roberta-l-squadv1.1

<!-- 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. -->

run05-roberta-large-squadv1.1-sl384-ds128-e2-tbs16

This model is a fine-tuned version of roberta-large on the squad dataset.

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: 16
• eval_batch_size: 64
• 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 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1

Train

python run_qa.py \
    --model_name_or_path roberta-large \
    --dataset_name squad \
    --do_eval \
    --do_train \
    --evaluation_strategy steps \
    --eval_steps 500 \
    --learning_rate 3e-5 \
    --fp16 \
    --num_train_epochs 2 \
    --per_device_eval_batch_size 64 \
    --per_device_train_batch_size 16 \
    --max_seq_length 384 \
    --doc_stride 128 \
    --save_steps 1000 \
    --logging_steps 1 \
    --overwrite_output_dir \
    --run_name $RUNID \
    --output_dir $OUTDIR

Eval

export CUDA_VISIBLE_DEVICES=0

MODEL=vuiseng9/roberta-l-squadv1.1
OUTDIR=eval-$(basename $MODEL)
WORKDIR=transformers/examples/pytorch/question-answering
cd $WORKDIR

nohup python run_qa.py  \
    --model_name_or_path  $MODEL \
    --dataset_name squad  \
    --do_eval  \
    --per_device_eval_batch_size 16  \
    --max_seq_length 384  \
    --doc_stride 128  \
    --overwrite_output_dir \
    --output_dir $OUTDIR 2>&1 | tee $OUTDIR/run.log &

  eval_exact_match = 88.4674
  eval_f1          = 94.3001
  eval_samples     =   10790