dev_additional_special_tokens v. main

dev_additional_special_tokens @d2c4b3b/fix(accelerate_ppo_trainer): resize token embeddings without hydra/2023-06-26 main @475a284/Release: v0.7.0 (#511)/2023-06-23

Sorry

Created on June 26|Last edited on June 26

Comment

﻿
ppo_randomwalks/randomwalks/1gpu﻿
metrics/optimality
metrics/optimality
Showing first 2 runs
050100150Step0.20.40.60.8
metrics/lengths
metrics/lengths
Showing first 2 runs
050100150Step10203040506070
reward/mean
reward/mean
Showing first 2 runs
050100150Step0.20.40.60.8
Run set4
﻿
﻿
﻿
Run set4
﻿
ppo_sentiments/gpt2-imdb/1gpu﻿
Run set4
﻿
﻿
﻿
Run set4
﻿
ilql_sentiments/gpt2/1gpu﻿
Run set4
﻿
﻿
﻿
Run set4
﻿
ppo_sentiments_t5/t5-imdb/1gpu﻿
Run set4
﻿
﻿
﻿
Run set4
﻿
ppo_hh/pythia-6B-static-sft/7gpus﻿
Run set4
﻿
﻿
﻿
Run set4
﻿
sft_sentiments/gpt2/1gpu﻿
Run set4
﻿
﻿
﻿
Run set4
﻿
ilql_randomwalks/GPT2Config/1gpu﻿
Run set4
﻿
﻿
﻿
Run set4
﻿
﻿

Add a comment