FuturisticVibes's picture
Upload folder using huggingface_hub
0738600 verified
raw
history blame
41.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.9409282700421944,
"eval_steps": 30,
"global_step": 236,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.016877637130801686,
"grad_norm": 0.08447265625,
"learning_rate": 3e-06,
"loss": 1.1751,
"step": 1
},
{
"epoch": 0.016877637130801686,
"eval_loss": 1.185997486114502,
"eval_runtime": 72.8223,
"eval_samples_per_second": 14.144,
"eval_steps_per_second": 14.144,
"step": 1
},
{
"epoch": 0.03375527426160337,
"grad_norm": 0.08544921875,
"learning_rate": 6e-06,
"loss": 1.1683,
"step": 2
},
{
"epoch": 0.05063291139240506,
"grad_norm": 0.0830078125,
"learning_rate": 9e-06,
"loss": 1.1737,
"step": 3
},
{
"epoch": 0.06751054852320675,
"grad_norm": 0.08544921875,
"learning_rate": 1.2e-05,
"loss": 1.1889,
"step": 4
},
{
"epoch": 0.08438818565400844,
"grad_norm": 0.0849609375,
"learning_rate": 1.5e-05,
"loss": 1.1619,
"step": 5
},
{
"epoch": 0.10126582278481013,
"grad_norm": 0.0869140625,
"learning_rate": 1.8e-05,
"loss": 1.1815,
"step": 6
},
{
"epoch": 0.11814345991561181,
"grad_norm": 0.08447265625,
"learning_rate": 2.1e-05,
"loss": 1.1726,
"step": 7
},
{
"epoch": 0.1350210970464135,
"grad_norm": 0.08740234375,
"learning_rate": 2.4e-05,
"loss": 1.1701,
"step": 8
},
{
"epoch": 0.1518987341772152,
"grad_norm": 0.08642578125,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.1818,
"step": 9
},
{
"epoch": 0.16877637130801687,
"grad_norm": 0.08935546875,
"learning_rate": 3e-05,
"loss": 1.1896,
"step": 10
},
{
"epoch": 0.18565400843881857,
"grad_norm": 0.0888671875,
"learning_rate": 2.999855077059572e-05,
"loss": 1.1873,
"step": 11
},
{
"epoch": 0.20253164556962025,
"grad_norm": 0.08984375,
"learning_rate": 2.9994203362418313e-05,
"loss": 1.1838,
"step": 12
},
{
"epoch": 0.21940928270042195,
"grad_norm": 0.0859375,
"learning_rate": 2.998695861552002e-05,
"loss": 1.1569,
"step": 13
},
{
"epoch": 0.23628691983122363,
"grad_norm": 0.08642578125,
"learning_rate": 2.9976817929807542e-05,
"loss": 1.1595,
"step": 14
},
{
"epoch": 0.25316455696202533,
"grad_norm": 0.078125,
"learning_rate": 2.996378326477153e-05,
"loss": 1.1348,
"step": 15
},
{
"epoch": 0.270042194092827,
"grad_norm": 0.07470703125,
"learning_rate": 2.9947857139107964e-05,
"loss": 1.1434,
"step": 16
},
{
"epoch": 0.2869198312236287,
"grad_norm": 0.140625,
"learning_rate": 2.992904263023146e-05,
"loss": 1.8213,
"step": 17
},
{
"epoch": 0.3037974683544304,
"grad_norm": 0.06787109375,
"learning_rate": 2.990734337368062e-05,
"loss": 1.1289,
"step": 18
},
{
"epoch": 0.3206751054852321,
"grad_norm": 0.0654296875,
"learning_rate": 2.9882763562415518e-05,
"loss": 1.1106,
"step": 19
},
{
"epoch": 0.33755274261603374,
"grad_norm": 0.06640625,
"learning_rate": 2.9855307946007532e-05,
"loss": 1.1381,
"step": 20
},
{
"epoch": 0.35443037974683544,
"grad_norm": 0.064453125,
"learning_rate": 2.982498182972154e-05,
"loss": 1.1192,
"step": 21
},
{
"epoch": 0.37130801687763715,
"grad_norm": 0.0615234375,
"learning_rate": 2.9791791073490795e-05,
"loss": 1.1105,
"step": 22
},
{
"epoch": 0.3881856540084388,
"grad_norm": 0.061767578125,
"learning_rate": 2.9755742090784617e-05,
"loss": 1.1207,
"step": 23
},
{
"epoch": 0.4050632911392405,
"grad_norm": 0.0634765625,
"learning_rate": 2.9716841847369106e-05,
"loss": 1.1083,
"step": 24
},
{
"epoch": 0.4219409282700422,
"grad_norm": 0.058349609375,
"learning_rate": 2.967509785996114e-05,
"loss": 1.1007,
"step": 25
},
{
"epoch": 0.4388185654008439,
"grad_norm": 0.0615234375,
"learning_rate": 2.963051819477592e-05,
"loss": 1.0842,
"step": 26
},
{
"epoch": 0.45569620253164556,
"grad_norm": 0.0625,
"learning_rate": 2.958311146596833e-05,
"loss": 1.0961,
"step": 27
},
{
"epoch": 0.47257383966244726,
"grad_norm": 0.05908203125,
"learning_rate": 2.953288683396841e-05,
"loss": 1.109,
"step": 28
},
{
"epoch": 0.48945147679324896,
"grad_norm": 0.061767578125,
"learning_rate": 2.9479854003711298e-05,
"loss": 1.0789,
"step": 29
},
{
