bert_base_train_wnli

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

• Loss: 0.7028
• 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
0.71	1.0	3	0.7028	0.5634
0.7063	2.0	6	0.7721	0.4225
0.6915	3.0	9	0.7470	0.4085
0.689	4.0	12	0.7902	0.2676
0.6975	5.0	15	0.8008	0.2254
0.6867	6.0	18	0.8028	0.2394

Framework versions

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