salesforce/CodeRL

Issues

• CodeT5 input for APPS/MBPP problems

  #27 opened 2 years ago by ysymyth
  2

• start_idx variable not defined in extract_example_test.ipynb

  #59 opened 8 months ago by log6305
  1

• How to arrange the file ‘models’？？？

  #58 opened 8 months ago by Mucalinda2436
  0

• Critic Training pre-processing steps

  #47 opened a year ago by xylankant
  3

• When will you release the implementation details of your critic sampling procedure please?

  #57 opened a year ago by JulietLJY
  0

• How to generate Critic Scores that can mimic a reward model

  #55 opened a year ago by AhmedKhaled945
  0

• problems in the critic model results

  #50 opened a year ago by Juanting-Xu
  0

• Problems in reproducing the RL fine-tuned results

  #30 opened 2 years ago by abhik1505040
  8

• Datasets for train_actor_rl.sh

  #24 opened 2 years ago by doviettung96
  11

• Any updates on Generating Programs with Critic Sampling?

  #35 opened 2 years ago by Symbolk
  0

• documentation request for test_one_solution.py

  #33 opened 2 years ago by ziwenyd
  0

• Critic training problem: Category imbalance in data

  #32 opened 2 years ago by rongaoli
  0

• what is the super-parameters for RL training

  #29 opened 2 years ago by Zyq-scut
  2

• Question about the max-pooling operation.

  #31 opened 2 years ago by rongaoli
  2

• exception of run_unit_tests.sh

  #19 opened 2 years ago by qfzhu
  1

• Finetuned model checkpoints

  #2 opened 2 years ago by boblee22
  9

• Actor model finetuning code based on reward and policy gradient

  #13 opened 2 years ago by parshinsh
  1

• Sample Temperature

  #22 opened 2 years ago by MrBlack0220
  1

• Question about the input of the critic model

  #28 opened 2 years ago by Zyq-scut
  1

• RL with execution-based reward

  #26 opened 2 years ago by ysymyth
  2

• Performance Results on HumanEval

  #25 opened 2 years ago by htcml
  1

• problem about run_unit_tests.sh

  #23 opened 2 years ago by MrBlack0220
  0

• Run generate.py with the CodeT5-large trained on the ground-truth programs

  #18 opened 2 years ago by doviettung96
  4

• Bugs for automated example input/output test case extraction

  #15 opened 2 years ago by zfj1998
  1

• Does `Trainer_Critic` class mimic `transformers`'s `Trainer` class?

  #14 opened 2 years ago by cwarny
  1

• Question about pre-training process

  #3 opened 2 years ago by natedingyifeng
  1

• Politically correct license description

  #1 opened 2 years ago by xloem
  1