Commits · e402b78dc22d41c3af7446b167ff4b0123e20e74 · Claudio Scheer / seq-to-seq-bert

Jun 10, 2020
- Update README.md · e402b78d
  Claudio Scheer authored Jun 10, 2020
  
  e402b78d
Jun 06, 2020
- Script to clear cache directories · 5f891542
  Claudio Scheer authored Jun 06, 2020
  
  5f891542
- Train on a smaller dataset · 84a3be85
  Claudio Scheer authored Jun 06, 2020
  
  84a3be85
Jun 05, 2020
- Increase training epochs · f27e43ee
  Claudio Scheer authored Jun 05, 2020
  
  f27e43ee
- Eval model · 0c45e9de
  Claudio Scheer authored Jun 05, 2020
  
  0c45e9de
- Use sys.argv to load the model · 2ead553b
  Claudio Scheer authored Jun 05, 2020
  
  2ead553b
- Use gradient_accumulation_steps · a22a608b
  Claudio Scheer authored Jun 05, 2020
  
  a22a608b
- Remove SQuAD dataset · 5a87357e
  Claudio Scheer authored Jun 05, 2020
  
  5a87357e
- Remove QA example · e15bf509
  Claudio Scheer authored Jun 05, 2020
  
  e15bf509
Jun 03, 2020
- Small dataset for local testing · 9568bc40
  Claudio Scheer authored Jun 03, 2020
  
  9568bc40
- Copy seq2seq model from simpletransformers · 394ac375
  Claudio Scheer authored Jun 03, 2020
  
  394ac375
Jun 02, 2020
- Change batch size to 8 · fa1eb338
  Claudio Scheer authored Jun 02, 2020
  
  fa1eb338
- Remove early_stopping_metric · 63fe6122
  Claudio Scheer authored Jun 02, 2020
  
  63fe6122
- Create smaller dataset · 80ef8a44
  Claudio Scheer authored Jun 02, 2020
  
  80ef8a44
- Add early_stopping_metric · 67454ab7
  Claudio Scheer authored Jun 02, 2020
  
  67454ab7
- Correct get_dataset path · c909f016
  Claudio Scheer authored Jun 02, 2020
  
  c909f016
- Sequence-to-sequence model · f86a52ca
  Claudio Scheer authored Jun 02, 2020
  
  f86a52ca
- Twitter dataset split · fa34e4a6
  Claudio Scheer authored Jun 02, 2020
  
  fa34e4a6
- Twitter dataset · 27ae1169
  Claudio Scheer authored Jun 02, 2020
  
  27ae1169
- Example with simpletransformers · 17775097
  Claudio Scheer authored Jun 02, 2020
  
  17775097
- Remove custom scripts · f1d77b16
  Claudio Scheer authored Jun 02, 2020
  
  f1d77b16
Jun 01, 2020
- Dev dataset · fadfffb1
  Claudio Scheer authored Jun 01, 2020
  
  fadfffb1
- run_squad.py from huggingface/transformers · 25ea5a4f
  Claudio Scheer authored Jun 01, 2020
  
  25ea5a4f
- Update notebooks · 96fe6e6d
  Claudio Scheer authored Jun 01, 2020
  
  96fe6e6d
- Load dataset into batches · 27db2e6c
  Claudio Scheer authored Jun 01, 2020
  
  27db2e6c
- SQuAD dataset · 966852d2
  Claudio Scheer authored Jun 01, 2020
  
  966852d2
May 31, 2020
- Update examples-bert-pre-trained notebook · ec2fb647
  Claudio Scheer authored May 31, 2020
  
  ec2fb647
- Rename notebook · 0ca3396d
  Claudio Scheer authored May 31, 2020
  
  0ca3396d
- Example of BERT pre-trained · 660d4451
  Claudio Scheer authored May 31, 2020
  
  660d4451
- Example using pre-trained BERT · 7d60eac3
  Claudio Scheer authored May 31, 2020
  
  7d60eac3
- Add README.md · 4c35773b
  Claudio Scheer authored May 31, 2020
  
  4c35773b
May 29, 2020
- Remove seq2seq files · f0237054
  Claudio Scheer authored May 29, 2020
  
  f0237054
May 26, 2020
- Update encoder image · d362cb0a
  Claudio Scheer authored May 26, 2020
  
  d362cb0a
May 25, 2020
- Describe embedding of encoder network · a80688f2
  Claudio Scheer authored May 25, 2020
  
  a80688f2
May 24, 2020
- Notebook explaining encoder network · f73317c8
  Claudio Scheer authored May 24, 2020
  
  f73317c8
May 23, 2020
- Describe CustomDataLoader:get_batches in data_loader notebook · 5ae7365e
  Claudio Scheer authored May 23, 2020
  
  5ae7365e
- Download nltk punkt · 1dd80c11
  Claudio Scheer authored May 23, 2020
  
  1dd80c11
- Add data augmentation ideas · 3c12812b
  Claudio Scheer authored May 23, 2020
  
  3c12812b
- Describe CustomDataLoader:__init__ in data_loader notebook · f506e431
  Claudio Scheer authored May 23, 2020
  
  f506e431
- Add dataset · 9de46293
  Claudio Scheer authored May 23, 2020
  
  9de46293