README.md

metadata

language:
  - en
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
  - text2text-generation
base_model: google/flan-t5-xl
datasets:
  - grammarly/coedit
model-index:
  - name: >-
      FlanT5 XL Grammarly CoEdit: Text Editing by Task-Specific Instruction
      Tuning
    results: []

FlanT5 XL Grammarly CoEdit: Text Editing by Task-Specific Instruction Tuning

This model is a fine-tuned version of google/flan-t5-xl on the coedit dataset. It achieves the following results on the evaluation set:

• Loss: 0.5379

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.6654	1.0	2158	0.5379

Framework versions

• PEFT 0.10.0
• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2