EtashGuha's picture
Upload model
a44057f verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.0,
"eval_steps": 500,
"global_step": 231,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.030303030303030304,
"grad_norm": 0.45404192269934357,
"learning_rate": 8.333333333333333e-07,
"loss": 0.8175,
"step": 1
},
{
"epoch": 0.06060606060606061,
"grad_norm": 0.4917731617433597,
"learning_rate": 1.6666666666666667e-06,
"loss": 0.8089,
"step": 2
},
{
"epoch": 0.09090909090909091,
"grad_norm": 0.43539133801235924,
"learning_rate": 2.5e-06,
"loss": 0.7975,
"step": 3
},
{
"epoch": 0.12121212121212122,
"grad_norm": 0.4519256892966392,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.8046,
"step": 4
},
{
"epoch": 0.15151515151515152,
"grad_norm": 0.28720192401944866,
"learning_rate": 4.166666666666667e-06,
"loss": 0.8215,
"step": 5
},
{
"epoch": 0.18181818181818182,
"grad_norm": 0.3677456465780556,
"learning_rate": 5e-06,
"loss": 0.7906,
"step": 6
},
{
"epoch": 0.21212121212121213,
"grad_norm": 0.9194352778005709,
"learning_rate": 5.833333333333334e-06,
"loss": 0.793,
"step": 7
},
{
"epoch": 0.24242424242424243,
"grad_norm": 0.7156412843519948,
"learning_rate": 6.666666666666667e-06,
"loss": 0.8245,
"step": 8
},
{
"epoch": 0.2727272727272727,
"grad_norm": 0.5089150053764867,
"learning_rate": 7.500000000000001e-06,
"loss": 0.7622,
"step": 9
},
{
"epoch": 0.30303030303030304,
"grad_norm": 0.3780110166718658,
"learning_rate": 8.333333333333334e-06,
"loss": 0.747,
"step": 10
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.5222565876804458,
"learning_rate": 9.166666666666666e-06,
"loss": 0.7662,
"step": 11
},
{
"epoch": 0.36363636363636365,
"grad_norm": 0.6222553686265413,
"learning_rate": 1e-05,
"loss": 0.7814,
"step": 12
},
{
"epoch": 0.3939393939393939,
"grad_norm": 0.5185673069907736,
"learning_rate": 1.0833333333333334e-05,
"loss": 0.7766,
"step": 13
},
{
"epoch": 0.42424242424242425,
"grad_norm": 0.3854806334293932,
"learning_rate": 1.1666666666666668e-05,
"loss": 0.8209,
"step": 14
},
{
"epoch": 0.45454545454545453,
"grad_norm": 0.4663667588511311,
"learning_rate": 1.25e-05,
"loss": 0.7498,
"step": 15
},
{
"epoch": 0.48484848484848486,
"grad_norm": 0.49386497838516236,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.7466,
"step": 16
},
{
"epoch": 0.5151515151515151,
"grad_norm": 0.456157458159694,
"learning_rate": 1.416666666666667e-05,
"loss": 0.7514,
"step": 17
},
{
"epoch": 0.5454545454545454,
"grad_norm": 0.391640681561914,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.7879,
"step": 18
},
{
"epoch": 0.5757575757575758,
"grad_norm": 0.4601977317335622,
"learning_rate": 1.5833333333333333e-05,
"loss": 0.804,
"step": 19
},
{
"epoch": 0.6060606060606061,
"grad_norm": 0.4848501100787871,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.7816,
"step": 20
},
{
"epoch": 0.6363636363636364,
"grad_norm": 0.41383228738964295,
"learning_rate": 1.7500000000000002e-05,
"loss": 0.7771,
"step": 21
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.540316477528811,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.8016,
"step": 22
},
{
"epoch": 0.696969696969697,
"grad_norm": 0.40379514416188667,
"learning_rate": 1.916666666666667e-05,
"loss": 0.8217,
"step": 23
},
{
"epoch": 0.7272727272727273,
"grad_norm": 0.4756570316376291,
"learning_rate": 2e-05,
"loss": 0.7633,
"step": 24
},
{
"epoch": 0.7575757575757576,
"grad_norm": 0.41399508025723236,
"learning_rate": 1.999884834944106e-05,
"loss": 0.7889,
"step": 25
},
{
"epoch": 0.7878787878787878,
"grad_norm": 0.4457872415888005,
"learning_rate": 1.9995393663024054e-05,
"loss": 0.7973,
"step": 26
},
{
"epoch": 0.8181818181818182,
"grad_norm": 0.3956381370526351,
"learning_rate": 1.9989636736467278e-05,
"loss": 0.7742,
"step": 27
},
{
"epoch": 0.8484848484848485,
"grad_norm": 0.4455994153429883,
"learning_rate": 1.9981578895764272e-05,
"loss": 0.7885,
"step": 28
},
{
"epoch": 0.8787878787878788,
