hushem_5x_beit_base_sgd_001_fold1

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: 1.5176
• Accuracy: 0.4

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
1.4454	1.0	27	1.5496	0.2667
1.3864	2.0	54	1.5125	0.2667
1.3701	3.0	81	1.4961	0.2667
1.3167	4.0	108	1.5066	0.2889
1.2134	5.0	135	1.5082	0.3333
1.1476	6.0	162	1.5110	0.3333
1.1471	7.0	189	1.5248	0.3333
1.1363	8.0	216	1.5434	0.3556
1.0955	9.0	243	1.5579	0.3778
1.0745	10.0	270	1.5619	0.3333
1.0401	11.0	297	1.5614	0.3333
1.0047	12.0	324	1.5711	0.3333
1.0055	13.0	351	1.5627	0.3333
0.9832	14.0	378	1.5529	0.3333
0.9676	15.0	405	1.5726	0.3333
0.9641	16.0	432	1.5677	0.3333
0.9328	17.0	459	1.5601	0.3333
0.9518	18.0	486	1.5678	0.3333
0.9109	19.0	513	1.5762	0.3333
0.9218	20.0	540	1.5662	0.3333
0.8731	21.0	567	1.5698	0.3333
0.8636	22.0	594	1.5667	0.3333
0.8235	23.0	621	1.5658	0.3333
0.8569	24.0	648	1.5702	0.3333
0.8347	25.0	675	1.5568	0.3333
0.8597	26.0	702	1.5638	0.3333
0.8371	27.0	729	1.5541	0.3333
0.8073	28.0	756	1.5468	0.3556
0.8391	29.0	783	1.5399	0.3556
0.8305	30.0	810	1.5379	0.3556
0.7771	31.0	837	1.5433	0.3778
0.8158	32.0	864	1.5408	0.3556
0.8402	33.0	891	1.5426	0.3778
0.7881	34.0	918	1.5356	0.3778
0.798	35.0	945	1.5324	0.4
0.75	36.0	972	1.5330	0.4
0.7699	37.0	999	1.5355	0.3778
0.7585	38.0	1026	1.5345	0.4
0.7272	39.0	1053	1.5315	0.4
0.7453	40.0	1080	1.5287	0.4
0.7465	41.0	1107	1.5241	0.4
0.7238	42.0	1134	1.5231	0.4
0.7663	43.0	1161	1.5207	0.4
0.7014	44.0	1188	1.5176	0.4
0.7481	45.0	1215	1.5184	0.4
0.7298	46.0	1242	1.5191	0.4
0.7342	47.0	1269	1.5176	0.4
0.706	48.0	1296	1.5175	0.4
0.7649	49.0	1323	1.5176	0.4
0.7295	50.0	1350	1.5176	0.4

Framework versions

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