metadata

license: bigscience-bloom-rail-1.0
tags:
  - generated_from_trainer
datasets:
  - squad_v2
base_model: bigscience/bloom-560m
model-index:
  - name: debug_bloom_squad
    results: []

POC - BLOOM for QuestionAnswering, tuned on squad_v2

This model is a fine-tuned version of bigscience/bloom-560m on the squad_v2 dataset. It is intended for a proof of concept, and perhaps to serve as a starting point for others trying to do the same thing.

Ongoing discussion surrounding this effort:

https://huggingface.co/bigscience/bloom/discussions/46#633c57b2ccce04161f82e6c2

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: 3e-05
train_batch_size: 6
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2.0
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.24.0.dev0
Pytorch 1.12.1+cu102
Datasets 2.6.1
Tokenizers 0.13.1