---
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: Graphcore/bert-base-uncased-squad
  results: []
---

# Graphcore/bert-base-uncased-squad11

This model is a fine-tuned version of [Graphcore/bert-base-uncased](https://huggingface.co/Graphcore/bert-base-uncased) on the squad dataset.


## Intended uses & limitations

More information needed

## Training and evaluation data

[squad dataset](https://huggingface.co/datasets/squad)

## Training procedure

Model was trained on 16 Graphcore Mk2 IPUs using the [optimum-graphcore](https://github.com/huggingface/optimum-graphcore) library.

Command line:

```
python examples/question-answering/run_qa.py \
  --model_name_or_path Graphcore/bert-base-uncased \
  --ipu_config_name Graphcore/bert-base-ipu \
  --dataset_name squad \
  --do_train \
  --do_eval \
  --num_train_epochs 3 \
  --per_device_train_batch_size 2 \
  --per_device_eval_batch_size 2 \
  --gradient_accumulation_steps 16 \
  --pod_type pod16 \
  --learning_rate 9e-5 \
  --max_seq_length 384 \
  --doc_stride 128 \
  --seed 42\
  --lr_scheduler_type linear \
  --loss_scaling 64 \
  --weight_decay 0.01 \
  --warmup_ratio 0.2 \
  --logging_steps 1 \
  --save_steps 50 \
  --dataloader_num_workers 64 \
  --ipu_config_overrides "embedding_serialization_factor=2" \
  --output_dir squad_v2_bert_base \
  --overwrite_output_dir
```

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 6e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: IPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
- training precision: Mixed Precision

### Training results

```
{ 
    "epoch": 3.0,
    "eval_exact_match": 81.79754020813624,
    "eval_f1": 88.84840994541061,
    "eval_samples": 10784
}
```


### Framework versions

- Transformers 4.18.0.dev0
- Pytorch 1.10.0+cpu
- Datasets 1.18.4
- Tokenizers 0.11.6