vit-msn-small-lateral_flow_ivalidation_train_test_6

This model is a fine-tuned version of facebook/vit-msn-small on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.4371
Accuracy: 0.8791

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-07
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
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: 0.3
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6672	0.9231	6	0.6980	0.4212
0.6617	2.0	13	0.6965	0.4249
0.6699	2.9231	19	0.6944	0.4396
0.662	4.0	26	0.6910	0.4396
0.6548	4.9231	32	0.6873	0.4579
0.6541	6.0	39	0.6825	0.4835
0.6222	6.9231	45	0.6777	0.5311
0.6555	8.0	52	0.6719	0.5421
0.6226	8.9231	58	0.6665	0.5861
0.5989	10.0	65	0.6603	0.6154
0.5754	10.9231	71	0.6555	0.6264
0.6251	12.0	78	0.6493	0.6484
0.5796	12.9231	84	0.6446	0.6667
0.5763	14.0	91	0.6390	0.6667
0.5952	14.9231	97	0.6333	0.6850
0.5675	16.0	104	0.6269	0.7033
0.5453	16.9231	110	0.6211	0.7106
0.5199	18.0	117	0.6150	0.7143
0.541	18.9231	123	0.6090	0.7216
0.5273	20.0	130	0.6007	0.7289
0.495	20.9231	136	0.5934	0.7289
0.4855	22.0	143	0.5855	0.7473
0.4763	22.9231	149	0.5787	0.7363
0.4287	24.0	156	0.5693	0.7509
0.445	24.9231	162	0.5619	0.7692
0.4343	26.0	169	0.5540	0.7802
0.3748	26.9231	175	0.5467	0.7875
0.4041	28.0	182	0.5421	0.8022
0.3543	28.9231	188	0.5291	0.8205
0.3972	30.0	195	0.5134	0.8278
0.3716	30.9231	201	0.5150	0.8242
0.3871	32.0	208	0.5100	0.8315
0.3729	32.9231	214	0.4986	0.8352
0.3286	34.0	221	0.4946	0.8462
0.4261	34.9231	227	0.4957	0.8388
0.4014	36.0	234	0.4850	0.8535
0.3514	36.9231	240	0.4807	0.8535
0.3883	38.0	247	0.4767	0.8535
0.3219	38.9231	253	0.4763	0.8535
0.4351	40.0	260	0.4738	0.8571
0.3068	40.9231	266	0.4688	0.8645
0.3356	42.0	273	0.4585	0.8645
0.345	42.9231	279	0.4541	0.8681
0.3254	44.0	286	0.4584	0.8645
0.3164	44.9231	292	0.4592	0.8571
0.3657	46.0	299	0.4534	0.8608
0.2655	46.9231	305	0.4502	0.8645
0.2981	48.0	312	0.4452	0.8645
0.3508	48.9231	318	0.4371	0.8791
0.3419	50.0	325	0.4394	0.8755
0.2668	50.9231	331	0.4430	0.8755
0.2972	52.0	338	0.4395	0.8718
0.3514	52.9231	344	0.4371	0.8755
0.3012	54.0	351	0.4330	0.8791
0.2725	54.9231	357	0.4298	0.8791
0.2547	56.0	364	0.4289	0.8718
0.2896	56.9231	370	0.4282	0.8718
0.3469	58.0	377	0.4273	0.8718
0.3528	58.9231	383	0.4269	0.8718
0.2552	60.0	390	0.4324	0.8681
0.239	60.9231	396	0.4319	0.8645
0.3321	62.0	403	0.4270	0.8718
0.3115	62.9231	409	0.4184	0.8718
0.306	64.0	416	0.4169	0.8718
0.3086	64.9231	422	0.4176	0.8718
0.4256	66.0	429	0.4196	0.8718
0.2798	66.9231	435	0.4219	0.8718
0.3016	68.0	442	0.4224	0.8718
0.2791	68.9231	448	0.4207	0.8718
0.2651	70.0	455	0.4189	0.8718
0.2466	70.9231	461	0.4178	0.8718
0.1913	72.0	468	0.4177	0.8718
0.2719	72.9231	474	0.4164	0.8718
0.3364	74.0	481	0.4166	0.8718
0.283	74.9231	487	0.4179	0.8755
0.2891	76.0	494	0.4174	0.8755
0.2625	76.9231	500	0.4180	0.8755
0.2843	78.0	507	0.4184	0.8718
0.375	78.9231	513	0.4167	0.8755
0.3107	80.0	520	0.4150	0.8755
0.3742	80.9231	526	0.4145	0.8718
0.2574	82.0	533	0.4145	0.8755
0.329	82.9231	539	0.4149	0.8755
0.2727	84.0	546	0.4145	0.8755
0.2977	84.9231	552	0.4149	0.8755
0.2611	86.0	559	0.4160	0.8718
0.2542	86.9231	565	0.4170	0.8718
0.2665	88.0	572	0.4171	0.8718
0.2654	88.9231	578	0.4170	0.8718
0.3059	90.0	585	0.4172	0.8718
0.2377	90.9231	591	0.4173	0.8718
0.2896	92.0	598	0.4172	0.8718
0.3133	92.3077	600	0.4172	0.8718

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.2.0
Tokenizers 0.19.1

Melo1512/vit-msn-small-lateral_flow_ivalidation_train_test_6

vit-msn-small-lateral_flow_ivalidation_train_test_6

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model