chinese-bert-wwm-ext-finetuned-cola

This model is a fine-tuned version of hfl/chinese-bert-wwm-ext on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5747
• Matthews Correlation: 0.4085

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.5824	1.0	66375	0.5746	0.4083
0.5824	2.0	66376	0.5747	0.4085

Framework versions

• Transformers 4.12.5
• Pytorch 1.7.1
• Datasets 1.15.1
• Tokenizers 0.10.3