{
  "best_global_step": 29928,
  "best_metric": 1.3960472345352173,
  "best_model_checkpoint": "/media/user/Expansion1/bge-small-en-v1.5-difficulty/checkpoint-29928",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 49880,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05012028869286287,
      "grad_norm": 20.904003143310547,
      "learning_rate": 4.949979951884523e-05,
      "loss": 2.8228,
      "num_input_tokens_seen": 512000,
      "step": 500,
      "train_runtime": 8.8913,
      "train_tokens_per_second": 57584.306
    },
    {
      "epoch": 0.10024057738572574,
      "grad_norm": 12.451107025146484,
      "learning_rate": 4.89985966319166e-05,
      "loss": 2.1773,
      "num_input_tokens_seen": 1024000,
      "step": 1000,
      "train_runtime": 17.6179,
      "train_tokens_per_second": 58122.733
    },
    {
      "epoch": 0.15036086607858862,
      "grad_norm": 16.641538619995117,
      "learning_rate": 4.8497393744987976e-05,
      "loss": 2.0748,
      "num_input_tokens_seen": 1536000,
      "step": 1500,
      "train_runtime": 26.3873,
      "train_tokens_per_second": 58209.831
    },
    {
      "epoch": 0.20048115477145148,
      "grad_norm": 73.38098907470703,
      "learning_rate": 4.799619085805934e-05,
      "loss": 1.9491,
      "num_input_tokens_seen": 2048000,
      "step": 2000,
      "train_runtime": 35.8472,
      "train_tokens_per_second": 57131.362
    },
    {
      "epoch": 0.25060144346431434,
      "grad_norm": 31.689462661743164,
      "learning_rate": 4.749498797113072e-05,
      "loss": 1.9053,
      "num_input_tokens_seen": 2560000,
      "step": 2500,
      "train_runtime": 44.4801,
      "train_tokens_per_second": 57553.849
    },
    {
      "epoch": 0.30072173215717724,
      "grad_norm": 29.609472274780273,
      "learning_rate": 4.6993785084202085e-05,
      "loss": 1.8656,
      "num_input_tokens_seen": 3072000,
      "step": 3000,
      "train_runtime": 52.9662,
      "train_tokens_per_second": 57999.273
    },
    {
      "epoch": 0.35084202085004007,
      "grad_norm": 38.602455139160156,
      "learning_rate": 4.649258219727346e-05,
      "loss": 1.7632,
      "num_input_tokens_seen": 3584000,
      "step": 3500,
      "train_runtime": 61.6619,
      "train_tokens_per_second": 58123.428
    },
    {
      "epoch": 0.40096230954290296,
      "grad_norm": 22.875041961669922,
      "learning_rate": 4.5991379310344826e-05,
      "loss": 1.7646,
      "num_input_tokens_seen": 4096000,
      "step": 4000,
      "train_runtime": 71.1096,
      "train_tokens_per_second": 57601.205
    },
    {
      "epoch": 0.45108259823576585,
      "grad_norm": 16.16622543334961,
      "learning_rate": 4.54901764234162e-05,
      "loss": 1.7776,
      "num_input_tokens_seen": 4608000,
      "step": 4500,
      "train_runtime": 80.4063,
      "train_tokens_per_second": 57308.917
    },
    {
      "epoch": 0.5012028869286287,
      "grad_norm": 32.55996322631836,
      "learning_rate": 4.4988973536487574e-05,
      "loss": 1.7116,
      "num_input_tokens_seen": 5120000,
      "step": 5000,
      "train_runtime": 89.0298,
      "train_tokens_per_second": 57508.845
    },
    {
      "epoch": 0.5513231756214916,
      "grad_norm": 20.554651260375977,
      "learning_rate": 4.448777064955895e-05,
      "loss": 1.5971,
      "num_input_tokens_seen": 5632000,
      "step": 5500,
      "train_runtime": 97.4489,
      "train_tokens_per_second": 57794.413
    },
    {
      "epoch": 0.6014434643143545,
      "grad_norm": 20.460784912109375,
      "learning_rate": 4.3986567762630315e-05,
      "loss": 1.659,
      "num_input_tokens_seen": 6144000,
      "step": 6000,
      "train_runtime": 105.9015,
      "train_tokens_per_second": 58016.196
    },
    {
      "epoch": 0.6515637530072174,
      "grad_norm": 13.925053596496582,
      "learning_rate": 4.348536487570168e-05,
      "loss": 1.7245,
