functionary-medium-v3.2 / trainer_state.json
khaimai's picture
Upload folder using huggingface_hub
440a944 verified
raw
history blame
92.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 169,
"global_step": 511,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0019569471624266144,
"grad_norm": 4.606130123138428,
"learning_rate": 3.125e-07,
"loss": 0.6812,
"step": 1
},
{
"epoch": 0.003913894324853229,
"grad_norm": 5.627719402313232,
"learning_rate": 6.25e-07,
"loss": 0.7188,
"step": 2
},
{
"epoch": 0.005870841487279843,
"grad_norm": 5.225893974304199,
"learning_rate": 9.375000000000001e-07,
"loss": 0.6832,
"step": 3
},
{
"epoch": 0.007827788649706457,
"grad_norm": 4.055615425109863,
"learning_rate": 1.25e-06,
"loss": 0.7478,
"step": 4
},
{
"epoch": 0.009784735812133072,
"grad_norm": 3.32236385345459,
"learning_rate": 1.5625e-06,
"loss": 0.6512,
"step": 5
},
{
"epoch": 0.011741682974559686,
"grad_norm": 2.5439915657043457,
"learning_rate": 1.8750000000000003e-06,
"loss": 0.72,
"step": 6
},
{
"epoch": 0.0136986301369863,
"grad_norm": 1.9466145038604736,
"learning_rate": 2.1875000000000002e-06,
"loss": 0.6302,
"step": 7
},
{
"epoch": 0.015655577299412915,
"grad_norm": 1.833212971687317,
"learning_rate": 2.5e-06,
"loss": 0.6859,
"step": 8
},
{
"epoch": 0.01761252446183953,
"grad_norm": 1.4203251600265503,
"learning_rate": 2.8125e-06,
"loss": 0.5943,
"step": 9
},
{
"epoch": 0.019569471624266144,
"grad_norm": 1.7164653539657593,
"learning_rate": 3.125e-06,
"loss": 0.5744,
"step": 10
},
{
"epoch": 0.021526418786692758,
"grad_norm": 1.4249149560928345,
"learning_rate": 3.4375e-06,
"loss": 0.5896,
"step": 11
},
{
"epoch": 0.023483365949119372,
"grad_norm": 1.2433736324310303,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.5873,
"step": 12
},
{
"epoch": 0.025440313111545987,
"grad_norm": 1.0826597213745117,
"learning_rate": 4.0625000000000005e-06,
"loss": 0.5792,
"step": 13
},
{
"epoch": 0.0273972602739726,
"grad_norm": 1.0738195180892944,
"learning_rate": 4.3750000000000005e-06,
"loss": 0.6032,
"step": 14
},
{
"epoch": 0.029354207436399216,
"grad_norm": 1.1434872150421143,
"learning_rate": 4.6875000000000004e-06,
"loss": 0.5698,
"step": 15
},
{
"epoch": 0.03131115459882583,
"grad_norm": 1.4672112464904785,
"learning_rate": 5e-06,
"loss": 0.5471,
"step": 16
},
{
"epoch": 0.033268101761252444,
"grad_norm": 0.9875673651695251,
"learning_rate": 4.999949650182267e-06,
"loss": 0.5393,
"step": 17
},
{
"epoch": 0.03522504892367906,
"grad_norm": 1.0974621772766113,
"learning_rate": 4.999798602757149e-06,
"loss": 0.5349,
"step": 18
},
{
"epoch": 0.03718199608610567,
"grad_norm": 1.2209999561309814,
"learning_rate": 4.999546863808815e-06,
"loss": 0.6743,
"step": 19
},
{
"epoch": 0.03913894324853229,
"grad_norm": 0.8842924237251282,
"learning_rate": 4.999194443477273e-06,
"loss": 0.5919,
"step": 20
},
{
"epoch": 0.0410958904109589,
"grad_norm": 1.0825450420379639,
"learning_rate": 4.998741355957963e-06,
"loss": 0.6438,
"step": 21
},
{
"epoch": 0.043052837573385516,
"grad_norm": 1.0688315629959106,
"learning_rate": 4.998187619501185e-06,
"loss": 0.5637,
"step": 22
},
{
"epoch": 0.04500978473581213,
"grad_norm": 0.8487011790275574,
"learning_rate": 4.99753325641136e-06,
"loss": 0.5082,
"step": 23
},
{
"epoch": 0.046966731898238745,
"grad_norm": 0.9255719780921936,
"learning_rate": 4.9967782930461405e-06,
"loss": 0.5081,
"step": 24
},
{
"epoch": 0.04892367906066536,
"grad_norm": 0.9492978453636169,
"learning_rate": 4.9959227598153395e-06,
"loss": 0.6473,
"step": 25
},
{
"epoch": 0.050880626223091974,
"grad_norm": 1.5718590021133423,
"learning_rate": 4.994966691179712e-06,
"loss": 0.5219,
"step": 26
},
{
"epoch": 0.05283757338551859,
"grad_norm": 0.9533342123031616,
"learning_rate": 4.993910125649561e-06,
"loss": 0.5279,
"step": 27
},
{
"epoch": 0.0547945205479452,
"grad_norm": 1.8043086528778076,
"learning_rate": 4.992753105783194e-06,
"loss": 0.5277,
"step": 28
},
{
"epoch": 0.05675146771037182,
"grad_norm": 1.317238450050354,
"learning_rate": 4.991495678185202e-06,
"loss": 0.4567,
"step": 29
},
{
"epoch": 0.05870841487279843,
"grad_norm": 1.1877973079681396,
"learning_rate": 4.990137893504585e-06,
"loss": 0.5536,
"step": 30
},
{
"epoch": 0.060665362035225046,
"grad_norm": 1.052051305770874,
"learning_rate": 4.988679806432712e-06,
"loss": 0.4946,
"step": 31
},
{
"epoch": 0.06262230919765166,
"grad_norm": 7.080264091491699,
"learning_rate": 4.987121475701118e-06,
"loss": 0.5056,
"step": 32
},
{
"epoch": 0.06457925636007827,
"grad_norm": 3.640033483505249,
"learning_rate": 4.985462964079137e-06,
"loss": 0.5162,
"step": 33
},
{
"epoch": 0.06653620352250489,
"grad_norm": 2.17399263381958,
"learning_rate": 4.983704338371375e-06,
"loss": 0.5314,
"step": 34
},
{
"epoch": 0.0684931506849315,
"grad_norm": 0.9113507270812988,
"learning_rate": 4.981845669415022e-06,
"loss": 0.5416,
"step": 35
},
{
"epoch": 0.07045009784735812,
"grad_norm": 0.865261971950531,
"learning_rate": 4.9798870320769884e-06,
"loss": 0.5266,
"step": 36
},
{
"epoch": 0.07240704500978473,
"grad_norm": 1.3988151550292969,
"learning_rate": 4.977828505250903e-06,
"loss": 0.4983,
"step": 37
},
{
"epoch": 0.07436399217221135,
"grad_norm": 1.0698161125183105,
"learning_rate": 4.975670171853926e-06,
"loss": 0.4723,
"step": 38
},
{
"epoch": 0.07632093933463796,
"grad_norm": 1.2741320133209229,
"learning_rate": 4.9734121188234115e-06,
"loss": 0.4996,
"step": 39
},
{
"epoch": 0.07827788649706457,
"grad_norm": 2.0048317909240723,
"learning_rate": 4.971054437113406e-06,
"loss": 0.6535,
"step": 40
},
{
"epoch": 0.08023483365949119,
"grad_norm": 1.2805678844451904,
"learning_rate": 4.968597221690986e-06,
"loss": 0.5198,
"step": 41
},
{
"epoch": 0.0821917808219178,
"grad_norm": 0.9233219027519226,
"learning_rate": 4.96604057153243e-06,
"loss": 0.5724,
"step": 42
},
{
"epoch": 0.08414872798434442,
"grad_norm": 0.9261006712913513,
"learning_rate": 4.963384589619233e-06,
"loss": 0.4601,
"step": 43
},
{
"epoch": 0.08610567514677103,
"grad_norm": 1.3594372272491455,
"learning_rate": 4.960629382933959e-06,
"loss": 0.5616,
"step": 44
},
{
"epoch": 0.08806262230919765,
"grad_norm": 2.4310686588287354,
"learning_rate": 4.957775062455933e-06,
"loss": 0.5442,
"step": 45
},
{
"epoch": 0.09001956947162426,
"grad_norm": 1.030832290649414,
"learning_rate": 4.9548217431567665e-06,
"loss": 0.5964,
"step": 46
},
{
"epoch": 0.09197651663405088,
"grad_norm": 0.831721305847168,
"learning_rate": 4.951769543995731e-06,
"loss": 0.44,
"step": 47
},
{
"epoch": 0.09393346379647749,
"grad_norm": 0.9876791834831238,
"learning_rate": 4.948618587914963e-06,
"loss": 0.5404,
"step": 48
},
{
"epoch": 0.0958904109589041,
"grad_norm": 0.9953415393829346,
"learning_rate": 4.9453690018345144e-06,
"loss": 0.5668,
"step": 49
},
{
"epoch": 0.09784735812133072,
"grad_norm": 0.8553183078765869,
"learning_rate": 4.9420209166472386e-06,
"loss": 0.5414,
"step": 50
},
{
"epoch": 0.09980430528375733,
"grad_norm": 0.7962396144866943,
"learning_rate": 4.938574467213519e-06,
"loss": 0.495,
"step": 51
},
{
"epoch": 0.10176125244618395,
"grad_norm": 0.7835857272148132,
"learning_rate": 4.935029792355834e-06,
"loss": 0.5037,
"step": 52
},
{
"epoch": 0.10371819960861056,
"grad_norm": 0.8453947901725769,
"learning_rate": 4.931387034853173e-06,
"loss": 0.5011,
"step": 53
},
{
"epoch": 0.10567514677103718,
"grad_norm": 1.8459208011627197,
"learning_rate": 4.927646341435276e-06,
"loss": 0.5554,
"step": 54
},
{
"epoch": 0.10763209393346379,
"grad_norm": 0.9212117195129395,
"learning_rate": 4.9238078627767285e-06,
"loss": 0.5886,
"step": 55
},
{
"epoch": 0.1095890410958904,
"grad_norm": 0.7834203243255615,
"learning_rate": 4.919871753490892e-06,
"loss": 0.4602,
"step": 56
},
{
"epoch": 0.11154598825831702,
"grad_norm": 0.9025184512138367,
"learning_rate": 4.9158381721236715e-06,
"loss": 0.4544,
"step": 57
},
{
"epoch": 0.11350293542074363,
"grad_norm": 1.1300384998321533,
"learning_rate": 4.91170728114714e-06,
"loss": 0.5704,
"step": 58
},
{
"epoch": 0.11545988258317025,
"grad_norm": 0.7926605343818665,
"learning_rate": 4.907479246952981e-06,
"loss": 0.5112,
"step": 59
},
{
"epoch": 0.11741682974559686,
"grad_norm": 0.7744232416152954,
"learning_rate": 4.903154239845798e-06,
"loss": 0.4894,
"step": 60
},
{
"epoch": 0.11937377690802348,
"grad_norm": 1.6636885404586792,
"learning_rate": 4.8987324340362445e-06,
"loss": 0.5311,
"step": 61
},
{
"epoch": 0.12133072407045009,
"grad_norm": 1.0098280906677246,
"learning_rate": 4.894214007634014e-06,
"loss": 0.4907,
"step": 62
},
{
"epoch": 0.1232876712328767,
"grad_norm": 1.0168606042861938,
"learning_rate": 4.889599142640663e-06,
"loss": 0.5128,
"step": 63
},
{
"epoch": 0.12524461839530332,
"grad_norm": 0.8393405079841614,
"learning_rate": 4.884888024942282e-06,
"loss": 0.4989,
"step": 64
},
{
"epoch": 0.12720156555772993,
"grad_norm": 1.2758891582489014,
"learning_rate": 4.880080844302004e-06,
"loss": 0.5329,
"step": 65
},
{
"epoch": 0.12915851272015655,
"grad_norm": 0.8657482862472534,
"learning_rate": 4.875177794352364e-06,
