--- license: other base_model: AI-Sweden-Models/gpt-sw3-126m tags: - trl - sft - generated_from_trainer model-index: - name: gpt-sw3-126m-njala results: [] datasets: - Sigurdur/njala language: - is library_name: transformers pipeline_tag: text-generation --- [Visualize in Weights & Biases](https://wandb.ai/sigurdurhaukur-team/huggingface/runs/4ut98dmr) # gpt-sw3-126m-njala This model is a fine-tuned version of [AI-Sweden-Models/gpt-sw3-126m](https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m) on [Sigurdur/njala](https://huggingface.co/Sigurdur/njala). ## Model description More information needed ## Intended uses & limitations For writing in the style of the Icelandic sagas, specifically Brennu-Njáls Saga ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.42.3 - Pytorch 2.1.2+cu118 - Datasets 2.20.0 - Tokenizers 0.19.1