WS800_ViT_42820348

This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1485
• Accuracy: 1.0

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.96	6	0.6689	0.925
No log	1.92	12	0.5584	0.975
No log	2.88	18	0.4389	0.9875
No log	4.0	25	0.3280	0.9875
No log	4.96	31	0.2582	1.0
No log	5.92	37	0.2105	1.0
No log	6.88	43	0.1805	1.0
0.3864	8.0	50	0.1601	1.0
0.3864	8.96	56	0.1504	1.0
0.3864	9.6	60	0.1485	1.0

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu118
• Datasets 2.16.1
• Tokenizers 0.15.0