Commands for training and testing on IMDB dataset.

[VikasRajashekar]

I am using the following command to train the model.

train_command = "python run_classifier.py \
  --do_train=True \
  --do_eval=True \
  --eval_all_ckpt=True \
  --task_name=imdb \
  --data_dir="+DATA_DIR+" \
  --output_dir="+OUTPUT_DIR+" \
  --model_dir="+CHECKPOINT_DIR+" \
  --uncased=False \
  --spiece_model_file="+PRETRAINED_MODEL_DIR+"/spiece.model \
  --model_config_path="+PRETRAINED_MODEL_DIR+"/xlnet_config.json \
  --init_checkpoint="+PRETRAINED_MODEL_DIR+"/xlnet_model.ckpt \
  --max_seq_length=128 \
  --train_batch_size=8 \
  --eval_batch_size=8 \
  --num_hosts=1 \
  --num_core_per_host=1 \
  --learning_rate=2e-5 \
  --train_steps=4000 \
  --warmup_steps=500 \
  --save_steps=500 \
  --iterations=500"

After that how to I test it on my test data set? The readme is not so clear. Can someone explain it?

[JungShinPlusPlus]

Hi. I have same question as well. I'm currently looking for a way to train IMDB with GPU. Thank you.