bert-base-uncased-squad-v1

This model is a fine-tuned version of bert-base-uncased on the squad dataset. It was finetuned following the Transformers Question Answering example:

python run_qa.py \
  --model_name_or_path bert-base-uncased \
  --dataset_name squad \
  --do_train \
  --do_eval \
  --per_device_train_batch_size 12 \
  --learning_rate 3e-5 \
  --num_train_epochs 2 \
  --max_seq_length 384 \
  --doc_stride 128 \

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 12
• 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

Training results

***** eval metrics *****
  epoch                   =        2.0
  eval_exact_match        =    81.3434
  eval_f1                 =    88.7002
  eval_samples            =      10784

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.8.0
• Tokenizers 0.13.2