0x1202's picture
Training in progress, step 200, checkpoint
06e3d3e verified
{
"best_metric": 0.7496414184570312,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 0.6065200909780136,
"eval_steps": 25,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003032600454890068,
"grad_norm": 0.5732214450836182,
"learning_rate": 2.9999999999999997e-05,
"loss": 1.2366,
"step": 1
},
{
"epoch": 0.003032600454890068,
"eval_loss": 2.233814001083374,
"eval_runtime": 2.1263,
"eval_samples_per_second": 23.515,
"eval_steps_per_second": 3.292,
"step": 1
},
{
"epoch": 0.006065200909780136,
"grad_norm": 0.5826615691184998,
"learning_rate": 5.9999999999999995e-05,
"loss": 1.2069,
"step": 2
},
{
"epoch": 0.009097801364670205,
"grad_norm": 0.8060511946678162,
"learning_rate": 8.999999999999999e-05,
"loss": 1.4296,
"step": 3
},
{
"epoch": 0.012130401819560273,
"grad_norm": 0.7838976979255676,
"learning_rate": 0.00011999999999999999,
"loss": 1.8031,
"step": 4
},
{
"epoch": 0.015163002274450341,
"grad_norm": 0.9152936935424805,
"learning_rate": 0.00015,
"loss": 2.8825,
"step": 5
},
{
"epoch": 0.01819560272934041,
"grad_norm": 0.9083536863327026,
"learning_rate": 0.00017999999999999998,
"loss": 2.8714,
"step": 6
},
{
"epoch": 0.02122820318423048,
"grad_norm": 0.7592295408248901,
"learning_rate": 0.00020999999999999998,
"loss": 2.6227,
"step": 7
},
{
"epoch": 0.024260803639120546,
"grad_norm": 0.8848680257797241,
"learning_rate": 0.00023999999999999998,
"loss": 2.3879,
"step": 8
},
{
"epoch": 0.027293404094010616,
"grad_norm": 1.1162092685699463,
"learning_rate": 0.00027,
"loss": 1.9078,
"step": 9
},
{
"epoch": 0.030326004548900682,
"grad_norm": 1.1469495296478271,
"learning_rate": 0.0003,
"loss": 2.3304,
"step": 10
},
{
"epoch": 0.03335860500379075,
"grad_norm": 1.7421014308929443,
"learning_rate": 0.0002999794957488703,
"loss": 2.6528,
"step": 11
},
{
"epoch": 0.03639120545868082,
"grad_norm": 2.160493850708008,
"learning_rate": 0.0002999179886011389,
"loss": 1.7365,
"step": 12
},
{
"epoch": 0.039423805913570885,
"grad_norm": 1.6525168418884277,
"learning_rate": 0.0002998154953722457,
"loss": 1.3977,
"step": 13
},
{
"epoch": 0.04245640636846096,
"grad_norm": 1.732264757156372,
"learning_rate": 0.00029967204408281613,
"loss": 0.9095,
"step": 14
},
{
"epoch": 0.045489006823351025,
"grad_norm": 1.9203606843948364,
"learning_rate": 0.00029948767395100045,
"loss": 0.8081,
"step": 15
},
{
"epoch": 0.04852160727824109,
"grad_norm": 1.9768295288085938,
"learning_rate": 0.0002992624353817517,
"loss": 0.5633,
"step": 16
},
{
"epoch": 0.05155420773313116,
"grad_norm": 1.7694615125656128,
"learning_rate": 0.0002989963899530457,
"loss": 0.8582,
"step": 17
},
{
"epoch": 0.05458680818802123,
"grad_norm": 5.227871417999268,
"learning_rate": 0.00029868961039904624,
"loss": 2.0478,
"step": 18
},
{
"epoch": 0.0576194086429113,
"grad_norm": 5.613846302032471,
"learning_rate": 0.00029834218059022024,
"loss": 2.628,
"step": 19
},
{
"epoch": 0.060652009097801364,
"grad_norm": 3.1168196201324463,
"learning_rate": 0.00029795419551040833,
"loss": 2.2502,
"step": 20
},
{
"epoch": 0.06368460955269144,
"grad_norm": 2.028256893157959,
"learning_rate": 0.00029752576123085736,
"loss": 1.9875,
"step": 21
},
{
"epoch": 0.0667172100075815,
"grad_norm": 2.2501745223999023,
"learning_rate": 0.0002970569948812214,
"loss": 1.3561,
"step": 22
},
{
"epoch": 0.06974981046247157,
"grad_norm": 2.091094970703125,
"learning_rate": 0.0002965480246175399,
"loss": 1.4375,
"step": 23
},
{
"epoch": 0.07278241091736164,
"grad_norm": 1.8560627698898315,
"learning_rate": 0.0002959989895872009,
"loss": 0.8881,
"step": 24
