cwaud's picture
Training in progress, epoch 3, checkpoint
66c316d verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 201,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.014925373134328358,
"grad_norm": 1.690108060836792,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.0929,
"step": 1
},
{
"epoch": 0.029850746268656716,
"grad_norm": 1.8146634101867676,
"learning_rate": 6.666666666666667e-05,
"loss": 2.2396,
"step": 2
},
{
"epoch": 0.04477611940298507,
"grad_norm": 1.9881230592727661,
"learning_rate": 0.0001,
"loss": 2.2041,
"step": 3
},
{
"epoch": 0.05970149253731343,
"grad_norm": 2.016158103942871,
"learning_rate": 0.00013333333333333334,
"loss": 2.176,
"step": 4
},
{
"epoch": 0.07462686567164178,
"grad_norm": 1.7050724029541016,
"learning_rate": 0.0001666666666666667,
"loss": 2.0313,
"step": 5
},
{
"epoch": 0.08955223880597014,
"grad_norm": 1.3839370012283325,
"learning_rate": 0.0002,
"loss": 1.818,
"step": 6
},
{
"epoch": 0.1044776119402985,
"grad_norm": 1.2064529657363892,
"learning_rate": 0.00019998832024742372,
"loss": 1.6223,
"step": 7
},
{
"epoch": 0.11940298507462686,
"grad_norm": 1.4260923862457275,
"learning_rate": 0.00019995328402117537,
"loss": 1.5066,
"step": 8
},
{
"epoch": 0.13432835820895522,
"grad_norm": 1.4008389711380005,
"learning_rate": 0.0001998949004149094,
"loss": 1.2986,
"step": 9
},
{
"epoch": 0.14925373134328357,
"grad_norm": 1.0532835721969604,
"learning_rate": 0.00019981318458209423,
"loss": 1.2209,
"step": 10
},
{
"epoch": 0.16417910447761194,
"grad_norm": 1.0162363052368164,
"learning_rate": 0.0001997081577320789,
"loss": 1.1007,
"step": 11
},
{
"epoch": 0.1791044776119403,
"grad_norm": 1.0316762924194336,
"learning_rate": 0.00019957984712458838,
"loss": 1.0087,
"step": 12
},
{
"epoch": 0.19402985074626866,
"grad_norm": 1.4354606866836548,
"learning_rate": 0.00019942828606264818,
"loss": 1.2594,
"step": 13
},
{
"epoch": 0.208955223880597,
"grad_norm": 2.1245648860931396,
"learning_rate": 0.0001992535138839406,
"loss": 1.4087,
"step": 14
},
{
"epoch": 0.22388059701492538,
"grad_norm": 1.2807283401489258,
"learning_rate": 0.0001990555759505946,
"loss": 1.3497,
"step": 15
},
{
"epoch": 0.23880597014925373,
"grad_norm": 0.7393147349357605,
"learning_rate": 0.00019883452363741216,
"loss": 1.263,
"step": 16
},
{
"epoch": 0.2537313432835821,
"grad_norm": 0.9481880068778992,
"learning_rate": 0.0001985904143185338,
"loss": 1.2411,
"step": 17
},
{
"epoch": 0.26865671641791045,
"grad_norm": 0.8055089116096497,
"learning_rate": 0.00019832331135254724,
"loss": 1.1185,
"step": 18
},
{
"epoch": 0.2835820895522388,
"grad_norm": 0.5172561407089233,
"learning_rate": 0.00019803328406604252,
"loss": 1.1209,
"step": 19
},
{
"epoch": 0.29850746268656714,
"grad_norm": 0.49716681241989136,
"learning_rate": 0.00019772040773561854,
"loss": 1.0457,
"step": 20
},
{
"epoch": 0.31343283582089554,
"grad_norm": 0.6212261915206909,
"learning_rate": 0.0001973847635683447,
"loss": 1.0181,
"step": 21
},
{
"epoch": 0.3283582089552239,
"grad_norm": 0.5520172119140625,
"learning_rate": 0.0001970264386806839,
"loss": 1.0484,
"step": 22
},
{
"epoch": 0.34328358208955223,
"grad_norm": 0.4611297845840454,
"learning_rate": 0.00019664552607588117,
"loss": 0.9581,
"step": 23
},
{
"epoch": 0.3582089552238806,
"grad_norm": 0.4654655158519745,
"learning_rate": 0.00019624212461982497,
"loss": 0.9156,
"step": 24
},
{
"epoch": 0.373134328358209,
"grad_norm": 0.6210163831710815,
