deu-baseline-small / README.md
bbunzeck's picture
Update README.md
803dc8b verified
metadata
library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: deu-baseline-small
    results: []
datasets:
  - BabyLM-community/babylm-deu
language:
  - de

deu-baseline-small

This model achieves the following results on the evaluation set:

  • Loss: 3.0813

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: 0.0001
  • train_batch_size: 64
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
3.9833 1.0 4944 3.4167
3.3928 2.0 9888 3.2166
3.2653 3.0 14832 3.1392
3.2041 4.0 19776 3.0987
3.1707 5.0 24720 3.0813

Framework versions

  • Transformers 4.53.0
  • Pytorch 2.7.1+cu126
  • Datasets 4.0.0
  • Tokenizers 0.21.2