fix-kl-controller v. main

fix-kl-controller @ee8cd4a/fix(ppo_trainer): update `AdaptiveKLController` with correct KL/2023-03-08 main @adbf8fc/Add intermediate checkpointing to `accelerate` trainers (#349)/2023-03-08

Sorry

Created on March 10|Last edited on March 10

Comment

﻿
ilql_randomwalks/GPT2Config/1gpu﻿
metrics/optimality@beta=1
metrics/optimality@beta=1
050100150Step00.10.20.30.4
metrics/lengths@beta=1
metrics/lengths@beta=1
050100150Step5060708090100
metrics/optimality@beta=100
metrics/optimality@beta=100
050100150Step00.20.40.60.8
Run set2
﻿
﻿
﻿
Run set2
﻿
ppo_sentiments_t5/t5-imdb/1gpu﻿
Run set0
﻿
﻿
﻿
Run set0
﻿
ppo_randomwalks/randomwalks/1gpu﻿
Run set2
﻿
﻿
﻿
Run set2
﻿
﻿

Add a comment