Validated_Balanced_Raw_Data_model_boost5

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: 1.1317
• Accuracy: 0.5377

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	1.2422	0.4151
1.2159	4.0	320	1.1955	0.4434
1.1707	5.0	400	1.1769	0.5047
1.1314	6.0	480	1.1844	0.4858
1.0789	7.0	560	1.1870	0.5142
1.0419	8.0	640	1.1317	0.5377
1.0222	9.0	720	1.2062	0.4906
1.0077	10.0	800	1.1582	0.4764
0.9161	11.0	880	1.1841	0.5047
0.9066	12.0	960	1.1603	0.5236
0.8948	13.0	1040	1.1681	0.4906
0.8382	14.0	1120	1.1980	0.4953
0.8279	15.0	1200	1.2145	0.4953
0.7839	16.0	1280	1.2142	0.5
0.7797	17.0	1360	1.2288	0.5
0.7794	18.0	1440	1.2374	0.5
0.7447	19.0	1520	1.2071	0.5047
0.7101	20.0	1600	1.1943	0.5142
0.7229	21.0	1680	1.1930	0.5142
0.6906	22.0	1760	1.2124	0.5189
0.6743	23.0	1840	1.2044	0.5283
0.7181	24.0	1920	1.2020	0.5330
0.7323	25.0	2000	1.2088	0.5236
0.6597	26.0	2080	1.2148	0.5189
0.6476	27.0	2160	1.2144	0.5189
0.6792	28.0	2240	1.2133	0.5142
0.6455	29.0	2320	1.2134	0.5283
0.6719	30.0	2400	1.2133	0.5283

Framework versions

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