0x1202's picture
Training in progress, step 200, checkpoint
8ea24df verified
{
"best_metric": 1.5290954113006592,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.031207333723425004,
"eval_steps": 25,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000156036668617125,
"grad_norm": 0.5206789970397949,
"learning_rate": 2.9999999999999997e-05,
"loss": 1.8396,
"step": 1
},
{
"epoch": 0.000156036668617125,
"eval_loss": 2.0503292083740234,
"eval_runtime": 6.7818,
"eval_samples_per_second": 7.373,
"eval_steps_per_second": 1.032,
"step": 1
},
{
"epoch": 0.00031207333723425,
"grad_norm": 0.7399382591247559,
"learning_rate": 5.9999999999999995e-05,
"loss": 1.9251,
"step": 2
},
{
"epoch": 0.0004681100058513751,
"grad_norm": 0.5232512354850769,
"learning_rate": 8.999999999999999e-05,
"loss": 1.7091,
"step": 3
},
{
"epoch": 0.0006241466744685,
"grad_norm": 0.5939716100692749,
"learning_rate": 0.00011999999999999999,
"loss": 1.6761,
"step": 4
},
{
"epoch": 0.0007801833430856252,
"grad_norm": 0.7300804257392883,
"learning_rate": 0.00015,
"loss": 1.7775,
"step": 5
},
{
"epoch": 0.0009362200117027502,
"grad_norm": 0.8115593194961548,
"learning_rate": 0.00017999999999999998,
"loss": 1.7865,
"step": 6
},
{
"epoch": 0.001092256680319875,
"grad_norm": 0.6184768080711365,
"learning_rate": 0.00020999999999999998,
"loss": 1.6461,
"step": 7
},
{
"epoch": 0.001248293348937,
"grad_norm": 0.5180591940879822,
"learning_rate": 0.00023999999999999998,
"loss": 1.7187,
"step": 8
},
{
"epoch": 0.0014043300175541251,
"grad_norm": 0.7737146019935608,
"learning_rate": 0.00027,
"loss": 1.8294,
"step": 9
},
{
"epoch": 0.0015603666861712503,
"grad_norm": 0.9050935506820679,
"learning_rate": 0.0003,
"loss": 1.7348,
"step": 10
},
{
"epoch": 0.0017164033547883754,
"grad_norm": 0.5098028779029846,
"learning_rate": 0.0002999794957488703,
"loss": 1.8777,
"step": 11
},
{
"epoch": 0.0018724400234055004,
"grad_norm": 0.4907428026199341,
"learning_rate": 0.0002999179886011389,
"loss": 1.8148,
"step": 12
},
{
"epoch": 0.0020284766920226254,
"grad_norm": 0.5255127549171448,
"learning_rate": 0.0002998154953722457,
"loss": 1.5608,
"step": 13
},
{
"epoch": 0.00218451336063975,
"grad_norm": 0.5427423715591431,
"learning_rate": 0.00029967204408281613,
"loss": 1.6659,
"step": 14
},
{
"epoch": 0.0023405500292568754,
"grad_norm": 0.5772568583488464,
"learning_rate": 0.00029948767395100045,
"loss": 1.6073,
"step": 15
},
{
"epoch": 0.002496586697874,
"grad_norm": 0.6227470636367798,
"learning_rate": 0.0002992624353817517,
"loss": 1.6161,
"step": 16
},
{
"epoch": 0.0026526233664911254,
"grad_norm": 0.6405678391456604,
"learning_rate": 0.0002989963899530457,
"loss": 1.4167,
"step": 17
},
{
"epoch": 0.0028086600351082502,
"grad_norm": 0.5659825205802917,
"learning_rate": 0.00029868961039904624,
"loss": 1.5947,
"step": 18
},
{
"epoch": 0.0029646967037253755,
"grad_norm": 0.6382486820220947,
"learning_rate": 0.00029834218059022024,
"loss": 1.5741,
"step": 19
},
{
"epoch": 0.0031207333723425007,
"grad_norm": 0.7297236919403076,
"learning_rate": 0.00029795419551040833,
"loss": 1.4322,
"step": 20
},
{
"epoch": 0.0032767700409596255,
"grad_norm": 0.9750998020172119,
"learning_rate": 0.00029752576123085736,
"loss": 1.5351,
"step": 21
},
{
"epoch": 0.0034328067095767507,
"grad_norm": 0.7237041592597961,
"learning_rate": 0.0002970569948812214,
"loss": 1.3667,
"step": 22
},
{
"epoch": 0.0035888433781938755,
"grad_norm": 0.8494530320167542,
"learning_rate": 0.0002965480246175399,
"loss": 1.3696,
"step": 23
},
{
"epoch": 0.0037448800468110007,
"grad_norm": 0.6190499067306519,
"learning_rate": 0.0002959989895872009,
"loss": 1.3582,
"step": 24
},
{
