metadata
license: mit
base_model: tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: PolizzeDonut-CR-ProvaCluster3di7-7Epochs-WD0.01-EvalStratEpoch
results: []
PolizzeDonut-CR-ProvaCluster3di7-7Epochs-WD0.01-EvalStratEpoch
This model is a fine-tuned version of tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1586
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 68 | 0.1404 |
| 0.17 | 2.0 | 136 | 0.1345 |
| 0.1327 | 3.0 | 204 | 0.1421 |
| 0.1327 | 4.0 | 272 | 0.1463 |
| 0.0872 | 5.0 | 340 | 0.1620 |
| 0.0684 | 6.0 | 408 | 0.1580 |
| 0.0684 | 7.0 | 476 | 0.1586 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2