},
{
"epoch": 0.0758150113722517,
"grad_norm": 1.5652915239334106,
"learning_rate": 0.0002954100398908995,
"loss": 1.1072,
"step": 25
},
{
"epoch": 0.0758150113722517,
"eval_loss": 1.6969295740127563,
"eval_runtime": 1.6362,
"eval_samples_per_second": 30.559,
"eval_steps_per_second": 4.278,
"step": 25
},
{
"epoch": 0.07884761182714177,
"grad_norm": 2.593773126602173,
"learning_rate": 0.0002947813365416023,
"loss": 2.3669,
"step": 26
},
{
"epoch": 0.08188021228203184,
"grad_norm": 3.031888961791992,
"learning_rate": 0.0002941130514205272,
"loss": 2.1705,
"step": 27
},
{
"epoch": 0.08491281273692192,
"grad_norm": 5.483036994934082,
"learning_rate": 0.0002934053672301536,
"loss": 2.0639,
"step": 28
},
{
"epoch": 0.08794541319181198,
"grad_norm": 2.578169584274292,
"learning_rate": 0.00029265847744427303,
"loss": 2.2763,
"step": 29
},
{
"epoch": 0.09097801364670205,
"grad_norm": 2.708948850631714,
"learning_rate": 0.00029187258625509513,
"loss": 2.6701,
"step": 30
},
{
"epoch": 0.09401061410159212,
"grad_norm": 2.3376152515411377,
"learning_rate": 0.00029104790851742417,
"loss": 2.552,
"step": 31
},
{
"epoch": 0.09704321455648218,
"grad_norm": 4.5717453956604,
"learning_rate": 0.0002901846696899191,
"loss": 2.5146,
"step": 32
},
{
"epoch": 0.10007581501137225,
"grad_norm": 3.326918601989746,
"learning_rate": 0.00028928310577345606,
"loss": 2.7361,
"step": 33
},
{
"epoch": 0.10310841546626232,
"grad_norm": 3.0180697441101074,
"learning_rate": 0.0002883434632466077,
"loss": 2.1276,
"step": 34
},
{
"epoch": 0.10614101592115238,
"grad_norm": 3.3345470428466797,
"learning_rate": 0.00028736599899825856,
"loss": 3.5262,
"step": 35
},
{
"epoch": 0.10917361637604246,
"grad_norm": 4.028136730194092,
"learning_rate": 0.00028635098025737434,
"loss": 1.3238,
"step": 36
},
{
"epoch": 0.11220621683093253,
"grad_norm": 2.7964673042297363,
"learning_rate": 0.00028529868451994384,
"loss": 1.9645,
"step": 37
},
{
"epoch": 0.1152388172858226,
"grad_norm": 2.7283153533935547,
"learning_rate": 0.0002842093994731145,
"loss": 1.6322,
"step": 38
},
{
"epoch": 0.11827141774071266,
"grad_norm": 3.139758586883545,
"learning_rate": 0.00028308342291654174,
"loss": 1.3747,
"step": 39
},
{
"epoch": 0.12130401819560273,
"grad_norm": 3.401658535003662,
"learning_rate": 0.00028192106268097334,
"loss": 1.0433,
"step": 40
},
{
"epoch": 0.1243366186504928,
"grad_norm": 3.2721481323242188,
"learning_rate": 0.00028072263654409154,
"loss": 0.9206,
"step": 41
},
{
"epoch": 0.12736921910538287,
"grad_norm": 2.2043514251708984,
"learning_rate": 0.0002794884721436361,
"loss": 0.6399,
"step": 42
},
{
"epoch": 0.13040181956027294,
"grad_norm": 2.3156049251556396,
"learning_rate": 0.00027821890688783083,
"loss": 0.8682,
"step": 43
},
{
"epoch": 0.133434420015163,
"grad_norm": 4.419061660766602,
"learning_rate": 0.0002769142878631403,
"loss": 0.5265,
"step": 44
},
{
"epoch": 0.13646702047005307,
"grad_norm": 2.9401931762695312,
"learning_rate": 0.00027557497173937923,
"loss": 0.4974,
"step": 45
},
{
"epoch": 0.13949962092494314,
"grad_norm": 2.4342000484466553,
"learning_rate": 0.000274201324672203,
"loss": 0.4075,
"step": 46
},
{
"epoch": 0.1425322213798332,
"grad_norm": 1.5229568481445312,
"learning_rate": 0.00027279372220300385,
"loss": 0.2443,
"step": 47
},
{
"epoch": 0.14556482183472327,
"grad_norm": 0.7514405846595764,
"learning_rate": 0.0002713525491562421,
"loss": 0.032,
"step": 48
},
{
"epoch": 0.14859742228961334,
"grad_norm": 3.046010732650757,
"learning_rate": 0.00026987819953423867,
"loss": 0.6208,
"step": 49
},
{
"epoch": 0.1516300227445034,
"grad_norm": 3.323383331298828,
