This model is a fine-tuned version of Aravindan/gpt2out on an unknown dataset. It achieves the following results on the evaluation set: — Loss: 1.9618 The following hyperparameters were used during training: — learningrate: 5e-05 — trainbatchsize: 8 — evalbatchsize: 8 — seed: 42 — gradientaccumulationsteps: 16 — totaltrainbatchsize: 128 — optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 — lrschedulertype: linear — lrschedulerwarmupratio: 0.1 — numepochs: 1 — Transformers 4.41.1 — Pytorch 2.1.2 — Datasets 2.19.1 — Tokenizers 0.19.1
Модальности:
Генерация текста
Задача: Генерация текста
Автор: Aravindan
Теги: tensorboard, gpt2, generated_from_trainer, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 18
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
