Magic_8B / trainer_state.json
jeiku's picture
Upload 11 files
b13b15c verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9878691983122363,
"eval_steps": 30,
"global_step": 236,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008447729672650475,
"grad_norm": 12.0625,
"learning_rate": 4.347826086956522e-07,
"loss": 1.4041,
"step": 1
},
{
"epoch": 0.008447729672650475,
"eval_loss": 1.5854278802871704,
"eval_runtime": 142.1442,
"eval_samples_per_second": 8.273,
"eval_steps_per_second": 4.137,
"step": 1
},
{
"epoch": 0.01689545934530095,
"grad_norm": 11.875,
"learning_rate": 8.695652173913044e-07,
"loss": 1.4201,
"step": 2
},
{
"epoch": 0.025343189017951427,
"grad_norm": 11.8125,
"learning_rate": 1.3043478260869566e-06,
"loss": 1.3999,
"step": 3
},
{
"epoch": 0.0337909186906019,
"grad_norm": 11.375,
"learning_rate": 1.7391304347826088e-06,
"loss": 1.3856,
"step": 4
},
{
"epoch": 0.042238648363252376,
"grad_norm": 11.0,
"learning_rate": 2.173913043478261e-06,
"loss": 1.3965,
"step": 5
},
{
"epoch": 0.050686378035902854,
"grad_norm": 11.5,
"learning_rate": 2.6086956521739132e-06,
"loss": 1.4083,
"step": 6
},
{
"epoch": 0.059134107708553325,
"grad_norm": 10.75,
"learning_rate": 3.043478260869566e-06,
"loss": 1.3994,
"step": 7
},
{
"epoch": 0.0675818373812038,
"grad_norm": 9.4375,
"learning_rate": 3.4782608695652175e-06,
"loss": 1.3706,
"step": 8
},
{
"epoch": 0.07602956705385427,
"grad_norm": 8.5625,
"learning_rate": 3.91304347826087e-06,
"loss": 1.341,
"step": 9
},
{
"epoch": 0.08447729672650475,
"grad_norm": 7.625,
"learning_rate": 4.347826086956522e-06,
"loss": 1.3271,
"step": 10
},
{
"epoch": 0.09292502639915523,
"grad_norm": 6.03125,
"learning_rate": 4.782608695652174e-06,
"loss": 1.2922,
"step": 11
},
{
"epoch": 0.10137275607180571,
"grad_norm": 5.3125,
"learning_rate": 5.2173913043478265e-06,
"loss": 1.2625,
"step": 12
},
{
"epoch": 0.10982048574445617,
"grad_norm": 4.625,
"learning_rate": 5.652173913043479e-06,
"loss": 1.215,
"step": 13
},
{
"epoch": 0.11826821541710665,
"grad_norm": 4.1875,
"learning_rate": 6.086956521739132e-06,
"loss": 1.1877,
"step": 14
},
{
"epoch": 0.12671594508975711,
"grad_norm": 4.21875,
"learning_rate": 6.521739130434783e-06,
"loss": 1.2066,
"step": 15
},
{
"epoch": 0.1351636747624076,
"grad_norm": 3.984375,
"learning_rate": 6.956521739130435e-06,
"loss": 1.1631,
"step": 16
},
{
"epoch": 0.14361140443505807,
"grad_norm": 3.796875,
"learning_rate": 7.391304347826087e-06,
"loss": 1.1573,
"step": 17
},
{
"epoch": 0.15205913410770855,
"grad_norm": 3.96875,
"learning_rate": 7.82608695652174e-06,
"loss": 1.1425,
"step": 18
},
{
"epoch": 0.16050686378035903,
"grad_norm": 3.390625,
"learning_rate": 8.260869565217392e-06,
"loss": 1.118,
"step": 19
},
{
"epoch": 0.1689545934530095,
"grad_norm": 5.0625,
"learning_rate": 8.695652173913044e-06,
"loss": 1.1083,
"step": 20
},
{
"epoch": 0.17740232312565998,
"grad_norm": 4.59375,
"learning_rate": 9.130434782608697e-06,
"loss": 1.1026,
"step": 21
},
{
"epoch": 0.18585005279831046,
"grad_norm": 4.28125,
"learning_rate": 9.565217391304349e-06,
"loss": 1.106,
"step": 22
},
{
"epoch": 0.19429778247096094,
"grad_norm": 2.71875,
"learning_rate": 1e-05,
"loss": 1.0824,
"step": 23
},
{
"epoch": 0.20274551214361142,
"grad_norm": 2.140625,
"learning_rate": 9.999456158087994e-06,
"loss": 1.0823,
"step": 24
},
{
"epoch": 0.21119324181626187,
"grad_norm": 1.6171875,
"learning_rate": 9.997824750657586e-06,
"loss": 1.0782,
"step": 25
},
{
"epoch": 0.21964097148891235,
"grad_norm": 1.765625,
"learning_rate": 9.995106132599869e-06,
"loss": 1.0511,
"step": 26
},
{
"epoch": 0.22808870116156282,
"grad_norm": 2.03125,
"learning_rate": 9.99130089531422e-06,
"loss": 1.0665,
"step": 27
},
{
"epoch": 0.2365364308342133,
"grad_norm": 1.921875,
"learning_rate": 9.98640986657965e-06,
"loss": 1.0453,
"step": 28
},
{
"epoch": 0.24498416050686378,
"grad_norm": 1.640625,
