Validated_Balanced_Raw_Data_model_vit

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

• Loss: 1.2154
• Accuracy: 0.5094

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: 8
• 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: 25.0
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.05

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4452	1.0	80	1.4537	0.2406
1.3534	2.0	160	1.4004	0.3538
1.2977	3.0	240	1.3417	0.3774
1.2604	4.0	320	1.3132	0.3774
1.2428	5.0	400	1.2443	0.4009
1.213	6.0	480	1.2148	0.4198
1.1426	7.0	560	1.2096	0.4670
1.1657	8.0	640	1.2066	0.4670
1.1249	9.0	720	1.2209	0.4387
1.1622	10.0	800	1.1446	0.4811
1.0625	11.0	880	1.1742	0.4670
1.1157	12.0	960	1.2200	0.4434
1.0807	13.0	1040	1.2117	0.4670
1.0629	14.0	1120	1.2296	0.4811
1.0323	15.0	1200	1.1887	0.4906
1.0128	16.0	1280	1.2075	0.4953
1.0266	17.0	1360	1.2082	0.5
1.004	18.0	1440	1.2154	0.5094
0.9543	19.0	1520	1.2048	0.5047
0.9439	20.0	1600	1.2218	0.4906
0.9891	21.0	1680	1.2136	0.4906
0.9801	22.0	1760	1.2166	0.4858
0.9632	23.0	1840	1.2149	0.4906
0.9584	24.0	1920	1.2135	0.4906
0.9561	25.0	2000	1.2136	0.4906

Framework versions

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