cimol's picture
Training in progress, step 200, checkpoint
b81e8b9 verified
{
"best_metric": 0.8045907020568848,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 1.6563146997929605,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008281573498964804,
"grad_norm": 0.8388795256614685,
"learning_rate": 7e-06,
"loss": 0.804,
"step": 1
},
{
"epoch": 0.008281573498964804,
"eval_loss": 1.1692047119140625,
"eval_runtime": 32.2894,
"eval_samples_per_second": 6.318,
"eval_steps_per_second": 1.579,
"step": 1
},
{
"epoch": 0.016563146997929608,
"grad_norm": 1.023823618888855,
"learning_rate": 1.4e-05,
"loss": 0.8544,
"step": 2
},
{
"epoch": 0.024844720496894408,
"grad_norm": 1.0270742177963257,
"learning_rate": 2.1e-05,
"loss": 0.8755,
"step": 3
},
{
"epoch": 0.033126293995859216,
"grad_norm": 0.9506105780601501,
"learning_rate": 2.8e-05,
"loss": 0.8441,
"step": 4
},
{
"epoch": 0.041407867494824016,
"grad_norm": 0.7932412028312683,
"learning_rate": 3.5e-05,
"loss": 0.7846,
"step": 5
},
{
"epoch": 0.049689440993788817,
"grad_norm": 0.7128869295120239,
"learning_rate": 4.2e-05,
"loss": 0.9147,
"step": 6
},
{
"epoch": 0.057971014492753624,
"grad_norm": 0.4176234304904938,
"learning_rate": 4.899999999999999e-05,
"loss": 0.7784,
"step": 7
},
{
"epoch": 0.06625258799171843,
"grad_norm": 0.6762263178825378,
"learning_rate": 5.6e-05,
"loss": 0.8248,
"step": 8
},
{
"epoch": 0.07453416149068323,
"grad_norm": 0.8291305899620056,
"learning_rate": 6.3e-05,
"loss": 0.8014,
"step": 9
},
{
"epoch": 0.08281573498964803,
"grad_norm": 0.8136356472969055,
"learning_rate": 7e-05,
"loss": 0.9253,
"step": 10
},
{
"epoch": 0.09109730848861283,
"grad_norm": 0.4319281578063965,
"learning_rate": 6.999521567473641e-05,
"loss": 0.8555,
"step": 11
},
{
"epoch": 0.09937888198757763,
"grad_norm": 0.36292925477027893,
"learning_rate": 6.998086400693241e-05,
"loss": 0.7425,
"step": 12
},
{
"epoch": 0.10766045548654245,
"grad_norm": 0.3616969585418701,
"learning_rate": 6.995694892019065e-05,
"loss": 0.9021,
"step": 13
},
{
"epoch": 0.11594202898550725,
"grad_norm": 0.3888731002807617,
"learning_rate": 6.99234769526571e-05,
"loss": 0.7912,
"step": 14
},
{
"epoch": 0.12422360248447205,
"grad_norm": 0.3677065968513489,
"learning_rate": 6.988045725523343e-05,
"loss": 0.6922,
"step": 15
},
{
"epoch": 0.13250517598343686,
"grad_norm": 0.38920730352401733,
"learning_rate": 6.982790158907539e-05,
"loss": 0.8843,
"step": 16
},
{
"epoch": 0.14078674948240166,
"grad_norm": 0.4462592601776123,
"learning_rate": 6.976582432237733e-05,
"loss": 0.9304,
"step": 17
},
{
"epoch": 0.14906832298136646,
"grad_norm": 0.40514039993286133,
"learning_rate": 6.969424242644413e-05,
"loss": 0.8461,
"step": 18
},
{
"epoch": 0.15734989648033126,
"grad_norm": 0.44129592180252075,
"learning_rate": 6.961317547105138e-05,
"loss": 0.8518,
"step": 19
},
{
"epoch": 0.16563146997929606,
"grad_norm": 0.4335060715675354,
"learning_rate": 6.952264561909527e-05,
"loss": 0.8793,
"step": 20
},
{
"epoch": 0.17391304347826086,
"grad_norm": 0.543445885181427,
"learning_rate": 6.942267762053337e-05,
"loss": 0.9113,
"step": 21
},
{
"epoch": 0.18219461697722567,
"grad_norm": 0.5542380809783936,
"learning_rate": 6.931329880561832e-05,
"loss": 0.9433,
"step": 22
},
{
"epoch": 0.19047619047619047,
"grad_norm": 0.516521692276001,
"learning_rate": 6.919453907742597e-05,
"loss": 0.9016,
"step": 23
},
{
"epoch": 0.19875776397515527,
"grad_norm": 0.5378891825675964,
"learning_rate": 6.90664309036802e-05,
"loss": 0.7877,
"step": 24
},
{