"learning_rate": 9.980434110374725e-06,
"loss": 1.0415,
"step": 29
},
{
"epoch": 0.25343189017951423,
"grad_norm": 2.265625,
"learning_rate": 9.973374926646117e-06,
"loss": 1.0445,
"step": 30
},
{
"epoch": 0.25343189017951423,
"eval_loss": 1.1312532424926758,
"eval_runtime": 142.3016,
"eval_samples_per_second": 8.264,
"eval_steps_per_second": 4.132,
"step": 30
},
{
"epoch": 0.26187961985216474,
"grad_norm": 1.03125,
"learning_rate": 9.965233851025816e-06,
"loss": 1.0201,
"step": 31
},
{
"epoch": 0.2703273495248152,
"grad_norm": 0.94140625,
"learning_rate": 9.956012654497073e-06,
"loss": 1.0249,
"step": 32
},
{
"epoch": 0.2787750791974657,
"grad_norm": 1.4765625,
"learning_rate": 9.945713343009154e-06,
"loss": 1.0274,
"step": 33
},
{
"epoch": 0.28722280887011614,
"grad_norm": 0.984375,
"learning_rate": 9.934338157040953e-06,
"loss": 1.0145,
"step": 34
},
{
"epoch": 0.29567053854276665,
"grad_norm": 1.265625,
"learning_rate": 9.921889571113629e-06,
"loss": 0.9935,
"step": 35
},
{
"epoch": 0.3041182682154171,
"grad_norm": 1.171875,
"learning_rate": 9.90837029325229e-06,
"loss": 0.982,
"step": 36
},
{
"epoch": 0.3125659978880676,
"grad_norm": 3.328125,
"learning_rate": 9.893783264396903e-06,
"loss": 1.0048,
"step": 37
},
{
"epoch": 0.32101372756071805,
"grad_norm": 1.15625,
"learning_rate": 9.878131657762535e-06,
"loss": 1.0004,
"step": 38
},
{
"epoch": 0.32946145723336856,
"grad_norm": 1.1796875,
"learning_rate": 9.861418878149056e-06,
"loss": 1.0112,
"step": 39
},
{
"epoch": 0.337909186906019,
"grad_norm": 1.25,
"learning_rate": 9.843648561200476e-06,
"loss": 1.0133,
"step": 40
},
{
"epoch": 0.34635691657866946,
"grad_norm": 1.1796875,
"learning_rate": 9.82482457261405e-06,
"loss": 0.9826,
"step": 41
},
{
"epoch": 0.35480464625131997,
"grad_norm": 1.6015625,
"learning_rate": 9.80495100729936e-06,
"loss": 0.9907,
"step": 42
},
{
"epoch": 0.3632523759239704,
"grad_norm": 0.9140625,
"learning_rate": 9.784032188487507e-06,
"loss": 0.9871,
"step": 43
},
{
"epoch": 0.3717001055966209,
"grad_norm": 1.40625,
"learning_rate": 9.762072666790658e-06,
"loss": 0.9809,
"step": 44
},
{
"epoch": 0.3801478352692714,
"grad_norm": 1.6171875,
"learning_rate": 9.73907721921212e-06,
"loss": 0.9862,
"step": 45
},
{
"epoch": 0.3885955649419219,
"grad_norm": 1.7734375,
"learning_rate": 9.715050848107167e-06,
"loss": 0.9739,
"step": 46
},
{
"epoch": 0.39704329461457233,
"grad_norm": 0.8828125,
"learning_rate": 9.689998780094839e-06,
"loss": 0.9704,
"step": 47
},
{
"epoch": 0.40549102428722283,
"grad_norm": 0.859375,
"learning_rate": 9.663926464920959e-06,
"loss": 0.9508,
"step": 48
},
{
"epoch": 0.4139387539598733,
"grad_norm": 1.4609375,
"learning_rate": 9.636839574272623e-06,
"loss": 0.9603,
"step": 49
},
{
"epoch": 0.42238648363252373,
"grad_norm": 1.078125,
"learning_rate": 9.608744000544392e-06,
"loss": 0.9525,
"step": 50
},
{
"epoch": 0.43083421330517424,
"grad_norm": 1.25,
"learning_rate": 9.579645855556481e-06,
"loss": 0.984,
"step": 51
},
{
"epoch": 0.4392819429778247,
"grad_norm": 1.859375,
"learning_rate": 9.54955146922521e-06,
"loss": 0.9727,
"step": 52
},
{
"epoch": 0.4477296726504752,
"grad_norm": 1.125,
"learning_rate": 9.51846738818602e-06,
"loss": 0.9785,
"step": 53
},
{
"epoch": 0.45617740232312565,
"grad_norm": 0.98828125,
"learning_rate": 9.48640037436934e-06,
"loss": 0.9683,
"step": 54
},
{
"epoch": 0.46462513199577615,
"grad_norm": 0.953125,
"learning_rate": 9.453357403529609e-06,
"loss": 0.9551,
"step": 55
},
{
"epoch": 0.4730728616684266,
"grad_norm": 1.6484375,
"learning_rate": 9.419345663727805e-06,
"loss": 0.9722,
"step": 56
},
{
"epoch": 0.4815205913410771,
"grad_norm": 1.3359375,
"learning_rate": 9.38437255376777e-06,
"loss": 0.9641,
"step": 57
},
{
"epoch": 0.48996832101372756,
"grad_norm": 0.96484375,
"learning_rate": 9.348445681586703e-06,
"loss": 0.9395,
"step": 58
},
{
"epoch": 0.498416050686378,
"grad_norm": 0.84765625,
