lora-8b-bio / checkpoint-548 /trainer_state.json
kloodia's picture
Upload folder using huggingface_hub
2442c9d verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9990884229717412,
"eval_steps": 137,
"global_step": 548,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 0.07610916346311569,
"learning_rate": 2e-05,
"loss": 1.795,
"step": 1
},
{
"epoch": 0.0,
"eval_loss": 1.8087825775146484,
"eval_runtime": 75.9539,
"eval_samples_per_second": 65.829,
"eval_steps_per_second": 16.457,
"step": 1
},
{
"epoch": 0.0,
"grad_norm": 0.0771929994225502,
"learning_rate": 4e-05,
"loss": 1.7825,
"step": 2
},
{
"epoch": 0.01,
"grad_norm": 0.08941341191530228,
"learning_rate": 6e-05,
"loss": 1.7737,
"step": 3
},
{
"epoch": 0.01,
"grad_norm": 0.08335491269826889,
"learning_rate": 8e-05,
"loss": 1.8004,
"step": 4
},
{
"epoch": 0.01,
"grad_norm": 0.08835520595312119,
"learning_rate": 0.0001,
"loss": 1.8495,
"step": 5
},
{
"epoch": 0.01,
"grad_norm": 0.08816578984260559,
"learning_rate": 0.00012,
"loss": 1.7758,
"step": 6
},
{
"epoch": 0.01,
"grad_norm": 0.09536299854516983,
"learning_rate": 0.00014,
"loss": 1.8001,
"step": 7
},
{
"epoch": 0.01,
"grad_norm": 0.07634323835372925,
"learning_rate": 0.00016,
"loss": 1.7022,
"step": 8
},
{
"epoch": 0.02,
"grad_norm": 0.06886536628007889,
"learning_rate": 0.00018,
"loss": 1.8428,
"step": 9
},
{
"epoch": 0.02,
"grad_norm": 0.07389801740646362,
"learning_rate": 0.0002,
"loss": 1.7598,
"step": 10
},
{
"epoch": 0.02,
"grad_norm": 0.06829163432121277,
"learning_rate": 0.00019999981517295864,
"loss": 1.7479,
"step": 11
},
{
"epoch": 0.02,
"grad_norm": 0.060045819729566574,
"learning_rate": 0.0001999992606925178,
"loss": 1.7454,
"step": 12
},
{
"epoch": 0.02,
"grad_norm": 0.08187604695558548,
"learning_rate": 0.0001999983365607271,
"loss": 1.7679,
"step": 13
},
{
"epoch": 0.03,
"grad_norm": 0.05995490401983261,
"learning_rate": 0.00019999704278100263,
"loss": 1.7599,
"step": 14
},
{
"epoch": 0.03,
"grad_norm": 0.055336710065603256,
"learning_rate": 0.00019999537935812698,
"loss": 1.8244,
"step": 15
},
{
"epoch": 0.03,
"grad_norm": 0.0541992112994194,
"learning_rate": 0.00019999334629824895,
"loss": 1.7756,
"step": 16
},
{
"epoch": 0.03,
"grad_norm": 0.05088195204734802,
"learning_rate": 0.00019999094360888392,
"loss": 1.7352,
"step": 17
},
{
"epoch": 0.03,
"grad_norm": 0.05157861113548279,
"learning_rate": 0.00019998817129891346,
"loss": 1.7634,
"step": 18
},
{
"epoch": 0.03,
"grad_norm": 0.055710840970277786,
"learning_rate": 0.00019998502937858557,
"loss": 1.7802,
"step": 19
},
{
"epoch": 0.04,
"grad_norm": 0.055150121450424194,
"learning_rate": 0.00019998151785951448,
"loss": 1.7445,
"step": 20
},
{
"epoch": 0.04,
"grad_norm": 0.0526655912399292,
"learning_rate": 0.0001999776367546806,
"loss": 1.6634,
"step": 21
},
{
"epoch": 0.04,
"grad_norm": 0.04809674620628357,
"learning_rate": 0.00019997338607843075,
"loss": 1.7277,
"step": 22
},
{
"epoch": 0.04,
"grad_norm": 0.049412671476602554,
"learning_rate": 0.00019996876584647754,
"loss": 1.7357,
"step": 23
},
{
"epoch": 0.04,
"grad_norm": 0.04948608949780464,
"learning_rate": 0.00019996377607589997,
"loss": 1.7323,
"step": 24
},
{
"epoch": 0.05,
"grad_norm": 0.050225820392370224,
"learning_rate": 0.00019995841678514294,
"loss": 1.7273,
"step": 25
},
{
"epoch": 0.05,
"grad_norm": 0.05085042864084244,
"learning_rate": 0.00019995268799401718,
"loss": 1.7564,
"step": 26
},
{
"epoch": 0.05,
"grad_norm": 0.04916631057858467,
"learning_rate": 0.00019994658972369948,
"loss": 1.7439,
"step": 27
},
{
"epoch": 0.05,
"grad_norm": 0.04791415110230446,
"learning_rate": 0.00019994012199673234,
"loss": 1.6813,
"step": 28
},
{
"epoch": 0.05,
"grad_norm": 0.04975065216422081,
"learning_rate": 0.00019993328483702393,
"loss": 1.691,
"step": 29
},
{
"epoch": 0.05,
"grad_norm": 0.055913638323545456,
"learning_rate": 0.00019992607826984816,
"loss": 1.7242,
"step": 30
},
{
"epoch": 0.06,
"grad_norm": 0.045829374343156815,
"learning_rate": 0.00019991850232184435,
"loss": 1.7334,
"step": 31
},
{
"epoch": 0.06,
"grad_norm": 0.053105831146240234,
"learning_rate": 0.00019991055702101734,
"loss": 1.7214,
"step": 32
},
{
"epoch": 0.06,
"grad_norm": 0.04539350047707558,
"learning_rate": 0.00019990224239673722,
"loss": 1.7698,
"step": 33
},
{
"epoch": 0.06,
"grad_norm": 0.046983517706394196,
"learning_rate": 0.00019989355847973932,
"loss": 1.6887,
"step": 34
},
{
"epoch": 0.06,
"grad_norm": 0.0471692830324173,
"learning_rate": 0.00019988450530212414,
"loss": 1.7571,
"step": 35
},
{
"epoch": 0.07,
"grad_norm": 0.046874694526195526,
"learning_rate": 0.00019987508289735716,
"loss": 1.7558,
"step": 36
},
{
"epoch": 0.07,
"grad_norm": 0.04474163055419922,
"learning_rate": 0.00019986529130026857,
"loss": 1.7465,
"step": 37
},
{
"epoch": 0.07,
"grad_norm": 0.044651810079813004,
"learning_rate": 0.00019985513054705348,
"loss": 1.6983,
"step": 38
},
{
"epoch": 0.07,
"grad_norm": 0.04951983690261841,
"learning_rate": 0.00019984460067527153,
"loss": 1.761,
"step": 39
},
{
"epoch": 0.07,
"grad_norm": 0.04424133151769638,
"learning_rate": 0.00019983370172384682,
"loss": 1.6383,
"step": 40
},
{
"epoch": 0.07,
"grad_norm": 0.052418872714042664,
"learning_rate": 0.00019982243373306772,
"loss": 1.779,
"step": 41
},
{
"epoch": 0.08,
"grad_norm": 0.04530750587582588,
"learning_rate": 0.0001998107967445869,
"loss": 1.6942,
"step": 42
},
{
"epoch": 0.08,
"grad_norm": 0.04790988191962242,
"learning_rate": 0.0001997987908014209,
"loss": 1.7053,
"step": 43
},
{
"epoch": 0.08,
"grad_norm": 0.04889607056975365,
"learning_rate": 0.0001997864159479502,
"loss": 1.7275,
"step": 44
},
{
"epoch": 0.08,
"grad_norm": 0.04314807429909706,
"learning_rate": 0.00019977367222991893,
"loss": 1.7393,
"step": 45
},
{
"epoch": 0.08,
"grad_norm": 0.04405505582690239,
"learning_rate": 0.00019976055969443479,
"loss": 1.7306,
"step": 46
},
{
"epoch": 0.09,
"grad_norm": 0.04656574875116348,
"learning_rate": 0.00019974707838996882,
"loss": 1.7686,
"step": 47
},
{
"epoch": 0.09,
"grad_norm": 0.04246290400624275,
"learning_rate": 0.00019973322836635518,
"loss": 1.7209,
"step": 48
},
{
"epoch": 0.09,
"grad_norm": 0.05493748560547829,
"learning_rate": 0.00019971900967479106,
"loss": 1.7155,
"step": 49
},
{
"epoch": 0.09,
"grad_norm": 0.0450466088950634,
"learning_rate": 0.0001997044223678364,
"loss": 1.6604,
"step": 50
},
{
"epoch": 0.09,
"grad_norm": 0.08634985238313675,
"learning_rate": 0.00019968946649941382,
"loss": 1.7321,
"step": 51
},
{
"epoch": 0.09,
"grad_norm": 0.04310084879398346,
"learning_rate": 0.00019967414212480831,
"loss": 1.7281,
"step": 52
},
{
"epoch": 0.1,
"grad_norm": 0.04666193947196007,
"learning_rate": 0.000199658449300667,
"loss": 1.6787,
"step": 53
},
{
"epoch": 0.1,
"grad_norm": 0.04957772046327591,
"learning_rate": 0.00019964238808499907,
"loss": 1.6919,
"step": 54
},
{
"epoch": 0.1,
"grad_norm": 0.0421697273850441,
"learning_rate": 0.00019962595853717548,
"loss": 1.7245,
"step": 55
},
{
"epoch": 0.1,
"grad_norm": 0.04654068127274513,
"learning_rate": 0.0001996091607179287,
"loss": 1.7123,
"step": 56
},
{
"epoch": 0.1,
"grad_norm": 0.04076274484395981,
"learning_rate": 0.00019959199468935258,
"loss": 1.7066,
"step": 57
},
{
"epoch": 0.11,
"grad_norm": 0.04215634986758232,
"learning_rate": 0.00019957446051490198,
"loss": 1.7748,
"step": 58
},
{
"epoch": 0.11,
"grad_norm": 0.04252045601606369,
"learning_rate": 0.0001995565582593928,
"loss": 1.7396,
"step": 59
},
{
"epoch": 0.11,
"grad_norm": 0.04455842077732086,
"learning_rate": 0.00019953828798900135,
"loss": 1.7236,
"step": 60
},
{
"epoch": 0.11,
"grad_norm": 0.044083647429943085,
"learning_rate": 0.0001995196497712645,
"loss": 1.7416,
"step": 61
},
{
"epoch": 0.11,
"grad_norm": 0.04511955380439758,
"learning_rate": 0.00019950064367507916,
"loss": 1.7481,
"step": 62
},
{
"epoch": 0.11,
"grad_norm": 0.0424315445125103,
"learning_rate": 0.00019948126977070217,
"loss": 1.7712,
"step": 63
},
{
"epoch": 0.12,
"grad_norm": 0.04309271275997162,
"learning_rate": 0.00019946152812974993,
"loss": 1.6927,
"step": 64
},
{
"epoch": 0.12,
"grad_norm": 0.042915165424346924,
"learning_rate": 0.00019944141882519817,
"loss": 1.7465,
"step": 65
},
{
"epoch": 0.12,
"grad_norm": 0.05950941890478134,
"learning_rate": 0.00019942094193138186,
"loss": 1.7035,
"step": 66
},
{
"epoch": 0.12,
"grad_norm": 0.042048510164022446,
"learning_rate": 0.0001994000975239946,
"loss": 1.7521,
"step": 67
},
{
"epoch": 0.12,
"grad_norm": 0.041577938944101334,
"learning_rate": 0.00019937888568008862,
"loss": 1.7439,
"step": 68
},
{
