Validated_Balanced_Raw_Data_model_boost6

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: 1.1222
• 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: 20.0
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3904	1.0	80	1.3300	0.3679
1.3255	2.0	160	1.2853	0.3868
1.2779	3.0	240	1.2196	0.4340
1.2267	4.0	320	1.1914	0.4528
1.1508	5.0	400	1.1553	0.5047
1.0964	6.0	480	1.2145	0.4764
1.0742	7.0	560	1.1814	0.5
1.0315	8.0	640	1.1222	0.5377
1.0283	9.0	720	1.1561	0.5189
0.999	10.0	800	1.1940	0.5094
0.961	11.0	880	1.1440	0.5047
0.9484	12.0	960	1.1716	0.5
0.8779	13.0	1040	1.1549	0.5142
0.8613	14.0	1120	1.1524	0.5283
0.8572	15.0	1200	1.1644	0.5189
0.8605	16.0	1280	1.1536	0.5236
0.8268	17.0	1360	1.1561	0.5283
0.8171	18.0	1440	1.1589	0.5283
0.8242	19.0	1520	1.1594	0.5236
0.7743	20.0	1600	1.1596	0.5283

Framework versions

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