RoyJoy's picture
Training in progress, step 200, checkpoint
ef72f65 verified
{
"best_metric": 0.22498248517513275,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.517799352750809,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0025889967637540453,
"grad_norm": 8.612391471862793,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.8772,
"step": 1
},
{
"epoch": 0.0025889967637540453,
"eval_loss": 1.1311349868774414,
"eval_runtime": 63.1174,
"eval_samples_per_second": 41.241,
"eval_steps_per_second": 5.165,
"step": 1
},
{
"epoch": 0.005177993527508091,
"grad_norm": 10.561990737915039,
"learning_rate": 6.666666666666667e-06,
"loss": 2.3642,
"step": 2
},
{
"epoch": 0.007766990291262136,
"grad_norm": 12.674636840820312,
"learning_rate": 1e-05,
"loss": 2.7038,
"step": 3
},
{
"epoch": 0.010355987055016181,
"grad_norm": 11.861933708190918,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.9593,
"step": 4
},
{
"epoch": 0.012944983818770227,
"grad_norm": 10.037701606750488,
"learning_rate": 1.6666666666666667e-05,
"loss": 2.8463,
"step": 5
},
{
"epoch": 0.015533980582524271,
"grad_norm": 8.951319694519043,
"learning_rate": 2e-05,
"loss": 2.6833,
"step": 6
},
{
"epoch": 0.018122977346278317,
"grad_norm": 11.811137199401855,
"learning_rate": 2.3333333333333336e-05,
"loss": 2.8029,
"step": 7
},
{
"epoch": 0.020711974110032363,
"grad_norm": 11.602544784545898,
"learning_rate": 2.6666666666666667e-05,
"loss": 2.5999,
"step": 8
},
{
"epoch": 0.02330097087378641,
"grad_norm": 10.852923393249512,
"learning_rate": 3e-05,
"loss": 2.3762,
"step": 9
},
{
"epoch": 0.025889967637540454,
"grad_norm": 16.908262252807617,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.2558,
"step": 10
},
{
"epoch": 0.0284789644012945,
"grad_norm": 19.876672744750977,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.9599,
"step": 11
},
{
"epoch": 0.031067961165048542,
"grad_norm": 36.011985778808594,
"learning_rate": 4e-05,
"loss": 1.9861,
"step": 12
},
{
"epoch": 0.03365695792880259,
"grad_norm": 37.01054000854492,
"learning_rate": 4.3333333333333334e-05,
"loss": 1.9578,
"step": 13
},
{
"epoch": 0.036245954692556634,
"grad_norm": 19.07244300842285,
"learning_rate": 4.666666666666667e-05,
"loss": 1.7452,
"step": 14
},
{
"epoch": 0.038834951456310676,
"grad_norm": 11.258912086486816,
"learning_rate": 5e-05,
"loss": 1.473,
"step": 15
},
{
"epoch": 0.041423948220064725,
"grad_norm": 9.571911811828613,
"learning_rate": 5.333333333333333e-05,
"loss": 1.4802,
"step": 16
},
{
"epoch": 0.04401294498381877,
"grad_norm": 5.4818878173828125,
"learning_rate": 5.666666666666667e-05,
"loss": 1.449,
"step": 17
},
{
"epoch": 0.04660194174757282,
"grad_norm": 3.5284886360168457,
"learning_rate": 6e-05,
"loss": 1.3482,
"step": 18
},
{
"epoch": 0.04919093851132686,
"grad_norm": 4.385798931121826,
"learning_rate": 6.333333333333333e-05,
"loss": 1.3401,
"step": 19
},
{
"epoch": 0.05177993527508091,
"grad_norm": 4.73576545715332,
"learning_rate": 6.666666666666667e-05,
"loss": 1.3967,
"step": 20
},
{
"epoch": 0.05436893203883495,
"grad_norm": 7.08858585357666,
"learning_rate": 7e-05,
"loss": 1.4665,
"step": 21
},
{
"epoch": 0.056957928802589,
"grad_norm": 5.8825225830078125,
"learning_rate": 7.333333333333333e-05,
"loss": 1.4479,
"step": 22
},
{
"epoch": 0.05954692556634304,
"grad_norm": 6.359987735748291,
"learning_rate": 7.666666666666667e-05,
"loss": 1.4314,
"step": 23
},
{
"epoch": 0.062135922330097085,
"grad_norm": 26.79585075378418,
"learning_rate": 8e-05,
"loss": 1.499,
