prxy5605's picture
Training in progress, step 200, checkpoint
9deaba9 verified
raw
history blame
36.5 kB
{
"best_metric": 1.3537832498550415,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.0871554635581218,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000435777317790609,
"grad_norm": 2.0851054191589355,
"learning_rate": 5e-06,
"loss": 1.6817,
"step": 1
},
{
"epoch": 0.000435777317790609,
"eval_loss": 2.0230047702789307,
"eval_runtime": 315.559,
"eval_samples_per_second": 12.248,
"eval_steps_per_second": 6.126,
"step": 1
},
{
"epoch": 0.000871554635581218,
"grad_norm": 2.216548204421997,
"learning_rate": 1e-05,
"loss": 1.8021,
"step": 2
},
{
"epoch": 0.001307331953371827,
"grad_norm": 2.3968324661254883,
"learning_rate": 1.5e-05,
"loss": 1.9165,
"step": 3
},
{
"epoch": 0.001743109271162436,
"grad_norm": 2.045064926147461,
"learning_rate": 2e-05,
"loss": 1.8139,
"step": 4
},
{
"epoch": 0.002178886588953045,
"grad_norm": 2.1230273246765137,
"learning_rate": 2.5e-05,
"loss": 1.8931,
"step": 5
},
{
"epoch": 0.002614663906743654,
"grad_norm": 1.675313949584961,
"learning_rate": 3e-05,
"loss": 1.762,
"step": 6
},
{
"epoch": 0.003050441224534263,
"grad_norm": 1.3971757888793945,
"learning_rate": 3.5e-05,
"loss": 1.5999,
"step": 7
},
{
"epoch": 0.003486218542324872,
"grad_norm": 1.214509129524231,
"learning_rate": 4e-05,
"loss": 1.663,
"step": 8
},
{
"epoch": 0.003921995860115481,
"grad_norm": 1.1938960552215576,
"learning_rate": 4.5e-05,
"loss": 1.6785,
"step": 9
},
{
"epoch": 0.00435777317790609,
"grad_norm": 1.2489292621612549,
"learning_rate": 5e-05,
"loss": 1.5493,
"step": 10
},
{
"epoch": 0.004793550495696699,
"grad_norm": 1.2138938903808594,
"learning_rate": 5.500000000000001e-05,
"loss": 1.622,
"step": 11
},
{
"epoch": 0.005229327813487308,
"grad_norm": 1.2661142349243164,
"learning_rate": 6e-05,
"loss": 1.5328,
"step": 12
},
{
"epoch": 0.005665105131277917,
"grad_norm": 1.047982931137085,
"learning_rate": 6.500000000000001e-05,
"loss": 1.5021,
"step": 13
},
{
"epoch": 0.006100882449068526,
"grad_norm": 0.9978450536727905,
"learning_rate": 7e-05,
"loss": 1.6194,
"step": 14
},
{
"epoch": 0.006536659766859135,
"grad_norm": 0.8680281043052673,
"learning_rate": 7.500000000000001e-05,
"loss": 1.3816,
"step": 15
},
{
"epoch": 0.006972437084649744,
"grad_norm": 0.9196011424064636,
"learning_rate": 8e-05,
"loss": 1.5334,
"step": 16
},
{
"epoch": 0.007408214402440353,
"grad_norm": 0.9667453765869141,
"learning_rate": 8.5e-05,
"loss": 1.4741,
"step": 17
},
{
"epoch": 0.007843991720230961,
"grad_norm": 0.8727541565895081,
"learning_rate": 9e-05,
"loss": 1.4547,
"step": 18
},
{
"epoch": 0.008279769038021571,
"grad_norm": 0.9195423722267151,
"learning_rate": 9.5e-05,
"loss": 1.5097,
"step": 19
},
{
"epoch": 0.00871554635581218,
"grad_norm": 1.05409574508667,
"learning_rate": 0.0001,
"loss": 1.4515,
"step": 20
},
{
"epoch": 0.00915132367360279,
"grad_norm": 0.8618441820144653,
"learning_rate": 9.999238475781957e-05,
"loss": 1.3947,
"step": 21
},
{
"epoch": 0.009587100991393397,
"grad_norm": 0.8809842467308044,
"learning_rate": 9.99695413509548e-05,
"loss": 1.4563,
"step": 22
},
{
"epoch": 0.010022878309184007,
"grad_norm": 0.8538223505020142,
"learning_rate": 9.99314767377287e-05,
"loss": 1.4483,
"step": 23
},
{
"epoch": 0.010458655626974615,
"grad_norm": 0.8714299201965332,
"learning_rate": 9.987820251299122e-05,
"loss": 1.438,
"step": 24
},
{
"epoch": 0.010894432944765225,
"grad_norm": 0.8516822457313538,
"learning_rate": 9.980973490458728e-05,
