*.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 experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_105/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text merged_hf/experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_105/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/distill_baseline/260803-rg4-multiteacher-mopd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/distill_baseline/260803-rg4-multiteacher-mopd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_105/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/distill_baseline/260803-rg4-multiteacher-mopd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_135/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/quantum_lock/distill_baseline/260803-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-quantum_lock-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_135/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-opdmain-gaxis-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s45-tr8k-va8k-is0520-b64-mb32-dp4/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260803-rcd-knights_knaves-q3-1p7b-base-t8b-s150-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4-sft-kk_answerfirst_tail384_v12-gs20/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_105/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p0p5-m0p5-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p1p0-m1p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_135/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/baseline/260804-rg4-multiteacher-grpo-q3-8b-base-t4b-s105-s150-b64n8-mb32-dp4-seed42/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/knights_knaves/ours/260804-rcd-knights_knaves-q3-8b-base-t4b-s105-fixedlam-p2p0-m2p0-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/self_reference/ours/260806-rcd-self_reference-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text