"learning_rate": 9.31157286260014e-06,
"loss": 0.953,
"step": 59
},
{
"epoch": 0.5068637803590285,
"grad_norm": 2.84375,
"learning_rate": 9.273762118001837e-06,
"loss": 0.9479,
"step": 60
},
{
"epoch": 0.5068637803590285,
"eval_loss": 1.0488032102584839,
"eval_runtime": 142.7281,
"eval_samples_per_second": 8.239,
"eval_steps_per_second": 4.12,
"step": 60
},
{
"epoch": 0.515311510031679,
"grad_norm": 0.87890625,
"learning_rate": 9.235021673018849e-06,
"loss": 0.9366,
"step": 61
},
{
"epoch": 0.5237592397043295,
"grad_norm": 0.84375,
"learning_rate": 9.195359955122244e-06,
"loss": 0.9726,
"step": 62
},
{
"epoch": 0.53220696937698,
"grad_norm": 0.8984375,
"learning_rate": 9.15478559219382e-06,
"loss": 0.9478,
"step": 63
},
{
"epoch": 0.5406546990496304,
"grad_norm": 1.234375,
"learning_rate": 9.113307410649222e-06,
"loss": 0.9812,
"step": 64
},
{
"epoch": 0.5491024287222809,
"grad_norm": 1.8671875,
"learning_rate": 9.070934433517872e-06,
"loss": 0.9506,
"step": 65
},
{
"epoch": 0.5575501583949314,
"grad_norm": 0.76171875,
"learning_rate": 9.027675878480131e-06,
"loss": 0.9582,
"step": 66
},
{
"epoch": 0.5659978880675819,
"grad_norm": 0.8203125,
"learning_rate": 8.983541155862114e-06,
"loss": 0.9444,
"step": 67
},
{
"epoch": 0.5744456177402323,
"grad_norm": 0.90234375,
"learning_rate": 8.938539866588593e-06,
"loss": 0.9455,
"step": 68
},
{
"epoch": 0.5828933474128828,
"grad_norm": 1.546875,
"learning_rate": 8.892681800094447e-06,
"loss": 0.9613,
"step": 69
},
{
"epoch": 0.5913410770855333,
"grad_norm": 0.796875,
"learning_rate": 8.845976932195104e-06,
"loss": 0.9584,
"step": 70
},
{
"epoch": 0.5997888067581837,
"grad_norm": 1.0859375,
"learning_rate": 8.798435422916425e-06,
"loss": 0.9418,
"step": 71
},
{
"epoch": 0.6082365364308342,
"grad_norm": 1.328125,
"learning_rate": 8.750067614284534e-06,
"loss": 0.9655,
"step": 72
},
{
"epoch": 0.6166842661034847,
"grad_norm": 1.7109375,
"learning_rate": 8.700884028076042e-06,
"loss": 0.9684,
"step": 73
},
{
"epoch": 0.6251319957761352,
"grad_norm": 1.515625,
"learning_rate": 8.650895363529172e-06,
"loss": 0.9617,
"step": 74
},
{
"epoch": 0.6335797254487856,
"grad_norm": 1.7578125,
"learning_rate": 8.600112495016289e-06,
"loss": 0.9341,
"step": 75
},
{
"epoch": 0.6420274551214361,
"grad_norm": 1.5234375,
"learning_rate": 8.548546469678311e-06,
"loss": 0.9542,
"step": 76
},
{
"epoch": 0.6504751847940866,
"grad_norm": 4.28125,
"learning_rate": 8.496208505021572e-06,
"loss": 0.982,
"step": 77
},
{
"epoch": 0.6589229144667371,
"grad_norm": 1.2578125,
"learning_rate": 8.443109986477574e-06,
"loss": 0.9432,
"step": 78
},
{
"epoch": 0.6673706441393875,
"grad_norm": 1.265625,
"learning_rate": 8.389262464926256e-06,
"loss": 0.9329,
"step": 79
},
{
"epoch": 0.675818373812038,
"grad_norm": 2.5,
"learning_rate": 8.334677654183254e-06,
"loss": 0.9208,
"step": 80
},
{
"epoch": 0.6842661034846885,
"grad_norm": 1.1484375,
"learning_rate": 8.279367428451703e-06,
"loss": 0.9526,
"step": 81
},
{
"epoch": 0.6927138331573389,
"grad_norm": 1.359375,
"learning_rate": 8.223343819739164e-06,
"loss": 0.9455,
"step": 82
},
{
"epoch": 0.7011615628299894,
"grad_norm": 1.4921875,
"learning_rate": 8.166619015240236e-06,
"loss": 0.9448,
"step": 83
},
{
"epoch": 0.7096092925026399,
"grad_norm": 1.8046875,
"learning_rate": 8.109205354685367e-06,
"loss": 0.9445,
"step": 84
},
{
"epoch": 0.7180570221752904,
"grad_norm": 1.8125,
"learning_rate": 8.051115327656538e-06,
"loss": 0.9399,
"step": 85
},
{
"epoch": 0.7265047518479408,
"grad_norm": 1.640625,
"learning_rate": 7.992361570870289e-06,
"loss": 0.9302,
"step": 86
},
{
"epoch": 0.7349524815205913,
"grad_norm": 0.83203125,
"learning_rate": 7.932956865428792e-06,
"loss": 0.9388,
"step": 87
},
{
"epoch": 0.7434002111932418,
"grad_norm": 3.375,
"learning_rate": 7.872914134039485e-06,
"loss": 0.9298,
"step": 88
},
{
"epoch": 0.7518479408658922,
"grad_norm": 2.703125,
"learning_rate": 7.812246438203905e-06,
