bert_train_book_ent_15p_mid_wnli

This model is a fine-tuned version of gokulsrinivasagan/bert_train_book_ent_15p_mid on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6854
• Accuracy: 0.5634

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
0.7086	1.0	3	0.6898	0.5634
0.7213	2.0	6	0.6862	0.5634
0.699	3.0	9	0.6976	0.4366
0.6982	4.0	12	0.7079	0.4366
0.6992	5.0	15	0.6951	0.4366
0.6953	6.0	18	0.6882	0.5634
0.6986	7.0	21	0.6854	0.5634
0.6991	8.0	24	0.6903	0.5634
0.6941	9.0	27	0.6972	0.4366
0.6926	10.0	30	0.6951	0.4366
0.6981	11.0	33	0.6896	0.5634
0.6941	12.0	36	0.6901	0.5634

Framework versions

• Transformers 4.51.2
• Pytorch 2.6.0+cu126
• Datasets 3.5.0
• Tokenizers 0.21.1