"grad_norm": 0.5001691581205011,
"learning_rate": 1.9971221996878395e-05,
"loss": 0.773,
"step": 29
},
{
"epoch": 0.9090909090909091,
"grad_norm": 0.3716715232168673,
"learning_rate": 1.9958568425315316e-05,
"loss": 0.7916,
"step": 30
},
{
"epoch": 0.9393939393939394,
"grad_norm": 0.42090023133566995,
"learning_rate": 1.9943621095573588e-05,
"loss": 0.8188,
"step": 31
},
{
"epoch": 0.9696969696969697,
"grad_norm": 0.4234847011956473,
"learning_rate": 1.9926383450473344e-05,
"loss": 0.7724,
"step": 32
},
{
"epoch": 1.0,
"grad_norm": 0.33502228724679345,
"learning_rate": 1.9906859460363307e-05,
"loss": 0.7806,
"step": 33
},
{
"epoch": 1.0303030303030303,
"grad_norm": 0.4751502077280668,
"learning_rate": 1.9885053622206305e-05,
"loss": 0.7569,
"step": 34
},
{
"epoch": 1.0606060606060606,
"grad_norm": 0.3945255799951885,
"learning_rate": 1.986097095854347e-05,
"loss": 0.7723,
"step": 35
},
{
"epoch": 1.0909090909090908,
"grad_norm": 0.5000631707654161,
"learning_rate": 1.9834617016337424e-05,
"loss": 0.7419,
"step": 36
},
{
"epoch": 1.121212121212121,
"grad_norm": 0.4299367812148087,
"learning_rate": 1.9805997865694616e-05,
"loss": 0.7838,
"step": 37
},
{
"epoch": 1.1515151515151516,
"grad_norm": 0.48123262096644726,
"learning_rate": 1.9775120098467212e-05,
"loss": 0.732,
"step": 38
},
{
"epoch": 1.1818181818181819,
"grad_norm": 0.4322275750955115,
"learning_rate": 1.9741990826734793e-05,
"loss": 0.7479,
"step": 39
},
{
"epoch": 1.2121212121212122,
"grad_norm": 0.4264785762340682,
"learning_rate": 1.970661768116622e-05,
"loss": 0.7416,
"step": 40
},
{
"epoch": 1.2424242424242424,
"grad_norm": 0.42755114582110104,
"learning_rate": 1.9669008809262064e-05,
"loss": 0.7445,
"step": 41
},
{
"epoch": 1.2727272727272727,
"grad_norm": 0.4647888549497104,
"learning_rate": 1.9629172873477995e-05,
"loss": 0.716,
"step": 42
},
{
"epoch": 1.303030303030303,
"grad_norm": 0.5548994096636525,
"learning_rate": 1.9587119049229558e-05,
"loss": 0.7794,
"step": 43
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.6512138493815964,
"learning_rate": 1.954285702277879e-05,
"loss": 0.7426,
"step": 44
},
{
"epoch": 1.3636363636363638,
"grad_norm": 0.6599233740244347,
"learning_rate": 1.9496396989003195e-05,
"loss": 0.7072,
"step": 45
},
{
"epoch": 1.393939393939394,
"grad_norm": 0.4918413839868032,
"learning_rate": 1.944774964904754e-05,
"loss": 0.7122,
"step": 46
},
{
"epoch": 1.4242424242424243,
"grad_norm": 0.46266316435390575,
"learning_rate": 1.9396926207859085e-05,
"loss": 0.7553,
"step": 47
},
{
"epoch": 1.4545454545454546,
"grad_norm": 0.5719611759228369,
"learning_rate": 1.9343938371606714e-05,
"loss": 0.7323,
"step": 48
},
{
"epoch": 1.4848484848484849,
"grad_norm": 0.4650467098543586,
"learning_rate": 1.9288798344984673e-05,
"loss": 0.719,
"step": 49
},
{
"epoch": 1.5151515151515151,
"grad_norm": 0.47262576040525817,
"learning_rate": 1.9231518828401458e-05,
"loss": 0.6852,
"step": 50
},
{
"epoch": 1.5454545454545454,
"grad_norm": 0.4139673970067043,
"learning_rate": 1.917211301505453e-05,
"loss": 0.7347,
"step": 51
},
{
"epoch": 1.5757575757575757,
"grad_norm": 0.3749062072660008,
"learning_rate": 1.911059458789152e-05,
"loss": 0.7037,
"step": 52
},
{
"epoch": 1.606060606060606,
"grad_norm": 0.4900872301837013,
"learning_rate": 1.9046977716458627e-05,
"loss": 0.7463,
"step": 53
},
{
"epoch": 1.6363636363636362,
"grad_norm": 0.4304472787186808,
"learning_rate": 1.8981277053636963e-05,
"loss": 0.7404,
"step": 54
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.41298688400235295,
"learning_rate": 1.891350773226754e-05,
"loss": 0.7248,
"step": 55
},
{
"epoch": 1.696969696969697,
"grad_norm": 0.4114916666439847,
"learning_rate": 1.8843685361665724e-05,
"loss": 0.7691,
"step": 56
},
{
"epoch": 1.7272727272727273,
"grad_norm": 0.4479321189387342,
"learning_rate": 1.8771826024025944e-05,
"loss": 0.6955,
"step": 57
},
{
"epoch": 1.7575757575757576,
"grad_norm": 0.39505808462042286,
"learning_rate": 1.8697946270717468e-05,