"loss": 0.9471,
"step": 89
},
{
"epoch": 0.7602956705385427,
"grad_norm": 3.0,
"learning_rate": 7.750966975376328e-06,
"loss": 0.9697,
"step": 90
},
{
"epoch": 0.7602956705385427,
"eval_loss": 1.028804063796997,
"eval_runtime": 142.7249,
"eval_samples_per_second": 8.24,
"eval_steps_per_second": 4.12,
"step": 90
},
{
"epoch": 0.7687434002111933,
"grad_norm": 1.546875,
"learning_rate": 7.689089076092851e-06,
"loss": 0.9306,
"step": 91
},
{
"epoch": 0.7771911298838438,
"grad_norm": 1.09375,
"learning_rate": 7.626626201071494e-06,
"loss": 0.9473,
"step": 92
},
{
"epoch": 0.7856388595564942,
"grad_norm": 1.5,
"learning_rate": 7.563591938284012e-06,
"loss": 0.9601,
"step": 93
},
{
"epoch": 0.7940865892291447,
"grad_norm": 1.453125,
"learning_rate": 7.500000000000001e-06,
"loss": 0.9532,
"step": 94
},
{
"epoch": 0.8025343189017952,
"grad_norm": 1.1484375,
"learning_rate": 7.4358642198039835e-06,
"loss": 0.9402,
"step": 95
},
{
"epoch": 0.8109820485744457,
"grad_norm": 1.46875,
"learning_rate": 7.371198549586091e-06,
"loss": 0.9503,
"step": 96
},
{
"epoch": 0.8194297782470961,
"grad_norm": 1.5625,
"learning_rate": 7.306017056507018e-06,
"loss": 0.9521,
"step": 97
},
{
"epoch": 0.8278775079197466,
"grad_norm": 1.046875,
"learning_rate": 7.240333919937893e-06,
"loss": 0.9512,
"step": 98
},
{
"epoch": 0.8363252375923971,
"grad_norm": 1.421875,
"learning_rate": 7.174163428375748e-06,
"loss": 0.9363,
"step": 99
},
{
"epoch": 0.8447729672650475,
"grad_norm": 2.453125,
"learning_rate": 7.107519976335241e-06,
"loss": 0.9602,
"step": 100
},
{
"epoch": 0.853220696937698,
"grad_norm": 1.3125,
"learning_rate": 7.040418061217325e-06,
"loss": 0.9253,
"step": 101
},
{
"epoch": 0.8616684266103485,
"grad_norm": 1.984375,
"learning_rate": 6.972872280155528e-06,
"loss": 0.9227,
"step": 102
},
{
"epoch": 0.870116156282999,
"grad_norm": 1.9765625,
"learning_rate": 6.9048973268405375e-06,
"loss": 0.935,
"step": 103
},
{
"epoch": 0.8785638859556494,
"grad_norm": 1.2578125,
"learning_rate": 6.836507988323785e-06,
"loss": 0.9207,
"step": 104
},
{
"epoch": 0.8870116156282999,
"grad_norm": 3.5,
"learning_rate": 6.767719141800718e-06,
"loss": 0.9622,
"step": 105
},
{
"epoch": 0.8954593453009504,
"grad_norm": 0.9609375,
"learning_rate": 6.698545751374465e-06,
"loss": 0.9386,
"step": 106
},
{
"epoch": 0.9039070749736009,
"grad_norm": 0.875,
"learning_rate": 6.629002864800589e-06,
"loss": 0.9356,
"step": 107
},
{
"epoch": 0.9123548046462513,
"grad_norm": 0.9921875,
"learning_rate": 6.55910561021365e-06,
"loss": 0.9412,
"step": 108
},
{
"epoch": 0.9208025343189018,
"grad_norm": 1.171875,
"learning_rate": 6.488869192836279e-06,
"loss": 0.9422,
"step": 109
},
{
"epoch": 0.9292502639915523,
"grad_norm": 1.2265625,
"learning_rate": 6.418308891671484e-06,
"loss": 0.9244,
"step": 110
},
{
"epoch": 0.9376979936642027,
"grad_norm": 1.375,
"learning_rate": 6.347440056178904e-06,
"loss": 0.9541,
"step": 111
},
{
"epoch": 0.9461457233368532,
"grad_norm": 0.83203125,
"learning_rate": 6.27627810293574e-06,
"loss": 0.9455,
"step": 112
},
{
"epoch": 0.9545934530095037,
"grad_norm": 1.5546875,
"learning_rate": 6.204838512283073e-06,
"loss": 0.9408,
"step": 113
},
{
"epoch": 0.9630411826821542,
"grad_norm": 0.875,
"learning_rate": 6.133136824958334e-06,
"loss": 0.9358,
"step": 114
},
{
"epoch": 0.9714889123548046,
"grad_norm": 1.2109375,
"learning_rate": 6.061188638714616e-06,
"loss": 0.9362,
"step": 115
},
{
"epoch": 0.9799366420274551,
"grad_norm": 1.9453125,
"learning_rate": 5.989009604927587e-06,
"loss": 0.9186,
"step": 116
},
{
"epoch": 0.9883843717001056,
"grad_norm": 2.03125,
"learning_rate": 5.916615425190744e-06,
"loss": 0.9247,
"step": 117
},
{
"epoch": 0.996832101372756,
"grad_norm": 1.6640625,
"learning_rate": 5.844021847899735e-06,
"loss": 0.9272,
"step": 118
},
{
"epoch": 1.0005274261603376,
"grad_norm": 1.25,
"learning_rate": 5.771244664826512e-06,
