*.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 model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-0.5b-q16-kv2-ep-16-sep--top2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-4k-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-4096/iter_0009536/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-a3e-dsv3-0.5b-q16-kv2-ep-16-sep-0-top3-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__10_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__10_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__11_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__11_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__12_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__12_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__13_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__13_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__14_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__14_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__15_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__15_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__8_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__8_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__9_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-auxfree-3b-q10-kv2-ep-64-sep-2-top6-cf-0-bias-1e-3-bf16-ep8-mp2-pp1-lr-7.8e-4-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__9_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-dsv3-0.5b-q16-kv2-ep-32-sep-0-top4-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-embdev-loss0.01-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-fp8tw-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gatelora-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gates-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-geglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-gelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-kvso-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2.5e-4-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba-0.5b-q16-kv2-hybrid0.08-bf16-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe010-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-moe110-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-mtp1-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-8-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-muon-zloss-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkl2n-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-qkln-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-rms_norm_real-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-seed20-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqreglu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-sqrelu-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std0.02-zloss-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-std002-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa1024mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa2048mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-ts-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tsad-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dev-tssb-dsv3-0.5b-q16-kv2-ep-16-sep-1-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__10_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__10_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__11_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__11_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__12_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__12_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__13_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__13_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__14_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__14_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__15_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__15_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__8_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__8_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__9_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-16-seqlen-8192/iter_0004768/__9_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/.metadata filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0000001/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/dsv3-0.5b-q16-kv2-ep-16-sep--top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/.metadata filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-0.0-mlc-0.05-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus--seqlen-8192/iter_0000001/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/.metadata filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0003576/__7_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text model/nop-swa512mamba_moe-0.5b-q16-kv2-hybrid0.08-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text