| *.7z filter=lfs diff=lfs merge=lfs -text |
| *.arrow filter=lfs diff=lfs merge=lfs -text |
| *.bin filter=lfs diff=lfs merge=lfs -text |
| *.bz2 filter=lfs diff=lfs merge=lfs -text |
| *.ckpt filter=lfs diff=lfs merge=lfs -text |
| *.ftz filter=lfs diff=lfs merge=lfs -text |
| *.gz filter=lfs diff=lfs merge=lfs -text |
| *.h5 filter=lfs diff=lfs merge=lfs -text |
| *.joblib filter=lfs diff=lfs merge=lfs -text |
| *.lfs.* filter=lfs diff=lfs merge=lfs -text |
| *.mlmodel filter=lfs diff=lfs merge=lfs -text |
| *.model filter=lfs diff=lfs merge=lfs -text |
| *.msgpack filter=lfs diff=lfs merge=lfs -text |
| *.npy filter=lfs diff=lfs merge=lfs -text |
| *.npz filter=lfs diff=lfs merge=lfs -text |
| *.onnx filter=lfs diff=lfs merge=lfs -text |
| *.ot filter=lfs diff=lfs merge=lfs -text |
| *.parquet filter=lfs diff=lfs merge=lfs -text |
| *.pb filter=lfs diff=lfs merge=lfs -text |
| *.pickle filter=lfs diff=lfs merge=lfs -text |
| *.pkl filter=lfs diff=lfs merge=lfs -text |
| *.pt filter=lfs diff=lfs merge=lfs -text |
| *.pth filter=lfs diff=lfs merge=lfs -text |
| *.rar filter=lfs diff=lfs merge=lfs -text |
| *.safetensors filter=lfs diff=lfs merge=lfs -text |
| saved_model/**/* filter=lfs diff=lfs merge=lfs -text |
| *.tar.* filter=lfs diff=lfs merge=lfs -text |
| *.tar filter=lfs diff=lfs merge=lfs -text |
| *.tflite filter=lfs diff=lfs merge=lfs -text |
| *.tgz filter=lfs diff=lfs merge=lfs -text |
| *.wasm filter=lfs diff=lfs merge=lfs -text |
| *.xz filter=lfs diff=lfs merge=lfs -text |
| *.zip filter=lfs diff=lfs merge=lfs -text |
| *.zst filter=lfs diff=lfs merge=lfs -text |
| *tfevents* filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-nnm/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_intermediate_algebra_2026-05-18T07-19-54.471926.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-nnm/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm8k_2026-05-18T06-39-56.379021.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-nnm/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_prealgebra_2026-05-18T07-19-54.471926.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-amid/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_4_1e-4/samples_gsm8k_2026-05-18T05-41-02.508952.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-20T10-51-44.023073.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-20T03-28-43.199239.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-20T06-05-44.033007.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-20T10-20-23.400947.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-amid/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm8k_2026-05-18T05-51-17.901957.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5b-tsd/Minsang__TSD-KD_Qwen2.5-1.5B/samples_gsm_plus_2026-05-20T08-57-55.093088.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-nnm/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_precalc_2026-05-18T07-19-54.471926.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-nnm/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_algebra_2026-05-18T07-19-54.471926.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-nnm/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_counting_and_prob_2026-05-18T07-19-54.471926.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-19T05-19-57.588279.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-amid/results__qwen2.5-1.5B-Instruct\#csd__ab_pr_0.5_0.5_8_1e-4/samples_gsm_plus_2026-05-18T02-02-06.353674.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-20T11-35-10.623586.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-amid/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_4_1e-4/samples_gsm8k_2026-05-18T05-27-08.479758.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-amid/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_4_1e-4/samples_gsm8k_2026-05-18T05-03-17.651644.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-20T07-07-10.798293.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_sciq_2026-05-20T05-48-32.711640.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/samples_gsm_plus_2026-05-21T18-14-03.701744.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-21T22-58-09.777308.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-20T10-45-09.944715.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-21T22-07-38.678553.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-20T14-33-31.362188.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-amid/results__qwen2.5-1.5B-Instruct\#amid__ab_pr_0.5_0.5_4_1e-4/samples_gsm_plus_2026-05-17T08-22-15.616148.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T03-13-08.441586.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-nnm/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_mbpp_2026-05-18T07-30-16.450598.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5b-tsd/Minsang__TSD-KD_Qwen2.5-1.5B/samples_gsm_plus_2026-05-20T09-44-19.696932.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-20T05-33-07.171742.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-amid/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_4_1e-4/samples_gsm8k_2026-05-18T05-31-42.614039.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0-1246/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0__1246/samples_gsm_plus_2026-05-16T05-48-29.086091.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-19T16-02-01.567296.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-21T17-26-49.376807.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-19T16-00-54.182264.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-20T05-14-37.474356.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lw__nnm0.2_K128_L4_epoch1_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-20T10-06-20.055408.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-21T19-04-38.994347.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm_plus_2026-05-20T05-58-40.592353.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm_plus_2026-05-20T11-11-49.737097.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm_plus_2026-05-20T03-58-28.135424.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-amid/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm_plus_2026-05-18T06-09-50.831279.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mbpp_2026-05-19T04-59-33.294652.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-19T04-46-37.564280.