"learning_rate": 0.00019581633901538626,
"loss": 0.8496,
"step": 25
},
{
"epoch": 0.3880597014925373,
"grad_norm": 0.8395450711250305,
"learning_rate": 0.0001953682797752431,
"loss": 1.3176,
"step": 26
},
{
"epoch": 0.40298507462686567,
"grad_norm": 0.695261538028717,
"learning_rate": 0.00019489806319319687,
"loss": 1.1809,
"step": 27
},
{
"epoch": 0.417910447761194,
"grad_norm": 0.48507070541381836,
"learning_rate": 0.0001944058113139884,
"loss": 1.166,
"step": 28
},
{
"epoch": 0.43283582089552236,
"grad_norm": 0.4849218726158142,
"learning_rate": 0.00019389165190162114,
"loss": 1.1374,
"step": 29
},
{
"epoch": 0.44776119402985076,
"grad_norm": 0.5968400835990906,
"learning_rate": 0.00019335571840619988,
"loss": 1.1094,
"step": 30
},
{
"epoch": 0.4626865671641791,
"grad_norm": 0.7121988534927368,
"learning_rate": 0.00019279814992929418,
"loss": 1.0958,
"step": 31
},
{
"epoch": 0.47761194029850745,
"grad_norm": 0.5847436189651489,
"learning_rate": 0.00019221909118783407,
"loss": 0.9935,
"step": 32
},
{
"epoch": 0.4925373134328358,
"grad_norm": 0.4457413852214813,
"learning_rate": 0.0001916186924765491,
"loss": 0.9889,
"step": 33
},
{
"epoch": 0.5074626865671642,
"grad_norm": 0.3817737102508545,
"learning_rate": 0.00019099710962895908,
"loss": 0.9586,
"step": 34
},
{
"epoch": 0.5223880597014925,
"grad_norm": 0.4596458077430725,
"learning_rate": 0.0001903545039769278,
"loss": 0.9506,
"step": 35
},
{
"epoch": 0.5373134328358209,
"grad_norm": 0.45744407176971436,
"learning_rate": 0.0001896910423087889,
"loss": 0.8788,
"step": 36
},
{
"epoch": 0.5522388059701493,
"grad_norm": 0.4180223345756531,
"learning_rate": 0.00018900689682605642,
"loss": 0.8059,
"step": 37
},
{
"epoch": 0.5671641791044776,
"grad_norm": 0.5419154167175293,
"learning_rate": 0.00018830224509872953,
"loss": 1.0703,
"step": 38
},
{
"epoch": 0.582089552238806,
"grad_norm": 0.8379240036010742,
"learning_rate": 0.00018757727001920445,
"loss": 1.2347,
"step": 39
},
{
"epoch": 0.5970149253731343,
"grad_norm": 0.7408146262168884,
"learning_rate": 0.00018683215975480452,
"loss": 1.2051,
"step": 40
},
{
"epoch": 0.6119402985074627,
"grad_norm": 0.4733333885669708,
"learning_rate": 0.00018606710769894153,
"loss": 1.112,
"step": 41
},
{
"epoch": 0.6268656716417911,
"grad_norm": 0.3522099554538727,
"learning_rate": 0.0001852823124209204,
"loss": 1.0547,
"step": 42
},
{
"epoch": 0.6417910447761194,
"grad_norm": 0.4999963939189911,
"learning_rate": 0.00018447797761440051,
"loss": 1.0523,
"step": 43
},
{
"epoch": 0.6567164179104478,
"grad_norm": 0.6665084362030029,
"learning_rate": 0.00018365431204452683,
"loss": 1.0204,
"step": 44
},
{
"epoch": 0.6716417910447762,
"grad_norm": 0.6554574370384216,
"learning_rate": 0.00018281152949374527,
"loss": 1.0063,
"step": 45
},
{
"epoch": 0.6865671641791045,
"grad_norm": 0.6276643872261047,
"learning_rate": 0.00018194984870631512,
"loss": 0.9716,
"step": 46
},
{
"epoch": 0.7014925373134329,
"grad_norm": 0.49094897508621216,
"learning_rate": 0.00018106949333153405,
"loss": 0.934,
"step": 47
},
{
"epoch": 0.7164179104477612,
"grad_norm": 0.4001779556274414,
"learning_rate": 0.00018017069186569001,
"loss": 0.9578,
"step": 48
},
{
"epoch": 0.7313432835820896,
"grad_norm": 0.40681931376457214,
"learning_rate": 0.00017925367759275495,
"loss": 0.8893,
"step": 49
},
{
"epoch": 0.746268656716418,
"grad_norm": 0.47569212317466736,
"learning_rate": 0.00017831868852383583,
