Validated_Balanced_Raw_Data_model_boost4

This model is a fine-tuned version of facebook/convnext-base-224-22k on the Logiroad/Validated_Balanced_Raw_Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 1.1481
• Accuracy: 0.5330

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: 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: 0.1
• num_epochs: 30.0
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3971	1.0	80	1.3381	0.3585
1.3299	2.0	160	1.2897	0.3632
1.2782	3.0	240	1.2420	0.4151
1.2151	4.0	320	1.1928	0.4481
1.1703	5.0	400	1.1871	0.4906
1.1426	6.0	480	1.1827	0.4811
1.0837	7.0	560	1.1960	0.5094
1.0393	8.0	640	1.1481	0.5330
1.0316	9.0	720	1.1935	0.4858
1.0134	10.0	800	1.1634	0.4953
0.9324	11.0	880	1.1869	0.5094
0.9005	12.0	960	1.1605	0.4858
0.8917	13.0	1040	1.1818	0.4858
0.8299	14.0	1120	1.1759	0.4953
0.8314	15.0	1200	1.1999	0.4906
0.7891	16.0	1280	1.2111	0.5
0.7702	17.0	1360	1.2256	0.4764
0.7821	18.0	1440	1.2364	0.5142
0.7391	19.0	1520	1.2108	0.5047
0.7078	20.0	1600	1.1987	0.5
0.7245	21.0	1680	1.1981	0.5283
0.6822	22.0	1760	1.2110	0.5283
0.6646	23.0	1840	1.2095	0.5330
0.7144	24.0	1920	1.2078	0.5236
0.7271	25.0	2000	1.2088	0.5189
0.6563	26.0	2080	1.2137	0.5094
0.6447	27.0	2160	1.2157	0.5236
0.6763	28.0	2240	1.2135	0.5189
0.6434	29.0	2320	1.2137	0.5189
0.6727	30.0	2400	1.2136	0.5189

Framework versions

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