"step": 24
},
{
"epoch": 0.06472491909385113,
"grad_norm": 9.032891273498535,
"learning_rate": 8.333333333333334e-05,
"loss": 1.5914,
"step": 25
},
{
"epoch": 0.06731391585760518,
"grad_norm": 10.370737075805664,
"learning_rate": 8.666666666666667e-05,
"loss": 1.5544,
"step": 26
},
{
"epoch": 0.06990291262135923,
"grad_norm": 7.443507671356201,
"learning_rate": 9e-05,
"loss": 1.3836,
"step": 27
},
{
"epoch": 0.07249190938511327,
"grad_norm": 4.631689548492432,
"learning_rate": 9.333333333333334e-05,
"loss": 1.2513,
"step": 28
},
{
"epoch": 0.07508090614886731,
"grad_norm": 3.5808937549591064,
"learning_rate": 9.666666666666667e-05,
"loss": 1.265,
"step": 29
},
{
"epoch": 0.07766990291262135,
"grad_norm": 3.6336581707000732,
"learning_rate": 0.0001,
"loss": 1.2874,
"step": 30
},
{
"epoch": 0.08025889967637541,
"grad_norm": 3.7123985290527344,
"learning_rate": 9.999146252290264e-05,
"loss": 1.2587,
"step": 31
},
{
"epoch": 0.08284789644012945,
"grad_norm": 3.7729804515838623,
"learning_rate": 9.996585300715116e-05,
"loss": 1.3292,
"step": 32
},
{
"epoch": 0.0854368932038835,
"grad_norm": 6.0967206954956055,
"learning_rate": 9.99231801983717e-05,
"loss": 1.3803,
"step": 33
},
{
"epoch": 0.08802588996763754,
"grad_norm": 4.336344242095947,
"learning_rate": 9.986345866928941e-05,
"loss": 1.328,
"step": 34
},
{
"epoch": 0.09061488673139159,
"grad_norm": 4.434997081756592,
"learning_rate": 9.978670881475172e-05,
"loss": 1.2927,
"step": 35
},
{
"epoch": 0.09320388349514563,
"grad_norm": 7.466955661773682,
"learning_rate": 9.96929568447637e-05,
"loss": 1.5473,
"step": 36
},
{
"epoch": 0.09579288025889968,
"grad_norm": 6.0542497634887695,
"learning_rate": 9.958223477553714e-05,
"loss": 1.4992,
"step": 37
},
{
"epoch": 0.09838187702265372,
"grad_norm": 6.534477233886719,
"learning_rate": 9.94545804185573e-05,
"loss": 1.3268,
"step": 38
},
{
"epoch": 0.10097087378640776,
"grad_norm": 6.788901329040527,
"learning_rate": 9.931003736767013e-05,
"loss": 1.2662,
"step": 39
},
{
"epoch": 0.10355987055016182,
"grad_norm": 4.574948310852051,
"learning_rate": 9.91486549841951e-05,
"loss": 1.2097,
"step": 40
},
{
"epoch": 0.10614886731391586,
"grad_norm": 2.7755305767059326,
"learning_rate": 9.89704883800683e-05,
"loss": 1.1472,
"step": 41
},
{
"epoch": 0.1087378640776699,
"grad_norm": 3.1703152656555176,
"learning_rate": 9.877559839902184e-05,
"loss": 1.2213,
"step": 42
},
{
"epoch": 0.11132686084142394,
"grad_norm": 2.9166173934936523,
"learning_rate": 9.85640515958057e-05,
"loss": 1.1592,
"step": 43
},
{
"epoch": 0.113915857605178,
"grad_norm": 3.054363965988159,
"learning_rate": 9.833592021345937e-05,
"loss": 1.1857,
"step": 44
},
{
"epoch": 0.11650485436893204,
"grad_norm": 3.5410144329071045,
"learning_rate": 9.809128215864097e-05,
"loss": 1.2165,
"step": 45
},
{
"epoch": 0.11909385113268608,
"grad_norm": 4.187359809875488,
"learning_rate": 9.783022097502204e-05,
"loss": 1.2585,
"step": 46
},
{
"epoch": 0.12168284789644013,
"grad_norm": 4.440476894378662,
"learning_rate": 9.755282581475769e-05,
"loss": 1.258,
"step": 47
},
{
"epoch": 0.12427184466019417,
"grad_norm": 7.523629188537598,
"learning_rate": 9.725919140804099e-05,
"loss": 1.2681,
"step": 48
},
{
"epoch": 0.1268608414239482,
"grad_norm": 19.543785095214844,
"learning_rate": 9.694941803075283e-05,
"loss": 1.3755,
"step": 49
},
{
"epoch": 0.12944983818770225,
"grad_norm": 14.362659454345703,
"learning_rate": 9.662361147021779e-05,
"loss": 1.4683,
"step": 50
},
{
"epoch": 0.12944983818770225,