      "num_input_tokens_seen": 6656000,
      "step": 6500,
      "train_runtime": 114.3689,
      "train_tokens_per_second": 58197.66
    },
    {
      "epoch": 0.7016840417000801,
      "grad_norm": 25.706527709960938,
      "learning_rate": 4.2984161988773056e-05,
      "loss": 1.6292,
      "num_input_tokens_seen": 7168000,
      "step": 7000,
      "train_runtime": 122.8607,
      "train_tokens_per_second": 58342.5
    },
    {
      "epoch": 0.751804330392943,
      "grad_norm": 52.04703903198242,
      "learning_rate": 4.248295910184443e-05,
      "loss": 1.6496,
      "num_input_tokens_seen": 7680000,
      "step": 7500,
      "train_runtime": 131.9546,
      "train_tokens_per_second": 58201.853
    },
    {
      "epoch": 0.8019246190858059,
      "grad_norm": 21.66624641418457,
      "learning_rate": 4.1981756214915804e-05,
      "loss": 1.6804,
      "num_input_tokens_seen": 8192000,
      "step": 8000,
      "train_runtime": 141.0149,
      "train_tokens_per_second": 58093.165
    },
    {
      "epoch": 0.8520449077786688,
      "grad_norm": 21.243003845214844,
      "learning_rate": 4.148055332798717e-05,
      "loss": 1.7315,
      "num_input_tokens_seen": 8704000,
      "step": 8500,
      "train_runtime": 150.3982,
      "train_tokens_per_second": 57873.03
    },
    {
      "epoch": 0.9021651964715317,
      "grad_norm": 31.12165069580078,
      "learning_rate": 4.0979350441058546e-05,
      "loss": 1.6813,
      "num_input_tokens_seen": 9216000,
      "step": 9000,
      "train_runtime": 159.4212,
      "train_tokens_per_second": 57809.11
    },
    {
      "epoch": 0.9522854851643946,
      "grad_norm": 53.82347869873047,
      "learning_rate": 4.047814755412991e-05,
      "loss": 1.6662,
      "num_input_tokens_seen": 9728000,
      "step": 9500,
      "train_runtime": 168.0353,
      "train_tokens_per_second": 57892.585
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5963636636734009,
      "eval_mse": 1.5963637144905036,
      "eval_runtime": 11.8793,
      "eval_samples_per_second": 1679.557,
      "eval_steps_per_second": 209.945,
      "num_input_tokens_seen": 10215168,
      "step": 9976
    },
    {
      "epoch": 1.0024057738572574,
      "grad_norm": 32.9880485534668,
      "learning_rate": 3.997694466720128e-05,
      "loss": 1.6371,
      "num_input_tokens_seen": 10239744,
      "step": 10000,
      "train_runtime": 188.7939,
      "train_tokens_per_second": 54237.687
    },
    {
      "epoch": 1.0525260625501203,
      "grad_norm": 30.20238494873047,
      "learning_rate": 3.9475741780272654e-05,
      "loss": 1.2172,
      "num_input_tokens_seen": 10751744,
      "step": 10500,
      "train_runtime": 197.3774,
      "train_tokens_per_second": 54473.022
    },
    {
      "epoch": 1.1026463512429832,
      "grad_norm": 6.598354339599609,
      "learning_rate": 3.897453889334403e-05,
      "loss": 1.2349,
      "num_input_tokens_seen": 11263744,
      "step": 11000,
      "train_runtime": 205.8828,
      "train_tokens_per_second": 54709.488
    },
    {
      "epoch": 1.152766639935846,
      "grad_norm": 18.5355167388916,
      "learning_rate": 3.84733360064154e-05,
      "loss": 1.2043,
      "num_input_tokens_seen": 11775744,
      "step": 11500,
      "train_runtime": 214.374,
      "train_tokens_per_second": 54930.852
    },
    {
      "epoch": 1.202886928628709,
      "grad_norm": 27.85222816467285,
      "learning_rate": 3.797213311948677e-05,
      "loss": 1.2044,
      "num_input_tokens_seen": 12287744,
      "step": 12000,
      "train_runtime": 222.8513,
      "train_tokens_per_second": 55138.757
    },
    {
      "epoch": 1.2530072173215718,
      "grad_norm": 11.679412841796875,
      "learning_rate": 3.747093023255814e-05,
      "loss": 1.194,
      "num_input_tokens_seen": 12799744,
      "step": 12500,
      "train_runtime": 231.332,
