jssky's picture
Training in progress, step 280, checkpoint
76f9231 verified
raw
history blame
49.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5,
"eval_steps": 140,
"global_step": 280,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0017857142857142857,
"grad_norm": 0.14711466431617737,
"learning_rate": 2e-05,
"loss": 1.6301,
"step": 1
},
{
"epoch": 0.0035714285714285713,
"grad_norm": 0.13304685056209564,
"learning_rate": 4e-05,
"loss": 1.6271,
"step": 2
},
{
"epoch": 0.005357142857142857,
"grad_norm": 0.1233660876750946,
"learning_rate": 6e-05,
"loss": 1.6548,
"step": 3
},
{
"epoch": 0.007142857142857143,
"grad_norm": 0.1381577104330063,
"learning_rate": 8e-05,
"loss": 1.7853,
"step": 4
},
{
"epoch": 0.008928571428571428,
"grad_norm": 0.14668770134449005,
"learning_rate": 0.0001,
"loss": 1.7507,
"step": 5
},
{
"epoch": 0.010714285714285714,
"grad_norm": 0.168854758143425,
"learning_rate": 0.00012,
"loss": 1.9486,
"step": 6
},
{
"epoch": 0.0125,
"grad_norm": 0.2166246473789215,
"learning_rate": 0.00014,
"loss": 1.9167,
"step": 7
},
{
"epoch": 0.014285714285714285,
"grad_norm": 0.23894698917865753,
"learning_rate": 0.00016,
"loss": 1.8384,
"step": 8
},
{
"epoch": 0.01607142857142857,
"grad_norm": 0.2704271674156189,
"learning_rate": 0.00018,
"loss": 1.8232,
"step": 9
},
{
"epoch": 0.017857142857142856,
"grad_norm": 0.24295401573181152,
"learning_rate": 0.0002,
"loss": 2.1559,
"step": 10
},
{
"epoch": 0.019642857142857142,
"grad_norm": 0.23109205067157745,
"learning_rate": 0.00019999836866486503,
"loss": 1.7082,
"step": 11
},
{
"epoch": 0.02142857142857143,
"grad_norm": 0.205198273062706,
"learning_rate": 0.00019999347471268516,
"loss": 1.8417,
"step": 12
},
{
"epoch": 0.023214285714285715,
"grad_norm": 0.2678169012069702,
"learning_rate": 0.00019998531830313395,
"loss": 1.9222,
"step": 13
},
{
"epoch": 0.025,
"grad_norm": 0.2563900053501129,
"learning_rate": 0.0001999738997023281,
"loss": 1.8931,
"step": 14
},
{
"epoch": 0.026785714285714284,
"grad_norm": 0.31391921639442444,
"learning_rate": 0.00019995921928281894,
"loss": 1.9403,
"step": 15
},
{
"epoch": 0.02857142857142857,
"grad_norm": 0.23522017896175385,
"learning_rate": 0.00019994127752358013,
"loss": 1.8728,
"step": 16
},
{
"epoch": 0.030357142857142857,
"grad_norm": 0.2517368495464325,
"learning_rate": 0.00019992007500999214,
"loss": 1.9224,
"step": 17
},
{
"epoch": 0.03214285714285714,
"grad_norm": 0.27111852169036865,
"learning_rate": 0.00019989561243382312,
"loss": 1.9046,
"step": 18
},
{
"epoch": 0.033928571428571426,
"grad_norm": 0.2616860568523407,
"learning_rate": 0.00019986789059320615,
"loss": 2.1173,
"step": 19
},
{
"epoch": 0.03571428571428571,
"grad_norm": 0.23268847167491913,
"learning_rate": 0.00019983691039261357,
"loss": 1.8406,
"step": 20
},
{
"epoch": 0.0375,
"grad_norm": 0.30090174078941345,
"learning_rate": 0.00019980267284282717,
"loss": 1.7514,
"step": 21
},
{
"epoch": 0.039285714285714285,
"grad_norm": 0.23314997553825378,
"learning_rate": 0.00019976517906090529,
"loss": 1.7518,
"step": 22
},
{
"epoch": 0.04107142857142857,
"grad_norm": 0.2630898952484131,
"learning_rate": 0.0001997244302701464,
"loss": 1.7533,
"step": 23
},
{
"epoch": 0.04285714285714286,
"grad_norm": 0.3203246593475342,
"learning_rate": 0.00019968042780004917,
"loss": 1.534,
"step": 24
},
{
"epoch": 0.044642857142857144,
"grad_norm": 0.48179084062576294,
"learning_rate": 0.00019963317308626914,
"loss": 1.4211,
"step": 25
},
{
"epoch": 0.04642857142857143,
"grad_norm": 0.36420196294784546,
"learning_rate": 0.0001995826676705718,
"loss": 1.4275,
"step": 26
},
{
"epoch": 0.048214285714285716,
"grad_norm": 0.35330235958099365,
"learning_rate": 0.00019952891320078236,
"loss": 1.5612,
"step": 27
},
{
"epoch": 0.05,
"grad_norm": 0.27140146493911743,
"learning_rate": 0.00019947191143073186,
"loss": 1.6001,
"step": 28
},
{
"epoch": 0.05178571428571429,
"grad_norm": 0.2987808883190155,
"learning_rate": 0.00019941166422020014,
"loss": 1.3943,
"step": 29
},
{
"epoch": 0.05357142857142857,
"grad_norm": 0.3032172918319702,
"learning_rate": 0.00019934817353485501,
"loss": 1.4888,
"step": 30
},
{
"epoch": 0.055357142857142855,
"grad_norm": 0.6096982359886169,
"learning_rate": 0.00019928144144618824,
"loss": 1.7057,
"step": 31
},
{
"epoch": 0.05714285714285714,
"grad_norm": 0.30788663029670715,
"learning_rate": 0.0001992114701314478,
"loss": 1.3929,
"step": 32
},
{
"epoch": 0.05892857142857143,
"grad_norm": 0.33283260464668274,
"learning_rate": 0.00019913826187356696,
"loss": 1.5611,
"step": 33
},
{
"epoch": 0.060714285714285714,
"grad_norm": 0.3044683337211609,
"learning_rate": 0.00019906181906108984,
"loss": 1.2961,
"step": 34
},
{
"epoch": 0.0625,
"grad_norm": 0.3300105929374695,
"learning_rate": 0.0001989821441880933,
"loss": 1.3975,
"step": 35
},
{
