Fiery101/distilgpt2-finetuned-radar

This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set: — Loss: 3.0715 The following hyperparameters were used during training: — learningrate: 2e-05 — trainbatchsize: 8 — evalbatchsize: 8 — seed: 42 — optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 — lrschedulertype: linear — numepochs: 3.0 — Transformers 4.31.0 — Pytorch 1.13.0a0+d0d6b1f — Datasets 2.14.0 — Tokenizers 0.13.3

Модальности:
Генерация текста

Задача: Генерация текста
Автор: Fiery101
Теги: tensorboard, gpt2, generated_from_trainer, text-generation-inference, endpoints_compatible
Лайков: 2  |  Загрузок: 28

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.