"eval_loss": 0.3648124039173126,
"eval_runtime": 64.5567,
"eval_samples_per_second": 40.321,
"eval_steps_per_second": 5.05,
"step": 50
},
{
"epoch": 0.13203883495145632,
"grad_norm": 12.063788414001465,
"learning_rate": 9.628188298907782e-05,
"loss": 1.4899,
"step": 51
},
{
"epoch": 0.13462783171521037,
"grad_norm": 8.200540542602539,
"learning_rate": 9.592434928729616e-05,
"loss": 1.3093,
"step": 52
},
{
"epoch": 0.1372168284789644,
"grad_norm": 3.508943796157837,
"learning_rate": 9.555113246230442e-05,
"loss": 1.1634,
"step": 53
},
{
"epoch": 0.13980582524271845,
"grad_norm": 2.361328601837158,
"learning_rate": 9.516235996730645e-05,
"loss": 1.0916,
"step": 54
},
{
"epoch": 0.1423948220064725,
"grad_norm": 2.5727005004882812,
"learning_rate": 9.475816456775313e-05,
"loss": 1.0954,
"step": 55
},
{
"epoch": 0.14498381877022654,
"grad_norm": 3.032360792160034,
"learning_rate": 9.43386842960031e-05,
"loss": 1.175,
"step": 56
},
{
"epoch": 0.14757281553398058,
"grad_norm": 2.9916622638702393,
"learning_rate": 9.39040624041849e-05,
"loss": 1.1121,
"step": 57
},
{
"epoch": 0.15016181229773462,
"grad_norm": 3.048910140991211,
"learning_rate": 9.345444731527642e-05,
"loss": 1.0988,
"step": 58
},
{
"epoch": 0.15275080906148866,
"grad_norm": 3.363703489303589,
"learning_rate": 9.298999257241863e-05,
"loss": 1.1841,
"step": 59
},
{
"epoch": 0.1553398058252427,
"grad_norm": 3.3770105838775635,
"learning_rate": 9.251085678648072e-05,
"loss": 1.1814,
"step": 60
},
{
"epoch": 0.15792880258899678,
"grad_norm": 4.700929641723633,
"learning_rate": 9.201720358189464e-05,
"loss": 1.2283,
"step": 61
},
{
"epoch": 0.16051779935275082,
"grad_norm": 5.556697845458984,
"learning_rate": 9.150920154077754e-05,
"loss": 1.3271,
"step": 62
},
{
"epoch": 0.16310679611650486,
"grad_norm": 5.743304252624512,
"learning_rate": 9.098702414536107e-05,
"loss": 1.2262,
"step": 63
},
{
"epoch": 0.1656957928802589,
"grad_norm": 5.529282093048096,
"learning_rate": 9.045084971874738e-05,
"loss": 1.198,
"step": 64
},
{
"epoch": 0.16828478964401294,
"grad_norm": 3.399848222732544,
"learning_rate": 8.9900861364012e-05,
"loss": 1.1249,
"step": 65
},
{
"epoch": 0.170873786407767,
"grad_norm": 2.213207244873047,
"learning_rate": 8.933724690167417e-05,
"loss": 1.0662,
"step": 66
},
{
"epoch": 0.17346278317152103,
"grad_norm": 2.491964101791382,
"learning_rate": 8.876019880555649e-05,
"loss": 1.0862,
"step": 67
},
{
"epoch": 0.17605177993527507,
"grad_norm": 2.7167015075683594,
"learning_rate": 8.816991413705516e-05,
"loss": 1.1059,
"step": 68
},
{
"epoch": 0.1786407766990291,
"grad_norm": 2.776489734649658,
"learning_rate": 8.756659447784368e-05,
"loss": 1.0858,
"step": 69
},
{
"epoch": 0.18122977346278318,
"grad_norm": 2.965355396270752,
"learning_rate": 8.695044586103296e-05,
"loss": 1.125,
"step": 70
},
{
"epoch": 0.18381877022653723,
"grad_norm": 2.7822370529174805,
"learning_rate": 8.632167870081121e-05,
"loss": 1.0688,
"step": 71
},
{
"epoch": 0.18640776699029127,
"grad_norm": 4.001903533935547,
"learning_rate": 8.568050772058762e-05,
"loss": 1.1053,
"step": 72
},
{
"epoch": 0.1889967637540453,
"grad_norm": 3.649930477142334,
"learning_rate": 8.502715187966455e-05,
"loss": 1.1806,
"step": 73
},
{
"epoch": 0.19158576051779935,
"grad_norm": 4.8959550857543945,
"learning_rate": 8.436183429846313e-05,
"loss": 1.2705,
"step": 74
},
{
"epoch": 0.1941747572815534,
"grad_norm": 7.251972198486328,
"learning_rate": 8.368478218232787e-05,
"loss": 1.3655,
"step": 75
},
{
