GiantTreeG/german-jeopardy-longt5-base-256

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

german-jeopardy-longt5-base-256

This model is a fine-tuned version of google/long-t5-tglobal-base on the lmqg/qg_dequad dataset. It achieves the following results on the evaluation set:

• —Loss: 1.7833
• —Brevity Penalty: 0.8244
• —System Length: 17427
• —Reference Length: 20793
• —ROUGE-1: 34.80
• —ROUGE-2: 16.54
• —ROUGE-L: 33.69
• —ROUGE-Lsum: 33.70
• —Exact Match: 1.50
• —BLEU: 10.52
• —F1: 33.92

Model description

See google/long-t5-tglobal-base for more information about the model architecture. The model was trained on a single NVIDIA RTX 3090 GPU with 24GB of VRAM.

Intended uses & limitations

This model can be used for question generation on German text.

Training and evaluation data

See lmqg/qg_dequad.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 0.0001
• —trainbatchsize: 8
• —evalbatchsize: 4
• —seed: 7
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 256
• —optimizer: Adafactor
• —lrschedulertype: constant
• —num_epochs: 20

Training results

Framework versions

• —Transformers 4.32.1
• —Pytorch 2.1.0
• —Datasets 2.12.0
• —Tokenizers 0.13.3