beit-base-patch16-224-hasta-65-fold5

This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.1241
• Accuracy: 0.5556

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.5714	1	1.1680	0.3333
No log	1.7143	3	1.2100	0.1944
No log	2.8571	5	1.3667	0.2778
No log	4.0	7	1.1208	0.3889
No log	4.5714	8	1.1168	0.3611
1.132	5.7143	10	1.4031	0.2778
1.132	6.8571	12	1.2012	0.3333
1.132	8.0	14	1.2353	0.2778
1.132	8.5714	15	1.2099	0.3056
1.132	9.7143	17	1.0942	0.3611
1.132	10.8571	19	1.1301	0.4444
1.0271	12.0	21	1.0591	0.4167
1.0271	12.5714	22	1.0648	0.4444
1.0271	13.7143	24	1.1125	0.4722
1.0271	14.8571	26	1.1097	0.4722
1.0271	16.0	28	1.0616	0.4444
1.0271	16.5714	29	1.0284	0.4722
0.9507	17.7143	31	1.0291	0.5
0.9507	18.8571	33	1.0692	0.4722
0.9507	20.0	35	1.1153	0.5
0.9507	20.5714	36	1.1719	0.4444
0.9507	21.7143	38	1.0161	0.4444
0.8001	22.8571	40	1.1361	0.4444
0.8001	24.0	42	1.3277	0.4444
0.8001	24.5714	43	1.1331	0.5
0.8001	25.7143	45	1.0659	0.4722
0.8001	26.8571	47	1.1309	0.5278
0.8001	28.0	49	1.1241	0.5556
0.7175	28.5714	50	1.1371	0.5278
0.7175	29.7143	52	1.0928	0.5
0.7175	30.8571	54	1.2129	0.4444
0.7175	32.0	56	1.0321	0.5
0.7175	32.5714	57	1.0809	0.5278
0.7175	33.7143	59	0.9813	0.5278
0.6766	34.8571	61	1.0617	0.5
0.6766	36.0	63	0.9618	0.5278
0.6766	36.5714	64	0.9541	0.5556
0.6766	37.7143	66	0.9689	0.5278
0.6766	38.8571	68	1.1063	0.5556
0.5934	40.0	70	1.0139	0.5
0.5934	40.5714	71	1.0087	0.5
0.5934	41.7143	73	1.0309	0.5
0.5934	42.8571	75	1.0636	0.5
0.5934	44.0	77	1.1057	0.5
0.5934	44.5714	78	1.1015	0.4722
0.4926	45.7143	80	1.0938	0.5278
0.4926	46.8571	82	1.0807	0.5
0.4926	48.0	84	1.1275	0.5278
0.4926	48.5714	85	1.1604	0.5278
0.4926	49.7143	87	1.1296	0.5278
0.4926	50.8571	89	1.0748	0.5278
0.4964	52.0	91	1.0716	0.5278
0.4964	52.5714	92	1.0780	0.5278
0.4964	53.7143	94	1.0755	0.5278
0.4964	54.8571	96	1.0680	0.5278
0.4964	56.0	98	1.0676	0.5278
0.4964	56.5714	99	1.0692	0.5278
0.404	57.1429	100	1.0692	0.5278

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1