Bloom-1b7-creative-writing-IT-baseline

Bloom-1b7-creative-writing-IT

This model is a fine-tuned version of bigscience/bloom-1b7 on an a creative writing - short story dataset.

https://huggingface.co/datasets/adambjorn/UnrelatedForgettingOverhead/viewer/creative

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

Training and evaluation data here: https://huggingface.co/datasets/adambjorn/UnrelatedForgettingOverhead/viewer/creative

Training procedure

The model was instruction tuned on the dataset in the following way:

Given the set of promts:

prompts = [
    "Write a creative short story based on the following title:",
    "Here is a title for a story. Craft a short narrative around it:",
    "Using the title given, develop a short story:",
    "Imagine a short story that starts with this title:",
    "Create a brief story with the following title:"
]

each training example is generated by concatenating one of the prompts with the 'title' and 'selftext' in the following way:

concatenated_texts = [random.choice(prompts) + " " + title + "</s>" + "Story: " + selftext for title, selftext in zip(titles, selftexts)]

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Final reported loss: {'loss': 0.0135, 'grad_norm': 0.6041152477264404, 'learning_rate': 7.446808510638299e-07, 'epoch': 9.89}

Average over tuning: {'train_runtime': 1111.4187, 'train_samples_per_second': 1.71, 'train_steps_per_second': 0.423, 'train_loss': 0.4682149670225509, 'epoch': 9.89}

Framework versions

• Transformers 4.38.1
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2