jeqcho's picture
Upload seed0/checkpoint-150
876b4d6 verified
Raw
History Blame
26.7 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.989010989010989,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 0.8349836468696594,
"learning_rate": 0.0,
"loss": 0.9434,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 0.8700987696647644,
"learning_rate": 4e-05,
"loss": 0.9905,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 0.9241365194320679,
"learning_rate": 8e-05,
"loss": 0.9438,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 0.9019892811775208,
"learning_rate": 0.00012,
"loss": 0.9216,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 0.8872910141944885,
"learning_rate": 0.00016,
"loss": 0.9374,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 0.5874530076980591,
"learning_rate": 0.0002,
"loss": 0.7673,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 0.5062956809997559,
"learning_rate": 0.00019955654101995565,
"loss": 0.8011,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 0.5953829288482666,
"learning_rate": 0.00019911308203991133,
"loss": 0.8455,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 0.5616072416305542,
"learning_rate": 0.00019866962305986697,
"loss": 0.8265,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.49180087447166443,
"learning_rate": 0.00019822616407982261,
"loss": 0.8561,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.42030951380729675,
"learning_rate": 0.00019778270509977829,
"loss": 0.8796,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.3004567325115204,
"learning_rate": 0.00019733924611973393,
"loss": 0.8636,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.2698984444141388,
"learning_rate": 0.0001968957871396896,
"loss": 0.718,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.25445133447647095,
"learning_rate": 0.00019645232815964525,
"loss": 0.7235,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.22418756783008575,
"learning_rate": 0.00019600886917960092,
"loss": 0.688,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.2096303105354309,
"learning_rate": 0.00019556541019955653,
"loss": 0.7267,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.3029191195964813,
"learning_rate": 0.0001951219512195122,
"loss": 0.7763,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.2644464075565338,
"learning_rate": 0.00019467849223946785,
"loss": 0.7618,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.2536560893058777,
"learning_rate": 0.00019423503325942352,
"loss": 0.7999,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.24718916416168213,
"learning_rate": 0.00019379157427937917,
"loss": 0.752,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.2625150680541992,
"learning_rate": 0.00019334811529933484,
"loss": 0.736,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.32164040207862854,
"learning_rate": 0.00019290465631929045,
"loss": 0.7043,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.3981449604034424,
"learning_rate": 0.00019246119733924613,
"loss": 0.7057,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.3817313015460968,
"learning_rate": 0.00019201773835920177,
"loss": 0.7413,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.29256680607795715,
"learning_rate": 0.00019157427937915744,
"loss": 0.693,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.27523350715637207,
"learning_rate": 0.00019113082039911309,
"loss": 0.6474,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.23511967062950134,
"learning_rate": 0.00019068736141906876,
"loss": 0.6519,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.2961374819278717,
"learning_rate": 0.0001902439024390244,
"loss": 0.6426,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.2760772407054901,
"learning_rate": 0.00018980044345898005,
"loss": 0.7388,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.2285313606262207,
"learning_rate": 0.00018935698447893572,
"loss": 0.7756,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.2657061517238617,
"learning_rate": 0.00018891352549889136,
"loss": 0.7275,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.22572828829288483,
"learning_rate": 0.00018847006651884703,
"loss": 0.6793,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.26335304975509644,
"learning_rate": 0.00018802660753880268,
"loss": 0.7131,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.25231942534446716,
"learning_rate": 0.00018758314855875832,
"loss": 0.7715,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.2437426745891571,
"learning_rate": 0.00018713968957871397,
"loss": 0.7094,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.28558826446533203,
"learning_rate": 0.00018669623059866964,
"loss": 0.6937,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.2915894687175751,
"learning_rate": 0.00018625277161862528,
"loss": 0.7238,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.25342074036598206,