      "train_tokens_per_second": 55330.631
    },
    {
      "epoch": 1.3031275060144347,
      "grad_norm": 47.29853057861328,
      "learning_rate": 3.696972734562951e-05,
      "loss": 1.175,
      "num_input_tokens_seen": 13311744,
      "step": 13000,
      "train_runtime": 239.7491,
      "train_tokens_per_second": 55523.647
    },
    {
      "epoch": 1.3532477947072974,
      "grad_norm": 28.196550369262695,
      "learning_rate": 3.6468524458700885e-05,
      "loss": 1.1053,
      "num_input_tokens_seen": 13823744,
      "step": 13500,
      "train_runtime": 248.1824,
      "train_tokens_per_second": 55699.934
    },
    {
      "epoch": 1.4033680834001605,
      "grad_norm": 11.712139129638672,
      "learning_rate": 3.596732157177226e-05,
      "loss": 1.2474,
      "num_input_tokens_seen": 14335744,
      "step": 14000,
      "train_runtime": 256.6596,
      "train_tokens_per_second": 55855.081
    },
    {
      "epoch": 1.4534883720930232,
      "grad_norm": 35.03483963012695,
      "learning_rate": 3.5466118684843626e-05,
      "loss": 1.157,
      "num_input_tokens_seen": 14847744,
      "step": 14500,
      "train_runtime": 265.103,
      "train_tokens_per_second": 56007.454
    },
    {
      "epoch": 1.5036086607858863,
      "grad_norm": 16.22357749938965,
      "learning_rate": 3.4964915797915e-05,
      "loss": 1.1697,
      "num_input_tokens_seen": 15359744,
      "step": 15000,
      "train_runtime": 273.5202,
      "train_tokens_per_second": 56155.792
    },
    {
      "epoch": 1.553728949478749,
      "grad_norm": 28.68216896057129,
      "learning_rate": 3.446371291098637e-05,
      "loss": 1.1542,
      "num_input_tokens_seen": 15871744,
      "step": 15500,
      "train_runtime": 281.9474,
      "train_tokens_per_second": 56293.271
    },
    {
      "epoch": 1.6038492381716118,
      "grad_norm": 41.835914611816406,
      "learning_rate": 3.396251002405774e-05,
      "loss": 1.1151,
      "num_input_tokens_seen": 16383744,
      "step": 16000,
      "train_runtime": 290.4015,
      "train_tokens_per_second": 56417.558
    },
    {
      "epoch": 1.6539695268644747,
      "grad_norm": 22.626140594482422,
      "learning_rate": 3.346130713712911e-05,
      "loss": 1.2044,
      "num_input_tokens_seen": 16895744,
      "step": 16500,
      "train_runtime": 298.8386,
      "train_tokens_per_second": 56538.031
    },
    {
      "epoch": 1.7040898155573376,
      "grad_norm": 31.7674560546875,
      "learning_rate": 3.296010425020048e-05,
      "loss": 1.2626,
      "num_input_tokens_seen": 17407744,
      "step": 17000,
      "train_runtime": 307.3048,
      "train_tokens_per_second": 56646.502
    },
    {
      "epoch": 1.7542101042502005,
      "grad_norm": 129.8439483642578,
      "learning_rate": 3.2458901363271856e-05,
      "loss": 1.2292,
      "num_input_tokens_seen": 17919744,
      "step": 17500,
      "train_runtime": 315.79,
      "train_tokens_per_second": 56745.76
    },
    {
      "epoch": 1.8043303929430632,
      "grad_norm": 26.7992000579834,
      "learning_rate": 3.1957698476343223e-05,
      "loss": 1.1892,
      "num_input_tokens_seen": 18431744,
      "step": 18000,
      "train_runtime": 324.7824,
      "train_tokens_per_second": 56751.055
    },
    {
      "epoch": 1.8544506816359263,
      "grad_norm": 55.89463806152344,
      "learning_rate": 3.14564955894146e-05,
      "loss": 1.1872,
      "num_input_tokens_seen": 18943744,
      "step": 18500,
      "train_runtime": 333.1494,
      "train_tokens_per_second": 56862.606
    },
    {
      "epoch": 1.904570970328789,
      "grad_norm": 9.99189281463623,
      "learning_rate": 3.0955292702485965e-05,
      "loss": 1.2204,
      "num_input_tokens_seen": 19455744,
      "step": 19000,
      "train_runtime": 341.5672,
      "train_tokens_per_second": 56960.226
    },
    {
      "epoch": 1.954691259021652,