"loss": 0.7641,
"step": 50
},
{
"epoch": 0.7611940298507462,
"grad_norm": 0.6968297362327576,
"learning_rate": 0.00017736596733539909,
"loss": 1.2385,
"step": 51
},
{
"epoch": 0.7761194029850746,
"grad_norm": 0.7256303429603577,
"learning_rate": 0.00017639576130628376,
"loss": 1.2058,
"step": 52
},
{
"epoch": 0.7910447761194029,
"grad_norm": 0.6893110275268555,
"learning_rate": 0.00017540832225352012,
"loss": 1.2222,
"step": 53
},
{
"epoch": 0.8059701492537313,
"grad_norm": 0.4945465326309204,
"learning_rate": 0.0001744039064669709,
"loss": 1.1218,
"step": 54
},
{
"epoch": 0.8208955223880597,
"grad_norm": 0.4019485414028168,
"learning_rate": 0.00017338277464281108,
"loss": 1.0477,
"step": 55
},
{
"epoch": 0.835820895522388,
"grad_norm": 0.3658827245235443,
"learning_rate": 0.00017234519181586396,
"loss": 1.0071,
"step": 56
},
{
"epoch": 0.8507462686567164,
"grad_norm": 0.3937952220439911,
"learning_rate": 0.00017129142729081177,
"loss": 0.9923,
"step": 57
},
{
"epoch": 0.8656716417910447,
"grad_norm": 0.4745718836784363,
"learning_rate": 0.00017022175457229725,
"loss": 0.9878,
"step": 58
},
{
"epoch": 0.8805970149253731,
"grad_norm": 0.5112557411193848,
"learning_rate": 0.00016913645129393578,
"loss": 0.9179,
"step": 59
},
{
"epoch": 0.8955223880597015,
"grad_norm": 0.5845867991447449,
"learning_rate": 0.00016803579914625535,
"loss": 0.9084,
"step": 60
},
{
"epoch": 0.9104477611940298,
"grad_norm": 0.5979167222976685,
"learning_rate": 0.00016692008380358395,
"loss": 0.953,
"step": 61
},
{
"epoch": 0.9253731343283582,
"grad_norm": 0.5538232922554016,
"learning_rate": 0.00016578959484990263,
"loss": 0.8545,
"step": 62
},
{
"epoch": 0.9402985074626866,
"grad_norm": 0.3931979835033417,
"learning_rate": 0.00016464462570368402,
"loss": 0.9686,
"step": 63
},
{
"epoch": 0.9552238805970149,
"grad_norm": 0.36252066493034363,
"learning_rate": 0.00016348547354173558,
"loss": 1.1047,
"step": 64
},
{
"epoch": 0.9701492537313433,
"grad_norm": 0.4850124418735504,
"learning_rate": 0.0001623124392220673,
"loss": 1.0296,
"step": 65
},
{
"epoch": 0.9850746268656716,
"grad_norm": 0.4648304879665375,
"learning_rate": 0.00016112582720580402,
"loss": 0.9287,
"step": 66
},
{
"epoch": 1.0,
"grad_norm": 0.3998699486255646,
"learning_rate": 0.0001599259454781625,
"loss": 0.9156,
"step": 67
},
{
"epoch": 1.0149253731343284,
"grad_norm": 0.421875536441803,
"learning_rate": 0.00015871310546851383,
"loss": 1.1974,
"step": 68
},
{
"epoch": 1.0298507462686568,
"grad_norm": 0.39584335684776306,
"learning_rate": 0.00015748762196955197,
"loss": 1.1015,
"step": 69
},
{
"epoch": 1.044776119402985,
"grad_norm": 0.37235844135284424,
"learning_rate": 0.00015624981305558918,
"loss": 1.0992,
"step": 70
},
{
"epoch": 1.0597014925373134,
"grad_norm": 0.3330038785934448,
"learning_rate": 0.000155,
"loss": 1.0614,
"step": 71
},
{
"epoch": 1.0746268656716418,
"grad_norm": 0.3231871724128723,
"learning_rate": 0.00015373850719183454,
"loss": 0.9913,
"step": 72
},
{
"epoch": 1.0895522388059702,
"grad_norm": 0.3235574960708618,
"learning_rate": 0.0001524656620516234,
"loss": 0.9477,
"step": 73
},
{
"epoch": 1.1044776119402986,
"grad_norm": 0.37417852878570557,
"learning_rate": 0.0001511817949463956,
"loss": 0.9286,
"step": 74
},
{
"epoch": 1.1194029850746268,
"grad_norm": 0.39474931359291077,
"learning_rate": 0.00014988723910393175,
"loss": 0.9042,
"step": 75
},
{
"epoch": 1.1343283582089552,
"grad_norm": 0.485606849193573,
