distilbert_km_10_v2_wnli

This model is a fine-tuned version of Hartunka/distilbert_km_10_v2 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7238
• Accuracy: 0.4507

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
0.7255	1.0	3	0.7238	0.4507
0.7018	2.0	6	0.7716	0.3380
0.6967	3.0	9	0.7804	0.1972
0.6823	4.0	12	0.7970	0.3521
0.6847	5.0	15	0.8308	0.1408
0.6795	6.0	18	0.8760	0.1690

Framework versions

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