23.3 GB

Ctrl+K

1 contributor

History: 209 commits

Solshine

add checkpoints/grpo_dense_arm_priordev_cont1000/trainloss.csv (T3-supporting)

d2e0e52 verified 30 days ago

av_armA_cap48
add av_armA_cap48 2 months ago
av_grokking_runB_composed
add av_grokking_runB_composed 2 months ago
av_priordev_grokking_wd3
add av_priordev_grokking_wd3 2 months ago
av_priordev_grokking_wd3_ga8
add av_priordev_grokking_wd3_ga8 2 months ago
eval_named
add checkpoints/eval_named/wcomargin200/inject_config.json (T3-supporting) 30 days ago
grpo_dense_arm_priordev
add checkpoints/grpo_dense_arm_priordev/trainloss.csv (T1-dose-response) about 1 month ago
grpo_dense_arm_priordev_cont1000
add checkpoints/grpo_dense_arm_priordev_cont1000/trainloss.csv (T3-supporting) 30 days ago
grpo_dense_arm_priordev_cont500
add checkpoints/grpo_dense_arm_priordev_cont500/trainloss.csv (T1-dose-response) about 1 month ago
grpo_dense_arm_priordev_s1
add checkpoints/grpo_dense_arm_priordev_s1/trainloss.csv (T1-dose-response) 30 days ago
grpo_dense_arm_priordev_s1_cont500
add checkpoints/grpo_dense_arm_priordev_s1_cont500/trainloss.csv (T1-dose-response) 30 days ago
grpo_hardreward
add checkpoints/grpo_hardreward/trainloss.csv (T2-arms-controls) 30 days ago
grpo_marginft_on_dense500
add checkpoints/grpo_marginft_on_dense500/trainloss.csv (T2-arms-controls) 30 days ago
grpo_probe_arm_priordev
add checkpoints/grpo_probe_arm_priordev/trainloss.csv (T2-arms-controls) 30 days ago
grpo_probe_arm_priordev_t14
add checkpoints/grpo_probe_arm_priordev_t14/trainloss.csv (T2-arms-controls) 30 days ago
grpo_wcomargin_arm_priordev
add checkpoints/grpo_wcomargin_arm_priordev/trainloss.csv (T2-arms-controls) 30 days ago
grpo_wcomargin_smoke
add checkpoints/grpo_wcomargin_smoke/trainloss.csv (T2-arms-controls) 30 days ago