"epoch": 0.2070393374741201,
"grad_norm": 0.577548086643219,
"learning_rate": 6.892900930787656e-05,
"loss": 0.8454,
"step": 25
},
{
"epoch": 0.2153209109730849,
"grad_norm": 0.5783238410949707,
"learning_rate": 6.87823118597072e-05,
"loss": 0.8776,
"step": 26
},
{
"epoch": 0.2236024844720497,
"grad_norm": 0.5544853210449219,
"learning_rate": 6.862637866478969e-05,
"loss": 0.8123,
"step": 27
},
{
"epoch": 0.2318840579710145,
"grad_norm": 0.7183583974838257,
"learning_rate": 6.846125235370252e-05,
"loss": 0.941,
"step": 28
},
{
"epoch": 0.2401656314699793,
"grad_norm": 0.7497084140777588,
"learning_rate": 6.828697807033038e-05,
"loss": 0.9533,
"step": 29
},
{
"epoch": 0.2484472049689441,
"grad_norm": 1.0239611864089966,
"learning_rate": 6.81036034595222e-05,
"loss": 1.0226,
"step": 30
},
{
"epoch": 0.2567287784679089,
"grad_norm": 0.215080127120018,
"learning_rate": 6.791117865406564e-05,
"loss": 0.5555,
"step": 31
},
{
"epoch": 0.2650103519668737,
"grad_norm": 0.32441794872283936,
"learning_rate": 6.770975626098112e-05,
"loss": 0.7501,
"step": 32
},
{
"epoch": 0.2732919254658385,
"grad_norm": 0.309184730052948,
"learning_rate": 6.749939134713974e-05,
"loss": 0.7853,
"step": 33
},
{
"epoch": 0.2815734989648033,
"grad_norm": 0.3206530511379242,
"learning_rate": 6.728014142420846e-05,
"loss": 0.659,
"step": 34
},
{
"epoch": 0.2898550724637681,
"grad_norm": 0.2530266046524048,
"learning_rate": 6.7052066432927e-05,
"loss": 0.651,
"step": 35
},
{
"epoch": 0.2981366459627329,
"grad_norm": 0.27744585275650024,
"learning_rate": 6.681522872672069e-05,
"loss": 0.6502,
"step": 36
},
{
"epoch": 0.3064182194616977,
"grad_norm": 0.2372923493385315,
"learning_rate": 6.656969305465356e-05,
"loss": 0.7619,
"step": 37
},
{
"epoch": 0.3146997929606625,
"grad_norm": 0.2609351575374603,
"learning_rate": 6.631552654372672e-05,
"loss": 0.6668,
"step": 38
},
{
"epoch": 0.32298136645962733,
"grad_norm": 0.2953057885169983,
"learning_rate": 6.60527986805264e-05,
"loss": 0.7653,
"step": 39
},
{
"epoch": 0.33126293995859213,
"grad_norm": 0.32191261649131775,
"learning_rate": 6.578158129222711e-05,
"loss": 0.8575,
"step": 40
},
{
"epoch": 0.33954451345755693,
"grad_norm": 0.2882176339626312,
"learning_rate": 6.550194852695469e-05,
"loss": 0.7252,
"step": 41
},
{
"epoch": 0.34782608695652173,
"grad_norm": 0.27066636085510254,
"learning_rate": 6.521397683351509e-05,
"loss": 0.7575,
"step": 42
},
{
"epoch": 0.35610766045548653,
"grad_norm": 0.3208519518375397,
"learning_rate": 6.491774494049386e-05,
"loss": 0.8635,
"step": 43
},
{
"epoch": 0.36438923395445133,
"grad_norm": 0.35946550965309143,
"learning_rate": 6.461333383473272e-05,
"loss": 0.8081,
"step": 44
},
{
"epoch": 0.37267080745341613,
"grad_norm": 0.3770899176597595,
"learning_rate": 6.430082673918849e-05,
"loss": 0.8199,
"step": 45
},
{
"epoch": 0.38095238095238093,
"grad_norm": 0.36672505736351013,
"learning_rate": 6.398030909018069e-05,
"loss": 0.8569,
"step": 46
},
{
"epoch": 0.38923395445134573,
"grad_norm": 0.3554442226886749,
"learning_rate": 6.365186851403423e-05,
"loss": 0.8098,
"step": 47
},
{
"epoch": 0.39751552795031053,
"grad_norm": 0.3235284388065338,
"learning_rate": 6.331559480312315e-05,
"loss": 0.791,
"step": 48
},
{
"epoch": 0.4057971014492754,
"grad_norm": 0.3624836206436157,
"learning_rate": 6.297157989132236e-05,
"loss": 0.7369,
"step": 49
},
{
"epoch": 0.4140786749482402,
"grad_norm": 0.3535378873348236,
"learning_rate": 6.261991782887377e-05,
"loss": 0.6616,
"step": 50
},
{
"epoch": 0.4140786749482402,
