distilbert_lda_50_v1_book_wnli

This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_50_v1_book on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7043
• Accuracy: 0.3099

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
0.7047	1.0	3	0.7053	0.3099
0.6978	2.0	6	0.7043	0.3099
0.6905	3.0	9	0.7082	0.2958
0.6902	4.0	12	0.7104	0.3944
0.6922	5.0	15	0.7221	0.2535
0.6917	6.0	18	0.7358	0.3099
0.6893	7.0	21	0.7396	0.1972

Framework versions

• Transformers 4.46.3
• Pytorch 2.2.1+cu118
• Datasets 2.17.0
• Tokenizers 0.20.3