"learning_rate": 0.00026837107640945905,
"loss": 0.4257,
"step": 50
},
{
"epoch": 0.1516300227445034,
"eval_loss": 2.1368014812469482,
"eval_runtime": 1.6375,
"eval_samples_per_second": 30.534,
"eval_steps_per_second": 4.275,
"step": 50
},
{
"epoch": 0.15466262319939347,
"grad_norm": 4.283215522766113,
"learning_rate": 0.0002668315918143169,
"loss": 1.3323,
"step": 51
},
{
"epoch": 0.15769522365428354,
"grad_norm": 3.335487127304077,
"learning_rate": 0.00026526016662852886,
"loss": 1.1937,
"step": 52
},
{
"epoch": 0.1607278241091736,
"grad_norm": 2.471447706222534,
"learning_rate": 0.00026365723046405023,
"loss": 0.9932,
"step": 53
},
{
"epoch": 0.16376042456406367,
"grad_norm": 1.7774912118911743,
"learning_rate": 0.0002620232215476231,
"loss": 0.7889,
"step": 54
},
{
"epoch": 0.16679302501895377,
"grad_norm": 3.3943495750427246,
"learning_rate": 0.0002603585866009697,
"loss": 2.2703,
"step": 55
},
{
"epoch": 0.16982562547384383,
"grad_norm": 2.009979724884033,
"learning_rate": 0.00025866378071866334,
"loss": 2.3109,
"step": 56
},
{
"epoch": 0.1728582259287339,
"grad_norm": 2.5208301544189453,
"learning_rate": 0.00025693926724370956,
"loss": 2.1646,
"step": 57
},
{
"epoch": 0.17589082638362397,
"grad_norm": 1.7100300788879395,
"learning_rate": 0.00025518551764087326,
"loss": 1.8255,
"step": 58
},
{
"epoch": 0.17892342683851403,
"grad_norm": 1.4710556268692017,
"learning_rate": 0.00025340301136778483,
"loss": 1.0757,
"step": 59
},
{
"epoch": 0.1819560272934041,
"grad_norm": 1.435238003730774,
"learning_rate": 0.00025159223574386114,
"loss": 1.3513,
"step": 60
},
{
"epoch": 0.18498862774829417,
"grad_norm": 1.8190333843231201,
"learning_rate": 0.0002497536858170772,
"loss": 1.6192,
"step": 61
},
{
"epoch": 0.18802122820318423,
"grad_norm": 1.4935904741287231,
"learning_rate": 0.00024788786422862526,
"loss": 1.3938,
"step": 62
},
{
"epoch": 0.1910538286580743,
"grad_norm": 1.5081324577331543,
"learning_rate": 0.00024599528107549745,
"loss": 1.0642,
"step": 63
},
{
"epoch": 0.19408642911296436,
"grad_norm": 1.1953938007354736,
"learning_rate": 0.00024407645377103054,
"loss": 0.5319,
"step": 64
},
{
"epoch": 0.19711902956785443,
"grad_norm": 1.042183756828308,
"learning_rate": 0.00024213190690345018,
"loss": 0.2488,
"step": 65
},
{
"epoch": 0.2001516300227445,
"grad_norm": 0.7810710072517395,
"learning_rate": 0.00024016217209245374,
"loss": 0.2012,
"step": 66
},
{
"epoch": 0.20318423047763456,
"grad_norm": 0.7428088188171387,
"learning_rate": 0.00023816778784387094,
"loss": 0.2595,
"step": 67
},
{
"epoch": 0.20621683093252463,
"grad_norm": 1.495041012763977,
"learning_rate": 0.0002361492994024415,
"loss": 1.0473,
"step": 68
},
{
"epoch": 0.2092494313874147,
"grad_norm": 3.027667284011841,
"learning_rate": 0.0002341072586027509,
"loss": 1.2385,
"step": 69
},
{
"epoch": 0.21228203184230476,
"grad_norm": 2.402413845062256,
"learning_rate": 0.00023204222371836405,
"loss": 1.1585,
"step": 70
},
{
"epoch": 0.21531463229719486,
"grad_norm": 2.1353776454925537,
"learning_rate": 0.00022995475930919905,
"loss": 0.8443,
"step": 71
},
{
"epoch": 0.21834723275208492,
"grad_norm": 1.6501647233963013,
"learning_rate": 0.00022784543606718227,
"loss": 1.0337,
"step": 72
},
{
"epoch": 0.221379833206975,
"grad_norm": 4.340311527252197,
"learning_rate": 0.00022571483066022657,
"loss": 1.1674,
"step": 73
},
{
"epoch": 0.22441243366186506,
"grad_norm": 2.6187245845794678,
"learning_rate": 0.0002235635255745762,
"loss": 0.8261,
"step": 74
},
{
"epoch": 0.22744503411675512,
"grad_norm": 1.8873292207717896,
"learning_rate": 0.00022139210895556104,
"loss": 0.6276,
"step": 75
