tiny-bert-sst2-distilled

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:

• eval_loss: 3.0017
• eval_accuracy: 0.7477
• eval_runtime: 0.3985
• eval_samples_per_second: 2188.296
• eval_steps_per_second: 17.567
• epoch: 1.0
• step: 527

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: 6.708803333901887e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 33
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0
• Datasets 2.3.2
• Tokenizers 0.12.1