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
- Downloads last month
- 29