Classical-Data / trainer_state.json
PlutoG99001's picture
End of training
a66cf45 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.9741935483870967,
"eval_steps": 500,
"global_step": 308,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.025806451612903226,
"grad_norm": 3.5142855644226074,
"learning_rate": 0.00019870129870129872,
"loss": 8.9214,
"step": 2
},
{
"epoch": 0.05161290322580645,
"grad_norm": 3.772717237472534,
"learning_rate": 0.00019740259740259742,
"loss": 8.3405,
"step": 4
},
{
"epoch": 0.07741935483870968,
"grad_norm": 6.7029924392700195,
"learning_rate": 0.00019610389610389613,
"loss": 8.1379,
"step": 6
},
{
"epoch": 0.1032258064516129,
"grad_norm": 3.7924954891204834,
"learning_rate": 0.0001948051948051948,
"loss": 5.913,
"step": 8
},
{
"epoch": 0.12903225806451613,
"grad_norm": 4.214364051818848,
"learning_rate": 0.00019350649350649354,
"loss": 7.0624,
"step": 10
},
{
"epoch": 0.15483870967741936,
"grad_norm": 3.0830295085906982,
"learning_rate": 0.00019220779220779222,
"loss": 6.6031,
"step": 12
},
{
"epoch": 0.18064516129032257,
"grad_norm": 2.293950080871582,
"learning_rate": 0.00019090909090909092,
"loss": 6.1543,
"step": 14
},
{
"epoch": 0.2064516129032258,
"grad_norm": 2.8121275901794434,
"learning_rate": 0.00018961038961038963,
"loss": 5.6952,
"step": 16
},
{
"epoch": 0.23225806451612904,
"grad_norm": 3.2042553424835205,
"learning_rate": 0.00018831168831168833,
"loss": 5.6916,
"step": 18
},
{
"epoch": 0.25806451612903225,
"grad_norm": 3.4788341522216797,
"learning_rate": 0.000187012987012987,
"loss": 5.575,
"step": 20
},
{
"epoch": 0.2838709677419355,
"grad_norm": 1.1461117267608643,
"learning_rate": 0.00018571428571428572,
"loss": 5.7922,
"step": 22
},
{
"epoch": 0.3096774193548387,
"grad_norm": 1.7745267152786255,
"learning_rate": 0.00018441558441558442,
"loss": 5.5945,
"step": 24
},
{
"epoch": 0.33548387096774196,
"grad_norm": 1.0893975496292114,
"learning_rate": 0.00018311688311688313,
"loss": 6.1593,
"step": 26
},
{
"epoch": 0.36129032258064514,
"grad_norm": 2.169384241104126,
"learning_rate": 0.00018181818181818183,
"loss": 5.8243,
"step": 28
},
{
"epoch": 0.3870967741935484,
"grad_norm": 1.8578031063079834,
"learning_rate": 0.00018051948051948054,
"loss": 5.5041,
"step": 30
},
{
"epoch": 0.4129032258064516,
"grad_norm": 1.448111653327942,
"learning_rate": 0.00017922077922077922,
"loss": 5.3471,
"step": 32
},
{
"epoch": 0.43870967741935485,
"grad_norm": 1.828591227531433,
"learning_rate": 0.00017792207792207792,
"loss": 5.0863,
"step": 34
},
{
"epoch": 0.4645161290322581,
"grad_norm": 4.83806848526001,
"learning_rate": 0.00017662337662337663,
"loss": 6.5823,
"step": 36
},
{
"epoch": 0.49032258064516127,
"grad_norm": 2.1270275115966797,
"learning_rate": 0.00017532467532467534,
"loss": 5.3268,
"step": 38
},
{
"epoch": 0.5161290322580645,
"grad_norm": 1.42393958568573,
"learning_rate": 0.00017402597402597401,
"loss": 5.4203,
"step": 40
},
{
"epoch": 0.5419354838709678,
"grad_norm": 2.768852472305298,
"learning_rate": 0.00017272727272727275,
