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: 0.7148
Accuracy: 0.6346

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	0.92	3	1.0361	0.5192
No log	1.85	6	0.9621	0.5962
No log	2.77	9	0.8925	0.6154
0.9964	4.0	13	0.8220	0.5962
0.9964	4.92	16	0.8058	0.5769
0.9964	5.85	19	0.7298	0.6346
0.7724	6.77	22	0.7314	0.6346
0.7724	8.0	26	0.7068	0.6538
0.7724	8.92	29	0.6655	0.6731
0.6697	9.23	30	0.7148	0.6346

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

NDeee/Chess-model

Chess-model

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

NDeee/
Chess-model