"epoch": 0.5063291139240507,
"grad_norm": 0.06103515625,
"learning_rate": 2.9424023222761938e-05,
"loss": 1.1007,
"step": 30
},
{
"epoch": 0.5063291139240507,
"eval_loss": 1.091182827949524,
"eval_runtime": 74.0135,
"eval_samples_per_second": 13.916,
"eval_steps_per_second": 13.916,
"step": 30
},
{
"epoch": 0.5232067510548524,
"grad_norm": 0.059814453125,
"learning_rate": 2.9365405279334904e-05,
"loss": 1.0756,
"step": 31
},
{
"epoch": 0.540084388185654,
"grad_norm": 0.056396484375,
"learning_rate": 2.930401150020983e-05,
"loss": 1.0939,
"step": 32
},
{
"epoch": 0.5569620253164557,
"grad_norm": 0.05712890625,
"learning_rate": 2.9239853748542717e-05,
"loss": 1.0901,
"step": 33
},
{
"epoch": 0.5738396624472574,
"grad_norm": 0.054931640625,
"learning_rate": 2.9172944421573587e-05,
"loss": 1.0873,
"step": 34
},
{
"epoch": 0.5907172995780591,
"grad_norm": 0.0546875,
"learning_rate": 2.9103296448230986e-05,
"loss": 1.0584,
"step": 35
},
{
"epoch": 0.6075949367088608,
"grad_norm": 0.0556640625,
"learning_rate": 2.9030923286633703e-05,
"loss": 1.0692,
"step": 36
},
{
"epoch": 0.6244725738396625,
"grad_norm": 0.16015625,
"learning_rate": 2.8955838921490252e-05,
"loss": 1.782,
"step": 37
},
{
"epoch": 0.6413502109704642,
"grad_norm": 0.052001953125,
"learning_rate": 2.8878057861396606e-05,
"loss": 1.0667,
"step": 38
},
{
"epoch": 0.6582278481012658,
"grad_norm": 0.052001953125,
"learning_rate": 2.8797595136032675e-05,
"loss": 1.0656,
"step": 39
},
{
"epoch": 0.6751054852320675,
"grad_norm": 0.052734375,
"learning_rate": 2.8714466293258142e-05,
"loss": 1.0736,
"step": 40
},
{
"epoch": 0.6919831223628692,
"grad_norm": 0.053955078125,
"learning_rate": 2.8628687396108107e-05,
"loss": 1.0638,
"step": 41
},
{
"epoch": 0.7088607594936709,
"grad_norm": 0.05224609375,
"learning_rate": 2.8540275019689237e-05,
"loss": 1.0746,
"step": 42
},
{
"epoch": 0.7257383966244726,
"grad_norm": 0.051513671875,
"learning_rate": 2.8449246247976947e-05,
"loss": 1.0608,
"step": 43
},
{
"epoch": 0.7426160337552743,
"grad_norm": 0.052001953125,
"learning_rate": 2.835561867051426e-05,
"loss": 1.0619,
"step": 44
},
{
"epoch": 0.759493670886076,
"grad_norm": 0.051025390625,
"learning_rate": 2.825941037901294e-05,
"loss": 1.048,
"step": 45
},
{
"epoch": 0.7763713080168776,
"grad_norm": 0.05078125,
"learning_rate": 2.816063996385765e-05,
"loss": 1.0761,
"step": 46
},
{
"epoch": 0.7932489451476793,
"grad_norm": 0.0498046875,
"learning_rate": 2.805932651051372e-05,
"loss": 1.0443,
"step": 47
},
{
"epoch": 0.810126582278481,
"grad_norm": 0.051025390625,
"learning_rate": 2.7955489595839228e-05,
"loss": 1.0527,
"step": 48
},
{
"epoch": 0.8270042194092827,
"grad_norm": 0.052734375,
"learning_rate": 2.784914928430218e-05,
"loss": 1.0498,
"step": 49
},
{
"epoch": 0.8438818565400844,
"grad_norm": 0.049560546875,
"learning_rate": 2.7740326124103416e-05,
"loss": 1.0537,
"step": 50
},
{
"epoch": 0.8607594936708861,
"grad_norm": 0.053466796875,
"learning_rate": 2.762904114320609e-05,
"loss": 1.0326,
"step": 51
},
{
"epoch": 0.8776371308016878,
"grad_norm": 0.04931640625,
"learning_rate": 2.751531584527241e-05,
"loss": 1.043,
"step": 52
},
{
"epoch": 0.8945147679324894,
"grad_norm": 0.05126953125,
"learning_rate": 2.7399172205508476e-05,
"loss": 1.0463,
"step": 53
},
{
"epoch": 0.9113924050632911,
"grad_norm": 0.0517578125,
"learning_rate": 2.7280632666418013e-05,
"loss": 1.0476,
"step": 54
},
{
"epoch": 0.9282700421940928,
"grad_norm": 0.053466796875,
"learning_rate": 2.715972013346576e-05,
"loss": 1.0467,
"step": 55
},
{
"epoch": 0.9451476793248945,
"grad_norm": 0.0498046875,
"learning_rate": 2.703645797065147e-05,
"loss": 1.0467,
"step": 56
},
{
"epoch": 0.9620253164556962,
"grad_norm": 0.05078125,
"learning_rate": 2.6910869995995247e-05,
"loss": 1.05,
"step": 57
},
{
"epoch": 0.9789029535864979,
"grad_norm": 0.053955078125,
"learning_rate": 2.678298047693518e-05,
"loss": 1.0453,
"step": 58
},
{
"epoch": 0.9957805907172996,
"grad_norm": 0.050048828125,
"learning_rate": 2.6652814125638142e-05,
"loss": 1.0348,
