1{"step": 0, "loss": 4.941596031188965, "lr": 3.3333333333333333e-06, "grad_norm": 11.574689865112305, "tokens": 6745, "tok_per_s": 3448.674497642418, "t": 2.57}2{"step": 100, "loss": 1.024980902671814, "lr": 0.0003366666666666667, "grad_norm": 6.284777641296387, "tokens": 743327, "tok_per_s": 24635.56415165761, "t": 30.78}3{"step": 200, "loss": 0.3161088228225708, "lr": 0.00067, "grad_norm": 1.373868703842163, "tokens": 1487594, "tok_per_s": 30610.546350138597, "t": 49.21}4{"step": 300, "loss": 0.30001285672187805, "lr": 0.001, "grad_norm": 0.9516773223876953, "tokens": 2224234, "tok_per_s": 32789.997595509114, "t": 68.44}5{"step": 400, "loss": 0.3070284128189087, "lr": 0.0009998972383511385, "grad_norm": 0.535650372505188, "tokens": 2958062, "tok_per_s": 34020.53726643474, "t": 87.56}6{"step": 500, "loss": 0.26402828097343445, "lr": 0.0009995890003376942, "grad_norm": 0.28448614478111267, "tokens": 3686492, "tok_per_s": 34827.95914207498, "t": 106.46}7{"step": 600, "loss": 0.26615840196609497, "lr": 0.0009990754267376514, "grad_norm": 0.1614493727684021, "tokens": 4423182, "tok_per_s": 35174.945536219624, "t": 126.36}8{"step": 700, "loss": 0.26372361183166504, "lr": 0.0009983567521095432, "grad_norm": 0.1251145452260971, "tokens": 5161053, "tok_per_s": 35589.20662235398, "t": 145.63}9{"step": 800, "loss": 0.2783412039279938, "lr": 0.000997433304685324, "grad_norm": 0.15038050711154938, "tokens": 5899309, "tok_per_s": 35916.9021250508, "t": 164.86}10{"step": 900, "loss": 0.26982399821281433, "lr": 0.0009963055062204608, "grad_norm": 0.18118366599082947, "tokens": 6639495, "tok_per_s": 36137.222541925905, "t": 184.34}11{"step": 999, "val_loss_b0": 0.2594514171899984, "t": 203.77}12{"step": 1000, "loss": 0.23169617354869843, "lr": 0.000994973871801308, "grad_norm": 0.11366917192935944, "tokens": 7378163, "tok_per_s": 36281.5789031001, "t": 203.97}13{"step": 1100, "loss": 0.2553258240222931, "lr": 0.0009934390096098592, "grad_norm": 0.3918009102344513, "tokens": 8114548, "tok_per_s": 36353.84211880216, "t": 223.82}14{"step": 1200, "loss": 0.2367946058511734, "lr": 0.0009917016206459795, "grad_norm": 0.13034524023532867, "tokens": 8855020, "tok_per_s": 36497.31428960828, "t": 243.23}15{"step": 1300, "loss": 0.23620161414146423, "lr": 0.0009897624984072447, "grad_norm": 0.10524164885282516, "tokens": 9601501, "tok_per_s": 36627.59412114859, "t": 262.75}16{"step": 1400, "loss": 0.2609722912311554, "lr": 0.000987622528526538, "grad_norm": 0.1504184454679489, "tokens": 10343983, "tok_per_s": 36734.75257922134, "t": 282.2}17{"step": 1500, "loss": 0.24786852300167084, "lr": 0.0009852826883675633, "grad_norm": 0.09120374917984009, "tokens": 11090019, "tok_per_s": 36781.989637705716, "t": 302.12}18{"step": 1600, "loss": 0.27017742395401, "lr": 0.0009827440465784664, "grad_norm": 0.1314472109079361, "tokens": 11842461, "tok_per_s": 36910.85801666111, "t": 321.45}19{"step": 1700, "loss": 0.24035435914993286, "lr": 0.0009800077626037633, "grad_norm": 0.11899533122777939, "tokens": 12581243, "tok_per_s": 36989.74402483245, "t": 340.74}20{"step": 1800, "loss": 0.23397061228752136, "lr": 0.000977075086154801, "grad_norm": 0.08897548168897629, "tokens": 13321567, "tok_per_s": 37016.40677754357, "t": 360.49}21{"step": 1900, "loss": 0.2829379141330719, "lr": 0.00097394735663899, "grad_norm": 0.10278685390949249, "tokens": 14065036, "tok_per_s": 37033.02886921329, "t": 380.41}22{"step": 1999, "val_loss_b0": 0.2532890506143083, "t": 399.96}23{"step": 2000, "loss": 0.25057756900787354, "lr": 0.000970626002548074, "grad_norm": 0.12103113532066345, "tokens": 14797545, "tok_per_s": 37036.8869671652, "t": 400.15}24{"step": 2100, "loss": 0.23892416059970856, "lr": 0.0009671125408057098, "grad_norm": 0.08961229771375656, "tokens": 15540833, "tok_per_s": 36457.20327366902, "t": 426.89}25{"step": 2200, "loss": 0.24898186326026917, "lr": 0.0009634085760746613, "grad_norm": 0.14835017919540405, "tokens": 16275558, "tok_per_s": 35731.45537336063, "t": 456.11}26