| # Suggested data paths when using GPT-NeoX locally | |
| { | |
| "data_path": "data/enwik8/enwik8_text_document", | |
| # or for weighted datasets: | |
| # "train-data-paths": ["data/enwik8/enwik8_text_document", "data/enwik8/enwik8_text_document"], | |
| # "test-data-paths": ["data/enwik8/enwik8_text_document", "data/enwik8/enwik8_text_document"], | |
| # "valid-data-paths": ["data/enwik8/enwik8_text_document", "data/enwik8/enwik8_text_document"], | |
| # "train-data-weights": [1., 2.], | |
| # "test-data-weights": [2., 1.], | |
| # "valid-data-weights": [0.5, 0.4], | |
| # If weight_by_num_documents is True, Builds dataset weights from a multinomial distribution over groups of data according to the number of documents in each group. | |
| # WARNING: setting this to True will override any user provided weights | |
| # "weight_by_num_documents": false, | |
| # "weighted_sampler_alpha": 0.3, | |
| "vocab_file": "data/gpt2-vocab.json", | |
| "merge_file": "data/gpt2-merges.txt", | |
| "save": "checkpoints", | |
| "load": "checkpoints", | |
| "checkpoint_validation_with_forward_pass": False, | |
| "tensorboard_dir": "tensorboard", | |
| "log_dir": "logs", | |
| "use_wandb": True, | |
| "wandb_host": "https://api.wandb.ai", | |
| "wandb_project": "neox" | |
| } | |