farmery's picture
Training in progress, step 200, checkpoint
b1cde46 verified
{
"best_metric": 1.2190457582473755,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.22566995768688294,
"eval_steps": 25,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0011283497884344146,
"grad_norm": 2.329026222229004,
"learning_rate": 2.9999999999999997e-05,
"loss": 7.8327,
"step": 1
},
{
"epoch": 0.0011283497884344146,
"eval_loss": 1.8493825197219849,
"eval_runtime": 0.927,
"eval_samples_per_second": 53.939,
"eval_steps_per_second": 2.158,
"step": 1
},
{
"epoch": 0.002256699576868829,
"grad_norm": 2.3431859016418457,
"learning_rate": 5.9999999999999995e-05,
"loss": 8.1595,
"step": 2
},
{
"epoch": 0.003385049365303244,
"grad_norm": 2.081698179244995,
"learning_rate": 8.999999999999999e-05,
"loss": 8.0671,
"step": 3
},
{
"epoch": 0.004513399153737658,
"grad_norm": 2.0647974014282227,
"learning_rate": 0.00011999999999999999,
"loss": 7.9456,
"step": 4
},
{
"epoch": 0.005641748942172073,
"grad_norm": 2.0253243446350098,
"learning_rate": 0.00015,
"loss": 7.8193,
"step": 5
},
{
"epoch": 0.006770098730606488,
"grad_norm": 1.4307833909988403,
"learning_rate": 0.00017999999999999998,
"loss": 7.4121,
"step": 6
},
{
"epoch": 0.007898448519040903,
"grad_norm": 1.0701168775558472,
"learning_rate": 0.00020999999999999998,
"loss": 6.8897,
"step": 7
},
{
"epoch": 0.009026798307475317,
"grad_norm": 1.9487756490707397,
"learning_rate": 0.00023999999999999998,
"loss": 6.466,
"step": 8
},
{
"epoch": 0.010155148095909733,
"grad_norm": 1.9409021139144897,
"learning_rate": 0.00027,
"loss": 6.9887,
"step": 9
},
{
"epoch": 0.011283497884344146,
"grad_norm": 1.6208417415618896,
"learning_rate": 0.0003,
"loss": 6.8313,
"step": 10
},
{
"epoch": 0.012411847672778562,
"grad_norm": 1.7929236888885498,
"learning_rate": 0.0002999794957488703,
"loss": 5.9184,
"step": 11
},
{
"epoch": 0.013540197461212976,
"grad_norm": 1.67026948928833,
"learning_rate": 0.0002999179886011389,
"loss": 5.341,
"step": 12
},
{
"epoch": 0.01466854724964739,
"grad_norm": 2.5940780639648438,
"learning_rate": 0.0002998154953722457,
"loss": 6.6078,
"step": 13
},
{
"epoch": 0.015796897038081806,
"grad_norm": 3.121809244155884,
"learning_rate": 0.00029967204408281613,
"loss": 7.5101,
"step": 14
},
{
"epoch": 0.01692524682651622,
"grad_norm": 2.4316179752349854,
"learning_rate": 0.00029948767395100045,
"loss": 7.2457,
"step": 15
},
{
"epoch": 0.018053596614950634,
"grad_norm": 1.3626655340194702,
"learning_rate": 0.0002992624353817517,
"loss": 7.0315,
"step": 16
},
{
"epoch": 0.01918194640338505,
"grad_norm": 0.8948074579238892,
"learning_rate": 0.0002989963899530457,
"loss": 6.9543,
"step": 17
},
{
"epoch": 0.020310296191819465,
"grad_norm": 0.7801365852355957,
"learning_rate": 0.00029868961039904624,
"loss": 6.8188,
"step": 18
},
{
"epoch": 0.021438645980253877,
"grad_norm": 0.722312331199646,
"learning_rate": 0.00029834218059022024,
"loss": 6.3831,
"step": 19
},
{
"epoch": 0.022566995768688293,
"grad_norm": 0.7751977443695068,
"learning_rate": 0.00029795419551040833,
"loss": 6.0422,
"step": 20
},
{
"epoch": 0.02369534555712271,
"grad_norm": 0.9843526482582092,
"learning_rate": 0.00029752576123085736,
"loss": 6.1225,
"step": 21
},
{
"epoch": 0.024823695345557124,
"grad_norm": 1.2983520030975342,
"learning_rate": 0.0002970569948812214,
"loss": 6.8024,
"step": 22
},
{
"epoch": 0.025952045133991537,
"grad_norm": 1.4247089624404907,
"learning_rate": 0.0002965480246175399,
"loss": 5.2116,
"step": 23
},
{
"epoch": 0.027080394922425952,
"grad_norm": 1.7652044296264648,
"learning_rate": 0.0002959989895872009,
"loss": 5.3744,