"loss": 1.382,
"step": 25
},
{
"epoch": 0.011330210262555833,
"grad_norm": 0.9048829078674316,
"learning_rate": 9.972609476841367e-05,
"loss": 1.469,
"step": 26
},
{
"epoch": 0.011765987580346443,
"grad_norm": 0.8362917900085449,
"learning_rate": 9.962730758206611e-05,
"loss": 1.4376,
"step": 27
},
{
"epoch": 0.012201764898137051,
"grad_norm": 0.8152568936347961,
"learning_rate": 9.951340343707852e-05,
"loss": 1.4729,
"step": 28
},
{
"epoch": 0.012637542215927661,
"grad_norm": 0.8475168943405151,
"learning_rate": 9.938441702975689e-05,
"loss": 1.4389,
"step": 29
},
{
"epoch": 0.01307331953371827,
"grad_norm": 0.8305416703224182,
"learning_rate": 9.924038765061042e-05,
"loss": 1.444,
"step": 30
},
{
"epoch": 0.013509096851508879,
"grad_norm": 0.8335140943527222,
"learning_rate": 9.908135917238321e-05,
"loss": 1.3876,
"step": 31
},
{
"epoch": 0.013944874169299489,
"grad_norm": 0.8393346667289734,
"learning_rate": 9.890738003669029e-05,
"loss": 1.4717,
"step": 32
},
{
"epoch": 0.014380651487090097,
"grad_norm": 0.8358327150344849,
"learning_rate": 9.871850323926177e-05,
"loss": 1.3911,
"step": 33
},
{
"epoch": 0.014816428804880707,
"grad_norm": 0.8287831544876099,
"learning_rate": 9.851478631379982e-05,
"loss": 1.3734,
"step": 34
},
{
"epoch": 0.015252206122671315,
"grad_norm": 0.7427653670310974,
"learning_rate": 9.829629131445342e-05,
"loss": 1.3105,
"step": 35
},
{
"epoch": 0.015687983440461923,
"grad_norm": 0.8388314843177795,
"learning_rate": 9.806308479691595e-05,
"loss": 1.4373,
"step": 36
},
{
"epoch": 0.016123760758252535,
"grad_norm": 0.7671462297439575,
"learning_rate": 9.781523779815179e-05,
"loss": 1.3883,
"step": 37
},
{
"epoch": 0.016559538076043143,
"grad_norm": 0.8673655986785889,
"learning_rate": 9.755282581475769e-05,
"loss": 1.3485,
"step": 38
},
{
"epoch": 0.01699531539383375,
"grad_norm": 0.8480393290519714,
"learning_rate": 9.727592877996585e-05,
"loss": 1.4058,
"step": 39
},
{
"epoch": 0.01743109271162436,
"grad_norm": 0.8280643820762634,
"learning_rate": 9.698463103929542e-05,
"loss": 1.47,
"step": 40
},
{
"epoch": 0.01786687002941497,
"grad_norm": 0.7347378730773926,
"learning_rate": 9.667902132486009e-05,
"loss": 1.2069,
"step": 41
},
{
"epoch": 0.01830264734720558,
"grad_norm": 0.8081456422805786,
"learning_rate": 9.635919272833938e-05,
"loss": 1.4003,
"step": 42
},
{
"epoch": 0.018738424664996187,
"grad_norm": 0.7185221314430237,
"learning_rate": 9.602524267262203e-05,
"loss": 1.2813,
"step": 43
},
{
"epoch": 0.019174201982786795,
"grad_norm": 0.7656445503234863,
"learning_rate": 9.567727288213005e-05,
"loss": 1.4089,
"step": 44
},
{
"epoch": 0.019609979300577406,
"grad_norm": 0.936586320400238,
"learning_rate": 9.53153893518325e-05,
"loss": 1.3603,
"step": 45
},
{
"epoch": 0.020045756618368014,
"grad_norm": 0.7969225645065308,
"learning_rate": 9.493970231495835e-05,
"loss": 1.3352,
"step": 46
},
{
"epoch": 0.020481533936158623,
"grad_norm": 0.8012515306472778,
"learning_rate": 9.45503262094184e-05,
"loss": 1.3508,
"step": 47
},
{
"epoch": 0.02091731125394923,
"grad_norm": 0.7480721473693848,
"learning_rate": 9.414737964294636e-05,
"loss": 1.3603,
"step": 48
},
{
"epoch": 0.021353088571739842,
"grad_norm": 0.814703643321991,
"learning_rate": 9.373098535696979e-05,
"loss": 1.3205,
"step": 49
},
{
"epoch": 0.02178886588953045,
"grad_norm": 0.9260087609291077,
"learning_rate": 9.330127018922194e-05,
"loss": 1.3108,
"step": 50
},
{
"epoch": 0.02178886588953045,
"eval_loss": 1.3878036737442017,
"eval_runtime": 317.8565,
