Skip to main content
sorry
Projects
trlx-references
Reports
dense-reward-carper v. main

dense-reward-carper v. main

dense-reward-carper @6bc1c54/fix(ppo_randomwalks): `reward_fn` signature to accommodate tokenizer/2023-07-17 main @5c5abca/feat(readme): add instructions to avoid OOMs with hyperparameters (#470)/2023-07-13
Sorry
Created on July 17|Last edited on July 17

ppo_hh/pythia-6B-static-sft/7gpus


02004006008001k1.2k1.4kStep-1.6-1.5-1.4-1.3-1.2-1.1-1
Run set
2



Run set
2


ppo_sentiments/gpt2-imdb/1gpu


Run set
2



Run set
2


ppo_randomwalks/randomwalks/1gpu


Run set
2



Run set
2


ilql_randomwalks/GPT2Config/1gpu


Run set
2



Run set
2


ppo_sentiments_t5/t5-imdb/1gpu


Run set
2



Run set
2


sft_sentiments/gpt2/1gpu


Run set
2



Run set
2


ilql_sentiments/gpt2/1gpu


Run set
2



Run set
2


Created with ❤️ on Weights & Biases.

https://wandb.ai/sorry/trlx-references/reports/dense-reward-carper-v-main--Vmlldzo0OTAxNzUx
Made with Weights & Biases. Sign up or log in to create reports like this one.