"step": 24
},
{
"epoch": 0.028208744710860368,
"grad_norm": 2.102250814437866,
"learning_rate": 0.0002954100398908995,
"loss": 5.219,
"step": 25
},
{
"epoch": 0.028208744710860368,
"eval_loss": 1.5778019428253174,
"eval_runtime": 0.9244,
"eval_samples_per_second": 54.086,
"eval_steps_per_second": 2.163,
"step": 25
},
{
"epoch": 0.02933709449929478,
"grad_norm": 1.2431399822235107,
"learning_rate": 0.0002947813365416023,
"loss": 6.5458,
"step": 26
},
{
"epoch": 0.030465444287729196,
"grad_norm": 1.3730992078781128,
"learning_rate": 0.0002941130514205272,
"loss": 6.7832,
"step": 27
},
{
"epoch": 0.03159379407616361,
"grad_norm": 1.315158486366272,
"learning_rate": 0.0002934053672301536,
"loss": 6.6666,
"step": 28
},
{
"epoch": 0.03272214386459803,
"grad_norm": 1.163815975189209,
"learning_rate": 0.00029265847744427303,
"loss": 6.3753,
"step": 29
},
{
"epoch": 0.03385049365303244,
"grad_norm": 1.0512897968292236,
"learning_rate": 0.00029187258625509513,
"loss": 6.4854,
"step": 30
},
{
"epoch": 0.03497884344146685,
"grad_norm": 0.9329174757003784,
"learning_rate": 0.00029104790851742417,
"loss": 6.0975,
"step": 31
},
{
"epoch": 0.03610719322990127,
"grad_norm": 0.9194326400756836,
"learning_rate": 0.0002901846696899191,
"loss": 5.8655,
"step": 32
},
{
"epoch": 0.03723554301833568,
"grad_norm": 0.8717550039291382,
"learning_rate": 0.00028928310577345606,
"loss": 5.5092,
"step": 33
},
{
"epoch": 0.0383638928067701,
"grad_norm": 1.0720285177230835,
"learning_rate": 0.0002883434632466077,
"loss": 5.8958,
"step": 34
},
{
"epoch": 0.039492242595204514,
"grad_norm": 1.364632487297058,
"learning_rate": 0.00028736599899825856,
"loss": 5.5699,
"step": 35
},
{
"epoch": 0.04062059238363893,
"grad_norm": 1.5736411809921265,
"learning_rate": 0.00028635098025737434,
"loss": 4.9146,
"step": 36
},
{
"epoch": 0.041748942172073346,
"grad_norm": 2.038267135620117,
"learning_rate": 0.00028529868451994384,
"loss": 4.5817,
"step": 37
},
{
"epoch": 0.042877291960507755,
"grad_norm": 2.09726619720459,
"learning_rate": 0.0002842093994731145,
"loss": 5.7581,
"step": 38
},
{
"epoch": 0.04400564174894217,
"grad_norm": 1.095707654953003,
"learning_rate": 0.00028308342291654174,
"loss": 6.2337,
"step": 39
},
{
"epoch": 0.045133991537376586,
"grad_norm": 1.0019348859786987,
"learning_rate": 0.00028192106268097334,
"loss": 6.3296,
"step": 40
},
{
"epoch": 0.046262341325811,
"grad_norm": 0.9030014276504517,
"learning_rate": 0.00028072263654409154,
"loss": 6.402,
"step": 41
},
{
"epoch": 0.04739069111424542,
"grad_norm": 0.8619905114173889,
"learning_rate": 0.0002794884721436361,
"loss": 6.2695,
"step": 42
},
{
"epoch": 0.04851904090267983,
"grad_norm": 0.8936153054237366,
"learning_rate": 0.00027821890688783083,
"loss": 6.0026,
"step": 43
},
{
"epoch": 0.04964739069111425,
"grad_norm": 0.9484244585037231,
"learning_rate": 0.0002769142878631403,
"loss": 5.6795,
"step": 44
},
{
"epoch": 0.05077574047954866,
"grad_norm": 0.9728612899780273,
"learning_rate": 0.00027557497173937923,
"loss": 5.4194,
"step": 45
},
{
"epoch": 0.05190409026798307,
"grad_norm": 1.0981996059417725,
"learning_rate": 0.000274201324672203,
"loss": 5.4014,
"step": 46
},
{
"epoch": 0.05303244005641749,
"grad_norm": 1.1872891187667847,
"learning_rate": 0.00027279372220300385,
"loss": 5.7736,
"step": 47
},
{
"epoch": 0.054160789844851905,
"grad_norm": 1.309627890586853,
"learning_rate": 0.0002713525491562421,
"loss": 5.0138,
"step": 48
},
{
"epoch": 0.05528913963328632,
"grad_norm": 1.4937684535980225,
"learning_rate": 0.00026987819953423867,
"loss": 4.3466,
"step": 49
},
{
"epoch": 0.056417489421720736,