"epoch": 0.13,
"grad_norm": 0.04538682475686073,
"learning_rate": 0.00019935730647807436,
"loss": 1.7528,
"step": 69
},
{
"epoch": 0.13,
"grad_norm": 0.04102981090545654,
"learning_rate": 0.00019933535999772025,
"loss": 1.6828,
"step": 70
},
{
"epoch": 0.13,
"grad_norm": 0.04318905994296074,
"learning_rate": 0.00019931304632015228,
"loss": 1.7532,
"step": 71
},
{
"epoch": 0.13,
"grad_norm": 0.043007493019104004,
"learning_rate": 0.00019929036552785397,
"loss": 1.7353,
"step": 72
},
{
"epoch": 0.13,
"grad_norm": 0.04308176040649414,
"learning_rate": 0.00019926731770466568,
"loss": 1.6882,
"step": 73
},
{
"epoch": 0.13,
"grad_norm": 0.04227353632450104,
"learning_rate": 0.00019924390293578472,
"loss": 1.7302,
"step": 74
},
{
"epoch": 0.14,
"grad_norm": 0.0429629310965538,
"learning_rate": 0.0001992201213077647,
"loss": 1.6822,
"step": 75
},
{
"epoch": 0.14,
"grad_norm": 0.042203355580568314,
"learning_rate": 0.00019919597290851538,
"loss": 1.7601,
"step": 76
},
{
"epoch": 0.14,
"grad_norm": 0.04265713319182396,
"learning_rate": 0.00019917145782730232,
"loss": 1.7725,
"step": 77
},
{
"epoch": 0.14,
"grad_norm": 0.04848012328147888,
"learning_rate": 0.00019914657615474653,
"loss": 1.7587,
"step": 78
},
{
"epoch": 0.14,
"grad_norm": 0.042650256305933,
"learning_rate": 0.00019912132798282408,
"loss": 1.7422,
"step": 79
},
{
"epoch": 0.15,
"grad_norm": 0.04107372462749481,
"learning_rate": 0.00019909571340486593,
"loss": 1.7059,
"step": 80
},
{
"epoch": 0.15,
"grad_norm": 0.04788720980286598,
"learning_rate": 0.00019906973251555734,
"loss": 1.7205,
"step": 81
},
{
"epoch": 0.15,
"grad_norm": 0.041231803596019745,
"learning_rate": 0.0001990433854109378,
"loss": 1.7277,
"step": 82
},
{
"epoch": 0.15,
"grad_norm": 0.04246293380856514,
"learning_rate": 0.0001990166721884004,
"loss": 1.7739,
"step": 83
},
{
"epoch": 0.15,
"grad_norm": 0.04331424832344055,
"learning_rate": 0.00019898959294669167,
"loss": 1.6913,
"step": 84
},
{
"epoch": 0.15,
"grad_norm": 0.04720227047801018,
"learning_rate": 0.00019896214778591115,
"loss": 1.7079,
"step": 85
},
{
"epoch": 0.16,
"grad_norm": 0.05255519971251488,
"learning_rate": 0.00019893433680751103,
"loss": 1.7182,
"step": 86
},
{
"epoch": 0.16,
"grad_norm": 0.042392294853925705,
"learning_rate": 0.00019890616011429568,
"loss": 1.778,
"step": 87
},
{
"epoch": 0.16,
"grad_norm": 0.043008286505937576,
"learning_rate": 0.0001988776178104214,
"loss": 1.7518,
"step": 88
},
{
"epoch": 0.16,
"grad_norm": 0.044135116040706635,
"learning_rate": 0.00019884871000139595,
"loss": 1.7534,
"step": 89
},
{
"epoch": 0.16,
"grad_norm": 0.041827455163002014,
"learning_rate": 0.00019881943679407832,
"loss": 1.7291,
"step": 90
},
{
"epoch": 0.17,
"grad_norm": 0.05515114963054657,
"learning_rate": 0.00019878979829667803,
"loss": 1.7471,
"step": 91
},
{
"epoch": 0.17,
"grad_norm": 0.040826503187417984,
"learning_rate": 0.00019875979461875503,
"loss": 1.6408,
"step": 92
},
{
"epoch": 0.17,
"grad_norm": 0.04585504159331322,
"learning_rate": 0.00019872942587121915,
"loss": 1.6874,
"step": 93
},
{
"epoch": 0.17,
"grad_norm": 0.04665527120232582,
"learning_rate": 0.00019869869216632968,
"loss": 1.6968,
"step": 94
},
{
"epoch": 0.17,
"grad_norm": 0.046703219413757324,
"learning_rate": 0.000198667593617695,
"loss": 1.7401,
"step": 95
},
{
"epoch": 0.18,
"grad_norm": 0.04115475341677666,
"learning_rate": 0.00019863613034027224,
"loss": 1.7227,
"step": 96
},
{
"epoch": 0.18,
"grad_norm": 0.04217168688774109,
"learning_rate": 0.00019860430245036663,
"loss": 1.7268,
"step": 97
},
{
"epoch": 0.18,
"grad_norm": 0.044889383018016815,
"learning_rate": 0.00019857211006563125,
"loss": 1.7006,
"step": 98
},
{
"epoch": 0.18,
"grad_norm": 0.04161443933844566,
"learning_rate": 0.00019853955330506663,
"loss": 1.7266,
"step": 99
},
{
"epoch": 0.18,
"grad_norm": 0.042708829045295715,
"learning_rate": 0.00019850663228902012,
"loss": 1.7314,
"step": 100
},
{
"epoch": 0.18,
"grad_norm": 0.046648308634757996,
"learning_rate": 0.00019847334713918557,
"loss": 1.7362,
"step": 101
},
{
"epoch": 0.19,
"grad_norm": 0.04414999857544899,
"learning_rate": 0.00019843969797860294,
"loss": 1.7065,
"step": 102
},
{
"epoch": 0.19,
"grad_norm": 0.04574083164334297,
"learning_rate": 0.00019840568493165772,
"loss": 1.7333,
"step": 103
},
{
"epoch": 0.19,
"grad_norm": 0.041924796998500824,
"learning_rate": 0.0001983713081240805,
"loss": 1.6517,
"step": 104
},
{
"epoch": 0.19,
"grad_norm": 0.04238827899098396,
"learning_rate": 0.00019833656768294662,
"loss": 1.776,
"step": 105
},
{
"epoch": 0.19,
"grad_norm": 0.04292167350649834,
"learning_rate": 0.00019830146373667548,
"loss": 1.6601,
"step": 106
},
{
"epoch": 0.2,
"grad_norm": 0.0433412566781044,
"learning_rate": 0.00019826599641503025,
"loss": 1.6841,
"step": 107
},
{
"epoch": 0.2,
"grad_norm": 0.04201202839612961,
"learning_rate": 0.00019823016584911735,
"loss": 1.764,
"step": 108
},
{
"epoch": 0.2,
"grad_norm": 0.04234587028622627,
"learning_rate": 0.00019819397217138595,
"loss": 1.7243,
"step": 109
},
{
"epoch": 0.2,
"grad_norm": 0.04268571734428406,
"learning_rate": 0.0001981574155156274,
"loss": 1.7656,
"step": 110
},
{
"epoch": 0.2,
"grad_norm": 0.041506245732307434,
"learning_rate": 0.00019812049601697492,
"loss": 1.6636,
"step": 111
},
{
"epoch": 0.2,
"grad_norm": 0.04152766987681389,
"learning_rate": 0.00019808321381190294,
"loss": 1.7478,
"step": 112
},
{
"epoch": 0.21,
"grad_norm": 0.041750356554985046,
"learning_rate": 0.00019804556903822663,
"loss": 1.7518,
"step": 113
},
{
"epoch": 0.21,
"grad_norm": 0.04935223609209061,
"learning_rate": 0.00019800756183510144,
"loss": 1.7673,
"step": 114
},
{
"epoch": 0.21,
"grad_norm": 0.042300984263420105,
"learning_rate": 0.00019796919234302255,
"loss": 1.7753,
"step": 115
},
{
"epoch": 0.21,
"grad_norm": 0.04224342852830887,
"learning_rate": 0.00019793046070382437,
"loss": 1.7226,
"step": 116
},
{
"epoch": 0.21,
"grad_norm": 0.044274065643548965,
"learning_rate": 0.00019789136706067998,
"loss": 1.7065,
"step": 117
},
{
"epoch": 0.22,
"grad_norm": 0.04910755529999733,
"learning_rate": 0.00019785191155810062,
"loss": 1.6387,
"step": 118
},
{
"epoch": 0.22,
"grad_norm": 0.04774147644639015,
"learning_rate": 0.00019781209434193515,
"loss": 1.7297,
"step": 119
},
{
"epoch": 0.22,
"grad_norm": 0.04416586086153984,
"learning_rate": 0.00019777191555936957,
"loss": 1.8096,
"step": 120
},
{
"epoch": 0.22,
"grad_norm": 0.04406105354428291,
"learning_rate": 0.00019773137535892635,
"loss": 1.7629,
"step": 121
},
{
"epoch": 0.22,
"grad_norm": 0.043473679572343826,
"learning_rate": 0.00019769047389046402,
"loss": 1.6979,
"step": 122
},
{
"epoch": 0.22,
"grad_norm": 0.04570621997117996,
"learning_rate": 0.00019764921130517653,
"loss": 1.7123,
"step": 123
},
{
"epoch": 0.23,
"grad_norm": 0.04326749965548515,
"learning_rate": 0.00019760758775559274,
"loss": 1.716,
"step": 124
},
{
"epoch": 0.23,
"grad_norm": 0.04397182539105415,
"learning_rate": 0.00019756560339557572,
"loss": 1.73,
"step": 125
},
{
"epoch": 0.23,
"grad_norm": 0.04468885809183121,
"learning_rate": 0.00019752325838032244,
"loss": 1.7136,
"step": 126
},
{
"epoch": 0.23,
"grad_norm": 0.04554520919919014,
"learning_rate": 0.00019748055286636295,
"loss": 1.7448,
"step": 127
},
{
"epoch": 0.23,
"grad_norm": 0.04646708443760872,
"learning_rate": 0.00019743748701155995,
"loss": 1.6956,
"step": 128
},
{
"epoch": 0.24,
"grad_norm": 0.042717937380075455,
"learning_rate": 0.00019739406097510812,
"loss": 1.7245,
"step": 129
},
{
"epoch": 0.24,
"grad_norm": 0.04367038235068321,
"learning_rate": 0.00019735027491753353,
"loss": 1.7102,
"step": 130
},
{
"epoch": 0.24,
"grad_norm": 0.04296841099858284,
"learning_rate": 0.0001973061290006932,
"loss": 1.7163,
"step": 131
},
{
"epoch": 0.24,
"grad_norm": 0.043665811419487,
"learning_rate": 0.00019726162338777424,
"loss": 1.7172,
"step": 132
},
{
"epoch": 0.24,
"grad_norm": 0.046134624630212784,
"learning_rate": 0.00019721675824329354,
"loss": 1.7327,
"step": 133
},
{
"epoch": 0.24,
"grad_norm": 0.04857848584651947,
"learning_rate": 0.00019717153373309692,
"loss": 1.6647,
"step": 134
},
{
"epoch": 0.25,
"grad_norm": 0.047723885625600815,
"learning_rate": 0.00019712595002435861,
"loss": 1.7422,
"step": 135
},
{
"epoch": 0.25,
"grad_norm": 0.04413154348731041,
"learning_rate": 0.00019708000728558064,
"loss": 1.6943,
"step": 136
},
{
"epoch": 0.25,
"grad_norm": 0.043105412274599075,
"learning_rate": 0.00019703370568659225,
"loss": 1.7519,
"step": 137
},
{
"epoch": 0.25,
"eval_loss": 1.7284438610076904,
"eval_runtime": 76.3963,