"loss": 0.7683,
"step": 58
},
{
"epoch": 1.7878787878787878,
"grad_norm": 0.4149877700202695,
"learning_rate": 1.8622063118472135e-05,
"loss": 0.7197,
"step": 59
},
{
"epoch": 1.8181818181818183,
"grad_norm": 0.3699320087286979,
"learning_rate": 1.8544194045464888e-05,
"loss": 0.7289,
"step": 60
},
{
"epoch": 1.8484848484848486,
"grad_norm": 0.41486600284521025,
"learning_rate": 1.8464356987288012e-05,
"loss": 0.7193,
"step": 61
},
{
"epoch": 1.878787878787879,
"grad_norm": 0.3567474690754212,
"learning_rate": 1.8382570332820045e-05,
"loss": 0.7219,
"step": 62
},
{
"epoch": 1.9090909090909092,
"grad_norm": 0.40722062536298453,
"learning_rate": 1.8298852919990254e-05,
"loss": 0.7396,
"step": 63
},
{
"epoch": 1.9393939393939394,
"grad_norm": 0.4010891948969097,
"learning_rate": 1.821322403143969e-05,
"loss": 0.7745,
"step": 64
},
{
"epoch": 1.9696969696969697,
"grad_norm": 0.33429885493126726,
"learning_rate": 1.812570339007983e-05,
"loss": 0.7324,
"step": 65
},
{
"epoch": 2.0,
"grad_norm": 0.39491205167588617,
"learning_rate": 1.8036311154549783e-05,
"loss": 0.7409,
"step": 66
},
{
"epoch": 2.0303030303030303,
"grad_norm": 0.484969972603566,
"learning_rate": 1.7945067914573147e-05,
"loss": 0.7062,
"step": 67
},
{
"epoch": 2.0606060606060606,
"grad_norm": 0.4863336277140621,
"learning_rate": 1.7851994686215592e-05,
"loss": 0.6927,
"step": 68
},
{
"epoch": 2.090909090909091,
"grad_norm": 0.5096357683183218,
"learning_rate": 1.77571129070442e-05,
"loss": 0.6612,
"step": 69
},
{
"epoch": 2.121212121212121,
"grad_norm": 0.48322952651428286,
"learning_rate": 1.766044443118978e-05,
"loss": 0.6412,
"step": 70
},
{
"epoch": 2.1515151515151514,
"grad_norm": 0.4221595004501216,
"learning_rate": 1.7562011524313187e-05,
"loss": 0.7077,
"step": 71
},
{
"epoch": 2.1818181818181817,
"grad_norm": 0.43611020839153114,
"learning_rate": 1.7461836858476858e-05,
"loss": 0.6949,
"step": 72
},
{
"epoch": 2.212121212121212,
"grad_norm": 0.45578329588946437,
"learning_rate": 1.7359943506922775e-05,
"loss": 0.6669,
"step": 73
},
{
"epoch": 2.242424242424242,
"grad_norm": 0.45417147247230943,
"learning_rate": 1.725635493875799e-05,
"loss": 0.6681,
"step": 74
},
{
"epoch": 2.2727272727272725,
"grad_norm": 0.4160955768518612,
"learning_rate": 1.7151095013548996e-05,
"loss": 0.673,
"step": 75
},
{
"epoch": 2.303030303030303,
"grad_norm": 0.4276838043195557,
"learning_rate": 1.7044187975826126e-05,
"loss": 0.6851,
"step": 76
},
{
"epoch": 2.3333333333333335,
"grad_norm": 0.3928420657759498,
"learning_rate": 1.693565844949933e-05,
"loss": 0.6649,
"step": 77
},
{
"epoch": 2.3636363636363638,
"grad_norm": 0.399555483034014,
"learning_rate": 1.6825531432186545e-05,
"loss": 0.634,
"step": 78
},
{
"epoch": 2.393939393939394,
"grad_norm": 0.426521795086231,
"learning_rate": 1.671383228945597e-05,
"loss": 0.6878,
"step": 79
},
{
"epoch": 2.4242424242424243,
"grad_norm": 0.36158253835514503,
"learning_rate": 1.6600586748983642e-05,
"loss": 0.6794,
"step": 80
},
{
"epoch": 2.4545454545454546,
"grad_norm": 0.39932078739571836,
"learning_rate": 1.648582089462756e-05,
"loss": 0.6718,
"step": 81
},
{
"epoch": 2.484848484848485,
"grad_norm": 0.41834253839933744,
"learning_rate": 1.6369561160419783e-05,
"loss": 0.6493,
"step": 82
},
{
"epoch": 2.515151515151515,
"grad_norm": 0.3642773746555324,
"learning_rate": 1.625183432447789e-05,
"loss": 0.6824,
"step": 83
},
{
"epoch": 2.5454545454545454,
"grad_norm": 0.3801539406045018,
"learning_rate": 1.6132667502837164e-05,
"loss": 0.6479,
"step": 84
},
{
"epoch": 2.5757575757575757,
"grad_norm": 0.36062164140177216,
"learning_rate": 1.6012088143204953e-05,
"loss": 0.6697,
"step": 85
},
{
"epoch": 2.606060606060606,
"grad_norm": 0.3609319591166014,
"learning_rate": 1.589012401863864e-05,
"loss": 0.6665,
"step": 86
},
{
"epoch": 2.6363636363636362,
"grad_norm": 0.3557810864627686,
"learning_rate": 1.5766803221148676e-05,
"loss": 0.7038,
"step": 87
},
{
