{
  "best_metric": 1.7139549255371094,
  "best_model_checkpoint": "outputs/checkpoint-500",
  "epoch": 0.7483629560336763,
  "eval_steps": 25,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014967259120673526,
      "grad_norm": 2.434373378753662,
      "learning_rate": 4e-05,
      "loss": 2.0037,
      "step": 1
    },
    {
      "epoch": 0.002993451824134705,
      "grad_norm": 2.795464038848877,
      "learning_rate": 8e-05,
      "loss": 1.9814,
      "step": 2
    },
    {
      "epoch": 0.004490177736202058,
      "grad_norm": 2.0998575687408447,
      "learning_rate": 0.00012,
      "loss": 2.0044,
      "step": 3
    },
    {
      "epoch": 0.00598690364826941,
      "grad_norm": 4.470895290374756,
      "learning_rate": 0.00016,
      "loss": 1.8696,
      "step": 4
    },
    {
      "epoch": 0.007483629560336763,
      "grad_norm": 1.6047176122665405,
      "learning_rate": 0.0002,
      "loss": 1.8021,
      "step": 5
    },
    {
      "epoch": 0.008980355472404116,
      "grad_norm": 1.9450230598449707,
      "learning_rate": 0.0001996638655462185,
      "loss": 1.8558,
      "step": 6
    },
    {
      "epoch": 0.01047708138447147,
      "grad_norm": 1.4420437812805176,
      "learning_rate": 0.00019932773109243698,
      "loss": 1.9079,
      "step": 7
    },
    {
      "epoch": 0.01197380729653882,
      "grad_norm": 2.428009033203125,
      "learning_rate": 0.00019899159663865548,
      "loss": 1.7173,
      "step": 8
    },
    {
      "epoch": 0.013470533208606174,
      "grad_norm": 1.6478683948516846,
      "learning_rate": 0.00019865546218487395,
      "loss": 1.7631,
      "step": 9
    },
    {
      "epoch": 0.014967259120673527,
      "grad_norm": 1.6283013820648193,
      "learning_rate": 0.00019831932773109245,
      "loss": 1.9375,
      "step": 10
    },
    {
      "epoch": 0.01646398503274088,
      "grad_norm": 1.7736356258392334,
      "learning_rate": 0.00019798319327731095,
      "loss": 1.7921,
      "step": 11
    },
    {
      "epoch": 0.017960710944808233,
      "grad_norm": 1.3353335857391357,
      "learning_rate": 0.00019764705882352942,
      "loss": 1.8699,
      "step": 12
    },
    {
      "epoch": 0.019457436856875586,
      "grad_norm": 1.5582761764526367,
      "learning_rate": 0.00019731092436974792,
      "loss": 1.8015,
      "step": 13
    },
    {
      "epoch": 0.02095416276894294,
      "grad_norm": 1.3032814264297485,
      "learning_rate": 0.00019697478991596642,
      "loss": 1.8513,
      "step": 14
    },
    {
      "epoch": 0.02245088868101029,
      "grad_norm": 1.3724833726882935,
      "learning_rate": 0.00019663865546218486,
      "loss": 1.8694,
      "step": 15
    },
    {
      "epoch": 0.02394761459307764,
      "grad_norm": 1.715156078338623,
      "learning_rate": 0.00019630252100840336,
      "loss": 1.7997,
      "step": 16
    },
    {
      "epoch": 0.025444340505144995,
      "grad_norm": 1.9989070892333984,
      "learning_rate": 0.00019596638655462186,
      "loss": 1.7037,
      "step": 17
    },
    {
      "epoch": 0.026941066417212348,
      "grad_norm": 1.6255011558532715,
      "learning_rate": 0.00019563025210084033,
      "loss": 1.8382,
      "step": 18
    },
    {
      "epoch": 0.0284377923292797,
      "grad_norm": 1.305870532989502,
      "learning_rate": 0.00019529411764705883,
      "loss": 1.8095,
      "step": 19
    },
    {
      "epoch": 0.029934518241347054,
      "grad_norm": 3.40390944480896,
      "learning_rate": 0.0001949579831932773,
      "loss": 1.6112,
      "step": 20
    },
    {
      "epoch": 0.0314312441534144,
      "grad_norm": 1.1514052152633667,
      "learning_rate": 0.0001946218487394958,
      "loss": 1.9725,
      "step": 21
    },
    {
      "epoch": 0.03292797006548176,
      "grad_norm": 1.9419797658920288,
      "learning_rate": 0.0001942857142857143,
      "loss": 1.8492,
      "step": 22
    },
    {
      "epoch": 0.03442469597754911,
      "grad_norm": 1.830913782119751,
      "learning_rate": 0.00019394957983193278,
      "loss": 1.7852,
      "step": 23
    },
    {
      "epoch": 0.035921421889616466,
      "grad_norm": 1.345436453819275,
      "learning_rate": 0.00019361344537815127,
      "loss": 1.8929,
      "step": 24
    },
    {
      "epoch": 0.037418147801683815,
      "grad_norm": 1.1833657026290894,
      "learning_rate": 0.00019327731092436975,
      "loss": 1.8822,
      "step": 25
    },
    {
      "epoch": 0.037418147801683815,
      "eval_loss": 1.7638475894927979,
      "eval_runtime": 13.3387,
      "eval_samples_per_second": 4.798,
      "eval_steps_per_second": 2.399,
      "step": 25
    },
    {
      "epoch": 0.03891487371375117,
      "grad_norm": 1.4092592000961304,
      "learning_rate": 0.00019294117647058825,
      "loss": 1.954,
      "step": 26
    },
    {
      "epoch": 0.04041159962581852,
      "grad_norm": 1.201281189918518,
      "learning_rate": 0.00019260504201680674,
      "loss": 1.9364,
      "step": 27
    },
    {
      "epoch": 0.04190832553788588,
      "grad_norm": 1.407148838043213,
      "learning_rate": 0.00019226890756302522,
      "loss": 1.7673,
      "step": 28
    },
    {
      "epoch": 0.04340505144995323,
      "grad_norm": 1.3781392574310303,
      "learning_rate": 0.00019193277310924372,
      "loss": 1.81,
      "step": 29
    },
    {
      "epoch": 0.04490177736202058,
      "grad_norm": 1.4952391386032104,
      "learning_rate": 0.00019159663865546221,
      "loss": 1.8216,
      "step": 30
    },
    {
      "epoch": 0.046398503274087934,
      "grad_norm": 1.5127140283584595,
      "learning_rate": 0.0001912605042016807,
      "loss": 1.8316,
      "step": 31
    },
    {
      "epoch": 0.04789522918615528,
      "grad_norm": 1.3208520412445068,
      "learning_rate": 0.00019092436974789919,
      "loss": 1.7302,
      "step": 32
    },
    {
      "epoch": 0.04939195509822264,
      "grad_norm": 1.3473477363586426,
      "learning_rate": 0.00019058823529411766,
      "loss": 1.9661,
      "step": 33
    },
    {
      "epoch": 0.05088868101028999,
      "grad_norm": 1.201379418373108,
      "learning_rate": 0.00019025210084033613,
      "loss": 1.8531,
      "step": 34
    },
    {
      "epoch": 0.052385406922357346,
      "grad_norm": 1.32240891456604,
      "learning_rate": 0.00018991596638655463,
      "loss": 1.7485,
      "step": 35
    },
    {
      "epoch": 0.053882132834424695,
      "grad_norm": 1.3222694396972656,
      "learning_rate": 0.0001895798319327731,
      "loss": 1.7939,
      "step": 36
    },
    {
      "epoch": 0.05537885874649205,
      "grad_norm": 1.1342493295669556,
      "learning_rate": 0.0001892436974789916,
      "loss": 1.855,
      "step": 37
    },
    {
      "epoch": 0.0568755846585594,
      "grad_norm": 1.4912521839141846,
      "learning_rate": 0.0001889075630252101,
      "loss": 1.8394,
      "step": 38
    },
    {
      "epoch": 0.05837231057062675,
      "grad_norm": 1.4635943174362183,
      "learning_rate": 0.00018857142857142857,
      "loss": 1.7669,
      "step": 39
    },
    {
      "epoch": 0.05986903648269411,
      "grad_norm": 1.4757208824157715,
      "learning_rate": 0.00018823529411764707,
      "loss": 1.7842,
      "step": 40
    },
    {
      "epoch": 0.06136576239476146,
      "grad_norm": 1.5162277221679688,
      "learning_rate": 0.00018789915966386554,
      "loss": 1.8873,
      "step": 41
    },
    {
      "epoch": 0.0628624883068288,
      "grad_norm": 1.3085792064666748,
      "learning_rate": 0.00018756302521008404,
      "loss": 1.9716,
      "step": 42
    },
    {
      "epoch": 0.06435921421889616,
      "grad_norm": 1.1214959621429443,
      "learning_rate": 0.00018722689075630254,
      "loss": 1.8991,
      "step": 43
    },
    {
      "epoch": 0.06585594013096352,
      "grad_norm": 1.1944588422775269,
      "learning_rate": 0.000186890756302521,
      "loss": 1.8894,
      "step": 44
    },
    {
      "epoch": 0.06735266604303088,
      "grad_norm": 1.509717345237732,
      "learning_rate": 0.0001865546218487395,
      "loss": 1.8035,
      "step": 45
    },
    {
      "epoch": 0.06884939195509822,
      "grad_norm": 1.3220465183258057,
      "learning_rate": 0.000186218487394958,
      "loss": 1.8673,
      "step": 46
    },
    {
      "epoch": 0.07034611786716558,
      "grad_norm": 1.3592686653137207,
      "learning_rate": 0.00018588235294117648,
      "loss": 1.8396,
      "step": 47
    },
    {
      "epoch": 0.07184284377923293,
      "grad_norm": 1.3568888902664185,
      "learning_rate": 0.00018554621848739498,
      "loss": 1.6562,
      "step": 48
    },
    {
      "epoch": 0.07333956969130027,
      "grad_norm": 1.1371209621429443,
      "learning_rate": 0.00018521008403361345,
      "loss": 1.9563,
      "step": 49
    },
    {
      "epoch": 0.07483629560336763,
      "grad_norm": 1.234221339225769,
      "learning_rate": 0.00018487394957983195,
      "loss": 1.7702,
      "step": 50
    },
    {
      "epoch": 0.07483629560336763,
      "eval_loss": 1.7585577964782715,
      "eval_runtime": 9.906,
      "eval_samples_per_second": 6.461,
      "eval_steps_per_second": 3.23,
      "step": 50
    },
    {
      "epoch": 0.07633302151543499,
      "grad_norm": 1.4679025411605835,
      "learning_rate": 0.00018453781512605045,
      "loss": 1.7903,
      "step": 51
    },
    {
      "epoch": 0.07782974742750234,
      "grad_norm": 1.6469783782958984,
      "learning_rate": 0.0001842016806722689,
      "loss": 1.9121,
      "step": 52
    },
    {
      "epoch": 0.07932647333956969,
      "grad_norm": 1.0950040817260742,
      "learning_rate": 0.0001838655462184874,
      "loss": 1.8015,
      "step": 53
    },
    {
      "epoch": 0.08082319925163704,
      "grad_norm": 1.4614354372024536,
      "learning_rate": 0.0001835294117647059,
      "loss": 1.8627,
      "step": 54
    },
    {
      "epoch": 0.0823199251637044,
      "grad_norm": 1.0772849321365356,
      "learning_rate": 0.00018319327731092437,
