metadata
base_model: ahmedesmail16/Train-Test-Augmentation-V2-beit-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Train-Test-Augmentation-V2-beit-large
results: []
Train-Test-Augmentation-V2-beit-large
This model is a fine-tuned version of ahmedesmail16/Train-Test-Augmentation-V2-beit-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7562
- Accuracy: 0.8519
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0753 | 1.0 | 55 | 0.5558 | 0.8519 |
| 0.0191 | 2.0 | 110 | 0.6652 | 0.8447 |
| 0.0062 | 3.0 | 165 | 0.5826 | 0.8582 |
| 0.0018 | 4.0 | 220 | 0.7664 | 0.8408 |
| 0.001 | 5.0 | 275 | 0.7562 | 0.8519 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2