"grad_norm": 2.226705551147461,
"learning_rate": 0.00026837107640945905,
"loss": 4.4268,
"step": 50
},
{
"epoch": 0.056417489421720736,
"eval_loss": 1.4124763011932373,
"eval_runtime": 0.9265,
"eval_samples_per_second": 53.969,
"eval_steps_per_second": 2.159,
"step": 50
},
{
"epoch": 0.057545839210155145,
"grad_norm": 1.2287338972091675,
"learning_rate": 0.0002668315918143169,
"loss": 5.9483,
"step": 51
},
{
"epoch": 0.05867418899858956,
"grad_norm": 1.1035747528076172,
"learning_rate": 0.00026526016662852886,
"loss": 5.8749,
"step": 52
},
{
"epoch": 0.059802538787023976,
"grad_norm": 1.0043808221817017,
"learning_rate": 0.00026365723046405023,
"loss": 6.175,
"step": 53
},
{
"epoch": 0.06093088857545839,
"grad_norm": 0.926740825176239,
"learning_rate": 0.0002620232215476231,
"loss": 5.9433,
"step": 54
},
{
"epoch": 0.06205923836389281,
"grad_norm": 0.9313489198684692,
"learning_rate": 0.0002603585866009697,
"loss": 5.6321,
"step": 55
},
{
"epoch": 0.06318758815232722,
"grad_norm": 0.964909017086029,
"learning_rate": 0.00025866378071866334,
"loss": 5.5165,
"step": 56
},
{
"epoch": 0.06431593794076164,
"grad_norm": 1.0046005249023438,
"learning_rate": 0.00025693926724370956,
"loss": 5.192,
"step": 57
},
{
"epoch": 0.06544428772919605,
"grad_norm": 1.0198701620101929,
"learning_rate": 0.00025518551764087326,
"loss": 5.2003,
"step": 58
},
{
"epoch": 0.06657263751763047,
"grad_norm": 1.121709942817688,
"learning_rate": 0.00025340301136778483,
"loss": 5.3789,
"step": 59
},
{
"epoch": 0.06770098730606489,
"grad_norm": 1.2831264734268188,
"learning_rate": 0.00025159223574386114,
"loss": 4.9242,
"step": 60
},
{
"epoch": 0.0688293370944993,
"grad_norm": 1.6610859632492065,
"learning_rate": 0.0002497536858170772,
"loss": 4.4988,
"step": 61
},
{
"epoch": 0.0699576868829337,
"grad_norm": 1.9437819719314575,
"learning_rate": 0.00024788786422862526,
"loss": 4.6885,
"step": 62
},
{
"epoch": 0.07108603667136812,
"grad_norm": 1.6009527444839478,
"learning_rate": 0.00024599528107549745,
"loss": 4.855,
"step": 63
},
{
"epoch": 0.07221438645980253,
"grad_norm": 1.137581706047058,
"learning_rate": 0.00024407645377103054,
"loss": 6.0198,
"step": 64
},
{
"epoch": 0.07334273624823695,
"grad_norm": 1.0899896621704102,
"learning_rate": 0.00024213190690345018,
"loss": 5.977,
"step": 65
},
{
"epoch": 0.07447108603667137,
"grad_norm": 0.9216344952583313,
"learning_rate": 0.00024016217209245374,
"loss": 6.1254,
"step": 66
},
{
"epoch": 0.07559943582510578,
"grad_norm": 0.9301073551177979,
"learning_rate": 0.00023816778784387094,
"loss": 5.8078,
"step": 67
},
{
"epoch": 0.0767277856135402,
"grad_norm": 1.0301451683044434,
"learning_rate": 0.0002361492994024415,
"loss": 5.5032,
"step": 68
},
{
"epoch": 0.07785613540197461,
"grad_norm": 1.0664621591567993,
"learning_rate": 0.0002341072586027509,
"loss": 5.1622,
"step": 69
},
{
"epoch": 0.07898448519040903,
"grad_norm": 1.1214557886123657,
"learning_rate": 0.00023204222371836405,
"loss": 4.8582,
"step": 70
},
{
"epoch": 0.08011283497884344,
"grad_norm": 1.042541265487671,
"learning_rate": 0.00022995475930919905,
"loss": 5.163,
"step": 71
},
{
"epoch": 0.08124118476727786,
"grad_norm": 1.1517643928527832,
"learning_rate": 0.00022784543606718227,
"loss": 5.0302,
"step": 72
},
{
"epoch": 0.08236953455571228,
"grad_norm": 1.358541488647461,
"learning_rate": 0.00022571483066022657,
"loss": 4.503,
"step": 73
},
{
"epoch": 0.08349788434414669,
"grad_norm": 1.5903517007827759,
"learning_rate": 0.0002235635255745762,
"loss": 4.1238,
"step": 74
},
{
"epoch": 0.0846262341325811,
"grad_norm": 2.215933084487915,
"learning_rate": 0.00022139210895556104,
