jeqcho's picture
Upload folder using huggingface_hub
32db283 verified
Raw
History Blame Contribute Delete
73.4 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.764835164835165,
"eval_steps": 500,
"global_step": 420,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 2.0722603797912598,
"learning_rate": 0.0,
"loss": 3.2131,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.6677350997924805,
"learning_rate": 4e-05,
"loss": 2.5554,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 1.6039100885391235,
"learning_rate": 8e-05,
"loss": 2.6951,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.6277270317077637,
"learning_rate": 0.00012,
"loss": 2.9003,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 2.0207111835479736,
"learning_rate": 0.00016,
"loss": 2.6989,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 2.6012003421783447,
"learning_rate": 0.0002,
"loss": 2.2728,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 2.338730812072754,
"learning_rate": 0.00019955654101995565,
"loss": 1.7083,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 2.3853142261505127,
"learning_rate": 0.00019911308203991133,
"loss": 1.5367,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 1.1683852672576904,
"learning_rate": 0.00019866962305986697,
"loss": 1.2907,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.9153192639350891,
"learning_rate": 0.00019822616407982261,
"loss": 1.16,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 1.4894245862960815,
"learning_rate": 0.00019778270509977829,
"loss": 1.5419,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.8791560530662537,
"learning_rate": 0.00019733924611973393,
"loss": 1.323,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.5337121486663818,
"learning_rate": 0.0001968957871396896,
"loss": 1.1458,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.5149000883102417,
"learning_rate": 0.00019645232815964525,
"loss": 1.0808,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.4778643846511841,
"learning_rate": 0.00019600886917960092,
"loss": 1.088,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.47255033254623413,
"learning_rate": 0.00019556541019955653,
"loss": 1.0745,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.43144354224205017,
"learning_rate": 0.0001951219512195122,
"loss": 1.2685,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.38666868209838867,
"learning_rate": 0.00019467849223946785,
"loss": 1.0754,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.38462671637535095,
"learning_rate": 0.00019423503325942352,
"loss": 0.9311,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.35871055722236633,
"learning_rate": 0.00019379157427937917,
"loss": 0.95,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.43639278411865234,
"learning_rate": 0.00019334811529933484,
"loss": 0.9915,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.3904358446598053,
"learning_rate": 0.00019290465631929045,
"loss": 1.0229,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.3931411802768707,
"learning_rate": 0.00019246119733924613,
"loss": 0.897,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.3906334340572357,
"learning_rate": 0.00019201773835920177,
"loss": 1.0983,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.3786067068576813,
"learning_rate": 0.00019157427937915744,
"loss": 1.0237,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.36092478036880493,
"learning_rate": 0.00019113082039911309,
"loss": 0.9729,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.27863427996635437,
"learning_rate": 0.00019068736141906876,
"loss": 0.9565,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.30928313732147217,
"learning_rate": 0.0001902439024390244,
"loss": 1.0746,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.3250511586666107,
"learning_rate": 0.00018980044345898005,
"loss": 0.9843,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.30846866965293884,
"learning_rate": 0.00018935698447893572,
"loss": 1.0582,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.3773055672645569,
"learning_rate": 0.00018891352549889136,
"loss": 0.9213,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.3716050386428833,
"learning_rate": 0.00018847006651884703,
"loss": 0.9804,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.3420291244983673,
"learning_rate": 0.00018802660753880268,
"loss": 1.0815,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.2763300836086273,
"learning_rate": 0.00018758314855875832,
"loss": 0.902,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.3937534689903259,
"learning_rate": 0.00018713968957871397,
"loss": 1.1645,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.27199873328208923,
"learning_rate": 0.00018669623059866964,
"loss": 0.8738,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.2848569452762604,
"learning_rate": 0.00018625277161862528,
"loss": 1.0149,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.31365159153938293,
"learning_rate": 0.00018580931263858095,
"loss": 0.9087,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.24746054410934448,
"learning_rate": 0.0001853658536585366,
"loss": 0.9948,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.23962347209453583,
"learning_rate": 0.00018492239467849224,
"loss": 1.1008,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.28994685411453247,
"learning_rate": 0.0001844789356984479,
"loss": 0.915,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.30804207921028137,
"learning_rate": 0.00018403547671840356,
"loss": 0.8168,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.397780179977417,
"learning_rate": 0.0001835920177383592,
"loss": 1.0102,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.28575780987739563,
"learning_rate": 0.00018314855875831487,
"loss": 1.0709,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.2701430022716522,
"learning_rate": 0.00018270509977827052,
"loss": 0.9748,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.34878647327423096,
"learning_rate": 0.00018226164079822616,
"loss": 0.9461,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.29195308685302734,
"learning_rate": 0.00018181818181818183,
"loss": 0.9907,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.32355818152427673,
"learning_rate": 0.00018137472283813748,
"loss": 1.0469,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.3442789614200592,
"learning_rate": 0.00018093126385809312,
"loss": 1.017,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.3519359827041626,
"learning_rate": 0.0001804878048780488,
"loss": 0.9013,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.26735949516296387,
"learning_rate": 0.00018004434589800444,
"loss": 1.0039,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.27275341749191284,
"learning_rate": 0.00017960088691796008,
"loss": 0.8377,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.3131617307662964,
"learning_rate": 0.00017915742793791575,
"loss": 1.079,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.3103640675544739,
