Model synced from source: Hyeongwon/P2-split2_prob_Qwen3-8B-Base_0325-04-bs128-lr1e-5-epoch6
Updated 2026-05-13 06:11:39 +08:00
Model synced from source: Hyeongwon/P2-split2_prob_Qwen3-8B-Base_0325-01
Updated 2026-05-13 05:45:26 +08:00
Model synced from source: Hyeongwon/P19-split2-prob-6x-bs128-lr2e5-zero3-ep3
Updated 2026-05-13 04:30:42 +08:00
Model synced from source: Hyeongwon/P19-split4-prob-6x-bs128-lr2e5-zero3-ep3
Updated 2026-05-13 04:30:42 +08:00
Model synced from source: Hyeongwon/P12-frac0p05-fullft-lr5e5-ep6
Updated 2026-05-13 02:31:40 +08:00
Model synced from source: Hyeongwon/P2-split4_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5
Updated 2026-05-12 10:04:19 +08:00
Model synced from source: Hyeongwon/P9-split2_only_answer_Qwen3-4B-Base_0402-01-5e-6
Updated 2026-05-11 23:42:23 +08:00
Model synced from source: Hyeongwon/P9-split5_prob_Qwen3-4B-Base_0322-01
Updated 2026-05-10 02:33:08 +08:00
Model synced from source: Hyeongwon/P2-split2_bs512_epoch10_2e-5_prob_Qwen3-4B-Base_0320-01
Updated 2026-05-07 19:06:29 +08:00
Model synced from source: Hyeongwon/P9-split2_prob_Qwen3-4B-Base_0322-01
Updated 2026-05-07 00:59:49 +08:00
Model synced from source: Hyeongwon/P2-split2_prob_rg_v2_Qwen3-4B-Base-0415
Updated 2026-05-05 06:48:56 +08:00
Model synced from source: Hyeongwon/P2-split2_prob_Qwen3-8B-Base_0325-03-bs128
Updated 2026-05-04 07:55:21 +08:00
Model synced from source: Hyeongwon/P2-split2_prob_rg_v2_Qwen3-4B-Base
Updated 2026-05-03 17:35:44 +08:00
Model synced from source: Hyeongwon/P2-split2_reasoning_only_Qwen3-4B-Base_0424-bs64-epoch3
Updated 2026-05-02 22:50:04 +08:00
Model synced from source: Hyeongwon/P2-split2_complete_independent_Qwen3-4B-Base_0425-bs64-epoch3
Updated 2026-05-01 13:13:16 +08:00