{
  "best_metric": 0.06430045515298843,
  "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold9/checkpoint-80",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 0.2449030578136444,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.2218,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.24171064794063568,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2155,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.29363134503364563,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.1872,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.2547593414783478,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3016,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.2707783281803131,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.223,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.3024180233478546,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.1803,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.2824287414550781,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.176,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.23733387887477875,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2049,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.2060697227716446,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1292,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.19718976318836212,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1903,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.12897364795207977,
      "eval_runtime": 24.1485,
      "eval_samples_per_second": 1.863,
      "eval_steps_per_second": 1.863,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.21620500087738037,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1265,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.21922700107097626,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1484,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.17794308066368103,
      "learning_rate": 0.0001,
      "loss": 0.0999,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.22712421417236328,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1262,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.24222469329833984,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.0718,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.1972365379333496,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1254,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.13944408297538757,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.0871,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.1257743239402771,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.0606,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.14348773658275604,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1145,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.1434425413608551,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1096,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.08251665532588959,
      "eval_runtime": 24.0407,
      "eval_samples_per_second": 1.872,
      "eval_steps_per_second": 1.872,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.17193934321403503,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0795,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.1412028968334198,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0698,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.13354283571243286,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0812,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.1417178064584732,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1009,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.11303646117448807,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0851,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.14305493235588074,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.068,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.1320960819721222,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0771,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.09631136804819107,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1052,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.13920649886131287,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0772,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.09726130962371826,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0595,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.07180650532245636,
      "eval_runtime": 24.0509,
      "eval_samples_per_second": 1.871,
      "eval_steps_per_second": 1.871,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.10261917114257812,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1116,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.13251414895057678,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0985,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.12217247486114502,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.092,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.11586838960647583,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0845,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.09095937013626099,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0383,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.10343356430530548,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0981,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.09901493787765503,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0589,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.10670553892850876,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1135,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.10633300989866257,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1016,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.08515916764736176,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0329,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.06832799315452576,
      "eval_runtime": 24.0681,
      "eval_samples_per_second": 1.87,
      "eval_steps_per_second": 1.87,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.09051170200109482,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0297,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.07513455301523209,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0444,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.09506039321422577,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0868,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.11074140667915344,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1201,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.07152170687913895,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0265,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.07951117306947708,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0412,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.09947697818279266,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0804,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.09722726792097092,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0733,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.10544433444738388,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0585,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.1027018278837204,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0676,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.06593237817287445,
      "eval_runtime": 24.0689,
      "eval_samples_per_second": 1.87,
      "eval_steps_per_second": 1.87,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.08724581450223923,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.0689,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.07848672568798065,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0461,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.0906754657626152,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0792,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.084195576608181,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0764,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.1022232323884964,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0388,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.10651250928640366,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0877,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.09016381949186325,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0578,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.11179405450820923,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0608,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.10544200986623764,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0585,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.10589328408241272,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.058,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06448403000831604,
      "eval_runtime": 24.0395,
      "eval_samples_per_second": 1.872,
      "eval_steps_per_second": 1.872,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.08941201120615005,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0281,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.0949765294790268,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0636,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.09317196905612946,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0418,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.1047525405883789,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0397,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.12745285034179688,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0809,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.08987182378768921,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0512,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.13599684834480286,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0909,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.13886308670043945,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.1175,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.11121316254138947,
      "learning_rate": 5e-05,
      "loss": 0.0745,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.11462701857089996,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0762,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06464677304029465,
      "eval_runtime": 24.0487,
      "eval_samples_per_second": 1.871,
      "eval_steps_per_second": 1.871,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.10356437414884567,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0584,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.12310153990983963,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0815,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.14446136355400085,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0783,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.11070472002029419,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.049,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.1546012908220291,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0431,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.1295369416475296,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0631,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.09451998770236969,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0334,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.1328885406255722,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1065,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.093851737678051,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0305,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.11414070427417755,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0736,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06430045515298843,
      "eval_runtime": 24.0475,
      "eval_samples_per_second": 1.871,
      "eval_steps_per_second": 1.871,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.11441301554441452,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0502,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.0899779349565506,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0221,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.12804819643497467,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0925,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.10675077885389328,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.035,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.12324582785367966,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0686,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.0948246642947197,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0446,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.1134951040148735,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0413,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.15832611918449402,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.1184,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.14223675429821014,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0807,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.15457306802272797,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0461,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06514090299606323,
      "eval_runtime": 24.05,
      "eval_samples_per_second": 1.871,
      "eval_steps_per_second": 1.871,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.15105751156806946,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0843,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.12482753396034241,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0445,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.1051236167550087,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0369,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.12820354104042053,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0613,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.10922512412071228,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0333,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.11895215511322021,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0377,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.13706225156784058,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0752,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.12145527452230453,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0496,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.1275850087404251,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.049,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.1079578846693039,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0418,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.06434659659862518,
      "eval_runtime": 24.0326,
      "eval_samples_per_second": 1.872,
      "eval_steps_per_second": 1.872,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.08879292756319046,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.017,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.11166498810052872,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0374,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.11694914102554321,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.055,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.1035614013671875,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0208,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.13867759704589844,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0709,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.1166326031088829,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0469,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.10181581974029541,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0327,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.12328363955020905,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0556,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.12044549733400345,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0475,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.11026214063167572,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.036,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.06455562263727188,
      "eval_runtime": 24.0654,
      "eval_samples_per_second": 1.87,
      "eval_steps_per_second": 1.87,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.12235455214977264,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0524,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.13929158449172974,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.064,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.13404032588005066,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0536,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.11346849799156189,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.033,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.11569420248270035,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.044,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.09922175854444504,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0275,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.10174219310283661,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0316,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.13236071169376373,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.051,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.12899349629878998,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0642,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.11578886955976486,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0585,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.06467783451080322,
      "eval_runtime": 24.0475,
      "eval_samples_per_second": 1.871,
      "eval_steps_per_second": 1.871,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.1402849406003952,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0882,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.1214141994714737,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0558,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.10599435120820999,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0482,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.12227160483598709,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0504,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.11777521669864655,
      "learning_rate": 0.0,
      "loss": 0.0471,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.5260108630084813e+17,
      "train_loss": 0.07662292210757732,
      "train_runtime": 3927.7312,
      "train_samples_per_second": 0.516,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5260108630084813e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}