"step": 59
},
{
"epoch": 1.0126582278481013,
"grad_norm": 0.052490234375,
"learning_rate": 2.652039609422463e-05,
"loss": 1.0418,
"step": 60
},
{
"epoch": 1.0126582278481013,
"eval_loss": 1.0428293943405151,
"eval_runtime": 74.0734,
"eval_samples_per_second": 13.905,
"eval_steps_per_second": 13.905,
"step": 60
},
{
"epoch": 1.0147679324894514,
"grad_norm": 0.0732421875,
"learning_rate": 2.638575196990862e-05,
"loss": 1.0194,
"step": 61
},
{
"epoch": 1.0316455696202531,
"grad_norm": 0.049560546875,
"learning_rate": 2.624890777005332e-05,
"loss": 1.0365,
"step": 62
},
{
"epoch": 1.0485232067510548,
"grad_norm": 0.05126953125,
"learning_rate": 2.6109889937143828e-05,
"loss": 1.0426,
"step": 63
},
{
"epoch": 1.0654008438818565,
"grad_norm": 0.05126953125,
"learning_rate": 2.5968725333677628e-05,
"loss": 1.043,
"step": 64
},
{
"epoch": 1.0822784810126582,
"grad_norm": 0.051513671875,
"learning_rate": 2.582544123697395e-05,
"loss": 1.0243,
"step": 65
},
{
"epoch": 1.09915611814346,
"grad_norm": 0.0517578125,
"learning_rate": 2.568006533390295e-05,
"loss": 1.0258,
"step": 66
},
{
"epoch": 1.1160337552742616,
"grad_norm": 0.050537109375,
"learning_rate": 2.5532625715535733e-05,
"loss": 1.0248,
"step": 67
},
{
"epoch": 1.1329113924050633,
"grad_norm": 0.0498046875,
"learning_rate": 2.5383150871716342e-05,
"loss": 1.0083,
"step": 68
},
{
"epoch": 1.149789029535865,
"grad_norm": 0.05224609375,
"learning_rate": 2.5231669685556636e-05,
"loss": 1.0207,
"step": 69
},
{
"epoch": 1.1666666666666667,
"grad_norm": 0.051513671875,
"learning_rate": 2.507821142785516e-05,
"loss": 1.0435,
"step": 70
},
{
"epoch": 1.1835443037974684,
"grad_norm": 0.05224609375,
"learning_rate": 2.4922805751441174e-05,
"loss": 1.0354,
"step": 71
},
{
"epoch": 1.20042194092827,
"grad_norm": 0.054443359375,
"learning_rate": 2.4765482685444786e-05,
"loss": 1.0266,
"step": 72
},
{
"epoch": 1.2172995780590719,
"grad_norm": 0.05126953125,
"learning_rate": 2.460627262949443e-05,
"loss": 1.0411,
"step": 73
},
{
"epoch": 1.2341772151898733,
"grad_norm": 0.05126953125,
"learning_rate": 2.4445206347842714e-05,
"loss": 1.0224,
"step": 74
},
{
"epoch": 1.251054852320675,
"grad_norm": 0.052978515625,
"learning_rate": 2.428231496342181e-05,
"loss": 1.0253,
"step": 75
},
{
"epoch": 1.2679324894514767,
"grad_norm": 0.05322265625,
"learning_rate": 2.4117629951829602e-05,
"loss": 1.0298,
"step": 76
},
{
"epoch": 1.2848101265822784,
"grad_norm": 0.052490234375,
"learning_rate": 2.395118313524758e-05,
"loss": 1.0239,
"step": 77
},
{
"epoch": 1.3016877637130801,
"grad_norm": 0.0537109375,
"learning_rate": 2.3783006676291866e-05,
"loss": 1.0212,
"step": 78
},
{
"epoch": 1.3185654008438819,
"grad_norm": 0.052734375,
"learning_rate": 2.361313307179837e-05,
"loss": 1.0371,
"step": 79
},
{
"epoch": 1.3354430379746836,
"grad_norm": 0.05126953125,
"learning_rate": 2.3441595146543458e-05,
"loss": 1.0314,
"step": 80
},
{
"epoch": 1.3523206751054853,
"grad_norm": 0.052001953125,
"learning_rate": 2.3268426046901153e-05,
"loss": 1.0195,
"step": 81
},
{
"epoch": 1.369198312236287,
"grad_norm": 0.052978515625,
"learning_rate": 2.3093659234438266e-05,
"loss": 1.0219,
"step": 82
},
{
"epoch": 1.3860759493670887,
"grad_norm": 0.054931640625,
"learning_rate": 2.291732847944861e-05,
"loss": 1.0293,
"step": 83
},
{
"epoch": 1.4029535864978904,
"grad_norm": 0.052734375,
"learning_rate": 2.2739467854427512e-05,
"loss": 0.9992,
"step": 84
},
{
"epoch": 1.4198312236286919,
"grad_norm": 0.05224609375,
"learning_rate": 2.2560111727488e-05,
"loss": 1.0254,
"step": 85
},
{
"epoch": 1.4367088607594938,
"grad_norm": 0.0546875,
"learning_rate": 2.237929475571979e-05,
"loss": 1.0148,
"step": 86
},
{
"epoch": 1.4535864978902953,
"grad_norm": 0.055419921875,
"learning_rate": 2.219705187849254e-05,
"loss": 1.0228,
"step": 87
},
{
"epoch": 1.4704641350210972,
"grad_norm": 0.05810546875,
"learning_rate": 2.2013418310704422e-05,
"loss": 1.021,
"step": 88
},
{
"epoch": 1.4873417721518987,
"grad_norm": 0.0537109375,
"learning_rate": 2.1828429535977585e-05,
