albert-base-v2-finetuned-wnli

This model is a fine-tuned version of albert-base-v2 on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.6981
• 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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• 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	10	0.6954	0.4930
No log	2.0	20	0.6981	0.5634
No log	3.0	30	0.7036	0.4225
No log	4.0	40	0.7062	0.3944
No log	5.0	50	0.7035	0.4225

Framework versions

• Transformers 4.21.0
• Pytorch 1.12.0+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1