"loss": 0.9336,
"step": 119
},
{
"epoch": 1.0089662447257384,
"grad_norm": 1.140625,
"learning_rate": 5.698299707684031e-06,
"loss": 0.9126,
"step": 120
},
{
"epoch": 1.0089662447257384,
"eval_loss": 1.01927649974823,
"eval_runtime": 142.6079,
"eval_samples_per_second": 8.246,
"eval_steps_per_second": 4.123,
"step": 120
},
{
"epoch": 1.0174050632911393,
"grad_norm": 1.0546875,
"learning_rate": 5.6252028446822805e-06,
"loss": 0.9456,
"step": 121
},
{
"epoch": 1.02584388185654,
"grad_norm": 1.3984375,
"learning_rate": 5.55196997707635e-06,
"loss": 0.8995,
"step": 122
},
{
"epoch": 1.034282700421941,
"grad_norm": 1.7578125,
"learning_rate": 5.478617035707337e-06,
"loss": 0.9174,
"step": 123
},
{
"epoch": 1.0427215189873418,
"grad_norm": 3.015625,
"learning_rate": 5.4051599775368e-06,
"loss": 0.9243,
"step": 124
},
{
"epoch": 1.0511603375527425,
"grad_norm": 5.0,
"learning_rate": 5.33161478217552e-06,
"loss": 0.9076,
"step": 125
},
{
"epoch": 1.0595991561181435,
"grad_norm": 1.375,
"learning_rate": 5.257997448407366e-06,
"loss": 0.9037,
"step": 126
},
{
"epoch": 1.0680379746835442,
"grad_norm": 1.1015625,
"learning_rate": 5.184323990708959e-06,
"loss": 0.9205,
"step": 127
},
{
"epoch": 1.0764767932489452,
"grad_norm": 0.796875,
"learning_rate": 5.110610435765935e-06,
"loss": 0.9253,
"step": 128
},
{
"epoch": 1.084915611814346,
"grad_norm": 0.8828125,
"learning_rate": 5.0368728189865624e-06,
"loss": 0.8919,
"step": 129
},
{
"epoch": 1.0933544303797469,
"grad_norm": 1.0,
"learning_rate": 4.9631271810134375e-06,
"loss": 0.9086,
"step": 130
},
{
"epoch": 1.1017932489451476,
"grad_norm": 0.91015625,
"learning_rate": 4.8893895642340665e-06,
"loss": 0.919,
"step": 131
},
{
"epoch": 1.1102320675105486,
"grad_norm": 1.296875,
"learning_rate": 4.815676009291044e-06,
"loss": 0.8987,
"step": 132
},
{
"epoch": 1.1186708860759493,
"grad_norm": 1.5234375,
"learning_rate": 4.742002551592635e-06,
"loss": 0.8944,
"step": 133
},
{
"epoch": 1.1271097046413503,
"grad_norm": 1.15625,
"learning_rate": 4.668385217824482e-06,
"loss": 0.8949,
"step": 134
},
{
"epoch": 1.135548523206751,
"grad_norm": 1.125,
"learning_rate": 4.594840022463201e-06,
"loss": 0.9191,
"step": 135
},
{
"epoch": 1.143987341772152,
"grad_norm": 2.1875,
"learning_rate": 4.5213829642926635e-06,
"loss": 0.9198,
"step": 136
},
{
"epoch": 1.1524261603375527,
"grad_norm": 1.71875,
"learning_rate": 4.4480300229236525e-06,
"loss": 0.913,
"step": 137
},
{
"epoch": 1.1608649789029535,
"grad_norm": 0.83984375,
"learning_rate": 4.374797155317721e-06,
"loss": 0.901,
"step": 138
},
{
"epoch": 1.1693037974683544,
"grad_norm": 1.1328125,
"learning_rate": 4.30170029231597e-06,
"loss": 0.9069,
"step": 139
},
{
"epoch": 1.1777426160337552,
"grad_norm": 3.28125,
"learning_rate": 4.228755335173488e-06,
"loss": 0.9043,
"step": 140
},
{
"epoch": 1.1861814345991561,
"grad_norm": 1.8671875,
"learning_rate": 4.155978152100266e-06,
"loss": 0.9341,
"step": 141
},
{
"epoch": 1.1946202531645569,
"grad_norm": 1.890625,
"learning_rate": 4.0833845748092586e-06,
"loss": 0.9226,
"step": 142
},
{
"epoch": 1.2030590717299579,
"grad_norm": 2.28125,
"learning_rate": 4.010990395072414e-06,
"loss": 0.8963,
"step": 143
},
{
"epoch": 1.2114978902953586,
"grad_norm": 0.79296875,
"learning_rate": 3.938811361285386e-06,
"loss": 0.9268,
"step": 144
},
{
"epoch": 1.2199367088607596,
"grad_norm": 1.1328125,
"learning_rate": 3.866863175041666e-06,
"loss": 0.9315,
"step": 145
},
{
"epoch": 1.2283755274261603,
"grad_norm": 1.4453125,
"learning_rate": 3.7951614877169285e-06,
"loss": 0.9213,
"step": 146
},
{
"epoch": 1.2368143459915613,
"grad_norm": 1.5859375,
"learning_rate": 3.7237218970642624e-06,
"loss": 0.9374,
"step": 147
},
{
"epoch": 1.245253164556962,
"grad_norm": 0.6875,
"learning_rate": 3.6525599438210956e-06,
"loss": 0.9161,
"step": 148
},
{
"epoch": 1.253691983122363,
"grad_norm": 1.3203125,
"learning_rate": 3.5816911083285165e-06,