"learning_rate": 0.00014858233052627488,
"loss": 0.8646,
"step": 76
},
{
"epoch": 1.1492537313432836,
"grad_norm": 0.49617916345596313,
"learning_rate": 0.00014726740790252108,
"loss": 0.8742,
"step": 77
},
{
"epoch": 1.164179104477612,
"grad_norm": 0.46328800916671753,
"learning_rate": 0.0001459428125209126,
"loss": 0.8256,
"step": 78
},
{
"epoch": 1.1791044776119404,
"grad_norm": 0.41910260915756226,
"learning_rate": 0.0001446088881802566,
"loss": 0.7242,
"step": 79
},
{
"epoch": 1.1940298507462686,
"grad_norm": 0.3721103072166443,
"learning_rate": 0.000143265981100692,
"loss": 0.9349,
"step": 80
},
{
"epoch": 1.208955223880597,
"grad_norm": 0.35940876603126526,
"learning_rate": 0.00014191443983382822,
"loss": 1.1032,
"step": 81
},
{
"epoch": 1.2238805970149254,
"grad_norm": 0.4461018145084381,
"learning_rate": 0.00014055461517227847,
"loss": 1.0979,
"step": 82
},
{
"epoch": 1.2388059701492538,
"grad_norm": 0.5155666470527649,
"learning_rate": 0.00013918686005861145,
"loss": 1.0231,
"step": 83
},
{
"epoch": 1.2537313432835822,
"grad_norm": 0.5260865092277527,
"learning_rate": 0.00013781152949374526,
"loss": 1.0228,
"step": 84
},
{
"epoch": 1.2686567164179103,
"grad_norm": 0.47857630252838135,
"learning_rate": 0.0001364289804448068,
"loss": 0.9576,
"step": 85
},
{
"epoch": 1.2835820895522387,
"grad_norm": 0.4128516912460327,
"learning_rate": 0.00013503957175248075,
"loss": 0.9763,
"step": 86
},
{
"epoch": 1.2985074626865671,
"grad_norm": 0.3800605535507202,
"learning_rate": 0.00013364366403787283,
"loss": 0.9272,
"step": 87
},
{
"epoch": 1.3134328358208955,
"grad_norm": 0.3839597702026367,
"learning_rate": 0.00013224161960891025,
"loss": 0.8632,
"step": 88
},
{
"epoch": 1.328358208955224,
"grad_norm": 0.4173763394355774,
"learning_rate": 0.0001308338023663049,
"loss": 0.8838,
"step": 89
},
{
"epoch": 1.3432835820895521,
"grad_norm": 0.5093969106674194,
"learning_rate": 0.00012942057770910255,
"loss": 0.8444,
"step": 90
},
{
"epoch": 1.3582089552238805,
"grad_norm": 0.5481818914413452,
"learning_rate": 0.00012800231243984401,
"loss": 0.7714,
"step": 91
},
{
"epoch": 1.373134328358209,
"grad_norm": 0.6201927065849304,
"learning_rate": 0.00012657937466936106,
"loss": 0.707,
"step": 92
},
{
"epoch": 1.3880597014925373,
"grad_norm": 0.5079281330108643,
"learning_rate": 0.00012515213372123345,
"loss": 1.1623,
"step": 93
},
{
"epoch": 1.4029850746268657,
"grad_norm": 0.4763680398464203,
"learning_rate": 0.0001237209600359311,
"loss": 1.1181,
"step": 94
},
{
"epoch": 1.417910447761194,
"grad_norm": 0.38111981749534607,
"learning_rate": 0.00012228622507466587,
"loss": 0.9978,
"step": 95
},
{
"epoch": 1.4328358208955223,
"grad_norm": 0.38934579491615295,
"learning_rate": 0.00012084830122297907,
"loss": 1.0207,
"step": 96
},
{
"epoch": 1.4477611940298507,
"grad_norm": 0.5346177816390991,
"learning_rate": 0.00011940756169408881,
"loss": 1.0358,
"step": 97
},
{
"epoch": 1.462686567164179,
"grad_norm": 0.5502073764801025,
"learning_rate": 0.00011796438043202227,
"loss": 0.919,
"step": 98
},
{
"epoch": 1.4776119402985075,
"grad_norm": 0.5650199055671692,
"learning_rate": 0.00011651913201455864,
"loss": 0.9101,
"step": 99
},
{
"epoch": 1.4925373134328357,
"grad_norm": 0.46825388073921204,
"learning_rate": 0.00011507219155600737,
"loss": 0.9228,
"step": 100
},
{
"epoch": 1.5074626865671643,
"grad_norm": 0.42388054728507996,
"learning_rate": 0.00011362393460984737,