"eval_samples_per_second": 12.16,
"eval_steps_per_second": 6.081,
"step": 50
},
{
"epoch": 0.02222464320732106,
"grad_norm": 0.7175142168998718,
"learning_rate": 9.285836503510562e-05,
"loss": 1.3437,
"step": 51
},
{
"epoch": 0.022660420525111667,
"grad_norm": 0.7583256363868713,
"learning_rate": 9.24024048078213e-05,
"loss": 1.3406,
"step": 52
},
{
"epoch": 0.023096197842902278,
"grad_norm": 0.677870512008667,
"learning_rate": 9.193352839727121e-05,
"loss": 1.467,
"step": 53
},
{
"epoch": 0.023531975160692886,
"grad_norm": 0.725477397441864,
"learning_rate": 9.145187862775209e-05,
"loss": 1.3124,
"step": 54
},
{
"epoch": 0.023967752478483494,
"grad_norm": 0.683293342590332,
"learning_rate": 9.09576022144496e-05,
"loss": 1.4094,
"step": 55
},
{
"epoch": 0.024403529796274102,
"grad_norm": 0.7447341084480286,
"learning_rate": 9.045084971874738e-05,
"loss": 1.3858,
"step": 56
},
{
"epoch": 0.024839307114064714,
"grad_norm": 0.759089469909668,
"learning_rate": 8.993177550236464e-05,
"loss": 1.3845,
"step": 57
},
{
"epoch": 0.025275084431855322,
"grad_norm": 0.6921642422676086,
"learning_rate": 8.940053768033609e-05,
"loss": 1.4491,
"step": 58
},
{
"epoch": 0.02571086174964593,
"grad_norm": 0.6369518637657166,
"learning_rate": 8.885729807284856e-05,
"loss": 1.3408,
"step": 59
},
{
"epoch": 0.02614663906743654,
"grad_norm": 0.7366051077842712,
"learning_rate": 8.83022221559489e-05,
"loss": 1.4087,
"step": 60
},
{
"epoch": 0.02658241638522715,
"grad_norm": 0.7187365293502808,
"learning_rate": 8.773547901113862e-05,
"loss": 1.3983,
"step": 61
},
{
"epoch": 0.027018193703017758,
"grad_norm": 0.7734277844429016,
"learning_rate": 8.715724127386972e-05,
"loss": 1.5799,
"step": 62
},
{
"epoch": 0.027453971020808366,
"grad_norm": 0.6761085391044617,
"learning_rate": 8.656768508095853e-05,
"loss": 1.3576,
"step": 63
},
{
"epoch": 0.027889748338598978,
"grad_norm": 0.783863365650177,
"learning_rate": 8.596699001693255e-05,
"loss": 1.4574,
"step": 64
},
{
"epoch": 0.028325525656389586,
"grad_norm": 0.7435303330421448,
"learning_rate": 8.535533905932738e-05,
"loss": 1.4734,
"step": 65
},
{
"epoch": 0.028761302974180194,
"grad_norm": 0.7461963891983032,
"learning_rate": 8.473291852294987e-05,
"loss": 1.4228,
"step": 66
},
{
"epoch": 0.029197080291970802,
"grad_norm": 0.7791002988815308,
"learning_rate": 8.409991800312493e-05,
"loss": 1.4499,
"step": 67
},
{
"epoch": 0.029632857609761414,
"grad_norm": 0.692180335521698,
"learning_rate": 8.345653031794292e-05,
"loss": 1.4522,
"step": 68
},
{
"epoch": 0.03006863492755202,
"grad_norm": 0.7467637658119202,
"learning_rate": 8.280295144952536e-05,
"loss": 1.3698,
"step": 69
},
{
"epoch": 0.03050441224534263,
"grad_norm": 0.7586157321929932,
"learning_rate": 8.213938048432697e-05,
"loss": 1.454,
"step": 70
},
{
"epoch": 0.030940189563133238,
"grad_norm": 0.6296893358230591,
"learning_rate": 8.146601955249188e-05,
"loss": 1.34,
"step": 71
},
{
"epoch": 0.031375966880923846,
"grad_norm": 0.8413500189781189,
"learning_rate": 8.07830737662829e-05,
"loss": 1.3662,
"step": 72
},
{
"epoch": 0.03181174419871446,
"grad_norm": 0.672438383102417,
"learning_rate": 8.009075115760243e-05,
"loss": 1.3177,
"step": 73
},
{
"epoch": 0.03224752151650507,
"grad_norm": 0.7362287044525146,
"learning_rate": 7.938926261462366e-05,
"loss": 1.3813,
"step": 74
},
{
"epoch": 0.032683298834295674,
"grad_norm": 0.7228344082832336,
"learning_rate": 7.86788218175523e-05,
"loss": 1.4777,
"step": 75
},
{
"epoch": 0.033119076152086285,
