bert-large-cased-finetuned-rte

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

• Loss: 1.5187
• Accuracy: 0.6643

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6969	1.0	623	0.7039	0.5343
0.5903	2.0	1246	0.6461	0.7184
0.4557	3.0	1869	1.5187	0.6643

Framework versions

• Transformers 4.11.0.dev0
• Pytorch 1.9.0
• Datasets 1.12.1
• Tokenizers 0.10.3