"loss": 0.5058,
"step": 66
},
{
"epoch": 0.13111545988258316,
"grad_norm": 0.9110330939292908,
"learning_rate": 4.870179072587499e-06,
"loss": 0.5137,
"step": 67
},
{
"epoch": 0.13307240704500978,
"grad_norm": 0.8738705515861511,
"learning_rate": 4.865084880355193e-06,
"loss": 0.5423,
"step": 68
},
{
"epoch": 0.1350293542074364,
"grad_norm": 0.8127829432487488,
"learning_rate": 4.859895422848767e-06,
"loss": 0.5402,
"step": 69
},
{
"epoch": 0.136986301369863,
"grad_norm": 0.768864631652832,
"learning_rate": 4.854610909098813e-06,
"loss": 0.5301,
"step": 70
},
{
"epoch": 0.13894324853228962,
"grad_norm": 1.2464350461959839,
"learning_rate": 4.849231551964771e-06,
"loss": 0.5124,
"step": 71
},
{
"epoch": 0.14090019569471623,
"grad_norm": 0.9351313710212708,
"learning_rate": 4.843757568126366e-06,
"loss": 0.5152,
"step": 72
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.842991054058075,
"learning_rate": 4.838189178074867e-06,
"loss": 0.5254,
"step": 73
},
{
"epoch": 0.14481409001956946,
"grad_norm": 0.7789003252983093,
"learning_rate": 4.832526606104213e-06,
"loss": 0.5528,
"step": 74
},
{
"epoch": 0.14677103718199608,
"grad_norm": 0.8701135516166687,
"learning_rate": 4.826770080301978e-06,
"loss": 0.5243,
"step": 75
},
{
"epoch": 0.1487279843444227,
"grad_norm": 0.8384250998497009,
"learning_rate": 4.8209198325401815e-06,
"loss": 0.4648,
"step": 76
},
{
"epoch": 0.1506849315068493,
"grad_norm": 1.0472533702850342,
"learning_rate": 4.814976098465951e-06,
"loss": 0.5342,
"step": 77
},
{
"epoch": 0.15264187866927592,
"grad_norm": 0.9264402389526367,
"learning_rate": 4.808939117492028e-06,
"loss": 0.5267,
"step": 78
},
{
"epoch": 0.15459882583170254,
"grad_norm": 0.8155198097229004,
"learning_rate": 4.802809132787125e-06,
"loss": 0.5363,
"step": 79
},
{
"epoch": 0.15655577299412915,
"grad_norm": 0.8857468366622925,
"learning_rate": 4.796586391266135e-06,
"loss": 0.5021,
"step": 80
},
{
"epoch": 0.15851272015655576,
"grad_norm": 1.0320619344711304,
"learning_rate": 4.790271143580174e-06,
"loss": 0.4892,
"step": 81
},
{
"epoch": 0.16046966731898238,
"grad_norm": 0.9655166268348694,
"learning_rate": 4.783863644106502e-06,
"loss": 0.5493,
"step": 82
},
{
"epoch": 0.162426614481409,
"grad_norm": 1.3644921779632568,
"learning_rate": 4.777364150938263e-06,
"loss": 0.4835,
"step": 83
},
{
"epoch": 0.1643835616438356,
"grad_norm": 1.291692852973938,
"learning_rate": 4.770772925874093e-06,
"loss": 0.5755,
"step": 84
},
{
"epoch": 0.16634050880626222,
"grad_norm": 1.0446902513504028,
"learning_rate": 4.764090234407578e-06,
"loss": 0.5659,
"step": 85
},
{
"epoch": 0.16829745596868884,
"grad_norm": 0.9225801825523376,
"learning_rate": 4.757316345716554e-06,
"loss": 0.4067,
"step": 86
},
{
"epoch": 0.17025440313111545,
"grad_norm": 0.8291013240814209,
"learning_rate": 4.75045153265227e-06,
"loss": 0.4946,
"step": 87
},
{
"epoch": 0.17221135029354206,
"grad_norm": 1.1656488180160522,
"learning_rate": 4.743496071728396e-06,
"loss": 0.4933,
"step": 88
},
{
"epoch": 0.17416829745596868,
"grad_norm": 0.9090279936790466,
"learning_rate": 4.736450243109885e-06,
"loss": 0.5085,
"step": 89
},
{
"epoch": 0.1761252446183953,
"grad_norm": 1.2236806154251099,
"learning_rate": 4.729314330601684e-06,
"loss": 0.5147,
"step": 90
},
{
"epoch": 0.1780821917808219,
"grad_norm": 0.9335976839065552,
"learning_rate": 4.7220886216373095e-06,
"loss": 0.4589,
"step": 91
},
{
"epoch": 0.18003913894324852,
"grad_norm": 0.759772002696991,
"learning_rate": 4.714773407267264e-06,
"loss": 0.5398,
"step": 92
},
{
"epoch": 0.18199608610567514,
"grad_norm": 0.9582347869873047,
"learning_rate": 4.707368982147318e-06,
"loss": 0.5696,
"step": 93
},
{
"epoch": 0.18395303326810175,
"grad_norm": 0.9130314588546753,
"learning_rate": 4.699875644526633e-06,
"loss": 0.4803,
"step": 94
},
{
"epoch": 0.18590998043052837,
"grad_norm": 0.9103049635887146,
"learning_rate": 4.692293696235758e-06,
"loss": 0.4833,
"step": 95
},
{
"epoch": 0.18786692759295498,
"grad_norm": 0.7975893616676331,
"learning_rate": 4.684623442674463e-06,
"loss": 0.5263,
"step": 96
},
{
"epoch": 0.1898238747553816,
"grad_norm": 0.761643648147583,
"learning_rate": 4.676865192799443e-06,
"loss": 0.4519,
"step": 97
},
{
"epoch": 0.1917808219178082,
"grad_norm": 0.7510681748390198,
"learning_rate": 4.669019259111873e-06,
"loss": 0.4871,
"step": 98
},
{
"epoch": 0.19373776908023482,
"grad_norm": 1.1785235404968262,
"learning_rate": 4.661085957644817e-06,
"loss": 0.4644,
"step": 99
},
{
"epoch": 0.19569471624266144,
"grad_norm": 1.2464004755020142,
"learning_rate": 4.653065607950502e-06,
"loss": 0.4791,
"step": 100
},
{
"epoch": 0.19765166340508805,
"grad_norm": 2.580218553543091,
"learning_rate": 4.644958533087443e-06,
"loss": 0.4146,
"step": 101
},
{
"epoch": 0.19960861056751467,
"grad_norm": 0.9442769289016724,
"learning_rate": 4.636765059607434e-06,
"loss": 0.494,
"step": 102
},
{
"epoch": 0.20156555772994128,
"grad_norm": 0.7965562343597412,
"learning_rate": 4.628485517542393e-06,
"loss": 0.4496,
"step": 103
},
{
"epoch": 0.2035225048923679,
"grad_norm": 1.2338522672653198,
"learning_rate": 4.620120240391065e-06,
"loss": 0.4592,
"step": 104
},
{
"epoch": 0.2054794520547945,
"grad_norm": 0.8661827445030212,
"learning_rate": 4.611669565105597e-06,
"loss": 0.4883,
"step": 105
},
{
"epoch": 0.20743639921722112,
"grad_norm": 1.014655351638794,
"learning_rate": 4.603133832077953e-06,
"loss": 0.5101,
"step": 106
},
{
"epoch": 0.20939334637964774,
"grad_norm": 0.9033066630363464,
"learning_rate": 4.5945133851262185e-06,
"loss": 0.4515,
"step": 107
},
{
"epoch": 0.21135029354207435,
"grad_norm": 0.91737961769104,
"learning_rate": 4.585808571480739e-06,
"loss": 0.4886,
"step": 108
},
{
"epoch": 0.21330724070450097,
"grad_norm": 0.9076818823814392,
"learning_rate": 4.577019741770137e-06,
"loss": 0.5572,
"step": 109
},
{
"epoch": 0.21526418786692758,
"grad_norm": 0.9256044626235962,
"learning_rate": 4.5681472500071935e-06,
"loss": 0.5089,
"step": 110
},
{
"epoch": 0.2172211350293542,
"grad_norm": 0.8705273270606995,
"learning_rate": 4.559191453574582e-06,
"loss": 0.5199,
"step": 111
},
{
"epoch": 0.2191780821917808,
"grad_norm": 0.8358094096183777,
"learning_rate": 4.550152713210478e-06,
"loss": 0.5091,
"step": 112
},
{
"epoch": 0.22113502935420742,
"grad_norm": 1.0409964323043823,
"learning_rate": 4.541031392994025e-06,
"loss": 0.4997,
"step": 113
},
{
"epoch": 0.22309197651663404,
"grad_norm": 0.8039932250976562,
"learning_rate": 4.53182786033067e-06,
"loss": 0.537,
"step": 114
},
{
"epoch": 0.22504892367906065,
"grad_norm": 0.9191640615463257,
"learning_rate": 4.522542485937369e-06,
"loss": 0.5799,
"step": 115
},
{
"epoch": 0.22700587084148727,
"grad_norm": 0.8132153153419495,
"learning_rate": 4.513175643827647e-06,
"loss": 0.5217,
"step": 116
},
{
"epoch": 0.22896281800391388,
"grad_norm": 0.7776696085929871,
"learning_rate": 4.503727711296539e-06,
"loss": 0.4729,
"step": 117
},
{
"epoch": 0.2309197651663405,
"grad_norm": 0.8824874758720398,
"learning_rate": 4.494199068905389e-06,
"loss": 0.4977,
"step": 118
},
{
"epoch": 0.2328767123287671,
"grad_norm": 0.9938674569129944,
"learning_rate": 4.484590100466524e-06,
"loss": 0.5067,
"step": 119
},
{
"epoch": 0.23483365949119372,
"grad_norm": 1.018510103225708,
"learning_rate": 4.474901193027791e-06,
"loss": 0.5855,
"step": 120
},
{
"epoch": 0.23679060665362034,
"grad_norm": 1.0530946254730225,
"learning_rate": 4.4651327368569695e-06,
"loss": 0.4835,
"step": 121
},
{
"epoch": 0.23874755381604695,
"grad_norm": 0.7325494289398193,
"learning_rate": 4.455285125426049e-06,
"loss": 0.5043,
"step": 122
},
{
"epoch": 0.24070450097847357,
"grad_norm": 1.2264351844787598,
"learning_rate": 4.445358755395382e-06,
"loss": 0.4991,
"step": 123
},
{
"epoch": 0.24266144814090018,
"grad_norm": 0.7878324389457703,
"learning_rate": 4.435354026597707e-06,
"loss": 0.4943,
"step": 124
},
{
"epoch": 0.2446183953033268,
"grad_norm": 1.0379810333251953,
"learning_rate": 4.425271342022039e-06,
"loss": 0.5664,
"step": 125
},
{
"epoch": 0.2465753424657534,
"grad_norm": 1.2007404565811157,
"learning_rate": 4.415111107797445e-06,
"loss": 0.4495,
"step": 126
},
{
"epoch": 0.24853228962818003,
"grad_norm": 1.4260215759277344,
"learning_rate": 4.404873733176678e-06,
"loss": 0.4848,
"step": 127
},
{
"epoch": 0.25048923679060664,
"grad_norm": 0.7717714309692383,
"learning_rate": 4.3945596305196925e-06,
"loss": 0.4975,
"step": 128
},
{
"epoch": 0.25244618395303325,
"grad_norm": 1.0631009340286255,
"learning_rate": 4.384169215277042e-06,
"loss": 0.538,
"step": 129
},
{
"epoch": 0.25440313111545987,
"grad_norm": 0.9604893326759338,
"learning_rate": 4.373702905973136e-06,
"loss": 0.554,
"step": 130
},
{
"epoch": 0.2563600782778865,
"grad_norm": 0.8638473749160767,
"learning_rate": 4.363161124189387e-06,
"loss": 0.4839,
"step": 131
},
{
"epoch": 0.2583170254403131,
"grad_norm": 0.8187501430511475,
"learning_rate": 4.352544294547229e-06,
"loss": 0.5105,
"step": 132
},
{
"epoch": 0.2602739726027397,
"grad_norm": 1.4357470273971558,