"epoch": 2.6666666666666665,
"grad_norm": 0.32571574930810243,
"learning_rate": 1.5642154155228124e-05,
"loss": 0.6859,
"step": 88
},
{
"epoch": 2.6969696969696972,
"grad_norm": 0.35740454414375333,
"learning_rate": 1.5516205531310272e-05,
"loss": 0.6807,
"step": 89
},
{
"epoch": 2.7272727272727275,
"grad_norm": 0.353293086570693,
"learning_rate": 1.538898635915576e-05,
"loss": 0.6751,
"step": 90
},
{
"epoch": 2.757575757575758,
"grad_norm": 0.3635232148430636,
"learning_rate": 1.526052594117071e-05,
"loss": 0.6925,
"step": 91
},
{
"epoch": 2.787878787878788,
"grad_norm": 0.32947551714233064,
"learning_rate": 1.513085386565758e-05,
"loss": 0.6116,
"step": 92
},
{
"epoch": 2.8181818181818183,
"grad_norm": 0.3948262094416439,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.6581,
"step": 93
},
{
"epoch": 2.8484848484848486,
"grad_norm": 0.31363922102118225,
"learning_rate": 1.4867994483783485e-05,
"loss": 0.6705,
"step": 94
},
{
"epoch": 2.878787878787879,
"grad_norm": 0.35995682431320913,
"learning_rate": 1.4734867721853341e-05,
"loss": 0.6386,
"step": 95
},
{
"epoch": 2.909090909090909,
"grad_norm": 0.34315747409978997,
"learning_rate": 1.4600650377311523e-05,
"loss": 0.7049,
"step": 96
},
{
"epoch": 2.9393939393939394,
"grad_norm": 0.3102359902459931,
"learning_rate": 1.4465373364454001e-05,
"loss": 0.6951,
"step": 97
},
{
"epoch": 2.9696969696969697,
"grad_norm": 0.3313369384920703,
"learning_rate": 1.4329067841650274e-05,
"loss": 0.6954,
"step": 98
},
{
"epoch": 3.0,
"grad_norm": 0.3289930645921954,
"learning_rate": 1.4191765204166643e-05,
"loss": 0.6461,
"step": 99
},
{
"epoch": 3.0303030303030303,
"grad_norm": 0.554418451579518,
"learning_rate": 1.4053497076934948e-05,
"loss": 0.5918,
"step": 100
},
{
"epoch": 3.0606060606060606,
"grad_norm": 0.48985519582710435,
"learning_rate": 1.3914295307268396e-05,
"loss": 0.6034,
"step": 101
},
{
"epoch": 3.090909090909091,
"grad_norm": 0.588704246980213,
"learning_rate": 1.3774191957526144e-05,
"loss": 0.6231,
"step": 102
},
{
"epoch": 3.121212121212121,
"grad_norm": 0.5417698851668765,
"learning_rate": 1.3633219297728415e-05,
"loss": 0.5976,
"step": 103
},
{
"epoch": 3.1515151515151514,
"grad_norm": 0.48683148314426355,
"learning_rate": 1.3491409798123687e-05,
"loss": 0.5539,
"step": 104
},
{
"epoch": 3.1818181818181817,
"grad_norm": 0.4404191388960243,
"learning_rate": 1.3348796121709862e-05,
"loss": 0.59,
"step": 105
},
{
"epoch": 3.212121212121212,
"grad_norm": 0.6044644583011649,
"learning_rate": 1.3205411116710973e-05,
"loss": 0.556,
"step": 106
},
{
"epoch": 3.242424242424242,
"grad_norm": 0.4187532571010145,
"learning_rate": 1.3061287809011243e-05,
"loss": 0.6463,
"step": 107
},
{
"epoch": 3.2727272727272725,
"grad_norm": 0.5029972310900598,
"learning_rate": 1.291645939454825e-05,
"loss": 0.5826,
"step": 108
},
{
"epoch": 3.303030303030303,
"grad_norm": 0.41282532864997246,
"learning_rate": 1.277095923166689e-05,
"loss": 0.6166,
"step": 109
},
{
"epoch": 3.3333333333333335,
"grad_norm": 0.47490843385272996,
"learning_rate": 1.2624820833435939e-05,
"loss": 0.5746,
"step": 110
},
{
"epoch": 3.3636363636363638,
"grad_norm": 0.440401851756132,
"learning_rate": 1.2478077859929e-05,
"loss": 0.6117,
"step": 111
},
{
"epoch": 3.393939393939394,
"grad_norm": 0.3967519472519431,
"learning_rate": 1.2330764110471567e-05,
"loss": 0.6295,
"step": 112
},
{
"epoch": 3.4242424242424243,
"grad_norm": 0.44320916182805037,
"learning_rate": 1.2182913515856016e-05,
"loss": 0.6137,
"step": 113
},
{
"epoch": 3.4545454545454546,
"grad_norm": 0.3794432860970576,
"learning_rate": 1.2034560130526341e-05,
"loss": 0.6456,
"step": 114
},
{
"epoch": 3.484848484848485,
"grad_norm": 0.3715910139952054,
"learning_rate": 1.1885738124734359e-05,
"loss": 0.5677,
"step": 115
},
{
"epoch": 3.515151515151515,
"grad_norm": 0.4200754325291374,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.5601,
"step": 116
},
{
"epoch": 3.5454545454545454,