"loss": 1.0352,
"step": 89
},
{
"epoch": 1.5042194092827004,
"grad_norm": 0.054931640625,
"learning_rate": 2.1642121299801594e-05,
"loss": 1.0105,
"step": 90
},
{
"epoch": 1.5042194092827004,
"eval_loss": 1.0232045650482178,
"eval_runtime": 74.0589,
"eval_samples_per_second": 13.908,
"eval_steps_per_second": 13.908,
"step": 90
},
{
"epoch": 1.521097046413502,
"grad_norm": 0.054931640625,
"learning_rate": 2.1454529602626336e-05,
"loss": 1.0051,
"step": 91
},
{
"epoch": 1.5379746835443038,
"grad_norm": 0.0546875,
"learning_rate": 2.126569069290562e-05,
"loss": 1.023,
"step": 92
},
{
"epoch": 1.5548523206751055,
"grad_norm": 0.0546875,
"learning_rate": 2.107564106009286e-05,
"loss": 1.012,
"step": 93
},
{
"epoch": 1.5717299578059072,
"grad_norm": 0.0546875,
"learning_rate": 2.0884417427590217e-05,
"loss": 1.0136,
"step": 94
},
{
"epoch": 1.5886075949367089,
"grad_norm": 0.0546875,
"learning_rate": 2.0692056745652483e-05,
"loss": 1.0194,
"step": 95
},
{
"epoch": 1.6054852320675106,
"grad_norm": 0.0556640625,
"learning_rate": 2.0498596184247196e-05,
"loss": 1.0089,
"step": 96
},
{
"epoch": 1.6223628691983123,
"grad_norm": 0.054931640625,
"learning_rate": 2.030407312587224e-05,
"loss": 1.0226,
"step": 97
},
{
"epoch": 1.6392405063291138,
"grad_norm": 0.058349609375,
"learning_rate": 2.010852515833242e-05,
"loss": 1.0219,
"step": 98
},
{
"epoch": 1.6561181434599157,
"grad_norm": 0.0556640625,
"learning_rate": 1.9911990067476336e-05,
"loss": 1.0035,
"step": 99
},
{
"epoch": 1.6729957805907172,
"grad_norm": 0.055908203125,
"learning_rate": 1.9714505829895004e-05,
"loss": 1.0052,
"step": 100
},
{
"epoch": 1.689873417721519,
"grad_norm": 0.05712890625,
"learning_rate": 1.951611060558363e-05,
"loss": 1.0175,
"step": 101
},
{
"epoch": 1.7067510548523206,
"grad_norm": 0.056396484375,
"learning_rate": 1.9316842730567902e-05,
"loss": 1.0099,
"step": 102
},
{
"epoch": 1.7236286919831225,
"grad_norm": 0.05615234375,
"learning_rate": 1.9116740709496334e-05,
"loss": 0.998,
"step": 103
},
{
"epoch": 1.740506329113924,
"grad_norm": 0.05615234375,
"learning_rate": 1.8915843208199967e-05,
"loss": 0.996,
"step": 104
},
{
"epoch": 1.7573839662447257,
"grad_norm": 0.058837890625,
"learning_rate": 1.8714189046220946e-05,
"loss": 1.009,
"step": 105
},
{
"epoch": 1.7742616033755274,
"grad_norm": 0.059326171875,
"learning_rate": 1.851181718931141e-05,
"loss": 1.0127,
"step": 106
},
{
"epoch": 1.7911392405063291,
"grad_norm": 0.0556640625,
"learning_rate": 1.830876674190411e-05,
"loss": 1.0107,
"step": 107
},
{
"epoch": 1.8080168776371308,
"grad_norm": 0.06201171875,
"learning_rate": 1.8105076939556238e-05,
"loss": 1.0264,
"step": 108
},
{
"epoch": 1.8248945147679325,
"grad_norm": 0.056884765625,
"learning_rate": 1.790078714136792e-05,
"loss": 1.0068,
"step": 109
},
{
"epoch": 1.8417721518987342,
"grad_norm": 0.056640625,
"learning_rate": 1.769593682237682e-05,
"loss": 1.0094,
"step": 110
},
{
"epoch": 1.8586497890295357,
"grad_norm": 0.057861328125,
"learning_rate": 1.7490565565930382e-05,
"loss": 1.0135,
"step": 111
},
{
"epoch": 1.8755274261603376,
"grad_norm": 0.05859375,
"learning_rate": 1.7284713056037074e-05,
"loss": 0.993,
"step": 112
},
{
"epoch": 1.8924050632911391,
"grad_norm": 0.056884765625,
"learning_rate": 1.7078419069698283e-05,
"loss": 1.015,
"step": 113
},
{
"epoch": 1.909282700421941,
"grad_norm": 0.055908203125,
"learning_rate": 1.687172346922213e-05,
"loss": 1.0043,
"step": 114
},
{
"epoch": 1.9261603375527425,
"grad_norm": 0.05859375,
"learning_rate": 1.6664666194520873e-05,
"loss": 0.9959,
"step": 115
},
{
"epoch": 1.9430379746835444,
"grad_norm": 0.0625,
"learning_rate": 1.645728725539329e-05,
"loss": 1.0177,
"step": 116
},
{
"epoch": 1.959915611814346,
"grad_norm": 0.05810546875,
"learning_rate": 1.6249626723793572e-05,
"loss": 1.033,
"step": 117
},
{
"epoch": 1.9767932489451476,
"grad_norm": 0.059326171875,
"learning_rate": 1.6041724726088187e-05,
"loss": 1.0155,
"step": 118
},
{
"epoch": 1.9936708860759493,
"grad_norm": 0.060791015625,