"epoch": 0.19676375404530744,
"grad_norm": 9.770423889160156,
"learning_rate": 8.299622674393614e-05,
"loss": 1.1064,
"step": 76
},
{
"epoch": 0.19935275080906148,
"grad_norm": 8.65103530883789,
"learning_rate": 8.229640312433937e-05,
"loss": 1.1839,
"step": 77
},
{
"epoch": 0.20194174757281552,
"grad_norm": 5.945736885070801,
"learning_rate": 8.158555031266254e-05,
"loss": 1.1019,
"step": 78
},
{
"epoch": 0.2045307443365696,
"grad_norm": 3.460510730743408,
"learning_rate": 8.086391106448965e-05,
"loss": 1.0443,
"step": 79
},
{
"epoch": 0.20711974110032363,
"grad_norm": 2.2635905742645264,
"learning_rate": 8.013173181896283e-05,
"loss": 1.0537,
"step": 80
},
{
"epoch": 0.20970873786407768,
"grad_norm": 2.609692335128784,
"learning_rate": 7.938926261462366e-05,
"loss": 1.0779,
"step": 81
},
{
"epoch": 0.21229773462783172,
"grad_norm": 2.645723819732666,
"learning_rate": 7.863675700402526e-05,
"loss": 1.0427,
"step": 82
},
{
"epoch": 0.21488673139158576,
"grad_norm": 3.2835347652435303,
"learning_rate": 7.787447196714427e-05,
"loss": 1.1034,
"step": 83
},
{
"epoch": 0.2174757281553398,
"grad_norm": 3.677543878555298,
"learning_rate": 7.710266782362247e-05,
"loss": 1.2105,
"step": 84
},
{
"epoch": 0.22006472491909385,
"grad_norm": 3.5897769927978516,
"learning_rate": 7.63216081438678e-05,
"loss": 1.2181,
"step": 85
},
{
"epoch": 0.2226537216828479,
"grad_norm": 3.5425643920898438,
"learning_rate": 7.553155965904535e-05,
"loss": 1.1825,
"step": 86
},
{
"epoch": 0.22524271844660193,
"grad_norm": 4.001893997192383,
"learning_rate": 7.473279216998895e-05,
"loss": 1.2106,
"step": 87
},
{
"epoch": 0.227831715210356,
"grad_norm": 3.9724557399749756,
"learning_rate": 7.392557845506432e-05,
"loss": 1.1139,
"step": 88
},
{
"epoch": 0.23042071197411004,
"grad_norm": 4.996490955352783,
"learning_rate": 7.311019417701566e-05,
"loss": 1.1814,
"step": 89
},
{
"epoch": 0.23300970873786409,
"grad_norm": 3.354581117630005,
"learning_rate": 7.228691778882693e-05,
"loss": 1.0731,
"step": 90
},
{
"epoch": 0.23559870550161813,
"grad_norm": 1.9178783893585205,
"learning_rate": 7.145603043863045e-05,
"loss": 0.9357,
"step": 91
},
{
"epoch": 0.23818770226537217,
"grad_norm": 2.0360922813415527,
"learning_rate": 7.061781587369519e-05,
"loss": 0.9789,
"step": 92
},
{
"epoch": 0.2407766990291262,
"grad_norm": 2.401505470275879,
"learning_rate": 6.977256034352712e-05,
"loss": 1.0518,
"step": 93
},
{
"epoch": 0.24336569579288025,
"grad_norm": 2.738330364227295,
"learning_rate": 6.892055250211552e-05,
"loss": 1.0681,
"step": 94
},
{
"epoch": 0.2459546925566343,
"grad_norm": 3.1010687351226807,
"learning_rate": 6.806208330935766e-05,
"loss": 1.1431,
"step": 95
},
{
"epoch": 0.24854368932038834,
"grad_norm": 3.6441831588745117,
"learning_rate": 6.719744593169641e-05,
"loss": 1.1438,
"step": 96
},
{
"epoch": 0.2511326860841424,
"grad_norm": 3.7766201496124268,
"learning_rate": 6.632693564200416e-05,
"loss": 1.1669,
"step": 97
},
{
"epoch": 0.2537216828478964,
"grad_norm": 4.321850299835205,
"learning_rate": 6.545084971874738e-05,
"loss": 1.1743,
"step": 98
},
{
"epoch": 0.2563106796116505,
"grad_norm": 5.203691005706787,
"learning_rate": 6.456948734446624e-05,
"loss": 1.2916,
"step": 99
},
{
"epoch": 0.2588996763754045,
"grad_norm": 6.3613057136535645,
"learning_rate": 6.368314950360415e-05,
"loss": 1.2034,
"step": 100
},
{
"epoch": 0.2588996763754045,
"eval_loss": 0.2764929533004761,
"eval_runtime": 67.6851,
"eval_samples_per_second": 38.457,
"eval_steps_per_second": 4.816,