},
{
"epoch": 0.22744503411675512,
"eval_loss": 1.2340877056121826,
"eval_runtime": 1.6504,
"eval_samples_per_second": 30.296,
"eval_steps_per_second": 4.242,
"step": 75
},
{
"epoch": 0.2304776345716452,
"grad_norm": 1.3795561790466309,
"learning_rate": 0.00021920117444680317,
"loss": 1.1671,
"step": 76
},
{
"epoch": 0.23351023502653526,
"grad_norm": 2.4479212760925293,
"learning_rate": 0.00021699132102792097,
"loss": 1.5214,
"step": 77
},
{
"epoch": 0.23654283548142532,
"grad_norm": 2.233268976211548,
"learning_rate": 0.0002147631528507739,
"loss": 1.3013,
"step": 78
},
{
"epoch": 0.2395754359363154,
"grad_norm": 1.663133144378662,
"learning_rate": 0.00021251727907429355,
"loss": 1.0497,
"step": 79
},
{
"epoch": 0.24260803639120546,
"grad_norm": 1.6820964813232422,
"learning_rate": 0.0002102543136979454,
"loss": 1.8455,
"step": 80
},
{
"epoch": 0.24564063684609552,
"grad_norm": 1.9858072996139526,
"learning_rate": 0.0002079748753938678,
"loss": 1.2171,
"step": 81
},
{
"epoch": 0.2486732373009856,
"grad_norm": 1.5699634552001953,
"learning_rate": 0.0002056795873377331,
"loss": 1.2286,
"step": 82
},
{
"epoch": 0.2517058377558757,
"grad_norm": 1.4695563316345215,
"learning_rate": 0.00020336907703837748,
"loss": 1.815,
"step": 83
},
{
"epoch": 0.25473843821076575,
"grad_norm": 1.7311599254608154,
"learning_rate": 0.00020104397616624645,
"loss": 2.3227,
"step": 84
},
{
"epoch": 0.2577710386656558,
"grad_norm": 1.2741672992706299,
"learning_rate": 0.00019870492038070252,
"loss": 1.8355,
"step": 85
},
{
"epoch": 0.2608036391205459,
"grad_norm": 1.5505032539367676,
"learning_rate": 0.0001963525491562421,
"loss": 1.4854,
"step": 86
},
{
"epoch": 0.26383623957543595,
"grad_norm": 1.86395263671875,
"learning_rate": 0.0001939875056076697,
"loss": 1.8457,
"step": 87
},
{
"epoch": 0.266868840030326,
"grad_norm": 1.2954498529434204,
"learning_rate": 0.00019161043631427666,
"loss": 2.1125,
"step": 88
},
{
"epoch": 0.2699014404852161,
"grad_norm": 1.0831388235092163,
"learning_rate": 0.00018922199114307294,
"loss": 1.1493,
"step": 89
},
{
"epoch": 0.27293404094010615,
"grad_norm": 1.4645804166793823,
"learning_rate": 0.00018682282307111987,
"loss": 1.0175,
"step": 90
},
{
"epoch": 0.2759666413949962,
"grad_norm": 1.5428311824798584,
"learning_rate": 0.00018441358800701273,
"loss": 0.9792,
"step": 91
},
{
"epoch": 0.2789992418498863,
"grad_norm": 1.3811968564987183,
"learning_rate": 0.00018199494461156203,
"loss": 0.4531,
"step": 92
},
{
"epoch": 0.28203184230477635,
"grad_norm": 1.3926177024841309,
"learning_rate": 0.000179567554117722,
"loss": 0.4052,
"step": 93
},
{
"epoch": 0.2850644427596664,
"grad_norm": 1.544171929359436,
"learning_rate": 0.00017713208014981648,
"loss": 0.5097,
"step": 94
},
{
"epoch": 0.2880970432145565,
"grad_norm": 1.181302547454834,
"learning_rate": 0.00017468918854211007,
"loss": 0.327,
"step": 95
},
{
"epoch": 0.29112964366944655,
"grad_norm": 1.7300562858581543,
"learning_rate": 0.00017223954715677627,
"loss": 0.3545,
"step": 96
},
{
"epoch": 0.2941622441243366,
"grad_norm": 1.378700852394104,
"learning_rate": 0.00016978382570131034,
"loss": 0.2552,
"step": 97
},
{
"epoch": 0.2971948445792267,
"grad_norm": 1.5631200075149536,
"learning_rate": 0.00016732269554543794,
"loss": 0.2897,
"step": 98
},
{
"epoch": 0.30022744503411675,
"grad_norm": 0.8782522678375244,
"learning_rate": 0.00016485682953756942,
"loss": 0.1431,
"step": 99
},
{
"epoch": 0.3032600454890068,
"grad_norm": 2.4966511726379395,
"learning_rate": 0.00016238690182084986,
"loss": 0.5109,
"step": 100
},
{
"epoch": 0.3032600454890068,
"eval_loss": 1.3453013896942139,
