defect-classification-distilbert-baseline-20-epochs

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

• Loss: 0.2853
• Accuracy: 0.8811

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: 512
• eval_batch_size: 512
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6293	1.0	1062	0.5118	0.7980
0.5347	2.0	2124	0.3975	0.8323
0.4369	3.0	3186	0.3575	0.8526
0.4335	4.0	4248	0.3329	0.8627
0.4325	5.0	5310	0.3173	0.8693
0.4259	6.0	6372	0.3058	0.8763
0.35	7.0	7434	0.2999	0.8784
0.4424	8.0	8496	0.2985	0.8779
0.3915	9.0	9558	0.2987	0.8755
0.4196	10.0	10620	0.2942	0.8783
0.3827	11.0	11682	0.2936	0.8783
0.32	12.0	12744	0.2895	0.8806
0.3664	13.0	13806	0.2971	0.8737
0.3623	14.0	14868	0.2935	0.8760
0.3542	15.0	15930	0.2943	0.8745
0.3391	16.0	16992	0.2881	0.8810
0.3404	17.0	18054	0.2888	0.8783
0.3747	18.0	19116	0.2893	0.8776
0.38	19.0	20178	0.2856	0.8807
0.3123	20.0	21240	0.2853	0.8811

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0