ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_strong Updated Jul 18, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-sft-cot-lr3e-5_sched-linear_ep3_bs8_gs4_multi 2B • Updated Jul 12, 2025
ou474747/DSR1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_baselineB_multi Updated Jul 12, 2025
ou474747/DSR1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_baselineB_single Updated Jul 11, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-sft-cot-lr3e-5_sched-linear_ep3_bs8_gs4_single 2B • Updated Jul 11, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_codedowB Updated Jun 15, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr5.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_high_lrB Updated Jun 15, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-linear_ep3_bs8_gs4_linear_schedB Updated Jun 15, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_code_upB Updated Jun 15, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_baselineB Updated Jun 15, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr1.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_low_lrB Updated Jun 15, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_strong Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr5.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_high_lr Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-linear_ep3_bs8_gs4_linear_sched Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_code_up Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_code_down Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr2.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_baseline Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-rl-sft-cot-lr1.0e-6_sched-cosine_with_min_lr_ep3_bs8_gs4_low_lr Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-sft-cot-lr3e-5_sched-linear_ep3_bs8_gs4 2B • Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-sft-cot-lr3e-5_sched-cosine_ep3_bs8_gs4 2B • Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-sft-cot-lr2e-5_sched-linear_ep3_bs8_gs4 2B • Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-sft-cot-lr2e-5_sched-cosine_ep3_bs8_gs4 2B • Updated Jun 9, 2025
ou474747/DeepSeek-R1-Distill-Qwen-1.5B-sft-cot-lr1e-5_sched-linear_ep3_bs8_gs4 2B • Updated Jun 9, 2025