3class_EfficientFormer30M_ForTesting

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

• Loss: 0.0636
• Precision: 0.9798
• Recall: 0.9764
• Accuracy: 0.9818
• F1: 0.9781
• Roc Auc: 0.9983

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	Precision	Recall	Accuracy	F1	Roc Auc
0.1199	0.3436	200	0.0955	0.9604	0.9551	0.9650	0.9576	0.9958
0.0656	0.6873	400	0.0722	0.9754	0.9699	0.9774	0.9725	0.9972
0.0418	1.0309	600	0.0797	0.9758	0.9740	0.9793	0.9749	0.9969
0.0744	1.3746	800	0.0636	0.9798	0.9764	0.9818	0.9781	0.9983
0.0044	1.7182	1000	0.0659	0.9793	0.9756	0.9814	0.9774	0.9983
0.0412	2.0619	1200	0.0690	0.9782	0.9779	0.9818	0.9780	0.9983
0.0029	2.4055	1400	0.0744	0.9808	0.9780	0.9830	0.9794	0.9984
0.0245	2.7491	1600	0.0872	0.9813	0.9755	0.9821	0.9782	0.9981
0.0006	3.0928	1800	0.0753	0.9811	0.9794	0.9837	0.9803	0.9985
0.0049	3.4364	2000	0.0844	0.9799	0.9773	0.9823	0.9785	0.9984
0.0011	3.7801	2200	0.0827	0.9806	0.9778	0.9828	0.9792	0.9984

Framework versions

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