"eval_runtime": 1.6367,
"eval_samples_per_second": 30.55,
"eval_steps_per_second": 4.277,
"step": 100
},
{
"epoch": 0.3062926459438969,
"grad_norm": 2.116553544998169,
"learning_rate": 0.0001599135876488549,
"loss": 0.7869,
"step": 101
},
{
"epoch": 0.30932524639878695,
"grad_norm": 1.7891075611114502,
"learning_rate": 0.00015743756320098332,
"loss": 0.6726,
"step": 102
},
{
"epoch": 0.312357846853677,
"grad_norm": 1.2334423065185547,
"learning_rate": 0.0001549595053975962,
"loss": 0.5829,
"step": 103
},
{
"epoch": 0.3153904473085671,
"grad_norm": 1.21792733669281,
"learning_rate": 0.00015248009171495378,
"loss": 0.4098,
"step": 104
},
{
"epoch": 0.31842304776345715,
"grad_norm": 4.549845218658447,
"learning_rate": 0.00015,
"loss": 1.1113,
"step": 105
},
{
"epoch": 0.3214556482183472,
"grad_norm": 2.6019155979156494,
"learning_rate": 0.00014751990828504622,
"loss": 2.0139,
"step": 106
},
{
"epoch": 0.3244882486732373,
"grad_norm": 2.857210159301758,
"learning_rate": 0.00014504049460240375,
"loss": 1.7404,
"step": 107
},
{
"epoch": 0.32752084912812734,
"grad_norm": 2.389359474182129,
"learning_rate": 0.00014256243679901663,
"loss": 1.1878,
"step": 108
},
{
"epoch": 0.3305534495830174,
"grad_norm": 2.0703272819519043,
"learning_rate": 0.00014008641235114508,
"loss": 0.7422,
"step": 109
},
{
"epoch": 0.33358605003790753,
"grad_norm": 2.1270902156829834,
"learning_rate": 0.00013761309817915014,
"loss": 0.8381,
"step": 110
},
{
"epoch": 0.3366186504927976,
"grad_norm": 2.573129415512085,
"learning_rate": 0.00013514317046243058,
"loss": 1.0021,
"step": 111
},
{
"epoch": 0.33965125094768767,
"grad_norm": 2.3638718128204346,
"learning_rate": 0.00013267730445456208,
"loss": 1.0738,
"step": 112
},
{
"epoch": 0.34268385140257773,
"grad_norm": 1.510916829109192,
"learning_rate": 0.00013021617429868963,
"loss": 0.7256,
"step": 113
},
{
"epoch": 0.3457164518574678,
"grad_norm": 1.4690295457839966,
"learning_rate": 0.00012776045284322368,
"loss": 0.3295,
"step": 114
},
{
"epoch": 0.34874905231235787,
"grad_norm": 0.834520161151886,
"learning_rate": 0.00012531081145788987,
"loss": 0.2155,
"step": 115
},
{
"epoch": 0.35178165276724793,
"grad_norm": 0.8141886591911316,
"learning_rate": 0.00012286791985018355,
"loss": 0.1817,
"step": 116
},
{
"epoch": 0.354814253222138,
"grad_norm": 1.3728559017181396,
"learning_rate": 0.00012043244588227796,
"loss": 0.8601,
"step": 117
},
{
"epoch": 0.35784685367702807,
"grad_norm": 2.7137482166290283,
"learning_rate": 0.00011800505538843798,
"loss": 0.7255,
"step": 118
},
{
"epoch": 0.36087945413191813,
"grad_norm": 2.6060287952423096,
"learning_rate": 0.00011558641199298727,
"loss": 0.4437,
"step": 119
},
{
"epoch": 0.3639120545868082,
"grad_norm": 1.514891505241394,
"learning_rate": 0.00011317717692888012,
"loss": 0.3726,
"step": 120
},
{
"epoch": 0.36694465504169826,
"grad_norm": 1.1686081886291504,
"learning_rate": 0.00011077800885692702,
"loss": 0.6103,
"step": 121
},
{
"epoch": 0.36997725549658833,
"grad_norm": 1.221090316772461,
"learning_rate": 0.00010838956368572334,
"loss": 0.8926,
"step": 122
},
{
"epoch": 0.3730098559514784,
"grad_norm": 1.323407530784607,
"learning_rate": 0.0001060124943923303,
"loss": 0.5818,
"step": 123
},
{
"epoch": 0.37604245640636846,
"grad_norm": 0.9954697489738464,
"learning_rate": 0.0001036474508437579,
"loss": 0.5115,
"step": 124
},
{
"epoch": 0.37907505686125853,
"grad_norm": 0.8847994804382324,
"learning_rate": 0.00010129507961929748,
"loss": 0.5309,
"step": 125
},
{
"epoch": 0.37907505686125853,
"eval_loss": 0.8118882775306702,
"eval_runtime": 1.6485,
"eval_samples_per_second": 30.332,
