tuanio's picture
Model save
afac3f6
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: fine-tuning-binary_bert-cola-glue-steps47-bs128-0.0003-8-8-512-0.1
    results: []

fine-tuning-binary_bert-cola-glue-steps47-bs128-0.0003-8-8-512-0.1

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0003
  • Accuracy: 1.0

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: 0.0003
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 256
  • total_eval_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3086 0.21 5 0.0410 1.0
0.02 0.42 10 0.0019 1.0
0.0016 0.62 15 0.0005 1.0
0.0006 0.83 20 0.0003 1.0

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1