"learning_rate": 0.0001787139689578714,
"loss": 1.1037,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.3662891089916229,
"learning_rate": 0.00017827050997782707,
"loss": 1.2238,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.31076231598854065,
"learning_rate": 0.00017782705099778271,
"loss": 1.0621,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.364701509475708,
"learning_rate": 0.00017738359201773839,
"loss": 0.8895,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.3279484212398529,
"learning_rate": 0.000176940133037694,
"loss": 0.8092,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.4195176959037781,
"learning_rate": 0.00017649667405764967,
"loss": 1.0942,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.35336142778396606,
"learning_rate": 0.00017605321507760532,
"loss": 0.9458,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.2668030560016632,
"learning_rate": 0.000175609756097561,
"loss": 0.7203,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.2878060042858124,
"learning_rate": 0.00017516629711751663,
"loss": 0.8954,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.28040236234664917,
"learning_rate": 0.0001747228381374723,
"loss": 0.847,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.38638436794281006,
"learning_rate": 0.00017427937915742792,
"loss": 0.9154,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.3532263934612274,
"learning_rate": 0.0001738359201773836,
"loss": 0.967,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.24510745704174042,
"learning_rate": 0.00017339246119733924,
"loss": 0.9775,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.2761436402797699,
"learning_rate": 0.0001729490022172949,
"loss": 0.9424,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.2630966901779175,
"learning_rate": 0.00017250554323725056,
"loss": 0.9213,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.2421293705701828,
"learning_rate": 0.00017206208425720623,
"loss": 0.903,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.3474556505680084,
"learning_rate": 0.00017161862527716187,
"loss": 1.0754,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.25004228949546814,
"learning_rate": 0.00017117516629711752,
"loss": 0.9385,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.3480256199836731,
"learning_rate": 0.0001707317073170732,
"loss": 0.8971,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.35953742265701294,
"learning_rate": 0.00017028824833702883,
"loss": 1.0076,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.2506542503833771,
"learning_rate": 0.0001698447893569845,
"loss": 0.771,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.29169702529907227,
"learning_rate": 0.00016940133037694015,
"loss": 0.7205,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.26952701807022095,
"learning_rate": 0.00016895787139689582,
"loss": 1.0331,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.3254987895488739,
"learning_rate": 0.00016851441241685144,
"loss": 0.9197,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.2873916029930115,
"learning_rate": 0.0001680709534368071,
"loss": 1.0837,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.3419133424758911,
"learning_rate": 0.00016762749445676275,
"loss": 0.8816,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.29397767782211304,
"learning_rate": 0.00016718403547671842,
"loss": 1.0683,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.2623101472854614,
"learning_rate": 0.00016674057649667407,
"loss": 0.8472,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.44186830520629883,
"learning_rate": 0.00016629711751662974,
"loss": 1.2116,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.4125562906265259,
"learning_rate": 0.00016585365853658536,
"loss": 1.0062,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.3349130153656006,
"learning_rate": 0.00016541019955654103,
"loss": 0.8995,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.34971699118614197,
"learning_rate": 0.00016496674057649667,
"loss": 0.8694,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.3700663447380066,
"learning_rate": 0.00016452328159645234,
"loss": 1.0927,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.28516340255737305,
"learning_rate": 0.000164079822616408,
"loss": 0.8334,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.27797970175743103,
"learning_rate": 0.00016363636363636366,
"loss": 0.8108,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.3791492283344269,
"learning_rate": 0.0001631929046563193,
"loss": 0.8473,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.34083792567253113,
"learning_rate": 0.00016274944567627495,
"loss": 0.9353,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.28273823857307434,
"learning_rate": 0.0001623059866962306,
"loss": 0.8956,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.3167821764945984,
"learning_rate": 0.00016186252771618626,
"loss": 0.8953,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.26616188883781433,
"learning_rate": 0.0001614190687361419,
"loss": 0.8261,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.237916499376297,
"learning_rate": 0.00016097560975609758,
"loss": 0.8914,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.32362309098243713,
"learning_rate": 0.00016053215077605322,
"loss": 0.9295,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.2910405099391937,
"learning_rate": 0.00016008869179600887,
"loss": 1.047,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.279320627450943,
"learning_rate": 0.00015964523281596454,
"loss": 0.9465,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.36068761348724365,
"learning_rate": 0.00015920177383592018,
"loss": 1.0782,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.38116326928138733,
"learning_rate": 0.00015875831485587586,
"loss": 0.8893,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.28538259863853455,
"learning_rate": 0.0001583148558758315,
"loss": 0.8015,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.3541967272758484,
"learning_rate": 0.00015787139689578714,
"loss": 0.8434,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.34469982981681824,
"learning_rate": 0.0001574279379157428,
"loss": 0.8324,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.4213978946208954,
"learning_rate": 0.00015698447893569846,
"loss": 0.9444,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.3815469741821289,
"learning_rate": 0.0001565410199556541,
"loss": 0.8776,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.35397177934646606,
"learning_rate": 0.00015609756097560978,
"loss": 1.1552,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.2684699594974518,
"learning_rate": 0.00015565410199556542,
"loss": 0.7798,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.25741079449653625,
"learning_rate": 0.00015521064301552106,
"loss": 0.8422,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.32127293944358826,
"learning_rate": 0.0001547671840354767,
"loss": 0.8322,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.3340221643447876,