      "grad_norm": 54.246665954589844,
      "learning_rate": 3.0454089815557342e-05,
      "loss": 1.1219,
      "num_input_tokens_seen": 19967744,
      "step": 19500,
      "train_runtime": 349.8852,
      "train_tokens_per_second": 57069.408
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5621843338012695,
      "eval_mse": 1.5621842362558391,
      "eval_runtime": 11.3832,
      "eval_samples_per_second": 1752.758,
      "eval_steps_per_second": 219.095,
      "num_input_tokens_seen": 20430336,
      "step": 19952
    },
    {
      "epoch": 2.0048115477145148,
      "grad_norm": 17.869287490844727,
      "learning_rate": 2.995288692862871e-05,
      "loss": 1.1673,
      "num_input_tokens_seen": 20479488,
      "step": 20000,
      "train_runtime": 369.9881,
      "train_tokens_per_second": 55351.745
    },
    {
      "epoch": 2.054931836407378,
      "grad_norm": 14.97153377532959,
      "learning_rate": 2.9451684041700083e-05,
      "loss": 0.8127,
      "num_input_tokens_seen": 20991488,
      "step": 20500,
      "train_runtime": 378.574,
      "train_tokens_per_second": 55448.831
    },
    {
      "epoch": 2.1050521251002405,
      "grad_norm": 7.364150047302246,
      "learning_rate": 2.8950481154771454e-05,
      "loss": 0.873,
      "num_input_tokens_seen": 21503488,
      "step": 21000,
      "train_runtime": 387.1985,
      "train_tokens_per_second": 55536.084
    },
    {
      "epoch": 2.1551724137931036,
      "grad_norm": 11.669695854187012,
      "learning_rate": 2.844927826784282e-05,
      "loss": 0.7804,
      "num_input_tokens_seen": 22015488,
      "step": 21500,
      "train_runtime": 396.4685,
      "train_tokens_per_second": 55528.97
    },
    {
      "epoch": 2.2052927024859663,
      "grad_norm": 41.843666076660156,
      "learning_rate": 2.7948075380914195e-05,
      "loss": 0.837,
      "num_input_tokens_seen": 22527488,
      "step": 22000,
      "train_runtime": 405.5069,
      "train_tokens_per_second": 55553.891
    },
    {
      "epoch": 2.2554129911788294,
      "grad_norm": 10.829984664916992,
      "learning_rate": 2.7446872493985566e-05,
      "loss": 0.8482,
      "num_input_tokens_seen": 23039488,
      "step": 22500,
      "train_runtime": 414.5185,
      "train_tokens_per_second": 55581.321
    },
    {
      "epoch": 2.305533279871692,
      "grad_norm": 15.39234447479248,
      "learning_rate": 2.694566960705694e-05,
      "loss": 0.8762,
      "num_input_tokens_seen": 23551488,
      "step": 23000,
      "train_runtime": 423.7203,
      "train_tokens_per_second": 55582.623
    },
    {
      "epoch": 2.3556535685645548,
      "grad_norm": 18.18549919128418,
      "learning_rate": 2.6444466720128307e-05,
      "loss": 0.8161,
      "num_input_tokens_seen": 24063488,
      "step": 23500,
      "train_runtime": 432.5972,
      "train_tokens_per_second": 55625.626
    },
    {
      "epoch": 2.405773857257418,
      "grad_norm": 16.482131958007812,
      "learning_rate": 2.594326383319968e-05,
      "loss": 0.8603,
      "num_input_tokens_seen": 24575488,
      "step": 24000,
      "train_runtime": 441.489,
      "train_tokens_per_second": 55665.011
    },
    {
      "epoch": 2.4558941459502805,
      "grad_norm": 17.881376266479492,
      "learning_rate": 2.5442060946271052e-05,
      "loss": 0.8447,
      "num_input_tokens_seen": 25087488,
      "step": 24500,
      "train_runtime": 449.8679,
      "train_tokens_per_second": 55766.34
    },
    {
      "epoch": 2.5060144346431437,
      "grad_norm": 24.200584411621094,
      "learning_rate": 2.4940858059342422e-05,
      "loss": 0.8122,
      "num_input_tokens_seen": 25599488,
      "step": 25000,
      "train_runtime": 458.2036,
      "train_tokens_per_second": 55869.238
    },
    {
      "epoch": 2.5561347233360063,
      "grad_norm": 27.106565475463867,
      "learning_rate": 2.4439655172413793e-05,
      "loss": 0.87,
