{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.001564945226917,
  "eval_steps": 500,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006259780907668232,
      "grad_norm": 1.98288817639941,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.6599,
      "step": 1
    },
    {
      "epoch": 0.012519561815336464,
      "grad_norm": 2.008513351833145,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.6744,
      "step": 2
    },
    {
      "epoch": 0.018779342723004695,
      "grad_norm": 2.03144664277006,
      "learning_rate": 1.5e-06,
      "loss": 0.6721,
      "step": 3
    },
    {
      "epoch": 0.025039123630672927,
      "grad_norm": 1.9480725202469245,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6577,
      "step": 4
    },
    {
      "epoch": 0.03129890453834116,
      "grad_norm": 1.8678118004054254,
      "learning_rate": 2.5e-06,
      "loss": 0.6484,
      "step": 5
    },
    {
      "epoch": 0.03755868544600939,
      "grad_norm": 1.6583787538868422,
      "learning_rate": 3e-06,
      "loss": 0.6174,
      "step": 6
    },
    {
      "epoch": 0.04381846635367762,
      "grad_norm": 1.5614405714896737,
      "learning_rate": 3.5000000000000004e-06,
      "loss": 0.5896,
      "step": 7
    },
    {
      "epoch": 0.050078247261345854,
      "grad_norm": 0.5773143053283745,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5557,
      "step": 8
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 0.3043811484340276,
      "learning_rate": 4.5e-06,
      "loss": 0.541,
      "step": 9
    },
    {
      "epoch": 0.06259780907668232,
      "grad_norm": 0.8131531353366078,
      "learning_rate": 5e-06,
      "loss": 0.5595,
      "step": 10
    },
    {
      "epoch": 0.06885758998435054,
      "grad_norm": 0.424180567084822,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.5427,
      "step": 11
    },
    {
      "epoch": 0.07511737089201878,
      "grad_norm": 0.2913041969769501,
      "learning_rate": 6e-06,
      "loss": 0.5274,
      "step": 12
    },
    {
      "epoch": 0.081377151799687,
      "grad_norm": 0.34524917385772347,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.5337,
      "step": 13
    },
    {
      "epoch": 0.08763693270735524,
      "grad_norm": 0.36469195568794854,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.5279,
      "step": 14
    },
    {
      "epoch": 0.09389671361502347,
      "grad_norm": 0.35209082489157323,
      "learning_rate": 7.5e-06,
      "loss": 0.5296,
      "step": 15
    },
    {
      "epoch": 0.10015649452269171,
      "grad_norm": 0.28086156745404856,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5319,
      "step": 16
    },
    {
      "epoch": 0.10641627543035993,
      "grad_norm": 0.5457849868763605,
      "learning_rate": 8.500000000000002e-06,
      "loss": 0.5199,
      "step": 17
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 0.264594169690208,
      "learning_rate": 9e-06,
      "loss": 0.5234,
      "step": 18
    },
    {
      "epoch": 0.1189358372456964,
      "grad_norm": 0.2472097021778676,
      "learning_rate": 9.5e-06,
      "loss": 0.5248,
      "step": 19
    },
    {
      "epoch": 0.12519561815336464,
      "grad_norm": 0.2560549908847749,
      "learning_rate": 1e-05,
      "loss": 0.5159,
      "step": 20
    },
    {
      "epoch": 0.13145539906103287,
      "grad_norm": 0.4101523009554862,
      "learning_rate": 1.05e-05,
      "loss": 0.5058,
      "step": 21
    },
    {
      "epoch": 0.13771517996870108,
      "grad_norm": 0.22290433425318873,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.5099,
      "step": 22
    },
    {
      "epoch": 0.14397496087636932,
      "grad_norm": 0.2600145857043661,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 0.5076,
      "step": 23
    },
