defect-classification-distilbert-baseline-15-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: 0.2980
• Accuracy: 0.8765

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7058	1.0	1062	0.6084	0.7927
0.5439	2.0	2124	0.4581	0.8141
0.4417	3.0	3186	0.3951	0.8403
0.4504	4.0	4248	0.3578	0.8487
0.428	5.0	5310	0.3352	0.8584
0.4089	6.0	6372	0.3347	0.8638
0.3428	7.0	7434	0.3248	0.8681
0.4219	8.0	8496	0.3178	0.8715
0.3689	9.0	9558	0.3044	0.8736
0.3891	10.0	10620	0.3037	0.8724
0.3849	11.0	11682	0.3064	0.8713
0.3302	12.0	12744	0.3006	0.8758
0.3576	13.0	13806	0.3016	0.8742
0.3548	14.0	14868	0.2990	0.8766
0.3596	15.0	15930	0.2980	0.8765

Framework versions

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