led-large-book-summary: continued

Fine-tuned further to explore if any improvements vs. the default.

Details

This model is a version of pszemraj/led-large-book-summary further fine-tuned for two epochs.

Usage

It's recommended to use this model with beam search decoding. If interested, you can also use the textsum util repo to have most of this abstracted out for you:

pip install -U textsum

from textsum.summarize import Summarizer

model_name = "pszemraj/led-large-book-summary-continued"
summarizer = Summarizer(model_name) # GPU auto-detected
text = "put the text you don't want to read here"
summary = summarizer.summarize_string(text)
print(summary)

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 8191
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 2.0
• mixed_precision_training: Native AMP