hBERTv2_wnli

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6833
• 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
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7351	1.0	3	0.7260	0.5211
0.7223	2.0	6	0.6833	0.5634
0.7189	3.0	9	0.7110	0.4507
0.708	4.0	12	0.7059	0.5352
0.7032	5.0	15	0.6925	0.5352
0.6987	6.0	18	0.7121	0.4225
0.7109	7.0	21	0.6928	0.5352

Framework versions

• Transformers 4.26.1
• Pytorch 1.14.0a0+410ce96
• Datasets 2.10.1
• Tokenizers 0.13.2