"loss": 0.8535,
"step": 101
},
{
"epoch": 1.5223880597014925,
"grad_norm": 0.39270514249801636,
"learning_rate": 0.00011217473707125192,
"loss": 0.8353,
"step": 102
},
{
"epoch": 1.537313432835821,
"grad_norm": 0.42990821599960327,
"learning_rate": 0.0001107249750795251,
"loss": 0.7997,
"step": 103
},
{
"epoch": 1.5522388059701493,
"grad_norm": 0.4879288375377655,
"learning_rate": 0.00010927502492047492,
"loss": 0.7087,
"step": 104
},
{
"epoch": 1.5671641791044775,
"grad_norm": 0.4773794114589691,
"learning_rate": 0.00010782526292874813,
"loss": 0.9446,
"step": 105
},
{
"epoch": 1.582089552238806,
"grad_norm": 0.3559342622756958,
"learning_rate": 0.00010637606539015268,
"loss": 1.0926,
"step": 106
},
{
"epoch": 1.5970149253731343,
"grad_norm": 0.38176605105400085,
"learning_rate": 0.00010492780844399264,
"loss": 1.0961,
"step": 107
},
{
"epoch": 1.6119402985074627,
"grad_norm": 0.37334877252578735,
"learning_rate": 0.00010348086798544141,
"loss": 1.0699,
"step": 108
},
{
"epoch": 1.626865671641791,
"grad_norm": 0.34911951422691345,
"learning_rate": 0.00010203561956797775,
"loss": 0.9812,
"step": 109
},
{
"epoch": 1.6417910447761193,
"grad_norm": 0.35348981618881226,
"learning_rate": 0.00010059243830591121,
"loss": 0.9875,
"step": 110
},
{
"epoch": 1.6567164179104479,
"grad_norm": 0.36440154910087585,
"learning_rate": 9.915169877702095e-05,
"loss": 0.9164,
"step": 111
},
{
"epoch": 1.671641791044776,
"grad_norm": 0.3861341178417206,
"learning_rate": 9.771377492533418e-05,
"loss": 0.865,
"step": 112
},
{
"epoch": 1.6865671641791045,
"grad_norm": 0.4054892957210541,
"learning_rate": 9.627903996406892e-05,
"loss": 0.8351,
"step": 113
},
{
"epoch": 1.7014925373134329,
"grad_norm": 0.4275088906288147,
"learning_rate": 9.484786627876654e-05,
"loss": 0.8281,
"step": 114
},
{
"epoch": 1.716417910447761,
"grad_norm": 0.420304536819458,
"learning_rate": 9.342062533063898e-05,
"loss": 0.8573,
"step": 115
},
{
"epoch": 1.7313432835820897,
"grad_norm": 0.3914477527141571,
"learning_rate": 9.199768756015603e-05,
"loss": 0.7773,
"step": 116
},
{
"epoch": 1.7462686567164178,
"grad_norm": 0.43206727504730225,
"learning_rate": 9.057942229089747e-05,
"loss": 0.7021,
"step": 117
},
{
"epoch": 1.7611940298507462,
"grad_norm": 0.43827471137046814,
"learning_rate": 8.916619763369516e-05,
"loss": 1.1523,
"step": 118
},
{
"epoch": 1.7761194029850746,
"grad_norm": 0.3688608407974243,
"learning_rate": 8.775838039108974e-05,
"loss": 1.0733,
"step": 119
},
{
"epoch": 1.7910447761194028,
"grad_norm": 0.35826849937438965,
"learning_rate": 8.635633596212718e-05,
"loss": 1.0442,
"step": 120
},
{
"epoch": 1.8059701492537314,
"grad_norm": 0.35874509811401367,
"learning_rate": 8.496042824751926e-05,
"loss": 1.0133,
"step": 121
},
{
"epoch": 1.8208955223880596,
"grad_norm": 0.3662901818752289,
"learning_rate": 8.357101955519324e-05,
"loss": 0.9586,
"step": 122
},
{
"epoch": 1.835820895522388,
"grad_norm": 0.3741875886917114,
"learning_rate": 8.218847050625476e-05,
"loss": 0.9409,
"step": 123
},
{
"epoch": 1.8507462686567164,
"grad_norm": 0.378964364528656,
"learning_rate": 8.081313994138857e-05,
"loss": 0.8868,
"step": 124
},
{
"epoch": 1.8656716417910446,
"grad_norm": 0.3909272849559784,
"learning_rate": 7.944538482772156e-05,
"loss": 0.8837,
"step": 125
},
{
"epoch": 1.8805970149253732,
"grad_norm": 0.41188931465148926,
"learning_rate": 7.808556016617178e-05,
"loss": 0.8514,
"step": 126
},
{