    {
      "epoch": 0.15023474178403756,
      "grad_norm": 1.1584269063197106,
      "learning_rate": 1.2e-05,
      "loss": 0.5133,
      "step": 24
    },
    {
      "epoch": 0.1564945226917058,
      "grad_norm": 0.21303015786105067,
      "learning_rate": 1.25e-05,
      "loss": 0.5009,
      "step": 25
    },
    {
      "epoch": 0.162754303599374,
      "grad_norm": 2.5709430754104345,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.5067,
      "step": 26
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.42260631876680255,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 0.4951,
      "step": 27
    },
    {
      "epoch": 0.1752738654147105,
      "grad_norm": 0.2122989372030049,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.4968,
      "step": 28
    },
    {
      "epoch": 0.18153364632237873,
      "grad_norm": 0.36382001881720555,
      "learning_rate": 1.45e-05,
      "loss": 0.5035,
      "step": 29
    },
    {
      "epoch": 0.18779342723004694,
      "grad_norm": 0.22094603076455596,
      "learning_rate": 1.5e-05,
      "loss": 0.5049,
      "step": 30
    },
    {
      "epoch": 0.19405320813771518,
      "grad_norm": 0.17188920546056902,
      "learning_rate": 1.55e-05,
      "loss": 0.4979,
      "step": 31
    },
    {
      "epoch": 0.20031298904538342,
      "grad_norm": 0.18515458685485783,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.4916,
      "step": 32
    },
    {
      "epoch": 0.20657276995305165,
      "grad_norm": 0.783356101762532,
      "learning_rate": 1.65e-05,
      "loss": 0.4929,
      "step": 33
    },
    {
      "epoch": 0.21283255086071987,
      "grad_norm": 0.19059224326067628,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.4945,
      "step": 34
    },
    {
      "epoch": 0.2190923317683881,
      "grad_norm": 0.2275442577977743,
      "learning_rate": 1.75e-05,
      "loss": 0.4936,
      "step": 35
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 0.24798149507141237,
      "learning_rate": 1.8e-05,
      "loss": 0.4898,
      "step": 36
    },
    {
      "epoch": 0.23161189358372458,
      "grad_norm": 0.20682357544778035,
      "learning_rate": 1.85e-05,
      "loss": 0.4888,
      "step": 37
    },
    {
      "epoch": 0.2378716744913928,
      "grad_norm": 0.19518819682961547,
      "learning_rate": 1.9e-05,
      "loss": 0.4899,
      "step": 38
    },
    {
      "epoch": 0.24413145539906103,
      "grad_norm": 0.18423871547579748,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.4868,
      "step": 39
    },
    {
      "epoch": 0.25039123630672927,
      "grad_norm": 0.1714820355275791,
      "learning_rate": 2e-05,
      "loss": 0.4795,
      "step": 40
    },
    {
      "epoch": 0.2566510172143975,
      "grad_norm": 0.19187618384155788,
      "learning_rate": 2.05e-05,
      "loss": 0.4821,
      "step": 41
    },
    {
      "epoch": 0.26291079812206575,
      "grad_norm": 0.1422378326228944,
      "learning_rate": 2.1e-05,
      "loss": 0.4829,
      "step": 42
    },
    {
      "epoch": 0.26917057902973396,
      "grad_norm": 0.14724977757162294,
      "learning_rate": 2.15e-05,
      "loss": 0.4811,
      "step": 43
    },
    {
      "epoch": 0.27543035993740217,
      "grad_norm": 0.16077227738580077,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.477,
      "step": 44
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 0.15993679259901028,
      "learning_rate": 2.25e-05,
      "loss": 0.4789,
      "step": 45
    },
    {
      "epoch": 0.28794992175273865,
      "grad_norm": 0.14385134377084383,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.4641,
      "step": 46
    },
    {
      "epoch": 0.2942097026604069,
      "grad_norm": 0.14244559356804792,
      "learning_rate": 2.35e-05,
      "loss": 0.4767,