      "loss": 1.8474,
      "step": 55
    },
    {
      "epoch": 0.08381665107577176,
      "grad_norm": 0.8980317115783691,
      "learning_rate": 0.00018285714285714286,
      "loss": 1.9381,
      "step": 56
    },
    {
      "epoch": 0.0853133769878391,
      "grad_norm": 1.028698205947876,
      "learning_rate": 0.00018252100840336134,
      "loss": 1.8726,
      "step": 57
    },
    {
      "epoch": 0.08681010289990646,
      "grad_norm": 1.2643156051635742,
      "learning_rate": 0.00018218487394957984,
      "loss": 1.937,
      "step": 58
    },
    {
      "epoch": 0.08830682881197381,
      "grad_norm": 1.0845692157745361,
      "learning_rate": 0.00018184873949579833,
      "loss": 1.9708,
      "step": 59
    },
    {
      "epoch": 0.08980355472404115,
      "grad_norm": 1.2025495767593384,
      "learning_rate": 0.0001815126050420168,
      "loss": 1.8674,
      "step": 60
    },
    {
      "epoch": 0.09130028063610851,
      "grad_norm": 1.2060717344284058,
      "learning_rate": 0.0001811764705882353,
      "loss": 1.8268,
      "step": 61
    },
    {
      "epoch": 0.09279700654817587,
      "grad_norm": 1.3296293020248413,
      "learning_rate": 0.0001808403361344538,
      "loss": 1.6956,
      "step": 62
    },
    {
      "epoch": 0.09429373246024322,
      "grad_norm": 1.2353034019470215,
      "learning_rate": 0.00018050420168067228,
      "loss": 1.9816,
      "step": 63
    },
    {
      "epoch": 0.09579045837231057,
      "grad_norm": 1.5975768566131592,
      "learning_rate": 0.00018016806722689078,
      "loss": 1.7846,
      "step": 64
    },
    {
      "epoch": 0.09728718428437792,
      "grad_norm": 1.2220622301101685,
      "learning_rate": 0.00017983193277310925,
      "loss": 1.7895,
      "step": 65
    },
    {
      "epoch": 0.09878391019644528,
      "grad_norm": 1.2025718688964844,
      "learning_rate": 0.00017949579831932775,
      "loss": 1.9242,
      "step": 66
    },
    {
      "epoch": 0.10028063610851262,
      "grad_norm": 3.2830123901367188,
      "learning_rate": 0.00017915966386554625,
      "loss": 1.7076,
      "step": 67
    },
    {
      "epoch": 0.10177736202057998,
      "grad_norm": 1.5499017238616943,
      "learning_rate": 0.00017882352941176472,
      "loss": 1.7964,
      "step": 68
    },
    {
      "epoch": 0.10327408793264733,
      "grad_norm": 1.4630420207977295,
      "learning_rate": 0.00017848739495798322,
      "loss": 1.8724,
      "step": 69
    },
    {
      "epoch": 0.10477081384471469,
      "grad_norm": 1.4005722999572754,
      "learning_rate": 0.0001781512605042017,
      "loss": 1.6889,
      "step": 70
    },
    {
      "epoch": 0.10626753975678203,
      "grad_norm": 1.114207148551941,
      "learning_rate": 0.00017781512605042016,
      "loss": 1.8272,
      "step": 71
    },
    {
      "epoch": 0.10776426566884939,
      "grad_norm": 1.4557619094848633,
      "learning_rate": 0.00017747899159663866,
      "loss": 1.6877,
      "step": 72
    },
    {
      "epoch": 0.10926099158091675,
      "grad_norm": 1.4767951965332031,
      "learning_rate": 0.00017714285714285713,
      "loss": 1.8667,
      "step": 73
    },
    {
      "epoch": 0.1107577174929841,
      "grad_norm": 1.3078974485397339,
      "learning_rate": 0.00017680672268907563,
      "loss": 1.9319,
      "step": 74
    },
    {
      "epoch": 0.11225444340505145,
      "grad_norm": 1.1861608028411865,
      "learning_rate": 0.00017647058823529413,
      "loss": 1.9233,
      "step": 75
    },
    {
      "epoch": 0.11225444340505145,
      "eval_loss": 1.7611756324768066,
      "eval_runtime": 9.9015,
      "eval_samples_per_second": 6.464,
      "eval_steps_per_second": 3.232,
      "step": 75
    },
    {
      "epoch": 0.1137511693171188,
      "grad_norm": 1.1504981517791748,
      "learning_rate": 0.0001761344537815126,
      "loss": 1.8044,
      "step": 76
    },
    {
      "epoch": 0.11524789522918616,
      "grad_norm": 1.3776837587356567,
      "learning_rate": 0.0001757983193277311,
      "loss": 1.725,
      "step": 77
    },
    {
      "epoch": 0.1167446211412535,
      "grad_norm": 1.3975869417190552,
      "learning_rate": 0.0001754621848739496,
      "loss": 1.7935,
      "step": 78
    },
    {
      "epoch": 0.11824134705332086,
      "grad_norm": 1.3506461381912231,
      "learning_rate": 0.00017512605042016807,
      "loss": 1.7342,
      "step": 79
    },
    {
      "epoch": 0.11973807296538821,
      "grad_norm": 1.1317209005355835,
      "learning_rate": 0.00017478991596638657,
      "loss": 1.8149,
      "step": 80
    },
    {
      "epoch": 0.12123479887745557,
      "grad_norm": 1.2540264129638672,
      "learning_rate": 0.00017445378151260504,
      "loss": 1.84,
      "step": 81
    },
    {
      "epoch": 0.12273152478952291,
      "grad_norm": 1.23360276222229,
      "learning_rate": 0.00017411764705882354,
      "loss": 1.7623,
      "step": 82
    },
    {
      "epoch": 0.12422825070159027,
      "grad_norm": 1.0347758531570435,
      "learning_rate": 0.00017378151260504204,
      "loss": 1.7381,
      "step": 83
    },
    {
      "epoch": 0.1257249766136576,
      "grad_norm": 1.4501961469650269,
      "learning_rate": 0.0001734453781512605,
      "loss": 1.7075,
      "step": 84
    },
    {
      "epoch": 0.12722170252572498,
      "grad_norm": 1.0509997606277466,
      "learning_rate": 0.000173109243697479,
      "loss": 1.7295,
      "step": 85
    },
    {
      "epoch": 0.12871842843779233,
      "grad_norm": 1.2986621856689453,
      "learning_rate": 0.00017277310924369748,
      "loss": 1.7988,
      "step": 86
    },
    {
      "epoch": 0.13021515434985967,
      "grad_norm": 1.1701687574386597,
      "learning_rate": 0.00017243697478991598,
      "loss": 1.6763,
      "step": 87
    },
    {
      "epoch": 0.13171188026192704,
      "grad_norm": 1.2512173652648926,
      "learning_rate": 0.00017210084033613448,
      "loss": 1.6641,
      "step": 88
    },
    {
      "epoch": 0.13320860617399438,
      "grad_norm": 1.658525824546814,
      "learning_rate": 0.00017176470588235293,
      "loss": 1.6849,
      "step": 89
    },
    {
      "epoch": 0.13470533208606175,
      "grad_norm": 1.5465582609176636,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.6439,
      "step": 90
    },
    {
      "epoch": 0.1362020579981291,
      "grad_norm": 1.3289684057235718,
      "learning_rate": 0.00017109243697478992,
      "loss": 1.7429,
      "step": 91
    },
    {
      "epoch": 0.13769878391019644,
      "grad_norm": 1.3123184442520142,
      "learning_rate": 0.0001707563025210084,
      "loss": 1.6429,
      "step": 92
    },
    {
      "epoch": 0.1391955098222638,
      "grad_norm": 1.385330319404602,
      "learning_rate": 0.0001704201680672269,
      "loss": 1.8257,
      "step": 93
    },
    {
      "epoch": 0.14069223573433115,
      "grad_norm": 1.3719394207000732,
      "learning_rate": 0.0001700840336134454,
      "loss": 1.7493,
      "step": 94
    },
    {
      "epoch": 0.1421889616463985,
      "grad_norm": 1.468948245048523,
      "learning_rate": 0.00016974789915966387,
      "loss": 1.8626,
      "step": 95
    },
    {
      "epoch": 0.14368568755846586,
      "grad_norm": 1.2705055475234985,
      "learning_rate": 0.00016941176470588237,
      "loss": 1.79,
      "step": 96
    },
    {
      "epoch": 0.1451824134705332,
      "grad_norm": 1.0876643657684326,
      "learning_rate": 0.00016907563025210084,
      "loss": 1.9631,
      "step": 97
    },
    {
      "epoch": 0.14667913938260055,
      "grad_norm": 1.1760327816009521,
      "learning_rate": 0.00016873949579831934,
      "loss": 1.91,
      "step": 98
    },
    {
      "epoch": 0.14817586529466792,
      "grad_norm": 1.0915436744689941,
      "learning_rate": 0.00016840336134453784,
      "loss": 1.8369,
      "step": 99
    },
    {
      "epoch": 0.14967259120673526,
      "grad_norm": 1.4619494676589966,
      "learning_rate": 0.0001680672268907563,
      "loss": 1.7074,
      "step": 100
    },
    {
      "epoch": 0.14967259120673526,
      "eval_loss": 1.7622296810150146,
      "eval_runtime": 9.9165,
      "eval_samples_per_second": 6.454,
      "eval_steps_per_second": 3.227,
      "step": 100
    },
    {
      "epoch": 0.15116931711880263,
      "grad_norm": 1.147395372390747,
      "learning_rate": 0.0001677310924369748,
      "loss": 1.7815,
      "step": 101
    },
    {
      "epoch": 0.15266604303086997,
      "grad_norm": 1.1551228761672974,
      "learning_rate": 0.00016739495798319328,
      "loss": 1.9444,
      "step": 102
    },
    {
      "epoch": 0.15416276894293732,
      "grad_norm": 1.2220309972763062,
      "learning_rate": 0.00016705882352941178,
      "loss": 1.8735,
      "step": 103
    },
    {
      "epoch": 0.1556594948550047,
      "grad_norm": 1.315051555633545,
      "learning_rate": 0.00016672268907563028,
      "loss": 1.7284,
      "step": 104
    },
    {
      "epoch": 0.15715622076707203,
      "grad_norm": 1.2493054866790771,
      "learning_rate": 0.00016638655462184875,
      "loss": 1.7598,
      "step": 105
    },
    {
      "epoch": 0.15865294667913937,
      "grad_norm": 1.0625994205474854,
      "learning_rate": 0.00016605042016806725,
      "loss": 1.8334,
      "step": 106
    },
    {
      "epoch": 0.16014967259120674,
      "grad_norm": 1.284947395324707,
      "learning_rate": 0.00016571428571428575,
      "loss": 1.7762,
      "step": 107
    },
    {
      "epoch": 0.16164639850327409,
      "grad_norm": 1.27797269821167,
      "learning_rate": 0.0001653781512605042,
      "loss": 1.7898,
      "step": 108
    },
    {
      "epoch": 0.16314312441534143,
      "grad_norm": 1.4802685976028442,
      "learning_rate": 0.0001650420168067227,
      "loss": 1.7004,
      "step": 109
    },
    {
      "epoch": 0.1646398503274088,
      "grad_norm": 0.973327100276947,
      "learning_rate": 0.0001647058823529412,
      "loss": 1.9218,
      "step": 110
    },
    {
      "epoch": 0.16613657623947614,