"epoch": 0.06428571428571428,
"grad_norm": 0.3126329481601715,
"learning_rate": 0.00019889923985410576,
"loss": 1.2759,
"step": 36
},
{
"epoch": 0.06607142857142857,
"grad_norm": 0.33685699105262756,
"learning_rate": 0.00019881310876402223,
"loss": 1.162,
"step": 37
},
{
"epoch": 0.06785714285714285,
"grad_norm": 0.3971424996852875,
"learning_rate": 0.0001987237537280163,
"loss": 1.21,
"step": 38
},
{
"epoch": 0.06964285714285715,
"grad_norm": 0.43255800008773804,
"learning_rate": 0.00019863117766144806,
"loss": 1.0186,
"step": 39
},
{
"epoch": 0.07142857142857142,
"grad_norm": 0.4930873215198517,
"learning_rate": 0.00019853538358476932,
"loss": 1.0045,
"step": 40
},
{
"epoch": 0.07321428571428572,
"grad_norm": 0.4585554599761963,
"learning_rate": 0.00019843637462342497,
"loss": 1.1077,
"step": 41
},
{
"epoch": 0.075,
"grad_norm": 0.4778697192668915,
"learning_rate": 0.00019833415400775093,
"loss": 1.0817,
"step": 42
},
{
"epoch": 0.07678571428571429,
"grad_norm": 0.4595739245414734,
"learning_rate": 0.0001982287250728689,
"loss": 1.2805,
"step": 43
},
{
"epoch": 0.07857142857142857,
"grad_norm": 0.5665370225906372,
"learning_rate": 0.00019812009125857728,
"loss": 0.9855,
"step": 44
},
{
"epoch": 0.08035714285714286,
"grad_norm": 0.40399685502052307,
"learning_rate": 0.00019800825610923934,
"loss": 1.3264,
"step": 45
},
{
"epoch": 0.08214285714285714,
"grad_norm": 0.43560901284217834,
"learning_rate": 0.00019789322327366723,
"loss": 1.2724,
"step": 46
},
{
"epoch": 0.08392857142857142,
"grad_norm": 0.375598669052124,
"learning_rate": 0.000197774996505003,
"loss": 1.1722,
"step": 47
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.4257534146308899,
"learning_rate": 0.00019765357966059638,
"loss": 1.3607,
"step": 48
},
{
"epoch": 0.0875,
"grad_norm": 0.5437749028205872,
"learning_rate": 0.0001975289767018786,
"loss": 1.9812,
"step": 49
},
{
"epoch": 0.08928571428571429,
"grad_norm": 0.6295837163925171,
"learning_rate": 0.00019740119169423337,
"loss": 2.1601,
"step": 50
},
{
"epoch": 0.09107142857142857,
"grad_norm": 0.22341597080230713,
"learning_rate": 0.00019727022880686412,
"loss": 1.7096,
"step": 51
},
{
"epoch": 0.09285714285714286,
"grad_norm": 0.26040709018707275,
"learning_rate": 0.00019713609231265805,
"loss": 1.733,
"step": 52
},
{
"epoch": 0.09464285714285714,
"grad_norm": 0.2146587371826172,
"learning_rate": 0.00019699878658804672,
"loss": 1.7999,
"step": 53
},
{
"epoch": 0.09642857142857143,
"grad_norm": 0.2316572070121765,
"learning_rate": 0.0001968583161128631,
"loss": 1.6017,
"step": 54
},
{
"epoch": 0.09821428571428571,
"grad_norm": 0.20329022407531738,
"learning_rate": 0.00019671468547019573,
"loss": 1.7464,
"step": 55
},
{
"epoch": 0.1,
"grad_norm": 0.22198128700256348,
"learning_rate": 0.00019656789934623881,
"loss": 1.7584,
"step": 56
},
{
"epoch": 0.10178571428571428,
"grad_norm": 0.2108459621667862,
"learning_rate": 0.00019641796253013958,
"loss": 1.7389,
"step": 57
},
{
"epoch": 0.10357142857142858,
"grad_norm": 0.2677428126335144,
"learning_rate": 0.00019626487991384196,
"loss": 1.9166,
"step": 58
},
{
"epoch": 0.10535714285714286,
"grad_norm": 0.22205914556980133,
"learning_rate": 0.00019610865649192697,
"loss": 1.738,
"step": 59
},
{
"epoch": 0.10714285714285714,
"grad_norm": 0.22724869847297668,
"learning_rate": 0.00019594929736144976,
"loss": 1.7451,
"step": 60
},
{
"epoch": 0.10892857142857143,
"grad_norm": 0.24029673635959625,
"learning_rate": 0.00019578680772177327,
"loss": 1.9556,
"step": 61
},
{
"epoch": 0.11071428571428571,
"grad_norm": 0.2240082174539566,
"learning_rate": 0.00019562119287439873,
"loss": 1.6435,
"step": 62
},
{
"epoch": 0.1125,
"grad_norm": 0.23900961875915527,
"learning_rate": 0.00019545245822279243,
"loss": 1.7015,
"step": 63
},
{
"epoch": 0.11428571428571428,
"grad_norm": 0.2319100946187973,
"learning_rate": 0.0001952806092722098,
"loss": 1.7287,
"step": 64
},
{
"epoch": 0.11607142857142858,
"grad_norm": 0.22805678844451904,
"learning_rate": 0.00019510565162951537,
"loss": 1.7574,
"step": 65
},
{
"epoch": 0.11785714285714285,
"grad_norm": 0.2389436662197113,
"learning_rate": 0.00019492759100300019,
"loss": 1.7738,
"step": 66
},
{
"epoch": 0.11964285714285715,
"grad_norm": 0.23373426496982574,
"learning_rate": 0.00019474643320219532,
"loss": 1.5328,
"step": 67
},
{
"epoch": 0.12142857142857143,
"grad_norm": 0.2664267420768738,
"learning_rate": 0.0001945621841376825,
"loss": 2.0273,
"step": 68
},
{
"epoch": 0.12321428571428572,
"grad_norm": 0.2796079218387604,
"learning_rate": 0.0001943748498209012,
"loss": 1.547,
"step": 69
},
{
"epoch": 0.125,
"grad_norm": 0.2695769667625427,
"learning_rate": 0.00019418443636395248,
"loss": 1.6374,
"step": 70
},
{
"epoch": 0.12678571428571428,
"grad_norm": 0.3933340311050415,
"learning_rate": 0.00019399094997939957,
