*.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 pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step60000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step65000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step70000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step60000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k16/step72615/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step72615/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step70000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k1/step65000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step65000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step60000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step72615/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-190M-10xC-k4/step70000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step113942/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step105000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113942/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k1/step100000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step110000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step105000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text pretrain/olmo2-600M-10xC-k4/step113000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text