"learning_rate": 0.00018580931263858095,
"loss": 0.7323,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.22744007408618927,
"learning_rate": 0.0001853658536585366,
"loss": 0.703,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.25383231043815613,
"learning_rate": 0.00018492239467849224,
"loss": 0.7093,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.2194337695837021,
"learning_rate": 0.0001844789356984479,
"loss": 0.7367,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.32021859288215637,
"learning_rate": 0.00018403547671840356,
"loss": 0.6652,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.2328304797410965,
"learning_rate": 0.0001835920177383592,
"loss": 0.7016,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.24166613817214966,
"learning_rate": 0.00018314855875831487,
"loss": 0.6717,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.2733803391456604,
"learning_rate": 0.00018270509977827052,
"loss": 0.6979,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.2689957320690155,
"learning_rate": 0.00018226164079822616,
"loss": 0.6977,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.2698104977607727,
"learning_rate": 0.00018181818181818183,
"loss": 0.723,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.25856417417526245,
"learning_rate": 0.00018137472283813748,
"loss": 0.723,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.22988826036453247,
"learning_rate": 0.00018093126385809312,
"loss": 0.7356,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.24859416484832764,
"learning_rate": 0.0001804878048780488,
"loss": 0.6671,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.24891626834869385,
"learning_rate": 0.00018004434589800444,
"loss": 0.6628,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.22740386426448822,
"learning_rate": 0.00017960088691796008,
"loss": 0.6377,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.2636365294456482,
"learning_rate": 0.00017915742793791575,
"loss": 0.6901,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.2437390238046646,
"learning_rate": 0.0001787139689578714,
"loss": 0.72,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.23658742010593414,
"learning_rate": 0.00017827050997782707,
"loss": 0.7365,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.23923538625240326,
"learning_rate": 0.00017782705099778271,
"loss": 0.706,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.2877054512500763,
"learning_rate": 0.00017738359201773839,
"loss": 0.7436,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.2839520573616028,
"learning_rate": 0.000176940133037694,
"loss": 0.6779,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.2308293879032135,
"learning_rate": 0.00017649667405764967,
"loss": 0.6357,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.24402214586734772,
"learning_rate": 0.00017605321507760532,
"loss": 0.7508,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.23816415667533875,
"learning_rate": 0.000175609756097561,
"loss": 0.7249,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.28321942687034607,
"learning_rate": 0.00017516629711751663,
"loss": 0.7479,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.23680296540260315,
"learning_rate": 0.0001747228381374723,
"loss": 0.6413,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.23129238188266754,
"learning_rate": 0.00017427937915742792,
"loss": 0.6786,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.25140181183815,
"learning_rate": 0.0001738359201773836,
"loss": 0.7167,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.27190810441970825,
"learning_rate": 0.00017339246119733924,
"loss": 0.6267,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.23768772184848785,
"learning_rate": 0.0001729490022172949,
"loss": 0.7397,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.2618238031864166,
"learning_rate": 0.00017250554323725056,
"loss": 0.6987,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.24789907038211823,
"learning_rate": 0.00017206208425720623,
"loss": 0.6223,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.2744330167770386,
"learning_rate": 0.00017161862527716187,
"loss": 0.6964,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.23732465505599976,
"learning_rate": 0.00017117516629711752,
"loss": 0.6524,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.2278261035680771,
"learning_rate": 0.0001707317073170732,
"loss": 0.7437,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.24909941852092743,
"learning_rate": 0.00017028824833702883,
"loss": 0.6955,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.3007880449295044,
"learning_rate": 0.0001698447893569845,
"loss": 0.625,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.2338089644908905,
"learning_rate": 0.00016940133037694015,
"loss": 0.6843,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.27349653840065,
"learning_rate": 0.00016895787139689582,