"loss": 3.9516,
"step": 75
},
{
"epoch": 0.0846262341325811,
"eval_loss": 1.3470396995544434,
"eval_runtime": 0.9257,
"eval_samples_per_second": 54.012,
"eval_steps_per_second": 2.16,
"step": 75
},
{
"epoch": 0.08575458392101551,
"grad_norm": 1.2224204540252686,
"learning_rate": 0.00021920117444680317,
"loss": 5.5739,
"step": 76
},
{
"epoch": 0.08688293370944992,
"grad_norm": 1.1212488412857056,
"learning_rate": 0.00021699132102792097,
"loss": 5.4021,
"step": 77
},
{
"epoch": 0.08801128349788434,
"grad_norm": 1.0278078317642212,
"learning_rate": 0.0002147631528507739,
"loss": 5.8151,
"step": 78
},
{
"epoch": 0.08913963328631876,
"grad_norm": 0.9422174096107483,
"learning_rate": 0.00021251727907429355,
"loss": 5.7255,
"step": 79
},
{
"epoch": 0.09026798307475317,
"grad_norm": 1.0370837450027466,
"learning_rate": 0.0002102543136979454,
"loss": 5.2729,
"step": 80
},
{
"epoch": 0.09139633286318759,
"grad_norm": 1.12079918384552,
"learning_rate": 0.0002079748753938678,
"loss": 5.1387,
"step": 81
},
{
"epoch": 0.092524682651622,
"grad_norm": 1.1317256689071655,
"learning_rate": 0.0002056795873377331,
"loss": 5.0309,
"step": 82
},
{
"epoch": 0.09365303244005642,
"grad_norm": 1.006131649017334,
"learning_rate": 0.00020336907703837748,
"loss": 4.8928,
"step": 83
},
{
"epoch": 0.09478138222849083,
"grad_norm": 1.1238933801651,
"learning_rate": 0.00020104397616624645,
"loss": 5.1017,
"step": 84
},
{
"epoch": 0.09590973201692525,
"grad_norm": 1.30240797996521,
"learning_rate": 0.00019870492038070252,
"loss": 4.7929,
"step": 85
},
{
"epoch": 0.09703808180535967,
"grad_norm": 1.6435626745224,
"learning_rate": 0.0001963525491562421,
"loss": 4.5584,
"step": 86
},
{
"epoch": 0.09816643159379408,
"grad_norm": 1.8906351327896118,
"learning_rate": 0.0001939875056076697,
"loss": 3.7898,
"step": 87
},
{
"epoch": 0.0992947813822285,
"grad_norm": 1.7762223482131958,
"learning_rate": 0.00019161043631427666,
"loss": 4.8659,
"step": 88
},
{
"epoch": 0.1004231311706629,
"grad_norm": 1.1541883945465088,
"learning_rate": 0.00018922199114307294,
"loss": 5.3855,
"step": 89
},
{
"epoch": 0.10155148095909731,
"grad_norm": 1.1469545364379883,
"learning_rate": 0.00018682282307111987,
"loss": 5.462,
"step": 90
},
{
"epoch": 0.10267983074753173,
"grad_norm": 1.036082148551941,
"learning_rate": 0.00018441358800701273,
"loss": 5.8985,
"step": 91
},
{
"epoch": 0.10380818053596615,
"grad_norm": 0.9811453223228455,
"learning_rate": 0.00018199494461156203,
"loss": 5.5648,
"step": 92
},
{
"epoch": 0.10493653032440056,
"grad_norm": 1.0189131498336792,
"learning_rate": 0.000179567554117722,
"loss": 5.392,
"step": 93
},
{
"epoch": 0.10606488011283498,
"grad_norm": 1.0800825357437134,
"learning_rate": 0.00017713208014981648,
"loss": 5.1397,
"step": 94
},
{
"epoch": 0.1071932299012694,
"grad_norm": 1.1241695880889893,
"learning_rate": 0.00017468918854211007,
"loss": 5.2695,
"step": 95
},
{
"epoch": 0.10832157968970381,
"grad_norm": 1.098168969154358,
"learning_rate": 0.00017223954715677627,
"loss": 4.5699,
"step": 96
},
{
"epoch": 0.10944992947813822,
"grad_norm": 1.2497047185897827,
"learning_rate": 0.00016978382570131034,
"loss": 5.117,
"step": 97
},
{
"epoch": 0.11057827926657264,
"grad_norm": 1.505915880203247,
"learning_rate": 0.00016732269554543794,
"loss": 4.4247,
"step": 98
},
{
"epoch": 0.11170662905500706,
"grad_norm": 1.8070659637451172,
"learning_rate": 0.00016485682953756942,
"loss": 4.113,
"step": 99
},
{
"epoch": 0.11283497884344147,
"grad_norm": 2.4373724460601807,
"learning_rate": 0.00016238690182084986,
"loss": 4.1036,
"step": 100
},
{
"epoch": 0.11283497884344147,
"eval_loss": 1.3125555515289307,