"grad_norm": 0.6640066504478455,
"learning_rate": 7.795964517353735e-05,
"loss": 1.3769,
"step": 76
},
{
"epoch": 0.03355485346987689,
"grad_norm": 0.6730275750160217,
"learning_rate": 7.723195175075136e-05,
"loss": 1.3875,
"step": 77
},
{
"epoch": 0.0339906307876675,
"grad_norm": 0.7028450965881348,
"learning_rate": 7.649596321166024e-05,
"loss": 1.4002,
"step": 78
},
{
"epoch": 0.03442640810545811,
"grad_norm": 0.6365458369255066,
"learning_rate": 7.575190374550272e-05,
"loss": 1.2605,
"step": 79
},
{
"epoch": 0.03486218542324872,
"grad_norm": 0.6803222894668579,
"learning_rate": 7.500000000000001e-05,
"loss": 1.38,
"step": 80
},
{
"epoch": 0.03529796274103933,
"grad_norm": 0.6870620250701904,
"learning_rate": 7.424048101231686e-05,
"loss": 1.3394,
"step": 81
},
{
"epoch": 0.03573374005882994,
"grad_norm": 0.7038113474845886,
"learning_rate": 7.347357813929454e-05,
"loss": 1.4702,
"step": 82
},
{
"epoch": 0.036169517376620546,
"grad_norm": 0.637474775314331,
"learning_rate": 7.269952498697734e-05,
"loss": 1.3277,
"step": 83
},
{
"epoch": 0.03660529469441116,
"grad_norm": 0.7014281153678894,
"learning_rate": 7.191855733945387e-05,
"loss": 1.405,
"step": 84
},
{
"epoch": 0.03704107201220176,
"grad_norm": 0.6626453399658203,
"learning_rate": 7.113091308703498e-05,
"loss": 1.4336,
"step": 85
},
{
"epoch": 0.03747684932999237,
"grad_norm": 0.6772466897964478,
"learning_rate": 7.033683215379002e-05,
"loss": 1.3221,
"step": 86
},
{
"epoch": 0.037912626647782985,
"grad_norm": 0.7135924100875854,
"learning_rate": 6.953655642446368e-05,
"loss": 1.3905,
"step": 87
},
{
"epoch": 0.03834840396557359,
"grad_norm": 0.7085152864456177,
"learning_rate": 6.873032967079561e-05,
"loss": 1.3089,
"step": 88
},
{
"epoch": 0.0387841812833642,
"grad_norm": 0.7906420826911926,
"learning_rate": 6.7918397477265e-05,
"loss": 1.3709,
"step": 89
},
{
"epoch": 0.03921995860115481,
"grad_norm": 0.6890827417373657,
"learning_rate": 6.710100716628344e-05,
"loss": 1.2915,
"step": 90
},
{
"epoch": 0.03965573591894542,
"grad_norm": 0.6224659085273743,
"learning_rate": 6.627840772285784e-05,
"loss": 1.2344,
"step": 91
},
{
"epoch": 0.04009151323673603,
"grad_norm": 0.6973520517349243,
"learning_rate": 6.545084971874738e-05,
"loss": 1.3544,
"step": 92
},
{
"epoch": 0.040527290554526633,
"grad_norm": 0.6966316103935242,
"learning_rate": 6.461858523613684e-05,
"loss": 1.2701,
"step": 93
},
{
"epoch": 0.040963067872317245,
"grad_norm": 0.7485948801040649,
"learning_rate": 6.378186779084995e-05,
"loss": 1.4688,
"step": 94
},
{
"epoch": 0.04139884519010786,
"grad_norm": 0.6849566698074341,
"learning_rate": 6.294095225512603e-05,
"loss": 1.2395,
"step": 95
},
{
"epoch": 0.04183462250789846,
"grad_norm": 0.7672956585884094,
"learning_rate": 6.209609477998338e-05,
"loss": 1.2718,
"step": 96
},
{
"epoch": 0.04227039982568907,
"grad_norm": 0.7076390385627747,
"learning_rate": 6.124755271719325e-05,
"loss": 1.3193,
"step": 97
},
{
"epoch": 0.042706177143479684,
"grad_norm": 0.7060564756393433,
"learning_rate": 6.0395584540887963e-05,
"loss": 1.2844,
"step": 98
},
{
"epoch": 0.04314195446127029,
"grad_norm": 0.7379676699638367,
"learning_rate": 5.9540449768827246e-05,
"loss": 1.2361,
"step": 99
},
{
"epoch": 0.0435777317790609,
"grad_norm": 0.851557731628418,
"learning_rate": 5.868240888334653e-05,
"loss": 1.3533,
"step": 100
},
{
"epoch": 0.0435777317790609,
"eval_loss": 1.3684649467468262,
"eval_runtime": 318.0205,
"eval_samples_per_second": 12.153,
"eval_steps_per_second": 6.078,
"step": 100
},
{