"loss": 1.2037,
"step": 71
},
{
"epoch": 0.12857142857142856,
"grad_norm": 0.2825562357902527,
"learning_rate": 0.0001937943969800652,
"loss": 1.5649,
"step": 72
},
{
"epoch": 0.13035714285714287,
"grad_norm": 0.3704264760017395,
"learning_rate": 0.00019359478377882567,
"loss": 1.292,
"step": 73
},
{
"epoch": 0.13214285714285715,
"grad_norm": 0.3214375972747803,
"learning_rate": 0.00019339211688840157,
"loss": 1.2539,
"step": 74
},
{
"epoch": 0.13392857142857142,
"grad_norm": 0.337907612323761,
"learning_rate": 0.00019318640292114524,
"loss": 1.3202,
"step": 75
},
{
"epoch": 0.1357142857142857,
"grad_norm": 0.30557796359062195,
"learning_rate": 0.00019297764858882514,
"loss": 1.074,
"step": 76
},
{
"epoch": 0.1375,
"grad_norm": 0.3154335916042328,
"learning_rate": 0.00019276586070240682,
"loss": 1.1813,
"step": 77
},
{
"epoch": 0.1392857142857143,
"grad_norm": 0.3587944209575653,
"learning_rate": 0.0001925510461718307,
"loss": 1.3602,
"step": 78
},
{
"epoch": 0.14107142857142857,
"grad_norm": 0.35669559240341187,
"learning_rate": 0.0001923332120057866,
"loss": 1.3626,
"step": 79
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.48954322934150696,
"learning_rate": 0.000192112365311485,
"loss": 1.4762,
"step": 80
},
{
"epoch": 0.14464285714285716,
"grad_norm": 0.4903950095176697,
"learning_rate": 0.00019188851329442547,
"loss": 1.6974,
"step": 81
},
{
"epoch": 0.14642857142857144,
"grad_norm": 0.35062992572784424,
"learning_rate": 0.00019166166325816118,
"loss": 1.2373,
"step": 82
},
{
"epoch": 0.14821428571428572,
"grad_norm": 0.5671891570091248,
"learning_rate": 0.0001914318226040608,
"loss": 1.5644,
"step": 83
},
{
"epoch": 0.15,
"grad_norm": 0.338214248418808,
"learning_rate": 0.000191198998831067,
"loss": 1.3717,
"step": 84
},
{
"epoch": 0.15178571428571427,
"grad_norm": 0.4187781512737274,
"learning_rate": 0.00019096319953545185,
"loss": 1.1211,
"step": 85
},
{
"epoch": 0.15357142857142858,
"grad_norm": 0.3229452967643738,
"learning_rate": 0.00019072443241056883,
"loss": 1.0473,
"step": 86
},
{
"epoch": 0.15535714285714286,
"grad_norm": 0.376589298248291,
"learning_rate": 0.00019048270524660196,
"loss": 0.9684,
"step": 87
},
{
"epoch": 0.15714285714285714,
"grad_norm": 0.4261431396007538,
"learning_rate": 0.00019023802593031154,
"loss": 1.0243,
"step": 88
},
{
"epoch": 0.15892857142857142,
"grad_norm": 0.4411628544330597,
"learning_rate": 0.0001899904024447769,
"loss": 1.2739,
"step": 89
},
{
"epoch": 0.16071428571428573,
"grad_norm": 0.3415679335594177,
"learning_rate": 0.00018973984286913584,
"loss": 1.2494,
"step": 90
},
{
"epoch": 0.1625,
"grad_norm": 0.48547816276550293,
"learning_rate": 0.0001894863553783212,
"loss": 1.0384,
"step": 91
},
{
"epoch": 0.16428571428571428,
"grad_norm": 0.398359090089798,
"learning_rate": 0.00018922994824279395,
"loss": 1.2409,
"step": 92
},
{
"epoch": 0.16607142857142856,
"grad_norm": 0.4025682806968689,
"learning_rate": 0.00018897062982827344,
"loss": 1.0646,
"step": 93
},
{
"epoch": 0.16785714285714284,
"grad_norm": 0.46782195568084717,
"learning_rate": 0.00018870840859546456,
"loss": 1.2167,
"step": 94
},
{
"epoch": 0.16964285714285715,
"grad_norm": 0.45423248410224915,
"learning_rate": 0.00018844329309978145,
"loss": 1.2359,
"step": 95
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.380495548248291,
"learning_rate": 0.0001881752919910686,
"loss": 1.0583,
"step": 96
},
{
"epoch": 0.1732142857142857,
"grad_norm": 0.41103506088256836,
"learning_rate": 0.00018790441401331847,
"loss": 1.2755,
"step": 97
},
{
"epoch": 0.175,
"grad_norm": 0.4458900988101959,
"learning_rate": 0.00018763066800438636,
"loss": 1.3651,
"step": 98
},
{
"epoch": 0.1767857142857143,
"grad_norm": 0.5115835666656494,
"learning_rate": 0.00018735406289570192,
"loss": 1.5389,
"step": 99
},
{
"epoch": 0.17857142857142858,
"grad_norm": 0.6476715803146362,
"learning_rate": 0.00018707460771197774,
"loss": 2.1173,
"step": 100
},
{
"epoch": 0.18035714285714285,
"grad_norm": 0.18222245573997498,
"learning_rate": 0.00018679231157091506,
"loss": 1.3799,
"step": 101
},
{
"epoch": 0.18214285714285713,
"grad_norm": 0.2210777848958969,
"learning_rate": 0.0001865071836829061,
"loss": 1.6362,
"step": 102
},
{
"epoch": 0.18392857142857144,
"grad_norm": 0.21902061998844147,
"learning_rate": 0.00018621923335073376,
"loss": 1.6673,
"step": 103
},
{
"epoch": 0.18571428571428572,
"grad_norm": 0.21758711338043213,
"learning_rate": 0.00018592846996926793,
"loss": 1.669,
"step": 104
},
{
"epoch": 0.1875,
"grad_norm": 0.21447710692882538,
"learning_rate": 0.0001856349030251589,
"loss": 1.6173,
"step": 105
},
{
"epoch": 0.18928571428571428,
"grad_norm": 0.20819346606731415,
"learning_rate": 0.00018533854209652818,
"loss": 1.6841,
"step": 106
},
{
"epoch": 0.19107142857142856,
"grad_norm": 0.19584102928638458,