"eval_runtime": 0.9275,
"eval_samples_per_second": 53.907,
"eval_steps_per_second": 2.156,
"step": 100
},
{
"epoch": 0.11396332863187589,
"grad_norm": 0.9204098582267761,
"learning_rate": 0.0001599135876488549,
"loss": 5.2458,
"step": 101
},
{
"epoch": 0.11509167842031029,
"grad_norm": 0.9850059747695923,
"learning_rate": 0.00015743756320098332,
"loss": 5.2276,
"step": 102
},
{
"epoch": 0.1162200282087447,
"grad_norm": 1.01457941532135,
"learning_rate": 0.0001549595053975962,
"loss": 5.6306,
"step": 103
},
{
"epoch": 0.11734837799717912,
"grad_norm": 0.9400536417961121,
"learning_rate": 0.00015248009171495378,
"loss": 5.4706,
"step": 104
},
{
"epoch": 0.11847672778561354,
"grad_norm": 0.9083569645881653,
"learning_rate": 0.00015,
"loss": 5.3956,
"step": 105
},
{
"epoch": 0.11960507757404795,
"grad_norm": 0.9668806791305542,
"learning_rate": 0.00014751990828504622,
"loss": 4.9937,
"step": 106
},
{
"epoch": 0.12073342736248237,
"grad_norm": 1.028422474861145,
"learning_rate": 0.00014504049460240375,
"loss": 5.1075,
"step": 107
},
{
"epoch": 0.12186177715091678,
"grad_norm": 1.027681589126587,
"learning_rate": 0.00014256243679901663,
"loss": 4.7467,
"step": 108
},
{
"epoch": 0.1229901269393512,
"grad_norm": 1.2261557579040527,
"learning_rate": 0.00014008641235114508,
"loss": 5.2596,
"step": 109
},
{
"epoch": 0.12411847672778561,
"grad_norm": 1.4716525077819824,
"learning_rate": 0.00013761309817915014,
"loss": 5.1429,
"step": 110
},
{
"epoch": 0.12524682651622002,
"grad_norm": 1.658657431602478,
"learning_rate": 0.00013514317046243058,
"loss": 4.148,
"step": 111
},
{
"epoch": 0.12637517630465445,
"grad_norm": 1.9725309610366821,
"learning_rate": 0.00013267730445456208,
"loss": 4.1838,
"step": 112
},
{
"epoch": 0.12750352609308885,
"grad_norm": 1.6347661018371582,
"learning_rate": 0.00013021617429868963,
"loss": 4.557,
"step": 113
},
{
"epoch": 0.12863187588152328,
"grad_norm": 1.091661810874939,
"learning_rate": 0.00012776045284322368,
"loss": 5.1064,
"step": 114
},
{
"epoch": 0.12976022566995768,
"grad_norm": 1.130980372428894,
"learning_rate": 0.00012531081145788987,
"loss": 5.6629,
"step": 115
},
{
"epoch": 0.1308885754583921,
"grad_norm": 1.0200557708740234,
"learning_rate": 0.00012286791985018355,
"loss": 5.4764,
"step": 116
},
{
"epoch": 0.1320169252468265,
"grad_norm": 0.9153003692626953,
"learning_rate": 0.00012043244588227796,
"loss": 5.3841,
"step": 117
},
{
"epoch": 0.13314527503526094,
"grad_norm": 0.9858378171920776,
"learning_rate": 0.00011800505538843798,
"loss": 5.2284,
"step": 118
},
{
"epoch": 0.13427362482369534,
"grad_norm": 1.0522313117980957,
"learning_rate": 0.00011558641199298727,
"loss": 5.2795,
"step": 119
},
{
"epoch": 0.13540197461212977,
"grad_norm": 1.0890685319900513,
"learning_rate": 0.00011317717692888012,
"loss": 4.7377,
"step": 120
},
{
"epoch": 0.13653032440056417,
"grad_norm": 1.0877487659454346,
"learning_rate": 0.00011077800885692702,
"loss": 4.4636,
"step": 121
},
{
"epoch": 0.1376586741889986,
"grad_norm": 1.2406129837036133,
"learning_rate": 0.00010838956368572334,
"loss": 4.596,
"step": 122
},
{
"epoch": 0.138787023977433,
"grad_norm": 1.5327285528182983,
"learning_rate": 0.0001060124943923303,
"loss": 4.4116,
"step": 123
},
{
"epoch": 0.1399153737658674,
"grad_norm": 1.823967695236206,
"learning_rate": 0.0001036474508437579,
"loss": 3.8576,
"step": 124
},
{
"epoch": 0.14104372355430184,
"grad_norm": 2.4966747760772705,
"learning_rate": 0.00010129507961929748,
"loss": 4.3004,
"step": 125
},
{
"epoch": 0.14104372355430184,
"eval_loss": 1.2886390686035156,
"eval_runtime": 0.9259,
"eval_samples_per_second": 54.002,