"eval_loss": 0.8644523024559021,
"eval_runtime": 32.248,
"eval_samples_per_second": 6.326,
"eval_steps_per_second": 1.581,
"step": 50
},
{
"epoch": 0.422360248447205,
"grad_norm": 0.3799665868282318,
"learning_rate": 6.226070475667393e-05,
"loss": 0.7939,
"step": 51
},
{
"epoch": 0.4306418219461698,
"grad_norm": 0.4117141664028168,
"learning_rate": 6.189403887999006e-05,
"loss": 0.7855,
"step": 52
},
{
"epoch": 0.4389233954451346,
"grad_norm": 0.4020320177078247,
"learning_rate": 6.152002044161171e-05,
"loss": 0.8022,
"step": 53
},
{
"epoch": 0.4472049689440994,
"grad_norm": 0.46013712882995605,
"learning_rate": 6.113875169444539e-05,
"loss": 0.8572,
"step": 54
},
{
"epoch": 0.4554865424430642,
"grad_norm": 0.45274391770362854,
"learning_rate": 6.0750336873559605e-05,
"loss": 0.7123,
"step": 55
},
{
"epoch": 0.463768115942029,
"grad_norm": 0.5365428328514099,
"learning_rate": 6.035488216768811e-05,
"loss": 0.8758,
"step": 56
},
{
"epoch": 0.4720496894409938,
"grad_norm": 0.641646146774292,
"learning_rate": 5.9952495690198894e-05,
"loss": 0.9564,
"step": 57
},
{
"epoch": 0.4803312629399586,
"grad_norm": 0.508011519908905,
"learning_rate": 5.954328744953709e-05,
"loss": 0.8731,
"step": 58
},
{
"epoch": 0.4886128364389234,
"grad_norm": 0.8867300152778625,
"learning_rate": 5.91273693191498e-05,
"loss": 0.9009,
"step": 59
},
{
"epoch": 0.4968944099378882,
"grad_norm": 0.9791533946990967,
"learning_rate": 5.870485500690094e-05,
"loss": 1.1371,
"step": 60
},
{
"epoch": 0.505175983436853,
"grad_norm": 0.24218077957630157,
"learning_rate": 5.827586002398468e-05,
"loss": 0.6875,
"step": 61
},
{
"epoch": 0.5134575569358178,
"grad_norm": 0.22737136483192444,
"learning_rate": 5.784050165334589e-05,
"loss": 0.7116,
"step": 62
},
{
"epoch": 0.5217391304347826,
"grad_norm": 0.2559671103954315,
"learning_rate": 5.739889891761608e-05,
"loss": 0.7719,
"step": 63
},
{
"epoch": 0.5300207039337475,
"grad_norm": 0.24487318098545074,
"learning_rate": 5.6951172546573794e-05,
"loss": 0.7212,
"step": 64
},
{
"epoch": 0.5383022774327122,
"grad_norm": 0.23421718180179596,
"learning_rate": 5.6497444944138376e-05,
"loss": 0.7471,
"step": 65
},
{
"epoch": 0.546583850931677,
"grad_norm": 0.21821844577789307,
"learning_rate": 5.603784015490587e-05,
"loss": 0.6552,
"step": 66
},
{
"epoch": 0.5548654244306418,
"grad_norm": 0.26210862398147583,
"learning_rate": 5.557248383023655e-05,
"loss": 0.774,
"step": 67
},
{
"epoch": 0.5631469979296067,
"grad_norm": 0.2591906785964966,
"learning_rate": 5.510150319390302e-05,
"loss": 0.687,
"step": 68
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.26978063583374023,
"learning_rate": 5.4625027007308546e-05,
"loss": 0.7278,
"step": 69
},
{
"epoch": 0.5797101449275363,
"grad_norm": 0.24709314107894897,
"learning_rate": 5.414318553428494e-05,
"loss": 0.5976,
"step": 70
},
{
"epoch": 0.587991718426501,
"grad_norm": 0.30029296875,
"learning_rate": 5.3656110505479776e-05,
"loss": 0.7129,
"step": 71
},
{
"epoch": 0.5962732919254659,
"grad_norm": 0.32972994446754456,
"learning_rate": 5.316393508234253e-05,
"loss": 0.8332,
"step": 72
},
{
"epoch": 0.6045548654244306,
"grad_norm": 0.3365096151828766,
"learning_rate": 5.266679382071953e-05,
"loss": 0.8121,
"step": 73
},
{
"epoch": 0.6128364389233955,
"grad_norm": 0.31908273696899414,
"learning_rate": 5.216482263406778e-05,
"loss": 0.8543,
"step": 74
},
{
"epoch": 0.6211180124223602,
"grad_norm": 0.3485449552536011,
"learning_rate": 5.1658158756297576e-05,
"loss": 0.8116,
"step": 75
},
{
