Validated_Balanced_Raw_Data_model_boost8

This model is a fine-tuned version of facebook/convnext-small-224 on the Logiroad/Validated_Balanced_Raw_Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 1.1054
• Accuracy: 0.5425

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 1337
• 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: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 25
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.05

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.326	1.0	80	1.2990	0.3868
1.2698	2.0	160	1.2875	0.3726
1.2271	3.0	240	1.2136	0.4245
1.1742	4.0	320	1.1844	0.4717
1.1507	5.0	400	1.1472	0.4906
1.1228	6.0	480	1.1568	0.4623
1.0484	7.0	560	1.1222	0.4811
1.0224	8.0	640	1.1054	0.5425
0.9876	9.0	720	1.1333	0.5
0.9897	10.0	800	1.1368	0.4811
0.9133	11.0	880	1.0923	0.5
0.8814	12.0	960	1.1101	0.4717
0.8185	13.0	1040	1.1416	0.4953
0.7917	14.0	1120	1.1237	0.5047
0.7773	15.0	1200	1.0994	0.5047
0.7289	16.0	1280	1.1059	0.5094
0.7337	17.0	1360	1.1085	0.5142
0.7052	18.0	1440	1.1131	0.5189
0.6703	19.0	1520	1.1068	0.5330
0.6482	20.0	1600	1.1251	0.5189
0.6421	21.0	1680	1.1164	0.5283
0.6738	22.0	1760	1.1147	0.5377
0.6459	23.0	1840	1.1152	0.5283
0.6302	24.0	1920	1.1156	0.5283
0.689	25.0	2000	1.1157	0.5283

Framework versions

• Transformers 4.46.1
• Pytorch 2.3.0
• Datasets 3.1.0
• Tokenizers 0.20.3