<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
fisura-hormigon
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0123
- Accuracy: 0.9978
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0989 | 0.17 | 500 | 0.0477 | 0.9871 |
| 0.0531 | 0.33 | 1000 | 0.0493 | 0.9865 |
| 0.046 | 0.5 | 1500 | 0.0381 | 0.9894 |
| 0.0392 | 0.67 | 2000 | 0.1129 | 0.9734 |
| 0.0459 | 0.83 | 2500 | 0.0364 | 0.9904 |
| 0.0255 | 1.0 | 3000 | 0.0305 | 0.9934 |
| 0.0188 | 1.17 | 3500 | 0.0247 | 0.9949 |
| 0.0222 | 1.33 | 4000 | 0.0206 | 0.9921 |
| 0.02 | 1.5 | 4500 | 0.0154 | 0.9952 |
| 0.0191 | 1.67 | 5000 | 0.0132 | 0.9952 |
| 0.0141 | 1.83 | 5500 | 0.0294 | 0.9905 |
| 0.0201 | 2.0 | 6000 | 0.0155 | 0.9968 |
| 0.0114 | 2.17 | 6500 | 0.0161 | 0.9965 |
| 0.0071 | 2.33 | 7000 | 0.0124 | 0.9975 |
| 0.0083 | 2.5 | 7500 | 0.0141 | 0.9969 |
| 0.0143 | 2.67 | 8000 | 0.0242 | 0.9932 |
| 0.0088 | 2.83 | 8500 | 0.0123 | 0.9972 |
| 0.0034 | 3.0 | 9000 | 0.0120 | 0.9972 |
| 0.0064 | 3.17 | 9500 | 0.0100 | 0.9978 |
| 0.0012 | 3.33 | 10000 | 0.0166 | 0.996 |
| 0.006 | 3.5 | 10500 | 0.0110 | 0.998 |
| 0.0007 | 3.67 | 11000 | 0.0126 | 0.9972 |
| 0.0034 | 3.83 | 11500 | 0.0122 | 0.9979 |
| 0.0057 | 4.0 | 12000 | 0.0123 | 0.9978 |
Framework versions
- Transformers 4.29.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