"epoch": 0.629399585921325,
"grad_norm": 0.33620256185531616,
"learning_rate": 5.114694070425407e-05,
"loss": 0.7493,
"step": 76
},
{
"epoch": 0.6376811594202898,
"grad_norm": 0.35500848293304443,
"learning_rate": 5.063130823984823e-05,
"loss": 0.7026,
"step": 77
},
{
"epoch": 0.6459627329192547,
"grad_norm": 0.4022809565067291,
"learning_rate": 5.011140233184724e-05,
"loss": 0.7928,
"step": 78
},
{
"epoch": 0.6542443064182195,
"grad_norm": 0.41914957761764526,
"learning_rate": 4.958736511733516e-05,
"loss": 0.8219,
"step": 79
},
{
"epoch": 0.6625258799171843,
"grad_norm": 0.4002333879470825,
"learning_rate": 4.905933986285393e-05,
"loss": 0.8019,
"step": 80
},
{
"epoch": 0.6708074534161491,
"grad_norm": 0.46458199620246887,
"learning_rate": 4.8527470925235824e-05,
"loss": 0.7353,
"step": 81
},
{
"epoch": 0.6790890269151139,
"grad_norm": 0.5049306154251099,
"learning_rate": 4.799190371213772e-05,
"loss": 0.935,
"step": 82
},
{
"epoch": 0.6873706004140787,
"grad_norm": 0.48192158341407776,
"learning_rate": 4.745278464228808e-05,
"loss": 0.8568,
"step": 83
},
{
"epoch": 0.6956521739130435,
"grad_norm": 0.5385396480560303,
"learning_rate": 4.69102611054575e-05,
"loss": 0.8613,
"step": 84
},
{
"epoch": 0.7039337474120083,
"grad_norm": 0.4860864579677582,
"learning_rate": 4.6364481422163926e-05,
"loss": 0.8288,
"step": 85
},
{
"epoch": 0.7122153209109731,
"grad_norm": 0.4691753387451172,
"learning_rate": 4.581559480312316e-05,
"loss": 0.7301,
"step": 86
},
{
"epoch": 0.7204968944099379,
"grad_norm": 0.6713128685951233,
"learning_rate": 4.526375130845627e-05,
"loss": 1.0118,
"step": 87
},
{
"epoch": 0.7287784679089027,
"grad_norm": 0.8337951302528381,
"learning_rate": 4.4709101806664554e-05,
"loss": 0.8735,
"step": 88
},
{
"epoch": 0.7370600414078675,
"grad_norm": 0.7612811326980591,
"learning_rate": 4.4151797933383685e-05,
"loss": 0.9304,
"step": 89
},
{
"epoch": 0.7453416149068323,
"grad_norm": 0.8643386960029602,
"learning_rate": 4.359199204992797e-05,
"loss": 1.0096,
"step": 90
},
{
"epoch": 0.7536231884057971,
"grad_norm": 0.20685485005378723,
"learning_rate": 4.30298372016363e-05,
"loss": 0.6227,
"step": 91
},
{
"epoch": 0.7619047619047619,
"grad_norm": 0.25332385301589966,
"learning_rate": 4.246548707603114e-05,
"loss": 0.7315,
"step": 92
},
{
"epoch": 0.7701863354037267,
"grad_norm": 0.24437353014945984,
"learning_rate": 4.1899095960801805e-05,
"loss": 0.6921,
"step": 93
},
{
"epoch": 0.7784679089026915,
"grad_norm": 0.2593900263309479,
"learning_rate": 4.133081870162385e-05,
"loss": 0.7514,
"step": 94
},
{
"epoch": 0.7867494824016563,
"grad_norm": 0.2574782371520996,
"learning_rate": 4.076081065982569e-05,
"loss": 0.6447,
"step": 95
},
{
"epoch": 0.7950310559006211,
"grad_norm": 0.3053584396839142,
"learning_rate": 4.018922766991447e-05,
"loss": 0.6437,
"step": 96
},
{
"epoch": 0.8033126293995859,
"grad_norm": 0.2642808258533478,
"learning_rate": 3.961622599697241e-05,
"loss": 0.7539,
"step": 97
},
{
"epoch": 0.8115942028985508,
"grad_norm": 0.2618858814239502,
"learning_rate": 3.9041962293935516e-05,
"loss": 0.6641,
"step": 98
},
{
"epoch": 0.8198757763975155,
"grad_norm": 0.2602124512195587,
"learning_rate": 3.84665935587662e-05,
"loss": 0.6166,
"step": 99
},
{
"epoch": 0.8281573498964804,
"grad_norm": 0.2887020707130432,
"learning_rate": 3.7890277091531636e-05,
"loss": 0.6502,
"step": 100
},
{
"epoch": 0.8281573498964804,
"eval_loss": 0.8196816444396973,
"eval_runtime": 32.2536,
"eval_samples_per_second": 6.325,
"eval_steps_per_second": 1.581,
"step": 100