"learning_rate": 0.00015432372505543238,
"loss": 0.9798,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.34005194902420044,
"learning_rate": 0.00015388026607538802,
"loss": 0.8661,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.3739411532878876,
"learning_rate": 0.0001534368070953437,
"loss": 1.021,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.3668403625488281,
"learning_rate": 0.00015299334811529934,
"loss": 0.9958,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.3145362436771393,
"learning_rate": 0.00015254988913525498,
"loss": 1.0518,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.3513026535511017,
"learning_rate": 0.00015210643015521066,
"loss": 1.0291,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.34400007128715515,
"learning_rate": 0.0001516629711751663,
"loss": 0.9739,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.3597501516342163,
"learning_rate": 0.00015121951219512197,
"loss": 1.2324,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.2896723449230194,
"learning_rate": 0.00015077605321507762,
"loss": 0.8937,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.30057957768440247,
"learning_rate": 0.0001503325942350333,
"loss": 0.8983,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.3905964195728302,
"learning_rate": 0.0001498891352549889,
"loss": 0.7167,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.3202342092990875,
"learning_rate": 0.00014944567627494458,
"loss": 0.8969,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.2450852394104004,
"learning_rate": 0.00014900221729490022,
"loss": 0.9203,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.3147158622741699,
"learning_rate": 0.0001485587583148559,
"loss": 0.7941,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.34787628054618835,
"learning_rate": 0.00014811529933481154,
"loss": 1.0058,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.3001445233821869,
"learning_rate": 0.0001476718403547672,
"loss": 0.8574,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.3221536874771118,
"learning_rate": 0.00014722838137472282,
"loss": 1.1149,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.32140639424324036,
"learning_rate": 0.0001467849223946785,
"loss": 1.1972,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.30501997470855713,
"learning_rate": 0.00014634146341463414,
"loss": 0.929,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.3393065333366394,
"learning_rate": 0.0001458980044345898,
"loss": 0.8179,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.3530517816543579,
"learning_rate": 0.00014545454545454546,
"loss": 1.0044,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.29705455899238586,
"learning_rate": 0.00014501108647450113,
"loss": 0.9902,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.3452480733394623,
"learning_rate": 0.00014456762749445675,
"loss": 0.9743,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.2938392162322998,
"learning_rate": 0.00014412416851441242,
"loss": 0.8866,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.30601850152015686,
"learning_rate": 0.00014368070953436806,
"loss": 0.9861,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.28590455651283264,
"learning_rate": 0.00014323725055432373,
"loss": 0.8338,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.2874011695384979,
"learning_rate": 0.00014279379157427938,
"loss": 0.9952,
"step": 135
},
{
"epoch": 0.8967032967032967,
"grad_norm": 0.3361506462097168,
"learning_rate": 0.00014235033259423505,
"loss": 1.0219,
"step": 136
},
{
"epoch": 0.9032967032967033,
"grad_norm": 0.3574809730052948,
"learning_rate": 0.0001419068736141907,
"loss": 0.8814,
"step": 137
},
{
"epoch": 0.9098901098901099,
"grad_norm": 0.4311088025569916,
"learning_rate": 0.00014146341463414634,
"loss": 0.9013,
"step": 138
},
{
"epoch": 0.9164835164835164,
"grad_norm": 0.26233023405075073,
"learning_rate": 0.000141019955654102,
"loss": 0.8736,
"step": 139
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.35940396785736084,
"learning_rate": 0.00014057649667405765,
"loss": 0.9749,
"step": 140
},
{
"epoch": 0.9296703296703297,
"grad_norm": 0.27149611711502075,
"learning_rate": 0.00014013303769401332,
"loss": 0.922,
"step": 141
},
{
"epoch": 0.9362637362637363,
"grad_norm": 0.4147508442401886,
"learning_rate": 0.00013968957871396897,
"loss": 1.0781,
"step": 142
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.295341432094574,
"learning_rate": 0.00013924611973392464,
"loss": 0.9529,
"step": 143
},
{
"epoch": 0.9494505494505494,
"grad_norm": 0.36334657669067383,
"learning_rate": 0.00013880266075388026,
"loss": 0.8085,
"step": 144
},
{
"epoch": 0.9560439560439561,
"grad_norm": 0.24359752237796783,
"learning_rate": 0.00013835920177383593,
"loss": 0.7036,
"step": 145
},
{
"epoch": 0.9626373626373627,
"grad_norm": 0.3110310733318329,
"learning_rate": 0.00013791574279379157,
"loss": 0.7797,
"step": 146
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.3413989841938019,
"learning_rate": 0.00013747228381374724,
"loss": 1.0027,
"step": 147
},
{
"epoch": 0.9758241758241758,
"grad_norm": 0.2888753116130829,
"learning_rate": 0.0001370288248337029,
"loss": 0.8844,
"step": 148
},
{
"epoch": 0.9824175824175824,
"grad_norm": 0.32249295711517334,
"learning_rate": 0.00013658536585365856,
"loss": 0.8261,
"step": 149
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.4273090660572052,
"learning_rate": 0.00013614190687361418,
"loss": 1.0066,
"step": 150
},
{
"epoch": 0.9956043956043956,
"grad_norm": 0.28998544812202454,
"learning_rate": 0.00013569844789356985,
"loss": 0.8485,
"step": 151
},
{
"epoch": 1.0,
"grad_norm": 0.4690309762954712,
"learning_rate": 0.0001352549889135255,
"loss": 0.6486,
"step": 152
},
{
"epoch": 1.0065934065934066,
"grad_norm": 0.3045438528060913,
"learning_rate": 0.00013481152993348116,
"loss": 0.8676,
"step": 153
},
{
"epoch": 1.0131868131868131,
"grad_norm": 0.3148064613342285,
"learning_rate": 0.0001343680709534368,
"loss": 0.9665,
"step": 154
},
{
"epoch": 1.0197802197802197,
"grad_norm": 0.32930025458335876,
"learning_rate": 0.00013392461197339248,
"loss": 0.8087,
"step": 155
},
{
"epoch": 1.0263736263736263,
"grad_norm": 0.2816562354564667,
"learning_rate": 0.00013348115299334812,
"loss": 0.7944,
"step": 156
},
{
"epoch": 1.032967032967033,
"grad_norm": 0.3011133074760437,
"learning_rate": 0.00013303769401330377,
"loss": 0.7996,
"step": 157
},
{
"epoch": 1.0395604395604396,
"grad_norm": 0.3297262191772461,
"learning_rate": 0.00013259423503325944,
"loss": 0.8268,
"step": 158
},
{
"epoch": 1.0461538461538462,
"grad_norm": 0.3308207392692566,
"learning_rate": 0.00013215077605321509,
"loss": 0.7508,
"step": 159
},
{
"epoch": 1.0527472527472528,
"grad_norm": 0.3697322607040405,
"learning_rate": 0.00013170731707317076,
"loss": 0.7181,
"step": 160
},
{
"epoch": 1.0593406593406594,
"grad_norm": 0.3329128921031952,
"learning_rate": 0.0001312638580931264,
"loss": 0.7619,
"step": 161
},
{
"epoch": 1.065934065934066,
"grad_norm": 0.36436977982521057,