      "step": 47
    },
    {
      "epoch": 0.3004694835680751,
      "grad_norm": 0.1481660114240819,
      "learning_rate": 2.4e-05,
      "loss": 0.4759,
      "step": 48
    },
    {
      "epoch": 0.30672926447574334,
      "grad_norm": 0.14195363156015162,
      "learning_rate": 2.45e-05,
      "loss": 0.471,
      "step": 49
    },
    {
      "epoch": 0.3129890453834116,
      "grad_norm": 0.15220552720898642,
      "learning_rate": 2.5e-05,
      "loss": 0.4715,
      "step": 50
    },
    {
      "epoch": 0.3192488262910798,
      "grad_norm": 0.13409784658365015,
      "learning_rate": 2.5500000000000003e-05,
      "loss": 0.4692,
      "step": 51
    },
    {
      "epoch": 0.325508607198748,
      "grad_norm": 0.13766694658848178,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.47,
      "step": 52
    },
    {
      "epoch": 0.3317683881064163,
      "grad_norm": 0.13097864679643595,
      "learning_rate": 2.6500000000000004e-05,
      "loss": 0.4651,
      "step": 53
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 0.13207003285729219,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.4714,
      "step": 54
    },
    {
      "epoch": 0.3442879499217527,
      "grad_norm": 0.14128427173382038,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.4719,
      "step": 55
    },
    {
      "epoch": 0.350547730829421,
      "grad_norm": 0.13599048333974484,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.4657,
      "step": 56
    },
    {
      "epoch": 0.3568075117370892,
      "grad_norm": 0.1547358977814178,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 0.4599,
      "step": 57
    },
    {
      "epoch": 0.36306729264475746,
      "grad_norm": 0.1357320992255676,
      "learning_rate": 2.9e-05,
      "loss": 0.4615,
      "step": 58
    },
    {
      "epoch": 0.36932707355242567,
      "grad_norm": 0.14465717873045295,
      "learning_rate": 2.95e-05,
      "loss": 0.4738,
      "step": 59
    },
    {
      "epoch": 0.3755868544600939,
      "grad_norm": 0.5900603203611421,
      "learning_rate": 3e-05,
      "loss": 0.4702,
      "step": 60
    },
    {
      "epoch": 0.38184663536776214,
      "grad_norm": 0.17729474902277623,
      "learning_rate": 3.05e-05,
      "loss": 0.4592,
      "step": 61
    },
    {
      "epoch": 0.38810641627543035,
      "grad_norm": 0.22055664690525556,
      "learning_rate": 3.1e-05,
      "loss": 0.47,
      "step": 62
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 0.22917133262033845,
      "learning_rate": 3.15e-05,
      "loss": 0.4668,
      "step": 63
    },
    {
      "epoch": 0.40062597809076683,
      "grad_norm": 0.23278911760289017,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.4691,
      "step": 64
    },
    {
      "epoch": 0.40688575899843504,
      "grad_norm": 0.23911939507472177,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 0.4662,
      "step": 65
    },
    {
      "epoch": 0.4131455399061033,
      "grad_norm": 0.19447041878105836,
      "learning_rate": 3.3e-05,
      "loss": 0.4633,
      "step": 66
    },
    {
      "epoch": 0.4194053208137715,
      "grad_norm": 0.17498726962496755,
      "learning_rate": 3.35e-05,
      "loss": 0.4654,
      "step": 67
    },
    {
      "epoch": 0.42566510172143973,
      "grad_norm": 0.24918375228266929,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.477,
      "step": 68
    },
    {
      "epoch": 0.431924882629108,
      "grad_norm": 0.2850664865678729,
      "learning_rate": 3.45e-05,
      "loss": 0.4648,
      "step": 69
    },
    {
      "epoch": 0.4381846635367762,
      "grad_norm": 0.27562629972396513,
      "learning_rate": 3.5e-05,
      "loss": 0.4667,
      "step": 70
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.22637202856522412,
      "learning_rate": 3.55e-05,
