pre_CIDAUTv3
This model is a fine-tuned version of ricardoSLabs/pre_CIDAUTv2 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1209
- Accuracy: 0.9841
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 |
|---|---|---|---|---|
| No log | 0.8889 | 4 | 0.5177 | 0.7937 |
| No log | 2.0 | 9 | 0.3085 | 0.8889 |
| 1.0669 | 2.8889 | 13 | 0.2461 | 0.8889 |
| 1.0669 | 4.0 | 18 | 0.1346 | 0.9683 |
| 0.2558 | 4.4444 | 20 | 0.1209 | 0.9841 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0