"learning_rate": 0.00013082039911308205,
"loss": 0.7969,
"step": 162
},
{
"epoch": 1.0725274725274725,
"grad_norm": 0.33429184556007385,
"learning_rate": 0.0001303769401330377,
"loss": 1.0637,
"step": 163
},
{
"epoch": 1.079120879120879,
"grad_norm": 0.4259260892868042,
"learning_rate": 0.00012993348115299336,
"loss": 0.968,
"step": 164
},
{
"epoch": 1.0857142857142856,
"grad_norm": 0.3352951109409332,
"learning_rate": 0.000129490022172949,
"loss": 0.8191,
"step": 165
},
{
"epoch": 1.0923076923076924,
"grad_norm": 0.4135381579399109,
"learning_rate": 0.00012904656319290468,
"loss": 0.9858,
"step": 166
},
{
"epoch": 1.098901098901099,
"grad_norm": 0.3486995995044708,
"learning_rate": 0.00012860310421286032,
"loss": 0.8626,
"step": 167
},
{
"epoch": 1.1054945054945056,
"grad_norm": 0.37806546688079834,
"learning_rate": 0.00012815964523281597,
"loss": 0.9596,
"step": 168
},
{
"epoch": 1.1120879120879121,
"grad_norm": 0.3310850262641907,
"learning_rate": 0.0001277161862527716,
"loss": 0.9345,
"step": 169
},
{
"epoch": 1.1186813186813187,
"grad_norm": 0.3593229651451111,
"learning_rate": 0.00012727272727272728,
"loss": 0.9171,
"step": 170
},
{
"epoch": 1.1252747252747253,
"grad_norm": 0.38787880539894104,
"learning_rate": 0.00012682926829268293,
"loss": 0.8608,
"step": 171
},
{
"epoch": 1.1318681318681318,
"grad_norm": 0.35755735635757446,
"learning_rate": 0.0001263858093126386,
"loss": 0.7518,
"step": 172
},
{
"epoch": 1.1384615384615384,
"grad_norm": 0.45123910903930664,
"learning_rate": 0.00012594235033259424,
"loss": 0.8825,
"step": 173
},
{
"epoch": 1.145054945054945,
"grad_norm": 0.3731641471385956,
"learning_rate": 0.00012549889135254989,
"loss": 0.9151,
"step": 174
},
{
"epoch": 1.1516483516483516,
"grad_norm": 0.4211123287677765,
"learning_rate": 0.00012505543237250553,
"loss": 0.9073,
"step": 175
},
{
"epoch": 1.1582417582417581,
"grad_norm": 0.3269520103931427,
"learning_rate": 0.0001246119733924612,
"loss": 0.7488,
"step": 176
},
{
"epoch": 1.164835164835165,
"grad_norm": 0.36462828516960144,
"learning_rate": 0.00012416851441241685,
"loss": 0.8809,
"step": 177
},
{
"epoch": 1.1714285714285715,
"grad_norm": 0.36362966895103455,
"learning_rate": 0.00012372505543237252,
"loss": 0.8035,
"step": 178
},
{
"epoch": 1.178021978021978,
"grad_norm": 0.3671634793281555,
"learning_rate": 0.00012328159645232816,
"loss": 0.9194,
"step": 179
},
{
"epoch": 1.1846153846153846,
"grad_norm": 0.3457624018192291,
"learning_rate": 0.0001228381374722838,
"loss": 0.7065,
"step": 180
},
{
"epoch": 1.1912087912087912,
"grad_norm": 0.4401772618293762,
"learning_rate": 0.00012239467849223948,
"loss": 0.9267,
"step": 181
},
{
"epoch": 1.1978021978021978,
"grad_norm": 0.4606243371963501,
"learning_rate": 0.00012195121951219512,
"loss": 0.836,
"step": 182
},
{
"epoch": 1.2043956043956043,
"grad_norm": 0.3353036940097809,
"learning_rate": 0.00012150776053215078,
"loss": 0.6218,
"step": 183
},
{
"epoch": 1.210989010989011,
"grad_norm": 0.4171563684940338,
"learning_rate": 0.00012106430155210644,
"loss": 0.7914,
"step": 184
},
{
"epoch": 1.2175824175824177,
"grad_norm": 0.3640008270740509,
"learning_rate": 0.0001206208425720621,
"loss": 0.8632,
"step": 185
},
{
"epoch": 1.2241758241758243,
"grad_norm": 0.43573465943336487,
"learning_rate": 0.00012017738359201774,
"loss": 0.8191,
"step": 186
},
{
"epoch": 1.2307692307692308,
"grad_norm": 0.3201373219490051,
"learning_rate": 0.0001197339246119734,
"loss": 0.7808,
"step": 187
},
{
"epoch": 1.2373626373626374,
"grad_norm": 0.403213769197464,
"learning_rate": 0.00011929046563192906,
"loss": 0.9004,
"step": 188
},
{
"epoch": 1.243956043956044,
"grad_norm": 0.4063056707382202,
"learning_rate": 0.00011884700665188471,
"loss": 0.9791,
"step": 189
},
{
"epoch": 1.2505494505494505,
"grad_norm": 0.4900030195713043,
"learning_rate": 0.00011840354767184036,
"loss": 0.8013,
"step": 190
},
{
"epoch": 1.2571428571428571,
"grad_norm": 0.49652716517448425,
"learning_rate": 0.00011796008869179602,
"loss": 0.9993,
"step": 191
},
{
"epoch": 1.2637362637362637,
"grad_norm": 0.4425002634525299,
"learning_rate": 0.00011751662971175166,
"loss": 0.8854,
"step": 192
},
{
"epoch": 1.2703296703296703,
"grad_norm": 0.46226751804351807,
"learning_rate": 0.00011707317073170732,
"loss": 0.9893,
"step": 193
},
{
"epoch": 1.2769230769230768,
"grad_norm": 0.3779703378677368,
"learning_rate": 0.00011662971175166298,
"loss": 0.7875,
"step": 194
},
{
"epoch": 1.2835164835164834,
"grad_norm": 0.4313388168811798,
"learning_rate": 0.00011618625277161863,
"loss": 0.7672,
"step": 195
},
{
"epoch": 1.2901098901098902,
"grad_norm": 0.36810222268104553,
"learning_rate": 0.00011574279379157429,
"loss": 0.6342,
"step": 196
},
{
"epoch": 1.2967032967032968,
"grad_norm": 0.37219274044036865,
"learning_rate": 0.00011529933481152995,
"loss": 0.8084,
"step": 197
},
{
"epoch": 1.3032967032967033,
"grad_norm": 0.4840892553329468,
"learning_rate": 0.00011485587583148558,
"loss": 0.804,
"step": 198
},
{
"epoch": 1.30989010989011,
"grad_norm": 0.4374985694885254,
"learning_rate": 0.00011441241685144124,
"loss": 0.8546,
"step": 199
},
{
"epoch": 1.3164835164835165,
"grad_norm": 0.3962724208831787,
"learning_rate": 0.0001139689578713969,
"loss": 0.7414,
"step": 200
},
{
"epoch": 1.323076923076923,
"grad_norm": 0.37382033467292786,
"learning_rate": 0.00011352549889135255,
"loss": 0.8653,
"step": 201
},
{
"epoch": 1.3296703296703296,
"grad_norm": 0.44277113676071167,
"learning_rate": 0.00011308203991130821,
"loss": 0.8241,
"step": 202
},
{
"epoch": 1.3362637362637364,
"grad_norm": 0.46842196583747864,
"learning_rate": 0.00011263858093126387,
"loss": 0.7964,
"step": 203
},
{
"epoch": 1.342857142857143,
"grad_norm": 0.4144313931465149,
"learning_rate": 0.00011219512195121953,
"loss": 0.7453,
"step": 204
},
{
"epoch": 1.3494505494505495,
"grad_norm": 0.4482251703739166,
"learning_rate": 0.00011175166297117516,
"loss": 0.9691,
"step": 205
},
{
"epoch": 1.3560439560439561,
"grad_norm": 0.41152456402778625,
"learning_rate": 0.00011130820399113082,
"loss": 0.7846,
"step": 206
},
{
"epoch": 1.3626373626373627,
"grad_norm": 0.4497469961643219,
"learning_rate": 0.00011086474501108647,
"loss": 1.001,
"step": 207
},
{
"epoch": 1.3692307692307693,
"grad_norm": 0.45057448744773865,
"learning_rate": 0.00011042128603104213,
"loss": 0.8659,
"step": 208
},
{
"epoch": 1.3758241758241758,
"grad_norm": 0.4924719035625458,
"learning_rate": 0.00010997782705099779,
"loss": 0.9199,
"step": 209
},
{
"epoch": 1.3824175824175824,
"grad_norm": 0.4531312584877014,
"learning_rate": 0.00010953436807095345,
"loss": 0.9154,
"step": 210
},
{
"epoch": 1.389010989010989,
"grad_norm": 0.43056848645210266,
"learning_rate": 0.00010909090909090909,
"loss": 0.8943,
"step": 211
},
{
"epoch": 1.3956043956043955,
"grad_norm": 0.4362466037273407,
"learning_rate": 0.00010864745011086475,
"loss": 0.6209,
"step": 212
},
{
"epoch": 1.402197802197802,
"grad_norm": 0.5599644780158997,
"learning_rate": 0.00010820399113082041,
"loss": 0.8043,
"step": 213
},
{
"epoch": 1.4087912087912087,
