Историја ревизија

Аутор SHA1 Порука Датум
  Xingyao Wang 7340b78962 feat(eval): rewrite log_completions to save completions to directory (#4566) пре 1 година
  mamoodi 6f2e678028 Fix eval output path in case of @ char (#4416) пре 1 година
  Xingyao Wang 25f9413965 [Eval] Fix eval stuck when `result` is too large for pbar (#4361) пре 1 година
  Xingyao Wang 9cc9b19958 eval: improve swebench infer error handling and retry (#4205) пре 1 година
  Xingyao Wang 53a015f718 fix: make llm_completions optional to fix `eval_infer.py` (#4148) пре 1 година
  tobitege c3bbe604eb (fix) Fix logging in shared eval file to prevent key disclosure (#4108) пре 1 година
  Xingyao Wang 81b3cd71b3 [eval] log evaluating warnings directly to console (#4026) пре 1 година
  Xingyao Wang 1b1d8f0b02 [eval] Use `imap_unorderd` for parallizing evaluation (#4040) пре 1 година
  Xingyao Wang a66e738957 [eval] use mp Pool instead ProcessPoolExecutor (#4025) пре 1 година
  Xingyao Wang 714e46f29a [eval] save eventstream & llm completions for SWE-Bench run_infer (#3923) пре 1 година
  Xingyao Wang 5d7f2fd4ae [eval] Allow evaluation of SWE-Bench patches on `RemoteRuntime` (#3927) пре 1 година
  Xingyao Wang f996b31d64 [eval] Fix multi-processing bug (again^3) & allow set EXP_NAME for each `run_infer` (#3907) пре 1 година
  Xingyao Wang 2b3925278d [eval] refactor process instance logic into `update_progress` (#3875) пре 1 година
  Engel Nyst 379f2b6f23 Fix queue length on Macs (#3867) пре 1 година
  Xingyao Wang 3a1b8c093b [eval] yet another eval fixes on multi-processing (#3854) пре 1 година
  Xingyao Wang 78c5f58adc refactor & improve retry for the reliability of `RemoteRuntime` & evaluation (#3846) пре 1 година
  tobitege dbb671a8a5 logname fix; improve test calling instruction (#3666) пре 1 година
  Xingyao Wang 090c911a50 (refactor) Make `Runtime` class synchronous (#3661) пре 1 година
  tobitege 9c39f07430 (enh) Aider-Bench: make resumable with skip_num arg (#3626) пре 1 година
  Raj Maheshwari e72dc96d13 [Fix] Stop API key from leaking in evaluation outputs. (#3603) пре 1 година
  tobitege 8fcf0817d4 (eval) Aider_bench: add eval_ids arg to run specific instance id's (#3592) пре 1 година
  Robert Brennan 01ae22ef57 Rename OpenDevin to OpenHands (#3472) пре 1 година
  Xingyao Wang 31b244f95e [Refactor, Evaluation] Refactor and clean up evaluation harness to remove global config and use EventStreamRuntime (#3230) пре 1 година
  Graham Neubig 3a21198424 Remove monologue agent (#3036) пре 1 година
  Xingyao Wang cf910dfa9d fix eval api_key leak in metadata; fix llm config in run infer (#2998) пре 1 година
  Engel Nyst d37b2973b2 Refactoring: event stream based agent history (#2709) пре 1 година
  Xingyao Wang f6dc89b41a [Evaluation] Simplify eval & and multi-processing related fixes (#2810) пре 1 година
  Graham Neubig a081935fd8 Simplify eval code (#2775) пре 1 година