},
{
"epoch": 0.8364389233954451,
"grad_norm": 0.3054017126560211,
"learning_rate": 3.7313170451399475e-05,
"loss": 0.7171,
"step": 101
},
{
"epoch": 0.84472049689441,
"grad_norm": 0.2971940040588379,
"learning_rate": 3.673543141356278e-05,
"loss": 0.7747,
"step": 102
},
{
"epoch": 0.8530020703933747,
"grad_norm": 0.28216373920440674,
"learning_rate": 3.6157217926105783e-05,
"loss": 0.7735,
"step": 103
},
{
"epoch": 0.8612836438923396,
"grad_norm": 0.3302093744277954,
"learning_rate": 3.557868806682255e-05,
"loss": 0.7433,
"step": 104
},
{
"epoch": 0.8695652173913043,
"grad_norm": 0.39043137431144714,
"learning_rate": 3.5e-05,
"loss": 0.8474,
"step": 105
},
{
"epoch": 0.8778467908902692,
"grad_norm": 0.3387686312198639,
"learning_rate": 3.442131193317745e-05,
"loss": 0.7744,
"step": 106
},
{
"epoch": 0.8861283643892339,
"grad_norm": 0.3744807243347168,
"learning_rate": 3.384278207389421e-05,
"loss": 0.844,
"step": 107
},
{
"epoch": 0.8944099378881988,
"grad_norm": 0.3628387749195099,
"learning_rate": 3.3264568586437216e-05,
"loss": 0.7452,
"step": 108
},
{
"epoch": 0.9026915113871635,
"grad_norm": 0.34833672642707825,
"learning_rate": 3.268682954860052e-05,
"loss": 0.727,
"step": 109
},
{
"epoch": 0.9109730848861284,
"grad_norm": 0.38752731680870056,
"learning_rate": 3.210972290846837e-05,
"loss": 0.7226,
"step": 110
},
{
"epoch": 0.9192546583850931,
"grad_norm": 0.4460507035255432,
"learning_rate": 3.15334064412338e-05,
"loss": 0.783,
"step": 111
},
{
"epoch": 0.927536231884058,
"grad_norm": 0.4155882000923157,
"learning_rate": 3.0958037706064485e-05,
"loss": 0.7733,
"step": 112
},
{
"epoch": 0.9358178053830227,
"grad_norm": 0.42916351556777954,
"learning_rate": 3.038377400302758e-05,
"loss": 0.8132,
"step": 113
},
{
"epoch": 0.9440993788819876,
"grad_norm": 0.40436169505119324,
"learning_rate": 2.9810772330085524e-05,
"loss": 0.7043,
"step": 114
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.5273613333702087,
"learning_rate": 2.9239189340174306e-05,
"loss": 0.8491,
"step": 115
},
{
"epoch": 0.9606625258799172,
"grad_norm": 0.5109385848045349,
"learning_rate": 2.8669181298376163e-05,
"loss": 0.7627,
"step": 116
},
{
"epoch": 0.968944099378882,
"grad_norm": 0.6382851600646973,
"learning_rate": 2.8100904039198193e-05,
"loss": 0.7009,
"step": 117
},
{
"epoch": 0.9772256728778468,
"grad_norm": 0.6231806874275208,
"learning_rate": 2.7534512923968863e-05,
"loss": 1.0499,
"step": 118
},
{
"epoch": 0.9855072463768116,
"grad_norm": 0.8011189103126526,
"learning_rate": 2.6970162798363695e-05,
"loss": 0.9278,
"step": 119
},
{
"epoch": 0.9937888198757764,
"grad_norm": 0.8758801221847534,
"learning_rate": 2.640800795007203e-05,
"loss": 1.0722,
"step": 120
},
{
"epoch": 1.0020703933747412,
"grad_norm": 0.6602959632873535,
"learning_rate": 2.5848202066616305e-05,
"loss": 0.8362,
"step": 121
},
{
"epoch": 1.010351966873706,
"grad_norm": 0.22043457627296448,
"learning_rate": 2.5290898193335446e-05,
"loss": 0.6068,
"step": 122
},
{
"epoch": 1.0186335403726707,
"grad_norm": 0.2249661386013031,
"learning_rate": 2.4736248691543736e-05,
"loss": 0.6206,
"step": 123
},
{
"epoch": 1.0269151138716357,
"grad_norm": 0.23550471663475037,
"learning_rate": 2.4184405196876842e-05,
"loss": 0.7048,
"step": 124
},
{
"epoch": 1.0351966873706004,
"grad_norm": 0.2546531856060028,
"learning_rate": 2.363551857783608e-05,
"loss": 0.6356,
"step": 125
},
{
"epoch": 1.0434782608695652,
"grad_norm": 0.23183418810367584,
"learning_rate": 2.308973889454249e-05,
"loss": 0.7009,
