bert-base-uncased-finetuned-rte

This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.8075
• 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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	63	0.6777	0.5668
No log	2.0	126	0.6723	0.6282
No log	3.0	189	0.7238	0.6318
No log	4.0	252	0.7993	0.6354
No log	5.0	315	0.8075	0.6643

Framework versions

• Transformers 4.15.0
• Pytorch 1.10.0+cu111
• Datasets 1.18.1
• Tokenizers 0.10.3