"loss": 0.6825,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.2793181836605072,
"learning_rate": 0.00016851441241685144,
"loss": 0.6529,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.2612224221229553,
"learning_rate": 0.0001680709534368071,
"loss": 0.6807,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.2740105986595154,
"learning_rate": 0.00016762749445676275,
"loss": 0.6294,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.2226412147283554,
"learning_rate": 0.00016718403547671842,
"loss": 0.6569,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.2254134714603424,
"learning_rate": 0.00016674057649667407,
"loss": 0.6569,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.22373083233833313,
"learning_rate": 0.00016629711751662974,
"loss": 0.6733,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.2485770583152771,
"learning_rate": 0.00016585365853658536,
"loss": 0.6422,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.25764942169189453,
"learning_rate": 0.00016541019955654103,
"loss": 0.6682,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.24047411978244781,
"learning_rate": 0.00016496674057649667,
"loss": 0.7126,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.21252930164337158,
"learning_rate": 0.00016452328159645234,
"loss": 0.7109,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.25431081652641296,
"learning_rate": 0.000164079822616408,
"loss": 0.6416,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.24909189343452454,
"learning_rate": 0.00016363636363636366,
"loss": 0.6963,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.25534072518348694,
"learning_rate": 0.0001631929046563193,
"loss": 0.7898,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.22847016155719757,
"learning_rate": 0.00016274944567627495,
"loss": 0.6903,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.27691230177879333,
"learning_rate": 0.0001623059866962306,
"loss": 0.6963,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.2628577649593353,
"learning_rate": 0.00016186252771618626,
"loss": 0.7605,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.29095378518104553,
"learning_rate": 0.0001614190687361419,
"loss": 0.6878,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.24262812733650208,
"learning_rate": 0.00016097560975609758,
"loss": 0.7383,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.21234223246574402,
"learning_rate": 0.00016053215077605322,
"loss": 0.6735,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.2478182166814804,
"learning_rate": 0.00016008869179600887,
"loss": 0.6334,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.22873812913894653,
"learning_rate": 0.00015964523281596454,
"loss": 0.6968,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.24787071347236633,
"learning_rate": 0.00015920177383592018,
"loss": 0.7076,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.2913095951080322,
"learning_rate": 0.00015875831485587586,
"loss": 0.6785,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.27481356263160706,
"learning_rate": 0.0001583148558758315,
"loss": 0.7055,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.24760739505290985,
"learning_rate": 0.00015787139689578714,
"loss": 0.7027,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.2754676342010498,
"learning_rate": 0.0001574279379157428,
"loss": 0.7027,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.2395099550485611,
"learning_rate": 0.00015698447893569846,
"loss": 0.6846,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.2519392669200897,
"learning_rate": 0.0001565410199556541,
"loss": 0.7722,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.24618907272815704,
"learning_rate": 0.00015609756097560978,
"loss": 0.6933,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.2342153638601303,
"learning_rate": 0.00015565410199556542,
"loss": 0.6866,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.23813366889953613,
"learning_rate": 0.00015521064301552106,
"loss": 0.6476,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.21853409707546234,
"learning_rate": 0.0001547671840354767,
"loss": 0.6401,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.22005102038383484,
"learning_rate": 0.00015432372505543238,
"loss": 0.6173,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.2145771086215973,
"learning_rate": 0.00015388026607538802,
"loss": 0.6712,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.2519795894622803,
"learning_rate": 0.0001534368070953437,
"loss": 0.7036,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.21608349680900574,
"learning_rate": 0.00015299334811529934,
"loss": 0.7213,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.2526698410511017,
"learning_rate": 0.00015254988913525498,
"loss": 0.6326,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.22119538486003876,
"learning_rate": 0.00015210643015521066,
