test6 / README.md
piazzola's picture
End of training
4c7cbf7 verified
|
raw
history blame
1.73 kB
metadata
license: apache-2.0
base_model: google-bert/bert-large-uncased
tags:
  - generated_from_trainer
model-index:
  - name: checkpoint
    results: []

checkpoint

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

  • Loss: 0.5713

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: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss
0.9089 0.4 7373 0.8463
0.6975 0.8 14746 0.6603
0.5207 1.2 22119 0.6005
0.4985 1.6 29492 0.5558
0.4572 2.0 36865 0.5206
0.3228 2.4 44238 0.5485
0.305 2.8 51611 0.5243
0.2171 3.2 58984 0.5674
0.2057 3.6 66357 0.5713

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2