"loss": 5.3403,
"step": 42
},
{
"epoch": 0.567741935483871,
"grad_norm": 0.7816085815429688,
"learning_rate": 0.00017142857142857143,
"loss": 5.6736,
"step": 44
},
{
"epoch": 0.5935483870967742,
"grad_norm": 0.8368009924888611,
"learning_rate": 0.00017012987012987013,
"loss": 5.4177,
"step": 46
},
{
"epoch": 0.6193548387096774,
"grad_norm": 1.7966578006744385,
"learning_rate": 0.00016883116883116884,
"loss": 5.8706,
"step": 48
},
{
"epoch": 0.6451612903225806,
"grad_norm": 0.694948673248291,
"learning_rate": 0.00016753246753246754,
"loss": 5.2186,
"step": 50
},
{
"epoch": 0.6709677419354839,
"grad_norm": 2.0851364135742188,
"learning_rate": 0.00016623376623376625,
"loss": 5.452,
"step": 52
},
{
"epoch": 0.6967741935483871,
"grad_norm": 1.705665946006775,
"learning_rate": 0.00016493506493506495,
"loss": 5.5373,
"step": 54
},
{
"epoch": 0.7225806451612903,
"grad_norm": 1.5386658906936646,
"learning_rate": 0.00016363636363636366,
"loss": 5.8638,
"step": 56
},
{
"epoch": 0.7483870967741936,
"grad_norm": 1.3625737428665161,
"learning_rate": 0.00016233766233766234,
"loss": 5.2913,
"step": 58
},
{
"epoch": 0.7741935483870968,
"grad_norm": 1.357426643371582,
"learning_rate": 0.00016103896103896104,
"loss": 5.7317,
"step": 60
},
{
"epoch": 0.8,
"grad_norm": 1.1882686614990234,
"learning_rate": 0.00015974025974025975,
"loss": 5.9749,
"step": 62
},
{
"epoch": 0.8258064516129032,
"grad_norm": 1.0777816772460938,
"learning_rate": 0.00015844155844155845,
"loss": 5.4791,
"step": 64
},
{
"epoch": 0.8516129032258064,
"grad_norm": 0.7732660174369812,
"learning_rate": 0.00015714285714285716,
"loss": 5.9732,
"step": 66
},
{
"epoch": 0.8774193548387097,
"grad_norm": 1.0730479955673218,
"learning_rate": 0.00015584415584415587,
"loss": 5.4338,
"step": 68
},
{
"epoch": 0.9032258064516129,
"grad_norm": 1.4834214448928833,
"learning_rate": 0.00015454545454545454,
"loss": 5.1802,
"step": 70
},
{
"epoch": 0.9290322580645162,
"grad_norm": 2.2870066165924072,
"learning_rate": 0.00015324675324675325,
"loss": 6.3573,
"step": 72
},
{
"epoch": 0.9548387096774194,
"grad_norm": 0.935196578502655,
"learning_rate": 0.00015194805194805196,
"loss": 5.0633,
"step": 74
},
{
"epoch": 0.9806451612903225,
"grad_norm": 0.994687020778656,
"learning_rate": 0.00015064935064935066,
"loss": 5.8048,
"step": 76
},
{
"epoch": 1.0064516129032257,
"grad_norm": 2.274411201477051,
"learning_rate": 0.00014935064935064934,
"loss": 4.6835,
"step": 78
},
{
"epoch": 1.032258064516129,
"grad_norm": 1.2067323923110962,
"learning_rate": 0.00014805194805194807,
"loss": 5.4713,
"step": 80
},
{
"epoch": 1.0580645161290323,
"grad_norm": 0.9473636150360107,
"learning_rate": 0.00014675324675324675,
"loss": 5.8508,
"step": 82
},
{
"epoch": 1.0838709677419356,
"grad_norm": 5.7191996574401855,
"learning_rate": 0.00014545454545454546,
"loss": 4.9011,
"step": 84
},
{
"epoch": 1.1096774193548387,
"grad_norm": 2.201740026473999,
"learning_rate": 0.00014415584415584416,
"loss": 5.4717,
"step": 86
},
{
"epoch": 1.135483870967742,
"grad_norm": 1.0441229343414307,
