hushem_1x_beit_base_sgd_001_fold4

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: 1.2445
• Accuracy: 0.4286

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: 0.001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	6	1.4674	0.2857
1.5737	2.0	12	1.4371	0.2857
1.5737	3.0	18	1.4159	0.2857
1.4801	4.0	24	1.3992	0.3095
1.4412	5.0	30	1.3864	0.3095
1.4412	6.0	36	1.3718	0.3333
1.4214	7.0	42	1.3650	0.3333
1.4214	8.0	48	1.3546	0.3333
1.4025	9.0	54	1.3460	0.3571
1.3579	10.0	60	1.3410	0.3571
1.3579	11.0	66	1.3341	0.3810
1.3434	12.0	72	1.3286	0.3571
1.3434	13.0	78	1.3211	0.3571
1.3133	14.0	84	1.3148	0.3571
1.3087	15.0	90	1.3078	0.3810
1.3087	16.0	96	1.3038	0.3810
1.3233	17.0	102	1.2984	0.4048
1.3233	18.0	108	1.2937	0.4048
1.315	19.0	114	1.2905	0.4048
1.286	20.0	120	1.2858	0.4048
1.286	21.0	126	1.2830	0.4048
1.28	22.0	132	1.2809	0.3810
1.28	23.0	138	1.2789	0.3810
1.2571	24.0	144	1.2785	0.3810
1.23	25.0	150	1.2724	0.3810
1.23	26.0	156	1.2684	0.4048
1.2449	27.0	162	1.2640	0.4048
1.2449	28.0	168	1.2631	0.3810
1.2523	29.0	174	1.2607	0.3810
1.2307	30.0	180	1.2578	0.4286
1.2307	31.0	186	1.2559	0.4048
1.232	32.0	192	1.2529	0.4286
1.232	33.0	198	1.2518	0.4048
1.2339	34.0	204	1.2495	0.4286
1.2343	35.0	210	1.2485	0.4286
1.2343	36.0	216	1.2471	0.4286
1.2146	37.0	222	1.2460	0.4286
1.2146	38.0	228	1.2453	0.4286
1.2285	39.0	234	1.2453	0.4286
1.2244	40.0	240	1.2448	0.4286
1.2244	41.0	246	1.2445	0.4286
1.213	42.0	252	1.2445	0.4286
1.213	43.0	258	1.2445	0.4286
1.2249	44.0	264	1.2445	0.4286
1.1975	45.0	270	1.2445	0.4286
1.1975	46.0	276	1.2445	0.4286
1.2153	47.0	282	1.2445	0.4286
1.2153	48.0	288	1.2445	0.4286
1.2123	49.0	294	1.2445	0.4286
1.2144	50.0	300	1.2445	0.4286

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0