      "grad_norm": 1.3942281007766724,
      "learning_rate": 0.00016436974789915966,
      "loss": 1.9183,
      "step": 111
    },
    {
      "epoch": 0.1676333021515435,
      "grad_norm": 1.2495373487472534,
      "learning_rate": 0.00016403361344537816,
      "loss": 1.8296,
      "step": 112
    },
    {
      "epoch": 0.16913002806361085,
      "grad_norm": 1.2634400129318237,
      "learning_rate": 0.00016369747899159663,
      "loss": 1.9474,
      "step": 113
    },
    {
      "epoch": 0.1706267539756782,
      "grad_norm": 1.2135545015335083,
      "learning_rate": 0.00016336134453781513,
      "loss": 1.787,
      "step": 114
    },
    {
      "epoch": 0.17212347988774557,
      "grad_norm": 1.0599427223205566,
      "learning_rate": 0.00016302521008403363,
      "loss": 1.9359,
      "step": 115
    },
    {
      "epoch": 0.1736202057998129,
      "grad_norm": 1.1955755949020386,
      "learning_rate": 0.0001626890756302521,
      "loss": 1.7344,
      "step": 116
    },
    {
      "epoch": 0.17511693171188025,
      "grad_norm": 1.3276002407073975,
      "learning_rate": 0.0001623529411764706,
      "loss": 1.8934,
      "step": 117
    },
    {
      "epoch": 0.17661365762394762,
      "grad_norm": 1.4872647523880005,
      "learning_rate": 0.00016201680672268907,
      "loss": 1.8229,
      "step": 118
    },
    {
      "epoch": 0.17811038353601497,
      "grad_norm": 1.377747893333435,
      "learning_rate": 0.00016168067226890757,
      "loss": 1.7041,
      "step": 119
    },
    {
      "epoch": 0.1796071094480823,
      "grad_norm": 1.087159276008606,
      "learning_rate": 0.00016134453781512607,
      "loss": 1.8932,
      "step": 120
    },
    {
      "epoch": 0.18110383536014968,
      "grad_norm": 1.299407720565796,
      "learning_rate": 0.00016100840336134454,
      "loss": 1.8673,
      "step": 121
    },
    {
      "epoch": 0.18260056127221702,
      "grad_norm": 1.172582983970642,
      "learning_rate": 0.00016067226890756304,
      "loss": 1.7616,
      "step": 122
    },
    {
      "epoch": 0.1840972871842844,
      "grad_norm": 1.4097166061401367,
      "learning_rate": 0.00016033613445378154,
      "loss": 1.6969,
      "step": 123
    },
    {
      "epoch": 0.18559401309635173,
      "grad_norm": 1.0662322044372559,
      "learning_rate": 0.00016,
      "loss": 1.8128,
      "step": 124
    },
    {
      "epoch": 0.18709073900841908,
      "grad_norm": 1.2918486595153809,
      "learning_rate": 0.0001596638655462185,
      "loss": 1.8538,
      "step": 125
    },
    {
      "epoch": 0.18709073900841908,
      "eval_loss": 1.762688159942627,
      "eval_runtime": 9.9256,
      "eval_samples_per_second": 6.448,
      "eval_steps_per_second": 3.224,
      "step": 125
    },
    {
      "epoch": 0.18858746492048645,
      "grad_norm": 1.4962085485458374,
      "learning_rate": 0.00015932773109243698,
      "loss": 1.732,
      "step": 126
    },
    {
      "epoch": 0.1900841908325538,
      "grad_norm": 1.1726781129837036,
      "learning_rate": 0.00015899159663865546,
      "loss": 1.8208,
      "step": 127
    },
    {
      "epoch": 0.19158091674462113,
      "grad_norm": 1.1145118474960327,
      "learning_rate": 0.00015865546218487396,
      "loss": 1.8918,
      "step": 128
    },
    {
      "epoch": 0.1930776426566885,
      "grad_norm": 1.2448960542678833,
      "learning_rate": 0.00015831932773109243,
      "loss": 1.7441,
      "step": 129
    },
    {
      "epoch": 0.19457436856875585,
      "grad_norm": 1.1530712842941284,
      "learning_rate": 0.00015798319327731093,
      "loss": 1.8817,
      "step": 130
    },
    {
      "epoch": 0.1960710944808232,
      "grad_norm": 0.9994822144508362,
      "learning_rate": 0.00015764705882352943,
      "loss": 1.8655,
      "step": 131
    },
    {
      "epoch": 0.19756782039289056,
      "grad_norm": 1.475071668624878,
      "learning_rate": 0.0001573109243697479,
      "loss": 1.5336,
      "step": 132
    },
    {
      "epoch": 0.1990645463049579,
      "grad_norm": 1.0761913061141968,
      "learning_rate": 0.0001569747899159664,
      "loss": 1.9806,
      "step": 133
    },
    {
      "epoch": 0.20056127221702524,
      "grad_norm": 1.1356831789016724,
      "learning_rate": 0.00015663865546218487,
      "loss": 1.7876,
      "step": 134
    },
    {
      "epoch": 0.20205799812909261,
      "grad_norm": 1.2572017908096313,
      "learning_rate": 0.00015630252100840337,
      "loss": 1.7748,
      "step": 135
    },
    {
      "epoch": 0.20355472404115996,
      "grad_norm": 1.2248603105545044,
      "learning_rate": 0.00015596638655462187,
      "loss": 1.8696,
      "step": 136
    },
    {
      "epoch": 0.20505144995322733,
      "grad_norm": 1.1236392259597778,
      "learning_rate": 0.00015563025210084034,
      "loss": 1.8774,
      "step": 137
    },
    {
      "epoch": 0.20654817586529467,
      "grad_norm": 1.3141965866088867,
      "learning_rate": 0.00015529411764705884,
      "loss": 1.8864,
      "step": 138
    },
    {
      "epoch": 0.208044901777362,
      "grad_norm": 1.364126443862915,
      "learning_rate": 0.00015495798319327734,
      "loss": 1.6608,
      "step": 139
    },
    {
      "epoch": 0.20954162768942938,
      "grad_norm": 1.0413249731063843,
      "learning_rate": 0.0001546218487394958,
      "loss": 1.8559,
      "step": 140
    },
    {
      "epoch": 0.21103835360149673,
      "grad_norm": 1.0397676229476929,
      "learning_rate": 0.0001542857142857143,
      "loss": 1.8886,
      "step": 141
    },
    {
      "epoch": 0.21253507951356407,
      "grad_norm": 1.072859525680542,
      "learning_rate": 0.00015394957983193278,
      "loss": 1.8294,
      "step": 142
    },
    {
      "epoch": 0.21403180542563144,
      "grad_norm": 1.3657593727111816,
      "learning_rate": 0.00015361344537815128,
      "loss": 1.6844,
      "step": 143
    },
    {
      "epoch": 0.21552853133769878,
      "grad_norm": 1.4864728450775146,
      "learning_rate": 0.00015327731092436978,
      "loss": 1.7364,
      "step": 144
    },
    {
      "epoch": 0.21702525724976612,
      "grad_norm": 1.2342066764831543,
      "learning_rate": 0.00015294117647058822,
      "loss": 1.8441,
      "step": 145
    },
    {
      "epoch": 0.2185219831618335,
      "grad_norm": 1.788312315940857,
      "learning_rate": 0.00015260504201680672,
      "loss": 1.7228,
      "step": 146
    },
    {
      "epoch": 0.22001870907390084,
      "grad_norm": 1.1817758083343506,
      "learning_rate": 0.00015226890756302522,
      "loss": 1.7602,
      "step": 147
    },
    {
      "epoch": 0.2215154349859682,
      "grad_norm": 1.0265668630599976,
      "learning_rate": 0.0001519327731092437,
      "loss": 1.8208,
      "step": 148
    },
    {
      "epoch": 0.22301216089803555,
      "grad_norm": 1.2950278520584106,
      "learning_rate": 0.0001515966386554622,
      "loss": 1.7958,
      "step": 149
    },
    {
      "epoch": 0.2245088868101029,
      "grad_norm": 1.21755850315094,
      "learning_rate": 0.00015126050420168066,
      "loss": 1.9051,
      "step": 150
    },
    {
      "epoch": 0.2245088868101029,
      "eval_loss": 1.760790467262268,
      "eval_runtime": 9.9578,
      "eval_samples_per_second": 6.427,
      "eval_steps_per_second": 3.214,
      "step": 150
    },
    {
      "epoch": 0.22600561272217026,
      "grad_norm": 1.0923712253570557,
      "learning_rate": 0.00015092436974789916,
      "loss": 1.7108,
      "step": 151
    },
    {
      "epoch": 0.2275023386342376,
      "grad_norm": 1.222659945487976,
      "learning_rate": 0.00015058823529411766,
      "loss": 1.8221,
      "step": 152
    },
    {
      "epoch": 0.22899906454630495,
      "grad_norm": 1.2633992433547974,
      "learning_rate": 0.00015025210084033613,
      "loss": 1.7576,
      "step": 153
    },
    {
      "epoch": 0.23049579045837232,
      "grad_norm": 1.3663132190704346,
      "learning_rate": 0.00014991596638655463,
      "loss": 1.7411,
      "step": 154
    },
    {
      "epoch": 0.23199251637043966,
      "grad_norm": 1.0865604877471924,
      "learning_rate": 0.00014957983193277313,
      "loss": 1.7677,
      "step": 155
    },
    {
      "epoch": 0.233489242282507,
      "grad_norm": 1.0313267707824707,
      "learning_rate": 0.0001492436974789916,
      "loss": 1.8802,
      "step": 156
    },
    {
      "epoch": 0.23498596819457437,
      "grad_norm": 1.300527811050415,
      "learning_rate": 0.0001489075630252101,
      "loss": 1.7062,
      "step": 157
    },
    {
      "epoch": 0.23648269410664172,
      "grad_norm": 1.1446460485458374,
      "learning_rate": 0.00014857142857142857,
      "loss": 1.821,
      "step": 158
    },
    {
      "epoch": 0.2379794200187091,
      "grad_norm": 1.1422364711761475,
      "learning_rate": 0.00014823529411764707,
      "loss": 1.9409,
      "step": 159
    },
    {
      "epoch": 0.23947614593077643,
      "grad_norm": 1.2949453592300415,
      "learning_rate": 0.00014789915966386557,
      "loss": 1.9585,
      "step": 160
    },
    {
      "epoch": 0.24097287184284377,
      "grad_norm": 1.0998990535736084,
      "learning_rate": 0.00014756302521008404,
      "loss": 1.823,
      "step": 161
    },
    {
      "epoch": 0.24246959775491114,
      "grad_norm": 1.3279107809066772,
      "learning_rate": 0.00014722689075630254,
      "loss": 1.7261,
      "step": 162
    },
    {
      "epoch": 0.24396632366697849,
      "grad_norm": 1.1471811532974243,
      "learning_rate": 0.00014689075630252101,
      "loss": 1.8507,
      "step": 163
    },
    {
      "epoch": 0.24546304957904583,
      "grad_norm": 1.0583767890930176,
      "learning_rate": 0.0001465546218487395,
      "loss": 1.9237,
      "step": 164
    },
    {
      "epoch": 0.2469597754911132,
      "grad_norm": 1.3685698509216309,
      "learning_rate": 0.00014621848739495799,
      "loss": 1.8113,
      "step": 165
    },
    {
      "epoch": 0.24845650140318054,
