jaffe_crop_200_iter

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

Loss: 0.6110
Accuracy: 0.8333

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	2.7256	0.1667
No log	2.0	2	2.5775	0.1667
No log	3.0	3	2.5633	0.1333
No log	4.0	4	2.3386	0.1333
No log	5.0	5	2.3028	0.1
No log	6.0	6	2.1672	0.2333
No log	7.0	7	2.1696	0.0333
No log	8.0	8	2.0133	0.0667
No log	9.0	9	2.0010	0.1
2.3074	10.0	10	1.9153	0.3333
2.3074	11.0	11	2.0177	0.3
2.3074	12.0	12	1.8241	0.3333
2.3074	13.0	13	1.7967	0.3
2.3074	14.0	14	1.7210	0.3333
2.3074	15.0	15	1.6551	0.3333
2.3074	16.0	16	1.5307	0.5333
2.3074	17.0	17	1.4263	0.4333
2.3074	18.0	18	1.4219	0.4333
2.3074	19.0	19	1.4402	0.4333
1.5864	20.0	20	1.3050	0.5
1.5864	21.0	21	1.4508	0.4
1.5864	22.0	22	1.3384	0.4667
1.5864	23.0	23	1.1632	0.6
1.5864	24.0	24	1.0711	0.6333
1.5864	25.0	25	1.1361	0.4667
1.5864	26.0	26	1.2230	0.5667
1.5864	27.0	27	1.0167	0.7
1.5864	28.0	28	0.8815	0.6667
1.5864	29.0	29	1.0191	0.6667
0.7909	30.0	30	0.9474	0.6667
0.7909	31.0	31	0.9328	0.5333
0.7909	32.0	32	0.9476	0.6
0.7909	33.0	33	0.7911	0.7
0.7909	34.0	34	0.7609	0.7333
0.7909	35.0	35	0.9489	0.6333
0.7909	36.0	36	0.7199	0.6667
0.7909	37.0	37	0.6195	0.7667
0.7909	38.0	38	0.7611	0.7333
0.7909	39.0	39	0.8063	0.7333
0.3677	40.0	40	0.8360	0.6667
0.3677	41.0	41	0.7250	0.7333
0.3677	42.0	42	0.6228	0.8333
0.3677	43.0	43	0.7757	0.7667
0.3677	44.0	44	0.6767	0.7667
0.3677	45.0	45	0.8128	0.6667
0.3677	46.0	46	0.8584	0.7333
0.3677	47.0	47	0.8866	0.6333
0.3677	48.0	48	0.5143	0.8
0.3677	49.0	49	0.7074	0.7
0.192	50.0	50	0.7536	0.7333
0.192	51.0	51	0.7113	0.7667
0.192	52.0	52	0.8321	0.7
0.192	53.0	53	0.7229	0.7333
0.192	54.0	54	0.8839	0.7
0.192	55.0	55	0.5496	0.8
0.192	56.0	56	0.6769	0.8
0.192	57.0	57	0.5740	0.8333
0.192	58.0	58	0.6321	0.7667
0.192	59.0	59	0.7635	0.7667
0.1225	60.0	60	0.6869	0.8
0.1225	61.0	61	0.6595	0.8333
0.1225	62.0	62	0.5097	0.8
0.1225	63.0	63	0.5642	0.8333
0.1225	64.0	64	0.6503	0.8
0.1225	65.0	65	0.6877	0.7667
0.1225	66.0	66	0.6811	0.7333
0.1225	67.0	67	0.7854	0.7
0.1225	68.0	68	0.6378	0.8
0.1225	69.0	69	0.5148	0.8667
0.088	70.0	70	0.6571	0.8
0.088	71.0	71	0.7112	0.7333
0.088	72.0	72	0.6602	0.7333
0.088	73.0	73	0.4259	0.9
0.088	74.0	74	0.3600	0.8667
0.088	75.0	75	0.5726	0.8667
0.088	76.0	76	0.6638	0.7667
0.088	77.0	77	0.4641	0.8667
0.088	78.0	78	0.5186	0.8667
0.088	79.0	79	0.6024	0.8333
0.0581	80.0	80	0.4450	0.8667
0.0581	81.0	81	0.3267	0.9
0.0581	82.0	82	0.6442	0.8
0.0581	83.0	83	0.8130	0.8
0.0581	84.0	84	0.4391	0.8667
0.0581	85.0	85	0.5013	0.8333
0.0581	86.0	86	0.6059	0.8
0.0581	87.0	87	0.4916	0.8333
0.0581	88.0	88	0.4384	0.8667
0.0581	89.0	89	0.3366	0.9
0.0359	90.0	90	0.6082	0.7667
0.0359	91.0	91	0.2967	0.8333
0.0359	92.0	92	0.3954	0.9
0.0359	93.0	93	0.5354	0.8333
0.0359	94.0	94	0.4755	0.8667
0.0359	95.0	95	0.5060	0.8
0.0359	96.0	96	0.3716	0.8333
0.0359	97.0	97	0.3547	0.8333
0.0359	98.0	98	0.6991	0.8333
0.0359	99.0	99	0.4895	0.8333
0.0251	100.0	100	0.5676	0.8
0.0251	101.0	101	0.3866	0.8667
0.0251	102.0	102	0.7054	0.7667
0.0251	103.0	103	0.5586	0.8667
