hBERTv1_no_pretrain_qnli

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

• Loss: 0.6931
• Accuracy: 0.5054

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: 4e-05
• train_batch_size: 96
• eval_batch_size: 96
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7059	1.0	1092	0.7004	0.5054
0.6948	2.0	2184	0.6938	0.4946
0.6939	3.0	3276	0.6932	0.5054
0.6936	4.0	4368	0.6931	0.5054
0.6934	5.0	5460	0.6931	0.5054
0.6936	6.0	6552	0.6931	0.5054
0.6933	7.0	7644	0.6931	0.5054
0.6933	8.0	8736	0.6931	0.5054
0.6934	9.0	9828	0.6934	0.5054
0.6933	10.0	10920	0.6931	0.5054
0.6932	11.0	12012	0.6933	0.4946
0.6932	12.0	13104	0.6931	0.5054
0.6933	13.0	14196	0.6931	0.5054

Framework versions

• Transformers 4.30.2
• Pytorch 1.14.0a0+410ce96
• Datasets 2.12.0
• Tokenizers 0.13.3