is anyone know how to replace EXT_CKPT to train BertExtAbs?
I use this code
!python train.py -task abs -mode train -bert_data_path ../bert_data/cnndm -dec_dropout 0.2 -model_path ../models -sep_optim true -lr_bert 0.002 -lr_dec 0.2 -save_checkpoint_steps 2000 -batch_size 140 -train_steps 2000 -report_every 50 -accum_count 5 -use_bert_emb true -use_interval true -warmup_steps_bert 2000 -warmup_steps_dec 10000 -max_pos 512 -visible_gpus 0 -log_file ../logs/abs_bert_cnndm -load_from_extractive ../models

and then i got this error

[2022-01-15 14:50:25,555 INFO] Namespace(accum_count=5, alpha=0.6, batch_size=140, beam_size=5, bert_data_path='../bert_data/cnndm', beta1=0.9, beta2=0.999, block_trigram=True, dec_dropout=0.2, dec_ff_size=2048, dec_heads=8, dec_hidden_size=768, dec_layers=6, enc_dropout=0.2, enc_ff_size=512, enc_hidden_size=512, enc_layers=6, encoder='bert', ext_dropout=0.2, ext_ff_size=2048, ext_heads=8, ext_hidden_size=768, ext_layers=2, finetune_bert=True, generator_shard_size=32, gpu_ranks=[0], label_smoothing=0.1, large=False, load_from_extractive='../models', log_file='../logs/abs_bert_cnndm', lr=1, lr_bert=0.002, lr_dec=0.2, max_grad_norm=0, max_length=150, max_pos=512, max_tgt_len=140, min_length=15, mode='train', model_path='../models', optim='adam', param_init=0, param_init_glorot=True, recall_eval=False, report_every=50, report_rouge=True, result_path='../results/cnndm', save_checkpoint_steps=2000, seed=666, sep_optim=True, share_emb=False, task='abs', temp_dir='../temp', test_all=False, test_batch_size=200, test_from='', test_start_from=-1, train_from='', train_steps=2000, use_bert_emb=True, use_interval=True, visible_gpus='0', warmup_steps=8000, warmup_steps_bert=2000, warmup_steps_dec=10000, world_size=1) [2022-01-15 14:50:25,555 INFO] Device ID 0 [2022-01-15 14:50:25,555 INFO] Device cuda [2022-01-15 14:50:25,585 INFO] Loading bert from extractive model ../models Traceback (most recent call last): File "train.py", line 122, in <module> train_abs(args, device_id) File "/content/PreSumm/src/train_abstractive.py", line 273, in train_abs train_abs_single(args, device_id) File "/content/PreSumm/src/train_abstractive.py", line 303, in train_abs_single bert_from_extractive = torch.load(args.load_from_extractive, map_location=lambda storage, loc: storage) File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 594, in load with _open_file_like(f, 'rb') as opened_file: File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 230, in _open_file_like return _open_file(name_or_buffer, mode) File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 211, in __init__ super(_open_file, self).__init__(open(name, mode)) IsADirectoryError: [Errno 21] Is a directory: '../models'