"epoch": 0.0039009167154281255,
"grad_norm": 0.5850889086723328,
"learning_rate": 0.0002954100398908995,
"loss": 1.3,
"step": 25
},
{
"epoch": 0.0039009167154281255,
"eval_loss": 1.5691899061203003,
"eval_runtime": 6.4984,
"eval_samples_per_second": 7.694,
"eval_steps_per_second": 1.077,
"step": 25
},
{
"epoch": 0.004056953384045251,
"grad_norm": 0.6242693066596985,
"learning_rate": 0.0002947813365416023,
"loss": 1.3132,
"step": 26
},
{
"epoch": 0.004212990052662376,
"grad_norm": 0.5938582420349121,
"learning_rate": 0.0002941130514205272,
"loss": 1.3459,
"step": 27
},
{
"epoch": 0.0043690267212795,
"grad_norm": 0.6085400581359863,
"learning_rate": 0.0002934053672301536,
"loss": 1.4788,
"step": 28
},
{
"epoch": 0.004525063389896626,
"grad_norm": 0.607937753200531,
"learning_rate": 0.00029265847744427303,
"loss": 1.3011,
"step": 29
},
{
"epoch": 0.004681100058513751,
"grad_norm": 0.5721194744110107,
"learning_rate": 0.00029187258625509513,
"loss": 1.2466,
"step": 30
},
{
"epoch": 0.004837136727130876,
"grad_norm": 0.5731037259101868,
"learning_rate": 0.00029104790851742417,
"loss": 1.3303,
"step": 31
},
{
"epoch": 0.004993173395748,
"grad_norm": 0.770770251750946,
"learning_rate": 0.0002901846696899191,
"loss": 1.2681,
"step": 32
},
{
"epoch": 0.005149210064365126,
"grad_norm": 0.6642731428146362,
"learning_rate": 0.00028928310577345606,
"loss": 1.487,
"step": 33
},
{
"epoch": 0.005305246732982251,
"grad_norm": 0.6536151766777039,
"learning_rate": 0.0002883434632466077,
"loss": 1.3857,
"step": 34
},
{
"epoch": 0.005461283401599376,
"grad_norm": 0.6731511950492859,
"learning_rate": 0.00028736599899825856,
"loss": 1.207,
"step": 35
},
{
"epoch": 0.0056173200702165004,
"grad_norm": 0.9541279077529907,
"learning_rate": 0.00028635098025737434,
"loss": 1.3523,
"step": 36
},
{
"epoch": 0.005773356738833626,
"grad_norm": 0.8573929667472839,
"learning_rate": 0.00028529868451994384,
"loss": 1.3116,
"step": 37
},
{
"epoch": 0.005929393407450751,
"grad_norm": 0.8268851637840271,
"learning_rate": 0.0002842093994731145,
"loss": 1.0653,
"step": 38
},
{
"epoch": 0.006085430076067876,
"grad_norm": 0.8396204710006714,
"learning_rate": 0.00028308342291654174,
"loss": 1.1576,
"step": 39
},
{
"epoch": 0.006241466744685001,
"grad_norm": 0.9370057582855225,
"learning_rate": 0.00028192106268097334,
"loss": 1.2128,
"step": 40
},
{
"epoch": 0.006397503413302126,
"grad_norm": 0.9739757776260376,
"learning_rate": 0.00028072263654409154,
"loss": 1.0464,
"step": 41
},
{
"epoch": 0.006553540081919251,
"grad_norm": 1.0366929769515991,
"learning_rate": 0.0002794884721436361,
"loss": 0.931,
"step": 42
},
{
"epoch": 0.006709576750536376,
"grad_norm": 0.8668140769004822,
"learning_rate": 0.00027821890688783083,
"loss": 0.8618,
"step": 43
},
{
"epoch": 0.006865613419153501,
"grad_norm": 1.018534541130066,
"learning_rate": 0.0002769142878631403,
"loss": 0.7347,
"step": 44
},
{
"epoch": 0.007021650087770626,
"grad_norm": 0.9723997712135315,
"learning_rate": 0.00027557497173937923,
"loss": 0.9389,
"step": 45
},
{
"epoch": 0.007177686756387751,
"grad_norm": 1.248196005821228,
"learning_rate": 0.000274201324672203,
"loss": 0.9446,
"step": 46
},
{
"epoch": 0.007333723425004876,
"grad_norm": 1.2594249248504639,
"learning_rate": 0.00027279372220300385,
"loss": 0.904,
"step": 47
},
{
"epoch": 0.0074897600936220015,
"grad_norm": 1.3685013055801392,
"learning_rate": 0.0002713525491562421,
"loss": 0.8496,
"step": 48
},
{
"epoch": 0.007645796762239126,
"grad_norm": 1.558997392654419,
"learning_rate": 0.00026987819953423867,
"loss": 0.7315,
"step": 49
},
{
"epoch": 0.007801833430856251,
"grad_norm": 2.5568363666534424,
