metadata

license: apache-2.0
base_model: google/bert_uncased_L-2_H-128_A-2
tags:
  - generated_from_trainer
model-index:
  - name: tiny-bert-sst2-distilled
    results: []

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: 0.4144
eval_accuracy: 0.8229
eval_recall: 0.8885
eval_precision: 0.7855
eval_f1: 0.8338
eval_runtime: 28.3161
eval_samples_per_second: 36.093
eval_steps_per_second: 1.13
epoch: 5.0
step: 480

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: 0.00012559849066773733
train_batch_size: 32
eval_batch_size: 32
seed: 33
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 9

Framework versions

Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2