"eval_samples_per_second": 65.448,
"eval_steps_per_second": 16.362,
"step": 137
},
{
"epoch": 0.25,
"grad_norm": 0.04300757125020027,
"learning_rate": 0.00019698704539854918,
"loss": 1.7341,
"step": 138
},
{
"epoch": 0.25,
"grad_norm": 0.043961744755506516,
"learning_rate": 0.00019694002659393305,
"loss": 1.777,
"step": 139
},
{
"epoch": 0.26,
"grad_norm": 0.04376057907938957,
"learning_rate": 0.00019689264944655084,
"loss": 1.7403,
"step": 140
},
{
"epoch": 0.26,
"grad_norm": 0.04482461139559746,
"learning_rate": 0.00019684491413153411,
"loss": 1.6852,
"step": 141
},
{
"epoch": 0.26,
"grad_norm": 0.045192863792181015,
"learning_rate": 0.0001967968208253384,
"loss": 1.7494,
"step": 142
},
{
"epoch": 0.26,
"grad_norm": 0.04361759498715401,
"learning_rate": 0.00019674836970574254,
"loss": 1.7331,
"step": 143
},
{
"epoch": 0.26,
"grad_norm": 0.04294734448194504,
"learning_rate": 0.0001966995609518481,
"loss": 1.6375,
"step": 144
},
{
"epoch": 0.26,
"grad_norm": 0.04528161138296127,
"learning_rate": 0.00019665039474407863,
"loss": 1.746,
"step": 145
},
{
"epoch": 0.27,
"grad_norm": 0.04510699212551117,
"learning_rate": 0.00019660087126417906,
"loss": 1.7053,
"step": 146
},
{
"epoch": 0.27,
"grad_norm": 0.042807720601558685,
"learning_rate": 0.00019655099069521486,
"loss": 1.6748,
"step": 147
},
{
"epoch": 0.27,
"grad_norm": 0.04657953232526779,
"learning_rate": 0.00019650075322157168,
"loss": 1.684,
"step": 148
},
{
"epoch": 0.27,
"grad_norm": 0.04593012481927872,
"learning_rate": 0.00019645015902895437,
"loss": 1.7076,
"step": 149
},
{
"epoch": 0.27,
"grad_norm": 0.04362139105796814,
"learning_rate": 0.0001963992083043864,
"loss": 1.6773,
"step": 150
},
{
"epoch": 0.28,
"grad_norm": 0.04773354157805443,
"learning_rate": 0.00019634790123620926,
"loss": 1.7107,
"step": 151
},
{
"epoch": 0.28,
"grad_norm": 0.05423569679260254,
"learning_rate": 0.00019629623801408155,
"loss": 1.7052,
"step": 152
},
{
"epoch": 0.28,
"grad_norm": 0.043550509959459305,
"learning_rate": 0.00019624421882897855,
"loss": 1.7151,
"step": 153
},
{
"epoch": 0.28,
"grad_norm": 0.04896851256489754,
"learning_rate": 0.00019619184387319123,
"loss": 1.6611,
"step": 154
},
{
"epoch": 0.28,
"grad_norm": 0.04392845928668976,
"learning_rate": 0.00019613911334032583,
"loss": 1.738,
"step": 155
},
{
"epoch": 0.28,
"grad_norm": 0.04582325741648674,
"learning_rate": 0.00019608602742530283,
"loss": 1.6885,
"step": 156
},
{
"epoch": 0.29,
"grad_norm": 0.045696284621953964,
"learning_rate": 0.00019603258632435656,
"loss": 1.7365,
"step": 157
},
{
"epoch": 0.29,
"grad_norm": 0.043873440474271774,
"learning_rate": 0.00019597879023503417,
"loss": 1.8094,
"step": 158
},
{
"epoch": 0.29,
"grad_norm": 0.05078018456697464,
"learning_rate": 0.00019592463935619517,
"loss": 1.7341,
"step": 159
},
{
"epoch": 0.29,
"grad_norm": 0.042483873665332794,
"learning_rate": 0.00019587013388801047,
"loss": 1.7351,
"step": 160
},
{
"epoch": 0.29,
"grad_norm": 0.045154914259910583,
"learning_rate": 0.00019581527403196168,
"loss": 1.6645,
"step": 161
},
{
"epoch": 0.3,
"grad_norm": 0.04563280567526817,
"learning_rate": 0.0001957600599908406,
"loss": 1.7069,
"step": 162
},
{
"epoch": 0.3,
"grad_norm": 0.0451313816010952,
"learning_rate": 0.00019570449196874815,
"loss": 1.7392,
"step": 163
},
{
"epoch": 0.3,
"grad_norm": 0.04682654142379761,
"learning_rate": 0.0001956485701710938,
"loss": 1.6987,
"step": 164
},
{
"epoch": 0.3,
"grad_norm": 0.04211273416876793,
"learning_rate": 0.00019559229480459474,
"loss": 1.6973,
"step": 165
},
{
"epoch": 0.3,
"grad_norm": 0.04460490494966507,
"learning_rate": 0.00019553566607727517,
"loss": 1.7233,
"step": 166
},
{
"epoch": 0.3,
"grad_norm": 0.044608812779188156,
"learning_rate": 0.00019547868419846548,
"loss": 1.7371,
"step": 167
},
{
"epoch": 0.31,
"grad_norm": 0.04518236592411995,
"learning_rate": 0.00019542134937880154,
"loss": 1.7257,
"step": 168
},
{
"epoch": 0.31,
"grad_norm": 0.04374237731099129,
"learning_rate": 0.00019536366183022384,
"loss": 1.7136,
"step": 169
},
{
"epoch": 0.31,
"grad_norm": 0.04429790750145912,
"learning_rate": 0.00019530562176597673,
"loss": 1.7216,
"step": 170
},
{
"epoch": 0.31,
"grad_norm": 0.04807354509830475,
"learning_rate": 0.0001952472294006077,
"loss": 1.6568,
"step": 171
},
{
"epoch": 0.31,
"grad_norm": 0.04785493016242981,
"learning_rate": 0.00019518848494996655,
"loss": 1.7272,
"step": 172
},
{
"epoch": 0.32,
"grad_norm": 0.04472104460000992,
"learning_rate": 0.0001951293886312045,
"loss": 1.7283,
"step": 173
},
{
"epoch": 0.32,
"grad_norm": 0.04852326214313507,
"learning_rate": 0.00019506994066277348,
"loss": 1.6968,
"step": 174
},
{
"epoch": 0.32,
"grad_norm": 0.04624422639608383,
"learning_rate": 0.0001950101412644254,
"loss": 1.758,
"step": 175
},
{
"epoch": 0.32,
"grad_norm": 0.044666189700365067,
"learning_rate": 0.00019494999065721108,
"loss": 1.6933,
"step": 176
},
{
"epoch": 0.32,
"grad_norm": 0.05367857217788696,
"learning_rate": 0.0001948894890634798,
"loss": 1.7328,
"step": 177
},
{
"epoch": 0.32,
"grad_norm": 0.046923939138650894,
"learning_rate": 0.0001948286367068781,
"loss": 1.7367,
"step": 178
},
{
"epoch": 0.33,
"grad_norm": 0.04480034112930298,
"learning_rate": 0.00019476743381234926,
"loss": 1.7677,
"step": 179
},
{
"epoch": 0.33,
"grad_norm": 0.045380428433418274,
"learning_rate": 0.00019470588060613222,
"loss": 1.7439,
"step": 180
},
{
"epoch": 0.33,
"grad_norm": 0.04550057277083397,
"learning_rate": 0.00019464397731576094,
"loss": 1.6895,
"step": 181
},
{
"epoch": 0.33,
"grad_norm": 0.049537234008312225,
"learning_rate": 0.00019458172417006347,
"loss": 1.7274,
"step": 182
},
{
"epoch": 0.33,
"grad_norm": 0.04696514084935188,
"learning_rate": 0.0001945191213991611,
"loss": 1.7121,
"step": 183
},
{
"epoch": 0.34,
"grad_norm": 0.04783783480525017,
"learning_rate": 0.00019445616923446755,
"loss": 1.6942,
"step": 184
},
{
"epoch": 0.34,
"grad_norm": 0.04514686018228531,
"learning_rate": 0.00019439286790868802,
"loss": 1.7219,
"step": 185
},
{
"epoch": 0.34,
"grad_norm": 0.045743513852357864,
"learning_rate": 0.00019432921765581847,
"loss": 1.76,
"step": 186
},
{
"epoch": 0.34,
"grad_norm": 0.04406295716762543,
"learning_rate": 0.00019426521871114468,
"loss": 1.7531,
"step": 187
},
{
"epoch": 0.34,
"grad_norm": 0.04445353150367737,
"learning_rate": 0.00019420087131124131,
"loss": 1.7742,
"step": 188
},
{
"epoch": 0.34,
"grad_norm": 0.04396241530776024,
"learning_rate": 0.0001941361756939712,
"loss": 1.7701,
"step": 189
},
{
"epoch": 0.35,
"grad_norm": 0.04415050894021988,
"learning_rate": 0.0001940711320984843,
"loss": 1.7062,
"step": 190
},
{
"epoch": 0.35,
"grad_norm": 0.04672138765454292,
"learning_rate": 0.00019400574076521693,
"loss": 1.754,
"step": 191
},
{
"epoch": 0.35,
"grad_norm": 0.04417939484119415,
"learning_rate": 0.00019394000193589088,
"loss": 1.7357,
"step": 192
},
{
"epoch": 0.35,
"grad_norm": 0.04567494988441467,
"learning_rate": 0.00019387391585351234,
"loss": 1.752,
"step": 193
},
{
"epoch": 0.35,
"grad_norm": 0.045080311596393585,
"learning_rate": 0.00019380748276237123,
"loss": 1.736,
"step": 194
},
{
"epoch": 0.36,
"grad_norm": 0.04506627842783928,
"learning_rate": 0.0001937407029080402,
"loss": 1.6726,
"step": 195
},
{
"epoch": 0.36,
"grad_norm": 0.04523961618542671,
"learning_rate": 0.0001936735765373737,
"loss": 1.7621,
"step": 196
},
{
"epoch": 0.36,
"grad_norm": 0.04326867312192917,
"learning_rate": 0.00019360610389850712,
"loss": 1.7341,
"step": 197
},
{
"epoch": 0.36,
"grad_norm": 0.05188523977994919,
"learning_rate": 0.00019353828524085577,
"loss": 1.7277,
"step": 198
},
{
"epoch": 0.36,
"grad_norm": 0.04654062166810036,
"learning_rate": 0.00019347012081511415,
"loss": 1.6845,
"step": 199
},
{
"epoch": 0.36,
"grad_norm": 0.044841405004262924,
"learning_rate": 0.0001934016108732548,
"loss": 1.6611,
"step": 200
},
{
"epoch": 0.37,
"grad_norm": 0.0941338911652565,
"learning_rate": 0.00019333275566852756,
"loss": 1.6978,
"step": 201
},
{
"epoch": 0.37,
"grad_norm": 0.05048836022615433,
"learning_rate": 0.00019326355545545845,
"loss": 1.7056,
"step": 202
},
{
"epoch": 0.37,
"grad_norm": 0.046358656138181686,
"learning_rate": 0.00019319401048984892,
"loss": 1.649,
"step": 203
},
{
"epoch": 0.37,
"grad_norm": 0.04557095095515251,
"learning_rate": 0.00019312412102877473,
"loss": 1.6793,
"step": 204
},
{
"epoch": 0.37,
"grad_norm": 0.04551040008664131,
"learning_rate": 0.0001930538873305852,
"loss": 1.7339,
"step": 205
},
{
"epoch": 0.38,
"grad_norm": 0.044258005917072296,
"learning_rate": 0.000192983309654902,
"loss": 1.6627,