"step": 100
},
{
"epoch": 0.2614886731391586,
"grad_norm": 3.3049983978271484,
"learning_rate": 6.279213887972179e-05,
"loss": 0.9484,
"step": 101
},
{
"epoch": 0.26407766990291265,
"grad_norm": 3.41595196723938,
"learning_rate": 6.189675975213094e-05,
"loss": 1.0463,
"step": 102
},
{
"epoch": 0.26666666666666666,
"grad_norm": 3.7063159942626953,
"learning_rate": 6.099731789198344e-05,
"loss": 1.0549,
"step": 103
},
{
"epoch": 0.26925566343042073,
"grad_norm": 3.5637729167938232,
"learning_rate": 6.009412045785051e-05,
"loss": 1.0105,
"step": 104
},
{
"epoch": 0.27184466019417475,
"grad_norm": 3.321582317352295,
"learning_rate": 5.918747589082853e-05,
"loss": 1.017,
"step": 105
},
{
"epoch": 0.2744336569579288,
"grad_norm": 2.760406732559204,
"learning_rate": 5.82776938092065e-05,
"loss": 1.0604,
"step": 106
},
{
"epoch": 0.27702265372168283,
"grad_norm": 2.2482504844665527,
"learning_rate": 5.736508490273188e-05,
"loss": 0.9956,
"step": 107
},
{
"epoch": 0.2796116504854369,
"grad_norm": 2.5008554458618164,
"learning_rate": 5.644996082651017e-05,
"loss": 1.0292,
"step": 108
},
{
"epoch": 0.2822006472491909,
"grad_norm": 3.1802356243133545,
"learning_rate": 5.553263409457504e-05,
"loss": 1.0959,
"step": 109
},
{
"epoch": 0.284789644012945,
"grad_norm": 4.109099388122559,
"learning_rate": 5.4613417973165106e-05,
"loss": 1.1156,
"step": 110
},
{
"epoch": 0.287378640776699,
"grad_norm": 5.0009307861328125,
"learning_rate": 5.3692626373743706e-05,
"loss": 1.2309,
"step": 111
},
{
"epoch": 0.28996763754045307,
"grad_norm": 5.912919521331787,
"learning_rate": 5.27705737457985e-05,
"loss": 1.1948,
"step": 112
},
{
"epoch": 0.29255663430420714,
"grad_norm": 4.550836086273193,
"learning_rate": 5.184757496945726e-05,
"loss": 1.0999,
"step": 113
},
{
"epoch": 0.29514563106796116,
"grad_norm": 1.984678864479065,
"learning_rate": 5.092394524795649e-05,
"loss": 0.8638,
"step": 114
},
{
"epoch": 0.2977346278317152,
"grad_norm": 2.326871395111084,
"learning_rate": 5e-05,
"loss": 0.8946,
"step": 115
},
{
"epoch": 0.30032362459546924,
"grad_norm": 2.4947257041931152,
"learning_rate": 4.907605475204352e-05,
"loss": 0.8815,
"step": 116
},
{
"epoch": 0.3029126213592233,
"grad_norm": 2.2519426345825195,
"learning_rate": 4.8152425030542766e-05,
"loss": 0.9208,
"step": 117
},
{
"epoch": 0.3055016181229773,
"grad_norm": 2.274266242980957,
"learning_rate": 4.72294262542015e-05,
"loss": 0.9498,
"step": 118
},
{
"epoch": 0.3080906148867314,
"grad_norm": 2.3184547424316406,
"learning_rate": 4.6307373626256306e-05,
"loss": 0.9624,
"step": 119
},
{
"epoch": 0.3106796116504854,
"grad_norm": 2.551255941390991,
"learning_rate": 4.5386582026834906e-05,
"loss": 0.9275,
"step": 120
},
{
"epoch": 0.3132686084142395,
"grad_norm": 2.7774176597595215,
"learning_rate": 4.446736590542497e-05,
"loss": 1.0286,
"step": 121
},
{
"epoch": 0.31585760517799355,
"grad_norm": 3.2560079097747803,
"learning_rate": 4.3550039173489845e-05,
"loss": 1.0915,
"step": 122
},
{
"epoch": 0.31844660194174756,
"grad_norm": 3.729802370071411,
"learning_rate": 4.2634915097268115e-05,
"loss": 1.0848,
"step": 123
},
{
"epoch": 0.32103559870550163,
"grad_norm": 4.8128886222839355,
"learning_rate": 4.1722306190793495e-05,
"loss": 1.2002,
"step": 124
},
{
"epoch": 0.32362459546925565,
"grad_norm": 6.0503363609313965,
"learning_rate": 4.0812524109171476e-05,
"loss": 1.3538,
"step": 125
},
{
"epoch": 0.3262135922330097,
"grad_norm": 1.4161758422851562,
"learning_rate": 3.99058795421495e-05,
