metadata
license: mit
base_model: Amna100/PreTraining-MLM
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fold_9
results: []
fold_9
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: 0.0125
- Precision: 0.5832
- Recall: 0.6756
- F1: 0.6260
- Accuracy: 0.9991
- Roc Auc: 0.9923
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0286 | 1.0 | 632 | 0.0149 | 0.6469 | 0.4780 | 0.5498 | 0.9990 | 0.9920 | 0.9998 |
| 0.0113 | 2.0 | 1264 | 0.0125 | 0.5832 | 0.6756 | 0.6260 | 0.9991 | 0.9923 | 0.9998 |
| 0.0059 | 3.0 | 1896 | 0.0158 | 0.6230 | 0.5683 | 0.5944 | 0.9991 | 0.9925 | 0.9998 |
| 0.0024 | 4.0 | 2528 | 0.0151 | 0.6636 | 0.7024 | 0.6825 | 0.9992 | 0.9896 | 0.9998 |
| 0.0014 | 5.0 | 3160 | 0.0166 | 0.7341 | 0.5927 | 0.6559 | 0.9993 | 0.9837 | 0.9998 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1