"epoch": 1.8955223880597014,
"grad_norm": 0.4490172863006592,
"learning_rate": 7.673401889930802e-05,
"loss": 0.8751,
"step": 127
},
{
"epoch": 1.9104477611940298,
"grad_norm": 0.47430258989334106,
"learning_rate": 7.539111181974343e-05,
"loss": 0.8221,
"step": 128
},
{
"epoch": 1.9253731343283582,
"grad_norm": 0.4374563992023468,
"learning_rate": 7.405718747908743e-05,
"loss": 0.7239,
"step": 129
},
{
"epoch": 1.9402985074626866,
"grad_norm": 0.4078747034072876,
"learning_rate": 7.273259209747896e-05,
"loss": 0.8874,
"step": 130
},
{
"epoch": 1.955223880597015,
"grad_norm": 0.42563360929489136,
"learning_rate": 7.141766947372512e-05,
"loss": 1.0419,
"step": 131
},
{
"epoch": 1.9701492537313432,
"grad_norm": 0.4324108362197876,
"learning_rate": 7.011276089606829e-05,
"loss": 0.948,
"step": 132
},
{
"epoch": 1.9850746268656716,
"grad_norm": 0.42789846658706665,
"learning_rate": 6.881820505360443e-05,
"loss": 0.852,
"step": 133
},
{
"epoch": 2.0,
"grad_norm": 0.39731353521347046,
"learning_rate": 6.753433794837662e-05,
"loss": 0.8727,
"step": 134
},
{
"epoch": 2.014925373134328,
"grad_norm": 0.35240477323532104,
"learning_rate": 6.626149280816546e-05,
"loss": 1.0679,
"step": 135
},
{
"epoch": 2.029850746268657,
"grad_norm": 0.33283913135528564,
"learning_rate": 6.500000000000002e-05,
"loss": 1.0181,
"step": 136
},
{
"epoch": 2.044776119402985,
"grad_norm": 0.3615310788154602,
"learning_rate": 6.375018694441084e-05,
"loss": 0.9978,
"step": 137
},
{
"epoch": 2.0597014925373136,
"grad_norm": 0.36938410997390747,
"learning_rate": 6.251237803044805e-05,
"loss": 0.9883,
"step": 138
},
{
"epoch": 2.074626865671642,
"grad_norm": 0.3807987570762634,
"learning_rate": 6.128689453148619e-05,
"loss": 0.9572,
"step": 139
},
{
"epoch": 2.08955223880597,
"grad_norm": 0.37807610630989075,
"learning_rate": 6.00740545218375e-05,
"loss": 0.9174,
"step": 140
},
{
"epoch": 2.1044776119402986,
"grad_norm": 0.37602487206459045,
"learning_rate": 5.887417279419599e-05,
"loss": 0.8229,
"step": 141
},
{
"epoch": 2.1194029850746268,
"grad_norm": 0.35350197553634644,
"learning_rate": 5.7687560777932735e-05,
"loss": 0.8076,
"step": 142
},
{
"epoch": 2.1343283582089554,
"grad_norm": 0.3940332233905792,
"learning_rate": 5.651452645826445e-05,
"loss": 0.788,
"step": 143
},
{
"epoch": 2.1492537313432836,
"grad_norm": 0.46034398674964905,
"learning_rate": 5.5355374296315995e-05,
"loss": 0.7882,
"step": 144
},
{
"epoch": 2.1641791044776117,
"grad_norm": 0.4225603938102722,
"learning_rate": 5.421040515009737e-05,
"loss": 0.7197,
"step": 145
},
{
"epoch": 2.1791044776119404,
"grad_norm": 0.46008700132369995,
"learning_rate": 5.3079916196416055e-05,
"loss": 0.6569,
"step": 146
},
{
"epoch": 2.1940298507462686,
"grad_norm": 0.41973477602005005,
"learning_rate": 5.196420085374467e-05,
"loss": 0.8682,
"step": 147
},
{
"epoch": 2.208955223880597,
"grad_norm": 0.3677213191986084,
"learning_rate": 5.0863548706064245e-05,
"loss": 1.0353,
"step": 148
},
{
"epoch": 2.2238805970149254,
"grad_norm": 0.37162861227989197,
"learning_rate": 4.977824542770279e-05,
"loss": 1.001,
"step": 149
},
{
"epoch": 2.2388059701492535,
"grad_norm": 0.39737215638160706,
"learning_rate": 4.870857270918825e-05,
"loss": 0.9846,
"step": 150
},
{
"epoch": 2.253731343283582,
"grad_norm": 0.38380125164985657,
"learning_rate": 4.7654808184136064e-05,
"loss": 0.9606,
"step": 151
},
{
"epoch": 2.2686567164179103,
"grad_norm": 0.40244144201278687,
