metadata
base_model: google/vit-base-patch16-224-in21k
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: vit-base-patch16-224-in21k-lora
results: []
vit-base-patch16-224-in21k-lora
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: 0.3368
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: 0.005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.8192 | 1.0 | 148 | 0.4721 |
0.7016 | 2.0 | 296 | 0.4040 |
0.6583 | 3.0 | 444 | 0.3712 |
0.5792 | 4.0 | 592 | 0.3481 |
0.5452 | 5.0 | 740 | 0.3368 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1