      "loss": 0.4653,
      "step": 71
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 0.2295442026728235,
      "learning_rate": 3.6e-05,
      "loss": 0.4622,
      "step": 72
    },
    {
      "epoch": 0.4569640062597809,
      "grad_norm": 0.26572612655057165,
      "learning_rate": 3.65e-05,
      "loss": 0.4673,
      "step": 73
    },
    {
      "epoch": 0.46322378716744916,
      "grad_norm": 0.2496817546620412,
      "learning_rate": 3.7e-05,
      "loss": 0.4611,
      "step": 74
    },
    {
      "epoch": 0.4694835680751174,
      "grad_norm": 0.21430723659191686,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.4637,
      "step": 75
    },
    {
      "epoch": 0.4757433489827856,
      "grad_norm": 0.1799606207168491,
      "learning_rate": 3.8e-05,
      "loss": 0.4612,
      "step": 76
    },
    {
      "epoch": 0.48200312989045385,
      "grad_norm": 0.2329269891744439,
      "learning_rate": 3.85e-05,
      "loss": 0.4569,
      "step": 77
    },
    {
      "epoch": 0.48826291079812206,
      "grad_norm": 0.2859704851548014,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.4677,
      "step": 78
    },
    {
      "epoch": 0.4945226917057903,
      "grad_norm": 0.3153100598444141,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.465,
      "step": 79
    },
    {
      "epoch": 0.5007824726134585,
      "grad_norm": 0.3165950932566608,
      "learning_rate": 4e-05,
      "loss": 0.4755,
      "step": 80
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 0.3018577292754275,
      "learning_rate": 4.05e-05,
      "loss": 0.464,
      "step": 81
    },
    {
      "epoch": 0.513302034428795,
      "grad_norm": 0.39363558044861696,
      "learning_rate": 4.1e-05,
      "loss": 0.4701,
      "step": 82
    },
    {
      "epoch": 0.5195618153364632,
      "grad_norm": 0.44171413078007776,
      "learning_rate": 4.15e-05,
      "loss": 0.4697,
      "step": 83
    },
    {
      "epoch": 0.5258215962441315,
      "grad_norm": 0.4086449510625894,
      "learning_rate": 4.2e-05,
      "loss": 0.4611,
      "step": 84
    },
    {
      "epoch": 0.5320813771517997,
      "grad_norm": 0.3156689305434587,
      "learning_rate": 4.25e-05,
      "loss": 0.4633,
      "step": 85
    },
    {
      "epoch": 0.5383411580594679,
      "grad_norm": 0.37582415992669976,
      "learning_rate": 4.3e-05,
      "loss": 0.4689,
      "step": 86
    },
    {
      "epoch": 0.5446009389671361,
      "grad_norm": 0.3751728997948819,
      "learning_rate": 4.35e-05,
      "loss": 0.4658,
      "step": 87
    },
    {
      "epoch": 0.5508607198748043,
      "grad_norm": 0.2622604607003995,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.4641,
      "step": 88
    },
    {
      "epoch": 0.5571205007824727,
      "grad_norm": 0.27806769516567914,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.4689,
      "step": 89
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 0.37193892514568727,
      "learning_rate": 4.5e-05,
      "loss": 0.4645,
      "step": 90
    },
    {
      "epoch": 0.5696400625978091,
      "grad_norm": 0.319234610988282,
      "learning_rate": 4.55e-05,
      "loss": 0.4697,
      "step": 91
    },
    {
      "epoch": 0.5758998435054773,
      "grad_norm": 0.24391835650924631,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.4605,
      "step": 92
    },
    {
      "epoch": 0.5821596244131455,
      "grad_norm": 0.3860119064167233,
      "learning_rate": 4.6500000000000005e-05,
      "loss": 0.4721,
      "step": 93
    },
    {
      "epoch": 0.5884194053208138,
      "grad_norm": 0.43978262147491526,
      "learning_rate": 4.7e-05,
      "loss": 0.4692,
      "step": 94
    },
    {
      "epoch": 0.594679186228482,
      "grad_norm": 0.2869109051387356,