      "grad_norm": 1.5403902530670166,
      "learning_rate": 0.00014588235294117646,
      "loss": 1.797,
      "step": 166
    },
    {
      "epoch": 0.24995322731524788,
      "grad_norm": 1.0701065063476562,
      "learning_rate": 0.00014554621848739496,
      "loss": 1.8527,
      "step": 167
    },
    {
      "epoch": 0.2514499532273152,
      "grad_norm": 1.0490641593933105,
      "learning_rate": 0.00014521008403361346,
      "loss": 1.9737,
      "step": 168
    },
    {
      "epoch": 0.2529466791393826,
      "grad_norm": 1.1226781606674194,
      "learning_rate": 0.00014487394957983193,
      "loss": 1.8817,
      "step": 169
    },
    {
      "epoch": 0.25444340505144997,
      "grad_norm": 1.2346230745315552,
      "learning_rate": 0.00014453781512605043,
      "loss": 1.873,
      "step": 170
    },
    {
      "epoch": 0.2559401309635173,
      "grad_norm": 0.9842538237571716,
      "learning_rate": 0.00014420168067226893,
      "loss": 1.8042,
      "step": 171
    },
    {
      "epoch": 0.25743685687558465,
      "grad_norm": 1.217533826828003,
      "learning_rate": 0.0001438655462184874,
      "loss": 1.7716,
      "step": 172
    },
    {
      "epoch": 0.258933582787652,
      "grad_norm": 1.1946215629577637,
      "learning_rate": 0.0001435294117647059,
      "loss": 1.8272,
      "step": 173
    },
    {
      "epoch": 0.26043030869971934,
      "grad_norm": 1.1696230173110962,
      "learning_rate": 0.00014319327731092437,
      "loss": 1.801,
      "step": 174
    },
    {
      "epoch": 0.26192703461178674,
      "grad_norm": 1.2546944618225098,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.7625,
      "step": 175
    },
    {
      "epoch": 0.26192703461178674,
      "eval_loss": 1.7579066753387451,
      "eval_runtime": 9.9267,
      "eval_samples_per_second": 6.447,
      "eval_steps_per_second": 3.224,
      "step": 175
    },
    {
      "epoch": 0.2634237605238541,
      "grad_norm": 1.136839509010315,
      "learning_rate": 0.00014252100840336137,
      "loss": 1.8288,
      "step": 176
    },
    {
      "epoch": 0.2649204864359214,
      "grad_norm": 1.2978945970535278,
      "learning_rate": 0.00014218487394957984,
      "loss": 1.6907,
      "step": 177
    },
    {
      "epoch": 0.26641721234798876,
      "grad_norm": 1.340311050415039,
      "learning_rate": 0.00014184873949579834,
      "loss": 1.8468,
      "step": 178
    },
    {
      "epoch": 0.2679139382600561,
      "grad_norm": 1.236281156539917,
      "learning_rate": 0.0001415126050420168,
      "loss": 1.834,
      "step": 179
    },
    {
      "epoch": 0.2694106641721235,
      "grad_norm": 1.2765839099884033,
      "learning_rate": 0.0001411764705882353,
      "loss": 1.8231,
      "step": 180
    },
    {
      "epoch": 0.27090739008419085,
      "grad_norm": 1.9402660131454468,
      "learning_rate": 0.0001408403361344538,
      "loss": 1.8436,
      "step": 181
    },
    {
      "epoch": 0.2724041159962582,
      "grad_norm": 1.6397343873977661,
      "learning_rate": 0.00014050420168067225,
      "loss": 1.8738,
      "step": 182
    },
    {
      "epoch": 0.27390084190832553,
      "grad_norm": 1.2269023656845093,
      "learning_rate": 0.00014016806722689075,
      "loss": 1.724,
      "step": 183
    },
    {
      "epoch": 0.2753975678203929,
      "grad_norm": 1.0990972518920898,
      "learning_rate": 0.00013983193277310925,
      "loss": 1.805,
      "step": 184
    },
    {
      "epoch": 0.2768942937324602,
      "grad_norm": 1.2719955444335938,
      "learning_rate": 0.00013949579831932772,
      "loss": 1.8694,
      "step": 185
    },
    {
      "epoch": 0.2783910196445276,
      "grad_norm": 1.6118435859680176,
      "learning_rate": 0.00013915966386554622,
      "loss": 1.7453,
      "step": 186
    },
    {
      "epoch": 0.27988774555659496,
      "grad_norm": 1.2474150657653809,
      "learning_rate": 0.00013882352941176472,
      "loss": 1.7035,
      "step": 187
    },
    {
      "epoch": 0.2813844714686623,
      "grad_norm": 0.929045557975769,
      "learning_rate": 0.0001384873949579832,
      "loss": 1.4875,
      "step": 188
    },
    {
      "epoch": 0.28288119738072964,
      "grad_norm": 1.1837550401687622,
      "learning_rate": 0.0001381512605042017,
      "loss": 1.8196,
      "step": 189
    },
    {
      "epoch": 0.284377923292797,
      "grad_norm": 1.171769142150879,
      "learning_rate": 0.00013781512605042016,
      "loss": 1.8209,
      "step": 190
    },
    {
      "epoch": 0.2858746492048644,
      "grad_norm": 1.0087103843688965,
      "learning_rate": 0.00013747899159663866,
      "loss": 1.8493,
      "step": 191
    },
    {
      "epoch": 0.2873713751169317,
      "grad_norm": 1.0094703435897827,
      "learning_rate": 0.00013714285714285716,
      "loss": 1.8036,
      "step": 192
    },
    {
      "epoch": 0.28886810102899907,
      "grad_norm": 1.2591369152069092,
      "learning_rate": 0.00013680672268907563,
      "loss": 1.6686,
      "step": 193
    },
    {
      "epoch": 0.2903648269410664,
      "grad_norm": 1.1550267934799194,
      "learning_rate": 0.00013647058823529413,
      "loss": 1.7808,
      "step": 194
    },
    {
      "epoch": 0.29186155285313375,
      "grad_norm": 1.575493335723877,
      "learning_rate": 0.0001361344537815126,
      "loss": 1.6981,
      "step": 195
    },
    {
      "epoch": 0.2933582787652011,
      "grad_norm": 1.0852630138397217,
      "learning_rate": 0.0001357983193277311,
      "loss": 1.913,
      "step": 196
    },
    {
      "epoch": 0.2948550046772685,
      "grad_norm": 1.4476265907287598,
      "learning_rate": 0.0001354621848739496,
      "loss": 1.8064,
      "step": 197
    },
    {
      "epoch": 0.29635173058933584,
      "grad_norm": 1.1281249523162842,
      "learning_rate": 0.00013512605042016807,
      "loss": 1.9073,
      "step": 198
    },
    {
      "epoch": 0.2978484565014032,
      "grad_norm": 1.011376142501831,
      "learning_rate": 0.00013478991596638657,
      "loss": 1.9038,
      "step": 199
    },
    {
      "epoch": 0.2993451824134705,
      "grad_norm": 1.017004370689392,
      "learning_rate": 0.00013445378151260507,
      "loss": 1.842,
      "step": 200
    },
    {
      "epoch": 0.2993451824134705,
      "eval_loss": 1.751793384552002,
      "eval_runtime": 9.9274,
      "eval_samples_per_second": 6.447,
      "eval_steps_per_second": 3.223,
      "step": 200
    },
    {
      "epoch": 0.30084190832553787,
      "grad_norm": 1.280287504196167,
      "learning_rate": 0.00013411764705882352,
      "loss": 1.8463,
      "step": 201
    },
    {
      "epoch": 0.30233863423760526,
      "grad_norm": 1.071548581123352,
      "learning_rate": 0.00013378151260504202,
      "loss": 1.936,
      "step": 202
    },
    {
      "epoch": 0.3038353601496726,
      "grad_norm": 1.0402483940124512,
      "learning_rate": 0.00013344537815126052,
      "loss": 1.8919,
      "step": 203
    },
    {
      "epoch": 0.30533208606173995,
      "grad_norm": 1.404093623161316,
      "learning_rate": 0.000133109243697479,
      "loss": 1.7126,
      "step": 204
    },
    {
      "epoch": 0.3068288119738073,
      "grad_norm": 1.2647768259048462,
      "learning_rate": 0.0001327731092436975,
      "loss": 1.8001,
      "step": 205
    },
    {
      "epoch": 0.30832553788587463,
      "grad_norm": 1.1771318912506104,
      "learning_rate": 0.00013243697478991596,
      "loss": 1.8045,
      "step": 206
    },
    {
      "epoch": 0.309822263797942,
      "grad_norm": 1.1957385540008545,
      "learning_rate": 0.00013210084033613446,
      "loss": 1.7873,
      "step": 207
    },
    {
      "epoch": 0.3113189897100094,
      "grad_norm": 1.4250292778015137,
      "learning_rate": 0.00013176470588235296,
      "loss": 1.5988,
      "step": 208
    },
    {
      "epoch": 0.3128157156220767,
      "grad_norm": 1.1845389604568481,
      "learning_rate": 0.00013142857142857143,
      "loss": 1.7846,
      "step": 209
    },
    {
      "epoch": 0.31431244153414406,
      "grad_norm": 1.080325722694397,
      "learning_rate": 0.00013109243697478993,
      "loss": 1.9488,
      "step": 210
    },
    {
      "epoch": 0.3158091674462114,
      "grad_norm": 1.2887210845947266,
      "learning_rate": 0.0001307563025210084,
      "loss": 1.8574,
      "step": 211
    },
    {
      "epoch": 0.31730589335827875,
      "grad_norm": 1.1449840068817139,
      "learning_rate": 0.0001304201680672269,
      "loss": 1.8628,
      "step": 212
    },
    {
      "epoch": 0.31880261927034614,
      "grad_norm": 1.0899405479431152,
      "learning_rate": 0.0001300840336134454,
      "loss": 1.7998,
      "step": 213
    },
    {
      "epoch": 0.3202993451824135,
      "grad_norm": 1.1760225296020508,
      "learning_rate": 0.00012974789915966387,
      "loss": 1.7833,
      "step": 214
    },
    {
      "epoch": 0.32179607109448083,
      "grad_norm": 1.2030748128890991,
      "learning_rate": 0.00012941176470588237,
      "loss": 1.8504,
      "step": 215
    },
    {
      "epoch": 0.32329279700654817,
      "grad_norm": 1.0713863372802734,
      "learning_rate": 0.00012907563025210087,
      "loss": 1.9432,
      "step": 216
    },
    {
      "epoch": 0.3247895229186155,
      "grad_norm": 1.1058694124221802,
      "learning_rate": 0.00012873949579831934,
      "loss": 1.727,
      "step": 217
    },
    {
      "epoch": 0.32628624883068286,
      "grad_norm": 1.1129230260849,
      "learning_rate": 0.00012840336134453784,
      "loss": 1.9422,
      "step": 218
    },
    {
      "epoch": 0.32778297474275025,
      "grad_norm": 0.9841461181640625,
      "learning_rate": 0.0001280672268907563,
      "loss": 1.8916,
      "step": 219
    },
    {
      "epoch": 0.3292797006548176,
      "grad_norm": 1.3188430070877075,
      "learning_rate": 0.00012773109243697478,
      "loss": 1.7102,
      "step": 220
    },
    {
      "epoch": 0.33077642656688494,
      "grad_norm": 1.1673728227615356,
      "learning_rate": 0.00012739495798319328,
