distilbert_rand_50_v1_wnli

This model is a fine-tuned version of Hartunka/distilbert_rand_50_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6969
• Accuracy: 0.5493

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
0.7156	1.0	3	0.6969	0.5493
0.6966	2.0	6	0.7140	0.4225
0.6971	3.0	9	0.7073	0.4789
0.6959	4.0	12	0.7109	0.5070
0.6934	5.0	15	0.7317	0.3380
0.7012	6.0	18	0.7443	0.3099

Framework versions

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