|
--- |
|
base_model: EleutherAI/pile-t5-xl |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pile-t5-xl-instruction |
|
results: [] |
|
language: |
|
- en |
|
metrics: |
|
- rouge |
|
datasets: |
|
- taskydata/Pile-T5-Instruction |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# pile-t5-xl-instruction |
|
|
|
This model is a fine-tuned version of [EleutherAI/pile-t5-xl](https://huggingface.co/EleutherAI/pile-t5-xl) on [Pile-T5-Instruction](https://huggingface.co/datasets/taskydata/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](https://wandb.ai/jordanclive/tasky-instruction/runs/5yx1yzzk/overview) |
|
|
