Regression Report: sentiment_tuning_gpt2xl_grad_accu
[['?we=huggingface&wpn=trl&xaxis=_step&ceik=trl_ppo_trainer_config.value.reward_model&cen=trl_ppo_trainer_config.value.exp_name&metrics=env/reward_mean&metrics=objective/kl', 'sentiment_tuning?tag=v0.4.7-55-g110e672&cl=sentiment lvwerra/gpt2-imdb (PR-662)', 'sentiment_tuning_gpt2?tag=v0.4.7-55-g110e672&cl=sentiment gpt2 (PR-662)', 'sentiment_tuning_falcon_rw_1b?tag=v0.4.7-55-g110e672&cl=sentiment tiiuae/falcon-rw-1b (PR-662)', 'sentiment_tuning_gpt2xl_grad_accu?tag=v0.4.7-55-g110e672&cl=sentiment gpt2xl (PR-662)']]
Created on September 22|Last edited on September 22
Comment
sentiment lvwerra/gpt2-imdb (PR-662)
10
sentiment gpt2 (PR-662)
5
sentiment tiiuae/falcon-rw-1b (PR-662)
5
sentiment gpt2xl (PR-662)
5
Add a comment