"eval_steps_per_second": 2.16,
"step": 125
},
{
"epoch": 0.14217207334273624,
"grad_norm": 0.9914820194244385,
"learning_rate": 9.895602383375353e-05,
"loss": 5.0125,
"step": 126
},
{
"epoch": 0.14330042313117067,
"grad_norm": 1.0906481742858887,
"learning_rate": 9.663092296162251e-05,
"loss": 5.2648,
"step": 127
},
{
"epoch": 0.14442877291960507,
"grad_norm": 1.0027016401290894,
"learning_rate": 9.432041266226686e-05,
"loss": 5.4165,
"step": 128
},
{
"epoch": 0.1455571227080395,
"grad_norm": 0.8953999876976013,
"learning_rate": 9.202512460613219e-05,
"loss": 5.288,
"step": 129
},
{
"epoch": 0.1466854724964739,
"grad_norm": 0.9168447256088257,
"learning_rate": 8.97456863020546e-05,
"loss": 5.4026,
"step": 130
},
{
"epoch": 0.14781382228490833,
"grad_norm": 1.0525821447372437,
"learning_rate": 8.748272092570646e-05,
"loss": 4.8288,
"step": 131
},
{
"epoch": 0.14894217207334273,
"grad_norm": 1.1151782274246216,
"learning_rate": 8.523684714922608e-05,
"loss": 5.1716,
"step": 132
},
{
"epoch": 0.15007052186177716,
"grad_norm": 1.154405117034912,
"learning_rate": 8.300867897207903e-05,
"loss": 4.7533,
"step": 133
},
{
"epoch": 0.15119887165021156,
"grad_norm": 1.240439534187317,
"learning_rate": 8.079882555319684e-05,
"loss": 4.7972,
"step": 134
},
{
"epoch": 0.152327221438646,
"grad_norm": 1.4108296632766724,
"learning_rate": 7.860789104443896e-05,
"loss": 4.6784,
"step": 135
},
{
"epoch": 0.1534555712270804,
"grad_norm": 1.9870264530181885,
"learning_rate": 7.643647442542382e-05,
"loss": 4.3397,
"step": 136
},
{
"epoch": 0.1545839210155148,
"grad_norm": 2.1759731769561768,
"learning_rate": 7.428516933977347e-05,
"loss": 4.2203,
"step": 137
},
{
"epoch": 0.15571227080394923,
"grad_norm": 2.0424306392669678,
"learning_rate": 7.215456393281776e-05,
"loss": 4.6896,
"step": 138
},
{
"epoch": 0.15684062059238363,
"grad_norm": 1.0496714115142822,
"learning_rate": 7.004524069080096e-05,
"loss": 5.2309,
"step": 139
},
{
"epoch": 0.15796897038081806,
"grad_norm": 1.1061240434646606,
"learning_rate": 6.795777628163599e-05,
"loss": 5.3982,
"step": 140
},
{
"epoch": 0.15909732016925246,
"grad_norm": 1.058211326599121,
"learning_rate": 6.58927413972491e-05,
"loss": 5.1822,
"step": 141
},
{
"epoch": 0.1602256699576869,
"grad_norm": 0.9219530820846558,
"learning_rate": 6.385070059755846e-05,
"loss": 5.4801,
"step": 142
},
{
"epoch": 0.1613540197461213,
"grad_norm": 0.9278646111488342,
"learning_rate": 6.183221215612904e-05,
"loss": 5.067,
"step": 143
},
{
"epoch": 0.16248236953455572,
"grad_norm": 0.9372487664222717,
"learning_rate": 5.983782790754623e-05,
"loss": 5.1083,
"step": 144
},
{
"epoch": 0.16361071932299012,
"grad_norm": 0.9894881248474121,
"learning_rate": 5.786809309654982e-05,
"loss": 4.7132,
"step": 145
},
{
"epoch": 0.16473906911142455,
"grad_norm": 1.1469985246658325,
"learning_rate": 5.592354622896944e-05,
"loss": 4.6039,
"step": 146
},
{
"epoch": 0.16586741889985895,
"grad_norm": 1.2897059917449951,
"learning_rate": 5.40047189245025e-05,
"loss": 4.7095,
"step": 147
},
{
"epoch": 0.16699576868829338,
"grad_norm": 1.5844782590866089,
"learning_rate": 5.211213577137469e-05,
"loss": 4.692,
"step": 148
},
{
"epoch": 0.16812411847672779,
"grad_norm": 1.9257125854492188,
"learning_rate": 5.024631418292274e-05,
"loss": 3.9948,
"step": 149
},
{
"epoch": 0.1692524682651622,
"grad_norm": 2.462533473968506,
"learning_rate": 4.840776425613886e-05,
"loss": 3.9123,
"step": 150
},
{
"epoch": 0.1692524682651622,
"eval_loss": 1.2720993757247925,
"eval_runtime": 0.9278,
"eval_samples_per_second": 53.888,
"eval_steps_per_second": 2.156,
"step": 150
},