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_counting_and_prob_2026-05-21T20-09-58.294511.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_num_theory_2026-05-21T20-09-58.294511.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_intermediate_algebra_2026-05-21T20-09-58.294511.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm8k_2026-05-21T19-56-04.497992.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_mmlu_pro_math_2026-05-21T20-33-27.843841.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_prealgebra_2026-05-21T20-09-58.294511.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_geometry_2026-05-21T20-09-58.294511.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_precalc_2026-05-21T20-09-58.294511.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_mmlu_pro_math_2026-05-21T21-15-17.902035.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_intermediate_algebra_2026-05-21T20-52-01.134693.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_algebra_2026-05-21T23-19-57.890601.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_precalc_2026-05-21T20-52-01.134693.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-21T23-53-19.245282.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_prealgebra_2026-05-21T23-19-57.890601.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm8k_2026-05-21T20-38-57.497114.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_num_theory_2026-05-21T23-19-57.890601.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_algebra_2026-05-21T20-52-01.134693.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_precalc_2026-05-21T23-19-57.890601.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_counting_and_prob_2026-05-21T23-19-57.890601.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_geometry_2026-05-21T23-19-57.890601.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T04-30-26.192040.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T04-45-38.942117.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-20T10-44-29.653753.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T10-27-27.647641.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-21T22-15-42.779604.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_gsm8k_2026-05-21T21-21-27.176019.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/samples_minerva_math_precalc_2026-05-21T17-47-51.336222.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/samples_minerva_math_prealgebra_2026-05-21T17-47-51.336222.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/samples_minerva_math_intermediate_algebra_2026-05-21T17-47-51.336222.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_intermediate_algebra_2026-05-21T21-35-33.295225.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_geometry_2026-05-21T22-29-17.792749.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-21T22-09-52.686827.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_geometry_2026-05-21T21-35-33.295225.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_precalc_2026-05-21T22-29-17.792749.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_num_theory_2026-05-21T22-29-17.792749.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_prealgebra_2026-05-21T22-29-17.792749.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_algebra_2026-05-21T22-29-17.792749.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_intermediate_algebra_2026-05-21T22-29-17.792749.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-21T23-00-14.570401.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/samples_gsm8k_2026-05-21T17-34-22.668800.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_counting_and_prob_2026-05-21T22-29-17.792749.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/samples_minerva_math_algebra_2026-05-21T17-47-51.336222.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-21T17-28-31.668635.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_intermediate_algebra_2026-05-21T23-19-57.890601.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_num_theory_2026-05-21T16-54-41.262068.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_precalc_2026-05-21T16-54-41.262068.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_geometry_2026-05-21T16-54-41.262068.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_prealgebra_2026-05-21T16-54-41.262068.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_intermediate_algebra_2026-05-21T16-54-41.262068.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_counting_and_prob_2026-05-21T16-54-41.262068.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-21T23-05-45.631858.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_gsm8k_2026-05-21T16-40-30.991516.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr0.9/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T00-00-05.536749.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/samples_gsm8k_2026-05-21T16-34-13.857266.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr0.9_ckpt2492/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T02-39-46.573021.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt2492/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T03-44-09.453955.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_precalc_2026-05-21T18-35-42.244057.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_counting_and_prob_2026-05-21T18-35-42.244057.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_algebra_2026-05-21T16-54-41.262068.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-22T02-24-55.845923.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_geometry_2026-05-21T18-35-42.244057.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_prealgebra_2026-05-21T18-35-42.244057.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-21T19-06-40.893218.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_algebra_2026-05-22T02-46-47.903666.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_intermediate_algebra_2026-05-22T02-46-47.903666.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_intermediate_algebra_2026-05-21T18-35-42.244057.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5b-tsd/Minsang__TSD-KD_Qwen2.5-1.5B/samples_sciq_2026-05-20T07-36-21.609469.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5b-tsd/Minsang__TSD-KD_Qwen2.5-1.5B/samples_gsm8k_2026-05-20T08-39-25.330595.