"learning_rate": 4.6617225357188976e-05,
"loss": 0.8571,
"step": 152
},
{
"epoch": 2.283582089552239,
"grad_norm": 0.4329751431941986,
"learning_rate": 4.5596093533029116e-05,
"loss": 0.8531,
"step": 153
},
{
"epoch": 2.298507462686567,
"grad_norm": 0.45405519008636475,
"learning_rate": 4.459167774647993e-05,
"loss": 0.8512,
"step": 154
},
{
"epoch": 2.3134328358208958,
"grad_norm": 0.45590460300445557,
"learning_rate": 4.360423869371629e-05,
"loss": 0.8208,
"step": 155
},
{
"epoch": 2.328358208955224,
"grad_norm": 0.4376915395259857,
"learning_rate": 4.2634032664600895e-05,
"loss": 0.7654,
"step": 156
},
{
"epoch": 2.343283582089552,
"grad_norm": 0.45759543776512146,
"learning_rate": 4.168131147616417e-05,
"loss": 0.7857,
"step": 157
},
{
"epoch": 2.3582089552238807,
"grad_norm": 0.4490528702735901,
"learning_rate": 4.0746322407245066e-05,
"loss": 0.7051,
"step": 158
},
{
"epoch": 2.373134328358209,
"grad_norm": 0.4924563765525818,
"learning_rate": 3.982930813430999e-05,
"loss": 0.6348,
"step": 159
},
{
"epoch": 2.388059701492537,
"grad_norm": 0.35502833127975464,
"learning_rate": 3.893050666846596e-05,
"loss": 1.1142,
"step": 160
},
{
"epoch": 2.4029850746268657,
"grad_norm": 0.3795003890991211,
"learning_rate": 3.805015129368492e-05,
"loss": 1.0387,
"step": 161
},
{
"epoch": 2.417910447761194,
"grad_norm": 0.3922593593597412,
"learning_rate": 3.718847050625475e-05,
"loss": 1.0402,
"step": 162
},
{
"epoch": 2.4328358208955225,
"grad_norm": 0.4245050251483917,
"learning_rate": 3.6345687955473166e-05,
"loss": 0.9854,
"step": 163
},
{
"epoch": 2.4477611940298507,
"grad_norm": 0.39441049098968506,
"learning_rate": 3.552202238559953e-05,
"loss": 0.9561,
"step": 164
},
{
"epoch": 2.4626865671641793,
"grad_norm": 0.39788442850112915,
"learning_rate": 3.4717687579079596e-05,
"loss": 0.9104,
"step": 165
},
{
"epoch": 2.4776119402985075,
"grad_norm": 0.4182056784629822,
"learning_rate": 3.393289230105849e-05,
"loss": 0.8841,
"step": 166
},
{
"epoch": 2.4925373134328357,
"grad_norm": 0.42861151695251465,
"learning_rate": 3.316784024519553e-05,
"loss": 0.8055,
"step": 167
},
{
"epoch": 2.5074626865671643,
"grad_norm": 0.42246565222740173,
"learning_rate": 3.242272998079557e-05,
"loss": 0.7947,
"step": 168
},
{
"epoch": 2.5223880597014925,
"grad_norm": 0.46474263072013855,
"learning_rate": 3.1697754901270473e-05,
"loss": 0.8153,
"step": 169
},
{
"epoch": 2.5373134328358207,
"grad_norm": 0.4996289312839508,
"learning_rate": 3.099310317394359e-05,
"loss": 0.7579,
"step": 170
},
{
"epoch": 2.5522388059701493,
"grad_norm": 0.47399628162384033,
"learning_rate": 3.030895769121112e-05,
"loss": 0.6813,
"step": 171
},
{
"epoch": 2.5671641791044775,
"grad_norm": 0.4417833983898163,
"learning_rate": 2.9645496023072244e-05,
"loss": 0.8971,
"step": 172
},
{
"epoch": 2.582089552238806,
"grad_norm": 0.3691651225090027,
"learning_rate": 2.9002890371040918e-05,
"loss": 1.0862,
"step": 173
},
{
"epoch": 2.5970149253731343,
"grad_norm": 0.4065288007259369,
"learning_rate": 2.8381307523450916e-05,
"loss": 1.031,
"step": 174
},
{
"epoch": 2.611940298507463,
"grad_norm": 0.3905118405818939,
"learning_rate": 2.778090881216592e-05,
"loss": 0.9701,
"step": 175
},
{
"epoch": 2.626865671641791,
"grad_norm": 0.39984792470932007,
"learning_rate": 2.7201850070705826e-05,
"loss": 0.9493,
"step": 176
},
{
"epoch": 2.6417910447761193,
"grad_norm": 0.415585994720459,
"learning_rate": 2.664428159380013e-05,
