bachh

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: 0.5198
Accuracy: 0.8654

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: 0.0002
train_batch_size: 32
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8279	0.11	100	0.9659	0.6697
0.7801	0.22	200	0.8758	0.6725
0.7136	0.34	300	0.7788	0.7178
0.7302	0.45	400	0.7041	0.7438
0.6793	0.56	500	0.6882	0.7431
0.5872	0.67	600	0.6480	0.7683
0.5711	0.78	700	0.6490	0.7588
0.6003	0.9	800	0.6116	0.7727
0.4382	1.01	900	0.6016	0.7883
0.4666	1.12	1000	0.5848	0.7803
0.3944	1.23	1100	0.6039	0.7745
0.3805	1.35	1200	0.4929	0.8221
0.3795	1.46	1300	0.5391	0.8048
0.3727	1.57	1400	0.5303	0.8149
0.3658	1.68	1500	0.5471	0.8160
0.3289	1.79	1600	0.5170	0.8184
0.2832	1.91	1700	0.4795	0.8334
0.2048	2.02	1800	0.4942	0.8300
0.2085	2.13	1900	0.4743	0.8394
0.1449	2.24	2000	0.4642	0.8469
0.1662	2.35	2100	0.4669	0.8426
0.1603	2.47	2200	0.4721	0.8452
0.1079	2.58	2300	0.5236	0.8342
0.1952	2.69	2400	0.4448	0.8493
0.2091	2.8	2500	0.4959	0.8518
0.166	2.91	2600	0.5036	0.8356
0.055	3.03	2700	0.4854	0.8497
0.0639	3.14	2800	0.4987	0.8605
0.0421	3.25	2900	0.5258	0.8543
0.0292	3.36	3000	0.5287	0.8601
0.0136	3.48	3100	0.5250	0.8593
0.0421	3.59	3200	0.5192	0.8647
0.0307	3.7	3300	0.5251	0.8569
0.0536	3.81	3400	0.5300	0.8611
0.0269	3.92	3500	0.5198	0.8654

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2

karoladelk/bachh

bachh

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

为此模型做种