gokuls/tiny-bert-sst2-mobilebert-distillation

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

tiny-bert-sst2-mobilebert-distillation

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the glue dataset. It achieves the following results on the evaluation set:

• —Loss: 1.2829
• —Accuracy: 0.8394

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: 5e-05
• —trainbatchsize: 16
• —evalbatchsize: 16
• —seed: 33
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 10
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.21.1
• —Pytorch 1.12.1+cu113
• —Datasets 2.4.0
• —Tokenizers 0.12.1