"learning_rate": 4.341852844691012e-06,
"loss": 0.4532,
"step": 133
},
{
"epoch": 0.2622309197651663,
"grad_norm": 0.8292232155799866,
"learning_rate": 4.331087205270778e-06,
"loss": 0.451,
"step": 134
},
{
"epoch": 0.26418786692759294,
"grad_norm": 0.8243665099143982,
"learning_rate": 4.320247809924911e-06,
"loss": 0.4857,
"step": 135
},
{
"epoch": 0.26614481409001955,
"grad_norm": 0.9147266745567322,
"learning_rate": 4.309335095262675e-06,
"loss": 0.4778,
"step": 136
},
{
"epoch": 0.26810176125244617,
"grad_norm": 0.8612287044525146,
"learning_rate": 4.2983495008466285e-06,
"loss": 0.4627,
"step": 137
},
{
"epoch": 0.2700587084148728,
"grad_norm": 0.8230846524238586,
"learning_rate": 4.287291469174909e-06,
"loss": 0.4627,
"step": 138
},
{
"epoch": 0.2720156555772994,
"grad_norm": 0.8767359852790833,
"learning_rate": 4.276161445663423e-06,
"loss": 0.5119,
"step": 139
},
{
"epoch": 0.273972602739726,
"grad_norm": 0.8119643926620483,
"learning_rate": 4.264959878627891e-06,
"loss": 0.4495,
"step": 140
},
{
"epoch": 0.2759295499021526,
"grad_norm": 0.7973845601081848,
"learning_rate": 4.253687219265803e-06,
"loss": 0.5228,
"step": 141
},
{
"epoch": 0.27788649706457924,
"grad_norm": 0.892238199710846,
"learning_rate": 4.242343921638235e-06,
"loss": 0.5154,
"step": 142
},
{
"epoch": 0.27984344422700586,
"grad_norm": 1.3092166185379028,
"learning_rate": 4.230930442651558e-06,
"loss": 0.5085,
"step": 143
},
{
"epoch": 0.28180039138943247,
"grad_norm": 1.2284399271011353,
"learning_rate": 4.219447242039043e-06,
"loss": 0.4366,
"step": 144
},
{
"epoch": 0.2837573385518591,
"grad_norm": 1.0883151292800903,
"learning_rate": 4.207894782342337e-06,
"loss": 0.5958,
"step": 145
},
{
"epoch": 0.2857142857142857,
"grad_norm": 1.1132919788360596,
"learning_rate": 4.196273528892831e-06,
"loss": 0.4348,
"step": 146
},
{
"epoch": 0.2876712328767123,
"grad_norm": 1.2576059103012085,
"learning_rate": 4.18458394979292e-06,
"loss": 0.5247,
"step": 147
},
{
"epoch": 0.2896281800391389,
"grad_norm": 0.8995031714439392,
"learning_rate": 4.172826515897146e-06,
"loss": 0.5082,
"step": 148
},
{
"epoch": 0.29158512720156554,
"grad_norm": 0.7533922791481018,
"learning_rate": 4.161001700793231e-06,
"loss": 0.4644,
"step": 149
},
{
"epoch": 0.29354207436399216,
"grad_norm": 0.9206835031509399,
"learning_rate": 4.149109980783004e-06,
"loss": 0.494,
"step": 150
},
{
"epoch": 0.29549902152641877,
"grad_norm": 1.208590030670166,
"learning_rate": 4.137151834863213e-06,
"loss": 0.5545,
"step": 151
},
{
"epoch": 0.2974559686888454,
"grad_norm": 0.7689659595489502,
"learning_rate": 4.125127744706232e-06,
"loss": 0.4845,
"step": 152
},
{
"epoch": 0.299412915851272,
"grad_norm": 1.0235570669174194,
"learning_rate": 4.113038194640658e-06,
"loss": 0.4778,
"step": 153
},
{
"epoch": 0.3013698630136986,
"grad_norm": 1.1112617254257202,
"learning_rate": 4.100883671631806e-06,
"loss": 0.5206,
"step": 154
},
{
"epoch": 0.30332681017612523,
"grad_norm": 1.073519229888916,
"learning_rate": 4.088664665262091e-06,
"loss": 0.4944,
"step": 155
},
{
"epoch": 0.30528375733855184,
"grad_norm": 0.8319236040115356,
"learning_rate": 4.076381667711306e-06,
"loss": 0.4741,
"step": 156
},
{
"epoch": 0.30724070450097846,
"grad_norm": 1.2600641250610352,
"learning_rate": 4.064035173736804e-06,
"loss": 0.5311,
"step": 157
},
{
"epoch": 0.30919765166340507,
"grad_norm": 0.8686632513999939,
"learning_rate": 4.05162568065356e-06,
"loss": 0.5436,
"step": 158
},
{
"epoch": 0.3111545988258317,
"grad_norm": 0.7053869366645813,
"learning_rate": 4.039153688314146e-06,
"loss": 0.4846,
"step": 159
},
{
"epoch": 0.3131115459882583,
"grad_norm": 0.8360055685043335,
"learning_rate": 4.0266196990885955e-06,
"loss": 0.5041,
"step": 160
},
{
"epoch": 0.3150684931506849,
"grad_norm": 0.8842881321907043,
"learning_rate": 4.014024217844167e-06,
"loss": 0.4708,
"step": 161
},
{
"epoch": 0.31702544031311153,
"grad_norm": 1.0392301082611084,
"learning_rate": 4.001367751925008e-06,
"loss": 0.5315,
"step": 162
},
{
"epoch": 0.31898238747553814,
"grad_norm": 0.8801809549331665,
"learning_rate": 3.98865081113172e-06,
"loss": 0.4438,
"step": 163
},
{
"epoch": 0.32093933463796476,
"grad_norm": 1.395719289779663,
"learning_rate": 3.9758739077008256e-06,
"loss": 0.4929,
"step": 164
},
{
"epoch": 0.32289628180039137,
"grad_norm": 0.8075605034828186,
"learning_rate": 3.96303755628413e-06,
"loss": 0.4364,
"step": 165
},
{
"epoch": 0.324853228962818,
"grad_norm": 0.9566773772239685,
"learning_rate": 3.950142273927996e-06,
"loss": 0.4001,
"step": 166
},
{
"epoch": 0.3268101761252446,
"grad_norm": 2.270550012588501,
"learning_rate": 3.937188580052518e-06,
"loss": 0.4683,
"step": 167
},
{
"epoch": 0.3287671232876712,
"grad_norm": 0.8937717080116272,
"learning_rate": 3.924176996430597e-06,
"loss": 0.479,
"step": 168
},
{
"epoch": 0.33072407045009783,
"grad_norm": 0.9620490074157715,
"learning_rate": 3.911108047166924e-06,
"loss": 0.4669,
"step": 169
},
{
"epoch": 0.33072407045009783,
"eval_accuracy": 0.825246566025413,
"eval_accuracy_first_token": 0.9521367521367521,
"eval_accuracy_first_token_all": 0.9670737362807235,
"eval_accuracy_first_token_all_total": 6469,
"eval_accuracy_first_token_calculate": 0.7954545454545454,
"eval_accuracy_first_token_calculate_total": 44,
"eval_accuracy_first_token_execute": 1.0,
"eval_accuracy_first_token_execute_total": 202,
"eval_accuracy_first_token_get": 0.9649122807017544,
"eval_accuracy_first_token_get_total": 456,
"eval_accuracy_first_token_python": 0.8777777777777778,
"eval_accuracy_first_token_python_total": 990,
"eval_loss": 0.5176534056663513,
"eval_perplexity": 1.206566771452624,
"eval_runtime": 524.2306,
"eval_samples_per_second": 1.269,
"eval_steps_per_second": 0.16,
"eval_total_number_first_token": 9360,
"step": 169
},
{
"epoch": 0.33268101761252444,
"grad_norm": 0.8628460168838501,
"learning_rate": 3.897982258676867e-06,
"loss": 0.4727,
"step": 170
},
{
"epoch": 0.33463796477495106,
"grad_norm": 0.8537535071372986,
"learning_rate": 3.8848001596652765e-06,
"loss": 0.4746,
"step": 171
},
{
"epoch": 0.33659491193737767,
"grad_norm": 0.9613227248191833,
"learning_rate": 3.8715622811051754e-06,
"loss": 0.5148,
"step": 172
},
{
"epoch": 0.3385518590998043,
"grad_norm": 0.8833454251289368,
"learning_rate": 3.858269156216383e-06,
"loss": 0.5125,
"step": 173
},
{
"epoch": 0.3405088062622309,
"grad_norm": 0.9823891520500183,
"learning_rate": 3.844921320444031e-06,
"loss": 0.5127,
"step": 174
},
{
"epoch": 0.3424657534246575,
"grad_norm": 1.0789107084274292,
"learning_rate": 3.8315193114369995e-06,
"loss": 0.4935,
"step": 175
},
{
"epoch": 0.34442270058708413,
"grad_norm": 0.8753149509429932,
"learning_rate": 3.8180636690262565e-06,
"loss": 0.4543,
"step": 176
},
{
"epoch": 0.34637964774951074,
"grad_norm": 1.7468674182891846,
"learning_rate": 3.804554935203115e-06,
"loss": 0.4955,
"step": 177
},
{
"epoch": 0.34833659491193736,
"grad_norm": 0.9011304974555969,
"learning_rate": 3.7909936540974052e-06,
"loss": 0.5992,
"step": 178
},
{
"epoch": 0.350293542074364,
"grad_norm": 0.9541127681732178,
"learning_rate": 3.777380371955552e-06,
"loss": 0.5322,
"step": 179
},
{
"epoch": 0.3522504892367906,
"grad_norm": 1.3841750621795654,
"learning_rate": 3.7637156371185744e-06,
"loss": 0.4661,
"step": 180
},
{
"epoch": 0.3542074363992172,
"grad_norm": 1.0240124464035034,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.5231,
"step": 181
},
{
"epoch": 0.3561643835616438,
"grad_norm": 1.444016933441162,
"learning_rate": 3.7362340130636926e-06,
"loss": 0.5203,
"step": 182
},
{
"epoch": 0.35812133072407043,
"grad_norm": 0.7845962047576904,
"learning_rate": 3.7224182308015977e-06,
"loss": 0.4929,
"step": 183
},
{
"epoch": 0.36007827788649704,
"grad_norm": 1.0257796049118042,
"learning_rate": 3.7085532097114098e-06,
"loss": 0.4597,
"step": 184
},
{
"epoch": 0.36203522504892366,
"grad_norm": 0.9083458185195923,
"learning_rate": 3.6946395082741582e-06,
"loss": 0.5254,
"step": 185
},
{
"epoch": 0.3639921722113503,
"grad_norm": 0.9128417372703552,
"learning_rate": 3.6806776869317074e-06,
"loss": 0.4428,
"step": 186
},
{
"epoch": 0.3659491193737769,
"grad_norm": 1.1980143785476685,
"learning_rate": 3.6666683080641846e-06,
"loss": 0.5374,
"step": 187
},
{
"epoch": 0.3679060665362035,
"grad_norm": 0.8467942476272583,
"learning_rate": 3.6526119359673283e-06,
"loss": 0.4963,
"step": 188
},
{
"epoch": 0.3698630136986301,
"grad_norm": 0.8798732757568359,
"learning_rate": 3.6385091368297582e-06,
"loss": 0.5208,
"step": 189
},
{
"epoch": 0.37181996086105673,
"grad_norm": 0.8612852692604065,
"learning_rate": 3.624360478710165e-06,
"loss": 0.3989,
"step": 190
},
{
"epoch": 0.37377690802348335,
"grad_norm": 0.7529587149620056,
"learning_rate": 3.6101665315144357e-06,
"loss": 0.5015,
"step": 191
},
{
"epoch": 0.37573385518590996,
"grad_norm": 0.8704853653907776,
"learning_rate": 3.595927866972694e-06,
"loss": 0.4318,
"step": 192
},
{
"epoch": 0.3776908023483366,
"grad_norm": 1.1298363208770752,
"learning_rate": 3.581645058616271e-06,
