Blurry-classifier-efformer-v1

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0252
• Accuracy: 0.994
• Precision: 0.9940
• Recall: 0.9940
• F1: 0.9940
• Roc Auc: 0.9999

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.0495	0.5102	200	0.0473	0.983	0.9832	0.9832	0.9830	0.9994
0.0444	1.0204	400	0.0311	0.9902	0.9903	0.9902	0.9902	0.9995
0.0065	1.5306	600	0.0256	0.993	0.9930	0.9930	0.9930	0.9997
0.0071	2.0408	800	0.0326	0.9935	0.9935	0.9935	0.9935	0.9996
0.0039	2.5510	1000	0.0289	0.9935	0.9935	0.9935	0.9935	0.9998
0.0004	3.0612	1200	0.0252	0.994	0.9940	0.9940	0.9940	0.9999
0.0003	3.5714	1400	0.0282	0.9938	0.9937	0.9938	0.9937	0.9999

Framework versions

• Transformers 5.3.0
• Pytorch 2.10.0+cu128
• Datasets 4.7.0
• Tokenizers 0.22.2