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_counting_and_prob_2026-05-19T15-31-31.443457.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_geometry_2026-05-20T13-59-52.863729.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_precalc_2026-05-19T15-31-31.443457.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5b-tsd/Minsang__TSD-KD_Qwen2.5-1.5B/samples_gsm8k_2026-05-20T09-24-44.698376.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-19T05-03-19.631875.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-19T14-42-25.634092.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-19T16-03-33.329973.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-19T15-47-08.528666.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T04-02-44.931627.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T02-32-56.858752.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T02-02-38.373102.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_num_theory_2026-05-21T18-35-42.244057.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_num_theory_2026-05-21T21-35-33.295225.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_algebra_2026-05-21T18-35-42.244057.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_counting_and_prob_2026-05-21T21-35-33.295225.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_precalc_2026-05-21T21-35-33.295225.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_prealgebra_2026-05-21T21-35-33.295225.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-21T18-21-31.796596.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/samples_minerva_math_algebra_2026-05-21T21-35-33.295225.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/samples_mmlu_pro_math_2026-05-21T18-15-32.438748.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T01-36-44.654190.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T02-08-03.041526.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-amid/results__qwen2.5-1.5B-Instruct\#amid__ab_pr_0.5_0.5_4_1e-4/samples_gsm8k_2026-05-17T08-02-58.299918.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T00-56-12.500640.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-amid/results__qwen2.5-1.5B-Instruct\#csd__ab_pr_0.5_0.5_8_1e-4/samples_gsm8k_2026-05-18T01-45-38.483394.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-21T23-50-13.541723.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt1246/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T03-36-20.052365.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_algebra_2026-05-21T20-09-58.294511.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_precalc_2026-05-21T19-25-36.790826.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-21T19-50-55.324036.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_counting_and_prob_2026-05-21T19-25-36.790826.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_prealgebra_2026-05-21T19-25-36.790826.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_algebra_2026-05-21T19-25-36.790826.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_geometry_2026-05-21T19-25-36.790826.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_counting_and_prob_2026-05-21T20-52-01.134693.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_minerva_math_prealgebra_2026-05-21T20-52-01.134693.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_minerva_math_intermediate_algebra_2026-05-21T19-25-36.790826.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-21T19-11-58.605949.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5b-tsd/Minsang__TSD-KD_Qwen2.5-1.5B/samples_gsm8k_2026-05-20T07-25-44.261824.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm_plus_2026-05-21T21-13-42.194632.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T09-37-48.075763.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5b-tsd/Minsang__TSD-KD_Qwen2.5-1.5B/samples_gsm8k_2026-05-20T07-41-10.416362.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T04-59-22.053427.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T02-23-27.038737.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-20T13-59-52.863729.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-19T15-05-24.735051.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-19T14-47-12.766152.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-19T15-11-29.808755.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_algebra_2026-05-20T13-59-52.863729.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0-1246/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0__1246/samples_gsm8k_2026-05-16T05-36-28.370914.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0-1246/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0__1246/samples_gsm8k_2026-05-16T04-45-16.283740.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0-1246/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0__1246/samples_gsm8k_2026-05-16T04-47-56.106645.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_counting_and_prob_2026-05-20T13-59-52.863729.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T02-31-51.763404.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_mmlu_pro_math_2026-05-19T16-04-10.333630.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr0.9_ckpt2492/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T03-04-17.698928.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_prealgebra_2026-05-19T15-31-31.443457.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_algebra_2026-05-19T15-31-31.443457.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-19T15-31-31.443457.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt2492/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T04-07-43.255234.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_precalc_2026-05-20T13-59-52.863729.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-20T13-36-01.726430.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_prealgebra_2026-05-20T13-59-52.863729.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_minerva_math_geometry_2026-05-19T15-31-31.443457.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T02-00-20.534405.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-20T13-40-33.960642.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr0.9/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T00-24-17.065537.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-20T04-18-10.960852.