"loss": 0.5047,
"step": 193
},
{
"epoch": 0.3796477495107632,
"grad_norm": 1.2964321374893188,
"learning_rate": 3.5673186817546047e-06,
"loss": 0.4764,
"step": 194
},
{
"epoch": 0.3816046966731898,
"grad_norm": 2.080096960067749,
"learning_rate": 3.552949313452067e-06,
"loss": 0.4808,
"step": 195
},
{
"epoch": 0.3835616438356164,
"grad_norm": 0.8993785977363586,
"learning_rate": 3.5385375325047167e-06,
"loss": 0.5577,
"step": 196
},
{
"epoch": 0.38551859099804303,
"grad_norm": 0.8617794513702393,
"learning_rate": 3.5240839194169885e-06,
"loss": 0.5042,
"step": 197
},
{
"epoch": 0.38747553816046965,
"grad_norm": 0.9634183645248413,
"learning_rate": 3.5095890563783124e-06,
"loss": 0.466,
"step": 198
},
{
"epoch": 0.38943248532289626,
"grad_norm": 0.9015300273895264,
"learning_rate": 3.4950535272396564e-06,
"loss": 0.3887,
"step": 199
},
{
"epoch": 0.3913894324853229,
"grad_norm": 0.8658633828163147,
"learning_rate": 3.480477917490014e-06,
"loss": 0.4665,
"step": 200
},
{
"epoch": 0.3933463796477495,
"grad_norm": 0.7967968583106995,
"learning_rate": 3.4658628142328215e-06,
"loss": 0.515,
"step": 201
},
{
"epoch": 0.3953033268101761,
"grad_norm": 0.7495056986808777,
"learning_rate": 3.4512088061623077e-06,
"loss": 0.4345,
"step": 202
},
{
"epoch": 0.3972602739726027,
"grad_norm": 0.9585980772972107,
"learning_rate": 3.436516483539781e-06,
"loss": 0.4084,
"step": 203
},
{
"epoch": 0.39921722113502933,
"grad_norm": 0.9240750670433044,
"learning_rate": 3.4217864381698523e-06,
"loss": 0.4451,
"step": 204
},
{
"epoch": 0.40117416829745595,
"grad_norm": 1.2117798328399658,
"learning_rate": 3.4070192633766025e-06,
"loss": 0.5152,
"step": 205
},
{
"epoch": 0.40313111545988256,
"grad_norm": 0.868486225605011,
"learning_rate": 3.39221555397968e-06,
"loss": 0.5456,
"step": 206
},
{
"epoch": 0.4050880626223092,
"grad_norm": 0.7969531416893005,
"learning_rate": 3.37737590627034e-06,
"loss": 0.4295,
"step": 207
},
{
"epoch": 0.4070450097847358,
"grad_norm": 0.9103299975395203,
"learning_rate": 3.362500917987427e-06,
"loss": 0.4485,
"step": 208
},
{
"epoch": 0.4090019569471624,
"grad_norm": 1.0487585067749023,
"learning_rate": 3.3475911882933014e-06,
"loss": 0.4807,
"step": 209
},
{
"epoch": 0.410958904109589,
"grad_norm": 0.9155584573745728,
"learning_rate": 3.332647317749702e-06,
"loss": 0.4617,
"step": 210
},
{
"epoch": 0.41291585127201563,
"grad_norm": 0.9164103865623474,
"learning_rate": 3.3176699082935546e-06,
"loss": 0.5041,
"step": 211
},
{
"epoch": 0.41487279843444225,
"grad_norm": 0.7580545544624329,
"learning_rate": 3.3026595632127274e-06,
"loss": 0.465,
"step": 212
},
{
"epoch": 0.41682974559686886,
"grad_norm": 1.0577958822250366,
"learning_rate": 3.2876168871217322e-06,
"loss": 0.4055,
"step": 213
},
{
"epoch": 0.4187866927592955,
"grad_norm": 1.2304415702819824,
"learning_rate": 3.272542485937369e-06,
"loss": 0.3852,
"step": 214
},
{
"epoch": 0.4207436399217221,
"grad_norm": 0.905158281326294,
"learning_rate": 3.2574369668543187e-06,
"loss": 0.4861,
"step": 215
},
{
"epoch": 0.4227005870841487,
"grad_norm": 0.9109801054000854,
"learning_rate": 3.2423009383206876e-06,
"loss": 0.4247,
"step": 216
},
{
"epoch": 0.4246575342465753,
"grad_norm": 0.8025485277175903,
"learning_rate": 3.227135010013498e-06,
"loss": 0.5319,
"step": 217
},
{
"epoch": 0.42661448140900193,
"grad_norm": 0.883714497089386,
"learning_rate": 3.211939792814131e-06,
"loss": 0.5287,
"step": 218
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.9827890396118164,
"learning_rate": 3.19671589878372e-06,
"loss": 0.4799,
"step": 219
},
{
"epoch": 0.43052837573385516,
"grad_norm": 0.8296178579330444,
"learning_rate": 3.1814639411384953e-06,
"loss": 0.4725,
"step": 220
},
{
"epoch": 0.4324853228962818,
"grad_norm": 0.8092741370201111,
"learning_rate": 3.1661845342250874e-06,
"loss": 0.5054,
"step": 221
},
{
"epoch": 0.4344422700587084,
"grad_norm": 1.160125732421875,
"learning_rate": 3.1508782934957804e-06,
"loss": 0.6022,
"step": 222
},
{
"epoch": 0.436399217221135,
"grad_norm": 0.871837854385376,
"learning_rate": 3.1355458354837183e-06,
"loss": 0.4545,
"step": 223
},
{
"epoch": 0.4383561643835616,
"grad_norm": 0.8639246225357056,
"learning_rate": 3.1201877777780724e-06,
"loss": 0.449,
"step": 224
},
{
"epoch": 0.44031311154598823,
"grad_norm": 0.9144279956817627,
"learning_rate": 3.1048047389991693e-06,
"loss": 0.4308,
"step": 225
},
{
"epoch": 0.44227005870841485,
"grad_norm": 1.0165725946426392,
"learning_rate": 3.089397338773569e-06,
"loss": 0.4997,
"step": 226
},
{
"epoch": 0.44422700587084146,
"grad_norm": 0.7787861824035645,
"learning_rate": 3.0739661977091027e-06,
"loss": 0.4408,
"step": 227
},
{
"epoch": 0.4461839530332681,
"grad_norm": 0.8962077498435974,
"learning_rate": 3.0585119373698858e-06,
"loss": 0.4879,
"step": 228
},
{
"epoch": 0.4481409001956947,
"grad_norm": 0.8481760621070862,
"learning_rate": 3.04303518025127e-06,
"loss": 0.4525,
"step": 229
},
{
"epoch": 0.4500978473581213,
"grad_norm": 0.9689728021621704,
"learning_rate": 3.0275365497547747e-06,
"loss": 0.5199,
"step": 230
},
{
"epoch": 0.4520547945205479,
"grad_norm": 1.0657813549041748,
"learning_rate": 3.012016670162977e-06,
"loss": 0.4834,
"step": 231
},
{
"epoch": 0.45401174168297453,
"grad_norm": 1.0324097871780396,
"learning_rate": 2.9964761666143638e-06,
"loss": 0.5407,
"step": 232
},
{
"epoch": 0.45596868884540115,
"grad_norm": 0.8452147245407104,
"learning_rate": 2.980915665078153e-06,
"loss": 0.5108,
"step": 233
},
{
"epoch": 0.45792563600782776,
"grad_norm": 1.1484103202819824,
"learning_rate": 2.9653357923290753e-06,
"loss": 0.4082,
"step": 234
},
{
"epoch": 0.4598825831702544,
"grad_norm": 0.859313428401947,
"learning_rate": 2.949737175922135e-06,
"loss": 0.4752,
"step": 235
},
{
"epoch": 0.461839530332681,
"grad_norm": 0.87496417760849,
"learning_rate": 2.9341204441673267e-06,
"loss": 0.4624,
"step": 236
},
{
"epoch": 0.4637964774951076,
"grad_norm": 0.9420116543769836,
"learning_rate": 2.9184862261043272e-06,
"loss": 0.4557,
"step": 237
},
{
"epoch": 0.4657534246575342,
"grad_norm": 1.4860702753067017,
"learning_rate": 2.902835151477161e-06,
"loss": 0.4617,
"step": 238
},
{
"epoch": 0.46771037181996084,
"grad_norm": 0.8771023750305176,
"learning_rate": 2.887167850708831e-06,
"loss": 0.5299,
"step": 239
},
{
"epoch": 0.46966731898238745,
"grad_norm": 0.8673617839813232,
"learning_rate": 2.8714849548759293e-06,
"loss": 0.5504,
"step": 240
},
{
"epoch": 0.47162426614481406,
"grad_norm": 0.8307452201843262,
"learning_rate": 2.8557870956832135e-06,
"loss": 0.4735,
"step": 241
},
{
"epoch": 0.4735812133072407,
"grad_norm": 0.9233512282371521,
"learning_rate": 2.840074905438161e-06,
"loss": 0.3701,
"step": 242
},
{
"epoch": 0.4755381604696673,
"grad_norm": 1.0768812894821167,
"learning_rate": 2.8243490170255046e-06,
"loss": 0.4983,
"step": 243
},
{
"epoch": 0.4774951076320939,
"grad_norm": 0.9305315017700195,
"learning_rate": 2.808610063881737e-06,
"loss": 0.4137,
"step": 244
},
{
"epoch": 0.4794520547945205,
"grad_norm": 1.1971187591552734,
"learning_rate": 2.792858679969596e-06,
"loss": 0.452,
"step": 245
},
{
"epoch": 0.48140900195694714,
"grad_norm": 1.314292073249817,
"learning_rate": 2.7770954997525277e-06,
"loss": 0.526,
"step": 246
},
{
"epoch": 0.48336594911937375,
"grad_norm": 1.2386282682418823,
"learning_rate": 2.761321158169134e-06,
"loss": 0.5002,
"step": 247
},
{
"epoch": 0.48532289628180036,
"grad_norm": 0.9772767424583435,
"learning_rate": 2.745536290607593e-06,
"loss": 0.5091,
"step": 248
},
{
"epoch": 0.487279843444227,
"grad_norm": 1.0364662408828735,
"learning_rate": 2.729741532880069e-06,
"loss": 0.4752,
"step": 249
},
{
"epoch": 0.4892367906066536,
"grad_norm": 0.8030025362968445,
"learning_rate": 2.7139375211971e-06,
"loss": 0.462,
"step": 250
},
{
"epoch": 0.4911937377690802,
"grad_norm": 1.3889553546905518,
"learning_rate": 2.6981248921419713e-06,
"loss": 0.4102,
"step": 251
},
{
"epoch": 0.4931506849315068,
"grad_norm": 0.9577500224113464,
"learning_rate": 2.682304282645077e-06,
"loss": 0.5008,
"step": 252
},
{
"epoch": 0.49510763209393344,
"grad_norm": 1.3206193447113037,
"learning_rate": 2.66647632995826e-06,
"loss": 0.4624,
"step": 253
},
{
"epoch": 0.49706457925636005,
"grad_norm": 0.8159929513931274,
"learning_rate": 2.6506416716291466e-06,
"loss": 0.4561,
"step": 254
},
{
"epoch": 0.49902152641878667,
"grad_norm": 0.854573130607605,
"learning_rate": 2.634800945475465e-06,
"loss": 0.5503,
"step": 255
},
{
"epoch": 0.5009784735812133,
"grad_norm": 9.345633506774902,
"learning_rate": 2.6189547895593565e-06,
"loss": 0.5216,
"step": 256
},
{
"epoch": 0.50293542074364,
"grad_norm": 0.8881295323371887,
"learning_rate": 2.6031038421616684e-06,
"loss": 0.4713,
"step": 257
},
{
"epoch": 0.5048923679060665,
"grad_norm": 1.7568496465682983,
"learning_rate": 2.587248741756253e-06,
"loss": 0.5096,
"step": 258
},
{
"epoch": 0.5068493150684932,
"grad_norm": 0.8306764960289001,
"learning_rate": 2.5713901269842405e-06,
"loss": 0.4504,
"step": 259
},
{
"epoch": 0.5088062622309197,