"learning_rate": 0.00014285714285714287,
"loss": 5.5206,
"step": 88
},
{
"epoch": 1.1612903225806452,
"grad_norm": 1.0501593351364136,
"learning_rate": 0.00014155844155844155,
"loss": 5.2199,
"step": 90
},
{
"epoch": 1.1870967741935483,
"grad_norm": 1.1907446384429932,
"learning_rate": 0.00014025974025974028,
"loss": 4.8319,
"step": 92
},
{
"epoch": 1.2129032258064516,
"grad_norm": 4.133155345916748,
"learning_rate": 0.00013896103896103896,
"loss": 5.1049,
"step": 94
},
{
"epoch": 1.238709677419355,
"grad_norm": 1.399916172027588,
"learning_rate": 0.00013766233766233766,
"loss": 5.5704,
"step": 96
},
{
"epoch": 1.2645161290322582,
"grad_norm": 1.0567469596862793,
"learning_rate": 0.00013636363636363637,
"loss": 5.3263,
"step": 98
},
{
"epoch": 1.2903225806451613,
"grad_norm": 1.2196253538131714,
"learning_rate": 0.00013506493506493507,
"loss": 5.2236,
"step": 100
},
{
"epoch": 1.3161290322580645,
"grad_norm": 2.465505838394165,
"learning_rate": 0.00013376623376623375,
"loss": 5.0547,
"step": 102
},
{
"epoch": 1.3419354838709676,
"grad_norm": 0.9022129774093628,
"learning_rate": 0.00013246753246753249,
"loss": 5.8387,
"step": 104
},
{
"epoch": 1.367741935483871,
"grad_norm": 1.6524704694747925,
"learning_rate": 0.0001311688311688312,
"loss": 5.4351,
"step": 106
},
{
"epoch": 1.3935483870967742,
"grad_norm": 1.2133516073226929,
"learning_rate": 0.00012987012987012987,
"loss": 5.4708,
"step": 108
},
{
"epoch": 1.4193548387096775,
"grad_norm": 1.019903302192688,
"learning_rate": 0.00012857142857142858,
"loss": 5.8655,
"step": 110
},
{
"epoch": 1.4451612903225808,
"grad_norm": 1.1822901964187622,
"learning_rate": 0.00012727272727272728,
"loss": 5.3089,
"step": 112
},
{
"epoch": 1.4709677419354839,
"grad_norm": 0.8840041160583496,
"learning_rate": 0.000125974025974026,
"loss": 5.0657,
"step": 114
},
{
"epoch": 1.4967741935483871,
"grad_norm": 0.6745492219924927,
"learning_rate": 0.00012467532467532467,
"loss": 4.8004,
"step": 116
},
{
"epoch": 1.5225806451612902,
"grad_norm": 1.4586549997329712,
"learning_rate": 0.0001233766233766234,
"loss": 5.0572,
"step": 118
},
{
"epoch": 1.5483870967741935,
"grad_norm": 1.5153924226760864,
"learning_rate": 0.00012207792207792208,
"loss": 4.4382,
"step": 120
},
{
"epoch": 1.5741935483870968,
"grad_norm": 0.9981886148452759,
"learning_rate": 0.0001207792207792208,
"loss": 4.8087,
"step": 122
},
{
"epoch": 1.6,
"grad_norm": 0.7403278350830078,
"learning_rate": 0.00011948051948051949,
"loss": 5.2025,
"step": 124
},
{
"epoch": 1.6258064516129034,
"grad_norm": 1.1075459718704224,
"learning_rate": 0.0001181818181818182,
"loss": 4.946,
"step": 126
},
{
"epoch": 1.6516129032258065,
"grad_norm": 0.6300385594367981,
"learning_rate": 0.00011688311688311689,
"loss": 5.6817,
"step": 128
},
{
"epoch": 1.6774193548387095,
"grad_norm": 0.8701953291893005,
"learning_rate": 0.00011558441558441559,
"loss": 5.6561,
"step": 130
},
{
"epoch": 1.7032258064516128,
"grad_norm": 1.133817434310913,
"learning_rate": 0.00011428571428571428,
"loss": 5.6528,
"step": 132
},
{
