1: 0.7405
- Accuracy: 0.9976
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: 2e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0461 | 1.0 | 635 | 0.0107 | 0.7529 | 0.5858 | 0.6589 | 0.9972 |
| 0.0098 | 2.0 | 1270 | 0.0087 | 0.7176 | 0.7219 | 0.7198 | 0.9974 |
| 0.0068 | 3.0 | 1905 | 0.0091 | 0.7601 | 0.7219 | 0.7405 | 0.9976 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0