"learning_rate": 0.00026837107640945905,
"loss": 0.5887,
"step": 50
},
{
"epoch": 0.007801833430856251,
"eval_loss": 1.7641971111297607,
"eval_runtime": 6.498,
"eval_samples_per_second": 7.695,
"eval_steps_per_second": 1.077,
"step": 50
},
{
"epoch": 0.007957870099473376,
"grad_norm": 1.0979799032211304,
"learning_rate": 0.0002668315918143169,
"loss": 1.9635,
"step": 51
},
{
"epoch": 0.008113906768090502,
"grad_norm": 0.7584168314933777,
"learning_rate": 0.00026526016662852886,
"loss": 1.8387,
"step": 52
},
{
"epoch": 0.008269943436707627,
"grad_norm": 0.4578099846839905,
"learning_rate": 0.00026365723046405023,
"loss": 1.8186,
"step": 53
},
{
"epoch": 0.008425980105324752,
"grad_norm": 0.36827552318573,
"learning_rate": 0.0002620232215476231,
"loss": 1.6531,
"step": 54
},
{
"epoch": 0.008582016773941877,
"grad_norm": 0.37317103147506714,
"learning_rate": 0.0002603585866009697,
"loss": 1.6583,
"step": 55
},
{
"epoch": 0.008738053442559,
"grad_norm": 0.3559889495372772,
"learning_rate": 0.00025866378071866334,
"loss": 1.6362,
"step": 56
},
{
"epoch": 0.008894090111176126,
"grad_norm": 0.43494126200675964,
"learning_rate": 0.00025693926724370956,
"loss": 1.5891,
"step": 57
},
{
"epoch": 0.009050126779793251,
"grad_norm": 0.4401465654373169,
"learning_rate": 0.00025518551764087326,
"loss": 1.7659,
"step": 58
},
{
"epoch": 0.009206163448410376,
"grad_norm": 0.42876479029655457,
"learning_rate": 0.00025340301136778483,
"loss": 1.7553,
"step": 59
},
{
"epoch": 0.009362200117027502,
"grad_norm": 0.40875837206840515,
"learning_rate": 0.00025159223574386114,
"loss": 1.5298,
"step": 60
},
{
"epoch": 0.009518236785644627,
"grad_norm": 0.44727665185928345,
"learning_rate": 0.0002497536858170772,
"loss": 1.6135,
"step": 61
},
{
"epoch": 0.009674273454261752,
"grad_norm": 0.5202199816703796,
"learning_rate": 0.00024788786422862526,
"loss": 1.5425,
"step": 62
},
{
"epoch": 0.009830310122878877,
"grad_norm": 0.49328622221946716,
"learning_rate": 0.00024599528107549745,
"loss": 1.356,
"step": 63
},
{
"epoch": 0.009986346791496,
"grad_norm": 0.5118263363838196,
"learning_rate": 0.00024407645377103054,
"loss": 1.6002,
"step": 64
},
{
"epoch": 0.010142383460113126,
"grad_norm": 0.5199598670005798,
"learning_rate": 0.00024213190690345018,
"loss": 1.6028,
"step": 65
},
{
"epoch": 0.010298420128730251,
"grad_norm": 0.5822303295135498,
"learning_rate": 0.00024016217209245374,
"loss": 1.4667,
"step": 66
},
{
"epoch": 0.010454456797347376,
"grad_norm": 0.4809555113315582,
"learning_rate": 0.00023816778784387094,
"loss": 1.4673,
"step": 67
},
{
"epoch": 0.010610493465964502,
"grad_norm": 0.4947901666164398,
"learning_rate": 0.0002361492994024415,
"loss": 1.4091,
"step": 68
},
{
"epoch": 0.010766530134581627,
"grad_norm": 0.5388864278793335,
"learning_rate": 0.0002341072586027509,
"loss": 1.4656,
"step": 69
},
{
"epoch": 0.010922566803198752,
"grad_norm": 0.6104763150215149,
"learning_rate": 0.00023204222371836405,
"loss": 1.3579,
"step": 70
},
{
"epoch": 0.011078603471815877,
"grad_norm": 0.5101671814918518,
"learning_rate": 0.00022995475930919905,
"loss": 1.3509,
"step": 71
},
{
"epoch": 0.011234640140433001,
"grad_norm": 0.5573173761367798,
"learning_rate": 0.00022784543606718227,
"loss": 1.3699,
"step": 72
},
{
"epoch": 0.011390676809050126,
"grad_norm": 0.5211086869239807,
"learning_rate": 0.00022571483066022657,
"loss": 1.3698,
"step": 73
},
{
"epoch": 0.011546713477667251,
"grad_norm": 0.5853310227394104,
"learning_rate": 0.0002235635255745762,
"loss": 1.5265,
"step": 74
},
{
"epoch": 0.011702750146284377,
"grad_norm": 0.546154797077179,
"learning_rate": 0.00022139210895556104,
"loss": 1.4583,
"step": 75
},
{