{
"epoch": 0.17038081805359662,
"grad_norm": 0.8026057481765747,
"learning_rate": 4.659698863221513e-05,
"loss": 5.0132,
"step": 151
},
{
"epoch": 0.17150916784203102,
"grad_norm": 0.9444528222084045,
"learning_rate": 4.481448235912671e-05,
"loss": 5.3351,
"step": 152
},
{
"epoch": 0.17263751763046545,
"grad_norm": 1.0391024351119995,
"learning_rate": 4.306073275629044e-05,
"loss": 5.4513,
"step": 153
},
{
"epoch": 0.17376586741889985,
"grad_norm": 1.0214226245880127,
"learning_rate": 4.133621928133665e-05,
"loss": 5.3583,
"step": 154
},
{
"epoch": 0.17489421720733428,
"grad_norm": 0.9429175853729248,
"learning_rate": 3.964141339903026e-05,
"loss": 5.1097,
"step": 155
},
{
"epoch": 0.17602256699576868,
"grad_norm": 0.9097686409950256,
"learning_rate": 3.797677845237696e-05,
"loss": 5.2037,
"step": 156
},
{
"epoch": 0.1771509167842031,
"grad_norm": 0.9255871772766113,
"learning_rate": 3.634276953594982e-05,
"loss": 4.742,
"step": 157
},
{
"epoch": 0.1782792665726375,
"grad_norm": 0.9857163429260254,
"learning_rate": 3.473983337147118e-05,
"loss": 4.6819,
"step": 158
},
{
"epoch": 0.17940761636107194,
"grad_norm": 1.1553775072097778,
"learning_rate": 3.316840818568315e-05,
"loss": 4.8855,
"step": 159
},
{
"epoch": 0.18053596614950634,
"grad_norm": 1.3258355855941772,
"learning_rate": 3.162892359054098e-05,
"loss": 4.6796,
"step": 160
},
{
"epoch": 0.18166431593794077,
"grad_norm": 1.6616721153259277,
"learning_rate": 3.0121800465761293e-05,
"loss": 4.0664,
"step": 161
},
{
"epoch": 0.18279266572637518,
"grad_norm": 2.0758633613586426,
"learning_rate": 2.8647450843757897e-05,
"loss": 4.2889,
"step": 162
},
{
"epoch": 0.18392101551480958,
"grad_norm": 1.9801307916641235,
"learning_rate": 2.7206277796996144e-05,
"loss": 4.7948,
"step": 163
},
{
"epoch": 0.185049365303244,
"grad_norm": 0.7826558947563171,
"learning_rate": 2.5798675327796993e-05,
"loss": 5.0153,
"step": 164
},
{
"epoch": 0.1861777150916784,
"grad_norm": 0.9279558658599854,
"learning_rate": 2.4425028260620715e-05,
"loss": 5.4651,
"step": 165
},
{
"epoch": 0.18730606488011284,
"grad_norm": 0.930233895778656,
"learning_rate": 2.3085712136859668e-05,
"loss": 5.3147,
"step": 166
},
{
"epoch": 0.18843441466854724,
"grad_norm": 0.9067016243934631,
"learning_rate": 2.178109311216913e-05,
"loss": 5.2614,
"step": 167
},
{
"epoch": 0.18956276445698167,
"grad_norm": 0.9652501344680786,
"learning_rate": 2.0511527856363912e-05,
"loss": 5.162,
"step": 168
},
{
"epoch": 0.19069111424541607,
"grad_norm": 0.9314717650413513,
"learning_rate": 1.927736345590839e-05,
"loss": 4.726,
"step": 169
},
{
"epoch": 0.1918194640338505,
"grad_norm": 0.9261587262153625,
"learning_rate": 1.8078937319026654e-05,
"loss": 4.5722,
"step": 170
},
{
"epoch": 0.1929478138222849,
"grad_norm": 1.045760154724121,
"learning_rate": 1.6916577083458228e-05,
"loss": 4.8178,
"step": 171
},
{
"epoch": 0.19407616361071933,
"grad_norm": 1.229853630065918,
"learning_rate": 1.579060052688548e-05,
"loss": 4.512,
"step": 172
},
{
"epoch": 0.19520451339915373,
"grad_norm": 1.6810922622680664,
"learning_rate": 1.4701315480056164e-05,
"loss": 4.5544,
"step": 173
},
{
"epoch": 0.19633286318758816,
"grad_norm": 1.9203490018844604,
"learning_rate": 1.3649019742625623e-05,
"loss": 3.8509,
"step": 174
},
{
"epoch": 0.19746121297602257,
"grad_norm": 2.490200996398926,
"learning_rate": 1.2634001001741373e-05,
"loss": 3.8423,
"step": 175
},
{
"epoch": 0.19746121297602257,
"eval_loss": 1.242711067199707,
"eval_runtime": 0.9242,
"eval_samples_per_second": 54.103,
"eval_steps_per_second": 2.164,
"step": 175
},
{
"epoch": 0.198589562764457,
