model,checkpoint,tokens_B,phase,hellaswag,arc_easy,arc_challenge,piqa,arithmark3,arithmark_scorer,open_slm_index,val_loss Boris-2 (main run),export_0010B,10.0,stable,37.12,52.15,27.05,67.95,35.9,boris eval.py,22.19,2.8393 Boris-2 (main run),export_0020B,20.0,stable,38.56,52.9,28.58,67.85,37.6,boris eval.py,23.47,2.8092 Boris-2 (main run),export_0030B,30.0,stable,39.42,54.42,29.78,68.39,38.6,boris eval.py,24.82,2.7919 Boris-2 (main run),export_0040B,40.0,stable,39.32,52.86,27.73,67.25,36.7,boris eval.py,23.05,2.7832 Boris-2 (main run),export_0050B,50.0,stable,39.8,55.64,29.86,68.17,38.7,boris eval.py,25.1,2.7829 Boris-2 (main run),export_0060B,60.0,stable,39.9,56.78,28.07,67.9,35.8,boris eval.py,24.18,2.7774 Boris-2 (main run),export_0070B,70.0,stable,40.05,55.01,29.61,67.52,37.3,boris eval.py,24.34,2.7744 Boris-2 (main run),export_0080B,80.0,stable,40.37,55.72,28.24,68.01,35.7,boris eval.py,24.23,2.7755 Boris-2 (main run),export_0090B,90.0,stable,40.54,56.14,28.16,67.52,36.3,boris eval.py,24.22,2.7758 Boris-2 (main run),export_0100B,100.0,stable,40.75,56.19,29.18,69.37,38.0,boris eval.py,25.91,2.7713 Boris-2 (main run),export_0110B,110.0,stable,40.51,56.06,29.52,69.75,38.5,boris eval.py,26.19,2.7756 Boris-2 (main run),export_0120B,120.0,stable,40.65,56.44,30.03,68.28,38.6,boris eval.py,25.62,2.7692 Boris-2 (main run),export_0130B,130.0,stable,40.95,55.18,28.84,67.95,38.6,boris eval.py,25.11,2.7659 Boris-2 (main run),export_0140B,140.0,stable,41.07,54.88,28.75,68.12,36.7,boris eval.py,24.72,2.7662 Boris-2 (main run),export_0150B,150.0,stable,40.92,55.01,30.03,68.39,38.5,boris eval.py,25.5,2.7644 Boris-2 (main run),export_0160B,160.0,stable,41.81,53.54,29.01,68.77,39.5,boris eval.py,25.81,2.7655 Boris-2 (main run),export_0170B,170.0,stable,41.8,55.56,29.86,69.7,39.9,boris eval.py,26.94,2.764 Boris-2 (main run),export_0180B,180.0,decay,46.7,58.46,30.97,71.65,42.0,boris eval.py,31.03,2.6499 Boris-2 (main run),export_0190B,190.0,decay,48.5,58.8,32.08,71.76,43.1,boris eval.py,32.27,2.594 Boris-2-Preview-1,final (50B + 2.5B decay),52.5,preview,45.23,58.38,29.95,69.21,37.6,official,27.91,2.6252 Boris-2-Preview-2,final (100B + 2.5B decay),102.5,preview,46.59,59.13,30.2,70.84,42.2,official,30.57,2.6074 Boris-2-Preview-3 (internal),final (150B + 2.5B decay),152.5,preview,46.76,58.88,30.46,70.51,43.7,official,30.81,2.5917 Boris-2-Preview-3b (internal),"final (150B + 2.5B decay, Preview-2 mix)",152.5,preview,46.91,57.79,32.17,71.06,41.1,official,30.66,2.6021 Boris-2,stable phase end (pre-decay),174.0,stable,44.32,56.78,29.95,69.59,41.7,boris eval.py,28.47,2.7092 Boris-2,main run final (200B),200.0,final,50.36,60.1,32.25,72.91,42.0,official,33.59,2.5383 Boris-2,release (200B + 40M final stages),200.04,release,50.26,59.81,32.0,72.91,45.1,official,34.19,