add_BERT_no_pretrain_wnli

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

• Loss: 0.6852
• 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: 4e-05
• train_batch_size: 128
• eval_batch_size: 128
• 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
0.9529	1.0	5	0.6860	0.5634
0.762	2.0	10	0.8068	0.4366
0.7199	3.0	15	0.6987	0.4366
0.7092	4.0	20	0.6958	0.5634
0.7149	5.0	25	0.6854	0.5634
0.7069	6.0	30	0.6956	0.4366
0.7008	7.0	35	0.6986	0.4366
0.7079	8.0	40	0.6852	0.5634
0.7444	9.0	45	0.7382	0.4366
0.7147	10.0	50	0.7009	0.5634
0.7318	11.0	55	0.7316	0.4366
0.7212	12.0	60	0.6858	0.5634
0.7043	13.0	65	0.7075	0.4366

Framework versions

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