nnm / .gitattributes
VoCuc's picture
Add files using upload-large-folder tool
c8023bc verified
Raw
History Blame Contribute Delete
72.1 kB
*.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
llama-3.2-3B-it-distillm2/checkpoint-1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-distillm2/checkpoint-623/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-distillm2-1epoch/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-distillm2-1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-sft/checkpoint-1274/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-sft/checkpoint-1911/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-sft/checkpoint-637/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-sft/checkpoint-1149/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-sft/checkpoint-383/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-sft/checkpoint-767/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-distillm2/checkpoint-1869/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-distillm2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-distillm2-1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-distillm2/checkpoint-1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-distillm2/checkpoint-1869/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-distillm2/checkpoint-623/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-distillm2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-nnm-1epoch/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-nnm-1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
eval_results/vllm/llama-3.2-3B-it-nnm-1epoch-checkpoint-2492/outputs__llama-3.2-3B-it-nnm-1epoch__checkpoint-2492/samples_gsm8k_2026-05-13T02-27-13.092459.jsonl filter=lfs diff=lfs merge=lfs -text
eval_results/vllm/llama-3.2-3B-it-nnm-1epoch-checkpoint-2492/outputs__llama-3.2-3B-it-nnm-1epoch__checkpoint-2492/samples_gsm8k_2026-05-13T03-29-54.791747.jsonl filter=lfs diff=lfs merge=lfs -text
eval_results/vllm/llama-3.2-3B-it-sft-checkpoint-1911/outputs__llama-3.2-3B-it-sft__checkpoint-1911/samples_gsm8k_2026-05-13T02-55-07.007041.jsonl filter=lfs diff=lfs merge=lfs -text
eval_results/vllm/llama-3.2-3B-it-sft-checkpoint-1911/outputs__llama-3.2-3B-it-sft__checkpoint-1911/samples_gsm8k_2026-05-13T03-14-58.213602.jsonl filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-nnm-1epoch/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-nnm-1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
eval_results/vllm/qwen2.5-1.5B-it-sft-checkpoint-2492/outputs__qwen2.5-1.5B-it-nnm-1epoch__checkpoint-2492/samples_gsm8k_2026-05-13T07-13-14.665281.jsonl filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-nnm-1epoch_2/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-nnm-1epoch_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-nnm-1epoch_2/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-nnm-1epoch_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-distillm-1epoch/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-distillm-1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-nnm-chosen/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-nnm-chosen/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-nnm-concatenated-001/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama-3.2-3B-it-nnm-concatenated-001/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-nnm-chosen/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-nnm-chosen/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-nnm-concatenated/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-nnm-concatenated/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-nnm-concatenated-001/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-nnm-concatenated-001/tokenizer.json filter=lfs diff=lfs merge=lfs -text
vllm/deepseek-R1-Distill-Llama-8B/deepseek-ai__DeepSeek-R1-Distill-Llama-8B/samples_gsm8k_2026-05-14T00-41-21.367045.jsonl filter=lfs diff=lfs merge=lfs -text
vllm/llama-3.2-3B-it-distillm2-1epoch-checkpoint-2492/.__ckpts__llama-3.2-3B-it-distillm2-1epoch__checkpoint-2492/samples_gsm8k_2026-05-13T23-26-21.879511.jsonl filter=lfs diff=lfs merge=lfs -text
vllm/llama-3.2-3B-it-distillm2-checkpoint-1869/.__ckpts__llama-3.2-3B-it-distillm2__checkpoint-1869/samples_gsm8k_2026-05-13T23-09-54.347231.jsonl filter=lfs diff=lfs merge=lfs -text
vllm/llama-3.2-3B-it-sft-checkpoint-1911/.__ckpts__llama-3.2-3B-it-sft__checkpoint-1911/samples_gsm8k_2026-05-13T22-53-19.309415.jsonl filter=lfs diff=lfs merge=lfs -text
vllm/qwen2.5-1.5B-it-distillm2-1epoch-checkpoint-2492/.__ckpts__qwen2.5-1.5B-it-distillm2-1epoch__checkpoint-2492/samples_gsm8k_2026-05-13T22-36-18.055204.jsonl filter=lfs diff=lfs merge=lfs -text
vllm/qwen2.5-1.5B-it-distillm2-checkpoint-1869/.__ckpts__qwen2.5-1.5B-it-distillm2__checkpoint-1869/samples_gsm8k_2026-05-13T22-20-08.927720.jsonl filter=lfs diff=lfs merge=lfs -text
vllm/qwen2.5-1.5B-it-sft-checkpoint-1149/.__ckpts__qwen2.5-1.5B-it-sft__checkpoint-1149/samples_gsm8k_2026-05-13T22-03-27.869677.jsonl filter=lfs diff=lfs merge=lfs -text
vllm/qwen2.5-14B-Instruct/Qwen__Qwen2.5-14B-Instruct/samples_gsm8k_2026-05-14T00-03-51.166302.jsonl filter=lfs diff=lfs merge=lfs -text
vllm/qwen2.5-Math-1.5B-Instruct/Qwen__Qwen2.5-Math-1.5B-Instruct/samples_gsm8k_2026-05-14T00-23-34.753817.jsonl filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-distillm2-1epoch/checkpoint-4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-sft/checkpoint-3071/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-sft/checkpoint-6142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-it-sft/checkpoint-9213/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-distillm2-1epoch/checkpoint-2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-math-distillm2-1epoch/tokenizer.json 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/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_gsm_plus_2026-05-16T05-48-29.086091.jsonl filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/1246/tokenizer.json 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
qwen2.5-1.5B-Instruct\#amid/ab_pr_0.5_0.5_4_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#amid/ab_pr_0.5_0.5_4_1e-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#csd/ab_pr_0.5_0.5_8_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#csd/ab_pr_0.5_0.5_8_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#csd/ab_pr_0.5_0.5_8_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/1246_full/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch2_lr1e-4_kdr0.75/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch2_lr1e-4_kdr0.75/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch2_lr1e-4_kdr0.75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#csd/ab_pr_0.5_0.5_8_1e-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#amid/ab_pr_0.5_0.5_4_1e-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.9_K128_L4_epoch2_lr1e-4_kdr0.75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
layer_analysis/nuclear_norm.png filter=lfs diff=lfs merge=lfs -text
layer_analysis/nuclear_norm_norm.png filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/3738/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_amid/492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_csd/1476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_csd/1968/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_csd/2460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_csd/492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_csd/984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_srkl/1476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_srkl/1968/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_srkl/2460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_srkl/492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_geneva_srkl/984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_amid/13138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_amid/19707/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_amid/26276/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_amid/32845/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_amid/6569/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_csd/13138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_csd/19707/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_csd/26276/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_csd/32845/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_csd/6569/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_srkl/13138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_srkl/19707/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_srkl/26276/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_srkl/32845/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/distillm_1B_8B_maven_srkl/6569/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_geneva/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/1476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_geneva/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/1968/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_geneva/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/2460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_geneva/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_geneva/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/13138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/19707/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/26276/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/32845/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/6569/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/eval/0/answers.jsonl filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/eval/1/answers.jsonl filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/eval/2/answers.jsonl filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/eval/3/answers.jsonl filter=lfs diff=lfs merge=lfs -text
llama/sft_1B_maven/e5-bs2-lr5e-05-G1-N2-NN1-lora-16-64-0.1/eval/4/answers.jsonl filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_geneva/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/1476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_geneva/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/1968/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_geneva/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/2460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_geneva/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_geneva/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_maven/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/13138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_maven/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/19707/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_maven/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/26276/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_maven/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/32845/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/sft_8B_maven/e5-bs2-lr0.0001-G1-N2-NN1-lora-32-64-0.1/6569/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_geneva_srkl/1476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_geneva_srkl/1968/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_geneva_srkl/2460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_geneva_srkl/492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_geneva_srkl/984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_maven_srkl/13138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_maven_srkl/19707/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_maven_srkl/26276/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_maven_srkl/32845/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama/span_distillm/1B_8B_maven_srkl/6569/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.3_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K256_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K256_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K32_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K32_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K64_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K64_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/bnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/bnmm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lw/nnm0.2_K128_L4_epoch1_lr1e-4_kdr1.0/1246/tokenizer.json 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/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/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/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/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/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/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/nnm0.5_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/nnm0.5_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/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/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/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/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/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/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/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/nnm0.3_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/nnm0.3_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/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-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/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/nnm0.7_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/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/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-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_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/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_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_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/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/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/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/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/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/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/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/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-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/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-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/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/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/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/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/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/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_2026-05-19T15-05-24.735051.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_2026-05-19T15-11-29.808755.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/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_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/nnm0.5_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/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/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_precalc_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_mmlu_pro_math_2026-05-19T16-04-10.333630.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/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/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_2026-05-18T05-03-17.651644.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/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_2026-05-18T05-31-42.614039.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/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_mbpp_2026-05-18T07-30-16.450598.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/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_minerva_math_prealgebra_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_precalc_2026-05-18T07-19-54.471926.jsonl filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr0.9/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr0.9/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora/nnm0.2_K128_L4_epoch2_lr1e-4_kdr1.0/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/erank0.2_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lw/nnm0.2_K128_L4_epoch1_lr1e-4_kdr1.0/tokenizer.json 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_gsm8k_2026-05-20T13-40-33.960642.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/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/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/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/nnm0.1_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/nnm0.1_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/nnm0.1_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
qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd/ab_pr_0.5_0.5_2_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd/ab_pr_0.5_0.5_2_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd/ab_pr_0.5_0.5_2_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.2_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.2_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.5_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.5_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd_csd/gemma2-2b-it\#csd/ab_pr_0.5_0.5_2_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd_csd/gemma2-2b-it\#csd/ab_pr_0.5_0.5_2_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd_csd/gemma2-2b-it\#csd/ab_pr_0.5_0.5_2_1e-4/7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd_csd/gemma2-2b-it\#csd/csd_ab_pr_0.5_0.5_4_1e-4/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd_csd/gemma2-2b-it\#csd/csd_ab_pr_0.5_0.5_4_1e-4/4984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#csd_csd/gemma2-2b-it\#csd/csd_ab_pr_0.5_0.5_4_1e-4/7476/tokenizer.json 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/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_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/nnm0.1_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_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/nnm0.1_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/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/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/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_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/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_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_mmlu_pro_math_2026-05-21T18-15-32.438748.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/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_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_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/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_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_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_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_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_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/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/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_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/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_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_intermediate_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/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/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_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_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/nnm0.5_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_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_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_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_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/nnm0.5_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_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_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/nnm0.7_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_gsm_plus_2026-05-21T20-31-37.465527.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/nnm0.7_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_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_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_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_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_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/nnm0.7_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/nnm0.9_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/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_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/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_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/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/nnm0.9_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/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/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/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_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/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_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/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/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/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/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_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/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/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_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_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/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/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_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_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_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/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/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/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/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_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/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/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/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_mmlu_pro_math_2026-05-21T23-53-19.245282.jsonl filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.2_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.5_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K256_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K32_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm0.2_K64_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.5_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm1.0_K128_L4_epoch1_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.1_K128_L4_epoch1_lr1e-4_kdr0.75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora_mae/nnm0.3_K128_L4_epoch2_lr5e-5_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm_new0.3_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora/nnm0.7_K128_L4_epoch2_lr1e-4_kdr0.75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma2-2b-it\#sfkl_nnm_lora_mae/nnm0.3_K128_L4_epoch2_lr5e-5_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#amid/ab_pr_0.5_0.5_8_1e-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#csd/ab_pr_0.5_0.5_8_1e-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L2_epoch2_lr5e-5_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora_mae/nnm0.3_K128_L4_epoch2_lr5e-5_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L8_epoch2_lr5e-5_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.3_K128_L4_epoch2_lr5e-5_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-1.7B\#sfkl_nnm_lora_mae/nnm0.3_K128_L4_epoch2_lr5e-5_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L2_epoch2_lr5e-5_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L8_epoch2_lr5e-5_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.3_K128_L4_epoch2_lr5e-5_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora_mae/nnm0.1_K128_L4_epoch2_lr5e-5_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_3_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_3_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L8_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_4_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_4_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L2_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_2_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_2_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L2_epoch2_lr1e-4_kdr1.0/2492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L8_epoch2_lr1e-4_kdr1.0/1246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_2_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L2_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_3_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new0.1_K128_L8_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-1.5B-Instruct\#sfkl_nnm_lora/nnm_new_finetune_4_0.1_K128_L4_epoch2_lr1e-4_kdr1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text