TSC_classification_model

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: 0.0442
• Precision: 0.8034
• Recall: 0.7769
• F1: 0.7899
• Accuracy: 0.9944

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	48	0.0448	0.4732	0.4380	0.4549	0.9866
No log	2.0	96	0.0389	0.5349	0.5702	0.552	0.9902
No log	3.0	144	0.0346	0.7154	0.7273	0.7213	0.9932
No log	4.0	192	0.0355	0.7611	0.7107	0.7350	0.9937
No log	5.0	240	0.0375	0.7603	0.7603	0.7603	0.9939
No log	6.0	288	0.0376	0.7478	0.7107	0.7288	0.9937
No log	7.0	336	0.0414	0.7699	0.7190	0.7436	0.9939
No log	8.0	384	0.0427	0.7778	0.7521	0.7647	0.9942
No log	9.0	432	0.0432	0.8120	0.7851	0.7983	0.9947
No log	10.0	480	0.0438	0.7983	0.7851	0.7917	0.9947
0.0095	11.0	528	0.0441	0.8034	0.7769	0.7899	0.9944
0.0095	12.0	576	0.0442	0.8034	0.7769	0.7899	0.9944

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2