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-amid/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_4_1e-4/samples_gsm8k_2026-05-18T04-56-45.899724.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7B-it-amid/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_4_1e-4/samples_gsm8k_2026-05-18T05-08-12.243100.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-it-amid/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm8k_2026-05-18T01-31-47.476581.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T01-28-56.513857.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen3-1.7/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-20T05-56-27.888231.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-20T10-42-10.456164.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_sciq_2026-05-20T05-08-48.555954.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T10-00-28.593701.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-21T19-49-01.900213.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T09-50-17.328230.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lw__nnm0.2_K128_L4_epoch1_lr1e-4_kdr1.0/samples_gsm8k_2026-05-20T09-52-33.616213.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T00-32-12.561937.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T01-03-57.333023.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen3-1.7B\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm_plus_2026-05-21T20-31-37.465527.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt1246/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T03-12-11.694567.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt1246/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T04-15-33.550607.jsonl filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/combined.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/curvature.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_prealgebra_2026-05-22T05-38-41.398933.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_counting_and_prob_2026-05-22T05-38-41.398933.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_geometry_2026-05-22T05-38-41.398933.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_precalc_2026-05-22T05-38-41.398933.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-22T05-38-41.398933.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt1246/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T04-46-43.551572.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-22T05-19-40.308065.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt1246/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T05-10-07.792851.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-22T06-10-04.696171.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt1246/google__gemma-2-2b-it/samples_gsm_plus_2026-05-22T04-38-58.065773.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_num_theory_2026-05-22T05-38-41.398933.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-22T06-19-56.004914.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_algebra_2026-05-22T05-38-41.398933.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/Qwen__Qwen3-1.7B/samples_mmlu_pro_math_2026-05-22T06-13-14.564781.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_precalc_2026-05-22T06-38-34.456185.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_algebra_2026-05-22T06-38-34.456185.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_prealgebra_2026-05-22T06-38-34.456185.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-22T06-38-34.456185.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_mmlu_pro_math_2026-05-22T07-12-56.325960.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-22T07-09-47.586605.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_precalc_2026-05-22T07-45-02.614546.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_algebra_2026-05-22T07-45-02.614546.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_prealgebra_2026-05-22T07-45-02.614546.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-22T07-45-02.614546.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-22T07-21-47.855920.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_mmlu_pro_math_2026-05-22T08-21-27.170462.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T08-26-49.301712.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T08-08-58.906358.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-22T08-18-45.670761.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K32_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K32_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T09-35-50.331463.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K64_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K64_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T09-58-57.424759.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T10-44-13.431923.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm8k_2026-05-22T11-29-57.856097.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm8k_2026-05-22T11-52-17.561593.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T10-21-22.333852.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T11-07-01.212170.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K256_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K256_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T09-12-53.542798.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T12-38-47.865586.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T08-50-04.987715.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_mmlu_pro_math_2026-05-22T09-08-06.638177.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-22T12-15-52.533555.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K256_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K256_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T09-29-23.201238.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm_plus_2026-05-22T11-46-15.809720.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T08-43-37.227563.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T10-38-08.139906.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T12-32-41.708864.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T11-00-46.882615.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K64_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K64_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T10-15-15.003698.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.5_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.5_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T12-55-26.439430.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T09-06-37.727185.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch2_lr1e-4_kdr0.75/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm1.0_K128_L4_epoch2_lr1e-4_kdr0.75/samples_gsm_plus_2026-05-22T12-09-38.682624.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K32_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.2_K32_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T09-52-16.508150.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-22T11-23-42.725792.jsonl filter=lfs diff=lfs merge=lfs -text |