"grad_norm": 0.38885924220085144,
"learning_rate": 0.00010776053215077607,
"loss": 0.8007,
"step": 214
},
{
"epoch": 1.4153846153846155,
"grad_norm": 0.4377254843711853,
"learning_rate": 0.00010731707317073172,
"loss": 0.8852,
"step": 215
},
{
"epoch": 1.421978021978022,
"grad_norm": 0.3999001383781433,
"learning_rate": 0.00010687361419068738,
"loss": 0.9147,
"step": 216
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.46440982818603516,
"learning_rate": 0.00010643015521064301,
"loss": 0.8844,
"step": 217
},
{
"epoch": 1.4351648351648352,
"grad_norm": 0.46195998787879944,
"learning_rate": 0.00010598669623059867,
"loss": 0.7938,
"step": 218
},
{
"epoch": 1.4417582417582417,
"grad_norm": 0.38602715730667114,
"learning_rate": 0.00010554323725055433,
"loss": 0.6682,
"step": 219
},
{
"epoch": 1.4483516483516483,
"grad_norm": 0.4990112781524658,
"learning_rate": 0.00010509977827050999,
"loss": 1.0977,
"step": 220
},
{
"epoch": 1.4549450549450549,
"grad_norm": 0.3537238836288452,
"learning_rate": 0.00010465631929046564,
"loss": 0.7534,
"step": 221
},
{
"epoch": 1.4615384615384617,
"grad_norm": 0.5449821949005127,
"learning_rate": 0.0001042128603104213,
"loss": 1.017,
"step": 222
},
{
"epoch": 1.4681318681318682,
"grad_norm": 0.44483187794685364,
"learning_rate": 0.00010376940133037693,
"loss": 0.8461,
"step": 223
},
{
"epoch": 1.4747252747252748,
"grad_norm": 0.459046334028244,
"learning_rate": 0.00010332594235033259,
"loss": 0.8609,
"step": 224
},
{
"epoch": 1.4813186813186814,
"grad_norm": 0.4648573100566864,
"learning_rate": 0.00010288248337028825,
"loss": 0.7077,
"step": 225
},
{
"epoch": 1.487912087912088,
"grad_norm": 0.46832260489463806,
"learning_rate": 0.0001024390243902439,
"loss": 0.995,
"step": 226
},
{
"epoch": 1.4945054945054945,
"grad_norm": 0.5647684335708618,
"learning_rate": 0.00010199556541019956,
"loss": 0.9797,
"step": 227
},
{
"epoch": 1.501098901098901,
"grad_norm": 0.3861806094646454,
"learning_rate": 0.00010155210643015522,
"loss": 0.8115,
"step": 228
},
{
"epoch": 1.5076923076923077,
"grad_norm": 0.4496518671512604,
"learning_rate": 0.00010110864745011087,
"loss": 0.8522,
"step": 229
},
{
"epoch": 1.5142857142857142,
"grad_norm": 0.428604394197464,
"learning_rate": 0.00010066518847006652,
"loss": 0.8554,
"step": 230
},
{
"epoch": 1.5208791208791208,
"grad_norm": 0.46109339594841003,
"learning_rate": 0.00010022172949002218,
"loss": 0.9584,
"step": 231
},
{
"epoch": 1.5274725274725274,
"grad_norm": 0.5141985416412354,
"learning_rate": 9.977827050997783e-05,
"loss": 0.9228,
"step": 232
},
{
"epoch": 1.534065934065934,
"grad_norm": 0.49423670768737793,
"learning_rate": 9.933481152993348e-05,
"loss": 0.797,
"step": 233
},
{
"epoch": 1.5406593406593405,
"grad_norm": 0.47565293312072754,
"learning_rate": 9.889135254988914e-05,
"loss": 0.886,
"step": 234
},
{
"epoch": 1.5472527472527473,
"grad_norm": 0.4218743145465851,
"learning_rate": 9.84478935698448e-05,
"loss": 0.8496,
"step": 235
},
{
"epoch": 1.5538461538461539,
"grad_norm": 0.45972034335136414,
"learning_rate": 9.800443458980046e-05,
"loss": 0.7161,
"step": 236
},
{
"epoch": 1.5604395604395604,
"grad_norm": 0.5325828194618225,
"learning_rate": 9.75609756097561e-05,
"loss": 0.8005,
"step": 237
},
{
"epoch": 1.567032967032967,
"grad_norm": 0.4783444404602051,
"learning_rate": 9.711751662971176e-05,
"loss": 0.8983,
"step": 238
},
{
"epoch": 1.5736263736263736,
"grad_norm": 0.48973003029823303,
"learning_rate": 9.667405764966742e-05,
"loss": 0.8455,
"step": 239
},
{
"epoch": 1.5802197802197804,
"grad_norm": 0.4571506977081299,
"learning_rate": 9.623059866962306e-05,
"loss": 0.8023,
"step": 240
},
{
"epoch": 1.586813186813187,
"grad_norm": 0.40492597222328186,
"learning_rate": 9.578713968957872e-05,
"loss": 0.7615,
"step": 241
},
{
"epoch": 1.5934065934065935,
"grad_norm": 0.44703274965286255,
"learning_rate": 9.534368070953438e-05,
"loss": 0.8295,
"step": 242
},
{
"epoch": 1.6,
"grad_norm": 0.46830523014068604,
"learning_rate": 9.490022172949002e-05,
"loss": 0.7677,
"step": 243
},
{
"epoch": 1.6065934065934067,
"grad_norm": 0.5389837622642517,
"learning_rate": 9.445676274944568e-05,
"loss": 0.929,
"step": 244
},
{
"epoch": 1.6131868131868132,
"grad_norm": 0.4897559583187103,
"learning_rate": 9.401330376940134e-05,
"loss": 0.7929,
"step": 245
},
{
"epoch": 1.6197802197802198,
"grad_norm": 0.48635751008987427,
"learning_rate": 9.356984478935698e-05,
"loss": 0.8176,
"step": 246
},
{
"epoch": 1.6263736263736264,
"grad_norm": 0.5070086717605591,
"learning_rate": 9.312638580931264e-05,
"loss": 0.8988,
"step": 247
},
{
"epoch": 1.632967032967033,
"grad_norm": 0.5040110945701599,
"learning_rate": 9.26829268292683e-05,
"loss": 0.9827,
"step": 248
},
{
"epoch": 1.6395604395604395,
"grad_norm": 0.4893195331096649,
"learning_rate": 9.223946784922394e-05,
"loss": 0.9108,
"step": 249
},
{
"epoch": 1.646153846153846,
"grad_norm": 0.5183725953102112,
"learning_rate": 9.17960088691796e-05,
"loss": 1.0375,
"step": 250
},
{
"epoch": 1.6527472527472526,
"grad_norm": 0.5050914287567139,
"learning_rate": 9.135254988913526e-05,
"loss": 0.8868,
"step": 251
},
{
"epoch": 1.6593406593406592,
"grad_norm": 0.6539065837860107,
"learning_rate": 9.090909090909092e-05,
"loss": 0.919,
"step": 252
},
{
"epoch": 1.6659340659340658,
"grad_norm": 0.5070188045501709,
"learning_rate": 9.046563192904656e-05,
"loss": 0.8922,
"step": 253
},
{
"epoch": 1.6725274725274726,
"grad_norm": 0.5404043197631836,
"learning_rate": 9.002217294900222e-05,
"loss": 0.9583,
"step": 254
},
{
"epoch": 1.6791208791208792,
"grad_norm": 0.5274918079376221,
"learning_rate": 8.957871396895788e-05,
"loss": 0.9918,
"step": 255
},
{
"epoch": 1.6857142857142857,
"grad_norm": 0.5713817477226257,
"learning_rate": 8.913525498891354e-05,
"loss": 0.7026,
"step": 256
},
{
"epoch": 1.6923076923076923,
"grad_norm": 0.4875091314315796,
"learning_rate": 8.869179600886919e-05,
"loss": 0.7633,
"step": 257
},
{
"epoch": 1.6989010989010989,
"grad_norm": 0.4186699688434601,
"learning_rate": 8.824833702882484e-05,
"loss": 0.8017,
"step": 258
},
{
"epoch": 1.7054945054945057,
"grad_norm": 0.4443645477294922,
"learning_rate": 8.78048780487805e-05,
"loss": 0.6736,
"step": 259
},
{
"epoch": 1.7120879120879122,
"grad_norm": 0.4955357611179352,
"learning_rate": 8.736141906873615e-05,
"loss": 0.7624,
"step": 260
},
{
"epoch": 1.7186813186813188,
"grad_norm": 0.4375542104244232,
"learning_rate": 8.69179600886918e-05,
"loss": 0.7421,
"step": 261
},
{
"epoch": 1.7252747252747254,
"grad_norm": 0.47112950682640076,
"learning_rate": 8.647450110864746e-05,
"loss": 0.8486,
"step": 262
},
{
"epoch": 1.731868131868132,
"grad_norm": 0.6528114676475525,
"learning_rate": 8.603104212860311e-05,
"loss": 0.7325,
"step": 263
},
{
"epoch": 1.7384615384615385,
"grad_norm": 0.46200332045555115,
"learning_rate": 8.558758314855876e-05,
"loss": 0.8528,
"step": 264
},
{
"epoch": 1.745054945054945,
"grad_norm": 0.574214518070221,
"learning_rate": 8.514412416851442e-05,
"loss": 0.7978,
"step": 265
},
{
"epoch": 1.7516483516483516,