"learning_rate": 0.00018503939685265568,
"loss": 1.5907,
"step": 107
},
{
"epoch": 0.19285714285714287,
"grad_norm": 0.2108387053012848,
"learning_rate": 0.00018473747705366426,
"loss": 1.7855,
"step": 108
},
{
"epoch": 0.19464285714285715,
"grad_norm": 0.20142777264118195,
"learning_rate": 0.00018443279255020152,
"loss": 1.79,
"step": 109
},
{
"epoch": 0.19642857142857142,
"grad_norm": 0.20290708541870117,
"learning_rate": 0.00018412535328311814,
"loss": 1.8891,
"step": 110
},
{
"epoch": 0.1982142857142857,
"grad_norm": 0.20743344724178314,
"learning_rate": 0.00018381516928314367,
"loss": 1.6483,
"step": 111
},
{
"epoch": 0.2,
"grad_norm": 0.24931779503822327,
"learning_rate": 0.00018350225067055925,
"loss": 1.7883,
"step": 112
},
{
"epoch": 0.2017857142857143,
"grad_norm": 0.20271241664886475,
"learning_rate": 0.00018318660765486748,
"loss": 1.8015,
"step": 113
},
{
"epoch": 0.20357142857142857,
"grad_norm": 0.21297615766525269,
"learning_rate": 0.00018286825053445918,
"loss": 1.7595,
"step": 114
},
{
"epoch": 0.20535714285714285,
"grad_norm": 0.21898160874843597,
"learning_rate": 0.0001825471896962774,
"loss": 1.8246,
"step": 115
},
{
"epoch": 0.20714285714285716,
"grad_norm": 0.2433815449476242,
"learning_rate": 0.00018222343561547874,
"loss": 1.9214,
"step": 116
},
{
"epoch": 0.20892857142857144,
"grad_norm": 0.2514473497867584,
"learning_rate": 0.00018189699885509127,
"loss": 1.674,
"step": 117
},
{
"epoch": 0.21071428571428572,
"grad_norm": 0.23736989498138428,
"learning_rate": 0.0001815678900656702,
"loss": 1.7948,
"step": 118
},
{
"epoch": 0.2125,
"grad_norm": 0.22837956249713898,
"learning_rate": 0.00018123611998495007,
"loss": 1.9429,
"step": 119
},
{
"epoch": 0.21428571428571427,
"grad_norm": 0.2722070813179016,
"learning_rate": 0.00018090169943749476,
"loss": 1.2768,
"step": 120
},
{
"epoch": 0.21607142857142858,
"grad_norm": 0.23845739662647247,
"learning_rate": 0.00018056463933434398,
"loss": 1.7407,
"step": 121
},
{
"epoch": 0.21785714285714286,
"grad_norm": 0.24140624701976776,
"learning_rate": 0.00018022495067265753,
"loss": 1.378,
"step": 122
},
{
"epoch": 0.21964285714285714,
"grad_norm": 0.2878568768501282,
"learning_rate": 0.0001798826445353564,
"loss": 1.6684,
"step": 123
},
{
"epoch": 0.22142857142857142,
"grad_norm": 0.35590338706970215,
"learning_rate": 0.0001795377320907611,
"loss": 0.7946,
"step": 124
},
{
"epoch": 0.22321428571428573,
"grad_norm": 0.35154449939727783,
"learning_rate": 0.00017919022459222752,
"loss": 0.9185,
"step": 125
},
{
"epoch": 0.225,
"grad_norm": 0.31363779306411743,
"learning_rate": 0.00017884013337777943,
"loss": 1.3471,
"step": 126
},
{
"epoch": 0.22678571428571428,
"grad_norm": 0.36924973130226135,
"learning_rate": 0.00017848746986973883,
"loss": 1.3852,
"step": 127
},
{
"epoch": 0.22857142857142856,
"grad_norm": 0.44929584860801697,
"learning_rate": 0.00017813224557435312,
"loss": 0.82,
"step": 128
},
{
"epoch": 0.23035714285714284,
"grad_norm": 0.3592383563518524,
"learning_rate": 0.0001777744720814198,
"loss": 1.0219,
"step": 129
},
{
"epoch": 0.23214285714285715,
"grad_norm": 0.37820902466773987,
"learning_rate": 0.00017741416106390826,
"loss": 1.3303,
"step": 130
},
{
"epoch": 0.23392857142857143,
"grad_norm": 0.33376428484916687,
"learning_rate": 0.00017705132427757895,
"loss": 1.384,
"step": 131
},
{
"epoch": 0.2357142857142857,
"grad_norm": 0.3454584777355194,
"learning_rate": 0.00017668597356059978,
"loss": 1.2236,
"step": 132
},
{
"epoch": 0.2375,
"grad_norm": 0.345708429813385,
"learning_rate": 0.00017631812083316003,
"loss": 1.0293,
"step": 133
},
{
"epoch": 0.2392857142857143,
"grad_norm": 0.3823675811290741,
"learning_rate": 0.00017594777809708126,
"loss": 1.3131,
"step": 134
},
{
"epoch": 0.24107142857142858,
"grad_norm": 0.336627334356308,
"learning_rate": 0.00017557495743542585,
"loss": 1.2084,
"step": 135
},
{
"epoch": 0.24285714285714285,
"grad_norm": 0.3525237739086151,
"learning_rate": 0.0001751996710121026,
"loss": 1.1378,
"step": 136
},
{
"epoch": 0.24464285714285713,
"grad_norm": 0.38291576504707336,
"learning_rate": 0.00017482193107147014,
"loss": 0.8353,
"step": 137
},
{
"epoch": 0.24642857142857144,
"grad_norm": 0.4650520086288452,
"learning_rate": 0.0001744417499379372,
"loss": 1.2024,
"step": 138
},
{
"epoch": 0.24821428571428572,
"grad_norm": 0.32640358805656433,
"learning_rate": 0.0001740591400155606,
"loss": 1.2343,
"step": 139
},
{
"epoch": 0.25,
"grad_norm": 0.39074593782424927,
"learning_rate": 0.0001736741137876405,
"loss": 0.8896,
"step": 140
},
{
"epoch": 0.25,
"eval_loss": 1.4710056781768799,
"eval_runtime": 13.3678,
"eval_samples_per_second": 17.654,
"eval_steps_per_second": 8.827,
"step": 140
},
{
"epoch": 0.2517857142857143,
"grad_norm": 0.36249810457229614,
"learning_rate": 0.00017328668381631318,