"epoch": 0.04401350909685151,
"grad_norm": 0.6644337177276611,
"learning_rate": 5.782172325201155e-05,
"loss": 1.43,
"step": 101
},
{
"epoch": 0.04444928641464212,
"grad_norm": 0.6406741142272949,
"learning_rate": 5.695865504800327e-05,
"loss": 1.4389,
"step": 102
},
{
"epoch": 0.04488506373243273,
"grad_norm": 0.6088762283325195,
"learning_rate": 5.6093467170257374e-05,
"loss": 1.3575,
"step": 103
},
{
"epoch": 0.04532084105022333,
"grad_norm": 0.5756306052207947,
"learning_rate": 5.522642316338268e-05,
"loss": 1.2714,
"step": 104
},
{
"epoch": 0.045756618368013945,
"grad_norm": 0.5706756711006165,
"learning_rate": 5.435778713738292e-05,
"loss": 1.3047,
"step": 105
},
{
"epoch": 0.046192395685804556,
"grad_norm": 0.6538943648338318,
"learning_rate": 5.348782368720626e-05,
"loss": 1.4369,
"step": 106
},
{
"epoch": 0.04662817300359516,
"grad_norm": 0.6861059665679932,
"learning_rate": 5.26167978121472e-05,
"loss": 1.386,
"step": 107
},
{
"epoch": 0.04706395032138577,
"grad_norm": 0.667604386806488,
"learning_rate": 5.174497483512506e-05,
"loss": 1.3972,
"step": 108
},
{
"epoch": 0.047499727639176384,
"grad_norm": 0.5741658210754395,
"learning_rate": 5.0872620321864185e-05,
"loss": 1.3382,
"step": 109
},
{
"epoch": 0.04793550495696699,
"grad_norm": 0.6127682328224182,
"learning_rate": 5e-05,
"loss": 1.3597,
"step": 110
},
{
"epoch": 0.0483712822747576,
"grad_norm": 0.6162969470024109,
"learning_rate": 4.912737967813583e-05,
"loss": 1.3884,
"step": 111
},
{
"epoch": 0.048807059592548205,
"grad_norm": 0.6853535771369934,
"learning_rate": 4.825502516487497e-05,
"loss": 1.5718,
"step": 112
},
{
"epoch": 0.049242836910338816,
"grad_norm": 0.6162100434303284,
"learning_rate": 4.738320218785281e-05,
"loss": 1.4271,
"step": 113
},
{
"epoch": 0.04967861422812943,
"grad_norm": 0.5969780087471008,
"learning_rate": 4.6512176312793736e-05,
"loss": 1.3138,
"step": 114
},
{
"epoch": 0.05011439154592003,
"grad_norm": 0.563022792339325,
"learning_rate": 4.564221286261709e-05,
"loss": 1.2623,
"step": 115
},
{
"epoch": 0.050550168863710644,
"grad_norm": 0.658589780330658,
"learning_rate": 4.477357683661734e-05,
"loss": 1.4113,
"step": 116
},
{
"epoch": 0.050985946181501256,
"grad_norm": 0.6488298773765564,
"learning_rate": 4.390653282974264e-05,
"loss": 1.4764,
"step": 117
},
{
"epoch": 0.05142172349929186,
"grad_norm": 0.6470029950141907,
"learning_rate": 4.3041344951996746e-05,
"loss": 1.3366,
"step": 118
},
{
"epoch": 0.05185750081708247,
"grad_norm": 0.6214532852172852,
"learning_rate": 4.2178276747988446e-05,
"loss": 1.3507,
"step": 119
},
{
"epoch": 0.05229327813487308,
"grad_norm": 0.6346096396446228,
"learning_rate": 4.131759111665349e-05,
"loss": 1.36,
"step": 120
},
{
"epoch": 0.05272905545266369,
"grad_norm": 0.6477368474006653,
"learning_rate": 4.045955023117276e-05,
"loss": 1.4248,
"step": 121
},
{
"epoch": 0.0531648327704543,
"grad_norm": 0.6995759606361389,
"learning_rate": 3.960441545911204e-05,
"loss": 1.2993,
"step": 122
},
{
"epoch": 0.053600610088244904,
"grad_norm": 0.6448193788528442,
"learning_rate": 3.875244728280676e-05,
"loss": 1.4006,
"step": 123
},
{
"epoch": 0.054036387406035516,
"grad_norm": 0.5889584422111511,
"learning_rate": 3.790390522001662e-05,
"loss": 1.3996,
"step": 124
},
{
"epoch": 0.05447216472382613,
"grad_norm": 0.6430240869522095,
"learning_rate": 3.705904774487396e-05,
"loss": 1.3608,
"step": 125
},
{
"epoch": 0.05490794204161673,
"grad_norm": 0.6376746296882629,
"learning_rate": 3.6218132209150045e-05,
"loss": 1.3421,
"step": 126