"grad_norm": 0.4962877333164215,
"learning_rate": 8.470066518847007e-05,
"loss": 0.8764,
"step": 266
},
{
"epoch": 1.7582417582417582,
"grad_norm": 0.4789123237133026,
"learning_rate": 8.425720620842572e-05,
"loss": 0.8737,
"step": 267
},
{
"epoch": 1.7648351648351648,
"grad_norm": 0.5246762037277222,
"learning_rate": 8.381374722838138e-05,
"loss": 0.8024,
"step": 268
},
{
"epoch": 1.7714285714285714,
"grad_norm": 0.41688671708106995,
"learning_rate": 8.337028824833703e-05,
"loss": 0.5601,
"step": 269
},
{
"epoch": 1.778021978021978,
"grad_norm": 0.4610651433467865,
"learning_rate": 8.292682926829268e-05,
"loss": 0.6669,
"step": 270
},
{
"epoch": 1.7846153846153845,
"grad_norm": 0.5566967129707336,
"learning_rate": 8.248337028824834e-05,
"loss": 0.8098,
"step": 271
},
{
"epoch": 1.791208791208791,
"grad_norm": 0.48066723346710205,
"learning_rate": 8.2039911308204e-05,
"loss": 0.8288,
"step": 272
},
{
"epoch": 1.7978021978021979,
"grad_norm": 0.564047634601593,
"learning_rate": 8.159645232815965e-05,
"loss": 0.9512,
"step": 273
},
{
"epoch": 1.8043956043956044,
"grad_norm": 0.4820556938648224,
"learning_rate": 8.11529933481153e-05,
"loss": 0.499,
"step": 274
},
{
"epoch": 1.810989010989011,
"grad_norm": 0.5948233604431152,
"learning_rate": 8.070953436807095e-05,
"loss": 0.8845,
"step": 275
},
{
"epoch": 1.8175824175824176,
"grad_norm": 0.510066032409668,
"learning_rate": 8.026607538802661e-05,
"loss": 0.8913,
"step": 276
},
{
"epoch": 1.8241758241758241,
"grad_norm": 0.5342652797698975,
"learning_rate": 7.982261640798227e-05,
"loss": 0.8842,
"step": 277
},
{
"epoch": 1.830769230769231,
"grad_norm": 0.5228323340415955,
"learning_rate": 7.937915742793793e-05,
"loss": 0.8055,
"step": 278
},
{
"epoch": 1.8373626373626375,
"grad_norm": 0.501943826675415,
"learning_rate": 7.893569844789357e-05,
"loss": 0.8469,
"step": 279
},
{
"epoch": 1.843956043956044,
"grad_norm": 0.5378738641738892,
"learning_rate": 7.849223946784923e-05,
"loss": 0.9278,
"step": 280
},
{
"epoch": 1.8505494505494506,
"grad_norm": 0.632314920425415,
"learning_rate": 7.804878048780489e-05,
"loss": 1.0605,
"step": 281
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.40868574380874634,
"learning_rate": 7.760532150776053e-05,
"loss": 0.8974,
"step": 282
},
{
"epoch": 1.8637362637362638,
"grad_norm": 0.5296427607536316,
"learning_rate": 7.716186252771619e-05,
"loss": 0.8518,
"step": 283
},
{
"epoch": 1.8703296703296703,
"grad_norm": 0.48775559663772583,
"learning_rate": 7.671840354767185e-05,
"loss": 0.6894,
"step": 284
},
{
"epoch": 1.876923076923077,
"grad_norm": 0.5466031432151794,
"learning_rate": 7.627494456762749e-05,
"loss": 0.847,
"step": 285
},
{
"epoch": 1.8835164835164835,
"grad_norm": 0.6754628419876099,
"learning_rate": 7.583148558758315e-05,
"loss": 0.9727,
"step": 286
},
{
"epoch": 1.89010989010989,
"grad_norm": 0.5291099548339844,
"learning_rate": 7.538802660753881e-05,
"loss": 0.9499,
"step": 287
},
{
"epoch": 1.8967032967032966,
"grad_norm": 0.49350351095199585,
"learning_rate": 7.494456762749445e-05,
"loss": 0.6847,
"step": 288
},
{
"epoch": 1.9032967032967032,
"grad_norm": 0.4854298233985901,
"learning_rate": 7.450110864745011e-05,
"loss": 0.8089,
"step": 289
},
{
"epoch": 1.9098901098901098,
"grad_norm": 0.5256028771400452,
"learning_rate": 7.405764966740577e-05,
"loss": 0.789,
"step": 290
},
{
"epoch": 1.9164835164835163,
"grad_norm": 0.5372645854949951,
"learning_rate": 7.361419068736141e-05,
"loss": 0.9326,
"step": 291
},
{
"epoch": 1.9230769230769231,
"grad_norm": 0.4498584270477295,
"learning_rate": 7.317073170731707e-05,
"loss": 0.7562,
"step": 292
},
{
"epoch": 1.9296703296703297,
"grad_norm": 0.5483140349388123,
"learning_rate": 7.272727272727273e-05,
"loss": 0.6764,
"step": 293
},
{
"epoch": 1.9362637362637363,
"grad_norm": 0.6889297366142273,
"learning_rate": 7.228381374722837e-05,
"loss": 0.9722,
"step": 294
},
{
"epoch": 1.9428571428571428,
"grad_norm": 0.4986286163330078,
"learning_rate": 7.184035476718403e-05,
"loss": 0.9781,
"step": 295
},
{
"epoch": 1.9494505494505494,
"grad_norm": 0.6074146032333374,
"learning_rate": 7.139689578713969e-05,
"loss": 0.7487,
"step": 296
},
{
"epoch": 1.9560439560439562,
"grad_norm": 0.5098879337310791,
"learning_rate": 7.095343680709535e-05,
"loss": 0.97,
"step": 297
},
{
"epoch": 1.9626373626373628,
"grad_norm": 0.5738970041275024,
"learning_rate": 7.0509977827051e-05,
"loss": 0.7691,
"step": 298
},
{
"epoch": 1.9692307692307693,
"grad_norm": 0.4587015211582184,
"learning_rate": 7.006651884700666e-05,
"loss": 0.7854,
"step": 299
},
{
"epoch": 1.975824175824176,
"grad_norm": 0.5862131118774414,
"learning_rate": 6.962305986696232e-05,
"loss": 0.8636,
"step": 300
},
{
"epoch": 1.9824175824175825,
"grad_norm": 0.5810269713401794,
"learning_rate": 6.917960088691796e-05,
"loss": 0.9936,
"step": 301
},
{
"epoch": 1.989010989010989,
"grad_norm": 0.5479774475097656,
"learning_rate": 6.873614190687362e-05,
"loss": 0.6546,
"step": 302
},
{
"epoch": 1.9956043956043956,
"grad_norm": 0.5892533659934998,
"learning_rate": 6.829268292682928e-05,
"loss": 0.844,
"step": 303
},
{
"epoch": 2.0,
"grad_norm": 0.8855454921722412,
"learning_rate": 6.784922394678492e-05,
"loss": 0.7914,
"step": 304
},
{
"epoch": 2.0065934065934066,
"grad_norm": 0.4832310676574707,
"learning_rate": 6.740576496674058e-05,
"loss": 0.7066,
"step": 305
},
{
"epoch": 2.013186813186813,
"grad_norm": 0.5426770448684692,
"learning_rate": 6.696230598669624e-05,
"loss": 0.7472,
"step": 306
},
{
"epoch": 2.0197802197802197,
"grad_norm": 0.5049582123756409,
"learning_rate": 6.651884700665188e-05,
"loss": 0.6647,
"step": 307
},
{
"epoch": 2.0263736263736263,
"grad_norm": 0.5312483906745911,
"learning_rate": 6.607538802660754e-05,
"loss": 0.6106,
"step": 308
},
{
"epoch": 2.032967032967033,
"grad_norm": 0.4600354731082916,
"learning_rate": 6.56319290465632e-05,
"loss": 0.6874,
"step": 309
},
{
"epoch": 2.0395604395604394,
"grad_norm": 0.5751438140869141,
"learning_rate": 6.518847006651884e-05,
"loss": 0.7808,
"step": 310
},
{
"epoch": 2.046153846153846,
"grad_norm": 0.702257513999939,
"learning_rate": 6.47450110864745e-05,
"loss": 0.8011,
"step": 311
},
{
"epoch": 2.0527472527472526,
"grad_norm": 0.5525146126747131,
"learning_rate": 6.430155210643016e-05,
"loss": 0.86,
"step": 312
},
{
"epoch": 2.059340659340659,
"grad_norm": 0.5360015630722046,
"learning_rate": 6.38580931263858e-05,
"loss": 0.8189,
"step": 313
},
{
"epoch": 2.065934065934066,
"grad_norm": 0.7617823481559753,
"learning_rate": 6.341463414634146e-05,
"loss": 0.9794,
"step": 314
},
{
"epoch": 2.0725274725274727,
"grad_norm": 0.503940999507904,
"learning_rate": 6.297117516629712e-05,
"loss": 0.7177,
"step": 315
},
{
"epoch": 2.0791208791208793,
"grad_norm": 0.595704197883606,
"learning_rate": 6.252771618625277e-05,
"loss": 0.6856,
"step": 316
},
{
"epoch": 2.085714285714286,
"grad_norm": 0.6393610835075378,
"learning_rate": 6.208425720620842e-05,
"loss": 0.7924,
"step": 317
},
{
"epoch": 2.0923076923076924,
"grad_norm": 0.6112923622131348,