"loss": 1.1208,
"step": 141
},
{
"epoch": 0.25357142857142856,
"grad_norm": 0.3750612735748291,
"learning_rate": 0.00017289686274214118,
"loss": 1.2502,
"step": 142
},
{
"epoch": 0.25535714285714284,
"grad_norm": 0.4201869070529938,
"learning_rate": 0.0001725046632837007,
"loss": 1.1947,
"step": 143
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.4865645468235016,
"learning_rate": 0.00017211009823716694,
"loss": 0.8749,
"step": 144
},
{
"epoch": 0.25892857142857145,
"grad_norm": 0.38693225383758545,
"learning_rate": 0.00017171318047589637,
"loss": 1.2495,
"step": 145
},
{
"epoch": 0.26071428571428573,
"grad_norm": 0.40707525610923767,
"learning_rate": 0.00017131392295000674,
"loss": 1.2321,
"step": 146
},
{
"epoch": 0.2625,
"grad_norm": 0.39570894837379456,
"learning_rate": 0.00017091233868595467,
"loss": 1.301,
"step": 147
},
{
"epoch": 0.2642857142857143,
"grad_norm": 0.4085226058959961,
"learning_rate": 0.00017050844078611056,
"loss": 1.5369,
"step": 148
},
{
"epoch": 0.26607142857142857,
"grad_norm": 0.47094810009002686,
"learning_rate": 0.0001701022424283311,
"loss": 1.9374,
"step": 149
},
{
"epoch": 0.26785714285714285,
"grad_norm": 0.8517308831214905,
"learning_rate": 0.00016969375686552937,
"loss": 1.808,
"step": 150
},
{
"epoch": 0.26964285714285713,
"grad_norm": 0.1922745406627655,
"learning_rate": 0.00016928299742524234,
"loss": 1.6608,
"step": 151
},
{
"epoch": 0.2714285714285714,
"grad_norm": 0.2090916484594345,
"learning_rate": 0.00016886997750919619,
"loss": 1.8009,
"step": 152
},
{
"epoch": 0.2732142857142857,
"grad_norm": 0.21698515117168427,
"learning_rate": 0.00016845471059286887,
"loss": 1.7821,
"step": 153
},
{
"epoch": 0.275,
"grad_norm": 0.21791532635688782,
"learning_rate": 0.00016803721022505067,
"loss": 1.5901,
"step": 154
},
{
"epoch": 0.2767857142857143,
"grad_norm": 0.22199980914592743,
"learning_rate": 0.00016761749002740193,
"loss": 1.7047,
"step": 155
},
{
"epoch": 0.2785714285714286,
"grad_norm": 0.2096625566482544,
"learning_rate": 0.0001671955636940088,
"loss": 1.6898,
"step": 156
},
{
"epoch": 0.28035714285714286,
"grad_norm": 0.22975414991378784,
"learning_rate": 0.00016677144499093626,
"loss": 1.7631,
"step": 157
},
{
"epoch": 0.28214285714285714,
"grad_norm": 0.2187148928642273,
"learning_rate": 0.0001663451477557792,
"loss": 1.7872,
"step": 158
},
{
"epoch": 0.2839285714285714,
"grad_norm": 0.2257414609193802,
"learning_rate": 0.0001659166858972107,
"loss": 1.7732,
"step": 159
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.22986693680286407,
"learning_rate": 0.00016548607339452853,
"loss": 1.7031,
"step": 160
},
{
"epoch": 0.2875,
"grad_norm": 0.21585014462471008,
"learning_rate": 0.0001650533242971987,
"loss": 1.8421,
"step": 161
},
{
"epoch": 0.2892857142857143,
"grad_norm": 0.22519604861736298,
"learning_rate": 0.00016461845272439741,
"loss": 1.6529,
"step": 162
},
{
"epoch": 0.2910714285714286,
"grad_norm": 0.22279705107212067,
"learning_rate": 0.0001641814728645502,
"loss": 1.9288,
"step": 163
},
{
"epoch": 0.29285714285714287,
"grad_norm": 0.22392615675926208,
"learning_rate": 0.000163742398974869,
"loss": 1.693,
"step": 164
},
{
"epoch": 0.29464285714285715,
"grad_norm": 0.22729454934597015,
"learning_rate": 0.00016330124538088705,
"loss": 1.7027,
"step": 165
},
{
"epoch": 0.29642857142857143,
"grad_norm": 0.2229882776737213,
"learning_rate": 0.00016285802647599156,
"loss": 1.8262,
"step": 166
},
{
"epoch": 0.2982142857142857,
"grad_norm": 0.25520074367523193,
"learning_rate": 0.00016241275672095395,
"loss": 1.6009,
"step": 167
},
{
"epoch": 0.3,
"grad_norm": 0.24272315204143524,
"learning_rate": 0.00016196545064345812,
"loss": 1.9227,
"step": 168
},
{
"epoch": 0.30178571428571427,
"grad_norm": 0.24380216002464294,
"learning_rate": 0.00016151612283762652,
"loss": 1.5198,
"step": 169
},
{
"epoch": 0.30357142857142855,
"grad_norm": 0.3242342472076416,
"learning_rate": 0.00016106478796354382,
"loss": 1.6981,
"step": 170
},
{
"epoch": 0.3053571428571429,
"grad_norm": 0.277855783700943,
"learning_rate": 0.00016061146074677885,
"loss": 1.7011,
"step": 171
},
{
"epoch": 0.30714285714285716,
"grad_norm": 0.2710039019584656,
"learning_rate": 0.00016015615597790388,
"loss": 1.7522,
"step": 172
},
{
"epoch": 0.30892857142857144,
"grad_norm": 0.26541268825531006,
"learning_rate": 0.00015969888851201226,
"loss": 1.3804,
"step": 173
},
{
"epoch": 0.3107142857142857,
"grad_norm": 0.28985923528671265,
"learning_rate": 0.00015923967326823368,
"loss": 1.6453,
"step": 174
},
{
"epoch": 0.3125,
"grad_norm": 0.33939245343208313,
"learning_rate": 0.00015877852522924732,
"loss": 1.1725,
"step": 175
},
{
"epoch": 0.3142857142857143,
"grad_norm": 0.29770731925964355,
"learning_rate": 0.0001583154594407932,
"loss": 1.6746,
"step": 176
},
{
"epoch": 0.31607142857142856,