"step": 206
},
{
"epoch": 0.38,
"grad_norm": 0.0485963337123394,
"learning_rate": 0.00019291238826261843,
"loss": 1.715,
"step": 207
},
{
"epoch": 0.38,
"grad_norm": 0.047103844583034515,
"learning_rate": 0.00019284112341589832,
"loss": 1.6855,
"step": 208
},
{
"epoch": 0.38,
"grad_norm": 0.045252177864313126,
"learning_rate": 0.000192769515378175,
"loss": 1.7557,
"step": 209
},
{
"epoch": 0.38,
"grad_norm": 0.049794841557741165,
"learning_rate": 0.00019269756441415062,
"loss": 1.7116,
"step": 210
},
{
"epoch": 0.38,
"grad_norm": 0.04380947723984718,
"learning_rate": 0.00019262527078979478,
"loss": 1.7663,
"step": 211
},
{
"epoch": 0.39,
"grad_norm": 0.046488065272569656,
"learning_rate": 0.00019255263477234381,
"loss": 1.6724,
"step": 212
},
{
"epoch": 0.39,
"grad_norm": 0.0422043539583683,
"learning_rate": 0.00019247965663029976,
"loss": 1.7345,
"step": 213
},
{
"epoch": 0.39,
"grad_norm": 0.05002991482615471,
"learning_rate": 0.0001924063366334293,
"loss": 1.7468,
"step": 214
},
{
"epoch": 0.39,
"grad_norm": 0.04376322776079178,
"learning_rate": 0.0001923326750527628,
"loss": 1.7748,
"step": 215
},
{
"epoch": 0.39,
"grad_norm": 0.04664807394146919,
"learning_rate": 0.00019225867216059325,
"loss": 1.7156,
"step": 216
},
{
"epoch": 0.4,
"grad_norm": 0.047952812165021896,
"learning_rate": 0.0001921843282304754,
"loss": 1.7247,
"step": 217
},
{
"epoch": 0.4,
"grad_norm": 0.045118216425180435,
"learning_rate": 0.00019210964353722464,
"loss": 1.7354,
"step": 218
},
{
"epoch": 0.4,
"grad_norm": 0.054903436452150345,
"learning_rate": 0.00019203461835691594,
"loss": 1.7241,
"step": 219
},
{
"epoch": 0.4,
"grad_norm": 0.04747498407959938,
"learning_rate": 0.000191959252966883,
"loss": 1.7498,
"step": 220
},
{
"epoch": 0.4,
"grad_norm": 0.04605628177523613,
"learning_rate": 0.000191883547645717,
"loss": 1.6889,
"step": 221
},
{
"epoch": 0.4,
"grad_norm": 0.04835960268974304,
"learning_rate": 0.00019180750267326578,
"loss": 1.715,
"step": 222
},
{
"epoch": 0.41,
"grad_norm": 0.04828386381268501,
"learning_rate": 0.00019173111833063273,
"loss": 1.6931,
"step": 223
},
{
"epoch": 0.41,
"grad_norm": 0.04604095220565796,
"learning_rate": 0.0001916543949001756,
"loss": 1.6717,
"step": 224
},
{
"epoch": 0.41,
"grad_norm": 0.049674633890390396,
"learning_rate": 0.00019157733266550575,
"loss": 1.7746,
"step": 225
},
{
"epoch": 0.41,
"grad_norm": 0.04439341649413109,
"learning_rate": 0.00019149993191148687,
"loss": 1.6925,
"step": 226
},
{
"epoch": 0.41,
"grad_norm": 0.04741811007261276,
"learning_rate": 0.00019142219292423395,
"loss": 1.7219,
"step": 227
},
{
"epoch": 0.42,
"grad_norm": 0.049409981817007065,
"learning_rate": 0.00019134411599111242,
"loss": 1.7306,
"step": 228
},
{
"epoch": 0.42,
"grad_norm": 0.04618163779377937,
"learning_rate": 0.00019126570140073676,
"loss": 1.7271,
"step": 229
},
{
"epoch": 0.42,
"grad_norm": 0.04557076469063759,
"learning_rate": 0.0001911869494429698,
"loss": 1.7188,
"step": 230
},
{
"epoch": 0.42,
"grad_norm": 0.04645569249987602,
"learning_rate": 0.0001911078604089213,
"loss": 1.7191,
"step": 231
},
{
"epoch": 0.42,
"grad_norm": 0.04584849998354912,
"learning_rate": 0.0001910284345909471,
"loss": 1.7592,
"step": 232
},
{
"epoch": 0.42,
"grad_norm": 0.045582644641399384,
"learning_rate": 0.000190948672282648,
"loss": 1.6902,
"step": 233
},
{
"epoch": 0.43,
"grad_norm": 0.04627401754260063,
"learning_rate": 0.00019086857377886865,
"loss": 1.6937,
"step": 234
},
{
"epoch": 0.43,
"grad_norm": 0.04470285400748253,
"learning_rate": 0.00019078813937569643,
"loss": 1.6977,
"step": 235
},
{
"epoch": 0.43,
"grad_norm": 0.05287547782063484,
"learning_rate": 0.00019070736937046035,
"loss": 1.7539,
"step": 236
},
{
"epoch": 0.43,
"grad_norm": 0.04990493878722191,
"learning_rate": 0.00019062626406173006,
"loss": 1.7469,
"step": 237
},
{
"epoch": 0.43,
"grad_norm": 0.048645589500665665,
"learning_rate": 0.00019054482374931467,
"loss": 1.7037,
"step": 238
},
{
"epoch": 0.44,
"grad_norm": 0.04730357602238655,
"learning_rate": 0.0001904630487342616,
"loss": 1.7388,
"step": 239
},
{
"epoch": 0.44,
"grad_norm": 0.04754168912768364,
"learning_rate": 0.00019038093931885553,
"loss": 1.7805,
"step": 240
},
{
"epoch": 0.44,
"grad_norm": 0.04760801047086716,
"learning_rate": 0.00019029849580661727,
"loss": 1.7383,
"step": 241
},
{
"epoch": 0.44,
"grad_norm": 0.048467203974723816,
"learning_rate": 0.0001902157185023026,
"loss": 1.7078,
"step": 242
},
{
"epoch": 0.44,
"grad_norm": 0.0522041916847229,
"learning_rate": 0.00019013260771190126,
"loss": 1.7052,
"step": 243
},
{
"epoch": 0.44,
"grad_norm": 0.0501788929104805,
"learning_rate": 0.00019004916374263563,
"loss": 1.7818,
"step": 244
},
{
"epoch": 0.45,
"grad_norm": 0.04538620635867119,
"learning_rate": 0.00018996538690295979,
"loss": 1.6589,
"step": 245
},
{
"epoch": 0.45,
"grad_norm": 0.04511679336428642,
"learning_rate": 0.00018988127750255824,
"loss": 1.7179,
"step": 246
},
{
"epoch": 0.45,
"grad_norm": 0.04756203666329384,
"learning_rate": 0.0001897968358523448,
"loss": 1.7333,
"step": 247
},
{
"epoch": 0.45,
"grad_norm": 0.05278336629271507,
"learning_rate": 0.00018971206226446147,
"loss": 1.7431,
"step": 248
},
{
"epoch": 0.45,
"grad_norm": 0.05926801264286041,
"learning_rate": 0.00018962695705227728,
"loss": 1.7768,
"step": 249
},
{
"epoch": 0.46,
"grad_norm": 0.049290940165519714,
"learning_rate": 0.00018954152053038712,
"loss": 1.7119,
"step": 250
},
{
"epoch": 0.46,
"grad_norm": 0.04777907952666283,
"learning_rate": 0.0001894557530146106,
"loss": 1.7559,
"step": 251
},
{
"epoch": 0.46,
"grad_norm": 0.04726920276880264,
"learning_rate": 0.00018936965482199084,
"loss": 1.7861,
"step": 252
},
{
"epoch": 0.46,
"grad_norm": 0.04677857458591461,
"learning_rate": 0.0001892832262707933,
"loss": 1.7039,
"step": 253
},
{
"epoch": 0.46,
"grad_norm": 0.04724700003862381,
"learning_rate": 0.00018919646768050468,
"loss": 1.6704,
"step": 254
},
{
"epoch": 0.46,
"grad_norm": 0.04969072341918945,
"learning_rate": 0.00018910937937183166,
"loss": 1.7168,
"step": 255
},
{
"epoch": 0.47,
"grad_norm": 0.04533353075385094,
"learning_rate": 0.0001890219616666997,
"loss": 1.6751,
"step": 256
},
{
"epoch": 0.47,
"grad_norm": 0.04647386819124222,
"learning_rate": 0.0001889342148882519,
"loss": 1.7146,
"step": 257
},
{
"epoch": 0.47,
"grad_norm": 0.047208696603775024,
"learning_rate": 0.00018884613936084784,
"loss": 1.7378,
"step": 258
},
{
"epoch": 0.47,
"grad_norm": 0.04841624200344086,
"learning_rate": 0.0001887577354100623,
"loss": 1.7128,
"step": 259
},
{
"epoch": 0.47,
"grad_norm": 0.05073019117116928,
"learning_rate": 0.00018866900336268408,
"loss": 1.7206,
"step": 260
},
{
"epoch": 0.48,
"grad_norm": 0.051456011831760406,
"learning_rate": 0.00018857994354671482,
"loss": 1.755,
"step": 261
},
{
"epoch": 0.48,
"grad_norm": 0.04637736827135086,
"learning_rate": 0.0001884905562913678,
"loss": 1.7395,
"step": 262
},
{
"epoch": 0.48,
"grad_norm": 0.061346374452114105,
"learning_rate": 0.00018840084192706658,
"loss": 1.674,
"step": 263
},
{
"epoch": 0.48,
"grad_norm": 0.04413258284330368,
"learning_rate": 0.00018831080078544402,
"loss": 1.7288,
"step": 264
},
{
"epoch": 0.48,
"grad_norm": 0.0531301349401474,
"learning_rate": 0.0001882204331993409,
"loss": 1.7625,
"step": 265
},
{
"epoch": 0.48,
"grad_norm": 0.05146196484565735,
"learning_rate": 0.00018812973950280468,
"loss": 1.6815,
"step": 266
},
{
"epoch": 0.49,
"grad_norm": 0.047678787261247635,
"learning_rate": 0.0001880387200310883,
"loss": 1.7278,
"step": 267
},
{
"epoch": 0.49,
"grad_norm": 0.0556582510471344,
"learning_rate": 0.0001879473751206489,
"loss": 1.74,
"step": 268
},
{
"epoch": 0.49,
"grad_norm": 0.047515787184238434,
"learning_rate": 0.00018785570510914678,
"loss": 1.7207,
"step": 269
},
{
"epoch": 0.49,
"grad_norm": 0.04592055827379227,
"learning_rate": 0.0001877637103354438,
"loss": 1.6589,
"step": 270
},
{
"epoch": 0.49,
"grad_norm": 0.04531411454081535,
"learning_rate": 0.0001876713911396024,
"loss": 1.706,
"step": 271
},
{
"epoch": 0.5,
"grad_norm": 0.04682420939207077,
"learning_rate": 0.0001875787478628843,
"loss": 1.7297,
"step": 272
},
{
"epoch": 0.5,
"grad_norm": 0.04545978829264641,
"learning_rate": 0.00018748578084774913,
"loss": 1.6572,
"step": 273
},
{
"epoch": 0.5,
"grad_norm": 0.04849430173635483,
"learning_rate": 0.00018739249043785324,
"loss": 1.7442,
"step": 274
},
{
"epoch": 0.5,
"eval_loss": 1.726025938987732,
"eval_runtime": 76.0967,
"eval_samples_per_second": 65.706,
"eval_steps_per_second": 16.426,
"step": 274
},
{
"epoch": 0.5,