      "loss": 1.8466,
      "step": 221
    },
    {
      "epoch": 0.3322731524789523,
      "grad_norm": 1.170258641242981,
      "learning_rate": 0.00012705882352941175,
      "loss": 1.8602,
      "step": 222
    },
    {
      "epoch": 0.3337698783910196,
      "grad_norm": 1.1097817420959473,
      "learning_rate": 0.00012672268907563025,
      "loss": 1.912,
      "step": 223
    },
    {
      "epoch": 0.335266604303087,
      "grad_norm": 1.0673434734344482,
      "learning_rate": 0.00012638655462184875,
      "loss": 1.808,
      "step": 224
    },
    {
      "epoch": 0.33676333021515437,
      "grad_norm": 1.311902642250061,
      "learning_rate": 0.00012605042016806722,
      "loss": 1.8527,
      "step": 225
    },
    {
      "epoch": 0.33676333021515437,
      "eval_loss": 1.7518868446350098,
      "eval_runtime": 9.8911,
      "eval_samples_per_second": 6.47,
      "eval_steps_per_second": 3.235,
      "step": 225
    },
    {
      "epoch": 0.3382600561272217,
      "grad_norm": 1.0087488889694214,
      "learning_rate": 0.00012571428571428572,
      "loss": 1.9122,
      "step": 226
    },
    {
      "epoch": 0.33975678203928905,
      "grad_norm": 1.2666288614273071,
      "learning_rate": 0.0001253781512605042,
      "loss": 1.7594,
      "step": 227
    },
    {
      "epoch": 0.3412535079513564,
      "grad_norm": 1.1287747621536255,
      "learning_rate": 0.0001250420168067227,
      "loss": 1.8053,
      "step": 228
    },
    {
      "epoch": 0.34275023386342374,
      "grad_norm": 1.206766128540039,
      "learning_rate": 0.0001247058823529412,
      "loss": 1.9256,
      "step": 229
    },
    {
      "epoch": 0.34424695977549113,
      "grad_norm": 1.4732266664505005,
      "learning_rate": 0.00012436974789915966,
      "loss": 1.794,
      "step": 230
    },
    {
      "epoch": 0.3457436856875585,
      "grad_norm": 1.1438567638397217,
      "learning_rate": 0.00012403361344537816,
      "loss": 1.8223,
      "step": 231
    },
    {
      "epoch": 0.3472404115996258,
      "grad_norm": 1.1886340379714966,
      "learning_rate": 0.00012369747899159666,
      "loss": 1.7702,
      "step": 232
    },
    {
      "epoch": 0.34873713751169316,
      "grad_norm": 1.4150899648666382,
      "learning_rate": 0.00012336134453781513,
      "loss": 1.7094,
      "step": 233
    },
    {
      "epoch": 0.3502338634237605,
      "grad_norm": 1.446444034576416,
      "learning_rate": 0.00012302521008403363,
      "loss": 1.7575,
      "step": 234
    },
    {
      "epoch": 0.3517305893358279,
      "grad_norm": 1.254396677017212,
      "learning_rate": 0.0001226890756302521,
      "loss": 1.6884,
      "step": 235
    },
    {
      "epoch": 0.35322731524789525,
      "grad_norm": 1.2610015869140625,
      "learning_rate": 0.0001223529411764706,
      "loss": 1.8701,
      "step": 236
    },
    {
      "epoch": 0.3547240411599626,
      "grad_norm": 0.932133138179779,
      "learning_rate": 0.00012201680672268909,
      "loss": 1.8865,
      "step": 237
    },
    {
      "epoch": 0.35622076707202993,
      "grad_norm": 1.4056602716445923,
      "learning_rate": 0.00012168067226890756,
      "loss": 1.788,
      "step": 238
    },
    {
      "epoch": 0.3577174929840973,
      "grad_norm": 1.2466380596160889,
      "learning_rate": 0.00012134453781512605,
      "loss": 1.8152,
      "step": 239
    },
    {
      "epoch": 0.3592142188961646,
      "grad_norm": 1.1610888242721558,
      "learning_rate": 0.00012100840336134453,
      "loss": 1.8782,
      "step": 240
    },
    {
      "epoch": 0.360710944808232,
      "grad_norm": 1.1852293014526367,
      "learning_rate": 0.00012067226890756302,
      "loss": 1.7942,
      "step": 241
    },
    {
      "epoch": 0.36220767072029936,
      "grad_norm": 1.1470458507537842,
      "learning_rate": 0.00012033613445378152,
      "loss": 1.9395,
      "step": 242
    },
    {
      "epoch": 0.3637043966323667,
      "grad_norm": 1.1640129089355469,
      "learning_rate": 0.00012,
      "loss": 1.8221,
      "step": 243
    },
    {
      "epoch": 0.36520112254443404,
      "grad_norm": 1.7140247821807861,
      "learning_rate": 0.00011966386554621849,
      "loss": 1.8398,
      "step": 244
    },
    {
      "epoch": 0.3666978484565014,
      "grad_norm": 1.1535826921463013,
      "learning_rate": 0.00011932773109243697,
      "loss": 1.7175,
      "step": 245
    },
    {
      "epoch": 0.3681945743685688,
      "grad_norm": 1.1240558624267578,
      "learning_rate": 0.00011899159663865547,
      "loss": 1.8434,
      "step": 246
    },
    {
      "epoch": 0.3696913002806361,
      "grad_norm": 1.2826379537582397,
      "learning_rate": 0.00011865546218487396,
      "loss": 1.7932,
      "step": 247
    },
    {
      "epoch": 0.37118802619270347,
      "grad_norm": 1.423509955406189,
      "learning_rate": 0.00011831932773109244,
      "loss": 1.851,
      "step": 248
    },
    {
      "epoch": 0.3726847521047708,
      "grad_norm": 1.0698450803756714,
      "learning_rate": 0.00011798319327731093,
      "loss": 1.8628,
      "step": 249
    },
    {
      "epoch": 0.37418147801683815,
      "grad_norm": 1.2364152669906616,
      "learning_rate": 0.00011764705882352942,
      "loss": 1.8172,
      "step": 250
    },
    {
      "epoch": 0.37418147801683815,
      "eval_loss": 1.7512738704681396,
      "eval_runtime": 9.9241,
      "eval_samples_per_second": 6.449,
      "eval_steps_per_second": 3.224,
      "step": 250
    },
    {
      "epoch": 0.3756782039289055,
      "grad_norm": 1.073832392692566,
      "learning_rate": 0.00011731092436974791,
      "loss": 1.7081,
      "step": 251
    },
    {
      "epoch": 0.3771749298409729,
      "grad_norm": 1.0931236743927002,
      "learning_rate": 0.0001169747899159664,
      "loss": 1.8104,
      "step": 252
    },
    {
      "epoch": 0.37867165575304024,
      "grad_norm": 1.0120686292648315,
      "learning_rate": 0.00011663865546218489,
      "loss": 1.9482,
      "step": 253
    },
    {
      "epoch": 0.3801683816651076,
      "grad_norm": 1.493310570716858,
      "learning_rate": 0.00011630252100840337,
      "loss": 1.7734,
      "step": 254
    },
    {
      "epoch": 0.3816651075771749,
      "grad_norm": 1.1117216348648071,
      "learning_rate": 0.00011596638655462187,
      "loss": 1.8592,
      "step": 255
    },
    {
      "epoch": 0.38316183348924227,
      "grad_norm": 1.1169261932373047,
      "learning_rate": 0.00011563025210084036,
      "loss": 1.7698,
      "step": 256
    },
    {
      "epoch": 0.3846585594013096,
      "grad_norm": 1.1613709926605225,
      "learning_rate": 0.00011529411764705881,
      "loss": 1.8207,
      "step": 257
    },
    {
      "epoch": 0.386155285313377,
      "grad_norm": 1.2825706005096436,
      "learning_rate": 0.00011495798319327731,
      "loss": 1.822,
      "step": 258
    },
    {
      "epoch": 0.38765201122544435,
      "grad_norm": 0.9785429835319519,
      "learning_rate": 0.0001146218487394958,
      "loss": 1.7244,
      "step": 259
    },
    {
      "epoch": 0.3891487371375117,
      "grad_norm": 1.177465558052063,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.8048,
      "step": 260
    },
    {
      "epoch": 0.39064546304957903,
      "grad_norm": 1.3732517957687378,
      "learning_rate": 0.00011394957983193277,
      "loss": 1.752,
      "step": 261
    },
    {
      "epoch": 0.3921421889616464,
      "grad_norm": 1.217416763305664,
      "learning_rate": 0.00011361344537815127,
      "loss": 1.8383,
      "step": 262
    },
    {
      "epoch": 0.3936389148737138,
      "grad_norm": 1.1581103801727295,
      "learning_rate": 0.00011327731092436975,
      "loss": 1.7979,
      "step": 263
    },
    {
      "epoch": 0.3951356407857811,
      "grad_norm": 1.0889670848846436,
      "learning_rate": 0.00011294117647058824,
      "loss": 1.8704,
      "step": 264
    },
    {
      "epoch": 0.39663236669784846,
      "grad_norm": 1.3366667032241821,
      "learning_rate": 0.00011260504201680672,
      "loss": 1.8054,
      "step": 265
    },
    {
      "epoch": 0.3981290926099158,
      "grad_norm": 1.2124860286712646,
      "learning_rate": 0.00011226890756302521,
      "loss": 1.8366,
      "step": 266
    },
    {
      "epoch": 0.39962581852198314,
      "grad_norm": 1.3980365991592407,
      "learning_rate": 0.00011193277310924371,
      "loss": 1.7174,
      "step": 267
    },
    {
      "epoch": 0.4011225444340505,
      "grad_norm": 1.1408543586730957,
      "learning_rate": 0.0001115966386554622,
      "loss": 1.7571,
      "step": 268
    },
    {
      "epoch": 0.4026192703461179,
      "grad_norm": 1.1843181848526,
      "learning_rate": 0.00011126050420168068,
      "loss": 1.8332,
      "step": 269
    },
    {
      "epoch": 0.40411599625818523,
      "grad_norm": 1.4148800373077393,
      "learning_rate": 0.00011092436974789917,
      "loss": 1.9739,
      "step": 270
    },
    {
      "epoch": 0.40561272217025257,
      "grad_norm": 1.0253487825393677,
      "learning_rate": 0.00011058823529411766,
      "loss": 1.8726,
      "step": 271
    },
    {
      "epoch": 0.4071094480823199,
      "grad_norm": 1.3067514896392822,
      "learning_rate": 0.00011025210084033615,
      "loss": 1.6941,
      "step": 272
    },
    {
      "epoch": 0.40860617399438726,
      "grad_norm": 1.0671433210372925,
      "learning_rate": 0.00010991596638655464,
      "loss": 1.7697,
      "step": 273
    },
    {
      "epoch": 0.41010289990645465,
      "grad_norm": 1.3519949913024902,
      "learning_rate": 0.00010957983193277312,
      "loss": 1.7855,
      "step": 274
    },
    {
      "epoch": 0.411599625818522,
      "grad_norm": 1.076204538345337,
      "learning_rate": 0.00010924369747899159,
      "loss": 1.9365,
      "step": 275
    },
    {
      "epoch": 0.411599625818522,
      "eval_loss": 1.7478337287902832,
      "eval_runtime": 9.905,
      "eval_samples_per_second": 6.461,