"eval_steps_per_second": 4.246,
"step": 125
},
{
"epoch": 0.3821076573161486,
"grad_norm": 1.0781829357147217,
"learning_rate": 9.895602383375353e-05,
"loss": 1.2797,
"step": 126
},
{
"epoch": 0.38514025777103866,
"grad_norm": 1.266541838645935,
"learning_rate": 9.663092296162251e-05,
"loss": 1.5195,
"step": 127
},
{
"epoch": 0.38817285822592873,
"grad_norm": 1.4716166257858276,
"learning_rate": 9.432041266226686e-05,
"loss": 1.1823,
"step": 128
},
{
"epoch": 0.3912054586808188,
"grad_norm": 1.729562520980835,
"learning_rate": 9.202512460613219e-05,
"loss": 1.2575,
"step": 129
},
{
"epoch": 0.39423805913570886,
"grad_norm": 1.367742896080017,
"learning_rate": 8.97456863020546e-05,
"loss": 1.5417,
"step": 130
},
{
"epoch": 0.39727065959059893,
"grad_norm": 1.3168230056762695,
"learning_rate": 8.748272092570646e-05,
"loss": 1.6111,
"step": 131
},
{
"epoch": 0.400303260045489,
"grad_norm": 1.4090535640716553,
"learning_rate": 8.523684714922608e-05,
"loss": 1.9075,
"step": 132
},
{
"epoch": 0.40333586050037906,
"grad_norm": 1.2242377996444702,
"learning_rate": 8.300867897207903e-05,
"loss": 1.6223,
"step": 133
},
{
"epoch": 0.40636846095526913,
"grad_norm": 1.632868766784668,
"learning_rate": 8.079882555319684e-05,
"loss": 2.0089,
"step": 134
},
{
"epoch": 0.4094010614101592,
"grad_norm": 1.2393670082092285,
"learning_rate": 7.860789104443896e-05,
"loss": 1.9279,
"step": 135
},
{
"epoch": 0.41243366186504926,
"grad_norm": 1.6518961191177368,
"learning_rate": 7.643647442542382e-05,
"loss": 1.5933,
"step": 136
},
{
"epoch": 0.41546626231993933,
"grad_norm": 1.4009312391281128,
"learning_rate": 7.428516933977347e-05,
"loss": 2.0802,
"step": 137
},
{
"epoch": 0.4184988627748294,
"grad_norm": 1.5112993717193604,
"learning_rate": 7.215456393281776e-05,
"loss": 0.7962,
"step": 138
},
{
"epoch": 0.42153146322971946,
"grad_norm": 1.6284480094909668,
"learning_rate": 7.004524069080096e-05,
"loss": 1.1892,
"step": 139
},
{
"epoch": 0.4245640636846095,
"grad_norm": 1.3762167692184448,
"learning_rate": 6.795777628163599e-05,
"loss": 1.1679,
"step": 140
},
{
"epoch": 0.4275966641394996,
"grad_norm": 1.8651918172836304,
"learning_rate": 6.58927413972491e-05,
"loss": 0.6623,
"step": 141
},
{
"epoch": 0.4306292645943897,
"grad_norm": 2.2076892852783203,
"learning_rate": 6.385070059755846e-05,
"loss": 0.5948,
"step": 142
},
{
"epoch": 0.4336618650492798,
"grad_norm": 1.904805064201355,
"learning_rate": 6.183221215612904e-05,
"loss": 0.3524,
"step": 143
},
{
"epoch": 0.43669446550416985,
"grad_norm": 2.0237276554107666,
"learning_rate": 5.983782790754623e-05,
"loss": 0.3425,
"step": 144
},
{
"epoch": 0.4397270659590599,
"grad_norm": 1.636704444885254,
"learning_rate": 5.786809309654982e-05,
"loss": 0.4734,
"step": 145
},
{
"epoch": 0.44275966641395,
"grad_norm": 1.4179580211639404,
"learning_rate": 5.592354622896944e-05,
"loss": 0.2568,
"step": 146
},
{
"epoch": 0.44579226686884005,
"grad_norm": 1.702435851097107,
"learning_rate": 5.40047189245025e-05,
"loss": 0.2547,
"step": 147
},
{
"epoch": 0.4488248673237301,
"grad_norm": 1.4788601398468018,
"learning_rate": 5.211213577137469e-05,
"loss": 0.2914,
"step": 148
},
{
"epoch": 0.4518574677786202,
"grad_norm": 1.5061534643173218,
"learning_rate": 5.024631418292274e-05,
"loss": 0.1883,
"step": 149
},
{
"epoch": 0.45489006823351025,
"grad_norm": 1.25308358669281,
"learning_rate": 4.840776425613886e-05,
"loss": 0.1811,
"step": 150
},
{
"epoch": 0.45489006823351025,
"eval_loss": 0.7496414184570312,
"eval_runtime": 1.6384,
"eval_samples_per_second": 30.517,
"eval_steps_per_second": 4.272,
"step": 150
},
{
"epoch": 0.4579226686884003,