"epoch": 1.729032258064516,
"grad_norm": 1.6048352718353271,
"learning_rate": 0.000112987012987013,
"loss": 4.8602,
"step": 134
},
{
"epoch": 1.7548387096774194,
"grad_norm": 1.2783055305480957,
"learning_rate": 0.00011168831168831168,
"loss": 4.1662,
"step": 136
},
{
"epoch": 1.7806451612903227,
"grad_norm": 1.6137133836746216,
"learning_rate": 0.0001103896103896104,
"loss": 5.2295,
"step": 138
},
{
"epoch": 1.8064516129032258,
"grad_norm": 0.6374461054801941,
"learning_rate": 0.00010909090909090909,
"loss": 5.3992,
"step": 140
},
{
"epoch": 1.832258064516129,
"grad_norm": 0.8323061466217041,
"learning_rate": 0.0001077922077922078,
"loss": 5.1712,
"step": 142
},
{
"epoch": 1.8580645161290321,
"grad_norm": 0.6804484724998474,
"learning_rate": 0.00010649350649350649,
"loss": 5.3369,
"step": 144
},
{
"epoch": 1.8838709677419354,
"grad_norm": 0.9051455855369568,
"learning_rate": 0.0001051948051948052,
"loss": 5.3726,
"step": 146
},
{
"epoch": 1.9096774193548387,
"grad_norm": 0.5890415906906128,
"learning_rate": 0.00010389610389610389,
"loss": 5.4903,
"step": 148
},
{
"epoch": 1.935483870967742,
"grad_norm": 0.5433252453804016,
"learning_rate": 0.00010259740259740261,
"loss": 5.4437,
"step": 150
},
{
"epoch": 1.9612903225806453,
"grad_norm": 1.353121042251587,
"learning_rate": 0.0001012987012987013,
"loss": 4.1137,
"step": 152
},
{
"epoch": 1.9870967741935484,
"grad_norm": 1.0199609994888306,
"learning_rate": 0.0001,
"loss": 5.2558,
"step": 154
},
{
"epoch": 2.0129032258064514,
"grad_norm": 0.6021209359169006,
"learning_rate": 9.870129870129871e-05,
"loss": 5.5338,
"step": 156
},
{
"epoch": 2.0387096774193547,
"grad_norm": 0.9102515578269958,
"learning_rate": 9.74025974025974e-05,
"loss": 4.5988,
"step": 158
},
{
"epoch": 2.064516129032258,
"grad_norm": 0.7101506590843201,
"learning_rate": 9.610389610389611e-05,
"loss": 5.2622,
"step": 160
},
{
"epoch": 2.0903225806451613,
"grad_norm": 0.631308913230896,
"learning_rate": 9.480519480519481e-05,
"loss": 5.4718,
"step": 162
},
{
"epoch": 2.1161290322580646,
"grad_norm": 0.7462102770805359,
"learning_rate": 9.35064935064935e-05,
"loss": 5.0117,
"step": 164
},
{
"epoch": 2.141935483870968,
"grad_norm": 0.6367154717445374,
"learning_rate": 9.220779220779221e-05,
"loss": 4.9968,
"step": 166
},
{
"epoch": 2.167741935483871,
"grad_norm": 0.6959227323532104,
"learning_rate": 9.090909090909092e-05,
"loss": 5.6022,
"step": 168
},
{
"epoch": 2.193548387096774,
"grad_norm": 0.6119377613067627,
"learning_rate": 8.961038961038961e-05,
"loss": 4.9405,
"step": 170
},
{
"epoch": 2.2193548387096773,
"grad_norm": 0.6411863565444946,
"learning_rate": 8.831168831168831e-05,
"loss": 5.1413,
"step": 172
},
{
"epoch": 2.2451612903225806,
"grad_norm": 1.615324854850769,
"learning_rate": 8.701298701298701e-05,
"loss": 4.7308,
"step": 174
},
{
"epoch": 2.270967741935484,
"grad_norm": 0.5708146691322327,
"learning_rate": 8.571428571428571e-05,
"loss": 5.4497,
"step": 176
},
{
"epoch": 2.296774193548387,
"grad_norm": 0.8313891291618347,
"learning_rate": 8.441558441558442e-05,