| layer_analysis_2/amid/combined.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis_2/amid/curvature.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis_2/amid/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis_2/combined.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis_2/curvature.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis_2/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B-no-thinking/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-23T04-31-16.044540.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_qwen3-1.7B-no-chat-no-thinking/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-23T05-39-30.518532.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_qwen3-1.7B-no-chat-no-thinking/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-23T05-27-57.852900.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/google__gemma-2-2b-it/samples_gsm8k_2026-05-22T17-13-16.214666.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B-resoning/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-23T04-05-58.259676.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B-resoning/Qwen__Qwen3-1.7B/samples_hendrycks_math_intermediate_algebra_2026-05-23T03-52-12.782959.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B-resoning/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-23T03-41-07.623366.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_gemma-2-2b-it-no-chat/google__gemma-2-2b-it/samples_gsm8k_2026-05-23T01-46-57.905502.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/google__gemma-2-2b-it/samples_gsm8k_2026-05-23T01-19-45.346456.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_qwen3-1.7B-no-chat/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-23T05-23-39.003841.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_gemma-2-2b-it-nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0_run_eval_no_chat/google__gemma-2-2b-it/samples_gsm_plus_2026-05-23T02-42-52.509789.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_qwen3-1.7B-no-chat-no-thinking/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-23T05-53-05.998234.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_gemma-2-2b-it-no-chat/google__gemma-2-2b-it/samples_gsm_plus_2026-05-23T02-10-04.038174.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B-resoning/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-23T04-27-33.168887.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B-no-thinking/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-23T04-54-42.038783.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/google__gemma-2-2b-it/samples_gsm_plus_2026-05-23T01-43-09.512703.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_qwen3-1.7B-no-chat/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-23T05-09-07.875413.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_gemma-2-2b-it-nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0_run_eval_no_chat/google__gemma-2-2b-it/samples_gsm8k_2026-05-23T02-16-45.610007.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_hendrycks_math_prealgebra_2026-05-23T02-59-33.894819.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_minerva_math_prealgebra_2026-05-23T03-12-56.648901.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_hendrycks_math_precalc_2026-05-23T02-59-33.894819.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_minerva_math_geometry_2026-05-23T03-12-56.648901.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_minerva_math_num_theory_2026-05-23T03-12-56.648901.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_hendrycks_math_algebra_2026-05-23T02-59-33.894819.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_minerva_math_precalc_2026-05-23T03-12-56.648901.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_mbpp_2026-05-23T03-20-30.478807.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_minerva_math_algebra_2026-05-23T03-12-56.648901.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-23T02-48-34.033555.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_minerva_math_intermediate_algebra_2026-05-23T03-12-56.648901.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_minerva_math_counting_and_prob_2026-05-23T03-12-56.648901.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_hendrycks_math_counting_and_prob_2026-05-23T02-59-33.894819.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_hendrycks_math_intermediate_algebra_2026-05-23T02-59-33.894819.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_qwen3-1.7B-no-chat/Qwen__Qwen3-1.7B/samples_mbpp_2026-05-23T05-16-10.557122.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/no_chat_qwen3-1.7B-no-chat/Qwen__Qwen3-1.7B/samples_gsm8k_2026-05-23T04-58-17.749459.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_hendrycks_math_geometry_2026-05-23T02-59-33.894819.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B/Qwen__Qwen3-1.7B/samples_gsm_plus_2026-05-23T03-36-38.337821.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/results/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#csd__ab_pr_0.5_0.5_8_1e-4/samples_gsm8k_2026-05-24T08-29-39.044925.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it\#amid/ab_pr_0.5_0.5_2_1e-4/google__gemma-2-2b-it/samples_gsm8k_2026-05-24T09-51-14.971820.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it\#csd/ab_pr_0.5_0.5_2_1e-4/google__gemma-2-2b-it/samples_gsm8k_2026-05-24T10-16-46.036696.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/mae_nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt2492/google__gemma-2-2b-it/samples_gsm8k_2026-05-24T07-11-58.185782.