      "num_input_tokens_seen": 26111488,
      "step": 25500,
      "train_runtime": 466.5059,
      "train_tokens_per_second": 55972.475
    },
    {
      "epoch": 2.6062550120288694,
      "grad_norm": 14.02163028717041,
      "learning_rate": 2.3938452285485167e-05,
      "loss": 0.796,
      "num_input_tokens_seen": 26623488,
      "step": 26000,
      "train_runtime": 474.8448,
      "train_tokens_per_second": 56067.769
    },
    {
      "epoch": 2.656375300721732,
      "grad_norm": 41.64189910888672,
      "learning_rate": 2.3437249398556538e-05,
      "loss": 0.8395,
      "num_input_tokens_seen": 27135488,
      "step": 26500,
      "train_runtime": 483.1561,
      "train_tokens_per_second": 56162.989
    },
    {
      "epoch": 2.706495589414595,
      "grad_norm": 38.884735107421875,
      "learning_rate": 2.2936046511627908e-05,
      "loss": 0.8408,
      "num_input_tokens_seen": 27647488,
      "step": 27000,
      "train_runtime": 491.5528,
      "train_tokens_per_second": 56245.208
    },
    {
      "epoch": 2.756615878107458,
      "grad_norm": 13.188600540161133,
      "learning_rate": 2.243484362469928e-05,
      "loss": 0.831,
      "num_input_tokens_seen": 28159488,
      "step": 27500,
      "train_runtime": 499.9048,
      "train_tokens_per_second": 56329.703
    },
    {
      "epoch": 2.806736166800321,
      "grad_norm": 11.523019790649414,
      "learning_rate": 2.193364073777065e-05,
      "loss": 0.7867,
      "num_input_tokens_seen": 28671488,
      "step": 28000,
      "train_runtime": 508.2633,
      "train_tokens_per_second": 56410.704
    },
    {
      "epoch": 2.8568564554931837,
      "grad_norm": 13.656238555908203,
      "learning_rate": 2.143243785084202e-05,
      "loss": 0.8674,
      "num_input_tokens_seen": 29183488,
      "step": 28500,
      "train_runtime": 516.5998,
      "train_tokens_per_second": 56491.48
    },
    {
      "epoch": 2.9069767441860463,
      "grad_norm": 18.173336029052734,
      "learning_rate": 2.0931234963913394e-05,
      "loss": 0.7779,
      "num_input_tokens_seen": 29695488,
      "step": 29000,
      "train_runtime": 524.9627,
      "train_tokens_per_second": 56566.852
    },
    {
      "epoch": 2.9570970328789095,
      "grad_norm": 19.77488899230957,
      "learning_rate": 2.0430032076984765e-05,
      "loss": 0.84,
      "num_input_tokens_seen": 30207488,
      "step": 29500,
      "train_runtime": 533.3932,
      "train_tokens_per_second": 56632.684
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3960472345352173,
      "eval_mse": 1.3960471269684813,
      "eval_runtime": 11.3905,
      "eval_samples_per_second": 1751.635,
      "eval_steps_per_second": 218.954,
      "num_input_tokens_seen": 30645504,
      "step": 29928
    },
    {
      "epoch": 3.007217321571772,
      "grad_norm": 19.170400619506836,
      "learning_rate": 1.9928829190056135e-05,
      "loss": 0.7767,
      "num_input_tokens_seen": 30719232,
      "step": 30000,
      "train_runtime": 553.5789,
      "train_tokens_per_second": 55492.053
    },
    {
      "epoch": 3.0573376102646352,
      "grad_norm": 9.260679244995117,
      "learning_rate": 1.942762630312751e-05,
      "loss": 0.5755,
      "num_input_tokens_seen": 31231232,
      "step": 30500,
      "train_runtime": 562.1622,
      "train_tokens_per_second": 55555.554
    },
    {
      "epoch": 3.107457898957498,
      "grad_norm": 28.19110679626465,
      "learning_rate": 1.892642341619888e-05,
      "loss": 0.6213,
      "num_input_tokens_seen": 31743232,
      "step": 31000,
      "train_runtime": 570.8337,
      "train_tokens_per_second": 55608.548
    },
    {
      "epoch": 3.157578187650361,
      "grad_norm": 15.245288848876953,
      "learning_rate": 1.8425220529270247e-05,
      "loss": 0.5973,
      "num_input_tokens_seen": 32255232,
      "step": 31500,
      "train_runtime": 579.8015,