"grad_norm": 0.41667136318291725,
"learning_rate": 1.1586825464562515e-05,
"loss": 0.6025,
"step": 117
},
{
"epoch": 3.5757575757575757,
"grad_norm": 0.3967776189508287,
"learning_rate": 1.1436803658769082e-05,
"loss": 0.5983,
"step": 118
},
{
"epoch": 3.606060606060606,
"grad_norm": 0.38859872977785287,
"learning_rate": 1.1286450913828313e-05,
"loss": 0.5693,
"step": 119
},
{
"epoch": 3.6363636363636362,
"grad_norm": 0.3657265255161343,
"learning_rate": 1.113580186050475e-05,
"loss": 0.6084,
"step": 120
},
{
"epoch": 3.6666666666666665,
"grad_norm": 0.3499353718681901,
"learning_rate": 1.0984891197811686e-05,
"loss": 0.6265,
"step": 121
},
{
"epoch": 3.6969696969696972,
"grad_norm": 0.4094454939382451,
"learning_rate": 1.0833753685018935e-05,
"loss": 0.598,
"step": 122
},
{
"epoch": 3.7272727272727275,
"grad_norm": 0.32892441325866917,
"learning_rate": 1.0682424133646712e-05,
"loss": 0.5897,
"step": 123
},
{
"epoch": 3.757575757575758,
"grad_norm": 0.3833177656299727,
"learning_rate": 1.0530937399447496e-05,
"loss": 0.5897,
"step": 124
},
{
"epoch": 3.787878787878788,
"grad_norm": 0.3769241654165782,
"learning_rate": 1.0379328374377715e-05,
"loss": 0.5648,
"step": 125
},
{
"epoch": 3.8181818181818183,
"grad_norm": 0.34272214405489915,
"learning_rate": 1.0227631978561057e-05,
"loss": 0.6158,
"step": 126
},
{
"epoch": 3.8484848484848486,
"grad_norm": 0.3755040249036914,
"learning_rate": 1.0075883152245334e-05,
"loss": 0.6222,
"step": 127
},
{
"epoch": 3.878787878787879,
"grad_norm": 0.3364748840442625,
"learning_rate": 9.92411684775467e-06,
"loss": 0.6131,
"step": 128
},
{
"epoch": 3.909090909090909,
"grad_norm": 0.3313129750694039,
"learning_rate": 9.772368021438943e-06,
"loss": 0.5865,
"step": 129
},
{
"epoch": 3.9393939393939394,
"grad_norm": 0.34004338305513937,
"learning_rate": 9.620671625622287e-06,
"loss": 0.6016,
"step": 130
},
{
"epoch": 3.9696969696969697,
"grad_norm": 0.35450131562874504,
"learning_rate": 9.469062600552509e-06,
"loss": 0.6036,
"step": 131
},
{
"epoch": 4.0,
"grad_norm": 0.2884340463320288,
"learning_rate": 9.317575866353293e-06,
"loss": 0.5724,
"step": 132
},
{
"epoch": 4.03030303030303,
"grad_norm": 0.8221980611820946,
"learning_rate": 9.166246314981066e-06,
"loss": 0.5335,
"step": 133
},
{
"epoch": 4.0606060606060606,
"grad_norm": 0.3593534333309625,
"learning_rate": 9.015108802188314e-06,
"loss": 0.5397,
"step": 134
},
{
"epoch": 4.090909090909091,
"grad_norm": 1.016539585630258,
"learning_rate": 8.86419813949525e-06,
"loss": 0.4792,
"step": 135
},
{
"epoch": 4.121212121212121,
"grad_norm": 0.3836515827869688,
"learning_rate": 8.71354908617169e-06,
"loss": 0.5572,
"step": 136
},
{
"epoch": 4.151515151515151,
"grad_norm": 0.654174879353079,
"learning_rate": 8.56319634123092e-06,
"loss": 0.5373,
"step": 137
},
{
"epoch": 4.181818181818182,
"grad_norm": 0.4860925117352824,
"learning_rate": 8.413174535437486e-06,
"loss": 0.5021,
"step": 138
},
{
"epoch": 4.212121212121212,
"grad_norm": 0.44624230931575426,
"learning_rate": 8.263518223330698e-06,
"loss": 0.5429,
"step": 139
},
{
"epoch": 4.242424242424242,
"grad_norm": 0.7365373727628527,
"learning_rate": 8.114261875265643e-06,
"loss": 0.5491,
"step": 140
},
{
"epoch": 4.2727272727272725,
"grad_norm": 0.34738655001456165,
"learning_rate": 7.965439869473664e-06,
"loss": 0.5353,
"step": 141
},
{
"epoch": 4.303030303030303,
"grad_norm": 0.5685155911111173,
"learning_rate": 7.817086484143987e-06,
"loss": 0.5108,
"step": 142
},
{
"epoch": 4.333333333333333,
"grad_norm": 0.5025844097814388,
"learning_rate": 7.669235889528436e-06,
"loss": 0.5259,
"step": 143
},
{
"epoch": 4.363636363636363,
"grad_norm": 0.3485318123713458,
"learning_rate": 7.521922140071003e-06,
"loss": 0.4858,
"step": 144
},
{
"epoch": 4.393939393939394,
"grad_norm": 0.49548568133152016,
"learning_rate": 7.375179166564062e-06,
"loss": 0.5416,
"step": 145
},
{
"epoch": 4.424242424242424,
"grad_norm": 0.38895260895412237,
"learning_rate": 7.2290407683331154e-06,