      "eval_steps_per_second": 3.231,
      "step": 275
    },
    {
      "epoch": 0.41309635173058934,
      "grad_norm": 1.2591997385025024,
      "learning_rate": 0.00010890756302521008,
      "loss": 1.7309,
      "step": 276
    },
    {
      "epoch": 0.4145930776426567,
      "grad_norm": 1.340928554534912,
      "learning_rate": 0.00010857142857142856,
      "loss": 1.7348,
      "step": 277
    },
    {
      "epoch": 0.416089803554724,
      "grad_norm": 0.9326046109199524,
      "learning_rate": 0.00010823529411764706,
      "loss": 1.8101,
      "step": 278
    },
    {
      "epoch": 0.41758652946679137,
      "grad_norm": 1.3383642435073853,
      "learning_rate": 0.00010789915966386555,
      "loss": 1.7476,
      "step": 279
    },
    {
      "epoch": 0.41908325537885877,
      "grad_norm": 0.9598699808120728,
      "learning_rate": 0.00010756302521008403,
      "loss": 1.6919,
      "step": 280
    },
    {
      "epoch": 0.4205799812909261,
      "grad_norm": 1.019420862197876,
      "learning_rate": 0.00010722689075630252,
      "loss": 1.8148,
      "step": 281
    },
    {
      "epoch": 0.42207670720299345,
      "grad_norm": 1.142913579940796,
      "learning_rate": 0.000106890756302521,
      "loss": 1.8095,
      "step": 282
    },
    {
      "epoch": 0.4235734331150608,
      "grad_norm": 1.3397822380065918,
      "learning_rate": 0.0001065546218487395,
      "loss": 1.7827,
      "step": 283
    },
    {
      "epoch": 0.42507015902712814,
      "grad_norm": 1.3161386251449585,
      "learning_rate": 0.00010621848739495799,
      "loss": 1.8575,
      "step": 284
    },
    {
      "epoch": 0.42656688493919553,
      "grad_norm": 1.1929869651794434,
      "learning_rate": 0.00010588235294117647,
      "loss": 1.79,
      "step": 285
    },
    {
      "epoch": 0.4280636108512629,
      "grad_norm": 1.2960401773452759,
      "learning_rate": 0.00010554621848739496,
      "loss": 1.7203,
      "step": 286
    },
    {
      "epoch": 0.4295603367633302,
      "grad_norm": 1.117655873298645,
      "learning_rate": 0.00010521008403361346,
      "loss": 1.8556,
      "step": 287
    },
    {
      "epoch": 0.43105706267539756,
      "grad_norm": 1.117436408996582,
      "learning_rate": 0.00010487394957983194,
      "loss": 1.7695,
      "step": 288
    },
    {
      "epoch": 0.4325537885874649,
      "grad_norm": 1.0667588710784912,
      "learning_rate": 0.00010453781512605043,
      "loss": 1.8246,
      "step": 289
    },
    {
      "epoch": 0.43405051449953225,
      "grad_norm": 1.0113589763641357,
      "learning_rate": 0.00010420168067226892,
      "loss": 1.9029,
      "step": 290
    },
    {
      "epoch": 0.43554724041159965,
      "grad_norm": 1.0438803434371948,
      "learning_rate": 0.00010386554621848741,
      "loss": 1.8053,
      "step": 291
    },
    {
      "epoch": 0.437043966323667,
      "grad_norm": 2.1361262798309326,
      "learning_rate": 0.0001035294117647059,
      "loss": 1.7788,
      "step": 292
    },
    {
      "epoch": 0.43854069223573433,
      "grad_norm": 1.2499916553497314,
      "learning_rate": 0.00010319327731092439,
      "loss": 1.745,
      "step": 293
    },
    {
      "epoch": 0.4400374181478017,
      "grad_norm": 1.10703444480896,
      "learning_rate": 0.00010285714285714286,
      "loss": 1.8723,
      "step": 294
    },
    {
      "epoch": 0.441534144059869,
      "grad_norm": 0.9382535815238953,
      "learning_rate": 0.00010252100840336134,
      "loss": 1.8814,
      "step": 295
    },
    {
      "epoch": 0.4430308699719364,
      "grad_norm": 1.1860700845718384,
      "learning_rate": 0.00010218487394957983,
      "loss": 1.7975,
      "step": 296
    },
    {
      "epoch": 0.44452759588400376,
      "grad_norm": 1.0663989782333374,
      "learning_rate": 0.00010184873949579831,
      "loss": 1.8333,
      "step": 297
    },
    {
      "epoch": 0.4460243217960711,
      "grad_norm": 1.0662665367126465,
      "learning_rate": 0.0001015126050420168,
      "loss": 1.7244,
      "step": 298
    },
    {
      "epoch": 0.44752104770813844,
      "grad_norm": 1.1393229961395264,
      "learning_rate": 0.0001011764705882353,
      "loss": 1.7832,
      "step": 299
    },
    {
      "epoch": 0.4490177736202058,
      "grad_norm": 1.1080511808395386,
      "learning_rate": 0.00010084033613445378,
      "loss": 1.9043,
      "step": 300
    },
    {
      "epoch": 0.4490177736202058,
      "eval_loss": 1.7416434288024902,
      "eval_runtime": 9.9207,
      "eval_samples_per_second": 6.451,
      "eval_steps_per_second": 3.226,
      "step": 300
    },
    {
      "epoch": 0.4505144995322731,
      "grad_norm": 1.2179614305496216,
      "learning_rate": 0.00010050420168067227,
      "loss": 1.7529,
      "step": 301
    },
    {
      "epoch": 0.4520112254443405,
      "grad_norm": 1.0161402225494385,
      "learning_rate": 0.00010016806722689076,
      "loss": 1.9195,
      "step": 302
    },
    {
      "epoch": 0.45350795135640787,
      "grad_norm": 0.995812714099884,
      "learning_rate": 9.983193277310925e-05,
      "loss": 1.8102,
      "step": 303
    },
    {
      "epoch": 0.4550046772684752,
      "grad_norm": 1.1934641599655151,
      "learning_rate": 9.949579831932774e-05,
      "loss": 1.7814,
      "step": 304
    },
    {
      "epoch": 0.45650140318054255,
      "grad_norm": 0.8843271732330322,
      "learning_rate": 9.915966386554623e-05,
      "loss": 1.6012,
      "step": 305
    },
    {
      "epoch": 0.4579981290926099,
      "grad_norm": 1.0673537254333496,
      "learning_rate": 9.882352941176471e-05,
      "loss": 1.8338,
      "step": 306
    },
    {
      "epoch": 0.4594948550046773,
      "grad_norm": 1.007251262664795,
      "learning_rate": 9.848739495798321e-05,
      "loss": 1.9598,
      "step": 307
    },
    {
      "epoch": 0.46099158091674464,
      "grad_norm": 1.111372470855713,
      "learning_rate": 9.815126050420168e-05,
      "loss": 1.8086,
      "step": 308
    },
    {
      "epoch": 0.462488306828812,
      "grad_norm": 1.2300423383712769,
      "learning_rate": 9.781512605042017e-05,
      "loss": 1.8517,
      "step": 309
    },
    {
      "epoch": 0.4639850327408793,
      "grad_norm": 1.034952998161316,
      "learning_rate": 9.747899159663865e-05,
      "loss": 1.8743,
      "step": 310
    },
    {
      "epoch": 0.46548175865294666,
      "grad_norm": 1.1956812143325806,
      "learning_rate": 9.714285714285715e-05,
      "loss": 1.8484,
      "step": 311
    },
    {
      "epoch": 0.466978484565014,
      "grad_norm": 1.0862494707107544,
      "learning_rate": 9.680672268907564e-05,
      "loss": 1.8167,
      "step": 312
    },
    {
      "epoch": 0.4684752104770814,
      "grad_norm": 1.0881495475769043,
      "learning_rate": 9.647058823529412e-05,
      "loss": 1.7105,
      "step": 313
    },
    {
      "epoch": 0.46997193638914875,
      "grad_norm": 1.1325311660766602,
      "learning_rate": 9.613445378151261e-05,
      "loss": 1.7793,
      "step": 314
    },
    {
      "epoch": 0.4714686623012161,
      "grad_norm": 1.0453370809555054,
      "learning_rate": 9.579831932773111e-05,
      "loss": 1.8046,
      "step": 315
    },
    {
      "epoch": 0.47296538821328343,
      "grad_norm": 1.127502679824829,
      "learning_rate": 9.546218487394959e-05,
      "loss": 1.8062,
      "step": 316
    },
    {
      "epoch": 0.4744621141253508,
      "grad_norm": 1.0815576314926147,
      "learning_rate": 9.512605042016806e-05,
      "loss": 1.8572,
      "step": 317
    },
    {
      "epoch": 0.4759588400374182,
      "grad_norm": 1.1076608896255493,
      "learning_rate": 9.478991596638655e-05,
      "loss": 1.7315,
      "step": 318
    },
    {
      "epoch": 0.4774555659494855,
      "grad_norm": 1.1549115180969238,
      "learning_rate": 9.445378151260505e-05,
      "loss": 1.749,
      "step": 319
    },
    {
      "epoch": 0.47895229186155286,
      "grad_norm": 1.0027329921722412,
      "learning_rate": 9.411764705882353e-05,
      "loss": 1.9418,
      "step": 320
    },
    {
      "epoch": 0.4804490177736202,
      "grad_norm": 1.1883653402328491,
      "learning_rate": 9.378151260504202e-05,
      "loss": 1.7007,
      "step": 321
    },
    {
      "epoch": 0.48194574368568754,
      "grad_norm": 1.0235621929168701,
      "learning_rate": 9.34453781512605e-05,
      "loss": 1.7951,
      "step": 322
    },
    {
      "epoch": 0.4834424695977549,
      "grad_norm": 1.3429903984069824,
      "learning_rate": 9.3109243697479e-05,
      "loss": 1.8396,
      "step": 323
    },
    {
      "epoch": 0.4849391955098223,
      "grad_norm": 1.2389410734176636,
      "learning_rate": 9.277310924369749e-05,
      "loss": 1.8577,
      "step": 324
    },
    {
      "epoch": 0.4864359214218896,
      "grad_norm": 1.1658669710159302,
      "learning_rate": 9.243697478991598e-05,
      "loss": 1.7733,
      "step": 325
    },
    {
      "epoch": 0.4864359214218896,
      "eval_loss": 1.7379932403564453,
      "eval_runtime": 9.9225,
      "eval_samples_per_second": 6.45,
      "eval_steps_per_second": 3.225,
      "step": 325
    },
    {
      "epoch": 0.48793264733395697,
      "grad_norm": 1.2423300743103027,
      "learning_rate": 9.210084033613445e-05,
      "loss": 1.7292,
      "step": 326
    },
    {
      "epoch": 0.4894293732460243,
      "grad_norm": 1.0733031034469604,
      "learning_rate": 9.176470588235295e-05,
      "loss": 1.8459,
      "step": 327
    },
    {
      "epoch": 0.49092609915809166,
      "grad_norm": 1.0904580354690552,
      "learning_rate": 9.142857142857143e-05,
      "loss": 1.7226,
      "step": 328
    },
    {
      "epoch": 0.49242282507015905,
      "grad_norm": 1.271660327911377,
      "learning_rate": 9.109243697478992e-05,
      "loss": 1.7913,
      "step": 329
    },
    {
      "epoch": 0.4939195509822264,
      "grad_norm": 1.0605442523956299,
      "learning_rate": 9.07563025210084e-05,
      "loss": 1.8367,
      "step": 330
    },
    {