"grad_norm": 0.9716941118240356,
"learning_rate": 2.555528636628324e-06,
"loss": 0.4668,
"step": 260
},
{
"epoch": 0.5107632093933464,
"grad_norm": 0.8290694355964661,
"learning_rate": 2.53966490958702e-06,
"loss": 0.4288,
"step": 261
},
{
"epoch": 0.512720156555773,
"grad_norm": 0.9514800310134888,
"learning_rate": 2.5237995848489422e-06,
"loss": 0.5157,
"step": 262
},
{
"epoch": 0.5146771037181996,
"grad_norm": 1.515278935432434,
"learning_rate": 2.507933301467056e-06,
"loss": 0.4863,
"step": 263
},
{
"epoch": 0.5166340508806262,
"grad_norm": 0.9582359790802002,
"learning_rate": 2.4920666985329446e-06,
"loss": 0.4694,
"step": 264
},
{
"epoch": 0.5185909980430529,
"grad_norm": 0.8128112554550171,
"learning_rate": 2.4762004151510586e-06,
"loss": 0.4244,
"step": 265
},
{
"epoch": 0.5205479452054794,
"grad_norm": 1.151044487953186,
"learning_rate": 2.4603350904129802e-06,
"loss": 0.4555,
"step": 266
},
{
"epoch": 0.5225048923679061,
"grad_norm": 0.8072860240936279,
"learning_rate": 2.4444713633716764e-06,
"loss": 0.4173,
"step": 267
},
{
"epoch": 0.5244618395303327,
"grad_norm": 1.8496747016906738,
"learning_rate": 2.42860987301576e-06,
"loss": 0.4206,
"step": 268
},
{
"epoch": 0.5264187866927593,
"grad_norm": 1.096216082572937,
"learning_rate": 2.4127512582437486e-06,
"loss": 0.4501,
"step": 269
},
{
"epoch": 0.5283757338551859,
"grad_norm": 0.9519087076187134,
"learning_rate": 2.3968961578383324e-06,
"loss": 0.4848,
"step": 270
},
{
"epoch": 0.5303326810176126,
"grad_norm": 0.9204405546188354,
"learning_rate": 2.3810452104406444e-06,
"loss": 0.4526,
"step": 271
},
{
"epoch": 0.5322896281800391,
"grad_norm": 0.8748743534088135,
"learning_rate": 2.3651990545245357e-06,
"loss": 0.4547,
"step": 272
},
{
"epoch": 0.5342465753424658,
"grad_norm": 1.6212592124938965,
"learning_rate": 2.3493583283708542e-06,
"loss": 0.4937,
"step": 273
},
{
"epoch": 0.5362035225048923,
"grad_norm": 0.9793727993965149,
"learning_rate": 2.3335236700417404e-06,
"loss": 0.4456,
"step": 274
},
{
"epoch": 0.538160469667319,
"grad_norm": 1.7149184942245483,
"learning_rate": 2.3176957173549236e-06,
"loss": 0.4737,
"step": 275
},
{
"epoch": 0.5401174168297456,
"grad_norm": 0.9447053074836731,
"learning_rate": 2.3018751078580287e-06,
"loss": 0.4496,
"step": 276
},
{
"epoch": 0.5420743639921722,
"grad_norm": 0.9250771999359131,
"learning_rate": 2.2860624788029013e-06,
"loss": 0.4674,
"step": 277
},
{
"epoch": 0.5440313111545988,
"grad_norm": 0.8631194233894348,
"learning_rate": 2.2702584671199317e-06,
"loss": 0.48,
"step": 278
},
{
"epoch": 0.5459882583170255,
"grad_norm": 0.8921899199485779,
"learning_rate": 2.2544637093924072e-06,
"loss": 0.4009,
"step": 279
},
{
"epoch": 0.547945205479452,
"grad_norm": 0.811696469783783,
"learning_rate": 2.238678841830867e-06,
"loss": 0.4714,
"step": 280
},
{
"epoch": 0.5499021526418787,
"grad_norm": 0.7900722026824951,
"learning_rate": 2.2229045002474727e-06,
"loss": 0.3956,
"step": 281
},
{
"epoch": 0.5518590998043053,
"grad_norm": 0.8538399934768677,
"learning_rate": 2.2071413200304046e-06,
"loss": 0.3488,
"step": 282
},
{
"epoch": 0.5538160469667319,
"grad_norm": 0.9310709238052368,
"learning_rate": 2.1913899361182634e-06,
"loss": 0.3915,
"step": 283
},
{
"epoch": 0.5557729941291585,
"grad_norm": 0.8419170379638672,
"learning_rate": 2.1756509829744958e-06,
"loss": 0.4716,
"step": 284
},
{
"epoch": 0.5577299412915852,
"grad_norm": 1.2008228302001953,
"learning_rate": 2.1599250945618404e-06,
"loss": 0.4493,
"step": 285
},
{
"epoch": 0.5596868884540117,
"grad_norm": 0.8127449750900269,
"learning_rate": 2.1442129043167877e-06,
"loss": 0.4223,
"step": 286
},
{
"epoch": 0.5616438356164384,
"grad_norm": 1.0872187614440918,
"learning_rate": 2.128515045124071e-06,
"loss": 0.4814,
"step": 287
},
{
"epoch": 0.5636007827788649,
"grad_norm": 0.9573928713798523,
"learning_rate": 2.1128321492911697e-06,
"loss": 0.4606,
"step": 288
},
{
"epoch": 0.5655577299412916,
"grad_norm": 0.7555910348892212,
"learning_rate": 2.0971648485228404e-06,
"loss": 0.446,
"step": 289
},
{
"epoch": 0.5675146771037182,
"grad_norm": 0.9281080961227417,
"learning_rate": 2.0815137738956736e-06,
"loss": 0.4224,
"step": 290
},
{
"epoch": 0.5694716242661448,
"grad_norm": 1.0036050081253052,
"learning_rate": 2.0658795558326745e-06,
"loss": 0.4476,
"step": 291
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.8064005970954895,
"learning_rate": 2.0502628240778655e-06,
"loss": 0.4518,
"step": 292
},
{
"epoch": 0.5733855185909981,
"grad_norm": 0.8491390347480774,
"learning_rate": 2.034664207670925e-06,
"loss": 0.4947,
"step": 293
},
{
"epoch": 0.5753424657534246,
"grad_norm": 1.433266043663025,
"learning_rate": 2.019084334921849e-06,
"loss": 0.4929,
"step": 294
},
{
"epoch": 0.5772994129158513,
"grad_norm": 0.8420299291610718,
"learning_rate": 2.003523833385637e-06,
"loss": 0.4533,
"step": 295
},
{
"epoch": 0.5792563600782779,
"grad_norm": 2.3586318492889404,
"learning_rate": 1.987983329837024e-06,
"loss": 0.4257,
"step": 296
},
{
"epoch": 0.5812133072407045,
"grad_norm": 0.85833340883255,
"learning_rate": 1.972463450245226e-06,
"loss": 0.4875,
"step": 297
},
{
"epoch": 0.5831702544031311,
"grad_norm": 0.7927659749984741,
"learning_rate": 1.956964819748731e-06,
"loss": 0.415,
"step": 298
},
{
"epoch": 0.5851272015655578,
"grad_norm": 0.8850895762443542,
"learning_rate": 1.9414880626301147e-06,
"loss": 0.409,
"step": 299
},
{
"epoch": 0.5870841487279843,
"grad_norm": 1.509407877922058,
"learning_rate": 1.9260338022908972e-06,
"loss": 0.5041,
"step": 300
},
{
"epoch": 0.589041095890411,
"grad_norm": 1.5269814729690552,
"learning_rate": 1.9106026612264316e-06,
"loss": 0.4222,
"step": 301
},
{
"epoch": 0.5909980430528375,
"grad_norm": 1.386004090309143,
"learning_rate": 1.895195261000831e-06,
"loss": 0.5278,
"step": 302
},
{
"epoch": 0.5929549902152642,
"grad_norm": 1.278283953666687,
"learning_rate": 1.8798122222219288e-06,
"loss": 0.4823,
"step": 303
},
{
"epoch": 0.5949119373776908,
"grad_norm": 0.8502036333084106,
"learning_rate": 1.8644541645162834e-06,
"loss": 0.4682,
"step": 304
},
{
"epoch": 0.5968688845401174,
"grad_norm": 0.8835340142250061,
"learning_rate": 1.84912170650422e-06,
"loss": 0.3474,
"step": 305
},
{
"epoch": 0.598825831702544,
"grad_norm": 0.8175051212310791,
"learning_rate": 1.833815465774913e-06,
"loss": 0.4262,
"step": 306
},
{
"epoch": 0.6007827788649707,
"grad_norm": 1.031742811203003,
"learning_rate": 1.818536058861506e-06,
"loss": 0.4432,
"step": 307
},
{
"epoch": 0.6027397260273972,
"grad_norm": 0.9526416659355164,
"learning_rate": 1.803284101216281e-06,
"loss": 0.3981,
"step": 308
},
{
"epoch": 0.6046966731898239,
"grad_norm": 0.9259310364723206,
"learning_rate": 1.7880602071858694e-06,
"loss": 0.4249,
"step": 309
},
{
"epoch": 0.6066536203522505,
"grad_norm": 1.0978782176971436,
"learning_rate": 1.7728649899865024e-06,
"loss": 0.4955,
"step": 310
},
{
"epoch": 0.6086105675146771,
"grad_norm": 0.8304716944694519,
"learning_rate": 1.7576990616793139e-06,
"loss": 0.4666,
"step": 311
},
{
"epoch": 0.6105675146771037,
"grad_norm": 2.960554838180542,
"learning_rate": 1.7425630331456821e-06,
"loss": 0.412,
"step": 312
},
{
"epoch": 0.6125244618395304,
"grad_norm": 0.8440503478050232,
"learning_rate": 1.7274575140626318e-06,
"loss": 0.4814,
"step": 313
},
{
"epoch": 0.6144814090019569,
"grad_norm": 0.8478916883468628,
"learning_rate": 1.7123831128782686e-06,
"loss": 0.4708,
"step": 314
},
{
"epoch": 0.6164383561643836,
"grad_norm": 0.8599239587783813,
"learning_rate": 1.697340436787273e-06,
"loss": 0.428,
"step": 315
},
{
"epoch": 0.6183953033268101,
"grad_norm": 1.151842474937439,
"learning_rate": 1.6823300917064462e-06,
"loss": 0.3433,
"step": 316
},
{
"epoch": 0.6203522504892368,
"grad_norm": 0.8544068336486816,
"learning_rate": 1.6673526822502982e-06,
"loss": 0.4431,
"step": 317
},
{
"epoch": 0.6223091976516634,
"grad_norm": 1.1891425848007202,
"learning_rate": 1.6524088117066984e-06,
"loss": 0.4334,
"step": 318
},
{
"epoch": 0.62426614481409,
"grad_norm": 1.1379172801971436,
"learning_rate": 1.637499082012574e-06,
"loss": 0.5514,
"step": 319
},
{
"epoch": 0.6262230919765166,
"grad_norm": 1.0814030170440674,
"learning_rate": 1.6226240937296617e-06,
"loss": 0.4772,
"step": 320
},
{
"epoch": 0.6281800391389433,
"grad_norm": 0.9527184963226318,
"learning_rate": 1.6077844460203207e-06,
"loss": 0.4292,
"step": 321
},
{
"epoch": 0.6301369863013698,
"grad_norm": 0.9083294868469238,
"learning_rate": 1.5929807366233979e-06,
"loss": 0.501,
"step": 322
},
{
"epoch": 0.6320939334637965,
"grad_norm": 1.4445644617080688,
"learning_rate": 1.5782135618301486e-06,
"loss": 0.4924,
"step": 323
},
{
"epoch": 0.6340508806262231,
"grad_norm": 1.361970067024231,
"learning_rate": 1.56348351646022e-06,
"loss": 0.4487,
"step": 324
},
{
"epoch": 0.6360078277886497,
"grad_norm": 0.8321120142936707,
"learning_rate": 1.5487911938376925e-06,
"loss": 0.4566,
"step": 325
},
{
"epoch": 0.6379647749510763,
"grad_norm": 1.1182819604873657,
"learning_rate": 1.5341371857671782e-06,
"loss": 0.4253,