"grad_norm": 0.04745488613843918,
"learning_rate": 0.00018729887697804847,
"loss": 1.7398,
"step": 275
},
{
"epoch": 0.5,
"grad_norm": 0.05489857494831085,
"learning_rate": 0.00018720494081438078,
"loss": 1.701,
"step": 276
},
{
"epoch": 0.51,
"grad_norm": 0.04818108305335045,
"learning_rate": 0.00018711068229408903,
"loss": 1.7068,
"step": 277
},
{
"epoch": 0.51,
"grad_norm": 0.04530555009841919,
"learning_rate": 0.0001870161017656037,
"loss": 1.6966,
"step": 278
},
{
"epoch": 0.51,
"grad_norm": 0.045606572180986404,
"learning_rate": 0.00018692119957854558,
"loss": 1.7086,
"step": 279
},
{
"epoch": 0.51,
"grad_norm": 0.04626869410276413,
"learning_rate": 0.00018682597608372445,
"loss": 1.6981,
"step": 280
},
{
"epoch": 0.51,
"grad_norm": 0.04752146080136299,
"learning_rate": 0.0001867304316331379,
"loss": 1.692,
"step": 281
},
{
"epoch": 0.51,
"grad_norm": 0.046230729669332504,
"learning_rate": 0.0001866345665799698,
"loss": 1.7338,
"step": 282
},
{
"epoch": 0.52,
"grad_norm": 0.04928119108080864,
"learning_rate": 0.00018653838127858933,
"loss": 1.738,
"step": 283
},
{
"epoch": 0.52,
"grad_norm": 0.04641352593898773,
"learning_rate": 0.00018644187608454936,
"loss": 1.6792,
"step": 284
},
{
"epoch": 0.52,
"grad_norm": 0.04860611632466316,
"learning_rate": 0.00018634505135458525,
"loss": 1.663,
"step": 285
},
{
"epoch": 0.52,
"grad_norm": 0.046515002846717834,
"learning_rate": 0.00018624790744661355,
"loss": 1.7327,
"step": 286
},
{
"epoch": 0.52,
"grad_norm": 0.04668186604976654,
"learning_rate": 0.00018615044471973074,
"loss": 1.6987,
"step": 287
},
{
"epoch": 0.53,
"grad_norm": 0.047913163900375366,
"learning_rate": 0.00018605266353421176,
"loss": 1.7953,
"step": 288
},
{
"epoch": 0.53,
"grad_norm": 0.04924839362502098,
"learning_rate": 0.00018595456425150872,
"loss": 1.7891,
"step": 289
},
{
"epoch": 0.53,
"grad_norm": 0.049241986125707626,
"learning_rate": 0.00018585614723424962,
"loss": 1.7451,
"step": 290
},
{
"epoch": 0.53,
"grad_norm": 0.05132036283612251,
"learning_rate": 0.00018575741284623703,
"loss": 1.7598,
"step": 291
},
{
"epoch": 0.53,
"grad_norm": 0.04659922048449516,
"learning_rate": 0.00018565836145244662,
"loss": 1.7331,
"step": 292
},
{
"epoch": 0.53,
"grad_norm": 0.0466977022588253,
"learning_rate": 0.0001855589934190259,
"loss": 1.7171,
"step": 293
},
{
"epoch": 0.54,
"grad_norm": 0.049368374049663544,
"learning_rate": 0.00018545930911329287,
"loss": 1.6929,
"step": 294
},
{
"epoch": 0.54,
"grad_norm": 0.04552480950951576,
"learning_rate": 0.00018535930890373466,
"loss": 1.753,
"step": 295
},
{
"epoch": 0.54,
"grad_norm": 0.04755065590143204,
"learning_rate": 0.00018525899316000608,
"loss": 1.7472,
"step": 296
},
{
"epoch": 0.54,
"grad_norm": 0.050540413707494736,
"learning_rate": 0.0001851583622529284,
"loss": 1.7585,
"step": 297
},
{
"epoch": 0.54,
"grad_norm": 0.04644971713423729,
"learning_rate": 0.00018505741655448792,
"loss": 1.7531,
"step": 298
},
{
"epoch": 0.55,
"grad_norm": 0.05085503309965134,
"learning_rate": 0.00018495615643783446,
"loss": 1.6954,
"step": 299
},
{
"epoch": 0.55,
"grad_norm": 0.0480993427336216,
"learning_rate": 0.0001848545822772802,
"loss": 1.6976,
"step": 300
},
{
"epoch": 0.55,
"grad_norm": 0.0487300269305706,
"learning_rate": 0.00018475269444829818,
"loss": 1.7642,
"step": 301
},
{
"epoch": 0.55,
"grad_norm": 0.04805615171790123,
"learning_rate": 0.0001846504933275209,
"loss": 1.6666,
"step": 302
},
{
"epoch": 0.55,
"grad_norm": 0.045554857701063156,
"learning_rate": 0.00018454797929273902,
"loss": 1.7259,
"step": 303
},
{
"epoch": 0.55,
"grad_norm": 0.04570743814110756,
"learning_rate": 0.00018444515272289982,
"loss": 1.7067,
"step": 304
},
{
"epoch": 0.56,
"grad_norm": 0.047652073204517365,
"learning_rate": 0.00018434201399810594,
"loss": 1.8147,
"step": 305
},
{
"epoch": 0.56,
"grad_norm": 0.046781569719314575,
"learning_rate": 0.00018423856349961384,
"loss": 1.7509,
"step": 306
},
{
"epoch": 0.56,
"grad_norm": 0.04698612168431282,
"learning_rate": 0.00018413480160983254,
"loss": 1.7074,
"step": 307
},
{
"epoch": 0.56,
"grad_norm": 0.04796341061592102,
"learning_rate": 0.0001840307287123221,
"loss": 1.7444,
"step": 308
},
{
"epoch": 0.56,
"grad_norm": 0.047553375363349915,
"learning_rate": 0.00018392634519179225,
"loss": 1.7103,
"step": 309
},
{
"epoch": 0.57,
"grad_norm": 0.046323925256729126,
"learning_rate": 0.00018382165143410092,
"loss": 1.716,
"step": 310
},
{
"epoch": 0.57,
"grad_norm": 0.04571986570954323,
"learning_rate": 0.00018371664782625287,
"loss": 1.7035,
"step": 311
},
{
"epoch": 0.57,
"grad_norm": 0.05170504003763199,
"learning_rate": 0.0001836113347563982,
"loss": 1.7151,
"step": 312
},
{
"epoch": 0.57,
"grad_norm": 0.047869808971881866,
"learning_rate": 0.000183505712613831,
"loss": 1.7223,
"step": 313
},
{
"epoch": 0.57,
"grad_norm": 0.0482964813709259,
"learning_rate": 0.0001833997817889878,
"loss": 1.6805,
"step": 314
},
{
"epoch": 0.57,
"grad_norm": 0.0486602708697319,
"learning_rate": 0.00018329354267344625,
"loss": 1.7303,
"step": 315
},
{
"epoch": 0.58,
"grad_norm": 0.046554964035749435,
"learning_rate": 0.00018318699565992357,
"loss": 1.7745,
"step": 316
},
{
"epoch": 0.58,
"grad_norm": 0.047917045652866364,
"learning_rate": 0.00018308014114227513,
"loss": 1.718,
"step": 317
},
{
"epoch": 0.58,
"grad_norm": 0.0479004867374897,
"learning_rate": 0.00018297297951549304,
"loss": 1.7707,
"step": 318
},
{
"epoch": 0.58,
"grad_norm": 0.04681101068854332,
"learning_rate": 0.0001828655111757046,
"loss": 1.7646,
"step": 319
},
{
"epoch": 0.58,
"grad_norm": 0.05201521888375282,
"learning_rate": 0.00018275773652017097,
"loss": 1.7479,
"step": 320
},
{
"epoch": 0.59,
"grad_norm": 0.04852493852376938,
"learning_rate": 0.00018264965594728548,
"loss": 1.7463,
"step": 321
},
{
"epoch": 0.59,
"grad_norm": 0.046121757477521896,
"learning_rate": 0.00018254126985657246,
"loss": 1.7444,
"step": 322
},
{
"epoch": 0.59,
"grad_norm": 0.05163992941379547,
"learning_rate": 0.00018243257864868548,
"loss": 1.7134,
"step": 323
},
{
"epoch": 0.59,
"grad_norm": 0.06267976760864258,
"learning_rate": 0.00018232358272540604,
"loss": 1.6712,
"step": 324
},
{
"epoch": 0.59,
"grad_norm": 0.04854287579655647,
"learning_rate": 0.00018221428248964202,
"loss": 1.6932,
"step": 325
},
{
"epoch": 0.59,
"grad_norm": 0.046650100499391556,
"learning_rate": 0.00018210467834542615,
"loss": 1.768,
"step": 326
},
{
"epoch": 0.6,
"grad_norm": 0.04779491573572159,
"learning_rate": 0.00018199477069791474,
"loss": 1.7109,
"step": 327
},
{
"epoch": 0.6,
"grad_norm": 0.05170130729675293,
"learning_rate": 0.0001818845599533858,
"loss": 1.6926,
"step": 328
},
{
"epoch": 0.6,
"grad_norm": 0.04867775738239288,
"learning_rate": 0.00018177404651923787,
"loss": 1.6908,
"step": 329
},
{
"epoch": 0.6,
"grad_norm": 0.04707460105419159,
"learning_rate": 0.00018166323080398835,
"loss": 1.7461,
"step": 330
},
{
"epoch": 0.6,
"grad_norm": 0.048908475786447525,
"learning_rate": 0.00018155211321727212,
"loss": 1.7214,
"step": 331
},
{
"epoch": 0.61,
"grad_norm": 0.04802173003554344,
"learning_rate": 0.00018144069416983985,
"loss": 1.7528,
"step": 332
},
{
"epoch": 0.61,
"grad_norm": 0.04747573658823967,
"learning_rate": 0.00018132897407355657,
"loss": 1.6726,
"step": 333
},
{
"epoch": 0.61,
"grad_norm": 0.049620069563388824,
"learning_rate": 0.00018121695334140017,
"loss": 1.7215,
"step": 334
},
{
"epoch": 0.61,
"grad_norm": 0.047733817249536514,
"learning_rate": 0.00018110463238745988,
"loss": 1.7538,
"step": 335
},
{
"epoch": 0.61,
"grad_norm": 0.04856455698609352,
"learning_rate": 0.00018099201162693476,
"loss": 1.6833,
"step": 336
},
{
"epoch": 0.61,
"grad_norm": 0.04885758087038994,
"learning_rate": 0.00018087909147613193,
"loss": 1.7141,
"step": 337
},
{
"epoch": 0.62,
"grad_norm": 0.047947369515895844,
"learning_rate": 0.0001807658723524654,
"loss": 1.733,
"step": 338
},
{
"epoch": 0.62,
"grad_norm": 0.0499010868370533,
"learning_rate": 0.0001806523546744543,
"loss": 1.6825,
"step": 339
},
{
"epoch": 0.62,
"grad_norm": 0.048193834722042084,
"learning_rate": 0.0001805385388617213,
"loss": 1.7282,
"step": 340
},
{
"epoch": 0.62,
"grad_norm": 0.05272866412997246,
"learning_rate": 0.00018042442533499123,
"loss": 1.7599,
"step": 341
},
{
"epoch": 0.62,
"grad_norm": 0.047657158225774765,
"learning_rate": 0.00018031001451608943,
"loss": 1.7292,
"step": 342
},
{
"epoch": 0.63,
"grad_norm": 0.0498197004199028,
"learning_rate": 0.00018019530682794014,
"loss": 1.7417,
"step": 343
},
{
"epoch": 0.63,
"grad_norm": 0.04958554729819298,
"learning_rate": 0.00018008030269456505,