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/mae_nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt2492/google__gemma-2-2b-it/samples_gsm8k_2026-05-24T06-38-57.620842.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/mae_nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt2492/google__gemma-2-2b-it/samples_gsm_plus_2026-05-24T07-06-26.439723.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it\#amid/ab_pr_0.5_0.5_2_1e-4/google__gemma-2-2b-it/samples_gsm_plus_2026-05-24T10-14-32.817195.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_8_1e-4/samples_gsm_plus_2026-05-24T09-28-17.502905.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#csd__ab_pr_0.5_0.5_8_1e-4/samples_gsm_plus_2026-05-24T09-00-26.475013.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_8_1e-4/samples_hendrycks_math_intermediate_algebra_2026-05-24T09-07-27.833314.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_8_1e-4/samples_minerva_math_intermediate_algebra_2026-05-24T09-15-46.549323.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#csd__ab_pr_0.5_0.5_8_1e-4/samples_hendrycks_math_intermediate_algebra_2026-05-24T08-39-50.852962.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#amid__ab_pr_0.5_0.5_8_1e-4/samples_gsm8k_2026-05-24T09-02-12.316611.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#csd__ab_pr_0.5_0.5_8_1e-4/samples_gsm8k_2026-05-24T08-34-29.786403.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/results__qwen3-1.7B\#csd__ab_pr_0.5_0.5_8_1e-4/samples_minerva_math_intermediate_algebra_2026-05-24T08-48-16.651676.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it/mae_nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0_ckpt2492/google__gemma-2-2b-it/samples_gsm_plus_2026-05-24T07-39-39.328440.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae__nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/samples_gsm8k_2026-05-24T10-28-53.047939.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae__nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/samples_gsm_plus_2026-05-24T10-47-33.254529.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/gemma-2-2b-it\#csd/ab_pr_0.5_0.5_2_1e-4/google__gemma-2-2b-it/samples_gsm_plus_2026-05-24T10-40-19.084319.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#TSD/Minsang__TSD-KD_Qwen2.5-1.5B/samples_gsm8k_2026-05-25T01-05-33.934008.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-25T02-03-12.501789.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_4_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new_finetune_4_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-25T02-19-15.599747.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_3_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new_finetune_3_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-25T01-55-18.134173.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L8_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.1_K128_L8_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-25T02-25-41.590149.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L2_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.1_K128_L2_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-25T01-42-39.505161.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_2_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new_finetune_2_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm8k_2026-05-25T01-31-04.188054.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_2_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new_finetune_2_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-25T01-49-16.125446.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L2_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.1_K128_L2_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-25T01-57-38.497090.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-25T02-20-21.520481.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_4_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new_finetune_4_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-25T02-36-54.290952.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#TSD/Minsang__TSD-KD_Qwen2.5-1.5B/samples_gsm_plus_2026-05-25T01-30-43.261637.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_3_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new_finetune_3_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-25T02-13-06.960621.jsonl filter=lfs diff=lfs merge=lfs -text |
| eval_results_2/vllm/qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L8_epoch2_lr1e-4_kdr1.0/results__qwen2.5-1.5B-Instruct\#sfkl_nnm_lora__nnm_new0.1_K128_L8_epoch2_lr1e-4_kdr1.0/samples_gsm_plus_2026-05-25T02-42-41.192669.jsonl filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method/combined_1x5.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method/curvature.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method/effective_rank.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method/nuclear_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/amid/combined.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/amid/curvature.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/amid/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_math500/combined_1x5.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_math500/curvature.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_math500/effective_rank.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_math500/nuclear_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_math500/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd/combined_1x5.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd/curvature.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd/effective_rank.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd/matrix_entropy.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd/nuclear_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd_2/combined_1x5.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd_2/curvature.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd_2/effective_rank.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd_2/matrix_entropy.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd_2/nuclear_norm.png filter=lfs diff=lfs merge=lfs -text |
| layer_analysis/6_method_tsd_2/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text |
|
|