metadata
license: mit
base_model: Amna100/PreTraining-MLM
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fold_14
results: []
fold_14
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: 0.0110
- Precision: 0.6892
- Recall: 0.7390
- F1: 0.7132
- Accuracy: 0.9993
- Roc Auc: 0.9901
- Pr Auc: 0.9998
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Roc Auc | Pr Auc |
|---|---|---|---|---|---|---|---|---|---|
| 0.0331 | 1.0 | 632 | 0.0121 | 0.7739 | 0.4599 | 0.5770 | 0.9992 | 0.9907 | 0.9998 |
| 0.0123 | 2.0 | 1264 | 0.0110 | 0.6892 | 0.7390 | 0.7132 | 0.9993 | 0.9901 | 0.9998 |
| 0.0067 | 3.0 | 1896 | 0.0113 | 0.6801 | 0.6977 | 0.6888 | 0.9993 | 0.9925 | 0.9998 |
| 0.002 | 4.0 | 2528 | 0.0160 | 0.8169 | 0.6227 | 0.7067 | 0.9994 | 0.9836 | 0.9997 |
| 0.0017 | 5.0 | 3160 | 0.0139 | 0.7824 | 0.7339 | 0.7573 | 0.9995 | 0.9890 | 0.9998 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1