"learning_rate": 6.164079822616408e-05,
"loss": 0.7188,
"step": 318
},
{
"epoch": 2.098901098901099,
"grad_norm": 0.5725026726722717,
"learning_rate": 6.119733924611974e-05,
"loss": 0.7047,
"step": 319
},
{
"epoch": 2.1054945054945056,
"grad_norm": 0.6937968134880066,
"learning_rate": 6.075388026607539e-05,
"loss": 0.6402,
"step": 320
},
{
"epoch": 2.112087912087912,
"grad_norm": 0.6517937779426575,
"learning_rate": 6.031042128603105e-05,
"loss": 0.7285,
"step": 321
},
{
"epoch": 2.1186813186813187,
"grad_norm": 0.5639869570732117,
"learning_rate": 5.98669623059867e-05,
"loss": 0.8678,
"step": 322
},
{
"epoch": 2.1252747252747253,
"grad_norm": 0.6342422962188721,
"learning_rate": 5.942350332594236e-05,
"loss": 0.8049,
"step": 323
},
{
"epoch": 2.131868131868132,
"grad_norm": 0.5291990637779236,
"learning_rate": 5.898004434589801e-05,
"loss": 0.5225,
"step": 324
},
{
"epoch": 2.1384615384615384,
"grad_norm": 0.631882905960083,
"learning_rate": 5.853658536585366e-05,
"loss": 0.6412,
"step": 325
},
{
"epoch": 2.145054945054945,
"grad_norm": 0.5484399199485779,
"learning_rate": 5.809312638580932e-05,
"loss": 0.7667,
"step": 326
},
{
"epoch": 2.1516483516483516,
"grad_norm": 0.6447159051895142,
"learning_rate": 5.7649667405764975e-05,
"loss": 0.7609,
"step": 327
},
{
"epoch": 2.158241758241758,
"grad_norm": 0.5199384093284607,
"learning_rate": 5.720620842572062e-05,
"loss": 0.9443,
"step": 328
},
{
"epoch": 2.1648351648351647,
"grad_norm": 0.6888903379440308,
"learning_rate": 5.676274944567628e-05,
"loss": 0.7105,
"step": 329
},
{
"epoch": 2.1714285714285713,
"grad_norm": 0.5705382823944092,
"learning_rate": 5.6319290465631935e-05,
"loss": 0.6089,
"step": 330
},
{
"epoch": 2.178021978021978,
"grad_norm": 0.6593491435050964,
"learning_rate": 5.587583148558758e-05,
"loss": 0.6963,
"step": 331
},
{
"epoch": 2.184615384615385,
"grad_norm": 0.6359004974365234,
"learning_rate": 5.543237250554324e-05,
"loss": 0.7339,
"step": 332
},
{
"epoch": 2.1912087912087914,
"grad_norm": 0.6565458178520203,
"learning_rate": 5.4988913525498895e-05,
"loss": 0.8044,
"step": 333
},
{
"epoch": 2.197802197802198,
"grad_norm": 0.6484739184379578,
"learning_rate": 5.4545454545454546e-05,
"loss": 0.8198,
"step": 334
},
{
"epoch": 2.2043956043956046,
"grad_norm": 0.6816954016685486,
"learning_rate": 5.4101995565410204e-05,
"loss": 0.7146,
"step": 335
},
{
"epoch": 2.210989010989011,
"grad_norm": 0.7222168445587158,
"learning_rate": 5.365853658536586e-05,
"loss": 0.7429,
"step": 336
},
{
"epoch": 2.2175824175824177,
"grad_norm": 0.6570652723312378,
"learning_rate": 5.3215077605321506e-05,
"loss": 0.6706,
"step": 337
},
{
"epoch": 2.2241758241758243,
"grad_norm": 0.6258172988891602,
"learning_rate": 5.2771618625277164e-05,
"loss": 0.7186,
"step": 338
},
{
"epoch": 2.230769230769231,
"grad_norm": 0.7049463391304016,
"learning_rate": 5.232815964523282e-05,
"loss": 0.8033,
"step": 339
},
{
"epoch": 2.2373626373626374,
"grad_norm": 0.6348817348480225,
"learning_rate": 5.1884700665188466e-05,
"loss": 0.6755,
"step": 340
},
{
"epoch": 2.243956043956044,
"grad_norm": 0.6211584210395813,
"learning_rate": 5.1441241685144124e-05,
"loss": 0.6156,
"step": 341
},
{
"epoch": 2.2505494505494505,
"grad_norm": 0.613209068775177,
"learning_rate": 5.099778270509978e-05,
"loss": 0.8321,
"step": 342
},
{
"epoch": 2.257142857142857,
"grad_norm": 0.5939221382141113,
"learning_rate": 5.0554323725055433e-05,
"loss": 0.7474,
"step": 343
},
{
"epoch": 2.2637362637362637,
"grad_norm": 0.6400361657142639,
"learning_rate": 5.011086474501109e-05,
"loss": 0.8154,
"step": 344
},
{
"epoch": 2.2703296703296703,
"grad_norm": 0.5587393641471863,
"learning_rate": 4.966740576496674e-05,
"loss": 0.7079,
"step": 345
},
{
"epoch": 2.276923076923077,
"grad_norm": 0.5834840536117554,
"learning_rate": 4.92239467849224e-05,
"loss": 0.6904,
"step": 346
},
{
"epoch": 2.2835164835164834,
"grad_norm": 0.6756699085235596,
"learning_rate": 4.878048780487805e-05,
"loss": 0.8517,
"step": 347
},
{
"epoch": 2.29010989010989,
"grad_norm": 0.624579906463623,
"learning_rate": 4.833702882483371e-05,
"loss": 0.727,
"step": 348
},
{
"epoch": 2.2967032967032965,
"grad_norm": 0.6579897403717041,
"learning_rate": 4.789356984478936e-05,
"loss": 0.7827,
"step": 349
},
{
"epoch": 2.303296703296703,
"grad_norm": 0.6018035411834717,
"learning_rate": 4.745011086474501e-05,
"loss": 0.7323,
"step": 350
},
{
"epoch": 2.3098901098901097,
"grad_norm": 0.6663884520530701,
"learning_rate": 4.700665188470067e-05,
"loss": 0.7807,
"step": 351
},
{
"epoch": 2.3164835164835162,
"grad_norm": 0.5084959864616394,
"learning_rate": 4.656319290465632e-05,
"loss": 0.648,
"step": 352
},
{
"epoch": 2.3230769230769233,
"grad_norm": 0.6242216229438782,
"learning_rate": 4.611973392461197e-05,
"loss": 0.6324,
"step": 353
},
{
"epoch": 2.32967032967033,
"grad_norm": 0.6189213395118713,
"learning_rate": 4.567627494456763e-05,
"loss": 0.6608,
"step": 354
},
{
"epoch": 2.3362637362637364,
"grad_norm": 0.6547122597694397,
"learning_rate": 4.523281596452328e-05,
"loss": 0.8847,
"step": 355
},
{
"epoch": 2.342857142857143,
"grad_norm": 0.6705129742622375,
"learning_rate": 4.478935698447894e-05,
"loss": 0.6479,
"step": 356
},
{
"epoch": 2.3494505494505495,
"grad_norm": 0.5222570300102234,
"learning_rate": 4.4345898004434597e-05,
"loss": 0.6644,
"step": 357
},
{
"epoch": 2.356043956043956,
"grad_norm": 0.7039546370506287,
"learning_rate": 4.390243902439025e-05,
"loss": 0.7431,
"step": 358
},
{
"epoch": 2.3626373626373627,
"grad_norm": 0.685729444026947,
"learning_rate": 4.34589800443459e-05,
"loss": 0.7362,
"step": 359
},
{
"epoch": 2.3692307692307693,
"grad_norm": 0.5532290935516357,
"learning_rate": 4.301552106430156e-05,
"loss": 0.5502,
"step": 360
},
{
"epoch": 2.375824175824176,
"grad_norm": 0.6572507619857788,
"learning_rate": 4.257206208425721e-05,
"loss": 0.8119,
"step": 361
},
{
"epoch": 2.3824175824175824,
"grad_norm": 0.5911145210266113,
"learning_rate": 4.212860310421286e-05,
"loss": 0.5668,
"step": 362
},
{
"epoch": 2.389010989010989,
"grad_norm": 0.612006664276123,
"learning_rate": 4.168514412416852e-05,
"loss": 0.6907,
"step": 363
},
{
"epoch": 2.3956043956043955,
"grad_norm": 0.7296512126922607,
"learning_rate": 4.124168514412417e-05,
"loss": 0.6988,
"step": 364
},
{
"epoch": 2.402197802197802,
"grad_norm": 0.6444362998008728,
"learning_rate": 4.0798226164079826e-05,
"loss": 0.6473,
"step": 365
},
{
"epoch": 2.4087912087912087,
"grad_norm": 0.7072091698646545,
"learning_rate": 4.035476718403548e-05,
"loss": 0.6201,
"step": 366
},
{
"epoch": 2.4153846153846152,
"grad_norm": 0.6872286796569824,
"learning_rate": 3.9911308203991135e-05,
"loss": 0.6476,
"step": 367
},
{
"epoch": 2.421978021978022,
"grad_norm": 0.7309032678604126,
"learning_rate": 3.9467849223946786e-05,
"loss": 0.6996,
"step": 368
},
{
"epoch": 2.4285714285714284,
"grad_norm": 0.7869054079055786,
"learning_rate": 3.9024390243902444e-05,
"loss": 0.9602,
"step": 369
},
{
"epoch": 2.4351648351648354,
"grad_norm": 0.690997838973999,
