albert-xxlarge-v2-finetuned-wnli

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

• Loss: 0.6970
• Accuracy: 0.5070

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	13	0.8066	0.4366
No log	2.0	26	0.6970	0.5070
No log	3.0	39	0.7977	0.4507
No log	4.0	52	0.7906	0.4930
No log	5.0	65	0.8459	0.4366

Framework versions

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