"loss": 0.7361,
"step": 126
},
{
"epoch": 0.32880258899676373,
"grad_norm": 1.7377864122390747,
"learning_rate": 3.9002682108016585e-05,
"loss": 0.8361,
"step": 127
},
{
"epoch": 0.3313915857605178,
"grad_norm": 1.9191443920135498,
"learning_rate": 3.8103240247869075e-05,
"loss": 0.8595,
"step": 128
},
{
"epoch": 0.3339805825242718,
"grad_norm": 1.9472070932388306,
"learning_rate": 3.720786112027822e-05,
"loss": 0.8621,
"step": 129
},
{
"epoch": 0.3365695792880259,
"grad_norm": 1.959277629852295,
"learning_rate": 3.631685049639586e-05,
"loss": 0.8201,
"step": 130
},
{
"epoch": 0.33915857605177996,
"grad_norm": 2.203312635421753,
"learning_rate": 3.543051265553377e-05,
"loss": 0.8951,
"step": 131
},
{
"epoch": 0.341747572815534,
"grad_norm": 2.3594112396240234,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.9094,
"step": 132
},
{
"epoch": 0.34433656957928804,
"grad_norm": 2.7733709812164307,
"learning_rate": 3.367306435799584e-05,
"loss": 1.0573,
"step": 133
},
{
"epoch": 0.34692556634304206,
"grad_norm": 2.709257125854492,
"learning_rate": 3.2802554068303596e-05,
"loss": 0.8995,
"step": 134
},
{
"epoch": 0.34951456310679613,
"grad_norm": 3.445384979248047,
"learning_rate": 3.1937916690642356e-05,
"loss": 1.0222,
"step": 135
},
{
"epoch": 0.35210355987055014,
"grad_norm": 4.074124336242676,
"learning_rate": 3.107944749788449e-05,
"loss": 1.2069,
"step": 136
},
{
"epoch": 0.3546925566343042,
"grad_norm": 5.069247245788574,
"learning_rate": 3.0227439656472877e-05,
"loss": 1.2274,
"step": 137
},
{
"epoch": 0.3572815533980582,
"grad_norm": 4.2536211013793945,
"learning_rate": 2.9382184126304834e-05,
"loss": 1.0609,
"step": 138
},
{
"epoch": 0.3598705501618123,
"grad_norm": 1.5287104845046997,
"learning_rate": 2.8543969561369556e-05,
"loss": 0.7689,
"step": 139
},
{
"epoch": 0.36245954692556637,
"grad_norm": 1.7438405752182007,
"learning_rate": 2.771308221117309e-05,
"loss": 0.8113,
"step": 140
},
{
"epoch": 0.3650485436893204,
"grad_norm": 1.8701605796813965,
"learning_rate": 2.688980582298435e-05,
"loss": 0.8464,
"step": 141
},
{
"epoch": 0.36763754045307445,
"grad_norm": 1.9416054487228394,
"learning_rate": 2.607442154493568e-05,
"loss": 0.8544,
"step": 142
},
{
"epoch": 0.37022653721682847,
"grad_norm": 1.9130077362060547,
"learning_rate": 2.5267207830011068e-05,
"loss": 0.8093,
"step": 143
},
{
"epoch": 0.37281553398058254,
"grad_norm": 2.212625741958618,
"learning_rate": 2.446844034095466e-05,
"loss": 0.942,
"step": 144
},
{
"epoch": 0.37540453074433655,
"grad_norm": 2.4185450077056885,
"learning_rate": 2.3678391856132204e-05,
"loss": 0.9415,
"step": 145
},
{
"epoch": 0.3779935275080906,
"grad_norm": 2.5846853256225586,
"learning_rate": 2.2897332176377528e-05,
"loss": 0.9444,
"step": 146
},
{
"epoch": 0.38058252427184464,
"grad_norm": 3.020327091217041,
"learning_rate": 2.2125528032855724e-05,
"loss": 1.0272,
"step": 147
},
{
"epoch": 0.3831715210355987,
"grad_norm": 3.689166784286499,
"learning_rate": 2.136324299597474e-05,
"loss": 1.0999,
"step": 148
},
{
"epoch": 0.3857605177993528,
"grad_norm": 4.469290256500244,
"learning_rate": 2.061073738537635e-05,
"loss": 1.1435,
"step": 149
},
{
"epoch": 0.3883495145631068,
"grad_norm": 5.824495315551758,
"learning_rate": 1.9868268181037185e-05,
"loss": 1.2122,
"step": 150
},
{
"epoch": 0.3883495145631068,
"eval_loss": 0.23401835560798645,
"eval_runtime": 65.3101,
"eval_samples_per_second": 39.856,
"eval_steps_per_second": 4.992,
"step": 150
},
{
"epoch": 0.39093851132686086,