"grad_norm": 1.176184058189392,
"learning_rate": 4.659698863221513e-05,
"loss": 0.3398,
"step": 151
},
{
"epoch": 0.4609552691432904,
"grad_norm": 1.151708960533142,
"learning_rate": 4.481448235912671e-05,
"loss": 0.3601,
"step": 152
},
{
"epoch": 0.46398786959818045,
"grad_norm": 0.974331259727478,
"learning_rate": 4.306073275629044e-05,
"loss": 0.2929,
"step": 153
},
{
"epoch": 0.4670204700530705,
"grad_norm": 0.9359554052352905,
"learning_rate": 4.133621928133665e-05,
"loss": 0.3445,
"step": 154
},
{
"epoch": 0.4700530705079606,
"grad_norm": 2.2175326347351074,
"learning_rate": 3.964141339903026e-05,
"loss": 1.4245,
"step": 155
},
{
"epoch": 0.47308567096285065,
"grad_norm": 1.6879606246948242,
"learning_rate": 3.797677845237696e-05,
"loss": 1.6504,
"step": 156
},
{
"epoch": 0.4761182714177407,
"grad_norm": 1.5661247968673706,
"learning_rate": 3.634276953594982e-05,
"loss": 1.2227,
"step": 157
},
{
"epoch": 0.4791508718726308,
"grad_norm": 1.6378949880599976,
"learning_rate": 3.473983337147118e-05,
"loss": 1.0772,
"step": 158
},
{
"epoch": 0.48218347232752085,
"grad_norm": 1.839331865310669,
"learning_rate": 3.316840818568315e-05,
"loss": 0.6356,
"step": 159
},
{
"epoch": 0.4852160727824109,
"grad_norm": 1.9953904151916504,
"learning_rate": 3.162892359054098e-05,
"loss": 0.6139,
"step": 160
},
{
"epoch": 0.488248673237301,
"grad_norm": 4.8791184425354,
"learning_rate": 3.0121800465761293e-05,
"loss": 0.7722,
"step": 161
},
{
"epoch": 0.49128127369219105,
"grad_norm": 2.2169203758239746,
"learning_rate": 2.8647450843757897e-05,
"loss": 0.757,
"step": 162
},
{
"epoch": 0.4943138741470811,
"grad_norm": 1.8224825859069824,
"learning_rate": 2.7206277796996144e-05,
"loss": 0.8179,
"step": 163
},
{
"epoch": 0.4973464746019712,
"grad_norm": 0.8757375478744507,
"learning_rate": 2.5798675327796993e-05,
"loss": 0.5202,
"step": 164
},
{
"epoch": 0.5003790750568613,
"grad_norm": 0.8012860417366028,
"learning_rate": 2.4425028260620715e-05,
"loss": 0.1801,
"step": 165
},
{
"epoch": 0.5034116755117514,
"grad_norm": 0.6913158297538757,
"learning_rate": 2.3085712136859668e-05,
"loss": 0.2741,
"step": 166
},
{
"epoch": 0.5064442759666414,
"grad_norm": 0.6833317279815674,
"learning_rate": 2.178109311216913e-05,
"loss": 0.2653,
"step": 167
},
{
"epoch": 0.5094768764215315,
"grad_norm": 0.9797353744506836,
"learning_rate": 2.0511527856363912e-05,
"loss": 0.6669,
"step": 168
},
{
"epoch": 0.5125094768764216,
"grad_norm": 2.5909066200256348,
"learning_rate": 1.927736345590839e-05,
"loss": 0.2745,
"step": 169
},
{
"epoch": 0.5155420773313116,
"grad_norm": 2.055574655532837,
"learning_rate": 1.8078937319026654e-05,
"loss": 0.336,
"step": 170
},
{
"epoch": 0.5185746777862017,
"grad_norm": 1.7324495315551758,
"learning_rate": 1.6916577083458228e-05,
"loss": 0.2687,
"step": 171
},
{
"epoch": 0.5216072782410918,
"grad_norm": 0.9579265117645264,
"learning_rate": 1.579060052688548e-05,
"loss": 0.8671,
"step": 172
},
{
"epoch": 0.5246398786959818,
"grad_norm": 0.8632516860961914,
"learning_rate": 1.4701315480056164e-05,
"loss": 0.5554,
"step": 173
},
{
"epoch": 0.5276724791508719,
"grad_norm": 0.8002261519432068,
"learning_rate": 1.3649019742625623e-05,
"loss": 0.5221,
"step": 174
},
{
"epoch": 0.530705079605762,
"grad_norm": 0.9454600811004639,
"learning_rate": 1.2634001001741373e-05,
"loss": 0.7456,
"step": 175
},
{
"epoch": 0.530705079605762,
"eval_loss": 0.7249814867973328,
"eval_runtime": 1.6332,
"eval_samples_per_second": 30.615,
"eval_steps_per_second": 4.286,
"step": 175
},
{
"epoch": 0.533737680060652,
"grad_norm": 0.9941129088401794,