"epoch": 0.011702750146284377,
"eval_loss": 1.5641021728515625,
"eval_runtime": 6.4961,
"eval_samples_per_second": 7.697,
"eval_steps_per_second": 1.078,
"step": 75
},
{
"epoch": 0.011858786814901502,
"grad_norm": 0.515069842338562,
"learning_rate": 0.00021920117444680317,
"loss": 1.1777,
"step": 76
},
{
"epoch": 0.012014823483518627,
"grad_norm": 0.5579367280006409,
"learning_rate": 0.00021699132102792097,
"loss": 1.397,
"step": 77
},
{
"epoch": 0.012170860152135752,
"grad_norm": 0.7155484557151794,
"learning_rate": 0.0002147631528507739,
"loss": 1.2808,
"step": 78
},
{
"epoch": 0.012326896820752878,
"grad_norm": 0.6388354301452637,
"learning_rate": 0.00021251727907429355,
"loss": 1.1961,
"step": 79
},
{
"epoch": 0.012482933489370003,
"grad_norm": 0.5787919759750366,
"learning_rate": 0.0002102543136979454,
"loss": 1.2217,
"step": 80
},
{
"epoch": 0.012638970157987126,
"grad_norm": 0.705842912197113,
"learning_rate": 0.0002079748753938678,
"loss": 1.3552,
"step": 81
},
{
"epoch": 0.012795006826604251,
"grad_norm": 0.8084819316864014,
"learning_rate": 0.0002056795873377331,
"loss": 1.402,
"step": 82
},
{
"epoch": 0.012951043495221377,
"grad_norm": 0.8280103802680969,
"learning_rate": 0.00020336907703837748,
"loss": 1.3629,
"step": 83
},
{
"epoch": 0.013107080163838502,
"grad_norm": 0.7781316637992859,
"learning_rate": 0.00020104397616624645,
"loss": 1.2177,
"step": 84
},
{
"epoch": 0.013263116832455627,
"grad_norm": 0.7547453045845032,
"learning_rate": 0.00019870492038070252,
"loss": 1.3175,
"step": 85
},
{
"epoch": 0.013419153501072752,
"grad_norm": 0.7553347945213318,
"learning_rate": 0.0001963525491562421,
"loss": 1.2573,
"step": 86
},
{
"epoch": 0.013575190169689878,
"grad_norm": 0.6961191296577454,
"learning_rate": 0.0001939875056076697,
"loss": 1.3215,
"step": 87
},
{
"epoch": 0.013731226838307003,
"grad_norm": 0.7378870844841003,
"learning_rate": 0.00019161043631427666,
"loss": 1.3076,
"step": 88
},
{
"epoch": 0.013887263506924126,
"grad_norm": 0.7430673241615295,
"learning_rate": 0.00018922199114307294,
"loss": 0.9901,
"step": 89
},
{
"epoch": 0.014043300175541252,
"grad_norm": 0.8039370775222778,
"learning_rate": 0.00018682282307111987,
"loss": 0.9656,
"step": 90
},
{
"epoch": 0.014199336844158377,
"grad_norm": 0.8286400437355042,
"learning_rate": 0.00018441358800701273,
"loss": 1.3207,
"step": 91
},
{
"epoch": 0.014355373512775502,
"grad_norm": 0.8701859712600708,
"learning_rate": 0.00018199494461156203,
"loss": 0.939,
"step": 92
},
{
"epoch": 0.014511410181392627,
"grad_norm": 0.9127413630485535,
"learning_rate": 0.000179567554117722,
"loss": 0.7716,
"step": 93
},
{
"epoch": 0.014667446850009752,
"grad_norm": 0.8500394821166992,
"learning_rate": 0.00017713208014981648,
"loss": 0.82,
"step": 94
},
{
"epoch": 0.014823483518626878,
"grad_norm": 0.8914243578910828,
"learning_rate": 0.00017468918854211007,
"loss": 0.6128,
"step": 95
},
{
"epoch": 0.014979520187244003,
"grad_norm": 1.1174474954605103,
"learning_rate": 0.00017223954715677627,
"loss": 0.6678,
"step": 96
},
{
"epoch": 0.015135556855861128,
"grad_norm": 1.1993595361709595,
"learning_rate": 0.00016978382570131034,
"loss": 0.6074,
"step": 97
},
{
"epoch": 0.015291593524478252,
"grad_norm": 1.4612879753112793,
"learning_rate": 0.00016732269554543794,
"loss": 0.699,
"step": 98
},
{
"epoch": 0.015447630193095377,
"grad_norm": 1.3933491706848145,
"learning_rate": 0.00016485682953756942,
"loss": 0.7587,
"step": 99
},
{
"epoch": 0.015603666861712502,
"grad_norm": 1.3338792324066162,
"learning_rate": 0.00016238690182084986,
"loss": 0.3685,
"step": 100
},
{
"epoch": 0.015603666861712502,
"eval_loss": 1.7297264337539673,