"step": 126
},
{
"epoch": 1.05175983436853,
"grad_norm": 0.23346415162086487,
"learning_rate": 2.2547215357711918e-05,
"loss": 0.5939,
"step": 127
},
{
"epoch": 1.060041407867495,
"grad_norm": 0.24210385978221893,
"learning_rate": 2.2008096287862266e-05,
"loss": 0.7173,
"step": 128
},
{
"epoch": 1.0683229813664596,
"grad_norm": 0.22531944513320923,
"learning_rate": 2.1472529074764177e-05,
"loss": 0.5273,
"step": 129
},
{
"epoch": 1.0766045548654244,
"grad_norm": 0.25816595554351807,
"learning_rate": 2.0940660137146074e-05,
"loss": 0.6477,
"step": 130
},
{
"epoch": 1.0848861283643891,
"grad_norm": 0.2804325520992279,
"learning_rate": 2.041263488266484e-05,
"loss": 0.6571,
"step": 131
},
{
"epoch": 1.093167701863354,
"grad_norm": 0.274699330329895,
"learning_rate": 1.988859766815275e-05,
"loss": 0.6704,
"step": 132
},
{
"epoch": 1.1014492753623188,
"grad_norm": 0.26135748624801636,
"learning_rate": 1.9368691760151773e-05,
"loss": 0.6641,
"step": 133
},
{
"epoch": 1.1097308488612836,
"grad_norm": 0.3417491912841797,
"learning_rate": 1.885305929574593e-05,
"loss": 0.8094,
"step": 134
},
{
"epoch": 1.1180124223602483,
"grad_norm": 0.2966398298740387,
"learning_rate": 1.8341841243702424e-05,
"loss": 0.7448,
"step": 135
},
{
"epoch": 1.1262939958592133,
"grad_norm": 0.29686564207077026,
"learning_rate": 1.7835177365932225e-05,
"loss": 0.6288,
"step": 136
},
{
"epoch": 1.134575569358178,
"grad_norm": 0.332364946603775,
"learning_rate": 1.7333206179280478e-05,
"loss": 0.7955,
"step": 137
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.3861692249774933,
"learning_rate": 1.6836064917657478e-05,
"loss": 0.6987,
"step": 138
},
{
"epoch": 1.1511387163561078,
"grad_norm": 0.351142555475235,
"learning_rate": 1.6343889494520224e-05,
"loss": 0.72,
"step": 139
},
{
"epoch": 1.1594202898550725,
"grad_norm": 0.3705615997314453,
"learning_rate": 1.5856814465715064e-05,
"loss": 0.5818,
"step": 140
},
{
"epoch": 1.1677018633540373,
"grad_norm": 0.36091944575309753,
"learning_rate": 1.5374972992691458e-05,
"loss": 0.6673,
"step": 141
},
{
"epoch": 1.175983436853002,
"grad_norm": 0.39567896723747253,
"learning_rate": 1.4898496806096974e-05,
"loss": 0.6597,
"step": 142
},
{
"epoch": 1.184265010351967,
"grad_norm": 0.38994473218917847,
"learning_rate": 1.4427516169763444e-05,
"loss": 0.6453,
"step": 143
},
{
"epoch": 1.1925465838509317,
"grad_norm": 0.4518220126628876,
"learning_rate": 1.396215984509412e-05,
"loss": 0.7173,
"step": 144
},
{
"epoch": 1.2008281573498965,
"grad_norm": 0.4618150591850281,
"learning_rate": 1.3502555055861625e-05,
"loss": 0.6811,
"step": 145
},
{
"epoch": 1.2091097308488612,
"grad_norm": 0.4686547517776489,
"learning_rate": 1.3048827453426203e-05,
"loss": 0.6195,
"step": 146
},
{
"epoch": 1.2173913043478262,
"grad_norm": 0.4487763047218323,
"learning_rate": 1.2601101082383917e-05,
"loss": 0.6075,
"step": 147
},
{
"epoch": 1.225672877846791,
"grad_norm": 0.5483669638633728,
"learning_rate": 1.2159498346654094e-05,
"loss": 0.6045,
"step": 148
},
{
"epoch": 1.2339544513457557,
"grad_norm": 0.573219358921051,
"learning_rate": 1.1724139976015306e-05,
"loss": 0.7711,
"step": 149
},
{
"epoch": 1.2422360248447206,
"grad_norm": 0.6374213099479675,
"learning_rate": 1.1295144993099068e-05,
"loss": 0.6176,
"step": 150
},
{
"epoch": 1.2422360248447206,
"eval_loss": 0.8175904750823975,
"eval_runtime": 32.7299,
"eval_samples_per_second": 6.233,
"eval_steps_per_second": 1.558,
"step": 150
},
{
"epoch": 1.2505175983436854,
"grad_norm": 0.5926390290260315,
