Regression Report: train_reward_accelerate
[['?we=openrlbenchmark&wpn=lm-human-preferences&ceik=task_id&cen=task.value.policy.initial_model&metrics=train_reward/minibatch/error', '124M'], ['?we=openrlbenchmark&wpn=lm_human_preference_details&ceik=label_dataset&cen=exp_name&metrics=train/loss', 'train_reward_accelerate?tag=v0.1.0-49-g98820bb&tag=tf_adam&tag=gpt2-large&cl=tf_adam,gpt2-large', 'train_reward_accelerate?tag=v0.1.0-49-g98820bb&tag=pt_adam&tag=gpt2-large&cl=pt_adam,gpt2-large']]
Created on August 10|Last edited on August 10
Comment
openrlbenchmark/lm-human-preferences/124M ({})
40
tf_adam,gpt2-large
4
pt_adam,gpt2-large
10
openrlbenchmark/lm-human-preferences/124M ({})
41
tf_adam,gpt2-large
10
pt_adam,gpt2-large
10
Add a comment