crystina-z/monoXLMR.pft-msmarco

Trained with Tevatron reranker branch;

script:

epoch=3
bs=32
gradient_accumulation_steps=8
real_bs=$(( $bs / $gradient_accumulation_steps ))

CUDA_VISIBLE_DEVICES=0 python examples/reranker/reranker_train.py \
  --output_dir reranker_xlmr.bs-$bs.epoch-$epoch \
  --model_name_or_path xlm-roberta-large \
  --save_steps 20000 \
  --dataset_name Tevatron/msmarco-passage \
  --fp16 \
  --per_device_train_batch_size $real_bs \
  --gradient_accumulation_steps $gradient_accumulation_steps \
  --train_n_passages 8 \
  --learning_rate 5e-6 \
  --q_max_len 16 \
  --p_max_len 128 \
  --num_train_epochs $epoch \
  --logging_steps 500 \
  --dataloader_num_workers 4 \
  --overwrite_output_dir