"loss": 0.5123,
"step": 146
},
{
"epoch": 4.454545454545454,
"grad_norm": 0.3787457287350692,
"learning_rate": 7.0835406054517505e-06,
"loss": 0.5423,
"step": 147
},
{
"epoch": 4.484848484848484,
"grad_norm": 0.4078612790532545,
"learning_rate": 6.93871219098876e-06,
"loss": 0.5193,
"step": 148
},
{
"epoch": 4.515151515151516,
"grad_norm": 0.35138547275802173,
"learning_rate": 6.79458888328903e-06,
"loss": 0.4995,
"step": 149
},
{
"epoch": 4.545454545454545,
"grad_norm": 0.35711350869183073,
"learning_rate": 6.651203878290139e-06,
"loss": 0.4876,
"step": 150
},
{
"epoch": 4.575757575757576,
"grad_norm": 0.35616419823813167,
"learning_rate": 6.508590201876317e-06,
"loss": 0.51,
"step": 151
},
{
"epoch": 4.606060606060606,
"grad_norm": 0.36474499374188823,
"learning_rate": 6.366780702271589e-06,
"loss": 0.5099,
"step": 152
},
{
"epoch": 4.636363636363637,
"grad_norm": 0.3403698282794116,
"learning_rate": 6.225808042473857e-06,
"loss": 0.5031,
"step": 153
},
{
"epoch": 4.666666666666667,
"grad_norm": 0.33883017236772794,
"learning_rate": 6.085704692731609e-06,
"loss": 0.5239,
"step": 154
},
{
"epoch": 4.696969696969697,
"grad_norm": 0.3398850608166464,
"learning_rate": 5.946502923065054e-06,
"loss": 0.55,
"step": 155
},
{
"epoch": 4.7272727272727275,
"grad_norm": 0.3753451324323081,
"learning_rate": 5.8082347958333625e-06,
"loss": 0.5705,
"step": 156
},
{
"epoch": 4.757575757575758,
"grad_norm": 0.28415263780988786,
"learning_rate": 5.670932158349732e-06,
"loss": 0.4858,
"step": 157
},
{
"epoch": 4.787878787878788,
"grad_norm": 0.3274461121683733,
"learning_rate": 5.534626635546e-06,
"loss": 0.5129,
"step": 158
},
{
"epoch": 4.818181818181818,
"grad_norm": 0.31333297032587853,
"learning_rate": 5.399349622688479e-06,
"loss": 0.5393,
"step": 159
},
{
"epoch": 4.848484848484849,
"grad_norm": 0.3182090157724561,
"learning_rate": 5.2651322781466606e-06,
"loss": 0.5301,
"step": 160
},
{
"epoch": 4.878787878787879,
"grad_norm": 0.3065689083522182,
"learning_rate": 5.132005516216512e-06,
"loss": 0.5365,
"step": 161
},
{
"epoch": 4.909090909090909,
"grad_norm": 0.31168899765491165,
"learning_rate": 5.000000000000003e-06,
"loss": 0.5436,
"step": 162
},
{
"epoch": 4.9393939393939394,
"grad_norm": 0.32326413717899527,
"learning_rate": 4.869146134342426e-06,
"loss": 0.4996,
"step": 163
},
{
"epoch": 4.96969696969697,
"grad_norm": 0.286612363019893,
"learning_rate": 4.739474058829288e-06,
"loss": 0.4761,
"step": 164
},
{
"epoch": 5.0,
"grad_norm": 0.2951379128595362,
"learning_rate": 4.611013640844245e-06,
"loss": 0.5082,
"step": 165
},
{
"epoch": 5.03030303030303,
"grad_norm": 0.6396686995541148,
"learning_rate": 4.483794468689728e-06,
"loss": 0.4722,
"step": 166
},
{
"epoch": 5.0606060606060606,
"grad_norm": 0.3423121241028325,
"learning_rate": 4.357845844771881e-06,
"loss": 0.5007,
"step": 167
},
{
"epoch": 5.090909090909091,
"grad_norm": 0.4221329439669877,
"learning_rate": 4.2331967788513295e-06,
"loss": 0.4563,
"step": 168
},
{
"epoch": 5.121212121212121,
"grad_norm": 0.6155289420170268,
"learning_rate": 4.109875981361363e-06,
"loss": 0.4219,
"step": 169
},
{
"epoch": 5.151515151515151,
"grad_norm": 0.40123316857880825,
"learning_rate": 3.987911856795047e-06,
"loss": 0.4222,
"step": 170
},
{
"epoch": 5.181818181818182,
"grad_norm": 0.3320803102770148,
"learning_rate": 3.867332497162836e-06,
"loss": 0.4563,
"step": 171
},
{
"epoch": 5.212121212121212,
"grad_norm": 0.3948023088899153,
"learning_rate": 3.748165675522113e-06,
"loss": 0.473,
"step": 172
},
{
"epoch": 5.242424242424242,
"grad_norm": 0.3837070545882063,
"learning_rate": 3.630438839580217e-06,
"loss": 0.4906,
"step": 173
},
{
"epoch": 5.2727272727272725,
"grad_norm": 0.33592587876681307,
"learning_rate": 3.5141791053724405e-06,
"loss": 0.4917,
"step": 174
},
{
"epoch": 5.303030303030303,
"grad_norm": 0.31195103979332,
"learning_rate": 3.399413251016359e-06,
"loss": 0.4569,
"step": 175
},
{
"epoch": 5.333333333333333,
