metadata
base_model: google/vit-base-patch16-224-in21k
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: only-lora-beans-vit-base-patch16-224-in21k
results: []
only-lora-beans-vit-base-patch16-224-in21k
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5798
- Accuracy: 0.7594
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: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0967 | 1.0 | 130 | 0.9973 | 0.5414 |
| 1.0161 | 2.0 | 260 | 0.9222 | 0.5789 |
| 0.9472 | 3.0 | 390 | 0.8626 | 0.6391 |
| 0.7532 | 4.0 | 520 | 0.7299 | 0.7143 |
| 0.6792 | 5.0 | 650 | 0.6639 | 0.7068 |
| 0.6645 | 6.0 | 780 | 0.6238 | 0.7218 |
| 0.6056 | 7.0 | 910 | 0.6903 | 0.7444 |
| 0.614 | 8.0 | 1040 | 0.6278 | 0.7068 |
| 0.6298 | 9.0 | 1170 | 0.5370 | 0.7895 |
| 0.5867 | 10.0 | 1300 | 0.5798 | 0.7594 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1