"loss": 5.3687,
"step": 178
},
{
"epoch": 2.3225806451612905,
"grad_norm": 1.1731419563293457,
"learning_rate": 8.311688311688312e-05,
"loss": 5.3314,
"step": 180
},
{
"epoch": 2.3483870967741938,
"grad_norm": 0.7381497025489807,
"learning_rate": 8.181818181818183e-05,
"loss": 5.1178,
"step": 182
},
{
"epoch": 2.3741935483870966,
"grad_norm": 0.6883618831634521,
"learning_rate": 8.051948051948052e-05,
"loss": 5.9266,
"step": 184
},
{
"epoch": 2.4,
"grad_norm": 0.735080361366272,
"learning_rate": 7.922077922077923e-05,
"loss": 4.7453,
"step": 186
},
{
"epoch": 2.425806451612903,
"grad_norm": 0.6184589862823486,
"learning_rate": 7.792207792207793e-05,
"loss": 5.0924,
"step": 188
},
{
"epoch": 2.4516129032258065,
"grad_norm": 0.6305899024009705,
"learning_rate": 7.662337662337662e-05,
"loss": 5.1167,
"step": 190
},
{
"epoch": 2.47741935483871,
"grad_norm": 0.815334677696228,
"learning_rate": 7.532467532467533e-05,
"loss": 5.4719,
"step": 192
},
{
"epoch": 2.5032258064516126,
"grad_norm": 0.6805923581123352,
"learning_rate": 7.402597402597404e-05,
"loss": 4.4392,
"step": 194
},
{
"epoch": 2.5290322580645164,
"grad_norm": 0.6633741855621338,
"learning_rate": 7.272727272727273e-05,
"loss": 5.1926,
"step": 196
},
{
"epoch": 2.554838709677419,
"grad_norm": 0.6042450666427612,
"learning_rate": 7.142857142857143e-05,
"loss": 4.7079,
"step": 198
},
{
"epoch": 2.5806451612903225,
"grad_norm": 0.5892207622528076,
"learning_rate": 7.012987012987014e-05,
"loss": 4.9938,
"step": 200
},
{
"epoch": 2.606451612903226,
"grad_norm": 0.6753908395767212,
"learning_rate": 6.883116883116883e-05,
"loss": 5.0097,
"step": 202
},
{
"epoch": 2.632258064516129,
"grad_norm": 0.5345973968505859,
"learning_rate": 6.753246753246754e-05,
"loss": 5.1074,
"step": 204
},
{
"epoch": 2.6580645161290324,
"grad_norm": 0.4924313724040985,
"learning_rate": 6.623376623376624e-05,
"loss": 5.0817,
"step": 206
},
{
"epoch": 2.6838709677419352,
"grad_norm": 0.5989976525306702,
"learning_rate": 6.493506493506494e-05,
"loss": 4.2039,
"step": 208
},
{
"epoch": 2.709677419354839,
"grad_norm": 1.0730255842208862,
"learning_rate": 6.363636363636364e-05,
"loss": 4.2224,
"step": 210
},
{
"epoch": 2.735483870967742,
"grad_norm": 0.991038978099823,
"learning_rate": 6.233766233766233e-05,
"loss": 4.8869,
"step": 212
},
{
"epoch": 2.761290322580645,
"grad_norm": 0.5952357053756714,
"learning_rate": 6.103896103896104e-05,
"loss": 5.1753,
"step": 214
},
{
"epoch": 2.7870967741935484,
"grad_norm": 0.6798732876777649,
"learning_rate": 5.9740259740259744e-05,
"loss": 4.3396,
"step": 216
},
{
"epoch": 2.8129032258064517,
"grad_norm": 0.5361295342445374,
"learning_rate": 5.844155844155844e-05,
"loss": 5.2857,
"step": 218
},
{
"epoch": 2.838709677419355,
"grad_norm": 0.6326772570610046,
"learning_rate": 5.714285714285714e-05,
"loss": 4.7385,
"step": 220
},
{
"epoch": 2.864516129032258,
"grad_norm": 0.639589786529541,
"learning_rate": 5.584415584415584e-05,
"loss": 4.3803,
"step": 222
},
{
"epoch": 2.8903225806451616,
"grad_norm": 0.7248474955558777,