      "learning_rate": 4.75e-05,
      "loss": 0.4644,
      "step": 95
    },
    {
      "epoch": 0.6009389671361502,
      "grad_norm": 0.33046074741721215,
      "learning_rate": 4.8e-05,
      "loss": 0.4711,
      "step": 96
    },
    {
      "epoch": 0.6071987480438185,
      "grad_norm": 0.3874189152162858,
      "learning_rate": 4.85e-05,
      "loss": 0.4694,
      "step": 97
    },
    {
      "epoch": 0.6134585289514867,
      "grad_norm": 0.46318630797414556,
      "learning_rate": 4.9e-05,
      "loss": 0.4741,
      "step": 98
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 0.6037444606802089,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.4754,
      "step": 99
    },
    {
      "epoch": 0.6259780907668232,
      "grad_norm": 0.5037059436389102,
      "learning_rate": 5e-05,
      "loss": 0.4739,
      "step": 100
    },
    {
      "epoch": 0.6322378716744914,
      "grad_norm": 0.5631190436137139,
      "learning_rate": 4.9997404092249336e-05,
      "loss": 0.4699,
      "step": 101
    },
    {
      "epoch": 0.6384976525821596,
      "grad_norm": 0.39119483297638863,
      "learning_rate": 4.998961690809628e-05,
      "loss": 0.4703,
      "step": 102
    },
    {
      "epoch": 0.6447574334898278,
      "grad_norm": 0.40196303529424704,
      "learning_rate": 4.997664006472579e-05,
      "loss": 0.4749,
      "step": 103
    },
    {
      "epoch": 0.651017214397496,
      "grad_norm": 0.3397733110278162,
      "learning_rate": 4.9958476257072914e-05,
      "loss": 0.4654,
      "step": 104
    },
    {
      "epoch": 0.6572769953051644,
      "grad_norm": 0.2670846226151608,
      "learning_rate": 4.993512925726319e-05,
      "loss": 0.4716,
      "step": 105
    },
    {
      "epoch": 0.6635367762128326,
      "grad_norm": 0.36681659702689784,
      "learning_rate": 4.990660391382923e-05,
      "loss": 0.4704,
      "step": 106
    },
    {
      "epoch": 0.6697965571205008,
      "grad_norm": 0.26058292855009557,
      "learning_rate": 4.987290615070385e-05,
      "loss": 0.4647,
      "step": 107
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 0.25205128219384887,
      "learning_rate": 4.983404296598979e-05,
      "loss": 0.4725,
      "step": 108
    },
    {
      "epoch": 0.6823161189358372,
      "grad_norm": 0.3208687051782515,
      "learning_rate": 4.9790022430506463e-05,
      "loss": 0.471,
      "step": 109
    },
    {
      "epoch": 0.6885758998435054,
      "grad_norm": 0.2306209439140453,
      "learning_rate": 4.974085368611381e-05,
      "loss": 0.473,
      "step": 110
    },
    {
      "epoch": 0.6948356807511737,
      "grad_norm": 0.21458192536569118,
      "learning_rate": 4.968654694381379e-05,
      "loss": 0.4692,
      "step": 111
    },
    {
      "epoch": 0.701095461658842,
      "grad_norm": 0.24400329234341836,
      "learning_rate": 4.962711348162987e-05,
      "loss": 0.4742,
      "step": 112
    },
    {
      "epoch": 0.7073552425665102,
      "grad_norm": 0.5445701250609367,
      "learning_rate": 4.956256564226487e-05,
      "loss": 0.4677,
      "step": 113
    },
    {
      "epoch": 0.7136150234741784,
      "grad_norm": 0.2485591152431222,
      "learning_rate": 4.949291683053769e-05,
      "loss": 0.478,
      "step": 114
    },
    {
      "epoch": 0.7198748043818466,
      "grad_norm": 0.2683190648451619,
      "learning_rate": 4.941818151059956e-05,
      "loss": 0.468,
      "step": 115
    },
    {
      "epoch": 0.7261345852895149,
      "grad_norm": 0.17377296116604452,
      "learning_rate": 4.933837520293017e-05,
      "loss": 0.4682,
      "step": 116
    },
    {
      "epoch": 0.7323943661971831,
      "grad_norm": 0.19892874090328266,
      "learning_rate": 4.9253514481114535e-05,
      "loss": 0.4716,
      "step": 117
    },
    {
      "epoch": 0.7386541471048513,