},
{
"epoch": 0.055343719359407344,
"grad_norm": 0.6999002695083618,
"learning_rate": 3.5381414763863166e-05,
"loss": 1.4008,
"step": 127
},
{
"epoch": 0.055779496677197955,
"grad_norm": 0.622456431388855,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.3804,
"step": 128
},
{
"epoch": 0.05621527399498856,
"grad_norm": 0.6279011368751526,
"learning_rate": 3.372159227714218e-05,
"loss": 1.3072,
"step": 129
},
{
"epoch": 0.05665105131277917,
"grad_norm": 0.612434446811676,
"learning_rate": 3.289899283371657e-05,
"loss": 1.2956,
"step": 130
},
{
"epoch": 0.057086828630569776,
"grad_norm": 0.6098705530166626,
"learning_rate": 3.2081602522734986e-05,
"loss": 1.3117,
"step": 131
},
{
"epoch": 0.05752260594836039,
"grad_norm": 0.6360723376274109,
"learning_rate": 3.12696703292044e-05,
"loss": 1.279,
"step": 132
},
{
"epoch": 0.057958383266151,
"grad_norm": 0.6856507062911987,
"learning_rate": 3.046344357553632e-05,
"loss": 1.3226,
"step": 133
},
{
"epoch": 0.058394160583941604,
"grad_norm": 0.6899363994598389,
"learning_rate": 2.9663167846209998e-05,
"loss": 1.3294,
"step": 134
},
{
"epoch": 0.058829937901732215,
"grad_norm": 0.6617586016654968,
"learning_rate": 2.886908691296504e-05,
"loss": 1.4432,
"step": 135
},
{
"epoch": 0.05926571521952283,
"grad_norm": 0.712164580821991,
"learning_rate": 2.8081442660546125e-05,
"loss": 1.4219,
"step": 136
},
{
"epoch": 0.05970149253731343,
"grad_norm": 0.6878612637519836,
"learning_rate": 2.7300475013022663e-05,
"loss": 1.3542,
"step": 137
},
{
"epoch": 0.06013726985510404,
"grad_norm": 0.690792977809906,
"learning_rate": 2.6526421860705473e-05,
"loss": 1.319,
"step": 138
},
{
"epoch": 0.06057304717289465,
"grad_norm": 0.7101471424102783,
"learning_rate": 2.575951898768315e-05,
"loss": 1.3666,
"step": 139
},
{
"epoch": 0.06100882449068526,
"grad_norm": 0.7041705250740051,
"learning_rate": 2.500000000000001e-05,
"loss": 1.3118,
"step": 140
},
{
"epoch": 0.06144460180847587,
"grad_norm": 0.6758811473846436,
"learning_rate": 2.4248096254497288e-05,
"loss": 1.2953,
"step": 141
},
{
"epoch": 0.061880379126266476,
"grad_norm": 0.7130976319313049,
"learning_rate": 2.350403678833976e-05,
"loss": 1.3082,
"step": 142
},
{
"epoch": 0.06231615644405709,
"grad_norm": 0.6844936013221741,
"learning_rate": 2.2768048249248648e-05,
"loss": 1.2318,
"step": 143
},
{
"epoch": 0.06275193376184769,
"grad_norm": 0.7062429785728455,
"learning_rate": 2.2040354826462668e-05,
"loss": 1.2312,
"step": 144
},
{
"epoch": 0.0631877110796383,
"grad_norm": 0.6911125779151917,
"learning_rate": 2.132117818244771e-05,
"loss": 1.288,
"step": 145
},
{
"epoch": 0.06362348839742892,
"grad_norm": 0.6440110802650452,
"learning_rate": 2.061073738537635e-05,
"loss": 1.2698,
"step": 146
},
{
"epoch": 0.06405926571521953,
"grad_norm": 0.6771082878112793,
"learning_rate": 1.9909248842397584e-05,
"loss": 1.2934,
"step": 147
},
{
"epoch": 0.06449504303301014,
"grad_norm": 0.6761582493782043,
"learning_rate": 1.9216926233717085e-05,
"loss": 1.189,
"step": 148
},
{
"epoch": 0.06493082035080074,
"grad_norm": 0.722388505935669,
"learning_rate": 1.8533980447508137e-05,
"loss": 1.3512,
"step": 149
},
{
"epoch": 0.06536659766859135,
"grad_norm": 0.7161824107170105,
"learning_rate": 1.7860619515673033e-05,
"loss": 1.3205,
"step": 150
},
{
"epoch": 0.06536659766859135,
"eval_loss": 1.3558998107910156,
"eval_runtime": 318.2564,
"eval_samples_per_second": 12.144,
"eval_steps_per_second": 6.074,
"step": 150
},
{
"epoch": 0.06580237498638196,
"grad_norm": 0.5807382464408875,