"loss": 0.9227,
"step": 149
},
{
"epoch": 1.2621308016877637,
"grad_norm": 0.83984375,
"learning_rate": 3.511130807163724e-06,
"loss": 0.9006,
"step": 150
},
{
"epoch": 1.2621308016877637,
"eval_loss": 1.0156337022781372,
"eval_runtime": 142.5229,
"eval_samples_per_second": 8.251,
"eval_steps_per_second": 4.126,
"step": 150
},
{
"epoch": 1.2705696202531644,
"grad_norm": 1.859375,
"learning_rate": 3.440894389786352e-06,
"loss": 0.9186,
"step": 151
},
{
"epoch": 1.2790084388185654,
"grad_norm": 0.80078125,
"learning_rate": 3.370997135199413e-06,
"loss": 0.9189,
"step": 152
},
{
"epoch": 1.2874472573839664,
"grad_norm": 0.828125,
"learning_rate": 3.3014542486255365e-06,
"loss": 0.9234,
"step": 153
},
{
"epoch": 1.2958860759493671,
"grad_norm": 1.0546875,
"learning_rate": 3.2322808581992825e-06,
"loss": 0.9301,
"step": 154
},
{
"epoch": 1.3043248945147679,
"grad_norm": 1.265625,
"learning_rate": 3.1634920116762175e-06,
"loss": 0.8999,
"step": 155
},
{
"epoch": 1.3127637130801688,
"grad_norm": 1.1796875,
"learning_rate": 3.0951026731594634e-06,
"loss": 0.9196,
"step": 156
},
{
"epoch": 1.3212025316455696,
"grad_norm": 1.3046875,
"learning_rate": 3.0271277198444737e-06,
"loss": 0.9,
"step": 157
},
{
"epoch": 1.3296413502109705,
"grad_norm": 2.703125,
"learning_rate": 2.9595819387826753e-06,
"loss": 0.9072,
"step": 158
},
{
"epoch": 1.3380801687763713,
"grad_norm": 1.6015625,
"learning_rate": 2.89248002366476e-06,
"loss": 0.9319,
"step": 159
},
{
"epoch": 1.3465189873417722,
"grad_norm": 0.94140625,
"learning_rate": 2.8258365716242543e-06,
"loss": 0.9182,
"step": 160
},
{
"epoch": 1.354957805907173,
"grad_norm": 12.0625,
"learning_rate": 2.7596660800621076e-06,
"loss": 0.926,
"step": 161
},
{
"epoch": 1.363396624472574,
"grad_norm": 2.078125,
"learning_rate": 2.6939829434929834e-06,
"loss": 0.907,
"step": 162
},
{
"epoch": 1.3718354430379747,
"grad_norm": 1.109375,
"learning_rate": 2.6288014504139104e-06,
"loss": 0.9023,
"step": 163
},
{
"epoch": 1.3802742616033754,
"grad_norm": 1.78125,
"learning_rate": 2.5641357801960186e-06,
"loss": 0.9076,
"step": 164
},
{
"epoch": 1.3887130801687764,
"grad_norm": 1.296875,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.9169,
"step": 165
},
{
"epoch": 1.3971518987341773,
"grad_norm": 1.0703125,
"learning_rate": 2.4364080617159885e-06,
"loss": 0.909,
"step": 166
},
{
"epoch": 1.405590717299578,
"grad_norm": 1.015625,
"learning_rate": 2.373373798928507e-06,
"loss": 0.8992,
"step": 167
},
{
"epoch": 1.4140295358649788,
"grad_norm": 0.73828125,
"learning_rate": 2.310910923907149e-06,
"loss": 0.8999,
"step": 168
},
{
"epoch": 1.4224683544303798,
"grad_norm": 1.2578125,
"learning_rate": 2.249033024623672e-06,
"loss": 0.9233,
"step": 169
},
{
"epoch": 1.4309071729957805,
"grad_norm": 1.2578125,
"learning_rate": 2.187753561796097e-06,
"loss": 0.9251,
"step": 170
},
{
"epoch": 1.4393459915611815,
"grad_norm": 0.80859375,
"learning_rate": 2.127085865960516e-06,
"loss": 0.9033,
"step": 171
},
{
"epoch": 1.4477848101265822,
"grad_norm": 0.81640625,
"learning_rate": 2.0670431345712092e-06,
"loss": 0.9113,
"step": 172
},
{
"epoch": 1.4562236286919832,
"grad_norm": 0.93359375,
"learning_rate": 2.0076384291297134e-06,
"loss": 0.9255,
"step": 173
},
{
"epoch": 1.464662447257384,
"grad_norm": 1.0625,
"learning_rate": 1.9488846723434646e-06,
"loss": 0.8948,
"step": 174
},
{
"epoch": 1.4731012658227849,
"grad_norm": 0.7734375,
"learning_rate": 1.890794645314633e-06,
"loss": 0.9286,
"step": 175
},
{
"epoch": 1.4815400843881856,
"grad_norm": 1.453125,
"learning_rate": 1.8333809847597644e-06,
"loss": 0.9314,
"step": 176
},
{
"epoch": 1.4899789029535864,
"grad_norm": 1.0546875,
"learning_rate": 1.7766561802608374e-06,
"loss": 0.9154,
"step": 177
},
{
"epoch": 1.4984177215189873,
"grad_norm": 1.109375,
"learning_rate": 1.7206325715483003e-06,
"loss": 0.9293,
"step": 178
},
{
"epoch": 1.5068565400843883,