      "train_tokens_per_second": 55631.507
    },
    {
      "epoch": 3.2076984763432237,
      "grad_norm": 34.220157623291016,
      "learning_rate": 1.792401764234162e-05,
      "loss": 0.5561,
      "num_input_tokens_seen": 32767232,
      "step": 32000,
      "train_runtime": 588.9251,
      "train_tokens_per_second": 55639.047
    },
    {
      "epoch": 3.2578187650360864,
      "grad_norm": 10.271838188171387,
      "learning_rate": 1.7422814755412992e-05,
      "loss": 0.5686,
      "num_input_tokens_seen": 33279232,
      "step": 32500,
      "train_runtime": 598.0389,
      "train_tokens_per_second": 55647.268
    },
    {
      "epoch": 3.3079390537289495,
      "grad_norm": 35.49042892456055,
      "learning_rate": 1.6921611868484362e-05,
      "loss": 0.5994,
      "num_input_tokens_seen": 33791232,
      "step": 33000,
      "train_runtime": 606.7509,
      "train_tokens_per_second": 55692.103
    },
    {
      "epoch": 3.3580593424218126,
      "grad_norm": 19.885265350341797,
      "learning_rate": 1.6420408981555736e-05,
      "loss": 0.5594,
      "num_input_tokens_seen": 34303232,
      "step": 33500,
      "train_runtime": 615.4305,
      "train_tokens_per_second": 55738.597
    },
    {
      "epoch": 3.4081796311146753,
      "grad_norm": 20.058979034423828,
      "learning_rate": 1.5919206094627107e-05,
      "loss": 0.6017,
      "num_input_tokens_seen": 34815232,
      "step": 34000,
      "train_runtime": 624.1453,
      "train_tokens_per_second": 55780.657
    },
    {
      "epoch": 3.458299919807538,
      "grad_norm": 38.68717956542969,
      "learning_rate": 1.5418003207698478e-05,
      "loss": 0.5855,
      "num_input_tokens_seen": 35327232,
      "step": 34500,
      "train_runtime": 632.7468,
      "train_tokens_per_second": 55831.542
    },
    {
      "epoch": 3.508420208500401,
      "grad_norm": 25.634483337402344,
      "learning_rate": 1.4916800320769847e-05,
      "loss": 0.5994,
      "num_input_tokens_seen": 35839232,
      "step": 35000,
      "train_runtime": 641.389,
      "train_tokens_per_second": 55877.529
    },
    {
      "epoch": 3.5585404971932637,
      "grad_norm": 16.136917114257812,
      "learning_rate": 1.4415597433841219e-05,
      "loss": 0.6142,
      "num_input_tokens_seen": 36351232,
      "step": 35500,
      "train_runtime": 649.9489,
      "train_tokens_per_second": 55929.365
    },
    {
      "epoch": 3.608660785886127,
      "grad_norm": 15.063362121582031,
      "learning_rate": 1.391439454691259e-05,
      "loss": 0.5757,
      "num_input_tokens_seen": 36863232,
      "step": 36000,
      "train_runtime": 658.5582,
      "train_tokens_per_second": 55975.667
    },
    {
      "epoch": 3.6587810745789895,
      "grad_norm": 15.330507278442383,
      "learning_rate": 1.3413191659983962e-05,
      "loss": 0.5837,
      "num_input_tokens_seen": 37375232,
      "step": 36500,
      "train_runtime": 667.1211,
      "train_tokens_per_second": 56024.66
    },
    {
      "epoch": 3.7089013632718526,
      "grad_norm": 19.06484603881836,
      "learning_rate": 1.2911988773055334e-05,
      "loss": 0.5387,
      "num_input_tokens_seen": 37887232,
      "step": 37000,
      "train_runtime": 675.6704,
      "train_tokens_per_second": 56073.538
    },
    {
      "epoch": 3.7590216519647153,
      "grad_norm": 23.454689025878906,
      "learning_rate": 1.2410785886126705e-05,
      "loss": 0.6278,
      "num_input_tokens_seen": 38399232,
      "step": 37500,
      "train_runtime": 684.2734,
      "train_tokens_per_second": 56116.798
    },
    {
      "epoch": 3.809141940657578,
      "grad_norm": 14.470320701599121,
      "learning_rate": 1.1909582999198075e-05,
      "loss": 0.5842,
      "num_input_tokens_seen": 38911232,
      "step": 38000,
      "train_runtime": 692.8986,
      "train_tokens_per_second": 56157.179
    },
    {