      "grad_norm": 0.22470516800088272,
      "learning_rate": 4.91636169684011e-05,
      "loss": 0.4807,
      "step": 118
    },
    {
      "epoch": 0.7449139280125195,
      "grad_norm": 0.23033947133081567,
      "learning_rate": 4.906870133404187e-05,
      "loss": 0.4721,
      "step": 119
    },
    {
      "epoch": 0.7511737089201878,
      "grad_norm": 0.2764527709442302,
      "learning_rate": 4.896878728941531e-05,
      "loss": 0.4693,
      "step": 120
    },
    {
      "epoch": 0.7574334898278561,
      "grad_norm": 0.28746556965081915,
      "learning_rate": 4.8863895583932836e-05,
      "loss": 0.4767,
      "step": 121
    },
    {
      "epoch": 0.7636932707355243,
      "grad_norm": 0.32061574884194566,
      "learning_rate": 4.875404800072977e-05,
      "loss": 0.4643,
      "step": 122
    },
    {
      "epoch": 0.7699530516431925,
      "grad_norm": 0.34181281337669966,
      "learning_rate": 4.86392673521415e-05,
      "loss": 0.4602,
      "step": 123
    },
    {
      "epoch": 0.7762128325508607,
      "grad_norm": 0.30941984507586506,
      "learning_rate": 4.8519577474966074e-05,
      "loss": 0.4711,
      "step": 124
    },
    {
      "epoch": 0.7824726134585289,
      "grad_norm": 0.23600978038755785,
      "learning_rate": 4.839500322551386e-05,
      "loss": 0.4696,
      "step": 125
    },
    {
      "epoch": 0.7887323943661971,
      "grad_norm": 0.2577164285099203,
      "learning_rate": 4.8265570474445636e-05,
      "loss": 0.4644,
      "step": 126
    },
    {
      "epoch": 0.7949921752738655,
      "grad_norm": 0.27823451721774306,
      "learning_rate": 4.813130610139994e-05,
      "loss": 0.479,
      "step": 127
    },
    {
      "epoch": 0.8012519561815337,
      "grad_norm": 0.22061524932206344,
      "learning_rate": 4.7992237989410904e-05,
      "loss": 0.4711,
      "step": 128
    },
    {
      "epoch": 0.8075117370892019,
      "grad_norm": 0.20216340578684158,
      "learning_rate": 4.784839501911771e-05,
      "loss": 0.468,
      "step": 129
    },
    {
      "epoch": 0.8137715179968701,
      "grad_norm": 0.27542745611047786,
      "learning_rate": 4.7699807062766876e-05,
      "loss": 0.4754,
      "step": 130
    },
    {
      "epoch": 0.8200312989045383,
      "grad_norm": 0.21954180738847087,
      "learning_rate": 4.75465049780086e-05,
      "loss": 0.4595,
      "step": 131
    },
    {
      "epoch": 0.8262910798122066,
      "grad_norm": 0.19430624161738624,
      "learning_rate": 4.738852060148849e-05,
      "loss": 0.4747,
      "step": 132
    },
    {
      "epoch": 0.8325508607198748,
      "grad_norm": 0.1884671644058954,
      "learning_rate": 4.722588674223594e-05,
      "loss": 0.4748,
      "step": 133
    },
    {
      "epoch": 0.838810641627543,
      "grad_norm": 0.20913369047927102,
      "learning_rate": 4.7058637174850604e-05,
      "loss": 0.4653,
      "step": 134
    },
    {
      "epoch": 0.8450704225352113,
      "grad_norm": 0.19564021089464265,
      "learning_rate": 4.688680663248837e-05,
      "loss": 0.4644,
      "step": 135
    },
    {
      "epoch": 0.8513302034428795,
      "grad_norm": 0.17437877798570775,
      "learning_rate": 4.671043079964815e-05,
      "loss": 0.4666,
      "step": 136
    },
    {
      "epoch": 0.8575899843505478,
      "grad_norm": 0.18658537333186465,
      "learning_rate": 4.652954630476127e-05,
      "loss": 0.463,
      "step": 137
    },
    {
      "epoch": 0.863849765258216,
      "grad_norm": 0.1916983418252378,
      "learning_rate": 4.634419071258472e-05,
      "loss": 0.4801,
      "step": 138
    },
    {
      "epoch": 0.8701095461658842,
      "grad_norm": 0.18269150591223743,
      "learning_rate": 4.615440251639995e-05,
      "loss": 0.465,
      "step": 139
    },
    {