"learning_rate": 5.4545454545454546e-05,
"loss": 4.6668,
"step": 224
},
{
"epoch": 2.9161290322580644,
"grad_norm": 0.7551538348197937,
"learning_rate": 5.3246753246753245e-05,
"loss": 5.016,
"step": 226
},
{
"epoch": 2.9419354838709677,
"grad_norm": 0.4990728497505188,
"learning_rate": 5.1948051948051944e-05,
"loss": 5.0843,
"step": 228
},
{
"epoch": 2.967741935483871,
"grad_norm": 0.5729503035545349,
"learning_rate": 5.064935064935065e-05,
"loss": 4.573,
"step": 230
},
{
"epoch": 2.9935483870967743,
"grad_norm": 1.4705737829208374,
"learning_rate": 4.9350649350649355e-05,
"loss": 4.9812,
"step": 232
},
{
"epoch": 3.0193548387096776,
"grad_norm": 0.7053755521774292,
"learning_rate": 4.8051948051948054e-05,
"loss": 4.7651,
"step": 234
},
{
"epoch": 3.0451612903225804,
"grad_norm": 0.6120907664299011,
"learning_rate": 4.675324675324675e-05,
"loss": 5.2057,
"step": 236
},
{
"epoch": 3.0709677419354837,
"grad_norm": 0.6173492074012756,
"learning_rate": 4.545454545454546e-05,
"loss": 5.0342,
"step": 238
},
{
"epoch": 3.096774193548387,
"grad_norm": 0.5435605049133301,
"learning_rate": 4.415584415584416e-05,
"loss": 4.9538,
"step": 240
},
{
"epoch": 3.1225806451612903,
"grad_norm": 1.4004778861999512,
"learning_rate": 4.2857142857142856e-05,
"loss": 4.3856,
"step": 242
},
{
"epoch": 3.1483870967741936,
"grad_norm": 1.1300957202911377,
"learning_rate": 4.155844155844156e-05,
"loss": 5.0085,
"step": 244
},
{
"epoch": 3.174193548387097,
"grad_norm": 0.6826758980751038,
"learning_rate": 4.025974025974026e-05,
"loss": 5.3525,
"step": 246
},
{
"epoch": 3.2,
"grad_norm": 0.6162336468696594,
"learning_rate": 3.8961038961038966e-05,
"loss": 5.1639,
"step": 248
},
{
"epoch": 3.225806451612903,
"grad_norm": 0.7551366686820984,
"learning_rate": 3.7662337662337665e-05,
"loss": 5.1913,
"step": 250
},
{
"epoch": 3.2516129032258063,
"grad_norm": 0.5899360775947571,
"learning_rate": 3.6363636363636364e-05,
"loss": 5.022,
"step": 252
},
{
"epoch": 3.2774193548387096,
"grad_norm": 0.6666110157966614,
"learning_rate": 3.506493506493507e-05,
"loss": 4.697,
"step": 254
},
{
"epoch": 3.303225806451613,
"grad_norm": 0.5686184167861938,
"learning_rate": 3.376623376623377e-05,
"loss": 4.8758,
"step": 256
},
{
"epoch": 3.329032258064516,
"grad_norm": 0.7564727663993835,
"learning_rate": 3.246753246753247e-05,
"loss": 4.9468,
"step": 258
},
{
"epoch": 3.3548387096774195,
"grad_norm": 0.5773691534996033,
"learning_rate": 3.1168831168831166e-05,
"loss": 5.1122,
"step": 260
},
{
"epoch": 3.3806451612903228,
"grad_norm": 0.642393171787262,
"learning_rate": 2.9870129870129872e-05,
"loss": 5.233,
"step": 262
},
{
"epoch": 3.4064516129032256,
"grad_norm": 0.6513245701789856,
"learning_rate": 2.857142857142857e-05,
"loss": 4.2779,
"step": 264
},
{
"epoch": 3.432258064516129,
"grad_norm": 0.8267136812210083,
"learning_rate": 2.7272727272727273e-05,
"loss": 5.2998,
"step": 266
},
{
"epoch": 3.458064516129032,
"grad_norm": 0.5494163632392883,
"learning_rate": 2.5974025974025972e-05,
"loss": 5.4667,
"step": 268
},
{
