[ { "loss": 8.7351650390625, "learning_rate": 4.875491807360925e-05, "epoch": 0.02490163852781513, "total_flos": 2173275475968000, "step": 500 }, { "loss": 8.1599990234375, "learning_rate": 4.750983614721849e-05, "epoch": 0.04980327705563026, "total_flos": 4346550951936000, "step": 1000 }, { "loss": 7.94335546875, "learning_rate": 4.6264754220827736e-05, "epoch": 0.07470491558344539, "total_flos": 6519826427904000, "step": 1500 }, { "loss": 7.817630859375, "learning_rate": 4.5019672294436976e-05, "epoch": 0.09960655411126051, "total_flos": 8693101903872000, "step": 2000 }, { "loss": 7.721162109375, "learning_rate": 4.377459036804622e-05, "epoch": 0.12450819263907566, "total_flos": 10866377379840000, "step": 2500 }, { "loss": 7.63598046875, "learning_rate": 4.252950844165546e-05, "epoch": 0.14940983116689077, "total_flos": 13039652855808000, "step": 3000 }, { "loss": 7.557828125, "learning_rate": 4.128442651526471e-05, "epoch": 0.1743114696947059, "total_flos": 15212928331776000, "step": 3500 }, { "loss": 7.47056640625, "learning_rate": 4.003934458887395e-05, "epoch": 0.19921310822252103, "total_flos": 17386203807744000, "step": 4000 }, { "loss": 7.40528125, "learning_rate": 3.8794262662483196e-05, "epoch": 0.22411474675033619, "total_flos": 19559479283712000, "step": 4500 }, { "loss": 7.32109375, "learning_rate": 3.7549180736092436e-05, "epoch": 0.24901638527815131, "total_flos": 21732754759680000, "step": 5000 }, { "loss": 7.1830703125, "learning_rate": 3.630409880970168e-05, "epoch": 0.2739180238059664, "total_flos": 23906030235648000, "step": 5500 }, { "loss": 7.075640625, "learning_rate": 3.505901688331092e-05, "epoch": 0.29881966233378154, "total_flos": 26079305711616000, "step": 6000 }, { "loss": 6.9607734375, "learning_rate": 3.381393495692017e-05, "epoch": 0.3237213008615967, "total_flos": 28252581187584000, "step": 6500 }, { "loss": 6.8397734375, "learning_rate": 3.256885303052941e-05, "epoch": 0.3486229393894118, "total_flos": 30425856663552000, "step": 7000 }, { "loss": 6.7368984375, "learning_rate": 3.1323771104138656e-05, "epoch": 0.37352457791722693, "total_flos": 32599132139520000, "step": 7500 }, { "loss": 6.6454296875, "learning_rate": 3.00786891777479e-05, "epoch": 0.39842621644504206, "total_flos": 34772407615488000, "step": 8000 }, { "loss": 6.573265625, "learning_rate": 2.8833607251357143e-05, "epoch": 0.4233278549728572, "total_flos": 36945683091456000, "step": 8500 }, { "loss": 6.4836328125, "learning_rate": 2.7588525324966386e-05, "epoch": 0.44822949350067237, "total_flos": 39118958567424000, "step": 9000 }, { "loss": 6.418890625, "learning_rate": 2.634344339857563e-05, "epoch": 0.4731311320284875, "total_flos": 41292234043392000, "step": 9500 }, { "loss": 6.3506875, "learning_rate": 2.5098361472184873e-05, "epoch": 0.49803277055630263, "total_flos": 43465509519360000, "step": 10000 }, { "loss": 6.298296875, "learning_rate": 2.3853279545794113e-05, "epoch": 0.5229344090841177, "total_flos": 45638784995328000, "step": 10500 }, { "loss": 6.242953125, "learning_rate": 2.2608197619403356e-05, "epoch": 0.5478360476119328, "total_flos": 47812060471296000, "step": 11000 }, { "loss": 6.193828125, "learning_rate": 2.13631156930126e-05, "epoch": 0.572737686139748, "total_flos": 49985335947264000, "step": 11500 }, { "loss": 6.149265625, "learning_rate": 2.0118033766621843e-05, "epoch": 0.5976393246675631, "total_flos": 52158611423232000, "step": 12000 }, { "loss": 6.112984375, "learning_rate": 1.8872951840231086e-05, "epoch": 0.6225409631953782, "total_flos": 54331886899200000, "step": 12500 }, { "loss": 6.054078125, "learning_rate": 1.762786991384033e-05, "epoch": 0.6474426017231933, "total_flos": 56505162375168000, "step": 13000 }, { "loss": 6.0306875, "learning_rate": 1.6382787987449573e-05, "epoch": 0.6723442402510085, "total_flos": 58678437851136000, "step": 13500 }, { "loss": 5.998078125, "learning_rate": 1.5137706061058818e-05, "epoch": 0.6972458787788236, "total_flos": 60851713327104000, "step": 14000 }, { "loss": 5.964859375, "learning_rate": 1.3892624134668061e-05, "epoch": 0.7221475173066387, "total_flos": 63024988803072000, "step": 14500 }, { "loss": 5.938515625, "learning_rate": 1.2647542208277304e-05, "epoch": 0.7470491558344539, "total_flos": 65198264279040000, "step": 15000 }, { "loss": 5.9313125, "learning_rate": 1.1402460281886548e-05, "epoch": 0.771950794362269, "total_flos": 67371539755008000, "step": 15500 }, { "loss": 5.897203125, "learning_rate": 1.0157378355495791e-05, "epoch": 0.7968524328900841, "total_flos": 69544815230976000, "step": 16000 }, { "loss": 5.880890625, "learning_rate": 8.912296429105036e-06, "epoch": 0.8217540714178992, "total_flos": 71718090706944000, "step": 16500 }, { "loss": 5.86578125, "learning_rate": 7.66721450271428e-06, "epoch": 0.8466557099457144, "total_flos": 73891366182912000, "step": 17000 }, { "loss": 5.839921875, "learning_rate": 6.422132576323522e-06, "epoch": 0.8715573484735295, "total_flos": 76064641658880000, "step": 17500 }, { "loss": 5.851390625, "learning_rate": 5.177050649932766e-06, "epoch": 0.8964589870013447, "total_flos": 78237917134848000, "step": 18000 }, { "loss": 5.8313125, "learning_rate": 3.9319687235420096e-06, "epoch": 0.9213606255291599, "total_flos": 80411192610816000, "step": 18500 }, { "loss": 5.813203125, "learning_rate": 2.6868867971512525e-06, "epoch": 0.946262264056975, "total_flos": 82584468086784000, "step": 19000 }, { "loss": 5.82146875, "learning_rate": 1.441804870760496e-06, "epoch": 0.9711639025847901, "total_flos": 84757743562752000, "step": 19500 }, { "loss": 5.809875, "learning_rate": 1.9672294436973953e-07, "epoch": 0.9960655411126053, "total_flos": 86931019038720000, "step": 20000 } ]