"learning_rate": 1.5833621435302247e-05,
"loss": 1.0167,
"step": 119
},
{
"epoch": 2.010548523206751,
"grad_norm": 0.0595703125,
"learning_rate": 1.5625357063356825e-05,
"loss": 1.0082,
"step": 120
},
{
"epoch": 2.010548523206751,
"eval_loss": 1.0127062797546387,
"eval_runtime": 74.0711,
"eval_samples_per_second": 13.906,
"eval_steps_per_second": 13.906,
"step": 120
},
{
"epoch": 2.0147679324894514,
"grad_norm": 0.1865234375,
"learning_rate": 1.541697185329881e-05,
"loss": 1.6592,
"step": 121
},
{
"epoch": 2.0316455696202533,
"grad_norm": 0.0595703125,
"learning_rate": 1.5208506071524727e-05,
"loss": 1.0041,
"step": 122
},
{
"epoch": 2.048523206751055,
"grad_norm": 0.059326171875,
"learning_rate": 1.5e-05,
"loss": 1.0116,
"step": 123
},
{
"epoch": 2.0654008438818567,
"grad_norm": 0.05859375,
"learning_rate": 1.4791493928475275e-05,
"loss": 1.0026,
"step": 124
},
{
"epoch": 2.0822784810126582,
"grad_norm": 0.05810546875,
"learning_rate": 1.4583028146701191e-05,
"loss": 1.0122,
"step": 125
},
{
"epoch": 2.0991561181434597,
"grad_norm": 0.06005859375,
"learning_rate": 1.437464293664318e-05,
"loss": 1.0024,
"step": 126
},
{
"epoch": 2.1160337552742616,
"grad_norm": 0.060546875,
"learning_rate": 1.4166378564697757e-05,
"loss": 1.0092,
"step": 127
},
{
"epoch": 2.132911392405063,
"grad_norm": 0.05908203125,
"learning_rate": 1.3958275273911812e-05,
"loss": 1.0048,
"step": 128
},
{
"epoch": 2.149789029535865,
"grad_norm": 0.058837890625,
"learning_rate": 1.375037327620643e-05,
"loss": 0.9921,
"step": 129
},
{
"epoch": 2.1666666666666665,
"grad_norm": 0.06005859375,
"learning_rate": 1.3542712744606712e-05,
"loss": 1.0117,
"step": 130
},
{
"epoch": 2.1835443037974684,
"grad_norm": 0.05859375,
"learning_rate": 1.3335333805479126e-05,
"loss": 0.9965,
"step": 131
},
{
"epoch": 2.20042194092827,
"grad_norm": 0.059814453125,
"learning_rate": 1.3128276530777874e-05,
"loss": 1.0108,
"step": 132
},
{
"epoch": 2.217299578059072,
"grad_norm": 0.060791015625,
"learning_rate": 1.292158093030172e-05,
"loss": 1.0029,
"step": 133
},
{
"epoch": 2.2341772151898733,
"grad_norm": 0.058349609375,
"learning_rate": 1.2715286943962925e-05,
"loss": 0.9958,
"step": 134
},
{
"epoch": 2.2510548523206753,
"grad_norm": 0.05908203125,
"learning_rate": 1.2509434434069625e-05,
"loss": 1.0054,
"step": 135
},
{
"epoch": 2.2679324894514767,
"grad_norm": 0.0576171875,
"learning_rate": 1.2304063177623182e-05,
"loss": 0.9837,
"step": 136
},
{
"epoch": 2.2848101265822787,
"grad_norm": 0.060302734375,
"learning_rate": 1.2099212858632083e-05,
"loss": 1.0014,
"step": 137
},
{
"epoch": 2.30168776371308,
"grad_norm": 0.0595703125,
"learning_rate": 1.1894923060443763e-05,
"loss": 0.9816,
"step": 138
},
{
"epoch": 2.318565400843882,
"grad_norm": 0.0595703125,
"learning_rate": 1.169123325809589e-05,
"loss": 1.0021,
"step": 139
},
{
"epoch": 2.3354430379746836,
"grad_norm": 0.05859375,
"learning_rate": 1.1488182810688593e-05,
"loss": 1.0005,
"step": 140
},
{
"epoch": 2.352320675105485,
"grad_norm": 0.06103515625,
"learning_rate": 1.1285810953779057e-05,
"loss": 1.0167,
"step": 141
},
{
"epoch": 2.369198312236287,
"grad_norm": 0.059814453125,
"learning_rate": 1.1084156791800036e-05,
"loss": 1.0146,
"step": 142
},
{
"epoch": 2.3860759493670884,
"grad_norm": 0.05859375,
"learning_rate": 1.0883259290503665e-05,
"loss": 1.0024,
"step": 143
},
{
"epoch": 2.4029535864978904,
"grad_norm": 0.0576171875,
"learning_rate": 1.0683157269432097e-05,
"loss": 0.9959,
"step": 144
},
{
"epoch": 2.419831223628692,
"grad_norm": 0.060546875,
"learning_rate": 1.0483889394416373e-05,
"loss": 1.0059,
"step": 145
},
{
"epoch": 2.4367088607594938,
"grad_norm": 0.06396484375,
"learning_rate": 1.0285494170104996e-05,
"loss": 0.983,
"step": 146
},
{
"epoch": 2.4535864978902953,
"grad_norm": 0.06005859375,
"learning_rate": 1.0088009932523664e-05,
"loss": 1.0116,
"step": 147
},
{
"epoch": 2.470464135021097,
"grad_norm": 0.061279296875,
"learning_rate": 9.891474841667585e-06,
"loss": 1.0136,
"step": 148
},
{
"epoch": 2.4873417721518987,
