|
loss,grad_norm,learning_rate,epoch,step,eval_loss,eval_runtime,eval_samples_per_second,eval_steps_per_second,train_runtime,train_samples_per_second,train_steps_per_second,total_flos,train_loss
|
|
1.2424,0.449230105,4.00E-05,0.005,1,,,,,,,,,
|
|
1.2043,0.477637947,8.00E-05,0.01,2,,,,,,,,,
|
|
1.1605,0.646152377,0.00012,0.015,3,,,,,,,,,
|
|
1.2947,0.971785307,0.00016,0.02,4,,,,,,,,,
|
|
1.2834,0.670975924,0.0002,0.025,5,,,,,,,,,
|
|
,,,0.025,5,1.185093403,261.5559,1.529,0.191,,,,,
|
|
1.1935,0.959468901,0.000195349,0.03,6,,,,,,,,,
|
|
1.2369,6.31564188,0.000190698,0.035,7,,,,,,,,,
|
|
0.9857,1.23881793,0.000186047,0.04,8,,,,,,,,,
|
|
1.1408,1.150145054,0.000181395,0.045,9,,,,,,,,,
|
|
1.1035,0.907861412,0.000176744,0.05,10,,,,,,,,,
|
|
,,,0.05,10,1.001948118,260.5825,1.535,0.192,,,,,
|
|
1.0719,0.614182532,0.000172093,0.055,11,,,,,,,,,
|
|
0.9609,0.754423499,0.000167442,0.06,12,,,,,,,,,
|
|
0.9313,1.592000961,0.000162791,0.065,13,,,,,,,,,
|
|
1.0536,0.76292038,0.00015814,0.07,14,,,,,,,,,
|
|
0.9052,0.47425139,0.000153488,0.075,15,,,,,,,,,
|
|
,,,0.075,15,0.956191421,260.434,1.536,0.192,,,,,
|
|
0.8749,0.680823743,0.000148837,0.08,16,,,,,,,,,
|
|
0.8231,0.471886218,0.000144186,0.085,17,,,,,,,,,
|
|
0.8551,0.908425868,0.000139535,0.09,18,,,,,,,,,
|
|
0.9258,0.670297742,0.000134884,0.095,19,,,,,,,,,
|
|
0.8745,0.444643229,0.000130233,0.1,20,,,,,,,,,
|
|
,,,0.1,20,0.919027865,260.4188,1.536,0.192,,,,,
|
|
0.9034,0.541207969,0.000125581,0.105,21,,,,,,,,,
|
|
0.7407,1.094225049,0.00012093,0.11,22,,,,,,,,,
|
|
0.8844,1.140424371,0.000116279,0.115,23,,,,,,,,,
|
|
0.9849,0.590909362,0.000111628,0.12,24,,,,,,,,,
|
|
0.8385,0.885059714,0.000106977,0.125,25,,,,,,,,,
|
|
,,,0.125,25,0.893909931,260.5428,1.535,0.192,,,,,
|
|
0.8229,0.718320787,0.000102326,0.13,26,,,,,,,,,
|
|
0.8477,0.965009391,9.77E-05,0.135,27,,,,,,,,,
|
|
0.7501,0.79056263,9.30E-05,0.14,28,,,,,,,,,
|
|
1.1964,0.759783685,8.84E-05,0.145,29,,,,,,,,,
|
|
0.809,0.931057155,8.37E-05,0.15,30,,,,,,,,,
|
|
,,,0.15,30,0.87558347,260.4067,1.536,0.192,,,,,
|
|
0.8669,1.041511059,7.91E-05,0.155,31,,,,,,,,,
|
|
0.8235,0.546454132,7.44E-05,0.16,32,,,,,,,,,
|
|
0.9392,1.17530477,6.98E-05,0.165,33,,,,,,,,,
|
|
0.9129,0.505674183,6.51E-05,0.17,34,,,,,,,,,
|
|
0.9565,0.626393735,6.05E-05,0.175,35,,,,,,,,,
|
|
,,,0.175,35,0.858542025,260.3717,1.536,0.192,,,,,
|
|
0.8001,0.731396437,5.58E-05,0.18,36,,,,,,,,,
|
|
0.8504,0.64272815,5.12E-05,0.185,37,,,,,,,,,
|
|
0.9012,1.001707196,4.65E-05,0.19,38,,,,,,,,,
|
|
0.8804,0.967242897,4.19E-05,0.195,39,,,,,,,,,
|
|
0.8776,0.683520138,3.72E-05,0.2,40,,,,,,,,,
|
|
,,,0.2,40,0.847525775,260.2584,1.537,0.192,,,,,
|
|
0.6879,1.112055302,3.26E-05,0.205,41,,,,,,,,,
|
|
0.8564,1.140504122,2.79E-05,0.21,42,,,,,,,,,
|
|
0.8704,0.678111136,2.33E-05,0.215,43,,,,,,,,,
|
|
0.7457,0.64823544,1.86E-05,0.22,44,,,,,,,,,
|
|
0.9221,0.978411436,1.40E-05,0.225,45,,,,,,,,,
|
|
,,,0.225,45,0.841774344,260.5262,1.535,0.192,,,,,
|
|
0.988,0.716996193,9.30E-06,0.23,46,,,,,,,,,
|
|
0.7724,0.821450114,4.65E-06,0.235,47,,,,,,,,,
|
|
0.9051,0.782510281,0,0.24,48,,,,,,,,,
|
|
,,,0.24,48,,,,,2787.918,0.138,0.017,5.68062E+15,0.947014838
|
|
|