"eval_runtime": 6.4963,
"eval_samples_per_second": 7.697,
"eval_steps_per_second": 1.078,
"step": 100
},
{
"epoch": 0.015759703530329627,
"grad_norm": 1.328065037727356,
"learning_rate": 0.0001599135876488549,
"loss": 1.7923,
"step": 101
},
{
"epoch": 0.015915740198946753,
"grad_norm": 1.02339768409729,
"learning_rate": 0.00015743756320098332,
"loss": 1.9042,
"step": 102
},
{
"epoch": 0.016071776867563878,
"grad_norm": 0.5130980610847473,
"learning_rate": 0.0001549595053975962,
"loss": 1.7668,
"step": 103
},
{
"epoch": 0.016227813536181003,
"grad_norm": 0.37997496128082275,
"learning_rate": 0.00015248009171495378,
"loss": 1.689,
"step": 104
},
{
"epoch": 0.016383850204798128,
"grad_norm": 0.42504414916038513,
"learning_rate": 0.00015,
"loss": 1.529,
"step": 105
},
{
"epoch": 0.016539886873415253,
"grad_norm": 0.328225702047348,
"learning_rate": 0.00014751990828504622,
"loss": 1.3804,
"step": 106
},
{
"epoch": 0.01669592354203238,
"grad_norm": 0.3386905789375305,
"learning_rate": 0.00014504049460240375,
"loss": 1.6091,
"step": 107
},
{
"epoch": 0.016851960210649504,
"grad_norm": 0.33392131328582764,
"learning_rate": 0.00014256243679901663,
"loss": 1.6571,
"step": 108
},
{
"epoch": 0.01700799687926663,
"grad_norm": 0.3345213830471039,
"learning_rate": 0.00014008641235114508,
"loss": 1.594,
"step": 109
},
{
"epoch": 0.017164033547883754,
"grad_norm": 0.37102460861206055,
"learning_rate": 0.00013761309817915014,
"loss": 1.7052,
"step": 110
},
{
"epoch": 0.017320070216500876,
"grad_norm": 0.36494970321655273,
"learning_rate": 0.00013514317046243058,
"loss": 1.5868,
"step": 111
},
{
"epoch": 0.017476106885118,
"grad_norm": 0.36978891491889954,
"learning_rate": 0.00013267730445456208,
"loss": 1.5605,
"step": 112
},
{
"epoch": 0.017632143553735127,
"grad_norm": 0.4322417676448822,
"learning_rate": 0.00013021617429868963,
"loss": 1.5087,
"step": 113
},
{
"epoch": 0.017788180222352252,
"grad_norm": 0.42043352127075195,
"learning_rate": 0.00012776045284322368,
"loss": 1.5209,
"step": 114
},
{
"epoch": 0.017944216890969377,
"grad_norm": 0.47093257308006287,
"learning_rate": 0.00012531081145788987,
"loss": 1.5932,
"step": 115
},
{
"epoch": 0.018100253559586502,
"grad_norm": 0.3943566083908081,
"learning_rate": 0.00012286791985018355,
"loss": 1.5031,
"step": 116
},
{
"epoch": 0.018256290228203628,
"grad_norm": 0.4569840431213379,
"learning_rate": 0.00012043244588227796,
"loss": 1.6201,
"step": 117
},
{
"epoch": 0.018412326896820753,
"grad_norm": 0.3882908225059509,
"learning_rate": 0.00011800505538843798,
"loss": 1.441,
"step": 118
},
{
"epoch": 0.018568363565437878,
"grad_norm": 0.4978281557559967,
"learning_rate": 0.00011558641199298727,
"loss": 1.4181,
"step": 119
},
{
"epoch": 0.018724400234055003,
"grad_norm": 0.4600917100906372,
"learning_rate": 0.00011317717692888012,
"loss": 1.4694,
"step": 120
},
{
"epoch": 0.01888043690267213,
"grad_norm": 0.5189599990844727,
"learning_rate": 0.00011077800885692702,
"loss": 1.4932,
"step": 121
},
{
"epoch": 0.019036473571289254,
"grad_norm": 0.5141446590423584,
"learning_rate": 0.00010838956368572334,
"loss": 1.3281,
"step": 122
},
{
"epoch": 0.01919251023990638,
"grad_norm": 0.5593545436859131,
"learning_rate": 0.0001060124943923303,
"loss": 1.2175,
"step": 123
},
{
"epoch": 0.019348546908523504,
"grad_norm": 0.5619649291038513,
"learning_rate": 0.0001036474508437579,
"loss": 1.3246,
"step": 124
},
{
"epoch": 0.01950458357714063,
"grad_norm": 0.4860003590583801,
"learning_rate": 0.00010129507961929748,
"loss": 1.356,
"step": 125
},
{
"epoch": 0.01950458357714063,
"eval_loss": 1.5037603378295898,
"eval_runtime": 6.4994,
"eval_samples_per_second": 7.693,