"grad_norm": 0.057861328125,
"learning_rate": 9.695926874127765e-06,
"loss": 0.9937,
"step": 149
},
{
"epoch": 2.5042194092827,
"grad_norm": 0.0595703125,
"learning_rate": 9.501403815752813e-06,
"loss": 0.9946,
"step": 150
},
{
"epoch": 2.5042194092827,
"eval_loss": 1.0074498653411865,
"eval_runtime": 74.0482,
"eval_samples_per_second": 13.91,
"eval_steps_per_second": 13.91,
"step": 150
},
{
"epoch": 2.521097046413502,
"grad_norm": 0.060302734375,
"learning_rate": 9.307943254347521e-06,
"loss": 1.0043,
"step": 151
},
{
"epoch": 2.537974683544304,
"grad_norm": 0.06201171875,
"learning_rate": 9.115582572409789e-06,
"loss": 1.0125,
"step": 152
},
{
"epoch": 2.5548523206751055,
"grad_norm": 0.05859375,
"learning_rate": 8.92435893990714e-06,
"loss": 0.9753,
"step": 153
},
{
"epoch": 2.571729957805907,
"grad_norm": 0.060546875,
"learning_rate": 8.734309307094382e-06,
"loss": 0.9959,
"step": 154
},
{
"epoch": 2.588607594936709,
"grad_norm": 0.061279296875,
"learning_rate": 8.545470397373665e-06,
"loss": 1.0158,
"step": 155
},
{
"epoch": 2.605485232067511,
"grad_norm": 0.062255859375,
"learning_rate": 8.357878700198407e-06,
"loss": 1.0001,
"step": 156
},
{
"epoch": 2.6223628691983123,
"grad_norm": 0.060546875,
"learning_rate": 8.171570464022419e-06,
"loss": 0.9963,
"step": 157
},
{
"epoch": 2.6392405063291138,
"grad_norm": 0.0595703125,
"learning_rate": 7.986581689295577e-06,
"loss": 0.968,
"step": 158
},
{
"epoch": 2.6561181434599157,
"grad_norm": 0.059326171875,
"learning_rate": 7.802948121507462e-06,
"loss": 0.9872,
"step": 159
},
{
"epoch": 2.672995780590717,
"grad_norm": 0.0625,
"learning_rate": 7.620705244280208e-06,
"loss": 1.0181,
"step": 160
},
{
"epoch": 2.689873417721519,
"grad_norm": 0.06298828125,
"learning_rate": 7.439888272512004e-06,
"loss": 1.0057,
"step": 161
},
{
"epoch": 2.7067510548523206,
"grad_norm": 0.059814453125,
"learning_rate": 7.260532145572487e-06,
"loss": 0.9985,
"step": 162
},
{
"epoch": 2.7236286919831225,
"grad_norm": 0.059814453125,
"learning_rate": 7.082671520551391e-06,
"loss": 0.9973,
"step": 163
},
{
"epoch": 2.740506329113924,
"grad_norm": 0.06103515625,
"learning_rate": 6.906340765561734e-06,
"loss": 0.991,
"step": 164
},
{
"epoch": 2.757383966244726,
"grad_norm": 0.060546875,
"learning_rate": 6.731573953098851e-06,
"loss": 0.9979,
"step": 165
},
{
"epoch": 2.7742616033755274,
"grad_norm": 0.060546875,
"learning_rate": 6.558404853456545e-06,
"loss": 1.0096,
"step": 166
},
{
"epoch": 2.791139240506329,
"grad_norm": 0.060302734375,
"learning_rate": 6.38686692820163e-06,
"loss": 0.9981,
"step": 167
},
{
"epoch": 2.808016877637131,
"grad_norm": 0.0595703125,
"learning_rate": 6.2169933237081386e-06,
"loss": 1.0169,
"step": 168
},
{
"epoch": 2.8248945147679327,
"grad_norm": 0.0615234375,
"learning_rate": 6.048816864752422e-06,
"loss": 0.9934,
"step": 169
},
{
"epoch": 2.8417721518987342,
"grad_norm": 0.05859375,
"learning_rate": 5.882370048170403e-06,
"loss": 0.9913,
"step": 170
},
{
"epoch": 2.8586497890295357,
"grad_norm": 0.06005859375,
"learning_rate": 5.71768503657819e-06,
"loss": 1.0107,
"step": 171
},
{
"epoch": 2.8755274261603376,
"grad_norm": 0.060791015625,
"learning_rate": 5.55479365215729e-06,
"loss": 1.0098,
"step": 172
},
{
"epoch": 2.892405063291139,
"grad_norm": 0.0595703125,
"learning_rate": 5.393727370505569e-06,
"loss": 1.0123,
"step": 173
},
{
"epoch": 2.909282700421941,
"grad_norm": 0.060546875,
"learning_rate": 5.234517314555213e-06,
"loss": 0.9837,
"step": 174
},
{
"epoch": 2.9261603375527425,
"grad_norm": 0.060791015625,
"learning_rate": 5.077194248558827e-06,
"loss": 0.9865,
"step": 175
},
{
"epoch": 2.9430379746835444,
"grad_norm": 0.058349609375,
"learning_rate": 4.921788572144841e-06,
"loss": 0.995,
"step": 176
},
{
"epoch": 2.959915611814346,
"grad_norm": 0.06201171875,
"learning_rate": 4.768330314443367e-06,
"loss": 1.0009,
"step": 177
},
{
"epoch": 2.976793248945148,
"grad_norm": 0.060546875,
"learning_rate": 4.616849128283658e-06,
"loss": 1.0016,
"step": 178
},
{
"epoch": 2.9936708860759493,
