validated_cracks_dataset_relabeled_convnext_finetune_model

This model is a fine-tuned version of Logiroad/Validated_cracks_raw_dataset_359_convnext_model on the Logiroad/validated_cracks_dataset_relabeled dataset. It achieves the following results on the evaluation set:

• Loss: 0.9997
• Accuracy: 0.6139

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: 1e-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: 30.0
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.05

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9468	1.0	108	0.9880	0.6023
0.9275	2.0	216	1.0345	0.5830
0.9377	3.0	324	1.0231	0.5676
0.8461	4.0	432	0.9997	0.6139
0.8429	5.0	540	0.9873	0.5869
0.781	6.0	648	0.9971	0.6062
0.7621	7.0	756	1.0093	0.5830
0.7649	8.0	864	1.0585	0.5676
0.7912	9.0	972	1.0434	0.5753
0.7529	10.0	1080	1.0226	0.6100
0.6924	11.0	1188	1.0567	0.5869
0.7015	12.0	1296	1.0601	0.5830
0.7094	13.0	1404	1.0830	0.5637
0.749	14.0	1512	1.0384	0.5907
0.7433	15.0	1620	1.0581	0.5676
0.7595	16.0	1728	1.0641	0.5714
0.8132	17.0	1836	1.0863	0.5714
0.7951	18.0	1944	1.0517	0.5869
0.7861	19.0	2052	1.0631	0.5907
0.7334	20.0	2160	1.0507	0.5907
0.6807	21.0	2268	1.0659	0.5792
0.6905	22.0	2376	1.0681	0.5753
0.7242	23.0	2484	1.0530	0.5907
0.7342	24.0	2592	1.0660	0.5637
0.7736	25.0	2700	1.0709	0.5792
0.7798	26.0	2808	1.0627	0.5714
0.71	27.0	2916	1.0605	0.5869
0.706	28.0	3024	1.0606	0.5792
0.7421	29.0	3132	1.0606	0.5753
0.654	30.0	3240	1.0608	0.5753

Framework versions

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