distilbert_km_10_v1_wnli

This model is a fine-tuned version of Hartunka/distilbert_km_10_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7291
• Accuracy: 0.4648

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: 5e-05
• train_batch_size: 256
• eval_batch_size: 256
• seed: 10
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7317	1.0	3	0.7291	0.4648
0.6981	2.0	6	0.7765	0.2817
0.6939	3.0	9	0.8103	0.1831
0.6802	4.0	12	0.8170	0.1972
0.6814	5.0	15	0.8486	0.1690
0.6762	6.0	18	0.8927	0.1831

Framework versions

• Transformers 4.50.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.21.1