TinyBERT_General_6L_768D-finetuned-wikitext103

This model is a fine-tuned version of huawei-noah/TinyBERT_General_6L_768D on the wikitext dataset. It achieves the following results on the evaluation set:

• Loss: 3.3768

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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
4.1792	1.0	3125	3.5465
3.6726	2.0	6250	3.4226
3.6065	3.0	9375	3.3768

Framework versions

• Transformers 4.16.2
• Pytorch 1.8.1
• Datasets 1.11.0
• Tokenizers 0.10.3