"loss": 0.9129,
"step": 177
},
{
"epoch": 2.656716417910448,
"grad_norm": 0.42336076498031616,
"learning_rate": 2.610834809837891e-05,
"loss": 0.8791,
"step": 178
},
{
"epoch": 2.671641791044776,
"grad_norm": 0.45662274956703186,
"learning_rate": 2.5594188686011615e-05,
"loss": 0.871,
"step": 179
},
{
"epoch": 2.6865671641791042,
"grad_norm": 0.4160149395465851,
"learning_rate": 2.5101936806803117e-05,
"loss": 0.7626,
"step": 180
},
{
"epoch": 2.701492537313433,
"grad_norm": 0.43893417716026306,
"learning_rate": 2.463172022475691e-05,
"loss": 0.8046,
"step": 181
},
{
"epoch": 2.716417910447761,
"grad_norm": 0.4579525291919708,
"learning_rate": 2.418366098461374e-05,
"loss": 0.7713,
"step": 182
},
{
"epoch": 2.7313432835820897,
"grad_norm": 0.4761490523815155,
"learning_rate": 2.3757875380175044e-05,
"loss": 0.69,
"step": 183
},
{
"epoch": 2.746268656716418,
"grad_norm": 0.5591773986816406,
"learning_rate": 2.3354473924118842e-05,
"loss": 0.6075,
"step": 184
},
{
"epoch": 2.7611940298507465,
"grad_norm": 0.3821795880794525,
"learning_rate": 2.297356131931614e-05,
"loss": 1.0839,
"step": 185
},
{
"epoch": 2.7761194029850746,
"grad_norm": 0.37466174364089966,
"learning_rate": 2.261523643165532e-05,
"loss": 1.0221,
"step": 186
},
{
"epoch": 2.791044776119403,
"grad_norm": 0.3825508654117584,
"learning_rate": 2.22795922643815e-05,
"loss": 1.0,
"step": 187
},
{
"epoch": 2.8059701492537314,
"grad_norm": 0.41949060559272766,
"learning_rate": 2.196671593395749e-05,
"loss": 0.9473,
"step": 188
},
{
"epoch": 2.8208955223880596,
"grad_norm": 0.42044076323509216,
"learning_rate": 2.167668864745279e-05,
"loss": 0.8887,
"step": 189
},
{
"epoch": 2.835820895522388,
"grad_norm": 0.4112393856048584,
"learning_rate": 2.1409585681466204e-05,
"loss": 0.8724,
"step": 190
},
{
"epoch": 2.8507462686567164,
"grad_norm": 0.45745235681533813,
"learning_rate": 2.1165476362587846e-05,
"loss": 0.8562,
"step": 191
},
{
"epoch": 2.8656716417910446,
"grad_norm": 0.4491675794124603,
"learning_rate": 2.09444240494054e-05,
"loss": 0.8593,
"step": 192
},
{
"epoch": 2.8805970149253732,
"grad_norm": 0.4317816197872162,
"learning_rate": 2.0746486116059418e-05,
"loss": 0.7933,
"step": 193
},
{
"epoch": 2.8955223880597014,
"grad_norm": 0.46604618430137634,
"learning_rate": 2.0571713937351834e-05,
"loss": 0.7903,
"step": 194
},
{
"epoch": 2.91044776119403,
"grad_norm": 0.48169732093811035,
"learning_rate": 2.0420152875411624e-05,
"loss": 0.7668,
"step": 195
},
{
"epoch": 2.925373134328358,
"grad_norm": 0.4627380073070526,
"learning_rate": 2.0291842267921108e-05,
"loss": 0.6404,
"step": 196
},
{
"epoch": 2.9402985074626864,
"grad_norm": 0.44821980595588684,
"learning_rate": 2.0186815417905787e-05,
"loss": 0.8672,
"step": 197
},
{
"epoch": 2.955223880597015,
"grad_norm": 0.3909732699394226,
"learning_rate": 2.0105099585090603e-05,
"loss": 0.9487,
"step": 198
},
{
"epoch": 2.970149253731343,
"grad_norm": 0.4137306213378906,
"learning_rate": 2.0046715978824664e-05,
"loss": 0.8438,
"step": 199
},
{
"epoch": 2.9850746268656714,
"grad_norm": 0.4548170864582062,
"learning_rate": 2.001167975257628e-05,
"loss": 0.8052,
"step": 200
},
{
"epoch": 3.0,
"grad_norm": 0.4302070140838623,
"learning_rate": 2e-05,
"loss": 0.8199,
"step": 201
}
],
"logging_steps": 1,
"max_steps": 201,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 5.25183025013588e+17,
"train_batch_size": 18,
"trial_name": null,
"trial_params": null
}