"grad_norm": 0.36728919190444254,
"learning_rate": 3.2861677105440335e-06,
"loss": 0.4635,
"step": 176
},
{
"epoch": 5.363636363636363,
"grad_norm": 0.3517700737933514,
"learning_rate": 3.174468567813461e-06,
"loss": 0.4398,
"step": 177
},
{
"epoch": 5.393939393939394,
"grad_norm": 0.2943168684553675,
"learning_rate": 3.0643415505006733e-06,
"loss": 0.4284,
"step": 178
},
{
"epoch": 5.424242424242424,
"grad_norm": 0.26739447517561443,
"learning_rate": 2.9558120241738786e-06,
"loss": 0.4225,
"step": 179
},
{
"epoch": 5.454545454545454,
"grad_norm": 0.3507665474790921,
"learning_rate": 2.8489049864510053e-06,
"loss": 0.4641,
"step": 180
},
{
"epoch": 5.484848484848484,
"grad_norm": 0.40200384317116233,
"learning_rate": 2.7436450612420098e-06,
"loss": 0.4357,
"step": 181
},
{
"epoch": 5.515151515151516,
"grad_norm": 0.2823987694207428,
"learning_rate": 2.640056493077231e-06,
"loss": 0.4329,
"step": 182
},
{
"epoch": 5.545454545454545,
"grad_norm": 0.3194011591578307,
"learning_rate": 2.5381631415231455e-06,
"loss": 0.4591,
"step": 183
},
{
"epoch": 5.575757575757576,
"grad_norm": 12.00665981560085,
"learning_rate": 2.4379884756868167e-06,
"loss": 0.4422,
"step": 184
},
{
"epoch": 5.606060606060606,
"grad_norm": 0.4054663444384578,
"learning_rate": 2.339555568810221e-06,
"loss": 0.5145,
"step": 185
},
{
"epoch": 5.636363636363637,
"grad_norm": 0.3444464352203058,
"learning_rate": 2.2428870929558012e-06,
"loss": 0.4473,
"step": 186
},
{
"epoch": 5.666666666666667,
"grad_norm": 0.2630241472106751,
"learning_rate": 2.1480053137844115e-06,
"loss": 0.4549,
"step": 187
},
{
"epoch": 5.696969696969697,
"grad_norm": 0.26492666361572254,
"learning_rate": 2.054932085426856e-06,
"loss": 0.5098,
"step": 188
},
{
"epoch": 5.7272727272727275,
"grad_norm": 0.31298591883853255,
"learning_rate": 1.963688845450218e-06,
"loss": 0.4747,
"step": 189
},
{
"epoch": 5.757575757575758,
"grad_norm": 0.29755219202050065,
"learning_rate": 1.8742966099201699e-06,
"loss": 0.4705,
"step": 190
},
{
"epoch": 5.787878787878788,
"grad_norm": 0.31180141240352466,
"learning_rate": 1.7867759685603115e-06,
"loss": 0.4658,
"step": 191
},
{
"epoch": 5.818181818181818,
"grad_norm": 0.2548757714611652,
"learning_rate": 1.7011470800097496e-06,
"loss": 0.495,
"step": 192
},
{
"epoch": 5.848484848484849,
"grad_norm": 0.2495894264574609,
"learning_rate": 1.6174296671799571e-06,
"loss": 0.4912,
"step": 193
},
{
"epoch": 5.878787878787879,
"grad_norm": 0.27525778253407,
"learning_rate": 1.5356430127119915e-06,
"loss": 0.4414,
"step": 194
},
{
"epoch": 5.909090909090909,
"grad_norm": 0.2882641006805427,
"learning_rate": 1.4558059545351144e-06,
"loss": 0.4428,
"step": 195
},
{
"epoch": 5.9393939393939394,
"grad_norm": 0.2707067991284653,
"learning_rate": 1.3779368815278648e-06,
"loss": 0.4501,
"step": 196
},
{
"epoch": 5.96969696969697,
"grad_norm": 0.27255241451283946,
"learning_rate": 1.302053729282533e-06,
"loss": 0.4156,
"step": 197
},
{
"epoch": 6.0,
"grad_norm": 0.23902392900936897,
"learning_rate": 1.2281739759740575e-06,
"loss": 0.4772,
"step": 198
},
{
"epoch": 6.03030303030303,
"grad_norm": 0.59970297576034,
"learning_rate": 1.156314638334277e-06,
"loss": 0.4291,
"step": 199
},
{
"epoch": 6.0606060606060606,
"grad_norm": 0.4576800220633988,
"learning_rate": 1.086492267732462e-06,
"loss": 0.4452,
"step": 200
},
{
"epoch": 6.090909090909091,
"grad_norm": 0.4274779611887373,
"learning_rate": 1.01872294636304e-06,
"loss": 0.4869,
"step": 201
},
{
"epoch": 6.121212121212121,
"grad_norm": 0.2724706245307364,
"learning_rate": 9.530222835413739e-07,
"loss": 0.4514,
"step": 202
},
{
"epoch": 6.151515151515151,
"grad_norm": 0.2768126110602979,
"learning_rate": 8.894054121084839e-07,
"loss": 0.4111,
"step": 203
},
{
"epoch": 6.181818181818182,
"grad_norm": 0.36175848135934524,
"learning_rate": 8.278869849454718e-07,
"loss": 0.3967,
"step": 204
},
{
"epoch": 6.212121212121212,
"grad_norm": 0.3255617649420347,