      "epoch": 0.49541627689429374,
      "grad_norm": 1.0855785608291626,
      "learning_rate": 9.04201680672269e-05,
      "loss": 1.7726,
      "step": 331
    },
    {
      "epoch": 0.4969130028063611,
      "grad_norm": 1.0943794250488281,
      "learning_rate": 9.008403361344539e-05,
      "loss": 1.8692,
      "step": 332
    },
    {
      "epoch": 0.4984097287184284,
      "grad_norm": 1.1238775253295898,
      "learning_rate": 8.974789915966387e-05,
      "loss": 1.6684,
      "step": 333
    },
    {
      "epoch": 0.49990645463049577,
      "grad_norm": 1.1262332201004028,
      "learning_rate": 8.941176470588236e-05,
      "loss": 2.0474,
      "step": 334
    },
    {
      "epoch": 0.5014031805425632,
      "grad_norm": 1.1114274263381958,
      "learning_rate": 8.907563025210084e-05,
      "loss": 1.8302,
      "step": 335
    },
    {
      "epoch": 0.5028999064546305,
      "grad_norm": 1.2173712253570557,
      "learning_rate": 8.873949579831933e-05,
      "loss": 1.7415,
      "step": 336
    },
    {
      "epoch": 0.5043966323666979,
      "grad_norm": 1.0768870115280151,
      "learning_rate": 8.840336134453782e-05,
      "loss": 1.8232,
      "step": 337
    },
    {
      "epoch": 0.5058933582787652,
      "grad_norm": 1.3007467985153198,
      "learning_rate": 8.80672268907563e-05,
      "loss": 1.8447,
      "step": 338
    },
    {
      "epoch": 0.5073900841908325,
      "grad_norm": 1.1609522104263306,
      "learning_rate": 8.77310924369748e-05,
      "loss": 1.7427,
      "step": 339
    },
    {
      "epoch": 0.5088868101028999,
      "grad_norm": 1.3535274267196655,
      "learning_rate": 8.739495798319329e-05,
      "loss": 1.748,
      "step": 340
    },
    {
      "epoch": 0.5103835360149672,
      "grad_norm": 1.132091999053955,
      "learning_rate": 8.705882352941177e-05,
      "loss": 1.8139,
      "step": 341
    },
    {
      "epoch": 0.5118802619270346,
      "grad_norm": 1.1243830919265747,
      "learning_rate": 8.672268907563026e-05,
      "loss": 1.7954,
      "step": 342
    },
    {
      "epoch": 0.513376987839102,
      "grad_norm": 1.2013453245162964,
      "learning_rate": 8.638655462184874e-05,
      "loss": 1.7759,
      "step": 343
    },
    {
      "epoch": 0.5148737137511693,
      "grad_norm": 1.1899113655090332,
      "learning_rate": 8.605042016806724e-05,
      "loss": 1.9394,
      "step": 344
    },
    {
      "epoch": 0.5163704396632367,
      "grad_norm": 1.1117327213287354,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.7475,
      "step": 345
    },
    {
      "epoch": 0.517867165575304,
      "grad_norm": 0.9757189154624939,
      "learning_rate": 8.53781512605042e-05,
      "loss": 1.8084,
      "step": 346
    },
    {
      "epoch": 0.5193638914873714,
      "grad_norm": 1.1269667148590088,
      "learning_rate": 8.50420168067227e-05,
      "loss": 1.872,
      "step": 347
    },
    {
      "epoch": 0.5208606173994387,
      "grad_norm": 1.0271408557891846,
      "learning_rate": 8.470588235294118e-05,
      "loss": 1.8508,
      "step": 348
    },
    {
      "epoch": 0.5223573433115061,
      "grad_norm": 1.1958681344985962,
      "learning_rate": 8.436974789915967e-05,
      "loss": 1.7609,
      "step": 349
    },
    {
      "epoch": 0.5238540692235735,
      "grad_norm": 1.1345899105072021,
      "learning_rate": 8.403361344537815e-05,
      "loss": 1.7925,
      "step": 350
    },
    {
      "epoch": 0.5238540692235735,
      "eval_loss": 1.7380330562591553,
      "eval_runtime": 9.922,
      "eval_samples_per_second": 6.45,
      "eval_steps_per_second": 3.225,
      "step": 350
    },
    {
      "epoch": 0.5253507951356408,
      "grad_norm": 1.1461538076400757,
      "learning_rate": 8.369747899159664e-05,
      "loss": 1.7498,
      "step": 351
    },
    {
      "epoch": 0.5268475210477082,
      "grad_norm": 1.1772956848144531,
      "learning_rate": 8.336134453781514e-05,
      "loss": 1.8021,
      "step": 352
    },
    {
      "epoch": 0.5283442469597754,
      "grad_norm": 1.058077335357666,
      "learning_rate": 8.302521008403362e-05,
      "loss": 1.8782,
      "step": 353
    },
    {
      "epoch": 0.5298409728718428,
      "grad_norm": 1.0576335191726685,
      "learning_rate": 8.26890756302521e-05,
      "loss": 1.917,
      "step": 354
    },
    {
      "epoch": 0.5313376987839102,
      "grad_norm": 1.3313714265823364,
      "learning_rate": 8.23529411764706e-05,
      "loss": 1.5589,
      "step": 355
    },
    {
      "epoch": 0.5328344246959775,
      "grad_norm": 1.1257191896438599,
      "learning_rate": 8.201680672268908e-05,
      "loss": 1.8366,
      "step": 356
    },
    {
      "epoch": 0.5343311506080449,
      "grad_norm": 1.1489942073822021,
      "learning_rate": 8.168067226890757e-05,
      "loss": 1.7436,
      "step": 357
    },
    {
      "epoch": 0.5358278765201122,
      "grad_norm": 1.3241493701934814,
      "learning_rate": 8.134453781512605e-05,
      "loss": 1.6859,
      "step": 358
    },
    {
      "epoch": 0.5373246024321796,
      "grad_norm": 1.0549739599227905,
      "learning_rate": 8.100840336134454e-05,
      "loss": 1.7418,
      "step": 359
    },
    {
      "epoch": 0.538821328344247,
      "grad_norm": 1.207139015197754,
      "learning_rate": 8.067226890756304e-05,
      "loss": 1.8467,
      "step": 360
    },
    {
      "epoch": 0.5403180542563143,
      "grad_norm": 0.9392403364181519,
      "learning_rate": 8.033613445378152e-05,
      "loss": 1.8414,
      "step": 361
    },
    {
      "epoch": 0.5418147801683817,
      "grad_norm": 1.0758482217788696,
      "learning_rate": 8e-05,
      "loss": 1.8437,
      "step": 362
    },
    {
      "epoch": 0.543311506080449,
      "grad_norm": 1.3484997749328613,
      "learning_rate": 7.966386554621849e-05,
      "loss": 1.7959,
      "step": 363
    },
    {
      "epoch": 0.5448082319925164,
      "grad_norm": 1.1805089712142944,
      "learning_rate": 7.932773109243698e-05,
      "loss": 1.9371,
      "step": 364
    },
    {
      "epoch": 0.5463049579045838,
      "grad_norm": 1.1756744384765625,
      "learning_rate": 7.899159663865546e-05,
      "loss": 1.7701,
      "step": 365
    },
    {
      "epoch": 0.5478016838166511,
      "grad_norm": 1.1375999450683594,
      "learning_rate": 7.865546218487395e-05,
      "loss": 1.6643,
      "step": 366
    },
    {
      "epoch": 0.5492984097287185,
      "grad_norm": 1.069983720779419,
      "learning_rate": 7.831932773109243e-05,
      "loss": 1.8322,
      "step": 367
    },
    {
      "epoch": 0.5507951356407857,
      "grad_norm": 1.0515434741973877,
      "learning_rate": 7.798319327731093e-05,
      "loss": 1.7744,
      "step": 368
    },
    {
      "epoch": 0.5522918615528531,
      "grad_norm": 1.0633738040924072,
      "learning_rate": 7.764705882352942e-05,
      "loss": 1.8109,
      "step": 369
    },
    {
      "epoch": 0.5537885874649204,
      "grad_norm": 1.359668254852295,
      "learning_rate": 7.73109243697479e-05,
      "loss": 1.7944,
      "step": 370
    },
    {
      "epoch": 0.5552853133769878,
      "grad_norm": 1.2288023233413696,
      "learning_rate": 7.697478991596639e-05,
      "loss": 1.7918,
      "step": 371
    },
    {
      "epoch": 0.5567820392890552,
      "grad_norm": 1.1025428771972656,
      "learning_rate": 7.663865546218489e-05,
      "loss": 1.823,
      "step": 372
    },
    {
      "epoch": 0.5582787652011225,
      "grad_norm": 1.005429744720459,
      "learning_rate": 7.630252100840336e-05,
      "loss": 1.8222,
      "step": 373
    },
    {
      "epoch": 0.5597754911131899,
      "grad_norm": 1.2293034791946411,
      "learning_rate": 7.596638655462185e-05,
      "loss": 1.8342,
      "step": 374
    },
    {
      "epoch": 0.5612722170252572,
      "grad_norm": 1.0827324390411377,
      "learning_rate": 7.563025210084033e-05,
      "loss": 1.643,
      "step": 375
    },
    {
      "epoch": 0.5612722170252572,
      "eval_loss": 1.7346194982528687,
      "eval_runtime": 9.9111,
      "eval_samples_per_second": 6.457,
      "eval_steps_per_second": 3.229,
      "step": 375
    },
    {
      "epoch": 0.5627689429373246,
      "grad_norm": 1.0979185104370117,
      "learning_rate": 7.529411764705883e-05,
      "loss": 1.792,
      "step": 376
    },
    {
      "epoch": 0.564265668849392,
      "grad_norm": 1.0999720096588135,
      "learning_rate": 7.495798319327732e-05,
      "loss": 1.75,
      "step": 377
    },
    {
      "epoch": 0.5657623947614593,
      "grad_norm": 1.1695318222045898,
      "learning_rate": 7.46218487394958e-05,
      "loss": 1.7434,
      "step": 378
    },
    {
      "epoch": 0.5672591206735267,
      "grad_norm": 1.452539324760437,
      "learning_rate": 7.428571428571429e-05,
      "loss": 1.8034,
      "step": 379
    },
    {
      "epoch": 0.568755846585594,
      "grad_norm": 0.971097469329834,
      "learning_rate": 7.394957983193279e-05,
      "loss": 1.9281,
      "step": 380
    },
    {
      "epoch": 0.5702525724976614,
      "grad_norm": 1.190000057220459,
      "learning_rate": 7.361344537815127e-05,
      "loss": 1.8709,
      "step": 381
    },
    {
      "epoch": 0.5717492984097288,
      "grad_norm": 1.2394530773162842,
      "learning_rate": 7.327731092436974e-05,
      "loss": 1.8645,
      "step": 382
    },
    {
      "epoch": 0.573246024321796,
      "grad_norm": 1.0058298110961914,
      "learning_rate": 7.294117647058823e-05,
      "loss": 1.7103,
      "step": 383
    },
    {
      "epoch": 0.5747427502338635,
      "grad_norm": 0.9850262999534607,
      "learning_rate": 7.260504201680673e-05,
      "loss": 1.8576,
      "step": 384
    },
    {
      "epoch": 0.5762394761459307,
      "grad_norm": 0.9836248159408569,
      "learning_rate": 7.226890756302521e-05,
      "loss": 1.8989,
      "step": 385
    },
    {
      "epoch": 0.5777362020579981,
      "grad_norm": 0.9555202126502991,
      "learning_rate": 7.19327731092437e-05,
      "loss": 1.9098,