"grad_norm": 1.4624581336975098,
"learning_rate": 1.9136088935510362e-05,
"loss": 0.7601,
"step": 151
},
{
"epoch": 0.3935275080906149,
"grad_norm": 1.5358047485351562,
"learning_rate": 1.8414449687337464e-05,
"loss": 0.7365,
"step": 152
},
{
"epoch": 0.39611650485436894,
"grad_norm": 1.8620479106903076,
"learning_rate": 1.7703596875660645e-05,
"loss": 0.8749,
"step": 153
},
{
"epoch": 0.39870550161812296,
"grad_norm": 1.838742733001709,
"learning_rate": 1.700377325606388e-05,
"loss": 0.8029,
"step": 154
},
{
"epoch": 0.40129449838187703,
"grad_norm": 1.8708423376083374,
"learning_rate": 1.631521781767214e-05,
"loss": 0.8374,
"step": 155
},
{
"epoch": 0.40388349514563104,
"grad_norm": 1.9949666261672974,
"learning_rate": 1.5638165701536868e-05,
"loss": 0.7693,
"step": 156
},
{
"epoch": 0.4064724919093851,
"grad_norm": 2.179053783416748,
"learning_rate": 1.4972848120335453e-05,
"loss": 0.8748,
"step": 157
},
{
"epoch": 0.4090614886731392,
"grad_norm": 2.389301300048828,
"learning_rate": 1.4319492279412388e-05,
"loss": 0.9519,
"step": 158
},
{
"epoch": 0.4116504854368932,
"grad_norm": 2.7463135719299316,
"learning_rate": 1.3678321299188801e-05,
"loss": 0.9744,
"step": 159
},
{
"epoch": 0.41423948220064727,
"grad_norm": 2.8853588104248047,
"learning_rate": 1.3049554138967051e-05,
"loss": 0.9669,
"step": 160
},
{
"epoch": 0.4168284789644013,
"grad_norm": 3.77809739112854,
"learning_rate": 1.2433405522156332e-05,
"loss": 1.0887,
"step": 161
},
{
"epoch": 0.41941747572815535,
"grad_norm": 4.965099811553955,
"learning_rate": 1.183008586294485e-05,
"loss": 1.1214,
"step": 162
},
{
"epoch": 0.42200647249190937,
"grad_norm": 3.675790548324585,
"learning_rate": 1.1239801194443506e-05,
"loss": 0.8787,
"step": 163
},
{
"epoch": 0.42459546925566344,
"grad_norm": 1.4695855379104614,
"learning_rate": 1.066275309832584e-05,
"loss": 0.7685,
"step": 164
},
{
"epoch": 0.42718446601941745,
"grad_norm": 1.6097335815429688,
"learning_rate": 1.0099138635988026e-05,
"loss": 0.7544,
"step": 165
},
{
"epoch": 0.4297734627831715,
"grad_norm": 1.7829991579055786,
"learning_rate": 9.549150281252633e-06,
"loss": 0.8276,
"step": 166
},
{
"epoch": 0.4323624595469256,
"grad_norm": 1.853384017944336,
"learning_rate": 9.012975854638949e-06,
"loss": 0.8276,
"step": 167
},
{
"epoch": 0.4349514563106796,
"grad_norm": 1.9285295009613037,
"learning_rate": 8.490798459222476e-06,
"loss": 0.7999,
"step": 168
},
{
"epoch": 0.4375404530744337,
"grad_norm": 1.986692190170288,
"learning_rate": 7.982796418105371e-06,
"loss": 0.8228,
"step": 169
},
{
"epoch": 0.4401294498381877,
"grad_norm": 2.2278285026550293,
"learning_rate": 7.489143213519301e-06,
"loss": 0.8695,
"step": 170
},
{
"epoch": 0.44271844660194176,
"grad_norm": 2.41101336479187,
"learning_rate": 7.010007427581378e-06,
"loss": 0.9275,
"step": 171
},
{
"epoch": 0.4453074433656958,
"grad_norm": 2.734466791152954,
"learning_rate": 6.5455526847235825e-06,
"loss": 0.914,
"step": 172
},
{
"epoch": 0.44789644012944985,
"grad_norm": 3.5805823802948,
"learning_rate": 6.0959375958151045e-06,
"loss": 1.076,
"step": 173
},
{
"epoch": 0.45048543689320386,
"grad_norm": 4.150850296020508,
"learning_rate": 5.6613157039969055e-06,
"loss": 1.0419,
"step": 174
},
{
"epoch": 0.45307443365695793,
"grad_norm": 5.833034992218018,
"learning_rate": 5.241835432246889e-06,
"loss": 1.2505,
"step": 175
},
{
"epoch": 0.455663430420712,
"grad_norm": 1.305367112159729,
"learning_rate": 4.837640032693558e-06,
"loss": 0.686,
"step": 176
},
{
