tiny-bert-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. -->

tiny-bert-sst2-distilled

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

• eval_loss: 0.4465
• eval_accuracy: 0.7936
• eval_runtime: 2.0985
• eval_samples_per_second: 415.531
• eval_steps_per_second: 3.336
• 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: 4.5121940478076524e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 33
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 8
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cpu
• Datasets 3.5.0
• Tokenizers 0.21.1