teacher-status-van-tiny-256

This model is a fine-tuned version of Visual-Attention-Network/van-tiny on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0988
• Accuracy: 0.9831
• F1 Score: 0.9841
• Recall: 0.9789
• Precision: 0.9894

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Score	Recall	Precision
0.6928	0.96	12	0.6904	0.6685	0.7631	1.0	0.6169
0.6893	2.0	25	0.6683	0.5393	0.6985	1.0	0.5367
0.6726	2.96	37	0.5704	0.5843	0.7197	1.0	0.5621
0.5295	4.0	50	0.4148	0.9213	0.9263	0.9263	0.9263
0.4745	4.96	62	0.3108	0.9382	0.9430	0.9579	0.9286
0.4206	6.0	75	0.2301	0.9438	0.9474	0.9474	0.9474
0.3898	6.96	87	0.1820	0.9494	0.9519	0.9368	0.9674
0.3153	8.0	100	0.1545	0.9494	0.9538	0.9789	0.93
0.3077	8.96	112	0.1521	0.9607	0.9622	0.9368	0.9889
0.3048	10.0	125	0.1331	0.9607	0.9626	0.9474	0.9783
0.3004	10.96	137	0.1314	0.9607	0.9634	0.9684	0.9583
0.2839	12.0	150	0.1272	0.9607	0.9622	0.9368	0.9889
0.286	12.96	162	0.1189	0.9607	0.9622	0.9368	0.9889
0.2473	14.0	175	0.0977	0.9719	0.9733	0.9579	0.9891
0.2774	14.96	187	0.0988	0.9831	0.9841	0.9789	0.9894
0.2541	16.0	200	0.0969	0.9719	0.9733	0.9579	0.9891
0.2383	16.96	212	0.1042	0.9719	0.9733	0.9579	0.9891
0.2552	18.0	225	0.1081	0.9719	0.9733	0.9579	0.9891
0.2223	18.96	237	0.1150	0.9663	0.9681	0.9579	0.9785
0.2561	20.0	250	0.1234	0.9551	0.9574	0.9474	0.9677
0.2462	20.96	262	0.1178	0.9607	0.9630	0.9579	0.9681
0.2294	22.0	275	0.1262	0.9382	0.9430	0.9579	0.9286
0.2296	22.96	287	0.1290	0.9438	0.9479	0.9579	0.9381
0.2224	24.0	300	0.1153	0.9494	0.9529	0.9579	0.9479
0.2205	24.96	312	0.1150	0.9494	0.9529	0.9579	0.9479
0.2169	26.0	325	0.1121	0.9551	0.9574	0.9474	0.9677
0.2212	26.96	337	0.1145	0.9494	0.9529	0.9579	0.9479
0.2188	28.0	350	0.1131	0.9494	0.9524	0.9474	0.9574
0.2015	28.8	360	0.1130	0.9494	0.9524	0.9474	0.9574

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0