WS800_DeiT_42895082

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

• Loss: 0.2587
• Accuracy: 0.975

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	5	0.6389	0.5125
No log	2.0	10	0.1840	0.9375
No log	3.0	15	0.1272	0.9625
No log	4.0	20	0.1958	0.9625
No log	5.0	25	0.1635	0.975
No log	6.0	30	0.2280	0.975
No log	7.0	35	0.2664	0.9625
No log	8.0	40	0.2636	0.9625
No log	9.0	45	0.2582	0.975
0.1252	10.0	50	0.2571	0.975
0.1252	11.0	55	0.2571	0.975
0.1252	12.0	60	0.2572	0.975
0.1252	13.0	65	0.2574	0.975
0.1252	14.0	70	0.2577	0.975
0.1252	15.0	75	0.2580	0.975
0.1252	16.0	80	0.2582	0.975
0.1252	17.0	85	0.2584	0.975
0.1252	18.0	90	0.2586	0.975
0.1252	19.0	95	0.2587	0.975
0.0	20.0	100	0.2587	0.975

Framework versions

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