"grad_norm": 0.0625,
"learning_rate": 4.4673742844642716e-06,
"loss": 0.9979,
"step": 179
},
{
"epoch": 3.010548523206751,
"grad_norm": 0.062255859375,
"learning_rate": 4.319934666097055e-06,
"loss": 0.9826,
"step": 180
},
{
"epoch": 3.010548523206751,
"eval_loss": 1.0056920051574707,
"eval_runtime": 74.0404,
"eval_samples_per_second": 13.911,
"eval_steps_per_second": 13.911,
"step": 180
},
{
"epoch": 3.0126582278481013,
"grad_norm": 0.06396484375,
"learning_rate": 4.174558763026048e-06,
"loss": 1.0021,
"step": 181
},
{
"epoch": 3.029535864978903,
"grad_norm": 0.06201171875,
"learning_rate": 4.031274666322372e-06,
"loss": 0.9997,
"step": 182
},
{
"epoch": 3.0464135021097047,
"grad_norm": 0.0595703125,
"learning_rate": 3.8901100628561755e-06,
"loss": 1.0048,
"step": 183
},
{
"epoch": 3.0632911392405062,
"grad_norm": 0.060302734375,
"learning_rate": 3.7510922299466818e-06,
"loss": 0.9874,
"step": 184
},
{
"epoch": 3.080168776371308,
"grad_norm": 0.05810546875,
"learning_rate": 3.6142480300913805e-06,
"loss": 1.0054,
"step": 185
},
{
"epoch": 3.0970464135021096,
"grad_norm": 0.059814453125,
"learning_rate": 3.4796039057753703e-06,
"loss": 0.9991,
"step": 186
},
{
"epoch": 3.1139240506329116,
"grad_norm": 0.05859375,
"learning_rate": 3.3471858743618615e-06,
"loss": 0.9941,
"step": 187
},
{
"epoch": 3.130801687763713,
"grad_norm": 0.061767578125,
"learning_rate": 3.217019523064825e-06,
"loss": 1.0032,
"step": 188
},
{
"epoch": 3.147679324894515,
"grad_norm": 0.060791015625,
"learning_rate": 3.089130004004754e-06,
"loss": 0.9965,
"step": 189
},
{
"epoch": 3.1645569620253164,
"grad_norm": 0.05908203125,
"learning_rate": 2.96354202934853e-06,
"loss": 0.9954,
"step": 190
},
{
"epoch": 3.181434599156118,
"grad_norm": 0.0595703125,
"learning_rate": 2.8402798665342412e-06,
"loss": 0.9938,
"step": 191
},
{
"epoch": 3.19831223628692,
"grad_norm": 0.0615234375,
"learning_rate": 2.7193673335819893e-06,
"loss": 0.9967,
"step": 192
},
{
"epoch": 3.2151898734177213,
"grad_norm": 0.061279296875,
"learning_rate": 2.600827794491524e-06,
"loss": 1.0009,
"step": 193
},
{
"epoch": 3.2320675105485233,
"grad_norm": 0.0595703125,
"learning_rate": 2.4846841547275916e-06,
"loss": 0.9902,
"step": 194
},
{
"epoch": 3.2489451476793247,
"grad_norm": 0.0595703125,
"learning_rate": 2.3709588567939118e-06,
"loss": 0.9915,
"step": 195
},
{
"epoch": 3.2658227848101267,
"grad_norm": 0.061767578125,
"learning_rate": 2.259673875896585e-06,
"loss": 0.993,
"step": 196
},
{
"epoch": 3.282700421940928,
"grad_norm": 0.060302734375,
"learning_rate": 2.150850715697823e-06,
"loss": 1.0027,
"step": 197
},
{
"epoch": 3.29957805907173,
"grad_norm": 0.06005859375,
"learning_rate": 2.044510404160774e-06,
"loss": 0.9874,
"step": 198
},
{
"epoch": 3.3164556962025316,
"grad_norm": 0.1572265625,
"learning_rate": 1.9406734894862848e-06,
"loss": 1.6607,
"step": 199
},
{
"epoch": 3.3333333333333335,
"grad_norm": 0.0595703125,
"learning_rate": 1.8393600361423534e-06,
"loss": 1.002,
"step": 200
},
{
"epoch": 3.350210970464135,
"grad_norm": 0.06103515625,
"learning_rate": 1.7405896209870665e-06,
"loss": 1.0005,
"step": 201
},
{
"epoch": 3.367088607594937,
"grad_norm": 0.060302734375,
"learning_rate": 1.6443813294857452e-06,
"loss": 0.9842,
"step": 202
},
{
"epoch": 3.3839662447257384,
"grad_norm": 0.06298828125,
"learning_rate": 1.550753752023053e-06,
"loss": 0.9877,
"step": 203
},
{
"epoch": 3.40084388185654,
"grad_norm": 0.060546875,
"learning_rate": 1.459724980310767e-06,
"loss": 0.991,
"step": 204
},
{
"epoch": 3.4177215189873418,
"grad_norm": 0.060302734375,
"learning_rate": 1.3713126038918977e-06,
"loss": 0.9839,
"step": 205
},
{
"epoch": 3.4345991561181437,
"grad_norm": 0.060302734375,
"learning_rate": 1.2855337067418576e-06,
"loss": 0.9977,
"step": 206
},
{
"epoch": 3.451476793248945,
"grad_norm": 0.058837890625,
"learning_rate": 1.2024048639673225e-06,
"loss": 0.9981,
"step": 207
},
{
"epoch": 3.4683544303797467,
"grad_norm": 0.059814453125,
"learning_rate": 1.1219421386033958e-06,
"loss": 1.0007,
"step": 208