"epoch": 0.458252427184466,
"grad_norm": 1.51358962059021,
"learning_rate": 4.448867537695578e-06,
"loss": 0.7401,
"step": 177
},
{
"epoch": 0.4608414239482201,
"grad_norm": 1.6367487907409668,
"learning_rate": 4.075650712703849e-06,
"loss": 0.7588,
"step": 178
},
{
"epoch": 0.4634304207119741,
"grad_norm": 1.768928050994873,
"learning_rate": 3.71811701092219e-06,
"loss": 0.7916,
"step": 179
},
{
"epoch": 0.46601941747572817,
"grad_norm": 1.8522348403930664,
"learning_rate": 3.376388529782215e-06,
"loss": 0.7913,
"step": 180
},
{
"epoch": 0.4686084142394822,
"grad_norm": 1.9595167636871338,
"learning_rate": 3.0505819692471792e-06,
"loss": 0.7881,
"step": 181
},
{
"epoch": 0.47119741100323626,
"grad_norm": 2.242990493774414,
"learning_rate": 2.7408085919590264e-06,
"loss": 0.9085,
"step": 182
},
{
"epoch": 0.47378640776699027,
"grad_norm": 2.380833625793457,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.883,
"step": 183
},
{
"epoch": 0.47637540453074434,
"grad_norm": 2.463675022125244,
"learning_rate": 2.1697790249779636e-06,
"loss": 0.8586,
"step": 184
},
{
"epoch": 0.47896440129449835,
"grad_norm": 3.089585304260254,
"learning_rate": 1.908717841359048e-06,
"loss": 0.9745,
"step": 185
},
{
"epoch": 0.4815533980582524,
"grad_norm": 3.7443113327026367,
"learning_rate": 1.6640797865406288e-06,
"loss": 1.0367,
"step": 186
},
{
"epoch": 0.4841423948220065,
"grad_norm": 4.425037860870361,
"learning_rate": 1.4359484041943038e-06,
"loss": 1.0985,
"step": 187
},
{
"epoch": 0.4867313915857605,
"grad_norm": 3.4299700260162354,
"learning_rate": 1.2244016009781701e-06,
"loss": 0.9096,
"step": 188
},
{
"epoch": 0.4893203883495146,
"grad_norm": 1.3923226594924927,
"learning_rate": 1.0295116199317057e-06,
"loss": 0.6823,
"step": 189
},
{
"epoch": 0.4919093851132686,
"grad_norm": 1.570144772529602,
"learning_rate": 8.513450158049108e-07,
"loss": 0.7374,
"step": 190
},
{
"epoch": 0.49449838187702266,
"grad_norm": 1.7391892671585083,
"learning_rate": 6.899626323298713e-07,
"loss": 0.8171,
"step": 191
},
{
"epoch": 0.4970873786407767,
"grad_norm": 1.8321576118469238,
"learning_rate": 5.454195814427021e-07,
"loss": 0.807,
"step": 192
},
{
"epoch": 0.49967637540453075,
"grad_norm": 1.9245028495788574,
"learning_rate": 4.177652244628627e-07,
"loss": 0.774,
"step": 193
},
{
"epoch": 0.5022653721682848,
"grad_norm": 2.206279754638672,
"learning_rate": 3.0704315523631953e-07,
"loss": 0.8755,
"step": 194
},
{
"epoch": 0.5048543689320388,
"grad_norm": 2.2507548332214355,
"learning_rate": 2.1329118524827662e-07,
"loss": 0.8724,
"step": 195
},
{
"epoch": 0.5074433656957928,
"grad_norm": 2.3572773933410645,
"learning_rate": 1.3654133071059893e-07,
"loss": 0.9072,
"step": 196
},
{
"epoch": 0.510032362459547,
"grad_norm": 2.630845785140991,
"learning_rate": 7.681980162830282e-08,
"loss": 0.8965,
"step": 197
},
{
"epoch": 0.512621359223301,
"grad_norm": 3.3030409812927246,
"learning_rate": 3.4146992848854695e-08,
"loss": 0.9997,
"step": 198
},
{
"epoch": 0.515210355987055,
"grad_norm": 4.137526988983154,
"learning_rate": 8.537477097364522e-09,
"loss": 1.0538,
"step": 199
},
{
"epoch": 0.517799352750809,
"grad_norm": 5.67355489730835,
"learning_rate": 0.0,
"loss": 1.1843,
"step": 200
},
{
"epoch": 0.517799352750809,
"eval_loss": 0.22498248517513275,
"eval_runtime": 64.2833,
"eval_samples_per_second": 40.493,
"eval_steps_per_second": 5.071,
"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": 1.1605406885431214e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}