"grad_norm": 0.7016568779945374,
"learning_rate": 1.1656536753392287e-05,
"loss": 5.2993,
"step": 176
},
{
"epoch": 0.1997179125528914,
"grad_norm": 0.7517989873886108,
"learning_rate": 1.0716894226543953e-05,
"loss": 4.8794,
"step": 177
},
{
"epoch": 0.2008462623413258,
"grad_norm": 0.8460791110992432,
"learning_rate": 9.815330310080887e-06,
"loss": 5.2736,
"step": 178
},
{
"epoch": 0.20197461212976023,
"grad_norm": 0.867402195930481,
"learning_rate": 8.952091482575824e-06,
"loss": 5.0763,
"step": 179
},
{
"epoch": 0.20310296191819463,
"grad_norm": 0.9420872330665588,
"learning_rate": 8.127413744904804e-06,
"loss": 5.2391,
"step": 180
},
{
"epoch": 0.20423131170662906,
"grad_norm": 0.9415227770805359,
"learning_rate": 7.34152255572697e-06,
"loss": 4.984,
"step": 181
},
{
"epoch": 0.20535966149506346,
"grad_norm": 0.9311860799789429,
"learning_rate": 6.594632769846353e-06,
"loss": 4.9695,
"step": 182
},
{
"epoch": 0.2064880112834979,
"grad_norm": 0.9357183575630188,
"learning_rate": 5.886948579472778e-06,
"loss": 4.3698,
"step": 183
},
{
"epoch": 0.2076163610719323,
"grad_norm": 1.0420697927474976,
"learning_rate": 5.218663458397715e-06,
"loss": 4.9282,
"step": 184
},
{
"epoch": 0.20874471086036672,
"grad_norm": 1.3373925685882568,
"learning_rate": 4.589960109100444e-06,
"loss": 4.692,
"step": 185
},
{
"epoch": 0.20987306064880112,
"grad_norm": 1.719002604484558,
"learning_rate": 4.001010412799138e-06,
"loss": 4.1929,
"step": 186
},
{
"epoch": 0.21100141043723555,
"grad_norm": 1.9465909004211426,
"learning_rate": 3.451975382460109e-06,
"loss": 3.7969,
"step": 187
},
{
"epoch": 0.21212976022566996,
"grad_norm": 1.667880654335022,
"learning_rate": 2.9430051187785962e-06,
"loss": 4.4874,
"step": 188
},
{
"epoch": 0.21325811001410439,
"grad_norm": 0.6988529562950134,
"learning_rate": 2.4742387691426445e-06,
"loss": 5.0829,
"step": 189
},
{
"epoch": 0.2143864598025388,
"grad_norm": 0.7912782430648804,
"learning_rate": 2.0458044895916513e-06,
"loss": 5.3608,
"step": 190
},
{
"epoch": 0.2155148095909732,
"grad_norm": 0.8568992614746094,
"learning_rate": 1.6578194097797258e-06,
"loss": 5.3566,
"step": 191
},
{
"epoch": 0.21664315937940762,
"grad_norm": 0.8817715048789978,
"learning_rate": 1.3103896009537207e-06,
"loss": 5.4262,
"step": 192
},
{
"epoch": 0.21777150916784202,
"grad_norm": 0.8681627511978149,
"learning_rate": 1.0036100469542786e-06,
"loss": 5.1196,
"step": 193
},
{
"epoch": 0.21889985895627645,
"grad_norm": 0.9048206806182861,
"learning_rate": 7.375646182482875e-07,
"loss": 4.9811,
"step": 194
},
{
"epoch": 0.22002820874471085,
"grad_norm": 0.9085561633110046,
"learning_rate": 5.123260489995229e-07,
"loss": 4.606,
"step": 195
},
{
"epoch": 0.22115655853314528,
"grad_norm": 1.0050228834152222,
"learning_rate": 3.2795591718381975e-07,
"loss": 4.5133,
"step": 196
},
{
"epoch": 0.22228490832157968,
"grad_norm": 1.2002631425857544,
"learning_rate": 1.8450462775428942e-07,
"loss": 4.9258,
"step": 197
},
{
"epoch": 0.2234132581100141,
"grad_norm": 1.5850390195846558,
"learning_rate": 8.201139886109264e-08,
"loss": 4.2643,
"step": 198
},
{
"epoch": 0.22454160789844851,
"grad_norm": 1.851547122001648,
"learning_rate": 2.0504251129649374e-08,
"loss": 4.1506,
"step": 199
},
{
"epoch": 0.22566995768688294,
"grad_norm": 2.222015380859375,
"learning_rate": 0.0,
"loss": 3.3784,
"step": 200
},
{
"epoch": 0.22566995768688294,
"eval_loss": 1.2190457582473755,
"eval_runtime": 0.9287,
"eval_samples_per_second": 53.838,
"eval_steps_per_second": 2.154,
"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": 6.292469692812493e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}