"loss": 0.643,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.23445621132850647,
"learning_rate": 0.0001516629711751663,
"loss": 0.6562,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.21006852388381958,
"learning_rate": 0.00015121951219512197,
"loss": 0.7381,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.2904897928237915,
"learning_rate": 0.00015077605321507762,
"loss": 0.723,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.28895437717437744,
"learning_rate": 0.0001503325942350333,
"loss": 0.6517,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.24994221329689026,
"learning_rate": 0.0001498891352549889,
"loss": 0.6621,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.24564869701862335,
"learning_rate": 0.00014944567627494458,
"loss": 0.7548,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.2209189534187317,
"learning_rate": 0.00014900221729490022,
"loss": 0.6474,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.24389097094535828,
"learning_rate": 0.0001485587583148559,
"loss": 0.7471,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.23514863848686218,
"learning_rate": 0.00014811529933481154,
"loss": 0.6859,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.26364991068840027,
"learning_rate": 0.0001476718403547672,
"loss": 0.6276,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.2185850590467453,
"learning_rate": 0.00014722838137472282,
"loss": 0.7346,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.22511166334152222,
"learning_rate": 0.0001467849223946785,
"loss": 0.7208,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.20826543867588043,
"learning_rate": 0.00014634146341463414,
"loss": 0.6757,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.22027815878391266,
"learning_rate": 0.0001458980044345898,
"loss": 0.6839,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.23337896168231964,
"learning_rate": 0.00014545454545454546,
"loss": 0.6555,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.21975719928741455,
"learning_rate": 0.00014501108647450113,
"loss": 0.6829,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.2579653263092041,
"learning_rate": 0.00014456762749445675,
"loss": 0.6567,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.19928398728370667,
"learning_rate": 0.00014412416851441242,
"loss": 0.7138,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.23015153408050537,
"learning_rate": 0.00014368070953436806,
"loss": 0.695,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.25714021921157837,
"learning_rate": 0.00014323725055432373,
"loss": 0.7245,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.2980111837387085,
"learning_rate": 0.00014279379157427938,
"loss": 0.7276,
"step": 135
},
{
"epoch": 0.8967032967032967,
"grad_norm": 0.22255489230155945,
"learning_rate": 0.00014235033259423505,
"loss": 0.6282,
"step": 136
},
{
"epoch": 0.9032967032967033,
"grad_norm": 0.1886795461177826,
"learning_rate": 0.0001419068736141907,
"loss": 0.703,
"step": 137
},
{
"epoch": 0.9098901098901099,
"grad_norm": 0.20825117826461792,
"learning_rate": 0.00014146341463414634,
"loss": 0.7088,
"step": 138
},
{
"epoch": 0.9164835164835164,
"grad_norm": 0.23884426057338715,
"learning_rate": 0.000141019955654102,
"loss": 0.6704,
"step": 139
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.23004014790058136,
"learning_rate": 0.00014057649667405765,
"loss": 0.6254,
"step": 140
},
{
"epoch": 0.9296703296703297,
"grad_norm": 0.21654583513736725,
"learning_rate": 0.00014013303769401332,
"loss": 0.7034,
"step": 141
},
{
"epoch": 0.9362637362637363,
"grad_norm": 0.2495403289794922,
"learning_rate": 0.00013968957871396897,
"loss": 0.7006,
"step": 142
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.22400696575641632,
"learning_rate": 0.00013924611973392464,
"loss": 0.6787,
"step": 143
},
{
"epoch": 0.9494505494505494,
"grad_norm": 0.2399936020374298,
"learning_rate": 0.00013880266075388026,
"loss": 0.6231,
"step": 144
},
{
"epoch": 0.9560439560439561,
"grad_norm": 0.23908363282680511,
"learning_rate": 0.00013835920177383593,
"loss": 0.7955,
"step": 145
},
{
"epoch": 0.9626373626373627,
"grad_norm": 0.2390311360359192,
"learning_rate": 0.00013791574279379157,
"loss": 0.7071,
"step": 146
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.24296815693378448,
"learning_rate": 0.00013747228381374724,
"loss": 0.6154,
"step": 147
},
{
"epoch": 0.9758241758241758,
"grad_norm": 0.2415105700492859,
"learning_rate": 0.0001370288248337029,
"loss": 0.7034,
"step": 148
},
{
"epoch": 0.9824175824175824,
"grad_norm": 0.23874816298484802,
"learning_rate": 0.00013658536585365856,
"loss": 0.6519,
"step": 149
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.23809735476970673,
"learning_rate": 0.00013614190687361418,
"loss": 0.7036,
"step": 150
}
],
"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": 6.923770403377766e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}