xent 0 at step -1 and no produced extractive sumamry, raw text summarization

[Hellscream64]

Hello, when passing the following command in google colab:

!python /content/PreSumm/src/train.py -task ext -mode test_text -test_from /content/PreSumm/models/bertext_cnndm_transformer.pt -text_src /content/PreSumm/raw_data/temp_ext.raw_src -text_tgt /content/PreSumm/results/result.txt -log_file /content/PreSumm/logs/ext_bert_cnndm

i get the following message (and no summary):

2020-05-07 13:02:11,945 INFO] Loading checkpoint from /content/PreSumm/models/bertext_cnndm_transformer.pt
Namespace(accum_count=1, alpha=0.6, batch_size=140, beam_size=5, bert_data_path='../bert_data_new/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='', log_file='/content/PreSumm/logs/ext_bert_cnndm', lr=1, lr_bert=0.002, lr_dec=0.002, max_grad_norm=0, max_length=150, max_ndocs_in_batch=6, max_pos=512, max_tgt_len=140, min_length=15, mode='test_text', model_path='../models/', optim='adam', param_init=0, param_init_glorot=True, recall_eval=False, report_every=1, report_rouge=True, result_path='../results/cnndm', save_checkpoint_steps=5, seed=666, sep_optim=False, share_emb=False, task='ext', temp_dir='../temp', test_all=False, test_batch_size=200, test_from='/content/PreSumm/models/bertext_cnndm_transformer.pt', test_start_from=-1, text_src='/content/PreSumm/raw_data/temp_ext.raw_src', text_tgt='/content/PreSumm/results/result.txt', train_from='', train_steps=1000, use_bert_emb=False, use_interval=True, visible_gpus='-1', warmup_steps=8000, warmup_steps_bert=8000, warmup_steps_dec=8000, world_size=1)
[2020-05-07 13:02:38,988 INFO] https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-config.json not found in cache or force_download set to True, downloading to /tmp/tmpi493s3ng
100% 433/433 [00:00<00:00, 202874.62B/s]
[2020-05-07 13:02:39,141 INFO] copying /tmp/tmpi493s3ng to cache at ../temp/4dad0251492946e18ac39290fcfe91b89d370fee250efe9521476438fe8ca185.7156163d5fdc189c3016baca0775ffce230789d7fa2a42ef516483e4ca884517
[2020-05-07 13:02:39,141 INFO] creating metadata file for ../temp/4dad0251492946e18ac39290fcfe91b89d370fee250efe9521476438fe8ca185.7156163d5fdc189c3016baca0775ffce230789d7fa2a42ef516483e4ca884517
[2020-05-07 13:02:39,142 INFO] removing temp file /tmp/tmpi493s3ng
[2020-05-07 13:02:39,143 INFO] loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-config.json from cache at ../temp/4dad0251492946e18ac39290fcfe91b89d370fee250efe9521476438fe8ca185.7156163d5fdc189c3016baca0775ffce230789d7fa2a42ef516483e4ca884517
[2020-05-07 13:02:39,143 INFO] Model config {
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "finetuning_task": null,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "num_labels": 2,
  "output_attentions": false,
  "output_hidden_states": false,
  "pad_token_id": 0,
  "pruned_heads": {},
  "torchscript": false,
  "type_vocab_size": 2,
  "vocab_size": 30522
}

[2020-05-07 13:02:39,328 INFO] https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-pytorch_model.bin not found in cache or force_download set to True, downloading to /tmp/tmp7pfw_spl
100% 440473133/440473133 [00:30<00:00, 14625594.91B/s]
[2020-05-07 13:03:09,637 INFO] copying /tmp/tmp7pfw_spl to cache at ../temp/aa1ef1aede4482d0dbcd4d52baad8ae300e60902e88fcb0bebdec09afd232066.36ca03ab34a1a5d5fa7bc3d03d55c4fa650fed07220e2eeebc06ce58d0e9a157
[2020-05-07 13:03:10,881 INFO] creating metadata file for ../temp/aa1ef1aede4482d0dbcd4d52baad8ae300e60902e88fcb0bebdec09afd232066.36ca03ab34a1a5d5fa7bc3d03d55c4fa650fed07220e2eeebc06ce58d0e9a157
[2020-05-07 13:03:10,881 INFO] removing temp file /tmp/tmp7pfw_spl
[2020-05-07 13:03:10,935 INFO] loading weights file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-pytorch_model.bin from cache at ../temp/aa1ef1aede4482d0dbcd4d52baad8ae300e60902e88fcb0bebdec09afd232066.36ca03ab34a1a5d5fa7bc3d03d55c4fa650fed07220e2eeebc06ce58d0e9a157
gpu_rank 0
[2020-05-07 13:03:14,619 INFO] * number of parameters: 120512513
[2020-05-07 13:03:14,773 INFO] https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt not found in cache or force_download set to True, downloading to /tmp/tmp2oza5l6v
100% 231508/231508 [00:00<00:00, 1993268.83B/s]
[2020-05-07 13:03:15,056 INFO] copying /tmp/tmp2oza5l6v to cache at /root/.cache/torch/pytorch_transformers/26bc1ad6c0ac742e9b52263248f6d0f00068293b33709fae12320c0e35ccfbbb.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084
[2020-05-07 13:03:15,056 INFO] creating metadata file for /root/.cache/torch/pytorch_transformers/26bc1ad6c0ac742e9b52263248f6d0f00068293b33709fae12320c0e35ccfbbb.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084
[2020-05-07 13:03:15,056 INFO] removing temp file /tmp/tmp2oza5l6v
[2020-05-07 13:03:15,057 INFO] loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt from cache at /root/.cache/torch/pytorch_transformers/26bc1ad6c0ac742e9b52263248f6d0f00068293b33709fae12320c0e35ccfbbb.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084
  0% 0/2 [00:00<?, ?it/s]
[2020-05-07 13:03:15,096 INFO] Validation xent: 0 at step -1

what is wrong here? this is my colab: https://colab.research.google.com/drive/139TDJ32WxG2cIDOQIwnXccogGvbphVPw

[AyeshaSarwar]

I am also facing the same issue. There are only two files in the results folder containing .candidate and .gold file. and candidate file contains the same text from the raw text file.

[Hellscream64]

Yeah figured out, you have to name an specific filename in the resultparameter. I don't belive that's the intented way and the file which is produced has a realy strange name but it works.. Almost I'm currently facing the one sentence error (which should be solved :D)

AyeshaSarwar notifications@github.com schrieb am Mo., 18. Mai 2020, 18:32:

I am also facing the same issue. There are only two files in the results folder containing .candidate and .gold file but cannot find any system generated summary. Not even can determine from the command line output.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/nlpyang/PreSumm/issues/160#issuecomment-630298357, or unsubscribe https://github.com/notifications/unsubscribe-auth/ANNMBAJZXVBOA2XV5FVUZZTRSFPLJANCNFSM4M3KFK5Q .