"step": 326
},
{
"epoch": 0.639921722113503,
"grad_norm": 1.133865475654602,
"learning_rate": 1.5195220825099863e-06,
"loss": 0.4212,
"step": 327
},
{
"epoch": 0.6418786692759295,
"grad_norm": 0.9962513446807861,
"learning_rate": 1.5049464727603453e-06,
"loss": 0.4702,
"step": 328
},
{
"epoch": 0.6438356164383562,
"grad_norm": 1.1037347316741943,
"learning_rate": 1.4904109436216885e-06,
"loss": 0.5035,
"step": 329
},
{
"epoch": 0.6457925636007827,
"grad_norm": 1.0168620347976685,
"learning_rate": 1.475916080583012e-06,
"loss": 0.4762,
"step": 330
},
{
"epoch": 0.6477495107632094,
"grad_norm": 1.1695796251296997,
"learning_rate": 1.4614624674952843e-06,
"loss": 0.4313,
"step": 331
},
{
"epoch": 0.649706457925636,
"grad_norm": 1.4158042669296265,
"learning_rate": 1.4470506865479337e-06,
"loss": 0.4798,
"step": 332
},
{
"epoch": 0.6516634050880626,
"grad_norm": 0.9545938968658447,
"learning_rate": 1.4326813182453959e-06,
"loss": 0.4126,
"step": 333
},
{
"epoch": 0.6536203522504892,
"grad_norm": 1.0253559350967407,
"learning_rate": 1.4183549413837288e-06,
"loss": 0.4633,
"step": 334
},
{
"epoch": 0.6555772994129159,
"grad_norm": 0.9522657990455627,
"learning_rate": 1.4040721330273063e-06,
"loss": 0.4716,
"step": 335
},
{
"epoch": 0.6575342465753424,
"grad_norm": 0.9612335562705994,
"learning_rate": 1.3898334684855647e-06,
"loss": 0.4699,
"step": 336
},
{
"epoch": 0.6594911937377691,
"grad_norm": 0.9365352392196655,
"learning_rate": 1.375639521289836e-06,
"loss": 0.4775,
"step": 337
},
{
"epoch": 0.6614481409001957,
"grad_norm": 0.9329326152801514,
"learning_rate": 1.3614908631702435e-06,
"loss": 0.4236,
"step": 338
},
{
"epoch": 0.6614481409001957,
"eval_accuracy": 0.8283926414598568,
"eval_accuracy_first_token": 0.9538461538461539,
"eval_accuracy_first_token_all": 0.9723295718039883,
"eval_accuracy_first_token_all_total": 6469,
"eval_accuracy_first_token_calculate": 0.9090909090909091,
"eval_accuracy_first_token_calculate_total": 44,
"eval_accuracy_first_token_execute": 1.0,
"eval_accuracy_first_token_execute_total": 202,
"eval_accuracy_first_token_get": 0.9517543859649122,
"eval_accuracy_first_token_get_total": 456,
"eval_accuracy_first_token_python": 0.8838383838383839,
"eval_accuracy_first_token_python_total": 990,
"eval_loss": 0.5066910982131958,
"eval_perplexity": 1.2021342846813718,
"eval_runtime": 525.6643,
"eval_samples_per_second": 1.265,
"eval_steps_per_second": 0.16,
"eval_total_number_first_token": 9360,
"step": 338
},
{
"epoch": 0.6634050880626223,
"grad_norm": 0.9786916375160217,
"learning_rate": 1.3473880640326725e-06,
"loss": 0.4361,
"step": 339
},
{
"epoch": 0.6653620352250489,
"grad_norm": 0.9186453819274902,
"learning_rate": 1.3333316919358159e-06,
"loss": 0.4658,
"step": 340
},
{
"epoch": 0.6673189823874756,
"grad_norm": 1.02847421169281,
"learning_rate": 1.3193223130682937e-06,
"loss": 0.4517,
"step": 341
},
{
"epoch": 0.6692759295499021,
"grad_norm": 0.970281720161438,
"learning_rate": 1.3053604917258428e-06,
"loss": 0.4617,
"step": 342
},
{
"epoch": 0.6712328767123288,
"grad_norm": 0.7810537219047546,
"learning_rate": 1.2914467902885902e-06,
"loss": 0.4246,
"step": 343
},
{
"epoch": 0.6731898238747553,
"grad_norm": 0.9498399496078491,
"learning_rate": 1.2775817691984032e-06,
"loss": 0.4706,
"step": 344
},
{
"epoch": 0.675146771037182,
"grad_norm": 0.9036231637001038,
"learning_rate": 1.2637659869363085e-06,
"loss": 0.4826,
"step": 345
},
{
"epoch": 0.6771037181996086,
"grad_norm": 0.8129305243492126,
"learning_rate": 1.2500000000000007e-06,
"loss": 0.4163,
"step": 346
},
{
"epoch": 0.6790606653620352,
"grad_norm": 1.4746164083480835,
"learning_rate": 1.2362843628814267e-06,
"loss": 0.3961,
"step": 347
},
{
"epoch": 0.6810176125244618,
"grad_norm": 11.255887031555176,
"learning_rate": 1.222619628044449e-06,
"loss": 0.4761,
"step": 348
},
{
"epoch": 0.6829745596868885,
"grad_norm": 0.9121260643005371,
"learning_rate": 1.2090063459025956e-06,
"loss": 0.4277,
"step": 349
},
{
"epoch": 0.684931506849315,
"grad_norm": 0.9116764068603516,
"learning_rate": 1.1954450647968856e-06,
"loss": 0.4696,
"step": 350
},
{
"epoch": 0.6868884540117417,
"grad_norm": 1.206604242324829,
"learning_rate": 1.181936330973744e-06,
"loss": 0.4205,
"step": 351
},
{
"epoch": 0.6888454011741683,
"grad_norm": 0.8744117617607117,
"learning_rate": 1.1684806885630003e-06,
"loss": 0.5077,
"step": 352
},
{
"epoch": 0.6908023483365949,
"grad_norm": 2.155042886734009,
"learning_rate": 1.155078679555969e-06,
"loss": 0.4193,
"step": 353
},
{
"epoch": 0.6927592954990215,
"grad_norm": 0.9258475303649902,
"learning_rate": 1.1417308437836181e-06,
"loss": 0.3645,
"step": 354
},
{
"epoch": 0.6947162426614482,
"grad_norm": 0.7997338771820068,
"learning_rate": 1.1284377188948258e-06,
"loss": 0.4044,
"step": 355
},
{
"epoch": 0.6966731898238747,
"grad_norm": 0.8342923521995544,
"learning_rate": 1.1151998403347245e-06,
"loss": 0.4132,
"step": 356
},
{
"epoch": 0.6986301369863014,
"grad_norm": 1.0009496212005615,
"learning_rate": 1.1020177413231334e-06,
"loss": 0.4046,
"step": 357
},
{
"epoch": 0.700587084148728,
"grad_norm": 1.0892616510391235,
"learning_rate": 1.0888919528330778e-06,
"loss": 0.4878,
"step": 358
},
{
"epoch": 0.7025440313111546,
"grad_norm": 0.829866886138916,
"learning_rate": 1.0758230035694031e-06,
"loss": 0.4876,
"step": 359
},
{
"epoch": 0.7045009784735812,
"grad_norm": 0.9134871363639832,
"learning_rate": 1.062811419947482e-06,
"loss": 0.5027,
"step": 360
},
{
"epoch": 0.7064579256360078,
"grad_norm": 1.1233887672424316,
"learning_rate": 1.049857726072005e-06,
"loss": 0.3487,
"step": 361
},
{
"epoch": 0.7084148727984344,
"grad_norm": 0.8092291355133057,
"learning_rate": 1.036962443715872e-06,
"loss": 0.5009,
"step": 362
},
{
"epoch": 0.7103718199608611,
"grad_norm": 1.730331301689148,
"learning_rate": 1.0241260922991761e-06,
"loss": 0.386,
"step": 363
},
{
"epoch": 0.7123287671232876,
"grad_norm": 0.9802207946777344,
"learning_rate": 1.0113491888682802e-06,
"loss": 0.4209,
"step": 364
},
{
"epoch": 0.7142857142857143,
"grad_norm": 1.0146572589874268,
"learning_rate": 9.986322480749926e-07,
"loss": 0.6119,
"step": 365
},
{
"epoch": 0.7162426614481409,
"grad_norm": 0.930644154548645,
"learning_rate": 9.85975782155834e-07,
"loss": 0.4453,
"step": 366
},
{
"epoch": 0.7181996086105675,
"grad_norm": 1.2394402027130127,
"learning_rate": 9.733803009114045e-07,
"loss": 0.4364,
"step": 367
},
{
"epoch": 0.7201565557729941,
"grad_norm": 0.8096799850463867,
"learning_rate": 9.608463116858544e-07,
"loss": 0.3672,
"step": 368
},
{
"epoch": 0.7221135029354208,
"grad_norm": 0.9330917596817017,
"learning_rate": 9.483743193464409e-07,
"loss": 0.4665,
"step": 369
},
{
"epoch": 0.7240704500978473,
"grad_norm": 1.0829280614852905,
"learning_rate": 9.359648262631962e-07,
"loss": 0.4924,
"step": 370
},
{
"epoch": 0.726027397260274,
"grad_norm": 1.0950247049331665,
"learning_rate": 9.236183322886946e-07,
"loss": 0.4907,
"step": 371
},
{
"epoch": 0.7279843444227005,
"grad_norm": 0.8494971394538879,
"learning_rate": 9.113353347379097e-07,
"loss": 0.4286,
"step": 372
},
{
"epoch": 0.7299412915851272,
"grad_norm": 0.9138147830963135,
"learning_rate": 8.991163283681945e-07,
"loss": 0.4396,
"step": 373
},
{
"epoch": 0.7318982387475538,
"grad_norm": 1.6995892524719238,
"learning_rate": 8.869618053593429e-07,
"loss": 0.3989,
"step": 374
},
{
"epoch": 0.7338551859099804,
"grad_norm": 0.9424477815628052,
"learning_rate": 8.748722552937688e-07,
"loss": 0.4371,
"step": 375
},
{
"epoch": 0.735812133072407,
"grad_norm": 1.2042125463485718,
"learning_rate": 8.628481651367876e-07,
"loss": 0.4337,
"step": 376
},
{
"epoch": 0.7377690802348337,
"grad_norm": 0.9822342395782471,
"learning_rate": 8.508900192169964e-07,
"loss": 0.4329,
"step": 377
},
{
"epoch": 0.7397260273972602,
"grad_norm": 1.0332896709442139,
"learning_rate": 8.389982992067688e-07,
"loss": 0.4286,
"step": 378
},
{
"epoch": 0.7416829745596869,
"grad_norm": 0.8743665218353271,
"learning_rate": 8.271734841028553e-07,
"loss": 0.487,
"step": 379
},
{
"epoch": 0.7436399217221135,
"grad_norm": 0.9147298336029053,
"learning_rate": 8.154160502070804e-07,
"loss": 0.453,
"step": 380
},
{
"epoch": 0.7455968688845401,
"grad_norm": 1.113299012184143,
"learning_rate": 8.037264711071699e-07,
"loss": 0.4432,
"step": 381
},
{
"epoch": 0.7475538160469667,
"grad_norm": 0.934984564781189,
"learning_rate": 7.921052176576643e-07,
"loss": 0.5102,
"step": 382
},
{
"epoch": 0.7495107632093934,
"grad_norm": 0.8149503469467163,
"learning_rate": 7.805527579609575e-07,
"loss": 0.4834,
"step": 383
},
{
"epoch": 0.7514677103718199,
"grad_norm": 1.2893983125686646,
"learning_rate": 7.690695573484433e-07,
"loss": 0.3211,
"step": 384
},
{
"epoch": 0.7534246575342466,
"grad_norm": 1.0519015789031982,
"learning_rate": 7.576560783617667e-07,
"loss": 0.4613,
"step": 385
},
{
"epoch": 0.7553816046966731,
"grad_norm": 0.8619464039802551,
"learning_rate": 7.463127807341966e-07,
"loss": 0.4728,
"step": 386
},
{
"epoch": 0.7573385518590998,
"grad_norm": 0.890130341053009,
