bert-finetune / README.md
medelharchaoui's picture
Upload tokenizer
d8fe70f verified
metadata
license: apache-2.0
tags:
  - generated_from_trainer
base_model: google-bert/bert-base-cased
metrics:
  - accuracy
model-index:
  - name: bert-finetune
    results: []

bert-finetune

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

  • Loss: 1.6157
  • Accuracy: 0.581

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 125 1.2290 0.545
No log 2.0 250 1.3313 0.576
No log 3.0 375 1.6157 0.581

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.2.2
  • Datasets 2.19.0
  • Tokenizers 0.19.1