"loss": 1.7274,
"step": 344
},
{
"epoch": 0.63,
"grad_norm": 0.04730832576751709,
"learning_rate": 0.00017996500254108152,
"loss": 1.778,
"step": 345
},
{
"epoch": 0.63,
"grad_norm": 0.050828639417886734,
"learning_rate": 0.0001798494067937014,
"loss": 1.7285,
"step": 346
},
{
"epoch": 0.63,
"grad_norm": 0.046292368322610855,
"learning_rate": 0.00017973351587972905,
"loss": 1.7334,
"step": 347
},
{
"epoch": 0.63,
"grad_norm": 0.04758565500378609,
"learning_rate": 0.00017961733022755992,
"loss": 1.6814,
"step": 348
},
{
"epoch": 0.64,
"grad_norm": 0.050507742911577225,
"learning_rate": 0.00017950085026667903,
"loss": 1.6949,
"step": 349
},
{
"epoch": 0.64,
"grad_norm": 0.04801836982369423,
"learning_rate": 0.00017938407642765938,
"loss": 1.6594,
"step": 350
},
{
"epoch": 0.64,
"grad_norm": 0.04616666957736015,
"learning_rate": 0.00017926700914216016,
"loss": 1.6969,
"step": 351
},
{
"epoch": 0.64,
"grad_norm": 0.048213839530944824,
"learning_rate": 0.00017914964884292544,
"loss": 1.6908,
"step": 352
},
{
"epoch": 0.64,
"grad_norm": 0.04909725859761238,
"learning_rate": 0.00017903199596378227,
"loss": 1.7213,
"step": 353
},
{
"epoch": 0.65,
"grad_norm": 0.050252340734004974,
"learning_rate": 0.00017891405093963938,
"loss": 1.7094,
"step": 354
},
{
"epoch": 0.65,
"grad_norm": 0.05401075631380081,
"learning_rate": 0.00017879581420648534,
"loss": 1.7163,
"step": 355
},
{
"epoch": 0.65,
"grad_norm": 0.05027545616030693,
"learning_rate": 0.00017867728620138708,
"loss": 1.7362,
"step": 356
},
{
"epoch": 0.65,
"grad_norm": 0.047479428350925446,
"learning_rate": 0.00017855846736248822,
"loss": 1.6785,
"step": 357
},
{
"epoch": 0.65,
"grad_norm": 0.05026884377002716,
"learning_rate": 0.0001784393581290074,
"loss": 1.7221,
"step": 358
},
{
"epoch": 0.65,
"grad_norm": 0.04901432618498802,
"learning_rate": 0.00017831995894123683,
"loss": 1.6401,
"step": 359
},
{
"epoch": 0.66,
"grad_norm": 0.04764765873551369,
"learning_rate": 0.00017820027024054044,
"loss": 1.7361,
"step": 360
},
{
"epoch": 0.66,
"grad_norm": 0.046871528029441833,
"learning_rate": 0.0001780802924693524,
"loss": 1.7986,
"step": 361
},
{
"epoch": 0.66,
"grad_norm": 0.05453401803970337,
"learning_rate": 0.00017796002607117545,
"loss": 1.7447,
"step": 362
},
{
"epoch": 0.66,
"grad_norm": 0.04958674684166908,
"learning_rate": 0.00017783947149057925,
"loss": 1.7091,
"step": 363
},
{
"epoch": 0.66,
"grad_norm": 0.053141675889492035,
"learning_rate": 0.0001777186291731987,
"loss": 1.6866,
"step": 364
},
{
"epoch": 0.67,
"grad_norm": 0.047340743243694305,
"learning_rate": 0.00017759749956573238,
"loss": 1.7191,
"step": 365
},
{
"epoch": 0.67,
"grad_norm": 0.051203418523073196,
"learning_rate": 0.00017747608311594087,
"loss": 1.7238,
"step": 366
},
{
"epoch": 0.67,
"grad_norm": 0.047188933938741684,
"learning_rate": 0.00017735438027264495,
"loss": 1.762,
"step": 367
},
{
"epoch": 0.67,
"grad_norm": 0.056479763239622116,
"learning_rate": 0.00017723239148572422,
"loss": 1.6587,
"step": 368
},
{
"epoch": 0.67,
"grad_norm": 0.04922572523355484,
"learning_rate": 0.00017711011720611514,
"loss": 1.6988,
"step": 369
},
{
"epoch": 0.67,
"grad_norm": 0.046839334070682526,
"learning_rate": 0.00017698755788580963,
"loss": 1.7092,
"step": 370
},
{
"epoch": 0.68,
"grad_norm": 0.0491393506526947,
"learning_rate": 0.0001768647139778532,
"loss": 1.7313,
"step": 371
},
{
"epoch": 0.68,
"grad_norm": 0.04811710864305496,
"learning_rate": 0.0001767415859363434,
"loss": 1.8071,
"step": 372
},
{
"epoch": 0.68,
"grad_norm": 0.04601633548736572,
"learning_rate": 0.00017661817421642804,
"loss": 1.7594,
"step": 373
},
{
"epoch": 0.68,
"grad_norm": 0.05098440870642662,
"learning_rate": 0.00017649447927430362,
"loss": 1.6524,
"step": 374
},
{
"epoch": 0.68,
"grad_norm": 0.04978582262992859,
"learning_rate": 0.00017637050156721346,
"loss": 1.7448,
"step": 375
},
{
"epoch": 0.69,
"grad_norm": 0.05097389221191406,
"learning_rate": 0.00017624624155344626,
"loss": 1.7362,
"step": 376
},
{
"epoch": 0.69,
"grad_norm": 0.05258944630622864,
"learning_rate": 0.00017612169969233424,
"loss": 1.7033,
"step": 377
},
{
"epoch": 0.69,
"grad_norm": 0.05384654179215431,
"learning_rate": 0.0001759968764442515,
"loss": 1.6349,
"step": 378
},
{
"epoch": 0.69,
"grad_norm": 0.047803860157728195,
"learning_rate": 0.00017587177227061226,
"loss": 1.6655,
"step": 379
},
{
"epoch": 0.69,
"grad_norm": 0.04812454432249069,
"learning_rate": 0.00017574638763386916,
"loss": 1.7064,
"step": 380
},
{
"epoch": 0.69,
"grad_norm": 0.04860275238752365,
"learning_rate": 0.00017562072299751163,
"loss": 1.6648,
"step": 381
},
{
"epoch": 0.7,
"grad_norm": 0.049836620688438416,
"learning_rate": 0.00017549477882606418,
"loss": 1.6957,
"step": 382
},
{
"epoch": 0.7,
"grad_norm": 0.05114325135946274,
"learning_rate": 0.00017536855558508458,
"loss": 1.6257,
"step": 383
},
{
"epoch": 0.7,
"grad_norm": 0.054609425365924835,
"learning_rate": 0.00017524205374116214,
"loss": 1.6854,
"step": 384
},
{
"epoch": 0.7,
"grad_norm": 0.04757620766758919,
"learning_rate": 0.00017511527376191618,
"loss": 1.7425,
"step": 385
},
{
"epoch": 0.7,
"grad_norm": 0.05384545028209686,
"learning_rate": 0.00017498821611599397,
"loss": 1.712,
"step": 386
},
{
"epoch": 0.71,
"grad_norm": 0.04726232588291168,
"learning_rate": 0.00017486088127306932,
"loss": 1.701,
"step": 387
},
{
"epoch": 0.71,
"grad_norm": 0.04885297268629074,
"learning_rate": 0.0001747332697038407,
"loss": 1.7227,
"step": 388
},
{
"epoch": 0.71,
"grad_norm": 0.04793693870306015,
"learning_rate": 0.00017460538188002946,
"loss": 1.7058,
"step": 389
},
{
"epoch": 0.71,
"grad_norm": 0.04942973330616951,
"learning_rate": 0.0001744772182743782,
"loss": 1.7443,
"step": 390
},
{
"epoch": 0.71,
"grad_norm": 0.05246872082352638,
"learning_rate": 0.00017434877936064886,
"loss": 1.6807,
"step": 391
},
{
"epoch": 0.71,
"grad_norm": 0.04894121363759041,
"learning_rate": 0.0001742200656136212,
"loss": 1.7963,
"step": 392
},
{
"epoch": 0.72,
"grad_norm": 0.05082324892282486,
"learning_rate": 0.00017409107750909078,
"loss": 1.7024,
"step": 393
},
{
"epoch": 0.72,
"grad_norm": 0.04718152433633804,
"learning_rate": 0.00017396181552386741,
"loss": 1.711,
"step": 394
},
{
"epoch": 0.72,
"grad_norm": 0.05174902826547623,
"learning_rate": 0.00017383228013577331,
"loss": 1.7362,
"step": 395
},
{
"epoch": 0.72,
"grad_norm": 0.048003047704696655,
"learning_rate": 0.0001737024718236413,
"loss": 1.6944,
"step": 396
},
{
"epoch": 0.72,
"grad_norm": 0.0462164506316185,
"learning_rate": 0.00017357239106731317,
"loss": 1.7297,
"step": 397
},
{
"epoch": 0.73,
"grad_norm": 0.04808316007256508,
"learning_rate": 0.0001734420383476377,
"loss": 1.6971,
"step": 398
},
{
"epoch": 0.73,
"grad_norm": 0.05553476884961128,
"learning_rate": 0.00017331141414646904,
"loss": 1.7262,
"step": 399
},
{
"epoch": 0.73,
"grad_norm": 0.046341411769390106,
"learning_rate": 0.00017318051894666487,
"loss": 1.7135,
"step": 400
},
{
"epoch": 0.73,
"grad_norm": 0.048155754804611206,
"learning_rate": 0.00017304935323208466,
"loss": 1.7377,
"step": 401
},
{
"epoch": 0.73,
"grad_norm": 0.05066389963030815,
"learning_rate": 0.00017291791748758785,
"loss": 1.6516,
"step": 402
},
{
"epoch": 0.73,
"grad_norm": 0.05046610161662102,
"learning_rate": 0.000172786212199032,
"loss": 1.7536,
"step": 403
},
{
"epoch": 0.74,
"grad_norm": 0.0542440302670002,
"learning_rate": 0.00017265423785327107,
"loss": 1.7857,
"step": 404
},
{
"epoch": 0.74,
"grad_norm": 0.04833053797483444,
"learning_rate": 0.0001725219949381537,
"loss": 1.7594,
"step": 405
},
{
"epoch": 0.74,
"grad_norm": 0.047335654497146606,
"learning_rate": 0.00017238948394252115,
"loss": 1.7495,
"step": 406
},
{
"epoch": 0.74,
"grad_norm": 0.04961543157696724,
"learning_rate": 0.00017225670535620576,
"loss": 1.7201,
"step": 407
},
{
"epoch": 0.74,
"grad_norm": 0.04761854186654091,
"learning_rate": 0.00017212365967002893,
"loss": 1.7522,
"step": 408
},
{
"epoch": 0.75,
"grad_norm": 0.05010442063212395,
"learning_rate": 0.0001719903473757996,
"loss": 1.7535,
"step": 409
},
{
"epoch": 0.75,
"grad_norm": 0.049323149025440216,
"learning_rate": 0.000171856768966312,
"loss": 1.6984,
"step": 410
},
{
"epoch": 0.75,
"grad_norm": 0.08661342412233353,
"learning_rate": 0.0001717229249353442,
"loss": 1.7182,
"step": 411
},
{
"epoch": 0.75,
"eval_loss": 1.724851131439209,
"eval_runtime": 76.3068,
"eval_samples_per_second": 65.525,
"eval_steps_per_second": 16.381,
"step": 411
},
{
"epoch": 0.75,
"grad_norm": 0.05118868127465248,
"learning_rate": 0.00017158881577765612,
