*.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 miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1520/iter_0001520/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3500/iter_0003500/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0001780/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_1780-3900/iter_0003900/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3900/iter_0003900/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3940/iter_0003940/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_3980/iter_0003980/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4000/iter_0004000/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4140/iter_0004140/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4160/iter_0004160/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4280/iter_0004280/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4420/iter_0004420/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4560/iter_0004560/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_4580/iter_0004580/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/.metadata filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/__1_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/__2_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/__3_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/__4_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/__5_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/__6_0.distcp filter=lfs diff=lfs merge=lfs -text miles_sglang_grpo_adamw_bs2048_sgl64_cvd_mrouter_ctx16fix/raw_checkpoints/miles_multi_turn_lr1e-5_bs2048_kl0.001_res2560_adamw_grpo_miles_sglang_grpo_adamw_sgl64_cvd_mrouter_ctx16fix_steps_5000/iter_0005000/optimizer/__7_0.distcp filter=lfs diff=lfs merge=lfs -text