add verl_ckpt/v29_C_taxv3_plus_cf_sft_4b_s42_balance_noloc_sdar_off_resume120_b200_v28/global_step_560 (B200 continuation to its end, best saved step) 8c4ec9c verified cpyang commited on 4 days ago
add rl_balance_noloc_sdar_off_step560 (B200 continuation to its end, best saved step) 49d92f2 verified cpyang commited on 4 days ago
add verl_ckpt/v29_C_sft1e5_4b_s42_balance_noloc_resume60_b200_v28/global_step_220 (B200 continuation to its end, best saved step) b23135d verified cpyang commited on 4 days ago
add rl_sft1e5_balance_noloc_step220 (B200 continuation to its end, best saved step) a18260a verified cpyang commited on 4 days ago
add verl_ckpt/v29_C_taxv3_plus_cf_taxv3om_4b_s42_balance_noloc_resume270_b200_v28/global_step_1800 (B200 continuation to its end, best saved step) 12da06e verified cpyang commited on 4 days ago
add rl_balance_noloc_taxv3om_step1800 (B200 continuation to its end, best saved step) 3227c84 verified cpyang commited on 4 days ago
add verl_ckpt/v29_C_taxv3_plus_cf_taxv3om_4b_s42_balance_noloc_resume270_b200_v28/global_step_480 56fdce1 verified cpyang commited on 11 days ago
add rl_balance_noloc_taxv3om_step480 (B200 continuation, best of resume) dbb869f verified cpyang commited on 11 days ago
add verl_ckpt/v29_C_sft1e5_4b_s42_balance_noloc_resume60_b200_v28/global_step_180 520ca8b verified cpyang commited on 11 days ago
add rl_sft1e5_balance_noloc_step180 (B200 continuation, best of resume) 44c1996 verified cpyang commited on 11 days ago
add verl_ckpt/v29_C_taxv3_plus_cf_sft_4b_s42_balance_noloc_sdar_off_resume120_b200_v28/global_step_280 bfee23a verified cpyang commited on 11 days ago
add rl_balance_noloc_sdar_off_step280 (B200 continuation, best of resume) 5a60a35 verified cpyang commited on 11 days ago
add verl_ckpt/v29_C_taxv3_plus_cf_floc_sft_4b_s42_balance_floc_resume160_b200_v28/global_step_380 1f8540d verified cpyang commited on 11 days ago
add rl_balance_floc_step380 (B200 continuation, best of resume) b3e403a verified cpyang commited on 11 days ago
add verl_ckpt/v29_C_sft1e5_4b_s42_balance_noloc_resume60_b200_v28/global_step_120 6a68f84 verified cpyang commited on 12 days ago
add rl_sft1e5_balance_noloc_step120 (B200 continuation, best of resume) 112f9fb verified cpyang commited on 12 days ago
add verl_ckpt/v29_C_taxv3_plus_cf_floc_sft_4b_s42_balance_floc_resume160_b200_v28/global_step_240 aef6f74 verified cpyang commited on 12 days ago
add rl_balance_floc_step240 (B200 continuation, best of resume) 0aad144 verified cpyang commited on 12 days ago
add verl_ckpt/v29_C_taxv3_plus_cf_sft_4b_s42_balance_noloc_fullhist_resume140_b200_v28/global_step_260 b689ee4 verified cpyang commited on 12 days ago
add rl_balance_noloc_fullhist_step260 (B200 continuation, best of resume) 3a32dda verified cpyang commited on 12 days ago
Add raw verl checkpoint v29_C_taxv3_plus_cf_sft_4b_s42_balance_noloc_sdar_off_v28 global_step_120 (FSDP shards + optimizer, resumable) 57ff31c verified cpyang commited on 13 days ago
Add raw verl checkpoint v29_C_sft1e5_4b_s42_balance_noloc_v28 global_step_60 (FSDP shards + optimizer, resumable) 18915aa verified cpyang commited on 13 days ago
verl RL checkpoint global_step_270 (M_taxv3om balance-noloc): actor FSDP shards + optimizer + dataloader state 7ec530d verified cpyang commited on 13 days ago
Add raw verl checkpoint v29_C_taxv3_plus_cf_floc_sft_4b_s42_balance_floc_v28 global_step_160 (FSDP shards + optimizer, resumable) 0e01451 verified cpyang commited on 13 days ago
Add raw verl checkpoint v29_C_taxv3_plus_cf_sft_4b_s42_balance_noloc_fullhist_v28 global_step_140 (FSDP shards + optimizer, resumable) fe4eae5 verified cpyang commited on 13 days ago
Add rl_balance_noloc_sdar_off_step120: best RL checkpoint by val-key-askthreshold j/macro_f1 (Duke RTX Pro 6000 run) 3208d92 verified cpyang commited on 13 days ago
Add rl_sft1e5_balance_noloc_step60: best RL checkpoint by val-key-askthreshold j/macro_f1 (Duke RTX Pro 6000 run) 719d64c verified cpyang commited on 13 days ago
Add rl_balance_floc_step160: best RL checkpoint by val-key-askthreshold j/macro_f1 (Duke RTX Pro 6000 run) 9b83c9d verified cpyang commited on 13 days ago
Add rl_balance_noloc_fullhist_step140: best RL checkpoint by val-key-askthreshold j/macro_f1 (Duke RTX Pro 6000 run) 3092e43 verified cpyang commited on 13 days ago