pile-t5-xl-instruction

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

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 4
  • effective_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=0.00000001
  • num_epochs: 6

Training results

Wandb

Downloads last month
21
Safetensors
Model size
2.85B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for taskydata/pile-t5-xl-instruction

Finetuned
(2)
this model

Dataset used to train taskydata/pile-t5-xl-instruction