"learning_rate": 7.35040121372109e-07,
"loss": 0.4721,
"step": 387
},
{
"epoch": 0.7592954990215264,
"grad_norm": 1.1289362907409668,
"learning_rate": 7.238385543365783e-07,
"loss": 0.4206,
"step": 388
},
{
"epoch": 0.761252446183953,
"grad_norm": 0.8591368198394775,
"learning_rate": 7.127085308250914e-07,
"loss": 0.415,
"step": 389
},
{
"epoch": 0.7632093933463796,
"grad_norm": 0.9674418568611145,
"learning_rate": 7.016504991533727e-07,
"loss": 0.5114,
"step": 390
},
{
"epoch": 0.7651663405088063,
"grad_norm": 1.0890218019485474,
"learning_rate": 6.906649047373246e-07,
"loss": 0.3641,
"step": 391
},
{
"epoch": 0.7671232876712328,
"grad_norm": 0.9494483470916748,
"learning_rate": 6.797521900750897e-07,
"loss": 0.4682,
"step": 392
},
{
"epoch": 0.7690802348336595,
"grad_norm": 0.9544976949691772,
"learning_rate": 6.689127947292232e-07,
"loss": 0.4227,
"step": 393
},
{
"epoch": 0.7710371819960861,
"grad_norm": 2.679705858230591,
"learning_rate": 6.581471553089874e-07,
"loss": 0.4482,
"step": 394
},
{
"epoch": 0.7729941291585127,
"grad_norm": 0.8427915573120117,
"learning_rate": 6.474557054527709e-07,
"loss": 0.4048,
"step": 395
},
{
"epoch": 0.7749510763209393,
"grad_norm": 0.8168734312057495,
"learning_rate": 6.368388758106134e-07,
"loss": 0.377,
"step": 396
},
{
"epoch": 0.776908023483366,
"grad_norm": 1.0561057329177856,
"learning_rate": 6.262970940268653e-07,
"loss": 0.4315,
"step": 397
},
{
"epoch": 0.7788649706457925,
"grad_norm": 0.8930473923683167,
"learning_rate": 6.158307847229594e-07,
"loss": 0.5171,
"step": 398
},
{
"epoch": 0.7808219178082192,
"grad_norm": 1.0137521028518677,
"learning_rate": 6.05440369480308e-07,
"loss": 0.4549,
"step": 399
},
{
"epoch": 0.7827788649706457,
"grad_norm": 0.9667198061943054,
"learning_rate": 5.951262668233232e-07,
"loss": 0.4213,
"step": 400
},
{
"epoch": 0.7847358121330724,
"grad_norm": 0.7895818948745728,
"learning_rate": 5.848888922025553e-07,
"loss": 0.427,
"step": 401
},
{
"epoch": 0.786692759295499,
"grad_norm": 1.007455825805664,
"learning_rate": 5.747286579779607e-07,
"loss": 0.4125,
"step": 402
},
{
"epoch": 0.7886497064579256,
"grad_norm": 1.8778549432754517,
"learning_rate": 5.646459734022938e-07,
"loss": 0.4568,
"step": 403
},
{
"epoch": 0.7906066536203522,
"grad_norm": 0.976000964641571,
"learning_rate": 5.546412446046187e-07,
"loss": 0.5,
"step": 404
},
{
"epoch": 0.7925636007827789,
"grad_norm": 0.9260036945343018,
"learning_rate": 5.447148745739522e-07,
"loss": 0.4729,
"step": 405
},
{
"epoch": 0.7945205479452054,
"grad_norm": 0.851002037525177,
"learning_rate": 5.348672631430319e-07,
"loss": 0.4294,
"step": 406
},
{
"epoch": 0.7964774951076321,
"grad_norm": 0.976465106010437,
"learning_rate": 5.250988069722096e-07,
"loss": 0.4655,
"step": 407
},
{
"epoch": 0.7984344422700587,
"grad_norm": 0.9321781396865845,
"learning_rate": 5.154098995334769e-07,
"loss": 0.3931,
"step": 408
},
{
"epoch": 0.8003913894324853,
"grad_norm": 0.8924025297164917,
"learning_rate": 5.058009310946119e-07,
"loss": 0.4222,
"step": 409
},
{
"epoch": 0.8023483365949119,
"grad_norm": 0.8116724491119385,
"learning_rate": 4.962722887034616e-07,
"loss": 0.325,
"step": 410
},
{
"epoch": 0.8043052837573386,
"grad_norm": 0.9633209705352783,
"learning_rate": 4.868243561723535e-07,
"loss": 0.3769,
"step": 411
},
{
"epoch": 0.8062622309197651,
"grad_norm": 0.902252733707428,
"learning_rate": 4.774575140626317e-07,
"loss": 0.3959,
"step": 412
},
{
"epoch": 0.8082191780821918,
"grad_norm": 0.8941038250923157,
"learning_rate": 4.681721396693303e-07,
"loss": 0.4998,
"step": 413
},
{
"epoch": 0.8101761252446184,
"grad_norm": 1.213836669921875,
"learning_rate": 4.589686070059762e-07,
"loss": 0.5012,
"step": 414
},
{
"epoch": 0.812133072407045,
"grad_norm": 1.0174344778060913,
"learning_rate": 4.4984728678952234e-07,
"loss": 0.468,
"step": 415
},
{
"epoch": 0.8140900195694716,
"grad_norm": 1.8333814144134521,
"learning_rate": 4.4080854642541833e-07,
"loss": 0.4941,
"step": 416
},
{
"epoch": 0.8160469667318982,
"grad_norm": 1.6971678733825684,
"learning_rate": 4.318527499928074e-07,
"loss": 0.3649,
"step": 417
},
{
"epoch": 0.8180039138943248,
"grad_norm": 0.8866695165634155,
"learning_rate": 4.229802582298634e-07,
"loss": 0.4657,
"step": 418
},
{
"epoch": 0.8199608610567515,
"grad_norm": 1.3764787912368774,
"learning_rate": 4.141914285192619e-07,
"loss": 0.3836,
"step": 419
},
{
"epoch": 0.821917808219178,
"grad_norm": 0.9406548142433167,
"learning_rate": 4.0548661487378184e-07,
"loss": 0.497,
"step": 420
},
{
"epoch": 0.8238747553816047,
"grad_norm": 0.8251882195472717,
"learning_rate": 3.9686616792204677e-07,
"loss": 0.4032,
"step": 421
},
{
"epoch": 0.8258317025440313,
"grad_norm": 0.8226965069770813,
"learning_rate": 3.8833043489440477e-07,
"loss": 0.4526,
"step": 422
},
{
"epoch": 0.8277886497064579,
"grad_norm": 0.9033458232879639,
"learning_rate": 3.798797596089351e-07,
"loss": 0.4149,
"step": 423
},
{
"epoch": 0.8297455968688845,
"grad_norm": 0.9945986866950989,
"learning_rate": 3.715144824576078e-07,
"loss": 0.5138,
"step": 424
},
{
"epoch": 0.8317025440313112,
"grad_norm": 1.1671781539916992,
"learning_rate": 3.632349403925664e-07,
"loss": 0.4718,
"step": 425
},
{
"epoch": 0.8336594911937377,
"grad_norm": 1.2945449352264404,
"learning_rate": 3.5504146691255736e-07,
"loss": 0.4514,
"step": 426
},
{
"epoch": 0.8356164383561644,
"grad_norm": 1.3590197563171387,
"learning_rate": 3.469343920494986e-07,
"loss": 0.4147,
"step": 427
},
{
"epoch": 0.837573385518591,
"grad_norm": 0.8810437917709351,
"learning_rate": 3.389140423551834e-07,
"loss": 0.4462,
"step": 428
},
{
"epoch": 0.8395303326810176,
"grad_norm": 0.9122494459152222,
"learning_rate": 3.3098074088812686e-07,
"loss": 0.4766,
"step": 429
},
{
"epoch": 0.8414872798434442,
"grad_norm": 0.8525986075401306,
"learning_rate": 3.2313480720055747e-07,
"loss": 0.3684,
"step": 430
},
{
"epoch": 0.8434442270058709,
"grad_norm": 1.0988531112670898,
"learning_rate": 3.153765573255377e-07,
"loss": 0.4956,
"step": 431
},
{
"epoch": 0.8454011741682974,
"grad_norm": 0.7911211848258972,
"learning_rate": 3.0770630376424276e-07,
"loss": 0.4842,
"step": 432
},
{
"epoch": 0.8473581213307241,
"grad_norm": 1.0055835247039795,
"learning_rate": 3.0012435547336737e-07,
"loss": 0.3518,
"step": 433
},
{
"epoch": 0.8493150684931506,
"grad_norm": 1.304575800895691,
"learning_rate": 2.9263101785268253e-07,
"loss": 0.3509,
"step": 434
},
{
"epoch": 0.8512720156555773,
"grad_norm": 0.9222425818443298,
"learning_rate": 2.8522659273273606e-07,
"loss": 0.3888,
"step": 435
},
{
"epoch": 0.8532289628180039,
"grad_norm": 0.9765827059745789,
"learning_rate": 2.779113783626916e-07,
"loss": 0.4616,
"step": 436
},
{
"epoch": 0.8551859099804305,
"grad_norm": 0.972284734249115,
"learning_rate": 2.7068566939831646e-07,
"loss": 0.3573,
"step": 437
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.9025648832321167,
"learning_rate": 2.6354975689011576e-07,
"loss": 0.4246,
"step": 438
},
{
"epoch": 0.8590998043052838,
"grad_norm": 0.8234553933143616,
"learning_rate": 2.5650392827160446e-07,
"loss": 0.3739,
"step": 439
},
{
"epoch": 0.8610567514677103,
"grad_norm": 1.1872916221618652,
"learning_rate": 2.4954846734773054e-07,
"loss": 0.377,
"step": 440
},
{
"epoch": 0.863013698630137,
"grad_norm": 0.9565138816833496,
"learning_rate": 2.4268365428344737e-07,
"loss": 0.5044,
"step": 441
},
{
"epoch": 0.8649706457925636,
"grad_norm": 1.1466796398162842,
"learning_rate": 2.3590976559242278e-07,
"loss": 0.3848,
"step": 442
},
{
"epoch": 0.8669275929549902,
"grad_norm": 0.9302741289138794,
"learning_rate": 2.29227074125907e-07,
"loss": 0.5157,
"step": 443
},
{
"epoch": 0.8688845401174168,
"grad_norm": 0.9383424520492554,
"learning_rate": 2.2263584906173723e-07,
"loss": 0.4421,
"step": 444
},
{
"epoch": 0.8708414872798435,
"grad_norm": 1.1834505796432495,
"learning_rate": 2.1613635589349756e-07,
"loss": 0.4172,
"step": 445
},
{
"epoch": 0.87279843444227,
"grad_norm": 0.9577175378799438,
"learning_rate": 2.0972885641982605e-07,
"loss": 0.4004,
"step": 446
},
{
"epoch": 0.8747553816046967,
"grad_norm": 0.8691757321357727,
"learning_rate": 2.0341360873386673e-07,
"loss": 0.4321,
"step": 447
},
{
"epoch": 0.8767123287671232,
"grad_norm": 1.0094484090805054,
"learning_rate": 1.97190867212875e-07,
"loss": 0.428,
"step": 448
},
{
"epoch": 0.8786692759295499,
"grad_norm": 0.8963342308998108,
"learning_rate": 1.9106088250797266e-07,
"loss": 0.4358,
"step": 449
},
{
"epoch": 0.8806262230919765,
"grad_norm": 1.7301355600357056,
"learning_rate": 1.8502390153404936e-07,
"loss": 0.4104,
"step": 450
},
{
"epoch": 0.8825831702544031,
"grad_norm": 0.8558318614959717,
"learning_rate": 1.790801674598186e-07,
"loss": 0.4592,
"step": 451
},
{
"epoch": 0.8845401174168297,
"grad_norm": 0.8883755207061768,
"learning_rate": 1.732299196980225e-07,
"loss": 0.416,
"step": 452
},
{
"epoch": 0.8864970645792564,
"grad_norm": 1.679168701171875,
"learning_rate": 1.6747339389578732e-07,
"loss": 0.4899,
"step": 453
},
{
"epoch": 0.8884540117416829,
