Affine-top4_v1-5F2JV4RvwPyAPe9axBri86v18DY35gdKpVQQg7K1bNCCDbDY
qwen3_4B_high_step_220
64_v2_scalable
Affine-20-5FWcW3wkNg9E2GYPhZYsAEMLU83NfDXSGShLwZ2dRLJKz2kB
Affine-122-5EfE9uvUkrRE1mf38pixonrfAugyb7B9UAvriBzmThBL3Vwv
ds1p5b_code_sandbox-global_step_400
affine-ana9-17-5H4QxkyKjxKAYW3QvJ7nmMZNEosPfJiJ6UoJ611wt9QoFH2Y
ds-adam-1e-6-global_step_20
ds-adam-1e-6-global_step_140
ds-adam-1e-6-global_step_180
qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_160
affine-sxm-5Fk9K4EVdoAF2vHHWGE3QQpP5GG5YAz7kKHQVx7wNPszU4ah
Qwen3-1.7B-Wordle-RL
qwen3-4b_grpo_skywork_math-global_step_100
CORE-Qwen3-1.7B-MATH-A9-U-S-SG
rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_2_of_10
rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_7_of_10
sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_5_of_5
qwen3_1.7b_sudoku_one_action_easy_21_30_epoch2
qwen3_1.7b_sudoku_one_action_easy_21_30_epoch3
affine-5CVXMUxtv8GzVA6ZVc8F5UR9v8FWDxbYoAZ9Wwn9CR3h6XvC
a4a16420
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_1_of_5
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_3_of_5
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_4_of_5
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_5_of_5
sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_5_of_5
sft_qwen15_code200_lr_5e-6_constant_bsz_128_ckpt_3_of_5
sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_1_of_5
sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_4_of_5
sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_5_of_5
qwen2.5-3b-icd10-top50-multi-task
Qwen3-0.6B-Tiny-Hanabi-XML-SFT
Qwen3-1.7B-Tiny-Hanabi-XML-SFT
SFT-Warmup-1.7B-BCB
qwen1.7b-adam-reset-muon-lr-1e-6-fp64-global_step_200
Affine-ceo1870-5HTSoghu3gnMWgDdWyskXw26a4KnU7k3EUWsi7sJavY2wg4T
affine-finaltest-1
affine-crash-5CVLTzAwVNuFE6dsio9GDaZbVSGR67uHsk3BUEWCWPX7HLXH
Qwen3-1.7B-CCC-merged-cp3-LR1e-4
Rio-3.0-Nano
sub38-221