metadata
license: mit
base_model: Amna100/PreTraining-MLM
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: fold_2
results: []
fold_2
This model is a fine-tuned version of Amna100/PreTraining-MLM on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0123
- Precision: 0.1834
- Recall: 0.3042
- F1: 0.5248
- Pr Auc: 0.6254
- Roc Auc: 0.9352
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: 5e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Pr Auc | Roc Auc |
|---|---|---|---|---|---|---|---|---|
| 0.0324 | 1.0 | 630 | 0.0108 | 0.3745 | 0.9507 | 0.7320 | 0.5652 | 0.9573 |
| 0.0101 | 2.0 | 1260 | 0.0101 | 0.5987 | 0.1560 | 0.1560 | 0.5987 | 0.9585 |
| 0.0067 | 3.0 | 1890 | 0.0114 | 0.0581 | 0.8662 | 0.6011 | 0.6210 | 0.9303 |
| 0.0015 | 4.0 | 2520 | 0.0110 | 0.7081 | 0.0206 | 0.9699 | 0.5885 | 0.9400 |
| 0.0006 | 5.0 | 3150 | 0.0123 | 0.8324 | 0.2123 | 0.1818 | 0.6254 | 0.9352 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1