"learning_rate": 1.0872630680850196e-05,
"loss": 0.8074,
"step": 151
},
{
"epoch": 1.25879917184265,
"grad_norm": 0.2985449433326721,
"learning_rate": 1.0456712550462898e-05,
"loss": 0.5224,
"step": 152
},
{
"epoch": 1.2670807453416149,
"grad_norm": 0.3578867018222809,
"learning_rate": 1.0047504309801104e-05,
"loss": 0.6502,
"step": 153
},
{
"epoch": 1.2753623188405796,
"grad_norm": 0.3537825047969818,
"learning_rate": 9.645117832311886e-06,
"loss": 0.6731,
"step": 154
},
{
"epoch": 1.2836438923395446,
"grad_norm": 0.3358495533466339,
"learning_rate": 9.249663126440394e-06,
"loss": 0.6796,
"step": 155
},
{
"epoch": 1.2919254658385093,
"grad_norm": 0.29126879572868347,
"learning_rate": 8.861248305554624e-06,
"loss": 0.5348,
"step": 156
},
{
"epoch": 1.300207039337474,
"grad_norm": 0.317704439163208,
"learning_rate": 8.47997955838829e-06,
"loss": 0.6091,
"step": 157
},
{
"epoch": 1.308488612836439,
"grad_norm": 0.320115864276886,
"learning_rate": 8.10596112000994e-06,
"loss": 0.6371,
"step": 158
},
{
"epoch": 1.3167701863354038,
"grad_norm": 0.33530059456825256,
"learning_rate": 7.739295243326067e-06,
"loss": 0.6329,
"step": 159
},
{
"epoch": 1.3250517598343685,
"grad_norm": 0.31264767050743103,
"learning_rate": 7.380082171126228e-06,
"loss": 0.654,
"step": 160
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.32048940658569336,
"learning_rate": 7.028420108677635e-06,
"loss": 0.5732,
"step": 161
},
{
"epoch": 1.341614906832298,
"grad_norm": 0.33851999044418335,
"learning_rate": 6.684405196876842e-06,
"loss": 0.686,
"step": 162
},
{
"epoch": 1.349896480331263,
"grad_norm": 0.32517871260643005,
"learning_rate": 6.3481314859657675e-06,
"loss": 0.65,
"step": 163
},
{
"epoch": 1.3581780538302277,
"grad_norm": 0.2995445430278778,
"learning_rate": 6.019690909819298e-06,
"loss": 0.5915,
"step": 164
},
{
"epoch": 1.3664596273291925,
"grad_norm": 0.3606933653354645,
"learning_rate": 5.6991732608115e-06,
"loss": 0.7172,
"step": 165
},
{
"epoch": 1.3747412008281574,
"grad_norm": 0.3630608320236206,
"learning_rate": 5.386666165267256e-06,
"loss": 0.675,
"step": 166
},
{
"epoch": 1.3830227743271222,
"grad_norm": 0.36110809445381165,
"learning_rate": 5.08225505950613e-06,
"loss": 0.7061,
"step": 167
},
{
"epoch": 1.391304347826087,
"grad_norm": 0.3950647711753845,
"learning_rate": 4.786023166484913e-06,
"loss": 0.673,
"step": 168
},
{
"epoch": 1.3995859213250519,
"grad_norm": 0.3615090847015381,
"learning_rate": 4.498051473045291e-06,
"loss": 0.6181,
"step": 169
},
{
"epoch": 1.4078674948240166,
"grad_norm": 0.3696867823600769,
"learning_rate": 4.218418707772886e-06,
"loss": 0.6945,
"step": 170
},
{
"epoch": 1.4161490683229814,
"grad_norm": 0.3751198947429657,
"learning_rate": 3.947201319473587e-06,
"loss": 0.6095,
"step": 171
},
{
"epoch": 1.4244306418219461,
"grad_norm": 0.4392836093902588,
"learning_rate": 3.684473456273278e-06,
"loss": 0.7707,
"step": 172
},
{
"epoch": 1.4327122153209109,
"grad_norm": 0.38536399602890015,
"learning_rate": 3.4303069453464383e-06,
"loss": 0.5751,
"step": 173
},
{
"epoch": 1.4409937888198758,
"grad_norm": 0.44222986698150635,
"learning_rate": 3.184771273279312e-06,
"loss": 0.6717,
"step": 174
},
{
"epoch": 1.4492753623188406,
"grad_norm": 0.3905293047428131,
"learning_rate": 2.947933567072987e-06,
"loss": 0.5321,
"step": 175
},
{
"epoch": 1.4575569358178053,
"grad_norm": 0.49432647228240967,
"learning_rate": 2.719858575791534e-06,
"loss": 0.6326,
"step": 176
},
{
"epoch": 1.4658385093167703,
"grad_norm": 0.49581611156463623,