      "epoch": 0.8763693270735524,
      "grad_norm": 0.19124021712384207,
      "learning_rate": 4.5960221130018946e-05,
      "loss": 0.4624,
      "step": 140
    },
    {
      "epoch": 0.8826291079812206,
      "grad_norm": 0.17751289300487907,
      "learning_rate": 4.576168687959895e-05,
      "loss": 0.4667,
      "step": 141
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.16256598664527863,
      "learning_rate": 4.555884099526794e-05,
      "loss": 0.4724,
      "step": 142
    },
    {
      "epoch": 0.8951486697965572,
      "grad_norm": 0.17306660659668968,
      "learning_rate": 4.535172560256218e-05,
      "loss": 0.4764,
      "step": 143
    },
    {
      "epoch": 0.9014084507042254,
      "grad_norm": 0.15311694878287935,
      "learning_rate": 4.5140383713677916e-05,
      "loss": 0.4633,
      "step": 144
    },
    {
      "epoch": 0.9076682316118936,
      "grad_norm": 0.16327033693685952,
      "learning_rate": 4.492485921853894e-05,
      "loss": 0.4626,
      "step": 145
    },
    {
      "epoch": 0.9139280125195618,
      "grad_norm": 0.1577015015575217,
      "learning_rate": 4.4705196875681854e-05,
      "loss": 0.465,
      "step": 146
    },
    {
      "epoch": 0.92018779342723,
      "grad_norm": 0.14976303947345634,
      "learning_rate": 4.448144230296093e-05,
      "loss": 0.4732,
      "step": 147
    },
    {
      "epoch": 0.9264475743348983,
      "grad_norm": 0.1799041852337434,
      "learning_rate": 4.425364196807451e-05,
      "loss": 0.4638,
      "step": 148
    },
    {
      "epoch": 0.9327073552425665,
      "grad_norm": 0.25582934784311545,
      "learning_rate": 4.402184317891501e-05,
      "loss": 0.4687,
      "step": 149
    },
    {
      "epoch": 0.9389671361502347,
      "grad_norm": 0.14767269207211267,
      "learning_rate": 4.37860940737443e-05,
      "loss": 0.4622,
      "step": 150
    },
    {
      "epoch": 0.945226917057903,
      "grad_norm": 0.18510146862998086,
      "learning_rate": 4.354644361119672e-05,
      "loss": 0.4714,
      "step": 151
    },
    {
      "epoch": 0.9514866979655712,
      "grad_norm": 0.1834113544053396,
      "learning_rate": 4.330294156011172e-05,
      "loss": 0.4665,
      "step": 152
    },
    {
      "epoch": 0.9577464788732394,
      "grad_norm": 0.16106024098596552,
      "learning_rate": 4.305563848919824e-05,
      "loss": 0.4612,
      "step": 153
    },
    {
      "epoch": 0.9640062597809077,
      "grad_norm": 0.1582714001537092,
      "learning_rate": 4.2804585756532965e-05,
      "loss": 0.4656,
      "step": 154
    },
    {
      "epoch": 0.9702660406885759,
      "grad_norm": 0.1838011411088347,
      "learning_rate": 4.254983549889467e-05,
      "loss": 0.4585,
      "step": 155
    },
    {
      "epoch": 0.9765258215962441,
      "grad_norm": 0.22256207898681857,
      "learning_rate": 4.2291440620936796e-05,
      "loss": 0.4712,
      "step": 156
    },
    {
      "epoch": 0.9827856025039123,
      "grad_norm": 0.16842112143070276,
      "learning_rate": 4.2029454784200676e-05,
      "loss": 0.4691,
      "step": 157
    },
    {
      "epoch": 0.9890453834115805,
      "grad_norm": 0.15122887832488566,
      "learning_rate": 4.176393239597144e-05,
      "loss": 0.4778,
      "step": 158
    },
    {
      "epoch": 0.9953051643192489,
      "grad_norm": 0.1902639072378955,
      "learning_rate": 4.149492859797912e-05,
      "loss": 0.4688,
      "step": 159
    },
    {
      "epoch": 1.001564945226917,
      "grad_norm": 0.17200971150006397,
      "learning_rate": 4.122249925494726e-05,
      "loss": 0.464,
      "step": 160
    }
  ],
  "logging_steps": 1,
  "max_steps": 318,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 16,
  "total_flos": 1.0356139229184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}