"learning_rate": 7.684811715985429e-07,
"loss": 0.4209,
"step": 205
},
{
"epoch": 6.242424242424242,
"grad_norm": 0.37390031536194934,
"learning_rate": 7.1120165501533e-07,
"loss": 0.4709,
"step": 206
},
{
"epoch": 6.2727272727272725,
"grad_norm": 0.2842925028722727,
"learning_rate": 6.560616283932897e-07,
"loss": 0.4057,
"step": 207
},
{
"epoch": 6.303030303030303,
"grad_norm": 0.30737010509919,
"learning_rate": 6.030737921409169e-07,
"loss": 0.4025,
"step": 208
},
{
"epoch": 6.333333333333333,
"grad_norm": 0.2774212067126218,
"learning_rate": 5.522503509524591e-07,
"loss": 0.389,
"step": 209
},
{
"epoch": 6.363636363636363,
"grad_norm": 0.24902416809163633,
"learning_rate": 5.036030109968082e-07,
"loss": 0.4167,
"step": 210
},
{
"epoch": 6.393939393939394,
"grad_norm": 0.23884345151826672,
"learning_rate": 4.5714297722121105e-07,
"loss": 0.4448,
"step": 211
},
{
"epoch": 6.424242424242424,
"grad_norm": 0.2433230050086897,
"learning_rate": 4.128809507704445e-07,
"loss": 0.4279,
"step": 212
},
{
"epoch": 6.454545454545454,
"grad_norm": 0.23663270669548958,
"learning_rate": 3.708271265220087e-07,
"loss": 0.4333,
"step": 213
},
{
"epoch": 6.484848484848484,
"grad_norm": 0.26350115568381516,
"learning_rate": 3.309911907379393e-07,
"loss": 0.4435,
"step": 214
},
{
"epoch": 6.515151515151516,
"grad_norm": 0.2523958492422985,
"learning_rate": 2.9338231883378365e-07,
"loss": 0.4058,
"step": 215
},
{
"epoch": 6.545454545454545,
"grad_norm": 0.4363043626731539,
"learning_rate": 2.5800917326521013e-07,
"loss": 0.4212,
"step": 216
},
{
"epoch": 6.575757575757576,
"grad_norm": 0.24510225333558835,
"learning_rate": 2.248799015327907e-07,
"loss": 0.433,
"step": 217
},
{
"epoch": 6.606060606060606,
"grad_norm": 0.2515502412207173,
"learning_rate": 1.9400213430538773e-07,
"loss": 0.4114,
"step": 218
},
{
"epoch": 6.636363636363637,
"grad_norm": 0.22642116713616728,
"learning_rate": 1.6538298366257975e-07,
"loss": 0.4208,
"step": 219
},
{
"epoch": 6.666666666666667,
"grad_norm": 0.23045976062255522,
"learning_rate": 1.3902904145653094e-07,
"loss": 0.4377,
"step": 220
},
{
"epoch": 6.696969696969697,
"grad_norm": 0.3273677387615356,
"learning_rate": 1.1494637779369766e-07,
"loss": 0.4335,
"step": 221
},
{
"epoch": 6.7272727272727275,
"grad_norm": 0.2190561532506803,
"learning_rate": 9.314053963669245e-08,
"loss": 0.429,
"step": 222
},
{
"epoch": 6.757575757575758,
"grad_norm": 0.2173262726511028,
"learning_rate": 7.361654952665608e-08,
"loss": 0.4489,
"step": 223
},
{
"epoch": 6.787878787878788,
"grad_norm": 0.21008428279486377,
"learning_rate": 5.637890442641403e-08,
"loss": 0.4455,
"step": 224
},
{
"epoch": 6.818181818181818,
"grad_norm": 0.22018538950475083,
"learning_rate": 4.143157468468717e-08,
"loss": 0.4448,
"step": 225
},
{
"epoch": 6.848484848484849,
"grad_norm": 0.2150873034352879,
"learning_rate": 2.8778003121607834e-08,
"loss": 0.4125,
"step": 226
},
{
"epoch": 6.878787878787879,
"grad_norm": 0.2327869206947825,
"learning_rate": 1.8421104235727406e-08,
"loss": 0.4053,
"step": 227
},
{
"epoch": 6.909090909090909,
"grad_norm": 0.22670408223918043,
"learning_rate": 1.0363263532724433e-08,
"loss": 0.449,
"step": 228
},
{
"epoch": 6.9393939393939394,
"grad_norm": 0.22376706811314764,
"learning_rate": 4.606336975948589e-09,
"loss": 0.4298,
"step": 229
},
{
"epoch": 6.96969696969697,
"grad_norm": 0.21864456226252352,
"learning_rate": 1.1516505589381777e-09,
"loss": 0.4316,
"step": 230
},
{
"epoch": 7.0,
"grad_norm": 0.211507799811681,
"learning_rate": 0.0,
"loss": 0.443,
"step": 231
},
{
"epoch": 7.0,
"step": 231,
"total_flos": 2229330703810560.0,
"train_loss": 0.6009024948010713,
"train_runtime": 6779.558,
"train_samples_per_second": 3.263,
"train_steps_per_second": 0.034
}
],
"logging_steps": 1,
"max_steps": 231,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"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": 2229330703810560.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}