"eval_steps_per_second": 1.077,
"step": 125
},
{
"epoch": 0.019660620245757755,
"grad_norm": 0.6618039011955261,
"learning_rate": 9.895602383375353e-05,
"loss": 1.241,
"step": 126
},
{
"epoch": 0.019816656914374876,
"grad_norm": 0.5603771209716797,
"learning_rate": 9.663092296162251e-05,
"loss": 1.3383,
"step": 127
},
{
"epoch": 0.019972693582992,
"grad_norm": 0.5711013078689575,
"learning_rate": 9.432041266226686e-05,
"loss": 1.3882,
"step": 128
},
{
"epoch": 0.020128730251609127,
"grad_norm": 0.5455312132835388,
"learning_rate": 9.202512460613219e-05,
"loss": 1.1994,
"step": 129
},
{
"epoch": 0.020284766920226252,
"grad_norm": 0.5478842854499817,
"learning_rate": 8.97456863020546e-05,
"loss": 1.3298,
"step": 130
},
{
"epoch": 0.020440803588843377,
"grad_norm": 0.612348735332489,
"learning_rate": 8.748272092570646e-05,
"loss": 1.3007,
"step": 131
},
{
"epoch": 0.020596840257460503,
"grad_norm": 0.5542769432067871,
"learning_rate": 8.523684714922608e-05,
"loss": 1.211,
"step": 132
},
{
"epoch": 0.020752876926077628,
"grad_norm": 0.6410621404647827,
"learning_rate": 8.300867897207903e-05,
"loss": 1.3215,
"step": 133
},
{
"epoch": 0.020908913594694753,
"grad_norm": 0.6674242615699768,
"learning_rate": 8.079882555319684e-05,
"loss": 1.3031,
"step": 134
},
{
"epoch": 0.021064950263311878,
"grad_norm": 0.6528021097183228,
"learning_rate": 7.860789104443896e-05,
"loss": 1.3276,
"step": 135
},
{
"epoch": 0.021220986931929003,
"grad_norm": 0.7368160486221313,
"learning_rate": 7.643647442542382e-05,
"loss": 1.2318,
"step": 136
},
{
"epoch": 0.02137702360054613,
"grad_norm": 0.7098979949951172,
"learning_rate": 7.428516933977347e-05,
"loss": 1.3272,
"step": 137
},
{
"epoch": 0.021533060269163254,
"grad_norm": 0.680216908454895,
"learning_rate": 7.215456393281776e-05,
"loss": 1.2541,
"step": 138
},
{
"epoch": 0.02168909693778038,
"grad_norm": 0.7274788618087769,
"learning_rate": 7.004524069080096e-05,
"loss": 1.0468,
"step": 139
},
{
"epoch": 0.021845133606397504,
"grad_norm": 0.7748696804046631,
"learning_rate": 6.795777628163599e-05,
"loss": 1.0636,
"step": 140
},
{
"epoch": 0.02200117027501463,
"grad_norm": 0.6825678944587708,
"learning_rate": 6.58927413972491e-05,
"loss": 0.9245,
"step": 141
},
{
"epoch": 0.022157206943631755,
"grad_norm": 0.7998738884925842,
"learning_rate": 6.385070059755846e-05,
"loss": 0.9596,
"step": 142
},
{
"epoch": 0.02231324361224888,
"grad_norm": 0.7875250577926636,
"learning_rate": 6.183221215612904e-05,
"loss": 0.9371,
"step": 143
},
{
"epoch": 0.022469280280866002,
"grad_norm": 0.9212265610694885,
"learning_rate": 5.983782790754623e-05,
"loss": 0.721,
"step": 144
},
{
"epoch": 0.022625316949483127,
"grad_norm": 0.8048818111419678,
"learning_rate": 5.786809309654982e-05,
"loss": 0.7062,
"step": 145
},
{
"epoch": 0.022781353618100252,
"grad_norm": 1.0022319555282593,
"learning_rate": 5.592354622896944e-05,
"loss": 0.6178,
"step": 146
},
{
"epoch": 0.022937390286717377,
"grad_norm": 0.9216979742050171,
"learning_rate": 5.40047189245025e-05,
"loss": 0.7871,
"step": 147
},
{
"epoch": 0.023093426955334503,
"grad_norm": 1.163275957107544,
"learning_rate": 5.211213577137469e-05,
"loss": 0.5207,
"step": 148
},
{
"epoch": 0.023249463623951628,
"grad_norm": 1.1899170875549316,
"learning_rate": 5.024631418292274e-05,
"loss": 0.751,
"step": 149
},
{
"epoch": 0.023405500292568753,
"grad_norm": 1.1365642547607422,
"learning_rate": 4.840776425613886e-05,
"loss": 0.4787,
"step": 150
},
{
"epoch": 0.023405500292568753,
"eval_loss": 1.557321310043335,
"eval_runtime": 6.503,
"eval_samples_per_second": 7.689,
"eval_steps_per_second": 1.076,
"step": 150
},
{
"epoch": 0.02356153696118588,