"grad_norm": 1.34375,
"learning_rate": 1.665322345816746e-06,
"loss": 0.9358,
"step": 179
},
{
"epoch": 1.515295358649789,
"grad_norm": 1.109375,
"learning_rate": 1.6107375350737437e-06,
"loss": 0.9038,
"step": 180
},
{
"epoch": 1.515295358649789,
"eval_loss": 1.0140331983566284,
"eval_runtime": 142.6045,
"eval_samples_per_second": 8.247,
"eval_steps_per_second": 4.123,
"step": 180
},
{
"epoch": 1.5237341772151898,
"grad_norm": 0.796875,
"learning_rate": 1.556890013522428e-06,
"loss": 0.9108,
"step": 181
},
{
"epoch": 1.5321729957805907,
"grad_norm": 1.421875,
"learning_rate": 1.50379149497843e-06,
"loss": 0.9137,
"step": 182
},
{
"epoch": 1.5406118143459917,
"grad_norm": 1.7265625,
"learning_rate": 1.4514535303216893e-06,
"loss": 0.9258,
"step": 183
},
{
"epoch": 1.5490506329113924,
"grad_norm": 0.7890625,
"learning_rate": 1.3998875049837141e-06,
"loss": 0.8968,
"step": 184
},
{
"epoch": 1.5574894514767932,
"grad_norm": 1.1953125,
"learning_rate": 1.3491046364708294e-06,
"loss": 0.8999,
"step": 185
},
{
"epoch": 1.5659282700421941,
"grad_norm": 1.1640625,
"learning_rate": 1.2991159719239581e-06,
"loss": 0.9049,
"step": 186
},
{
"epoch": 1.5743670886075949,
"grad_norm": 1.1328125,
"learning_rate": 1.249932385715467e-06,
"loss": 0.9268,
"step": 187
},
{
"epoch": 1.5828059071729959,
"grad_norm": 1.25,
"learning_rate": 1.2015645770835765e-06,
"loss": 0.9136,
"step": 188
},
{
"epoch": 1.5912447257383966,
"grad_norm": 0.9609375,
"learning_rate": 1.1540230678048969e-06,
"loss": 0.8777,
"step": 189
},
{
"epoch": 1.5996835443037973,
"grad_norm": 1.671875,
"learning_rate": 1.1073181999055538e-06,
"loss": 0.8875,
"step": 190
},
{
"epoch": 1.6081223628691983,
"grad_norm": 6.3125,
"learning_rate": 1.0614601334114099e-06,
"loss": 0.9136,
"step": 191
},
{
"epoch": 1.6165611814345993,
"grad_norm": 1.015625,
"learning_rate": 1.016458844137887e-06,
"loss": 0.9114,
"step": 192
},
{
"epoch": 1.625,
"grad_norm": 0.83984375,
"learning_rate": 9.723241215198692e-07,
"loss": 0.9235,
"step": 193
},
{
"epoch": 1.6334388185654007,
"grad_norm": 1.3515625,
"learning_rate": 9.290655664821296e-07,
"loss": 0.9176,
"step": 194
},
{
"epoch": 1.6418776371308017,
"grad_norm": 1.765625,
"learning_rate": 8.866925893507805e-07,
"loss": 0.8998,
"step": 195
},
{
"epoch": 1.6503164556962027,
"grad_norm": 1.59375,
"learning_rate": 8.45214407806182e-07,
"loss": 0.9041,
"step": 196
},
{
"epoch": 1.6587552742616034,
"grad_norm": 1.6796875,
"learning_rate": 8.046400448777575e-07,
"loss": 0.9111,
"step": 197
},
{
"epoch": 1.6671940928270041,
"grad_norm": 1.1328125,
"learning_rate": 7.649783269811523e-07,
"loss": 0.9159,
"step": 198
},
{
"epoch": 1.6756329113924051,
"grad_norm": 1.84375,
"learning_rate": 7.26237881998163e-07,
"loss": 0.8953,
"step": 199
},
{
"epoch": 1.6840717299578059,
"grad_norm": 0.98828125,
"learning_rate": 6.884271373998608e-07,
"loss": 0.9039,
"step": 200
},
{
"epoch": 1.6925105485232068,
"grad_norm": 1.828125,
"learning_rate": 6.515543184133e-07,
"loss": 0.9155,
"step": 201
},
{
"epoch": 1.7009493670886076,
"grad_norm": 0.79296875,
"learning_rate": 6.156274462322292e-07,
"loss": 0.8962,
"step": 202
},
{
"epoch": 1.7093881856540083,
"grad_norm": 3.140625,
"learning_rate": 5.806543362721945e-07,
"loss": 0.9149,
"step": 203
},
{
"epoch": 1.7178270042194093,
"grad_norm": 0.75390625,
"learning_rate": 5.466425964703914e-07,
"loss": 0.9013,
"step": 204
},
{
"epoch": 1.7262658227848102,
"grad_norm": 2.28125,
"learning_rate": 5.135996256306619e-07,
"loss": 0.9258,
"step": 205
},
{
"epoch": 1.734704641350211,
"grad_norm": 0.80078125,
"learning_rate": 4.815326118139813e-07,
"loss": 0.9308,
"step": 206
},
{
"epoch": 1.7431434599156117,
"grad_norm": 0.7265625,
"learning_rate": 4.5044853077479134e-07,
"loss": 0.9125,
"step": 207
},
{
"epoch": 1.7515822784810127,
"grad_norm": 0.8828125,
"learning_rate": 4.203541444435211e-07,
"loss": 0.8996,
"step": 208
},