"loss": 1.683,
"step": 412
},
{
"epoch": 0.75,
"grad_norm": 0.053089968860149384,
"learning_rate": 0.00017145444198898776,
"loss": 1.7162,
"step": 413
},
{
"epoch": 0.75,
"grad_norm": 0.05191902816295624,
"learning_rate": 0.0001713198040660573,
"loss": 1.7223,
"step": 414
},
{
"epoch": 0.76,
"grad_norm": 0.05995416268706322,
"learning_rate": 0.00017118490250655932,
"loss": 1.7148,
"step": 415
},
{
"epoch": 0.76,
"grad_norm": 0.04749016463756561,
"learning_rate": 0.00017104973780916294,
"loss": 1.7364,
"step": 416
},
{
"epoch": 0.76,
"grad_norm": 0.047870930284261703,
"learning_rate": 0.00017091431047351,
"loss": 1.7607,
"step": 417
},
{
"epoch": 0.76,
"grad_norm": 0.04802364483475685,
"learning_rate": 0.00017077862100021318,
"loss": 1.6957,
"step": 418
},
{
"epoch": 0.76,
"grad_norm": 0.04796374961733818,
"learning_rate": 0.00017064266989085412,
"loss": 1.6972,
"step": 419
},
{
"epoch": 0.77,
"grad_norm": 0.048874564468860626,
"learning_rate": 0.00017050645764798164,
"loss": 1.736,
"step": 420
},
{
"epoch": 0.77,
"grad_norm": 0.052477337419986725,
"learning_rate": 0.00017036998477510992,
"loss": 1.7447,
"step": 421
},
{
"epoch": 0.77,
"grad_norm": 0.049993280321359634,
"learning_rate": 0.00017023325177671647,
"loss": 1.7635,
"step": 422
},
{
"epoch": 0.77,
"grad_norm": 0.09700744599103928,
"learning_rate": 0.00017009625915824037,
"loss": 1.7402,
"step": 423
},
{
"epoch": 0.77,
"grad_norm": 0.048865802586078644,
"learning_rate": 0.0001699590074260805,
"loss": 1.7229,
"step": 424
},
{
"epoch": 0.77,
"grad_norm": 0.04994821920990944,
"learning_rate": 0.00016982149708759343,
"loss": 1.672,
"step": 425
},
{
"epoch": 0.78,
"grad_norm": 0.05008814111351967,
"learning_rate": 0.00016968372865109176,
"loss": 1.7338,
"step": 426
},
{
"epoch": 0.78,
"grad_norm": 0.04830687865614891,
"learning_rate": 0.00016954570262584214,
"loss": 1.7177,
"step": 427
},
{
"epoch": 0.78,
"grad_norm": 0.04781452193856239,
"learning_rate": 0.0001694074195220634,
"loss": 1.7628,
"step": 428
},
{
"epoch": 0.78,
"grad_norm": 0.04739667847752571,
"learning_rate": 0.00016926887985092468,
"loss": 1.7107,
"step": 429
},
{
"epoch": 0.78,
"grad_norm": 0.0481286458671093,
"learning_rate": 0.00016913008412454357,
"loss": 1.7646,
"step": 430
},
{
"epoch": 0.79,
"grad_norm": 0.06283537298440933,
"learning_rate": 0.0001689910328559841,
"loss": 1.6896,
"step": 431
},
{
"epoch": 0.79,
"grad_norm": 0.04944480583071709,
"learning_rate": 0.00016885172655925495,
"loss": 1.6931,
"step": 432
},
{
"epoch": 0.79,
"grad_norm": 0.05051645264029503,
"learning_rate": 0.00016871216574930754,
"loss": 1.7752,
"step": 433
},
{
"epoch": 0.79,
"grad_norm": 0.05406402051448822,
"learning_rate": 0.0001685723509420341,
"loss": 1.7203,
"step": 434
},
{
"epoch": 0.79,
"grad_norm": 0.0995137020945549,
"learning_rate": 0.00016843228265426584,
"loss": 1.6454,
"step": 435
},
{
"epoch": 0.79,
"grad_norm": 0.05356389284133911,
"learning_rate": 0.00016829196140377085,
"loss": 1.7327,
"step": 436
},
{
"epoch": 0.8,
"grad_norm": 0.04902141913771629,
"learning_rate": 0.0001681513877092523,
"loss": 1.7262,
"step": 437
},
{
"epoch": 0.8,
"grad_norm": 0.047820378094911575,
"learning_rate": 0.00016801056209034672,
"loss": 1.7294,
"step": 438
},
{
"epoch": 0.8,
"grad_norm": 0.048359643667936325,
"learning_rate": 0.00016786948506762164,
"loss": 1.6959,
"step": 439
},
{
"epoch": 0.8,
"grad_norm": 0.04830753803253174,
"learning_rate": 0.00016772815716257412,
"loss": 1.7714,
"step": 440
},
{
"epoch": 0.8,
"grad_norm": 0.05318046733736992,
"learning_rate": 0.0001675865788976285,
"loss": 1.7325,
"step": 441
},
{
"epoch": 0.81,
"grad_norm": 0.04992082715034485,
"learning_rate": 0.0001674447507961346,
"loss": 1.7866,
"step": 442
},
{
"epoch": 0.81,
"grad_norm": 0.05253741890192032,
"learning_rate": 0.0001673026733823658,
"loss": 1.7273,
"step": 443
},
{
"epoch": 0.81,
"grad_norm": 0.05121272802352905,
"learning_rate": 0.00016716034718151706,
"loss": 1.7063,
"step": 444
},
{
"epoch": 0.81,
"grad_norm": 0.04715156927704811,
"learning_rate": 0.000167017772719703,
"loss": 1.7575,
"step": 445
},
{
"epoch": 0.81,
"grad_norm": 0.05717930197715759,
"learning_rate": 0.00016687495052395595,
"loss": 1.7835,
"step": 446
},
{
"epoch": 0.81,
"grad_norm": 0.04992460459470749,
"learning_rate": 0.00016673188112222394,
"loss": 1.7218,
"step": 447
},
{
"epoch": 0.82,
"grad_norm": 0.0481155663728714,
"learning_rate": 0.0001665885650433689,
"loss": 1.7269,
"step": 448
},
{
"epoch": 0.82,
"grad_norm": 0.0485762394964695,
"learning_rate": 0.00016644500281716456,
"loss": 1.6857,
"step": 449
},
{
"epoch": 0.82,
"grad_norm": 0.04729575663805008,
"learning_rate": 0.00016630119497429457,
"loss": 1.7208,
"step": 450
},
{
"epoch": 0.82,
"grad_norm": 0.051819782704114914,
"learning_rate": 0.00016615714204635043,
"loss": 1.7117,
"step": 451
},
{
"epoch": 0.82,
"grad_norm": 0.052782051265239716,
"learning_rate": 0.0001660128445658297,
"loss": 1.7811,
"step": 452
},
{
"epoch": 0.83,
"grad_norm": 0.05251288414001465,
"learning_rate": 0.00016586830306613393,
"loss": 1.7517,
"step": 453
},
{
"epoch": 0.83,
"grad_norm": 0.047806352376937866,
"learning_rate": 0.00016572351808156666,
"loss": 1.7132,
"step": 454
},
{
"epoch": 0.83,
"grad_norm": 0.05114049091935158,
"learning_rate": 0.0001655784901473315,
"loss": 1.7729,
"step": 455
},
{
"epoch": 0.83,
"grad_norm": 0.04811178147792816,
"learning_rate": 0.00016543321979953007,
"loss": 1.7855,
"step": 456
},
{
"epoch": 0.83,
"grad_norm": 0.05107167363166809,
"learning_rate": 0.00016528770757516027,
"loss": 1.7331,
"step": 457
},
{
"epoch": 0.84,
"grad_norm": 0.04712466895580292,
"learning_rate": 0.00016514195401211388,
"loss": 1.7048,
"step": 458
},
{
"epoch": 0.84,
"grad_norm": 0.05438878387212753,
"learning_rate": 0.0001649959596491749,
"loss": 1.753,
"step": 459
},
{
"epoch": 0.84,
"grad_norm": 0.04884348064661026,
"learning_rate": 0.00016484972502601753,
"loss": 1.6734,
"step": 460
},
{
"epoch": 0.84,
"grad_norm": 0.0536276139318943,
"learning_rate": 0.00016470325068320392,
"loss": 1.711,
"step": 461
},
{
"epoch": 0.84,
"grad_norm": 0.05346493422985077,
"learning_rate": 0.00016455653716218252,
"loss": 1.7366,
"step": 462
},
{
"epoch": 0.84,
"grad_norm": 0.05044522508978844,
"learning_rate": 0.0001644095850052858,
"loss": 1.7269,
"step": 463
},
{
"epoch": 0.85,
"grad_norm": 0.05273488536477089,
"learning_rate": 0.00016426239475572852,
"loss": 1.7586,
"step": 464
},
{
"epoch": 0.85,
"grad_norm": 0.053452517837285995,
"learning_rate": 0.0001641149669576053,
"loss": 1.7379,
"step": 465
},
{
"epoch": 0.85,
"grad_norm": 0.047611016780138016,
"learning_rate": 0.00016396730215588915,
"loss": 1.7471,
"step": 466
},
{
"epoch": 0.85,
"grad_norm": 0.05317235738039017,
"learning_rate": 0.00016381940089642893,
"loss": 1.6925,
"step": 467
},
{
"epoch": 0.85,
"grad_norm": 0.049223560839891434,
"learning_rate": 0.00016367126372594774,
"loss": 1.7229,
"step": 468
},
{
"epoch": 0.86,
"grad_norm": 0.047821756452322006,
"learning_rate": 0.0001635228911920407,
"loss": 1.7484,
"step": 469
},
{
"epoch": 0.86,
"grad_norm": 0.05013042315840721,
"learning_rate": 0.00016337428384317288,
"loss": 1.7435,
"step": 470
},
{
"epoch": 0.86,
"grad_norm": 0.04820725694298744,
"learning_rate": 0.00016322544222867742,
"loss": 1.7594,
"step": 471
},
{
"epoch": 0.86,
"grad_norm": 0.04791193827986717,
"learning_rate": 0.00016307636689875347,
"loss": 1.644,
"step": 472
},
{
"epoch": 0.86,
"grad_norm": 0.04905365779995918,
"learning_rate": 0.00016292705840446404,
"loss": 1.7144,
"step": 473
},
{
"epoch": 0.86,
"grad_norm": 0.04875028133392334,
"learning_rate": 0.00016277751729773407,
"loss": 1.712,
"step": 474
},
{
"epoch": 0.87,
"grad_norm": 0.05170164629817009,
"learning_rate": 0.0001626277441313484,
"loss": 1.7367,
"step": 475
},
{
"epoch": 0.87,
"grad_norm": 0.05205371975898743,
"learning_rate": 0.00016247773945894962,
"loss": 1.689,
"step": 476
},
{
"epoch": 0.87,
"grad_norm": 0.0485403798520565,
"learning_rate": 0.00016232750383503617,
"loss": 1.706,
"step": 477
},
{
"epoch": 0.87,
"grad_norm": 0.0538201630115509,
"learning_rate": 0.0001621770378149601,
"loss": 1.7284,
"step": 478
},
{
"epoch": 0.87,
"grad_norm": 0.04828377440571785,
"learning_rate": 0.00016202634195492524,
"loss": 1.661,
"step": 479
},
{
"epoch": 0.88,
"grad_norm": 0.050310611724853516,
"learning_rate": 0.000161875416811985,
"loss": 1.6852,
"step": 480
},
{
"epoch": 0.88,
"grad_norm": 0.050804853439331055,
"learning_rate": 0.00016172426294404032,
"loss": 1.7358,
"step": 481
},
{
"epoch": 0.88,
"grad_norm": 0.051962971687316895,
