README.md

metadata

base_model: EleutherAI/pile-t5-base
tags:
  - generated_from_trainer
model-index:
  - name: pile-t5-base-instruction
    results: []
language:
  - en
metrics:
  - rouge
datasets:
  - taskydata/Pile-T5-Instruction

pile-t5-base-instruction

This model is a fine-tuned version of EleutherAI/pile-t5-base on Pile-T5-Instruction dataset.

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1