Validated_Balanced_Raw_Data_model_boost9

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: 1.2586
• Accuracy: 0.4151

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
1.3942	1.0	80	1.3566	0.3349
1.3192	2.0	160	1.3104	0.3585
1.2795	3.0	240	1.2999	0.3726
1.2419	4.0	320	1.2860	0.3726
1.2213	5.0	400	1.2894	0.3679
1.2287	6.0	480	1.2863	0.3632
1.2123	7.0	560	1.2879	0.3915
1.2124	8.0	640	1.2767	0.3868
1.2144	9.0	720	1.2851	0.3726
1.2202	10.0	800	1.2683	0.3962
1.1804	11.0	880	1.2659	0.4009
1.2031	12.0	960	1.2658	0.3962
1.1428	13.0	1040	1.2621	0.4057
1.1224	14.0	1120	1.2655	0.4104
1.1486	15.0	1200	1.2606	0.3962
1.1451	16.0	1280	1.2636	0.4057
1.1717	17.0	1360	1.2596	0.4057
1.1231	18.0	1440	1.2626	0.4057
1.1468	19.0	1520	1.2617	0.3962
1.0958	20.0	1600	1.2586	0.4151
1.1456	21.0	1680	1.2587	0.4104
1.127	22.0	1760	1.2590	0.4151
1.1308	23.0	1840	1.2586	0.4151
1.1433	24.0	1920	1.2585	0.4151
1.1492	25.0	2000	1.2585	0.4151

Framework versions

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