vit-gabor-detection-v3

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4139
• Accuracy: 1.0

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: 2e-05
• train_batch_size: 200
• eval_batch_size: 200
• seed: 1337
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 120.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.6629	0.5
No log	2.0	2	0.6564	0.5
No log	3.0	3	0.6496	0.5
No log	4.0	4	0.6428	0.5
No log	5.0	5	0.6362	0.5
No log	6.0	6	0.6296	0.5
No log	7.0	7	0.6232	0.5
No log	8.0	8	0.6172	0.5
No log	9.0	9	0.6113	1.0
0.509	10.0	10	0.6058	1.0
0.509	11.0	11	0.6005	1.0
0.509	12.0	12	0.5950	1.0
0.509	13.0	13	0.5892	1.0
0.509	14.0	14	0.5832	1.0
0.509	15.0	15	0.5765	1.0
0.509	16.0	16	0.5699	1.0
0.509	17.0	17	0.5630	1.0
0.509	18.0	18	0.5562	1.0
0.509	19.0	19	0.5494	1.0
0.248	20.0	20	0.5426	1.0
0.248	21.0	21	0.5360	1.0
0.248	22.0	22	0.5295	1.0
0.248	23.0	23	0.5231	1.0
0.248	24.0	24	0.5175	1.0
0.248	25.0	25	0.5126	1.0
0.248	26.0	26	0.5079	1.0
0.248	27.0	27	0.5034	1.0
0.248	28.0	28	0.4991	1.0
0.248	29.0	29	0.4949	1.0
0.119	30.0	30	0.4908	1.0
0.119	31.0	31	0.4868	1.0
0.119	32.0	32	0.4833	1.0
0.119	33.0	33	0.4803	1.0
0.119	34.0	34	0.4777	1.0
0.119	35.0	35	0.4751	1.0
0.119	36.0	36	0.4727	1.0
0.119	37.0	37	0.4704	1.0
0.119	38.0	38	0.4681	1.0
0.119	39.0	39	0.4658	1.0
0.0692	40.0	40	0.4635	1.0
0.0692	41.0	41	0.4612	1.0
0.0692	42.0	42	0.4588	1.0
0.0692	43.0	43	0.4564	1.0
0.0692	44.0	44	0.4542	1.0
0.0692	45.0	45	0.4522	1.0
0.0692	46.0	46	0.4504	1.0
0.0692	47.0	47	0.4488	1.0
0.0692	48.0	48	0.4474	1.0
0.0692	49.0	49	0.4463	1.0
0.0487	50.0	50	0.4453	1.0
0.0487	51.0	51	0.4444	1.0
0.0487	52.0	52	0.4435	1.0
0.0487	53.0	53	0.4427	1.0
0.0487	54.0	54	0.4419	1.0
0.0487	55.0	55	0.4410	1.0
0.0487	56.0	56	0.4402	1.0
0.0487	57.0	57	0.4394	1.0
0.0487	58.0	58	0.4385	1.0
0.0487	59.0	59	0.4375	1.0
0.0374	60.0	60	0.4366	1.0
0.0374	61.0	61	0.4356	1.0
0.0374	62.0	62	0.4347	1.0
0.0374	63.0	63	0.4338	1.0
0.0374	64.0	64	0.4328	1.0
0.0374	65.0	65	0.4319	1.0
0.0374	66.0	66	0.4311	1.0
0.0374	67.0	67	0.4302	1.0
0.0374	68.0	68	0.4294	1.0
0.0374	69.0	69	0.4286	1.0
0.0321	70.0	70	0.4278	1.0
0.0321	71.0	71	0.4271	1.0
0.0321	72.0	72	0.4264	1.0
0.0321	73.0	73	0.4257	1.0
0.0321	74.0	74	0.4251	1.0
0.0321	75.0	75	0.4245	1.0
0.0321	76.0	76	0.4239	1.0
0.0321	77.0	77	0.4233	1.0
0.0321	78.0	78	0.4228	1.0
0.0321	79.0	79	0.4223	1.0
0.0285	80.0	80	0.4219	1.0
0.0285	81.0	81	0.4215	1.0
0.0285	82.0	82	0.4211	1.0
0.0285	83.0	83	0.4206	1.0
0.0285	84.0	84	0.4201	1.0
0.0285	85.0	85	0.4197	1.0
0.0285	86.0	86	0.4192	1.0
0.0285	87.0	87	0.4189	1.0
0.0285	88.0	88	0.4185	1.0
0.0285	89.0	89	0.4182	1.0
0.0268	90.0	90	0.4179	1.0
0.0268	91.0	91	0.4176	1.0
0.0268	92.0	92	0.4173	1.0
0.0268	93.0	93	0.4170	1.0
0.0268	94.0	94	0.4168	1.0
0.0268	95.0	95	0.4165	1.0
0.0268	96.0	96	0.4163	1.0
0.0268	97.0	97	0.4161	1.0
0.0268	98.0	98	0.4159	1.0
0.0268	99.0	99	0.4157	1.0
0.0249	100.0	100	0.4155	1.0
0.0249	101.0	101	0.4154	1.0
0.0249	102.0	102	0.4152	1.0
0.0249	103.0	103	0.4151	1.0
0.0249	104.0	104	0.4150	1.0
0.0249	105.0	105	0.4148	1.0
0.0249	106.0	106	0.4147	1.0
0.0249	107.0	107	0.4146	1.0
0.0249	108.0	108	0.4145	1.0
0.0249	109.0	109	0.4144	1.0
0.0242	110.0	110	0.4144	1.0
0.0242	111.0	111	0.4143	1.0
0.0242	112.0	112	0.4142	1.0
0.0242	113.0	113	0.4141	1.0
0.0242	114.0	114	0.4141	1.0
0.0242	115.0	115	0.4140	1.0
0.0242	116.0	116	0.4140	1.0
0.0242	117.0	117	0.4139	1.0
0.0242	118.0	118	0.4139	1.0
0.0242	119.0	119	0.4139	1.0
0.0292	120.0	120	0.4139	1.0

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.4.0
• Tokenizers 0.15.0