Chess-model

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: 1.2505
• Accuracy: 0.65

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	5	1.5147	0.525
1.4786	2.0	10	1.4011	0.575
1.4786	3.0	15	1.3046	0.5875
1.2682	4.0	20	1.2755	0.625
1.2682	5.0	25	1.2505	0.65

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2