This model is a fine-tuned version of cointegrated/rut5-small on the Google Kadle and Custom dataset. It achieves the following results on the evaluation set: — Loss: 0.0008 — Mean Distance: 0 — Max Distance: 3 The following hyperparameters were used during training: — learningrate: 0.0001 — trainbatchsize: 150 — evalbatchsize: 150 — seed: 42 — optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 — lrschedulertype: linear — lrschedulerwarmupratio: 0.1 — num_epochs: 15 — Transformers 4.37.2 — Pytorch 2.1.0+cu121 — Datasets 2.16.1 — Tokenizers 0.15.1
Модальности:
Генерация текста
Задача: Генерация текста
Автор: alexue4
Теги: tensorboard, t5, text2text-generation, generated_from_trainer, ru, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 56
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
