metadata
license: mit
base_model: Amna100/PreTraining-MLM
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fold_4
results: []
fold_4
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: 0.0096
- Precision: 0.7641
- Recall: 0.6825
- F1: 0.7210
- Accuracy: 0.9995
- Roc Auc: 0.9961
- Pr Auc: 0.9999
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0278 | 1.0 | 632 | 0.0107 | 0.5932 | 0.7270 | 0.6533 | 0.9993 | 0.9948 | 0.9999 |
| 0.01 | 2.0 | 1264 | 0.0096 | 0.7641 | 0.6825 | 0.7210 | 0.9995 | 0.9961 | 0.9999 |
| 0.0056 | 3.0 | 1896 | 0.0131 | 0.7207 | 0.6202 | 0.6667 | 0.9994 | 0.9827 | 0.9997 |
| 0.0025 | 4.0 | 2528 | 0.0114 | 0.7937 | 0.6736 | 0.7287 | 0.9995 | 0.9860 | 0.9997 |
| 0.0012 | 5.0 | 3160 | 0.0141 | 0.7727 | 0.6558 | 0.7095 | 0.9995 | 0.9860 | 0.9998 |
| 0.0008 | 6.0 | 3792 | 0.0126 | 0.7659 | 0.6795 | 0.7201 | 0.9995 | 0.9894 | 0.9998 |
| 0.0007 | 7.0 | 4424 | 0.0146 | 0.7845 | 0.6588 | 0.7161 | 0.9995 | 0.9917 | 0.9998 |
| 0.0003 | 8.0 | 5056 | 0.0161 | 0.7789 | 0.6588 | 0.7138 | 0.9995 | 0.9908 | 0.9998 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1