      "epoch": 3.859262229350441,
      "grad_norm": 11.054339408874512,
      "learning_rate": 1.1408380112269448e-05,
      "loss": 0.6072,
      "num_input_tokens_seen": 39423232,
      "step": 38500,
      "train_runtime": 701.5119,
      "train_tokens_per_second": 56197.522
    },
    {
      "epoch": 3.909382518043304,
      "grad_norm": 20.956043243408203,
      "learning_rate": 1.0907177225340818e-05,
      "loss": 0.5881,
      "num_input_tokens_seen": 39935232,
      "step": 39000,
      "train_runtime": 710.1801,
      "train_tokens_per_second": 56232.542
    },
    {
      "epoch": 3.959502806736167,
      "grad_norm": 21.301959991455078,
      "learning_rate": 1.040597433841219e-05,
      "loss": 0.5717,
      "num_input_tokens_seen": 40447232,
      "step": 39500,
      "train_runtime": 718.707,
      "train_tokens_per_second": 56277.777
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.5318739414215088,
      "eval_mse": 1.5318739121434626,
      "eval_runtime": 11.7094,
      "eval_samples_per_second": 1703.924,
      "eval_steps_per_second": 212.991,
      "num_input_tokens_seen": 40860672,
      "step": 39904
    },
    {
      "epoch": 4.0096230954290295,
      "grad_norm": 20.399166107177734,
      "learning_rate": 9.904771451483561e-06,
      "loss": 0.5301,
      "num_input_tokens_seen": 40958976,
      "step": 40000,
      "train_runtime": 739.6956,
      "train_tokens_per_second": 55372.745
    },
    {
      "epoch": 4.059743384121893,
      "grad_norm": 16.93513298034668,
      "learning_rate": 9.403568564554932e-06,
      "loss": 0.4388,
      "num_input_tokens_seen": 41470976,
      "step": 40500,
      "train_runtime": 748.1484,
      "train_tokens_per_second": 55431.487
    },
    {
      "epoch": 4.109863672814756,
      "grad_norm": 13.65589427947998,
      "learning_rate": 8.902365677626304e-06,
      "loss": 0.4392,
      "num_input_tokens_seen": 41982976,
      "step": 41000,
      "train_runtime": 756.7134,
      "train_tokens_per_second": 55480.685
    },
    {
      "epoch": 4.159983961507618,
      "grad_norm": 22.29100227355957,
      "learning_rate": 8.401162790697675e-06,
      "loss": 0.4336,
      "num_input_tokens_seen": 42494976,
      "step": 41500,
      "train_runtime": 765.1706,
      "train_tokens_per_second": 55536.602
    },
    {
      "epoch": 4.210104250200481,
      "grad_norm": 13.940652847290039,
      "learning_rate": 7.899959903769045e-06,
      "loss": 0.4294,
      "num_input_tokens_seen": 43006976,
      "step": 42000,
      "train_runtime": 773.729,
      "train_tokens_per_second": 55584.03
    },
    {
      "epoch": 4.260224538893344,
      "grad_norm": 23.97103500366211,
      "learning_rate": 7.398757016840417e-06,
      "loss": 0.4427,
      "num_input_tokens_seen": 43518976,
      "step": 42500,
      "train_runtime": 782.2722,
      "train_tokens_per_second": 55631.498
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 20.24034881591797,
      "learning_rate": 6.897554129911788e-06,
      "loss": 0.4178,
      "num_input_tokens_seen": 44030976,
      "step": 43000,
      "train_runtime": 790.7664,
      "train_tokens_per_second": 55681.394
    },
    {
      "epoch": 4.3604651162790695,
      "grad_norm": 33.19560623168945,
      "learning_rate": 6.396351242983161e-06,
      "loss": 0.4078,
      "num_input_tokens_seen": 44542976,
      "step": 43500,
      "train_runtime": 799.2809,
      "train_tokens_per_second": 55728.814
    },
    {
      "epoch": 4.410585404971933,
      "grad_norm": 10.608743667602539,
      "learning_rate": 5.895148356054531e-06,
      "loss": 0.4252,
      "num_input_tokens_seen": 45054976,
      "step": 44000,
      "train_runtime": 807.7614,
      "train_tokens_per_second": 55777.577
    },
    {
      "epoch": 4.460705693664796,
      "grad_norm": 18.352252960205078,
      "learning_rate": 5.393945469125902e-06,
