vit-estadosfenologicos

This model is a fine-tuned version of google/vit-base-patch32-384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1298
• Accuracy: 0.9581

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: 0.0005
• train_batch_size: 512
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	12	0.7243	0.8397
No log	2.0	24	0.3981	0.8720
No log	3.0	36	0.2737	0.9135
No log	4.0	48	0.2173	0.9250
No log	5.0	60	0.1910	0.9319
No log	6.0	72	0.1757	0.9354
No log	7.0	84	0.1638	0.9412
No log	8.0	96	0.1572	0.9377
0.4042	9.0	108	0.1504	0.9458
0.4042	10.0	120	0.1456	0.9412
0.4042	11.0	132	0.1415	0.9458
0.4042	12.0	144	0.1375	0.9458
0.4042	13.0	156	0.1351	0.9458
0.4042	14.0	168	0.1327	0.9469
0.4042	15.0	180	0.1294	0.9504
0.4042	16.0	192	0.1270	0.9469
0.1655	17.0	204	0.1258	0.9504
0.1655	18.0	216	0.1247	0.9516
0.1655	19.0	228	0.1221	0.9539
0.1655	20.0	240	0.1210	0.9527
0.1655	21.0	252	0.1208	0.9504
0.1655	22.0	264	0.1185	0.9550
0.1655	23.0	276	0.1176	0.9539
0.1655	24.0	288	0.1158	0.9539
0.1371	25.0	300	0.1162	0.9539
0.1371	26.0	312	0.1142	0.9550
0.1371	27.0	324	0.1148	0.9550
0.1371	28.0	336	0.1131	0.9550
0.1371	29.0	348	0.1122	0.9550
0.1371	30.0	360	0.1118	0.9550
0.1371	31.0	372	0.1116	0.9539
0.1371	32.0	384	0.1103	0.9550
0.1371	33.0	396	0.1102	0.9550
0.124	34.0	408	0.1103	0.9550
0.124	35.0	420	0.1089	0.9573
0.124	36.0	432	0.1088	0.9562
0.124	37.0	444	0.1092	0.9550
0.124	38.0	456	0.1079	0.9562
0.124	39.0	468	0.1082	0.9562
0.124	40.0	480	0.1077	0.9562
0.124	41.0	492	0.1071	0.9573
0.1168	42.0	504	0.1068	0.9573
0.1168	43.0	516	0.1073	0.9562
0.1168	44.0	528	0.1067	0.9562
0.1168	45.0	540	0.1066	0.9562
0.1168	46.0	552	0.1062	0.9573
0.1168	47.0	564	0.1063	0.9573
0.1168	48.0	576	0.1063	0.9562
0.1168	49.0	588	0.1063	0.9562
0.1129	50.0	600	0.1063	0.9562

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu126
• Datasets 3.3.2
• Tokenizers 0.21.0