philschmid/bert-mini-sst2-distilled

<!-- 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. -->

bert-mini-sst2-distilled

This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the glue dataset. It achieves the following results on the evaluation set:

• —Loss: 1.1792
• —Accuracy: 0.8567

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: 0.00021185586235152412
• —trainbatchsize: 1024
• —evalbatchsize: 1024
• —seed: 33
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 8
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.12.3
• —Pytorch 1.9.1
• —Datasets 1.15.1
• —Tokenizers 0.10.3