"learning_rate": 0.00016157288090983763,
"loss": 1.6692,
"step": 482
},
{
"epoch": 0.88,
"grad_norm": 0.05179814621806145,
"learning_rate": 0.0001614212712689668,
"loss": 1.6983,
"step": 483
},
{
"epoch": 0.88,
"grad_norm": 0.05398216098546982,
"learning_rate": 0.00016126943458185907,
"loss": 1.7261,
"step": 484
},
{
"epoch": 0.88,
"grad_norm": 0.049869704991579056,
"learning_rate": 0.00016111737140978494,
"loss": 1.6951,
"step": 485
},
{
"epoch": 0.89,
"grad_norm": 0.048107776790857315,
"learning_rate": 0.00016096508231485217,
"loss": 1.6941,
"step": 486
},
{
"epoch": 0.89,
"grad_norm": 0.05527656897902489,
"learning_rate": 0.00016081256786000357,
"loss": 1.7054,
"step": 487
},
{
"epoch": 0.89,
"grad_norm": 0.05169270187616348,
"learning_rate": 0.00016065982860901504,
"loss": 1.7307,
"step": 488
},
{
"epoch": 0.89,
"grad_norm": 0.04972197115421295,
"learning_rate": 0.00016050686512649354,
"loss": 1.6955,
"step": 489
},
{
"epoch": 0.89,
"grad_norm": 0.05033208429813385,
"learning_rate": 0.00016035367797787476,
"loss": 1.7013,
"step": 490
},
{
"epoch": 0.9,
"grad_norm": 0.05073223263025284,
"learning_rate": 0.00016020026772942125,
"loss": 1.6831,
"step": 491
},
{
"epoch": 0.9,
"grad_norm": 0.056367356330156326,
"learning_rate": 0.00016004663494822028,
"loss": 1.6654,
"step": 492
},
{
"epoch": 0.9,
"grad_norm": 0.049483008682727814,
"learning_rate": 0.0001598927802021817,
"loss": 1.7285,
"step": 493
},
{
"epoch": 0.9,
"grad_norm": 0.052070703357458115,
"learning_rate": 0.00015973870406003578,
"loss": 1.7948,
"step": 494
},
{
"epoch": 0.9,
"grad_norm": 0.05687413364648819,
"learning_rate": 0.0001595844070913314,
"loss": 1.7336,
"step": 495
},
{
"epoch": 0.9,
"grad_norm": 0.048987727612257004,
"learning_rate": 0.00015942988986643352,
"loss": 1.6661,
"step": 496
},
{
"epoch": 0.91,
"grad_norm": 0.05027730017900467,
"learning_rate": 0.00015927515295652143,
"loss": 1.7364,
"step": 497
},
{
"epoch": 0.91,
"grad_norm": 0.048406291753053665,
"learning_rate": 0.00015912019693358636,
"loss": 1.6419,
"step": 498
},
{
"epoch": 0.91,
"grad_norm": 0.05071192979812622,
"learning_rate": 0.00015896502237042963,
"loss": 1.6301,
"step": 499
},
{
"epoch": 0.91,
"grad_norm": 0.05111885070800781,
"learning_rate": 0.00015880962984066036,
"loss": 1.7112,
"step": 500
},
{
"epoch": 0.91,
"grad_norm": 0.06297910958528519,
"learning_rate": 0.0001586540199186933,
"loss": 1.7438,
"step": 501
},
{
"epoch": 0.92,
"grad_norm": 0.04950469359755516,
"learning_rate": 0.00015849819317974694,
"loss": 1.6837,
"step": 502
},
{
"epoch": 0.92,
"grad_norm": 0.04900701716542244,
"learning_rate": 0.0001583421501998412,
"loss": 1.7432,
"step": 503
},
{
"epoch": 0.92,
"grad_norm": 0.04949019104242325,
"learning_rate": 0.0001581858915557953,
"loss": 1.688,
"step": 504
},
{
"epoch": 0.92,
"grad_norm": 0.05047097057104111,
"learning_rate": 0.00015802941782522569,
"loss": 1.7256,
"step": 505
},
{
"epoch": 0.92,
"grad_norm": 0.04921870306134224,
"learning_rate": 0.0001578727295865439,
"loss": 1.7723,
"step": 506
},
{
"epoch": 0.92,
"grad_norm": 0.04841122031211853,
"learning_rate": 0.0001577158274189544,
"loss": 1.71,
"step": 507
},
{
"epoch": 0.93,
"grad_norm": 0.04886234924197197,
"learning_rate": 0.00015755871190245251,
"loss": 1.6622,
"step": 508
},
{
"epoch": 0.93,
"grad_norm": 0.04966573417186737,
"learning_rate": 0.00015740138361782207,
"loss": 1.7357,
"step": 509
},
{
"epoch": 0.93,
"grad_norm": 0.050070296972990036,
"learning_rate": 0.0001572438431466336,
"loss": 1.6803,
"step": 510
},
{
"epoch": 0.93,
"grad_norm": 0.054121073335409164,
"learning_rate": 0.00015708609107124177,
"loss": 1.7659,
"step": 511
},
{
"epoch": 0.93,
"grad_norm": 0.05084529519081116,
"learning_rate": 0.00015692812797478368,
"loss": 1.6943,
"step": 512
},
{
"epoch": 0.94,
"grad_norm": 0.056926507502794266,
"learning_rate": 0.0001567699544411763,
"loss": 1.6562,
"step": 513
},
{
"epoch": 0.94,
"grad_norm": 0.05053721368312836,
"learning_rate": 0.00015661157105511457,
"loss": 1.7624,
"step": 514
},
{
"epoch": 0.94,
"grad_norm": 0.048727016896009445,
"learning_rate": 0.00015645297840206915,
"loss": 1.7364,
"step": 515
},
{
"epoch": 0.94,
"grad_norm": 0.051376283168792725,
"learning_rate": 0.00015629417706828423,
"loss": 1.699,
"step": 516
},
{
"epoch": 0.94,
"grad_norm": 0.05029591917991638,
"learning_rate": 0.00015613516764077548,
"loss": 1.6972,
"step": 517
},
{
"epoch": 0.94,
"grad_norm": 0.053968969732522964,
"learning_rate": 0.00015597595070732765,
"loss": 1.7128,
"step": 518
},
{
"epoch": 0.95,
"grad_norm": 0.050694871693849564,
"learning_rate": 0.00015581652685649276,
"loss": 1.7681,
"step": 519
},
{
"epoch": 0.95,
"grad_norm": 0.052369993180036545,
"learning_rate": 0.00015565689667758746,
"loss": 1.7321,
"step": 520
},
{
"epoch": 0.95,
"grad_norm": 0.04850650206208229,
"learning_rate": 0.00015549706076069128,
"loss": 1.7162,
"step": 521
},
{
"epoch": 0.95,
"grad_norm": 0.04979635775089264,
"learning_rate": 0.00015533701969664424,
"loss": 1.7429,
"step": 522
},
{
"epoch": 0.95,
"grad_norm": 0.04920853301882744,
"learning_rate": 0.0001551767740770446,
"loss": 1.7103,
"step": 523
},
{
"epoch": 0.96,
"grad_norm": 0.05081456899642944,
"learning_rate": 0.0001550163244942469,
"loss": 1.7781,
"step": 524
},
{
"epoch": 0.96,
"grad_norm": 0.050754062831401825,
"learning_rate": 0.00015485567154135952,
"loss": 1.7496,
"step": 525
},
{
"epoch": 0.96,
"grad_norm": 0.050315603613853455,
"learning_rate": 0.00015469481581224272,
"loss": 1.7303,
"step": 526
},
{
"epoch": 0.96,
"grad_norm": 0.05050061643123627,
"learning_rate": 0.00015453375790150617,
"loss": 1.679,
"step": 527
},
{
"epoch": 0.96,
"grad_norm": 0.06212810054421425,
"learning_rate": 0.00015437249840450715,
"loss": 1.713,
"step": 528
},
{
"epoch": 0.96,
"grad_norm": 0.050966355949640274,
"learning_rate": 0.00015421103791734786,
"loss": 1.7551,
"step": 529
},
{
"epoch": 0.97,
"grad_norm": 0.04892159253358841,
"learning_rate": 0.00015404937703687363,
"loss": 1.6758,
"step": 530
},
{
"epoch": 0.97,
"grad_norm": 0.05551762133836746,
"learning_rate": 0.00015388751636067052,
"loss": 1.703,
"step": 531
},
{
"epoch": 0.97,
"grad_norm": 0.0516047477722168,
"learning_rate": 0.00015372545648706306,
"loss": 1.7407,
"step": 532
},
{
"epoch": 0.97,
"grad_norm": 0.05094458907842636,
"learning_rate": 0.0001535631980151123,
"loss": 1.6534,
"step": 533
},
{
"epoch": 0.97,
"grad_norm": 0.05045678839087486,
"learning_rate": 0.00015340074154461316,
"loss": 1.7335,
"step": 534
},
{
"epoch": 0.98,
"grad_norm": 0.05067756026983261,
"learning_rate": 0.00015323808767609277,
"loss": 1.7169,
"step": 535
},
{
"epoch": 0.98,
"grad_norm": 0.05005278438329697,
"learning_rate": 0.00015307523701080768,
"loss": 1.7778,
"step": 536
},
{
"epoch": 0.98,
"grad_norm": 0.04952746629714966,
"learning_rate": 0.0001529121901507421,
"loss": 1.7199,
"step": 537
},
{
"epoch": 0.98,
"grad_norm": 0.04711218178272247,
"learning_rate": 0.00015274894769860538,
"loss": 1.734,
"step": 538
},
{
"epoch": 0.98,
"grad_norm": 0.05313078686594963,
"learning_rate": 0.0001525855102578299,
"loss": 1.7733,
"step": 539
},
{
"epoch": 0.98,
"grad_norm": 0.04977120831608772,
"learning_rate": 0.0001524218784325688,
"loss": 1.731,
"step": 540
},
{
"epoch": 0.99,
"grad_norm": 0.05076899752020836,
"learning_rate": 0.00015225805282769383,
"loss": 1.7277,
"step": 541
},
{
"epoch": 0.99,
"grad_norm": 0.049164701253175735,
"learning_rate": 0.00015209403404879303,
"loss": 1.7032,
"step": 542
},
{
"epoch": 0.99,
"grad_norm": 0.0488349013030529,
"learning_rate": 0.00015192982270216854,
"loss": 1.765,
"step": 543
},
{
"epoch": 0.99,
"grad_norm": 0.04831582307815552,
"learning_rate": 0.0001517654193948343,
"loss": 1.7548,
"step": 544
},
{
"epoch": 0.99,
"grad_norm": 0.052940741181373596,
"learning_rate": 0.00015160082473451378,
"loss": 1.7209,
"step": 545
},
{
"epoch": 1.0,
"grad_norm": 0.056908875703811646,
"learning_rate": 0.00015143603932963795,
"loss": 1.6537,
"step": 546
},
{
"epoch": 1.0,
"grad_norm": 0.0509711354970932,
"learning_rate": 0.00015127106378934273,
"loss": 1.7151,
"step": 547
},
{
"epoch": 1.0,
"grad_norm": 0.04795239865779877,
"learning_rate": 0.000151105898723467,
"loss": 1.743,
"step": 548
},
{
"epoch": 1.0,
"eval_loss": 1.7236659526824951,
"eval_runtime": 76.6784,
"eval_samples_per_second": 65.207,
"eval_steps_per_second": 16.302,
"step": 548
}
],
"logging_steps": 1,
"max_steps": 1644,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 548,
"total_flos": 1.6352549111448207e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}