checkpoints / README.md
Mariaaaaa's picture
Mariaaaaa/best_model_with_bitfit
dd3f68f verified
metadata
license: mit
base_model: prajjwal1/bert-tiny
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: checkpoints
    results: []

checkpoints

This model is a fine-tuned version of prajjwal1/bert-tiny on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6530
  • Accuracy: 0.6392

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: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6751 1.0 1250 0.6668 0.626
0.6634 2.0 2500 0.6576 0.634
0.6584 3.0 3750 0.6556 0.6286
0.6548 4.0 5000 0.6530 0.6392

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2