bert_tiny_olda_book_10_v1_wnli

This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_olda_book_10_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6951
• 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 OptimizerNames.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
0.7049	1.0	3	0.6984	0.5070
0.7024	2.0	6	0.6951	0.5634
0.6926	3.0	9	0.7121	0.4366
0.6947	4.0	12	0.7110	0.4085
0.6935	5.0	15	0.7079	0.4366
0.6882	6.0	18	0.7144	0.3803
0.6881	7.0	21	0.7214	0.3521

Framework versions

• Transformers 4.46.1
• Pytorch 2.2.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.1