"grad_norm": 0.5859889984130859,
"learning_rate": 4.659698863221513e-05,
"loss": 1.7292,
"step": 151
},
{
"epoch": 0.023717573629803004,
"grad_norm": 0.656622052192688,
"learning_rate": 4.481448235912671e-05,
"loss": 1.7476,
"step": 152
},
{
"epoch": 0.02387361029842013,
"grad_norm": 0.6881511211395264,
"learning_rate": 4.306073275629044e-05,
"loss": 1.7677,
"step": 153
},
{
"epoch": 0.024029646967037254,
"grad_norm": 0.6253818273544312,
"learning_rate": 4.133621928133665e-05,
"loss": 1.7196,
"step": 154
},
{
"epoch": 0.02418568363565438,
"grad_norm": 0.5701533555984497,
"learning_rate": 3.964141339903026e-05,
"loss": 1.6054,
"step": 155
},
{
"epoch": 0.024341720304271505,
"grad_norm": 0.5354744791984558,
"learning_rate": 3.797677845237696e-05,
"loss": 1.5034,
"step": 156
},
{
"epoch": 0.02449775697288863,
"grad_norm": 0.49688154458999634,
"learning_rate": 3.634276953594982e-05,
"loss": 1.5255,
"step": 157
},
{
"epoch": 0.024653793641505755,
"grad_norm": 0.4480415880680084,
"learning_rate": 3.473983337147118e-05,
"loss": 1.5067,
"step": 158
},
{
"epoch": 0.02480983031012288,
"grad_norm": 0.4377897083759308,
"learning_rate": 3.316840818568315e-05,
"loss": 1.5721,
"step": 159
},
{
"epoch": 0.024965866978740005,
"grad_norm": 0.3571188151836395,
"learning_rate": 3.162892359054098e-05,
"loss": 1.6277,
"step": 160
},
{
"epoch": 0.025121903647357127,
"grad_norm": 0.37341997027397156,
"learning_rate": 3.0121800465761293e-05,
"loss": 1.4792,
"step": 161
},
{
"epoch": 0.025277940315974252,
"grad_norm": 0.39306336641311646,
"learning_rate": 2.8647450843757897e-05,
"loss": 1.4616,
"step": 162
},
{
"epoch": 0.025433976984591378,
"grad_norm": 0.3912915885448456,
"learning_rate": 2.7206277796996144e-05,
"loss": 1.5334,
"step": 163
},
{
"epoch": 0.025590013653208503,
"grad_norm": 0.42898595333099365,
"learning_rate": 2.5798675327796993e-05,
"loss": 1.5016,
"step": 164
},
{
"epoch": 0.025746050321825628,
"grad_norm": 0.434622198343277,
"learning_rate": 2.4425028260620715e-05,
"loss": 1.4769,
"step": 165
},
{
"epoch": 0.025902086990442753,
"grad_norm": 0.4403606057167053,
"learning_rate": 2.3085712136859668e-05,
"loss": 1.5076,
"step": 166
},
{
"epoch": 0.02605812365905988,
"grad_norm": 0.46792277693748474,
"learning_rate": 2.178109311216913e-05,
"loss": 1.4455,
"step": 167
},
{
"epoch": 0.026214160327677004,
"grad_norm": 0.4654604196548462,
"learning_rate": 2.0511527856363912e-05,
"loss": 1.444,
"step": 168
},
{
"epoch": 0.02637019699629413,
"grad_norm": 0.4601731598377228,
"learning_rate": 1.927736345590839e-05,
"loss": 1.414,
"step": 169
},
{
"epoch": 0.026526233664911254,
"grad_norm": 0.4720068871974945,
"learning_rate": 1.8078937319026654e-05,
"loss": 1.4869,
"step": 170
},
{
"epoch": 0.02668227033352838,
"grad_norm": 0.4721430540084839,
"learning_rate": 1.6916577083458228e-05,
"loss": 1.2791,
"step": 171
},
{
"epoch": 0.026838307002145505,
"grad_norm": 0.5119891166687012,
"learning_rate": 1.579060052688548e-05,
"loss": 1.2617,
"step": 172
},
{
"epoch": 0.02699434367076263,
"grad_norm": 0.49588125944137573,
"learning_rate": 1.4701315480056164e-05,
"loss": 1.3435,
"step": 173
},
{
"epoch": 0.027150380339379755,
"grad_norm": 0.5493288636207581,
"learning_rate": 1.3649019742625623e-05,
"loss": 1.3911,
"step": 174
},
{
"epoch": 0.02730641700799688,
"grad_norm": 0.5632110238075256,
"learning_rate": 1.2634001001741373e-05,
"loss": 1.3135,
"step": 175
},
{
"epoch": 0.02730641700799688,
"eval_loss": 1.5039618015289307,
"eval_runtime": 6.5029,
"eval_samples_per_second": 7.689,
"eval_steps_per_second": 1.076,
"step": 175
},
{
"epoch": 0.027462453676614006,
"grad_norm": 0.5210285186767578,
