Skip to content

Actions: CarperAI/trlx

Build

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
193 workflow runs
193 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Value branch
Build #1124: Pull request #530 synchronize by Dahoas
July 26, 2023 13:13 15m 47s value-branch
July 26, 2023 13:13 15m 47s
Fix LLaMA example (LLaMA 2)
Build #1123: Pull request #539 synchronize by PhungVanDuy
July 26, 2023 12:48 23m 4s PhungVanDuy:hot_fix_llama2_example
July 26, 2023 12:48 23m 4s
Value branch
Build #1122: Pull request #530 synchronize by Dahoas
July 26, 2023 09:17 15m 41s value-branch
July 26, 2023 09:17 15m 41s
Fix LLaMA example (LLaMA 2)
Build #1121: Pull request #539 synchronize by PhungVanDuy
July 25, 2023 22:29 19m 27s PhungVanDuy:hot_fix_llama2_example
July 25, 2023 22:29 19m 27s
Fix ordering of ppo epoch iteration
Build #1119: Pull request #522 synchronize by RobertKirk
July 25, 2023 12:34 23m 15s RobertKirk:main
July 25, 2023 12:34 23m 15s
fix(modeling): deepspeed checkpoint loading
Build #1118: Pull request #482 synchronize by maxreciprocate
July 25, 2023 10:58 18m 51s fix-checkpoint-loading
July 25, 2023 10:58 18m 51s
Add DS-Chat comparison
Build #1117: Pull request #538 opened by cat-state
July 24, 2023 17:11 24m 26s nemo-ppo-vs-ds-chat
July 24, 2023 17:11 24m 26s
fix(modeling): deepspeed checkpoint loading
Build #1116: Pull request #482 synchronize by maxreciprocate
July 24, 2023 12:21 14m 59s fix-checkpoint-loading
July 24, 2023 12:21 14m 59s
fix(modeling_ppo): load reference head under zero3 (#489)
Build #1115: Commit e36fe9d pushed by Dahoas
July 24, 2023 11:27 20m 6s main
July 24, 2023 11:27 20m 6s
Fix logging (#526)
Build #1114: Commit dbdefd8 pushed by maxreciprocate
July 24, 2023 11:13 20m 1s main
July 24, 2023 11:13 20m 1s
Fix logging
Build #1113: Pull request #526 synchronize by maxreciprocate
July 24, 2023 10:51 17m 37s fix-logging
July 24, 2023 10:51 17m 37s
Fix ordering of ppo epoch iteration
Build #1112: Pull request #522 synchronize by maxreciprocate
July 24, 2023 10:02 16m 3s RobertKirk:main
July 24, 2023 10:02 16m 3s
fix(modeling_ppo): load reference head under zero3
Build #1111: Pull request #489 synchronize by maxreciprocate
July 22, 2023 17:47 20m 42s fix-ppo-zero3
July 22, 2023 17:47 20m 42s
8-bit inference (#512)
Build #1110: Pull request #513 synchronize by glerzing
July 22, 2023 15:27 18m 34s glerzing:quantization
July 22, 2023 15:27 18m 34s
8-bit inference (#512)
Build #1109: Pull request #513 synchronize by glerzing
July 22, 2023 14:49 22m 10s glerzing:quantization
July 22, 2023 14:49 22m 10s
Fix ordering of ppo epoch iteration
Build #1108: Pull request #522 synchronize by maxreciprocate
July 22, 2023 14:47 17m 17s RobertKirk:main
July 22, 2023 14:47 17m 17s
Fix ordering of ppo epoch iteration
Build #1107: Pull request #522 synchronize by maxreciprocate
July 22, 2023 14:19 21m 0s RobertKirk:main
July 22, 2023 14:19 21m 0s
Update README.md (#537)
Build #1106: Commit 5d0f04d pushed by maxreciprocate
July 21, 2023 15:37 18m 0s main
July 21, 2023 15:37 18m 0s
Link to autocrit for reward model training in README
Build #1105: Pull request #537 opened by Dahoas
July 21, 2023 10:01 17m 29s autocrit-readme
July 21, 2023 10:01 17m 29s
Fix: rename model_tok to tokenizer is reward_fn arg (#534)
Build #1104: Commit 288d4cb pushed by maxreciprocate
July 20, 2023 11:39 21m 0s main
July 20, 2023 11:39 21m 0s
Fix: rename model_tok to tokenizer is reward_fn arg
Build #1103: Pull request #534 opened by Dahoas
July 20, 2023 09:24 18m 43s fix-reward-tokenizer
July 20, 2023 09:24 18m 43s
Dense reward carper (Fine grained feedback) (#514)
Build #1102: Commit 0c94ee8 pushed by Dahoas
July 19, 2023 09:01 17m 6s main
July 19, 2023 09:01 17m 6s
Fix ordering of ppo epoch iteration
Build #1101: Pull request #522 synchronize by RobertKirk
July 19, 2023 08:43 21m 19s RobertKirk:main
July 19, 2023 08:43 21m 19s
Value branch
Build #1100: Pull request #530 opened by Dahoas
July 18, 2023 13:36 16m 29s value-branch
July 18, 2023 13:36 16m 29s