"grad_norm": 0.8892528414726257,
"learning_rate": 1.6181082192513352e-07,
"loss": 0.4228,
"step": 454
},
{
"epoch": 0.8904109589041096,
"grad_norm": 1.5113455057144165,
"learning_rate": 1.5624243187363442e-07,
"loss": 0.4832,
"step": 455
},
{
"epoch": 0.8923679060665362,
"grad_norm": 1.2870134115219116,
"learning_rate": 1.507684480352292e-07,
"loss": 0.4141,
"step": 456
},
{
"epoch": 0.8943248532289628,
"grad_norm": 1.6229395866394043,
"learning_rate": 1.4538909090118846e-07,
"loss": 0.4619,
"step": 457
},
{
"epoch": 0.8962818003913894,
"grad_norm": 0.8794851899147034,
"learning_rate": 1.4010457715123355e-07,
"loss": 0.3665,
"step": 458
},
{
"epoch": 0.898238747553816,
"grad_norm": 0.8392042517662048,
"learning_rate": 1.3491511964480703e-07,
"loss": 0.4389,
"step": 459
},
{
"epoch": 0.9001956947162426,
"grad_norm": 1.3040436506271362,
"learning_rate": 1.2982092741250145e-07,
"loss": 0.3347,
"step": 460
},
{
"epoch": 0.9021526418786693,
"grad_norm": 2.594942331314087,
"learning_rate": 1.2482220564763669e-07,
"loss": 0.3493,
"step": 461
},
{
"epoch": 0.9041095890410958,
"grad_norm": 1.2146382331848145,
"learning_rate": 1.1991915569799645e-07,
"loss": 0.487,
"step": 462
},
{
"epoch": 0.9060665362035225,
"grad_norm": 0.9857767224311829,
"learning_rate": 1.1511197505771843e-07,
"loss": 0.3678,
"step": 463
},
{
"epoch": 0.9080234833659491,
"grad_norm": 0.9433605670928955,
"learning_rate": 1.1040085735933681e-07,
"loss": 0.4477,
"step": 464
},
{
"epoch": 0.9099804305283757,
"grad_norm": 1.0072382688522339,
"learning_rate": 1.0578599236598708e-07,
"loss": 0.4258,
"step": 465
},
{
"epoch": 0.9119373776908023,
"grad_norm": 0.977323591709137,
"learning_rate": 1.0126756596375687e-07,
"loss": 0.4071,
"step": 466
},
{
"epoch": 0.913894324853229,
"grad_norm": 0.924149751663208,
"learning_rate": 9.684576015420277e-08,
"loss": 0.477,
"step": 467
},
{
"epoch": 0.9158512720156555,
"grad_norm": 0.8529196381568909,
"learning_rate": 9.252075304701929e-08,
"loss": 0.4513,
"step": 468
},
{
"epoch": 0.9178082191780822,
"grad_norm": 1.0572128295898438,
"learning_rate": 8.829271885286095e-08,
"loss": 0.4472,
"step": 469
},
{
"epoch": 0.9197651663405088,
"grad_norm": 3.0187559127807617,
"learning_rate": 8.416182787632871e-08,
"loss": 0.3696,
"step": 470
},
{
"epoch": 0.9217221135029354,
"grad_norm": 1.2419676780700684,
"learning_rate": 8.012824650910938e-08,
"loss": 0.3411,
"step": 471
},
{
"epoch": 0.923679060665362,
"grad_norm": 0.8936371803283691,
"learning_rate": 7.619213722327184e-08,
"loss": 0.4494,
"step": 472
},
{
"epoch": 0.9256360078277887,
"grad_norm": 1.0433343648910522,
"learning_rate": 7.235365856472443e-08,
"loss": 0.4545,
"step": 473
},
{
"epoch": 0.9275929549902152,
"grad_norm": 0.9922037720680237,
"learning_rate": 6.86129651468273e-08,
"loss": 0.4118,
"step": 474
},
{
"epoch": 0.9295499021526419,
"grad_norm": 0.8298634886741638,
"learning_rate": 6.497020764416633e-08,
"loss": 0.4768,
"step": 475
},
{
"epoch": 0.9315068493150684,
"grad_norm": 0.8023221492767334,
"learning_rate": 6.142553278648239e-08,
"loss": 0.4451,
"step": 476
},
{
"epoch": 0.9334637964774951,
"grad_norm": 0.828525960445404,
"learning_rate": 5.7979083352762146e-08,
"loss": 0.3043,
"step": 477
},
{
"epoch": 0.9354207436399217,
"grad_norm": 1.59126615524292,
"learning_rate": 5.463099816548578e-08,
"loss": 0.3771,
"step": 478
},
{
"epoch": 0.9373776908023483,
"grad_norm": 1.2710837125778198,
"learning_rate": 5.1381412085036994e-08,
"loss": 0.4743,
"step": 479
},
{
"epoch": 0.9393346379647749,
"grad_norm": 0.953567624092102,
"learning_rate": 4.823045600426901e-08,
"loss": 0.4077,
"step": 480
},
{
"epoch": 0.9412915851272016,
"grad_norm": 0.9778720736503601,
"learning_rate": 4.5178256843233235e-08,
"loss": 0.4112,
"step": 481
},
{
"epoch": 0.9432485322896281,
"grad_norm": 0.8094834685325623,
"learning_rate": 4.2224937544067254e-08,
"loss": 0.4878,
"step": 482
},
{
"epoch": 0.9452054794520548,
"grad_norm": 0.8327929377555847,
"learning_rate": 3.9370617066040726e-08,
"loss": 0.3676,
"step": 483
},
{
"epoch": 0.9471624266144814,
"grad_norm": 0.8924036622047424,
"learning_rate": 3.661541038076755e-08,
"loss": 0.3628,
"step": 484
},
{
"epoch": 0.949119373776908,
"grad_norm": 1.062476634979248,
"learning_rate": 3.395942846757067e-08,
"loss": 0.3709,
"step": 485
},
{
"epoch": 0.9510763209393346,
"grad_norm": 0.9672690033912659,
"learning_rate": 3.1402778309014284e-08,
"loss": 0.4846,
"step": 486
},
{
"epoch": 0.9530332681017613,
"grad_norm": 0.9301928281784058,
"learning_rate": 2.8945562886593948e-08,
"loss": 0.4465,
"step": 487
},
{
"epoch": 0.9549902152641878,
"grad_norm": 1.6346007585525513,
"learning_rate": 2.6587881176588782e-08,
"loss": 0.3958,
"step": 488
},
{
"epoch": 0.9569471624266145,
"grad_norm": 0.9479952454566956,
"learning_rate": 2.4329828146074096e-08,
"loss": 0.3922,
"step": 489
},
{
"epoch": 0.958904109589041,
"grad_norm": 1.1471753120422363,
"learning_rate": 2.2171494749097243e-08,
"loss": 0.462,
"step": 490
},
{
"epoch": 0.9608610567514677,
"grad_norm": 0.9728820323944092,
"learning_rate": 2.011296792301165e-08,
"loss": 0.4206,
"step": 491
},
{
"epoch": 0.9628180039138943,
"grad_norm": 0.8930822014808655,
"learning_rate": 1.8154330584978785e-08,
"loss": 0.4664,
"step": 492
},
{
"epoch": 0.9647749510763209,
"grad_norm": 1.0260281562805176,
"learning_rate": 1.629566162862445e-08,
"loss": 0.4395,
"step": 493
},
{
"epoch": 0.9667318982387475,
"grad_norm": 1.2178572416305542,
"learning_rate": 1.453703592086353e-08,
"loss": 0.4311,
"step": 494
},
{
"epoch": 0.9686888454011742,
"grad_norm": 0.8803574442863464,
"learning_rate": 1.28785242988827e-08,
"loss": 0.4175,
"step": 495
},
{
"epoch": 0.9706457925636007,
"grad_norm": 0.9738378524780273,
"learning_rate": 1.132019356728853e-08,
"loss": 0.4419,
"step": 496
},
{
"epoch": 0.9726027397260274,
"grad_norm": 0.8282538056373596,
"learning_rate": 9.862106495415469e-09,
"loss": 0.4128,
"step": 497
},
{
"epoch": 0.974559686888454,
"grad_norm": 1.130934715270996,
"learning_rate": 8.504321814798433e-09,
"loss": 0.3772,
"step": 498
},
{
"epoch": 0.9765166340508806,
"grad_norm": 2.3474204540252686,
"learning_rate": 7.246894216806355e-09,
"loss": 0.4271,
"step": 499
},
{
"epoch": 0.9784735812133072,
"grad_norm": 0.9170702695846558,
"learning_rate": 6.089874350439507e-09,
"loss": 0.4163,
"step": 500
},
{
"epoch": 0.9804305283757339,
"grad_norm": 1.3329914808273315,
"learning_rate": 5.033308820289185e-09,
"loss": 0.4318,
"step": 501
},
{
"epoch": 0.9823874755381604,
"grad_norm": 0.9551968574523926,
"learning_rate": 4.07724018466088e-09,
"loss": 0.3538,
"step": 502
},
{
"epoch": 0.9843444227005871,
"grad_norm": 0.9140384197235107,
"learning_rate": 3.2217069538600932e-09,
"loss": 0.4503,
"step": 503
},
{
"epoch": 0.9863013698630136,
"grad_norm": 1.072695016860962,
"learning_rate": 2.4667435886402414e-09,
"loss": 0.4374,
"step": 504
},
{
"epoch": 0.9882583170254403,
"grad_norm": 0.8060042262077332,
"learning_rate": 1.8123804988159909e-09,
"loss": 0.4142,
"step": 505
},
{
"epoch": 0.9902152641878669,
"grad_norm": 1.2433676719665527,
"learning_rate": 1.2586440420372936e-09,
"loss": 0.4401,
"step": 506
},
{
"epoch": 0.9921722113502935,
"grad_norm": 1.1050037145614624,
"learning_rate": 8.0555652272718e-10,
"loss": 0.4379,
"step": 507
},
{
"epoch": 0.9921722113502935,
"eval_accuracy": 0.8291501000753674,
"eval_accuracy_first_token": 0.9575854700854701,
"eval_accuracy_first_token_all": 0.9726387385994744,
"eval_accuracy_first_token_all_total": 6469,
"eval_accuracy_first_token_calculate": 0.9090909090909091,
"eval_accuracy_first_token_calculate_total": 44,
"eval_accuracy_first_token_execute": 1.0,
"eval_accuracy_first_token_execute_total": 202,
"eval_accuracy_first_token_get": 0.956140350877193,
"eval_accuracy_first_token_get_total": 456,
"eval_accuracy_first_token_python": 0.8909090909090909,
"eval_accuracy_first_token_python_total": 990,
"eval_loss": 0.5047600269317627,
"eval_perplexity": 1.201347285698878,
"eval_runtime": 525.3078,
"eval_samples_per_second": 1.266,
"eval_steps_per_second": 0.16,
"eval_total_number_first_token": 9360,
"step": 507
},
{
"epoch": 0.9941291585127201,
"grad_norm": 0.9681710004806519,
"learning_rate": 4.5313619118553256e-10,
"loss": 0.4287,
"step": 508
},
{
"epoch": 0.9960861056751468,
"grad_norm": 0.8318100571632385,
"learning_rate": 2.0139724285161976e-10,
"loss": 0.4405,
"step": 509
},
{
"epoch": 0.9980430528375733,
"grad_norm": 0.8928787708282471,
"learning_rate": 5.0349817733719165e-11,
"loss": 0.3779,
"step": 510
},
{
"epoch": 1.0,
"grad_norm": 2.4657742977142334,
"learning_rate": 0.0,
"loss": 0.4483,
"step": 511
},
{
"epoch": 1.0,
"step": 511,
"total_flos": 529508264312832.0,
"train_loss": 0.47377988486140676,
"train_runtime": 61575.0259,
"train_samples_per_second": 0.133,
"train_steps_per_second": 0.008
}
],
"logging_steps": 1.0,
"max_steps": 511,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5.0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 529508264312832.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}