},
{
"epoch": 3.4852320675105486,
"grad_norm": 0.06298828125,
"learning_rate": 1.0441610785097471e-06,
"loss": 0.9977,
"step": 209
},
{
"epoch": 3.50210970464135,
"grad_norm": 0.0615234375,
"learning_rate": 9.690767133662976e-07,
"loss": 0.9898,
"step": 210
},
{
"epoch": 3.50210970464135,
"eval_loss": 1.0054612159729004,
"eval_runtime": 74.055,
"eval_samples_per_second": 13.909,
"eval_steps_per_second": 13.909,
"step": 210
},
{
"epoch": 3.518987341772152,
"grad_norm": 0.06201171875,
"learning_rate": 8.967035517690147e-07,
"loss": 0.9895,
"step": 211
},
{
"epoch": 3.5358649789029535,
"grad_norm": 0.06005859375,
"learning_rate": 8.270555784264167e-07,
"loss": 1.0005,
"step": 212
},
{
"epoch": 3.5527426160337554,
"grad_norm": 0.06103515625,
"learning_rate": 7.601462514572877e-07,
"loss": 0.9957,
"step": 213
},
{
"epoch": 3.569620253164557,
"grad_norm": 0.060546875,
"learning_rate": 6.959884997901705e-07,
"loss": 1.0034,
"step": 214
},
{
"epoch": 3.586497890295359,
"grad_norm": 0.060302734375,
"learning_rate": 6.345947206650981e-07,
"loss": 0.9898,
"step": 215
},
{
"epoch": 3.6033755274261603,
"grad_norm": 0.060791015625,
"learning_rate": 5.759767772380648e-07,
"loss": 1.0207,
"step": 216
},
{
"epoch": 3.620253164556962,
"grad_norm": 0.058837890625,
"learning_rate": 5.201459962886995e-07,
"loss": 0.9801,
"step": 217
},
{
"epoch": 3.6371308016877637,
"grad_norm": 0.06201171875,
"learning_rate": 4.6711316603159084e-07,
"loss": 1.0018,
"step": 218
},
{
"epoch": 3.6540084388185656,
"grad_norm": 0.1767578125,
"learning_rate": 4.1688853403167194e-07,
"loss": 1.7068,
"step": 219
},
{
"epoch": 3.670886075949367,
"grad_norm": 0.060302734375,
"learning_rate": 3.6948180522408006e-07,
"loss": 0.9958,
"step": 220
},
{
"epoch": 3.6877637130801686,
"grad_norm": 0.06298828125,
"learning_rate": 3.2490214003885963e-07,
"loss": 1.016,
"step": 221
},
{
"epoch": 3.7046413502109705,
"grad_norm": 0.060302734375,
"learning_rate": 2.831581526308935e-07,
"loss": 1.0015,
"step": 222
},
{
"epoch": 3.721518987341772,
"grad_norm": 0.060791015625,
"learning_rate": 2.4425790921538404e-07,
"loss": 1.0011,
"step": 223
},
{
"epoch": 3.738396624472574,
"grad_norm": 0.060791015625,
"learning_rate": 2.0820892650920686e-07,
"loss": 0.9869,
"step": 224
},
{
"epoch": 3.7552742616033754,
"grad_norm": 0.0595703125,
"learning_rate": 1.7501817027846255e-07,
"loss": 0.9881,
"step": 225
},
{
"epoch": 3.7721518987341773,
"grad_norm": 0.061767578125,
"learning_rate": 1.4469205399246844e-07,
"loss": 0.9939,
"step": 226
},
{
"epoch": 3.789029535864979,
"grad_norm": 0.061279296875,
"learning_rate": 1.1723643758448144e-07,
"loss": 0.9719,
"step": 227
},
{
"epoch": 3.8059071729957807,
"grad_norm": 0.061279296875,
"learning_rate": 9.265662631938399e-08,
"loss": 1.0162,
"step": 228
},
{
"epoch": 3.8227848101265822,
"grad_norm": 0.05908203125,
"learning_rate": 7.095736976853895e-08,
"loss": 1.0006,
"step": 229
},
{
"epoch": 3.8396624472573837,
"grad_norm": 0.060546875,
"learning_rate": 5.214286089203546e-08,
"loss": 0.983,
"step": 230
},
{
"epoch": 3.8565400843881856,
"grad_norm": 0.060302734375,
"learning_rate": 3.621673522847035e-08,
"loss": 0.9812,
"step": 231
},
{
"epoch": 3.8734177215189876,
"grad_norm": 0.061767578125,
"learning_rate": 2.3182070192460104e-08,
"loss": 0.9869,
"step": 232
},
{
"epoch": 3.890295358649789,
"grad_norm": 0.06005859375,
"learning_rate": 1.3041384479981489e-08,
"loss": 0.9926,
"step": 233
},
{
"epoch": 3.9071729957805905,
"grad_norm": 0.06005859375,
"learning_rate": 5.796637581689246e-09,
"loss": 0.9996,
"step": 234
},
{
"epoch": 3.9240506329113924,
"grad_norm": 0.06201171875,
"learning_rate": 1.4492294042839361e-09,
"loss": 1.011,
"step": 235
},
{
"epoch": 3.9409282700421944,
"grad_norm": 0.189453125,
"learning_rate": 0.0,
"loss": 1.6705,
"step": 236
}
],
"logging_steps": 1,
"max_steps": 236,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 30,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.636388374942843e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}