"learning_rate": 1.7197048550474643e-05,
"loss": 1.2307,
"step": 151
},
{
"epoch": 0.06623815230417257,
"grad_norm": 0.566876232624054,
"learning_rate": 1.6543469682057106e-05,
"loss": 1.3157,
"step": 152
},
{
"epoch": 0.06667392962196318,
"grad_norm": 0.6490059494972229,
"learning_rate": 1.5900081996875083e-05,
"loss": 1.4128,
"step": 153
},
{
"epoch": 0.06710970693975378,
"grad_norm": 0.6223024129867554,
"learning_rate": 1.526708147705013e-05,
"loss": 1.38,
"step": 154
},
{
"epoch": 0.06754548425754439,
"grad_norm": 0.6144639849662781,
"learning_rate": 1.4644660940672627e-05,
"loss": 1.3944,
"step": 155
},
{
"epoch": 0.067981261575335,
"grad_norm": 0.595415472984314,
"learning_rate": 1.4033009983067452e-05,
"loss": 1.328,
"step": 156
},
{
"epoch": 0.06841703889312561,
"grad_norm": 0.5314094424247742,
"learning_rate": 1.3432314919041478e-05,
"loss": 1.2152,
"step": 157
},
{
"epoch": 0.06885281621091623,
"grad_norm": 0.6001833081245422,
"learning_rate": 1.2842758726130283e-05,
"loss": 1.4542,
"step": 158
},
{
"epoch": 0.06928859352870684,
"grad_norm": 0.6430898308753967,
"learning_rate": 1.22645209888614e-05,
"loss": 1.3154,
"step": 159
},
{
"epoch": 0.06972437084649744,
"grad_norm": 0.6337030529975891,
"learning_rate": 1.1697777844051105e-05,
"loss": 1.4062,
"step": 160
},
{
"epoch": 0.07016014816428805,
"grad_norm": 0.6061561703681946,
"learning_rate": 1.1142701927151456e-05,
"loss": 1.3211,
"step": 161
},
{
"epoch": 0.07059592548207866,
"grad_norm": 0.602303147315979,
"learning_rate": 1.0599462319663905e-05,
"loss": 1.2714,
"step": 162
},
{
"epoch": 0.07103170279986927,
"grad_norm": 0.6715372800827026,
"learning_rate": 1.006822449763537e-05,
"loss": 1.466,
"step": 163
},
{
"epoch": 0.07146748011765988,
"grad_norm": 0.6462534070014954,
"learning_rate": 9.549150281252633e-06,
"loss": 1.3905,
"step": 164
},
{
"epoch": 0.07190325743545048,
"grad_norm": 0.6473283171653748,
"learning_rate": 9.042397785550405e-06,
"loss": 1.4684,
"step": 165
},
{
"epoch": 0.07233903475324109,
"grad_norm": 0.6403040289878845,
"learning_rate": 8.548121372247918e-06,
"loss": 1.4428,
"step": 166
},
{
"epoch": 0.0727748120710317,
"grad_norm": 0.6310374140739441,
"learning_rate": 8.066471602728803e-06,
"loss": 1.4184,
"step": 167
},
{
"epoch": 0.07321058938882231,
"grad_norm": 0.6313512325286865,
"learning_rate": 7.597595192178702e-06,
"loss": 1.3182,
"step": 168
},
{
"epoch": 0.07364636670661293,
"grad_norm": 0.6269996762275696,
"learning_rate": 7.1416349648943894e-06,
"loss": 1.4251,
"step": 169
},
{
"epoch": 0.07408214402440352,
"grad_norm": 0.7114905714988708,
"learning_rate": 6.698729810778065e-06,
"loss": 1.4552,
"step": 170
},
{
"epoch": 0.07451792134219413,
"grad_norm": 0.6751496195793152,
"learning_rate": 6.269014643030213e-06,
"loss": 1.4515,
"step": 171
},
{
"epoch": 0.07495369865998475,
"grad_norm": 0.6360151767730713,
"learning_rate": 5.852620357053651e-06,
"loss": 1.4074,
"step": 172
},
{
"epoch": 0.07538947597777536,
"grad_norm": 0.6181896328926086,
"learning_rate": 5.449673790581611e-06,
"loss": 1.3576,
"step": 173
},
{
"epoch": 0.07582525329556597,
"grad_norm": 0.6952101588249207,
"learning_rate": 5.060297685041659e-06,
"loss": 1.2972,
"step": 174
},
{
"epoch": 0.07626103061335658,
"grad_norm": 0.6665775775909424,
"learning_rate": 4.684610648167503e-06,
"loss": 1.3729,
"step": 175
},
{
"epoch": 0.07669680793114718,
"grad_norm": 0.6412355303764343,
"learning_rate": 4.322727117869951e-06,
"loss": 1.3881,
"step": 176
},
{
"epoch": 0.07713258524893779,
