polished-resonance-217

This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 256
eval_batch_size: 256
seed: 42
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: 15

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
1.4116	1.0	17	1.3279	0.4857	0.4335	0.4857	0.4311	0.6864
1.3746	2.0	34	1.1750	0.4870	0.5240	0.4870	0.4995	0.7706
1.1647	3.0	51	0.9635	0.5221	0.5858	0.5221	0.5105	0.7994
1.0134	4.0	68	0.8929	0.5234	0.5823	0.5234	0.5402	0.7975
0.9625	5.0	85	0.8761	0.5729	0.5577	0.5729	0.5576	0.8274
0.9373	6.0	102	0.9938	0.5768	0.5625	0.5768	0.5512	0.8306
0.8421	7.0	119	0.7692	0.4492	0.6542	0.4492	0.4196	0.8073
0.7684	8.0	136	0.6549	0.5977	0.6615	0.5977	0.6121	0.8453
0.7312	9.0	153	0.6826	0.5794	0.6666	0.5794	0.5661	0.8618
0.6827	10.0	170	0.6071	0.6068	0.6560	0.6068	0.6057	0.8665
0.6731	11.0	187	0.5996	0.6146	0.6701	0.6146	0.6224	0.8691
0.6675	12.0	204	0.6269	0.5703	0.7065	0.5703	0.5792	0.8664
0.658	13.0	221	0.5710	0.6536	0.6925	0.6536	0.6603	0.8783
0.6081	14.0	238	0.5664	0.6562	0.6910	0.6562	0.6603	0.8807
0.6179	15.0	255	0.5649	0.6562	0.6901	0.6562	0.6610	0.8810