distilbert_lda_5_v1_wnli

This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_5_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7299
• 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
0.7316	1.0	3	0.7449	0.3099
0.7137	2.0	6	0.7299	0.4507
0.7026	3.0	9	0.7607	0.2958
0.6937	4.0	12	0.7552	0.4930
0.7014	5.0	15	0.7826	0.2113
0.6909	6.0	18	0.8129	0.2394
0.6894	7.0	21	0.8085	0.2113

Framework versions

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