"learning_rate": 2.500608652860256e-06,
"loss": 0.6167,
"step": 177
},
{
"epoch": 1.474120082815735,
"grad_norm": 0.5105964541435242,
"learning_rate": 2.2902437390188737e-06,
"loss": 0.6004,
"step": 178
},
{
"epoch": 1.4824016563146998,
"grad_norm": 0.6480532884597778,
"learning_rate": 2.0888213459343587e-06,
"loss": 0.5838,
"step": 179
},
{
"epoch": 1.4906832298136645,
"grad_norm": 0.7326604723930359,
"learning_rate": 1.8963965404777875e-06,
"loss": 0.6759,
"step": 180
},
{
"epoch": 1.4989648033126293,
"grad_norm": 0.6053556799888611,
"learning_rate": 1.7130219296696263e-06,
"loss": 0.6138,
"step": 181
},
{
"epoch": 1.5072463768115942,
"grad_norm": 0.21714286506175995,
"learning_rate": 1.5387476462974824e-06,
"loss": 0.5251,
"step": 182
},
{
"epoch": 1.515527950310559,
"grad_norm": 0.2275223731994629,
"learning_rate": 1.3736213352103147e-06,
"loss": 0.6187,
"step": 183
},
{
"epoch": 1.5238095238095237,
"grad_norm": 0.2726026177406311,
"learning_rate": 1.2176881402928002e-06,
"loss": 0.7148,
"step": 184
},
{
"epoch": 1.5320910973084887,
"grad_norm": 0.22267615795135498,
"learning_rate": 1.0709906921234367e-06,
"loss": 0.4634,
"step": 185
},
{
"epoch": 1.5403726708074534,
"grad_norm": 0.23520763218402863,
"learning_rate": 9.33569096319799e-07,
"loss": 0.6049,
"step": 186
},
{
"epoch": 1.5486542443064182,
"grad_norm": 0.2739216387271881,
"learning_rate": 8.054609225740255e-07,
"loss": 0.784,
"step": 187
},
{
"epoch": 1.5569358178053831,
"grad_norm": 0.27384185791015625,
"learning_rate": 6.867011943816724e-07,
"loss": 0.6121,
"step": 188
},
{
"epoch": 1.5652173913043477,
"grad_norm": 0.3003735840320587,
"learning_rate": 5.77322379466617e-07,
"loss": 0.6644,
"step": 189
},
{
"epoch": 1.5734989648033126,
"grad_norm": 0.34010234475135803,
"learning_rate": 4.773543809047186e-07,
"loss": 0.6084,
"step": 190
},
{
"epoch": 1.5817805383022774,
"grad_norm": 0.29969656467437744,
"learning_rate": 3.868245289486027e-07,
"loss": 0.6366,
"step": 191
},
{
"epoch": 1.5900621118012421,
"grad_norm": 0.29340919852256775,
"learning_rate": 3.0575757355586817e-07,
"loss": 0.638,
"step": 192
},
{
"epoch": 1.598343685300207,
"grad_norm": 0.32281142473220825,
"learning_rate": 2.3417567762266497e-07,
"loss": 0.6753,
"step": 193
},
{
"epoch": 1.6066252587991718,
"grad_norm": 0.3351536989212036,
"learning_rate": 1.7209841092460043e-07,
"loss": 0.6692,
"step": 194
},
{
"epoch": 1.6149068322981366,
"grad_norm": 0.44075658917427063,
"learning_rate": 1.1954274476655534e-07,
"loss": 0.603,
"step": 195
},
{
"epoch": 1.6231884057971016,
"grad_norm": 0.3639785945415497,
"learning_rate": 7.652304734289127e-08,
"loss": 0.6775,
"step": 196
},
{
"epoch": 1.6314699792960663,
"grad_norm": 0.36761367321014404,
"learning_rate": 4.30510798093342e-08,
"loss": 0.7417,
"step": 197
},
{
"epoch": 1.639751552795031,
"grad_norm": 0.3425098657608032,
"learning_rate": 1.9135993067588284e-08,
"loss": 0.6121,
"step": 198
},
{
"epoch": 1.648033126293996,
"grad_norm": 0.38983044028282166,
"learning_rate": 4.784325263584854e-09,
"loss": 0.6343,
"step": 199
},
{
"epoch": 1.6563146997929605,
"grad_norm": 0.37634265422821045,
"learning_rate": 0.0,
"loss": 0.6523,
"step": 200
},
{
"epoch": 1.6563146997929605,
"eval_loss": 0.8045907020568848,
"eval_runtime": 32.2688,
"eval_samples_per_second": 6.322,
"eval_steps_per_second": 1.58,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 4,
"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": 6.558232004284908e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}