"grad_norm": 0.3280562460422516,
"learning_rate": 0.0001578504910111811,
"loss": 1.1357,
"step": 177
},
{
"epoch": 0.31785714285714284,
"grad_norm": 0.2856597304344177,
"learning_rate": 0.00015738363511079776,
"loss": 1.1127,
"step": 178
},
{
"epoch": 0.3196428571428571,
"grad_norm": 0.316491961479187,
"learning_rate": 0.00015691490697161182,
"loss": 1.4281,
"step": 179
},
{
"epoch": 0.32142857142857145,
"grad_norm": 0.3632654845714569,
"learning_rate": 0.00015644432188667695,
"loss": 1.3413,
"step": 180
},
{
"epoch": 0.32321428571428573,
"grad_norm": 0.34329405426979065,
"learning_rate": 0.00015597189520963277,
"loss": 1.0579,
"step": 181
},
{
"epoch": 0.325,
"grad_norm": 0.32447105646133423,
"learning_rate": 0.00015549764235420405,
"loss": 1.243,
"step": 182
},
{
"epoch": 0.3267857142857143,
"grad_norm": 0.3558500409126282,
"learning_rate": 0.0001550215787936977,
"loss": 1.1376,
"step": 183
},
{
"epoch": 0.32857142857142857,
"grad_norm": 0.3373570740222931,
"learning_rate": 0.00015454372006049803,
"loss": 1.1251,
"step": 184
},
{
"epoch": 0.33035714285714285,
"grad_norm": 0.36412546038627625,
"learning_rate": 0.00015406408174555976,
"loss": 1.3238,
"step": 185
},
{
"epoch": 0.33214285714285713,
"grad_norm": 0.364442378282547,
"learning_rate": 0.00015358267949789966,
"loss": 0.9448,
"step": 186
},
{
"epoch": 0.3339285714285714,
"grad_norm": 0.3172107934951782,
"learning_rate": 0.00015309952902408576,
"loss": 1.2744,
"step": 187
},
{
"epoch": 0.3357142857142857,
"grad_norm": 0.34173399209976196,
"learning_rate": 0.00015261464608772488,
"loss": 1.0923,
"step": 188
},
{
"epoch": 0.3375,
"grad_norm": 0.33419185876846313,
"learning_rate": 0.0001521280465089484,
"loss": 1.2762,
"step": 189
},
{
"epoch": 0.3392857142857143,
"grad_norm": 0.3866868317127228,
"learning_rate": 0.0001516397461638962,
"loss": 0.9595,
"step": 190
},
{
"epoch": 0.3410714285714286,
"grad_norm": 0.3978990614414215,
"learning_rate": 0.00015114976098419842,
"loss": 0.9993,
"step": 191
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.3546142876148224,
"learning_rate": 0.00015065810695645584,
"loss": 1.3421,
"step": 192
},
{
"epoch": 0.34464285714285714,
"grad_norm": 0.39728498458862305,
"learning_rate": 0.00015016480012171828,
"loss": 1.1209,
"step": 193
},
{
"epoch": 0.3464285714285714,
"grad_norm": 0.4170741140842438,
"learning_rate": 0.00014966985657496114,
"loss": 1.0024,
"step": 194
},
{
"epoch": 0.3482142857142857,
"grad_norm": 0.4226652681827545,
"learning_rate": 0.0001491732924645604,
"loss": 1.3139,
"step": 195
},
{
"epoch": 0.35,
"grad_norm": 0.3712114691734314,
"learning_rate": 0.00014867512399176563,
"loss": 1.1574,
"step": 196
},
{
"epoch": 0.3517857142857143,
"grad_norm": 0.3655322790145874,
"learning_rate": 0.00014817536741017152,
"loss": 1.6149,
"step": 197
},
{
"epoch": 0.3535714285714286,
"grad_norm": 0.4362059533596039,
"learning_rate": 0.0001476740390251875,
"loss": 1.7657,
"step": 198
},
{
"epoch": 0.35535714285714287,
"grad_norm": 0.43134769797325134,
"learning_rate": 0.00014717115519350567,
"loss": 1.7167,
"step": 199
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.7784890532493591,
"learning_rate": 0.00014666673232256738,
"loss": 2.036,
"step": 200
},
{
"epoch": 0.35892857142857143,
"grad_norm": 0.17376984655857086,
"learning_rate": 0.0001461607868700276,
"loss": 1.4856,
"step": 201
},
{
"epoch": 0.3607142857142857,
"grad_norm": 0.2141953408718109,
"learning_rate": 0.00014565333534321826,
"loss": 1.7491,
"step": 202
},
{
"epoch": 0.3625,
"grad_norm": 0.22548137605190277,
"learning_rate": 0.00014514439429860943,
"loss": 1.8457,
"step": 203
},
{
"epoch": 0.36428571428571427,
"grad_norm": 0.20618294179439545,
"learning_rate": 0.0001446339803412692,
"loss": 1.4987,
"step": 204
},
{
"epoch": 0.36607142857142855,
"grad_norm": 0.21025151014328003,
"learning_rate": 0.00014412211012432212,
"loss": 1.5568,
"step": 205
},
{
"epoch": 0.3678571428571429,
"grad_norm": 0.21678180992603302,
"learning_rate": 0.00014360880034840554,
"loss": 1.7841,
"step": 206
},
{
"epoch": 0.36964285714285716,
"grad_norm": 0.20914790034294128,
"learning_rate": 0.0001430940677611249,
"loss": 1.6693,
"step": 207
},
{
"epoch": 0.37142857142857144,
"grad_norm": 0.21597585082054138,
"learning_rate": 0.00014257792915650728,
"loss": 1.648,
"step": 208
},
{
"epoch": 0.3732142857142857,
"grad_norm": 0.23697789013385773,
"learning_rate": 0.00014206040137445348,
"loss": 1.7616,
"step": 209
},
{
"epoch": 0.375,
"grad_norm": 0.2535800635814667,
"learning_rate": 0.00014154150130018866,
"loss": 2.0279,
"step": 210
},
{
"epoch": 0.3767857142857143,
"grad_norm": 0.21204812824726105,
"learning_rate": 0.0001410212458637112,
"loss": 1.8472,
"step": 211
},
{
"epoch": 0.37857142857142856,
"grad_norm": 0.36059629917144775,
"learning_rate": 0.00014049965203924054,