      "loss": 0.3896,
      "num_input_tokens_seen": 45566976,
      "step": 44500,
      "train_runtime": 816.2905,
      "train_tokens_per_second": 55822.006
    },
    {
      "epoch": 4.510825982357659,
      "grad_norm": 15.188591957092285,
      "learning_rate": 4.892742582197274e-06,
      "loss": 0.4307,
      "num_input_tokens_seen": 46078976,
      "step": 45000,
      "train_runtime": 824.8467,
      "train_tokens_per_second": 55863.682
    },
    {
      "epoch": 4.560946271050521,
      "grad_norm": 19.425922393798828,
      "learning_rate": 4.391539695268645e-06,
      "loss": 0.4327,
      "num_input_tokens_seen": 46590976,
      "step": 45500,
      "train_runtime": 833.3927,
      "train_tokens_per_second": 55905.188
    },
    {
      "epoch": 4.611066559743384,
      "grad_norm": 22.44156265258789,
      "learning_rate": 3.890336808340016e-06,
      "loss": 0.4402,
      "num_input_tokens_seen": 47102976,
      "step": 46000,
      "train_runtime": 841.9356,
      "train_tokens_per_second": 55946.056
    },
    {
      "epoch": 4.661186848436247,
      "grad_norm": 24.460559844970703,
      "learning_rate": 3.3891339214113874e-06,
      "loss": 0.4257,
      "num_input_tokens_seen": 47614976,
      "step": 46500,
      "train_runtime": 850.4773,
      "train_tokens_per_second": 55986.182
    },
    {
      "epoch": 4.7113071371291095,
      "grad_norm": 15.877163887023926,
      "learning_rate": 2.8879310344827584e-06,
      "loss": 0.4257,
      "num_input_tokens_seen": 48126976,
      "step": 47000,
      "train_runtime": 859.0243,
      "train_tokens_per_second": 56025.165
    },
    {
      "epoch": 4.761427425821973,
      "grad_norm": 20.518606185913086,
      "learning_rate": 2.38672814755413e-06,
      "loss": 0.4038,
      "num_input_tokens_seen": 48638976,
      "step": 47500,
      "train_runtime": 867.5625,
      "train_tokens_per_second": 56063.943
    },
    {
      "epoch": 4.811547714514836,
      "grad_norm": 11.533647537231445,
      "learning_rate": 1.8855252606255011e-06,
      "loss": 0.4511,
      "num_input_tokens_seen": 49150976,
      "step": 48000,
      "train_runtime": 876.1744,
      "train_tokens_per_second": 56097.252
    },
    {
      "epoch": 4.861668003207699,
      "grad_norm": 12.317822456359863,
      "learning_rate": 1.3843223736968726e-06,
      "loss": 0.4037,
      "num_input_tokens_seen": 49662976,
      "step": 48500,
      "train_runtime": 884.7025,
      "train_tokens_per_second": 56135.228
    },
    {
      "epoch": 4.911788291900561,
      "grad_norm": 24.55292320251465,
      "learning_rate": 8.831194867682439e-07,
      "loss": 0.4227,
      "num_input_tokens_seen": 50174976,
      "step": 49000,
      "train_runtime": 893.1657,
      "train_tokens_per_second": 56176.561
    },
    {
      "epoch": 4.961908580593424,
      "grad_norm": 13.319286346435547,
      "learning_rate": 3.819165998396151e-07,
      "loss": 0.4359,
      "num_input_tokens_seen": 50686976,
      "step": 49500,
      "train_runtime": 901.6559,
      "train_tokens_per_second": 56215.43
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.4861232042312622,
      "eval_mse": 1.4861232131166864,
      "eval_runtime": 12.3183,
      "eval_samples_per_second": 1619.699,
      "eval_steps_per_second": 202.462,
      "num_input_tokens_seen": 51075840,
      "step": 49880
    },
    {
      "epoch": 5.0,
      "num_input_tokens_seen": 51075840,
      "step": 49880,
      "total_flos": 6571180888957440.0,
      "train_loss": 0.9716617676001505,
      "train_runtime": 920.9529,
      "train_samples_per_second": 433.279,
      "train_steps_per_second": 54.161
    }
  ],
  "logging_steps": 500,
  "max_steps": 49880,
  "num_input_tokens_seen": 51075840,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6571180888957440.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}