"epoch": 3.4838709677419355,
"grad_norm": 0.7057967782020569,
"learning_rate": 2.4675324675324678e-05,
"loss": 5.1893,
"step": 270
},
{
"epoch": 3.509677419354839,
"grad_norm": 0.5400364398956299,
"learning_rate": 2.3376623376623376e-05,
"loss": 4.9972,
"step": 272
},
{
"epoch": 3.535483870967742,
"grad_norm": 0.4732670485973358,
"learning_rate": 2.207792207792208e-05,
"loss": 4.896,
"step": 274
},
{
"epoch": 3.5612903225806454,
"grad_norm": 0.5432953834533691,
"learning_rate": 2.077922077922078e-05,
"loss": 5.0452,
"step": 276
},
{
"epoch": 3.587096774193548,
"grad_norm": 0.5461270213127136,
"learning_rate": 1.9480519480519483e-05,
"loss": 4.7124,
"step": 278
},
{
"epoch": 3.6129032258064515,
"grad_norm": 0.6231604218482971,
"learning_rate": 1.8181818181818182e-05,
"loss": 4.3152,
"step": 280
},
{
"epoch": 3.638709677419355,
"grad_norm": 0.42820078134536743,
"learning_rate": 1.6883116883116884e-05,
"loss": 4.9029,
"step": 282
},
{
"epoch": 3.664516129032258,
"grad_norm": 0.7605751752853394,
"learning_rate": 1.5584415584415583e-05,
"loss": 4.8563,
"step": 284
},
{
"epoch": 3.6903225806451614,
"grad_norm": 0.8210684061050415,
"learning_rate": 1.4285714285714285e-05,
"loss": 3.7461,
"step": 286
},
{
"epoch": 3.7161290322580647,
"grad_norm": 0.6016200184822083,
"learning_rate": 1.2987012987012986e-05,
"loss": 4.7194,
"step": 288
},
{
"epoch": 3.741935483870968,
"grad_norm": 0.7171183228492737,
"learning_rate": 1.1688311688311688e-05,
"loss": 4.5957,
"step": 290
},
{
"epoch": 3.767741935483871,
"grad_norm": 0.6558433175086975,
"learning_rate": 1.038961038961039e-05,
"loss": 4.5994,
"step": 292
},
{
"epoch": 3.793548387096774,
"grad_norm": 0.5295835733413696,
"learning_rate": 9.090909090909091e-06,
"loss": 5.5671,
"step": 294
},
{
"epoch": 3.8193548387096774,
"grad_norm": 0.6055201292037964,
"learning_rate": 7.792207792207792e-06,
"loss": 5.0694,
"step": 296
},
{
"epoch": 3.8451612903225807,
"grad_norm": 0.6041186451911926,
"learning_rate": 6.493506493506493e-06,
"loss": 5.0007,
"step": 298
},
{
"epoch": 3.870967741935484,
"grad_norm": 0.7281818985939026,
"learning_rate": 5.194805194805195e-06,
"loss": 4.3153,
"step": 300
},
{
"epoch": 3.896774193548387,
"grad_norm": 0.4925851821899414,
"learning_rate": 3.896103896103896e-06,
"loss": 5.5631,
"step": 302
},
{
"epoch": 3.9225806451612906,
"grad_norm": 0.6916934847831726,
"learning_rate": 2.5974025974025976e-06,
"loss": 5.3932,
"step": 304
},
{
"epoch": 3.9483870967741934,
"grad_norm": 0.6561426520347595,
"learning_rate": 1.2987012987012988e-06,
"loss": 5.3373,
"step": 306
},
{
"epoch": 3.9741935483870967,
"grad_norm": 0.6102042198181152,
"learning_rate": 0.0,
"loss": 5.1064,
"step": 308
},
{
"epoch": 3.9741935483870967,
"step": 308,
"total_flos": 723765039226044.0,
"train_loss": 5.270187915145577,
"train_runtime": 746.2778,
"train_samples_per_second": 3.318,
"train_steps_per_second": 0.413
}
],
"logging_steps": 2,
"max_steps": 308,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 723765039226044.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}