"loss": 1.8042,
"step": 212
},
{
"epoch": 0.38035714285714284,
"grad_norm": 0.21400661766529083,
"learning_rate": 0.0001399767368446634,
"loss": 1.698,
"step": 213
},
{
"epoch": 0.3821428571428571,
"grad_norm": 0.24055758118629456,
"learning_rate": 0.00013945251734097828,
"loss": 1.8758,
"step": 214
},
{
"epoch": 0.38392857142857145,
"grad_norm": 0.23605166375637054,
"learning_rate": 0.00013892701063173918,
"loss": 1.7425,
"step": 215
},
{
"epoch": 0.38571428571428573,
"grad_norm": 0.23343758285045624,
"learning_rate": 0.00013840023386249713,
"loss": 1.8683,
"step": 216
},
{
"epoch": 0.3875,
"grad_norm": 0.2475200593471527,
"learning_rate": 0.00013787220422024134,
"loss": 1.9091,
"step": 217
},
{
"epoch": 0.3892857142857143,
"grad_norm": 0.2618944048881531,
"learning_rate": 0.00013734293893283783,
"loss": 1.5086,
"step": 218
},
{
"epoch": 0.39107142857142857,
"grad_norm": 0.2627498209476471,
"learning_rate": 0.00013681245526846783,
"loss": 1.3878,
"step": 219
},
{
"epoch": 0.39285714285714285,
"grad_norm": 0.24390314519405365,
"learning_rate": 0.0001362807705350641,
"loss": 1.7332,
"step": 220
},
{
"epoch": 0.39464285714285713,
"grad_norm": 0.2768295705318451,
"learning_rate": 0.00013574790207974646,
"loss": 1.3123,
"step": 221
},
{
"epoch": 0.3964285714285714,
"grad_norm": 0.2606358230113983,
"learning_rate": 0.0001352138672882555,
"loss": 1.4506,
"step": 222
},
{
"epoch": 0.3982142857142857,
"grad_norm": 0.24806426465511322,
"learning_rate": 0.00013467868358438563,
"loss": 1.7087,
"step": 223
},
{
"epoch": 0.4,
"grad_norm": 0.2664608061313629,
"learning_rate": 0.00013414236842941644,
"loss": 1.3124,
"step": 224
},
{
"epoch": 0.4017857142857143,
"grad_norm": 0.2661263346672058,
"learning_rate": 0.00013360493932154302,
"loss": 1.2174,
"step": 225
},
{
"epoch": 0.4035714285714286,
"grad_norm": 0.3460038900375366,
"learning_rate": 0.00013306641379530514,
"loss": 0.6889,
"step": 226
},
{
"epoch": 0.40535714285714286,
"grad_norm": 0.2929069995880127,
"learning_rate": 0.000132526809421015,
"loss": 0.9457,
"step": 227
},
{
"epoch": 0.40714285714285714,
"grad_norm": 0.3459819257259369,
"learning_rate": 0.00013198614380418412,
"loss": 1.2547,
"step": 228
},
{
"epoch": 0.4089285714285714,
"grad_norm": 0.30105313658714294,
"learning_rate": 0.00013144443458494882,
"loss": 0.957,
"step": 229
},
{
"epoch": 0.4107142857142857,
"grad_norm": 0.3461960256099701,
"learning_rate": 0.00013090169943749476,
"loss": 1.3146,
"step": 230
},
{
"epoch": 0.4125,
"grad_norm": 0.34542855620384216,
"learning_rate": 0.00013035795606948023,
"loss": 1.1128,
"step": 231
},
{
"epoch": 0.4142857142857143,
"grad_norm": 0.37605586647987366,
"learning_rate": 0.00012981322222145846,
"loss": 1.5095,
"step": 232
},
{
"epoch": 0.4160714285714286,
"grad_norm": 0.37267056107521057,
"learning_rate": 0.00012926751566629875,
"loss": 1.071,
"step": 233
},
{
"epoch": 0.41785714285714287,
"grad_norm": 0.3052172064781189,
"learning_rate": 0.00012872085420860665,
"loss": 1.3136,
"step": 234
},
{
"epoch": 0.41964285714285715,
"grad_norm": 0.36694592237472534,
"learning_rate": 0.00012817325568414297,
"loss": 1.2439,
"step": 235
},
{
"epoch": 0.42142857142857143,
"grad_norm": 0.36055245995521545,
"learning_rate": 0.00012762473795924204,
"loss": 1.1165,
"step": 236
},
{
"epoch": 0.4232142857142857,
"grad_norm": 0.3014545738697052,
"learning_rate": 0.00012707531893022854,
"loss": 1.5423,
"step": 237
},
{
"epoch": 0.425,
"grad_norm": 0.3208891749382019,
"learning_rate": 0.00012652501652283377,
"loss": 1.1813,
"step": 238
},
{
"epoch": 0.42678571428571427,
"grad_norm": 0.38703230023384094,
"learning_rate": 0.00012597384869161084,
"loss": 0.7706,
"step": 239
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.38256821036338806,
"learning_rate": 0.00012542183341934872,
"loss": 1.0565,
"step": 240
},
{
"epoch": 0.4303571428571429,
"grad_norm": 0.3555380702018738,
"learning_rate": 0.0001248689887164855,
"loss": 0.849,
"step": 241
},
{
"epoch": 0.43214285714285716,
"grad_norm": 0.3472703993320465,
"learning_rate": 0.00012431533262052098,
"loss": 1.3984,
"step": 242
},
{
"epoch": 0.43392857142857144,
"grad_norm": 0.3631349503993988,
"learning_rate": 0.000123760883195428,
"loss": 0.8955,
"step": 243
},
{
"epoch": 0.4357142857142857,
"grad_norm": 0.349295973777771,
"learning_rate": 0.00012320565853106316,
"loss": 0.8866,
"step": 244
},
{
"epoch": 0.4375,
"grad_norm": 0.33635953068733215,
"learning_rate": 0.00012264967674257646,
"loss": 1.2419,
"step": 245
},
{
"epoch": 0.4392857142857143,
"grad_norm": 0.3833181858062744,
"learning_rate": 0.00012209295596982042,
"loss": 1.5507,
"step": 246
},
{
"epoch": 0.44107142857142856,
"grad_norm": 0.3737214505672455,
"learning_rate": 0.00012153551437675821,
"loss": 1.4881,
"step": 247
},
{
"epoch": 0.44285714285714284,
