bert_base_lda_5_v1_wnli

This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7339
• Accuracy: 0.3803

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
0.7595	1.0	3	0.7547	0.3803
0.7035	2.0	6	0.7339	0.3803
0.6886	3.0	9	0.7605	0.2113
0.6933	4.0	12	0.7814	0.2254
0.6894	5.0	15	0.8143	0.2254
0.6803	6.0	18	0.8258	0.1268
0.6799	7.0	21	0.8547	0.1690

Framework versions

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