"learning_rate": 1.1656536753392287e-05,
"loss": 1.0431,
"step": 176
},
{
"epoch": 0.5367702805155421,
"grad_norm": 1.2236559391021729,
"learning_rate": 1.0716894226543953e-05,
"loss": 1.7665,
"step": 177
},
{
"epoch": 0.5398028809704322,
"grad_norm": 1.2112020254135132,
"learning_rate": 9.815330310080887e-06,
"loss": 1.407,
"step": 178
},
{
"epoch": 0.5428354814253222,
"grad_norm": 0.9938328266143799,
"learning_rate": 8.952091482575824e-06,
"loss": 1.0979,
"step": 179
},
{
"epoch": 0.5458680818802123,
"grad_norm": 1.114398717880249,
"learning_rate": 8.127413744904804e-06,
"loss": 1.1426,
"step": 180
},
{
"epoch": 0.5489006823351024,
"grad_norm": 1.4169811010360718,
"learning_rate": 7.34152255572697e-06,
"loss": 1.6449,
"step": 181
},
{
"epoch": 0.5519332827899924,
"grad_norm": 1.2509397268295288,
"learning_rate": 6.594632769846353e-06,
"loss": 1.3782,
"step": 182
},
{
"epoch": 0.5549658832448825,
"grad_norm": 1.321242094039917,
"learning_rate": 5.886948579472778e-06,
"loss": 1.46,
"step": 183
},
{
"epoch": 0.5579984836997726,
"grad_norm": 1.6065739393234253,
"learning_rate": 5.218663458397715e-06,
"loss": 2.0705,
"step": 184
},
{
"epoch": 0.5610310841546626,
"grad_norm": 1.637670874595642,
"learning_rate": 4.589960109100444e-06,
"loss": 1.8571,
"step": 185
},
{
"epoch": 0.5640636846095527,
"grad_norm": 1.617815613746643,
"learning_rate": 4.001010412799138e-06,
"loss": 2.0011,
"step": 186
},
{
"epoch": 0.5670962850644428,
"grad_norm": 1.380850911140442,
"learning_rate": 3.451975382460109e-06,
"loss": 1.7508,
"step": 187
},
{
"epoch": 0.5701288855193328,
"grad_norm": 1.7648086547851562,
"learning_rate": 2.9430051187785962e-06,
"loss": 1.2211,
"step": 188
},
{
"epoch": 0.5731614859742229,
"grad_norm": 1.3612362146377563,
"learning_rate": 2.4742387691426445e-06,
"loss": 1.0974,
"step": 189
},
{
"epoch": 0.576194086429113,
"grad_norm": 1.6548246145248413,
"learning_rate": 2.0458044895916513e-06,
"loss": 0.7674,
"step": 190
},
{
"epoch": 0.579226686884003,
"grad_norm": 1.6227363348007202,
"learning_rate": 1.6578194097797258e-06,
"loss": 0.4966,
"step": 191
},
{
"epoch": 0.5822592873388931,
"grad_norm": 2.1612672805786133,
"learning_rate": 1.3103896009537207e-06,
"loss": 0.5805,
"step": 192
},
{
"epoch": 0.5852918877937832,
"grad_norm": 1.482163667678833,
"learning_rate": 1.0036100469542786e-06,
"loss": 0.5068,
"step": 193
},
{
"epoch": 0.5883244882486732,
"grad_norm": 1.0745387077331543,
"learning_rate": 7.375646182482875e-07,
"loss": 0.2758,
"step": 194
},
{
"epoch": 0.5913570887035633,
"grad_norm": 1.2835489511489868,
"learning_rate": 5.123260489995229e-07,
"loss": 0.2952,
"step": 195
},
{
"epoch": 0.5943896891584534,
"grad_norm": 1.2066874504089355,
"learning_rate": 3.2795591718381975e-07,
"loss": 0.2233,
"step": 196
},
{
"epoch": 0.5974222896133434,
"grad_norm": 0.9106021523475647,
"learning_rate": 1.8450462775428942e-07,
"loss": 0.2002,
"step": 197
},
{
"epoch": 0.6004548900682335,
"grad_norm": 1.0497798919677734,
"learning_rate": 8.201139886109264e-08,
"loss": 0.1902,
"step": 198
},
{
"epoch": 0.6034874905231236,
"grad_norm": 0.9898223876953125,
"learning_rate": 2.0504251129649374e-08,
"loss": 0.157,
"step": 199
},
{
"epoch": 0.6065200909780136,
"grad_norm": 0.5523911118507385,
"learning_rate": 0.0,
"loss": 0.0983,
"step": 200
},
{
"epoch": 0.6065200909780136,
"eval_loss": 0.7618037462234497,
"eval_runtime": 1.6354,
"eval_samples_per_second": 30.573,
"eval_steps_per_second": 4.28,
"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": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.128243999100109e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}