"learning_rate": 3.8580931263858095e-05,
"loss": 0.7703,
"step": 370
},
{
"epoch": 2.441758241758242,
"grad_norm": 0.7666214108467102,
"learning_rate": 3.8137472283813746e-05,
"loss": 0.7694,
"step": 371
},
{
"epoch": 2.4483516483516485,
"grad_norm": 0.6534345746040344,
"learning_rate": 3.7694013303769404e-05,
"loss": 0.5593,
"step": 372
},
{
"epoch": 2.454945054945055,
"grad_norm": 0.5466397404670715,
"learning_rate": 3.7250554323725055e-05,
"loss": 0.6913,
"step": 373
},
{
"epoch": 2.4615384615384617,
"grad_norm": 0.7387297749519348,
"learning_rate": 3.6807095343680706e-05,
"loss": 0.6425,
"step": 374
},
{
"epoch": 2.4681318681318682,
"grad_norm": 0.6546596884727478,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.6744,
"step": 375
},
{
"epoch": 2.474725274725275,
"grad_norm": 0.741736114025116,
"learning_rate": 3.5920177383592015e-05,
"loss": 0.6916,
"step": 376
},
{
"epoch": 2.4813186813186814,
"grad_norm": 0.643612802028656,
"learning_rate": 3.547671840354767e-05,
"loss": 0.7059,
"step": 377
},
{
"epoch": 2.487912087912088,
"grad_norm": 0.8267149329185486,
"learning_rate": 3.503325942350333e-05,
"loss": 0.7694,
"step": 378
},
{
"epoch": 2.4945054945054945,
"grad_norm": 0.7045459747314453,
"learning_rate": 3.458980044345898e-05,
"loss": 0.7958,
"step": 379
},
{
"epoch": 2.501098901098901,
"grad_norm": 0.7357338666915894,
"learning_rate": 3.414634146341464e-05,
"loss": 0.5966,
"step": 380
},
{
"epoch": 2.5076923076923077,
"grad_norm": 0.6819212436676025,
"learning_rate": 3.370288248337029e-05,
"loss": 0.7221,
"step": 381
},
{
"epoch": 2.5142857142857142,
"grad_norm": 0.693884015083313,
"learning_rate": 3.325942350332594e-05,
"loss": 0.6782,
"step": 382
},
{
"epoch": 2.520879120879121,
"grad_norm": 0.6668160557746887,
"learning_rate": 3.28159645232816e-05,
"loss": 0.5558,
"step": 383
},
{
"epoch": 2.5274725274725274,
"grad_norm": 0.7373205423355103,
"learning_rate": 3.237250554323725e-05,
"loss": 0.7097,
"step": 384
},
{
"epoch": 2.534065934065934,
"grad_norm": 0.7147855162620544,
"learning_rate": 3.19290465631929e-05,
"loss": 0.7148,
"step": 385
},
{
"epoch": 2.5406593406593405,
"grad_norm": 0.8732993602752686,
"learning_rate": 3.148558758314856e-05,
"loss": 0.7136,
"step": 386
},
{
"epoch": 2.547252747252747,
"grad_norm": 0.645398736000061,
"learning_rate": 3.104212860310421e-05,
"loss": 0.6196,
"step": 387
},
{
"epoch": 2.5538461538461537,
"grad_norm": 0.7994987964630127,
"learning_rate": 3.059866962305987e-05,
"loss": 0.7668,
"step": 388
},
{
"epoch": 2.5604395604395602,
"grad_norm": 0.6419384479522705,
"learning_rate": 3.0155210643015524e-05,
"loss": 0.6913,
"step": 389
},
{
"epoch": 2.567032967032967,
"grad_norm": 0.6542741060256958,
"learning_rate": 2.971175166297118e-05,
"loss": 0.7537,
"step": 390
},
{
"epoch": 2.5736263736263734,
"grad_norm": 0.7126234173774719,
"learning_rate": 2.926829268292683e-05,
"loss": 0.7019,
"step": 391
},
{
"epoch": 2.5802197802197804,
"grad_norm": 0.5850012898445129,
"learning_rate": 2.8824833702882487e-05,
"loss": 0.6164,
"step": 392
},
{
"epoch": 2.586813186813187,
"grad_norm": 0.7643885612487793,
"learning_rate": 2.838137472283814e-05,
"loss": 0.6755,
"step": 393
},
{
"epoch": 2.5934065934065935,
"grad_norm": 0.811208963394165,
"learning_rate": 2.793791574279379e-05,
"loss": 0.9008,
"step": 394
},
{
"epoch": 2.6,
"grad_norm": 0.6883062720298767,
"learning_rate": 2.7494456762749448e-05,
"loss": 0.7609,
"step": 395
},
{
"epoch": 2.6065934065934067,
"grad_norm": 0.6307688355445862,
"learning_rate": 2.7050997782705102e-05,
"loss": 0.7231,
"step": 396
},
{
"epoch": 2.6131868131868132,
"grad_norm": 0.6015840768814087,
"learning_rate": 2.6607538802660753e-05,
"loss": 0.5565,
"step": 397
},
{
"epoch": 2.61978021978022,
"grad_norm": 0.5913680195808411,
"learning_rate": 2.616407982261641e-05,
"loss": 0.557,
"step": 398
},
{
"epoch": 2.6263736263736264,
"grad_norm": 0.7772789597511292,
"learning_rate": 2.5720620842572062e-05,
"loss": 0.7484,
"step": 399
},
{
"epoch": 2.632967032967033,
"grad_norm": 0.7032859325408936,
"learning_rate": 2.5277161862527717e-05,
"loss": 0.5634,
"step": 400
},
{
"epoch": 2.6395604395604395,
"grad_norm": 0.6432788372039795,
"learning_rate": 2.483370288248337e-05,
"loss": 0.6029,
"step": 401
},
{
"epoch": 2.646153846153846,
"grad_norm": 0.7186959981918335,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.634,
"step": 402
},
{
"epoch": 2.6527472527472526,
"grad_norm": 0.7002720832824707,
"learning_rate": 2.394678492239468e-05,
"loss": 0.7689,
"step": 403
},
{
"epoch": 2.659340659340659,
"grad_norm": 0.8342587947845459,
"learning_rate": 2.3503325942350335e-05,
"loss": 0.9136,
"step": 404
},
{
"epoch": 2.665934065934066,
"grad_norm": 0.6448255777359009,
"learning_rate": 2.3059866962305986e-05,
"loss": 0.663,
"step": 405
},
{
"epoch": 2.672527472527473,
"grad_norm": 0.6710597276687622,
"learning_rate": 2.261640798226164e-05,
"loss": 0.8543,
"step": 406
},
{
"epoch": 2.6791208791208794,
"grad_norm": 0.6945552229881287,
"learning_rate": 2.2172949002217298e-05,
"loss": 0.7346,
"step": 407
},
{
"epoch": 2.685714285714286,
"grad_norm": 0.6935684084892273,
"learning_rate": 2.172949002217295e-05,
"loss": 0.7831,
"step": 408
},
{
"epoch": 2.6923076923076925,
"grad_norm": 0.7012293934822083,
"learning_rate": 2.1286031042128604e-05,
"loss": 0.7416,
"step": 409
},
{
"epoch": 2.698901098901099,
"grad_norm": 0.6519166827201843,
"learning_rate": 2.084257206208426e-05,
"loss": 0.6549,
"step": 410
},
{
"epoch": 2.7054945054945057,
"grad_norm": 0.7289109826087952,
"learning_rate": 2.0399113082039913e-05,
"loss": 0.6065,
"step": 411
},
{
"epoch": 2.7120879120879122,
"grad_norm": 0.6062592267990112,
"learning_rate": 1.9955654101995567e-05,
"loss": 0.7388,
"step": 412
},
{
"epoch": 2.718681318681319,
"grad_norm": 0.661196768283844,
"learning_rate": 1.9512195121951222e-05,
"loss": 0.6454,
"step": 413
},
{
"epoch": 2.7252747252747254,
"grad_norm": 0.7666320204734802,
"learning_rate": 1.9068736141906873e-05,
"loss": 0.7405,
"step": 414
},
{
"epoch": 2.731868131868132,
"grad_norm": 0.5990496873855591,
"learning_rate": 1.8625277161862528e-05,
"loss": 0.6254,
"step": 415
},
{
"epoch": 2.7384615384615385,
"grad_norm": 0.7445687055587769,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.7414,
"step": 416
},
{
"epoch": 2.745054945054945,
"grad_norm": 0.7187737226486206,
"learning_rate": 1.7738359201773837e-05,
"loss": 0.6837,
"step": 417
},
{
"epoch": 2.7516483516483516,
"grad_norm": 0.5171895623207092,
"learning_rate": 1.729490022172949e-05,
"loss": 0.7145,
"step": 418
},
{
"epoch": 2.758241758241758,
"grad_norm": 0.7890187501907349,
"learning_rate": 1.6851441241685146e-05,
"loss": 0.7052,
"step": 419
},
{
"epoch": 2.764835164835165,
"grad_norm": 0.7857847809791565,
"learning_rate": 1.64079822616408e-05,
"loss": 0.766,
"step": 420
}
],
"logging_steps": 1,
"max_steps": 456,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 15,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.915611699001754e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}