{
"epoch": 1.7600210970464136,
"grad_norm": 0.92578125,
"learning_rate": 3.9125599945560866e-07,
"loss": 0.9171,
"step": 209
},
{
"epoch": 1.7684599156118144,
"grad_norm": 1.25,
"learning_rate": 3.631604257273774e-07,
"loss": 0.9095,
"step": 210
},
{
"epoch": 1.7684599156118144,
"eval_loss": 1.0137686729431152,
"eval_runtime": 142.61,
"eval_samples_per_second": 8.246,
"eval_steps_per_second": 4.123,
"step": 210
},
{
"epoch": 1.7768987341772151,
"grad_norm": 0.87890625,
"learning_rate": 3.360735350790428e-07,
"loss": 0.886,
"step": 211
},
{
"epoch": 1.785337552742616,
"grad_norm": 0.8046875,
"learning_rate": 3.100012199051627e-07,
"loss": 0.8977,
"step": 212
},
{
"epoch": 1.793776371308017,
"grad_norm": 0.89453125,
"learning_rate": 2.8494915189283325e-07,
"loss": 0.9127,
"step": 213
},
{
"epoch": 1.8022151898734178,
"grad_norm": 0.81640625,
"learning_rate": 2.6092278078788004e-07,
"loss": 0.9386,
"step": 214
},
{
"epoch": 1.8106540084388185,
"grad_norm": 0.8125,
"learning_rate": 2.3792733320934348e-07,
"loss": 0.8919,
"step": 215
},
{
"epoch": 1.8190928270042193,
"grad_norm": 0.84375,
"learning_rate": 2.1596781151249524e-07,
"loss": 0.9077,
"step": 216
},
{
"epoch": 1.8275316455696202,
"grad_norm": 0.97265625,
"learning_rate": 1.9504899270064105e-07,
"loss": 0.8998,
"step": 217
},
{
"epoch": 1.8359704641350212,
"grad_norm": 1.28125,
"learning_rate": 1.7517542738595071e-07,
"loss": 0.8967,
"step": 218
},
{
"epoch": 1.844409282700422,
"grad_norm": 1.1875,
"learning_rate": 1.5635143879952575e-07,
"loss": 0.8876,
"step": 219
},
{
"epoch": 1.8528481012658227,
"grad_norm": 1.078125,
"learning_rate": 1.3858112185094418e-07,
"loss": 0.9276,
"step": 220
},
{
"epoch": 1.8612869198312236,
"grad_norm": 1.015625,
"learning_rate": 1.2186834223746612e-07,
"loss": 0.8981,
"step": 221
},
{
"epoch": 1.8697257383966246,
"grad_norm": 0.9921875,
"learning_rate": 1.0621673560309798e-07,
"loss": 0.9253,
"step": 222
},
{
"epoch": 1.8781645569620253,
"grad_norm": 0.8828125,
"learning_rate": 9.162970674771177e-08,
"loss": 0.9087,
"step": 223
},
{
"epoch": 1.886603375527426,
"grad_norm": 0.984375,
"learning_rate": 7.81104288863721e-08,
"loss": 0.8867,
"step": 224
},
{
"epoch": 1.895042194092827,
"grad_norm": 1.1015625,
"learning_rate": 6.566184295904777e-08,
"loss": 0.9037,
"step": 225
},
{
"epoch": 1.903481012658228,
"grad_norm": 0.80078125,
"learning_rate": 5.4286656990847897e-08,
"loss": 0.9141,
"step": 226
},
{
"epoch": 1.9119198312236287,
"grad_norm": 1.734375,
"learning_rate": 4.398734550292716e-08,
"loss": 0.9037,
"step": 227
},
{
"epoch": 1.9203586497890295,
"grad_norm": 1.3359375,
"learning_rate": 3.476614897418573e-08,
"loss": 0.8929,
"step": 228
},
{
"epoch": 1.9287974683544302,
"grad_norm": 0.88671875,
"learning_rate": 2.6625073353884756e-08,
"loss": 0.8782,
"step": 229
},
{
"epoch": 1.9372362869198312,
"grad_norm": 0.71484375,
"learning_rate": 1.9565889625275945e-08,
"loss": 0.8863,
"step": 230
},
{
"epoch": 1.9456751054852321,
"grad_norm": 0.7265625,
"learning_rate": 1.3590133420350315e-08,
"loss": 0.9191,
"step": 231
},
{
"epoch": 1.9541139240506329,
"grad_norm": 0.76953125,
"learning_rate": 8.699104685779835e-09,
"loss": 0.914,
"step": 232
},
{
"epoch": 1.9625527426160336,
"grad_norm": 0.74609375,
"learning_rate": 4.89386740013198e-09,
"loss": 0.9168,
"step": 233
},
{
"epoch": 1.9709915611814346,
"grad_norm": 2.171875,
"learning_rate": 2.1752493424148647e-09,
"loss": 0.9424,
"step": 234
},
{
"epoch": 1.9794303797468356,
"grad_norm": 0.99609375,
"learning_rate": 5.438419120062933e-10,
"loss": 0.9252,
"step": 235
},
{
"epoch": 1.9878691983122363,
"grad_norm": 0.859375,
"learning_rate": 0.0,
"loss": 0.9248,
"step": 236
}
],
"logging_steps": 1,
"max_steps": 236,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 59,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.847994502064636e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}