metadata
license: mit
base_model: Amna100/PreTraining-MLM
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fold_1
results: []
fold_1
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: 0.0113
- Precision: 0.8172
- Recall: 0.5823
- F1: 0.6801
- Accuracy: 0.9993
- Roc Auc: 0.9933
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0326 | 1.0 | 632 | 0.0138 | 0.6507 | 0.4668 | 0.5436 | 0.9991 | 0.9909 | 0.9998 |
| 0.0116 | 2.0 | 1264 | 0.0113 | 0.8172 | 0.5823 | 0.6801 | 0.9993 | 0.9933 | 0.9998 |
| 0.0071 | 3.0 | 1896 | 0.0131 | 0.7896 | 0.5995 | 0.6816 | 0.9993 | 0.9915 | 0.9998 |
| 0.0023 | 4.0 | 2528 | 0.0165 | 0.6275 | 0.6953 | 0.6597 | 0.9991 | 0.9899 | 0.9998 |
| 0.0013 | 5.0 | 3160 | 0.0173 | 0.7465 | 0.6585 | 0.6997 | 0.9993 | 0.9827 | 0.9996 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1