"grad_norm": 0.4705282747745514,
"learning_rate": 0.00012097737015087094,
"loss": 1.4864,
"step": 248
},
{
"epoch": 0.4446428571428571,
"grad_norm": 0.39539188146591187,
"learning_rate": 0.00012041854150256433,
"loss": 1.7855,
"step": 249
},
{
"epoch": 0.44642857142857145,
"grad_norm": 0.7369075417518616,
"learning_rate": 0.00011985904666457455,
"loss": 2.01,
"step": 250
},
{
"epoch": 0.44821428571428573,
"grad_norm": 0.18146094679832458,
"learning_rate": 0.00011929890389137337,
"loss": 1.5898,
"step": 251
},
{
"epoch": 0.45,
"grad_norm": 0.21558880805969238,
"learning_rate": 0.00011873813145857249,
"loss": 1.5816,
"step": 252
},
{
"epoch": 0.4517857142857143,
"grad_norm": 0.19599275290966034,
"learning_rate": 0.00011817674766232734,
"loss": 1.6433,
"step": 253
},
{
"epoch": 0.45357142857142857,
"grad_norm": 0.22075910866260529,
"learning_rate": 0.00011761477081874015,
"loss": 1.6005,
"step": 254
},
{
"epoch": 0.45535714285714285,
"grad_norm": 0.19471955299377441,
"learning_rate": 0.0001170522192632624,
"loss": 1.7133,
"step": 255
},
{
"epoch": 0.45714285714285713,
"grad_norm": 0.19876879453659058,
"learning_rate": 0.00011648911135009634,
"loss": 1.5085,
"step": 256
},
{
"epoch": 0.4589285714285714,
"grad_norm": 0.20565317571163177,
"learning_rate": 0.00011592546545159645,
"loss": 1.7386,
"step": 257
},
{
"epoch": 0.4607142857142857,
"grad_norm": 0.24483506381511688,
"learning_rate": 0.00011536129995766996,
"loss": 1.7162,
"step": 258
},
{
"epoch": 0.4625,
"grad_norm": 0.21543823182582855,
"learning_rate": 0.00011479663327517667,
"loss": 1.6966,
"step": 259
},
{
"epoch": 0.4642857142857143,
"grad_norm": 0.2661048471927643,
"learning_rate": 0.00011423148382732853,
"loss": 1.8821,
"step": 260
},
{
"epoch": 0.4660714285714286,
"grad_norm": 0.24292460083961487,
"learning_rate": 0.00011366587005308858,
"loss": 1.7085,
"step": 261
},
{
"epoch": 0.46785714285714286,
"grad_norm": 0.216167613863945,
"learning_rate": 0.0001130998104065693,
"loss": 1.7298,
"step": 262
},
{
"epoch": 0.46964285714285714,
"grad_norm": 0.2111697793006897,
"learning_rate": 0.00011253332335643043,
"loss": 1.8098,
"step": 263
},
{
"epoch": 0.4714285714285714,
"grad_norm": 0.23981061577796936,
"learning_rate": 0.00011196642738527659,
"loss": 1.7026,
"step": 264
},
{
"epoch": 0.4732142857142857,
"grad_norm": 0.2623251676559448,
"learning_rate": 0.00011139914098905406,
"loss": 1.7894,
"step": 265
},
{
"epoch": 0.475,
"grad_norm": 0.2482486367225647,
"learning_rate": 0.00011083148267644747,
"loss": 1.9019,
"step": 266
},
{
"epoch": 0.4767857142857143,
"grad_norm": 0.238911435008049,
"learning_rate": 0.00011026347096827578,
"loss": 1.6809,
"step": 267
},
{
"epoch": 0.4785714285714286,
"grad_norm": 0.24704696238040924,
"learning_rate": 0.00010969512439688816,
"loss": 1.6607,
"step": 268
},
{
"epoch": 0.48035714285714287,
"grad_norm": 0.25105100870132446,
"learning_rate": 0.00010912646150555919,
"loss": 1.5895,
"step": 269
},
{
"epoch": 0.48214285714285715,
"grad_norm": 0.2849842607975006,
"learning_rate": 0.00010855750084788398,
"loss": 2.0812,
"step": 270
},
{
"epoch": 0.48392857142857143,
"grad_norm": 0.2599342167377472,
"learning_rate": 0.00010798826098717276,
"loss": 1.1569,
"step": 271
},
{
"epoch": 0.4857142857142857,
"grad_norm": 0.28037258982658386,
"learning_rate": 0.00010741876049584523,
"loss": 1.1928,
"step": 272
},
{
"epoch": 0.4875,
"grad_norm": 0.29920563101768494,
"learning_rate": 0.00010684901795482456,
"loss": 1.2244,
"step": 273
},
{
"epoch": 0.48928571428571427,
"grad_norm": 0.2799164354801178,
"learning_rate": 0.00010627905195293135,
"loss": 1.4455,
"step": 274
},
{
"epoch": 0.49107142857142855,
"grad_norm": 0.23873603343963623,
"learning_rate": 0.00010570888108627681,
"loss": 0.852,
"step": 275
},
{
"epoch": 0.4928571428571429,
"grad_norm": 0.2817741632461548,
"learning_rate": 0.00010513852395765631,
"loss": 1.3203,
"step": 276
},
{
"epoch": 0.49464285714285716,
"grad_norm": 0.27295514941215515,
"learning_rate": 0.00010456799917594233,
"loss": 0.749,
"step": 277
},
{
"epoch": 0.49642857142857144,
"grad_norm": 0.30728739500045776,
"learning_rate": 0.00010399732535547734,
"loss": 1.0083,
"step": 278
},
{
"epoch": 0.4982142857142857,
"grad_norm": 0.32001444697380066,
"learning_rate": 0.00010342652111546635,
"loss": 1.573,
"step": 279
},
{
"epoch": 0.5,
"grad_norm": 0.3400101065635681,
"learning_rate": 0.00010285560507936961,
"loss": 1.0757,
"step": 280
},
{
"epoch": 0.5,
"eval_loss": 1.4439584016799927,
"eval_runtime": 13.9741,
"eval_samples_per_second": 16.888,
"eval_steps_per_second": 8.444,
"step": 280
}
],
"logging_steps": 1,
"max_steps": 560,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 140,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.129139501635994e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}