| #!/bin/bash |
|
|
|
|
| CUDA_VISIBLE_DEVICES=0 python run_glue.py \ |
| --model_name_or_path google-bert/bert-base-cased \ |
| --task_name "cola" \ |
| --do_train \ |
| --do_eval \ |
| --max_seq_length 128 \ |
| --per_device_train_batch_size 32 \ |
| --learning_rate 2.5e-5 \ |
| --num_train_epochs 6 \ |
| --output_dir "cola" \ |
| --overwrite_output_dir \ |
| --apply-trp --trp-depths 1 --trp-p 0.1 --trp-lambdas 0.4 0.2 0.1 |
|
|
|
|
| CUDA_VISIBLE_DEVICES=0 python run_glue.py \ |
| --model_name_or_path google-bert/bert-base-cased \ |
| --task_name "sst2" \ |
| --do_train \ |
| --do_eval \ |
| --max_seq_length 128 \ |
| --per_device_train_batch_size 64 \ |
| --learning_rate 3e-5 \ |
| --num_train_epochs 5 \ |
| --output_dir "sst2" \ |
| --overwrite_output_dir \ |
| --apply-trp --trp-depths 1 --trp-p 0.1 --trp-lambdas 0.4 0.2 0.1 |
|
|
|
|
| CUDA_VISIBLE_DEVICES=0 python run_glue.py \ |
| --model_name_or_path google-bert/bert-base-cased \ |
| --task_name "mrpc" \ |
| --do_train \ |
| --do_eval \ |
| --max_seq_length 128 \ |
| --per_device_train_batch_size 16 \ |
| --learning_rate 2e-5 \ |
| --num_train_epochs 4 \ |
| --output_dir "mrpc" \ |
| --overwrite_output_dir \ |
| --apply-trp --trp-depths 1 --trp-p 0.1 --trp-lambdas 0.4 0.2 0.1 |
|
|
| CUDA_VISIBLE_DEVICES=0 python run_glue.py \ |
| --model_name_or_path google-bert/bert-base-cased \ |
| --task_name "qqp" \ |
| --do_train \ |
| --do_eval \ |
| --max_seq_length 128 \ |
| --per_device_train_batch_size 32 \ |
| --learning_rate 1e-5 \ |
| --num_train_epochs 10 \ |
| --output_dir "qqp" \ |
| --overwrite_output_dir \ |
| --apply-trp --trp-depths 1 --trp-p 0.1 --trp-lambdas 0.4 0.2 0.1 |
|
|
| CUDA_VISIBLE_DEVICES=0 python run_glue.py \ |
| --model_name_or_path google-bert/bert-base-cased \ |
| --task_name "qnli" \ |
| --do_train \ |
| --do_eval \ |
| --max_seq_length 128 \ |
| --per_device_train_batch_size 32 \ |
| --learning_rate 2e-5 \ |
| --num_train_epochs 10 \ |
| --output_dir "qnli" \ |
| --overwrite_output_dir \ |
| --apply-trp --trp-depths 1 --trp-p 0.1 --trp-lambdas 0.4 0.2 0.1 |
|
|
|
|
| CUDA_VISIBLE_DEVICES=0 python run_glue.py \ |
| --model_name_or_path google-bert/bert-base-cased \ |
| --task_name "rte" \ |
| --do_train \ |
| --do_eval \ |
| --max_seq_length 128 \ |
| --per_device_train_batch_size 32 \ |
| --learning_rate 5e-5 \ |
| --num_train_epochs 5 \ |
| --output_dir "rte" \ |
| --overwrite_output_dir \ |
| --apply-trp --trp-depths 1 --trp-p 0.1 --trp-lambdas 0.4 0.2 0.1 |
|
|
|
|