"learning_rate": 1.1656536753392287e-05,
"loss": 1.3026,
"step": 176
},
{
"epoch": 0.02761849034523113,
"grad_norm": 0.5027701258659363,
"learning_rate": 1.0716894226543953e-05,
"loss": 1.3384,
"step": 177
},
{
"epoch": 0.027774527013848253,
"grad_norm": 0.5866262316703796,
"learning_rate": 9.815330310080887e-06,
"loss": 1.2597,
"step": 178
},
{
"epoch": 0.027930563682465378,
"grad_norm": 0.562569797039032,
"learning_rate": 8.952091482575824e-06,
"loss": 1.1673,
"step": 179
},
{
"epoch": 0.028086600351082503,
"grad_norm": 0.5758312344551086,
"learning_rate": 8.127413744904804e-06,
"loss": 1.2673,
"step": 180
},
{
"epoch": 0.02824263701969963,
"grad_norm": 0.630527138710022,
"learning_rate": 7.34152255572697e-06,
"loss": 1.1333,
"step": 181
},
{
"epoch": 0.028398673688316754,
"grad_norm": 0.6306747198104858,
"learning_rate": 6.594632769846353e-06,
"loss": 1.1823,
"step": 182
},
{
"epoch": 0.02855471035693388,
"grad_norm": 0.6545823812484741,
"learning_rate": 5.886948579472778e-06,
"loss": 1.2942,
"step": 183
},
{
"epoch": 0.028710747025551004,
"grad_norm": 0.5893822908401489,
"learning_rate": 5.218663458397715e-06,
"loss": 1.3816,
"step": 184
},
{
"epoch": 0.02886678369416813,
"grad_norm": 0.7559957504272461,
"learning_rate": 4.589960109100444e-06,
"loss": 1.2344,
"step": 185
},
{
"epoch": 0.029022820362785254,
"grad_norm": 0.6677363514900208,
"learning_rate": 4.001010412799138e-06,
"loss": 1.187,
"step": 186
},
{
"epoch": 0.02917885703140238,
"grad_norm": 0.6518210768699646,
"learning_rate": 3.451975382460109e-06,
"loss": 1.41,
"step": 187
},
{
"epoch": 0.029334893700019505,
"grad_norm": 1.0715693235397339,
"learning_rate": 2.9430051187785962e-06,
"loss": 1.3782,
"step": 188
},
{
"epoch": 0.02949093036863663,
"grad_norm": 0.708122193813324,
"learning_rate": 2.4742387691426445e-06,
"loss": 1.209,
"step": 189
},
{
"epoch": 0.029646967037253755,
"grad_norm": 0.8036530017852783,
"learning_rate": 2.0458044895916513e-06,
"loss": 1.1901,
"step": 190
},
{
"epoch": 0.02980300370587088,
"grad_norm": 0.7544365525245667,
"learning_rate": 1.6578194097797258e-06,
"loss": 0.9051,
"step": 191
},
{
"epoch": 0.029959040374488006,
"grad_norm": 1.1027196645736694,
"learning_rate": 1.3103896009537207e-06,
"loss": 0.932,
"step": 192
},
{
"epoch": 0.03011507704310513,
"grad_norm": 0.9608900547027588,
"learning_rate": 1.0036100469542786e-06,
"loss": 0.8063,
"step": 193
},
{
"epoch": 0.030271113711722256,
"grad_norm": 1.1689194440841675,
"learning_rate": 7.375646182482875e-07,
"loss": 0.7448,
"step": 194
},
{
"epoch": 0.030427150380339378,
"grad_norm": 0.760318398475647,
"learning_rate": 5.123260489995229e-07,
"loss": 0.5065,
"step": 195
},
{
"epoch": 0.030583187048956503,
"grad_norm": 1.0544284582138062,
"learning_rate": 3.2795591718381975e-07,
"loss": 0.6788,
"step": 196
},
{
"epoch": 0.03073922371757363,
"grad_norm": 0.9339509606361389,
"learning_rate": 1.8450462775428942e-07,
"loss": 0.583,
"step": 197
},
{
"epoch": 0.030895260386190754,
"grad_norm": 1.0725435018539429,
"learning_rate": 8.201139886109264e-08,
"loss": 0.6384,
"step": 198
},
{
"epoch": 0.03105129705480788,
"grad_norm": 1.464563012123108,
"learning_rate": 2.0504251129649374e-08,
"loss": 0.6107,
"step": 199
},
{
"epoch": 0.031207333723425004,
"grad_norm": 1.159019947052002,
"learning_rate": 0.0,
"loss": 0.4967,
"step": 200
},
{
"epoch": 0.031207333723425004,
"eval_loss": 1.5290954113006592,
"eval_runtime": 6.5031,
"eval_samples_per_second": 7.689,
"eval_steps_per_second": 1.076,
"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": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.153020955131904e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}