"grad_norm": 0.7119609713554382,
"learning_rate": 3.974757327377981e-06,
"loss": 1.3989,
"step": 177
},
{
"epoch": 0.0775683625667284,
"grad_norm": 0.6917702555656433,
"learning_rate": 3.6408072716606346e-06,
"loss": 1.5004,
"step": 178
},
{
"epoch": 0.07800413988451901,
"grad_norm": 0.6711847186088562,
"learning_rate": 3.3209786751399187e-06,
"loss": 1.3185,
"step": 179
},
{
"epoch": 0.07843991720230963,
"grad_norm": 0.6017194390296936,
"learning_rate": 3.0153689607045845e-06,
"loss": 1.3098,
"step": 180
},
{
"epoch": 0.07887569452010022,
"grad_norm": 0.651289165019989,
"learning_rate": 2.724071220034158e-06,
"loss": 1.2399,
"step": 181
},
{
"epoch": 0.07931147183789083,
"grad_norm": 0.6338282823562622,
"learning_rate": 2.4471741852423237e-06,
"loss": 1.4195,
"step": 182
},
{
"epoch": 0.07974724915568145,
"grad_norm": 0.6776835918426514,
"learning_rate": 2.1847622018482283e-06,
"loss": 1.3384,
"step": 183
},
{
"epoch": 0.08018302647347206,
"grad_norm": 0.6653581261634827,
"learning_rate": 1.9369152030840556e-06,
"loss": 1.4017,
"step": 184
},
{
"epoch": 0.08061880379126267,
"grad_norm": 0.6599856019020081,
"learning_rate": 1.70370868554659e-06,
"loss": 1.387,
"step": 185
},
{
"epoch": 0.08105458110905327,
"grad_norm": 0.5980033874511719,
"learning_rate": 1.4852136862001764e-06,
"loss": 1.298,
"step": 186
},
{
"epoch": 0.08149035842684388,
"grad_norm": 0.6334329843521118,
"learning_rate": 1.2814967607382432e-06,
"loss": 1.4484,
"step": 187
},
{
"epoch": 0.08192613574463449,
"grad_norm": 0.6860253810882568,
"learning_rate": 1.0926199633097157e-06,
"loss": 1.3165,
"step": 188
},
{
"epoch": 0.0823619130624251,
"grad_norm": 0.6104192733764648,
"learning_rate": 9.186408276168013e-07,
"loss": 1.2627,
"step": 189
},
{
"epoch": 0.08279769038021571,
"grad_norm": 0.655128002166748,
"learning_rate": 7.596123493895991e-07,
"loss": 1.3538,
"step": 190
},
{
"epoch": 0.08323346769800632,
"grad_norm": 0.6715838313102722,
"learning_rate": 6.15582970243117e-07,
"loss": 1.3321,
"step": 191
},
{
"epoch": 0.08366924501579692,
"grad_norm": 0.6423591375350952,
"learning_rate": 4.865965629214819e-07,
"loss": 1.2826,
"step": 192
},
{
"epoch": 0.08410502233358753,
"grad_norm": 0.6962019205093384,
"learning_rate": 3.7269241793390085e-07,
"loss": 1.3094,
"step": 193
},
{
"epoch": 0.08454079965137815,
"grad_norm": 0.6699984669685364,
"learning_rate": 2.7390523158633554e-07,
"loss": 1.2272,
"step": 194
},
{
"epoch": 0.08497657696916876,
"grad_norm": 0.6386066675186157,
"learning_rate": 1.9026509541272275e-07,
"loss": 1.313,
"step": 195
},
{
"epoch": 0.08541235428695937,
"grad_norm": 0.6663680076599121,
"learning_rate": 1.2179748700879012e-07,
"loss": 1.3142,
"step": 196
},
{
"epoch": 0.08584813160474997,
"grad_norm": 0.6899527907371521,
"learning_rate": 6.852326227130834e-08,
"loss": 1.2647,
"step": 197
},
{
"epoch": 0.08628390892254058,
"grad_norm": 0.7270941734313965,
"learning_rate": 3.04586490452119e-08,
"loss": 1.3399,
"step": 198
},
{
"epoch": 0.08671968624033119,
"grad_norm": 0.6916342377662659,
"learning_rate": 7.615242180436522e-09,
"loss": 1.2973,
"step": 199
},
{
"epoch": 0.0871554635581218,
"grad_norm": 0.8266770839691162,
"learning_rate": 0.0,
"loss": 1.3851,
"step": 200
},
{
"epoch": 0.0871554635581218,
"eval_loss": 1.3537832498550415,
"eval_runtime": 318.062,
"eval_samples_per_second": 12.152,
"eval_steps_per_second": 6.077,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.8578845122206106e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}