kavin comments

Repositories
Issues
Comments

Results 3 comments of


                                            kavin

The results can't be reproduced

the command is "python -m run_classifier.py --output_dir=./output/RTE \ --data_dir=./glue \ --vocab_file=albert_base_v2/vocab.txt \ --spm_model_file=albert_base_v2/30k-clean.model \ --albert_config_file=albert_base_v2/albert_config.json \ --do_lower_case \ --do_train \ --do_eval \ --use_tpu=False \ --init_checkpoint=albert_base_v2/model.ckpt-best \ --max_seq_length=512 \ --optimizer=adamw \...

Hyper-params settings for MNLI fine-tuning using Albert-v2

hi，I run the code according to the official command, but it doesn't reproduce the results, only get accuracy of ~52.6, can you tell me where is wrong?

[Problem/ Squad V2] the result is too low compare with the F1 score in paper, Is something wrong?

> hi, I meet the same problem, the result is too low, can you tell me how to change TPUEstimator to Estimator and change TPUEstimatorSpec to EstimatorSpec?