distilbert-base-uncased-classifier

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: 0.3165
• Accuracy: 0.8809
• F1: 0.7916

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0	0	0.6991	0.3573	0.4668
No log	0.6006	188	0.3642	0.8505	0.7246
No log	1.2013	376	0.3155	0.8761	0.7717
0.3491	1.8019	564	0.3068	0.8833	0.7972
0.3491	2.4026	752	0.3198	0.8833	0.8016
0.3491	3	939	0.3165	0.8809	0.7916

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2