0.0251	104.0	104	0.5839	0.8333
0.0251	105.0	105	0.5091	0.8333
0.0251	106.0	106	0.5459	0.9
0.0251	107.0	107	0.4228	0.9
0.0251	108.0	108	0.4447	0.9
0.0251	109.0	109	0.5052	0.8667
0.023	110.0	110	0.5494	0.8
0.023	111.0	111	0.6297	0.8333
0.023	112.0	112	0.6272	0.8667
0.023	113.0	113	0.6439	0.8333
0.023	114.0	114	0.3996	0.8667
0.023	115.0	115	0.4805	0.8333
0.023	116.0	116	0.4350	0.9
0.023	117.0	117	0.7719	0.8
0.023	118.0	118	0.5710	0.8333
0.023	119.0	119	0.3579	0.9
0.0292	120.0	120	0.3309	0.9333
0.0292	121.0	121	0.2649	0.9333
0.0292	122.0	122	0.3858	0.8333
0.0292	123.0	123	0.6109	0.8
0.0292	124.0	124	0.4734	0.8
0.0292	125.0	125	0.5604	0.8333
0.0292	126.0	126	0.3509	0.8667
0.0292	127.0	127	0.4752	0.9
0.0292	128.0	128	0.2966	0.8667
0.0292	129.0	129	0.5186	0.8667
0.0155	130.0	130	0.4547	0.8667
0.0155	131.0	131	0.3391	0.9
0.0155	132.0	132	0.4527	0.8667
0.0155	133.0	133	0.4476	0.8667
0.0155	134.0	134	0.5800	0.8667
0.0155	135.0	135	0.4653	0.8667
0.0155	136.0	136	0.3927	0.9
0.0155	137.0	137	0.4538	0.8333
0.0155	138.0	138	0.3952	0.9
0.0155	139.0	139	0.3949	0.9333
0.0112	140.0	140	0.5354	0.9
0.0112	141.0	141	0.5307	0.8333
0.0112	142.0	142	0.4757	0.9
0.0112	143.0	143	0.4342	0.9
0.0112	144.0	144	0.3978	0.9
0.0112	145.0	145	0.5695	0.8333
0.0112	146.0	146	0.5495	0.8
0.0112	147.0	147	0.4235	0.8667
0.0112	148.0	148	0.3878	0.9
0.0112	149.0	149	0.5536	0.9
0.0066	150.0	150	0.4343	0.8333
0.0066	151.0	151	0.5915	0.8667
0.0066	152.0	152	0.6523	0.8
0.0066	153.0	153	0.6478	0.8333
0.0066	154.0	154	0.6078	0.8333
0.0066	155.0	155	0.5253	0.9
0.0066	156.0	156	0.5023	0.9
0.0066	157.0	157	0.6782	0.8667
0.0066	158.0	158	0.4155	0.9
0.0066	159.0	159	0.6239	0.8667
0.0063	160.0	160	0.4657	0.8667
0.0063	161.0	161	0.3858	0.9
0.0063	162.0	162	0.4525	0.8667
0.0063	163.0	163	0.2853	0.9
0.0063	164.0	164	0.3835	0.8667
0.0063	165.0	165	0.3866	0.8333
0.0063	166.0	166	0.5272	0.8
0.0063	167.0	167	0.5175	0.8667
0.0063	168.0	168	0.5153	0.9
0.0063	169.0	169	0.4730	0.8667
0.0048	170.0	170	0.6657	0.8333
0.0048	171.0	171	0.5745	0.9
0.0048	172.0	172	0.7296	0.8
0.0048	173.0	173	0.4948	0.8333
0.0048	174.0	174	0.4577	0.8667
0.0048	175.0	175	0.5703	0.8667
0.0048	176.0	176	0.7392	0.8333
0.0048	177.0	177	0.7239	0.9
0.0048	178.0	178	0.3202	0.9
0.0048	179.0	179	0.4292	0.9
0.003	180.0	180	0.6611	0.8333
0.003	181.0	181	0.4829	0.9
0.003	182.0	182	0.4959	0.8667
0.003	183.0	183	0.2886	0.9
0.003	184.0	184	0.6587	0.8667
0.003	185.0	185	0.7223	0.8
0.003	186.0	186	0.6374	0.8667
0.003	187.0	187	0.5756	0.8333
0.003	188.0	188	0.6505	0.8667
0.003	189.0	189	0.5517	0.8667
0.0025	190.0	190	0.5176	0.8667
0.0025	191.0	191	0.4003	0.9
0.0025	192.0	192	0.5594	0.8667
0.0025	193.0	193	0.4229	0.9
0.0025	194.0	194	0.5938	0.8667
0.0025	195.0	195	0.6415	0.8667
0.0025	196.0	196	0.5056	0.8667
0.0025	197.0	197	0.5146	0.9
0.0025	198.0	198	0.5822	0.8667
0.0025	199.0	199	0.6066	0.8667
0.0021	200.0	200	0.6110	0.8333

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

ricardoSLabs/jaffe_crop_200_iter

jaffe_crop_200_iter

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model