german_prompt_100k / README.md
ivykopal's picture
Upload folder using huggingface_hub
087cef5 verified
metadata
license: apache-2.0
base_model: bigscience/mt0-base
tags:
  - generated_from_trainer
datasets:
  - wikipedia
metrics:
  - accuracy
model-index:
  - name: german_prompt_100k
    results: []

german_prompt_100k

This model is a fine-tuned version of bigscience/mt0-base on the wikipedia 20231101.de dataset. It achieves the following results on the evaluation set:

  • Loss: 2.9931
  • Accuracy: 0.5009

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: 0.5
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 100000

Training results

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2