      "step": 386
    },
    {
      "epoch": 0.5792329279700655,
      "grad_norm": 1.2133311033248901,
      "learning_rate": 7.159663865546218e-05,
      "loss": 1.719,
      "step": 387
    },
    {
      "epoch": 0.5807296538821328,
      "grad_norm": 1.0879029035568237,
      "learning_rate": 7.126050420168068e-05,
      "loss": 1.7404,
      "step": 388
    },
    {
      "epoch": 0.5822263797942002,
      "grad_norm": 1.1183611154556274,
      "learning_rate": 7.092436974789917e-05,
      "loss": 1.7065,
      "step": 389
    },
    {
      "epoch": 0.5837231057062675,
      "grad_norm": 1.1441535949707031,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.876,
      "step": 390
    },
    {
      "epoch": 0.5852198316183349,
      "grad_norm": 1.0589473247528076,
      "learning_rate": 7.025210084033613e-05,
      "loss": 1.7505,
      "step": 391
    },
    {
      "epoch": 0.5867165575304022,
      "grad_norm": 1.149380087852478,
      "learning_rate": 6.991596638655463e-05,
      "loss": 1.7483,
      "step": 392
    },
    {
      "epoch": 0.5882132834424696,
      "grad_norm": 1.18876314163208,
      "learning_rate": 6.957983193277311e-05,
      "loss": 1.6457,
      "step": 393
    },
    {
      "epoch": 0.589710009354537,
      "grad_norm": 1.4560132026672363,
      "learning_rate": 6.92436974789916e-05,
      "loss": 1.747,
      "step": 394
    },
    {
      "epoch": 0.5912067352666043,
      "grad_norm": 1.0865813493728638,
      "learning_rate": 6.890756302521008e-05,
      "loss": 1.7372,
      "step": 395
    },
    {
      "epoch": 0.5927034611786717,
      "grad_norm": 1.1931579113006592,
      "learning_rate": 6.857142857142858e-05,
      "loss": 1.9051,
      "step": 396
    },
    {
      "epoch": 0.594200187090739,
      "grad_norm": 1.0811692476272583,
      "learning_rate": 6.823529411764707e-05,
      "loss": 1.8224,
      "step": 397
    },
    {
      "epoch": 0.5956969130028064,
      "grad_norm": 1.2077957391738892,
      "learning_rate": 6.789915966386555e-05,
      "loss": 1.8336,
      "step": 398
    },
    {
      "epoch": 0.5971936389148738,
      "grad_norm": 1.0455660820007324,
      "learning_rate": 6.756302521008404e-05,
      "loss": 1.797,
      "step": 399
    },
    {
      "epoch": 0.598690364826941,
      "grad_norm": 1.0006000995635986,
      "learning_rate": 6.722689075630254e-05,
      "loss": 1.7179,
      "step": 400
    },
    {
      "epoch": 0.598690364826941,
      "eval_loss": 1.7308931350708008,
      "eval_runtime": 9.9241,
      "eval_samples_per_second": 6.449,
      "eval_steps_per_second": 3.224,
      "step": 400
    },
    {
      "epoch": 0.6001870907390084,
      "grad_norm": 1.143531322479248,
      "learning_rate": 6.689075630252101e-05,
      "loss": 1.8215,
      "step": 401
    },
    {
      "epoch": 0.6016838166510757,
      "grad_norm": 0.9073050618171692,
      "learning_rate": 6.65546218487395e-05,
      "loss": 1.9348,
      "step": 402
    },
    {
      "epoch": 0.6031805425631431,
      "grad_norm": 0.994017481803894,
      "learning_rate": 6.621848739495798e-05,
      "loss": 1.5425,
      "step": 403
    },
    {
      "epoch": 0.6046772684752105,
      "grad_norm": 1.1705002784729004,
      "learning_rate": 6.588235294117648e-05,
      "loss": 1.8536,
      "step": 404
    },
    {
      "epoch": 0.6061739943872778,
      "grad_norm": 0.9837265610694885,
      "learning_rate": 6.554621848739496e-05,
      "loss": 1.7408,
      "step": 405
    },
    {
      "epoch": 0.6076707202993452,
      "grad_norm": 0.9924471378326416,
      "learning_rate": 6.521008403361345e-05,
      "loss": 1.7051,
      "step": 406
    },
    {
      "epoch": 0.6091674462114125,
      "grad_norm": 1.0559359788894653,
      "learning_rate": 6.487394957983193e-05,
      "loss": 1.9459,
      "step": 407
    },
    {
      "epoch": 0.6106641721234799,
      "grad_norm": 1.2436074018478394,
      "learning_rate": 6.453781512605043e-05,
      "loss": 1.7981,
      "step": 408
    },
    {
      "epoch": 0.6121608980355472,
      "grad_norm": 1.278940200805664,
      "learning_rate": 6.420168067226892e-05,
      "loss": 1.7406,
      "step": 409
    },
    {
      "epoch": 0.6136576239476146,
      "grad_norm": 1.1248103380203247,
      "learning_rate": 6.386554621848739e-05,
      "loss": 1.7909,
      "step": 410
    },
    {
      "epoch": 0.615154349859682,
      "grad_norm": 1.1026619672775269,
      "learning_rate": 6.352941176470588e-05,
      "loss": 1.8588,
      "step": 411
    },
    {
      "epoch": 0.6166510757717493,
      "grad_norm": 1.1886570453643799,
      "learning_rate": 6.319327731092438e-05,
      "loss": 1.7935,
      "step": 412
    },
    {
      "epoch": 0.6181478016838167,
      "grad_norm": 1.0327427387237549,
      "learning_rate": 6.285714285714286e-05,
      "loss": 1.8984,
      "step": 413
    },
    {
      "epoch": 0.619644527595884,
      "grad_norm": 0.9914230108261108,
      "learning_rate": 6.252100840336135e-05,
      "loss": 1.9701,
      "step": 414
    },
    {
      "epoch": 0.6211412535079514,
      "grad_norm": 0.9550872445106506,
      "learning_rate": 6.218487394957983e-05,
      "loss": 1.7874,
      "step": 415
    },
    {
      "epoch": 0.6226379794200188,
      "grad_norm": 1.10657799243927,
      "learning_rate": 6.184873949579833e-05,
      "loss": 1.7691,
      "step": 416
    },
    {
      "epoch": 0.624134705332086,
      "grad_norm": 0.956917405128479,
      "learning_rate": 6.151260504201682e-05,
      "loss": 1.7304,
      "step": 417
    },
    {
      "epoch": 0.6256314312441534,
      "grad_norm": 1.0174245834350586,
      "learning_rate": 6.11764705882353e-05,
      "loss": 1.8446,
      "step": 418
    },
    {
      "epoch": 0.6271281571562207,
      "grad_norm": 1.321598768234253,
      "learning_rate": 6.084033613445378e-05,
      "loss": 1.5281,
      "step": 419
    },
    {
      "epoch": 0.6286248830682881,
      "grad_norm": 0.977022111415863,
      "learning_rate": 6.0504201680672267e-05,
      "loss": 1.8618,
      "step": 420
    },
    {
      "epoch": 0.6301216089803555,
      "grad_norm": 1.2729384899139404,
      "learning_rate": 6.016806722689076e-05,
      "loss": 1.6538,
      "step": 421
    },
    {
      "epoch": 0.6316183348924228,
      "grad_norm": 0.982009768486023,
      "learning_rate": 5.9831932773109244e-05,
      "loss": 1.8753,
      "step": 422
    },
    {
      "epoch": 0.6331150608044902,
      "grad_norm": 1.1528300046920776,
      "learning_rate": 5.9495798319327737e-05,
      "loss": 1.8639,
      "step": 423
    },
    {
      "epoch": 0.6346117867165575,
      "grad_norm": 1.096552848815918,
      "learning_rate": 5.915966386554622e-05,
      "loss": 1.7805,
      "step": 424
    },
    {
      "epoch": 0.6361085126286249,
      "grad_norm": 0.9799396991729736,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.9097,
      "step": 425
    },
    {
      "epoch": 0.6361085126286249,
      "eval_loss": 1.7265229225158691,
      "eval_runtime": 9.9192,
      "eval_samples_per_second": 6.452,
      "eval_steps_per_second": 3.226,
      "step": 425
    },
    {
      "epoch": 0.6376052385406923,
      "grad_norm": 0.9917983412742615,
      "learning_rate": 5.84873949579832e-05,
      "loss": 1.8196,
      "step": 426
    },
    {
      "epoch": 0.6391019644527596,
      "grad_norm": 0.9843238592147827,
      "learning_rate": 5.8151260504201685e-05,
      "loss": 1.8505,
      "step": 427
    },
    {
      "epoch": 0.640598690364827,
      "grad_norm": 1.1680494546890259,
      "learning_rate": 5.781512605042018e-05,
      "loss": 1.7219,
      "step": 428
    },
    {
      "epoch": 0.6420954162768943,
      "grad_norm": 1.100326657295227,
      "learning_rate": 5.7478991596638656e-05,
      "loss": 1.8383,
      "step": 429
    },
    {
      "epoch": 0.6435921421889617,
      "grad_norm": 1.1734800338745117,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.7812,
      "step": 430
    },
    {
      "epoch": 0.645088868101029,
      "grad_norm": 1.129654049873352,
      "learning_rate": 5.6806722689075634e-05,
      "loss": 1.6585,
      "step": 431
    },
    {
      "epoch": 0.6465855940130963,
      "grad_norm": 0.925308108329773,
      "learning_rate": 5.647058823529412e-05,
      "loss": 2.008,
      "step": 432
    },
    {
      "epoch": 0.6480823199251637,
      "grad_norm": 1.2162028551101685,
      "learning_rate": 5.6134453781512605e-05,
      "loss": 1.7252,
      "step": 433
    },
    {
      "epoch": 0.649579045837231,
      "grad_norm": 1.0221952199935913,
      "learning_rate": 5.57983193277311e-05,
      "loss": 1.8121,
      "step": 434
    },
    {
      "epoch": 0.6510757717492984,
      "grad_norm": 1.125623106956482,
      "learning_rate": 5.546218487394958e-05,
      "loss": 1.7751,
      "step": 435
    },
    {
      "epoch": 0.6525724976613657,
      "grad_norm": 1.0839701890945435,
      "learning_rate": 5.5126050420168075e-05,
      "loss": 1.7789,
      "step": 436
    },
    {
      "epoch": 0.6540692235734331,
      "grad_norm": 1.1495144367218018,
      "learning_rate": 5.478991596638656e-05,
      "loss": 1.7065,
      "step": 437
    },
    {
      "epoch": 0.6555659494855005,
      "grad_norm": 1.1935160160064697,
      "learning_rate": 5.445378151260504e-05,
      "loss": 1.6623,
      "step": 438
    },
    {
      "epoch": 0.6570626753975678,
      "grad_norm": 1.0761985778808594,
      "learning_rate": 5.411764705882353e-05,
      "loss": 1.7685,
      "step": 439
    },
    {
      "epoch": 0.6585594013096352,
      "grad_norm": 1.2685760259628296,
      "learning_rate": 5.378151260504202e-05,
      "loss": 1.6965,
      "step": 440
    },
    {
      "epoch": 0.6600561272217025,
      "grad_norm": 1.3311073780059814,
      "learning_rate": 5.34453781512605e-05,
      "loss": 1.7738,
      "step": 441
    },
    {
      "epoch": 0.6615528531337699,
      "grad_norm": 1.2063039541244507,
      "learning_rate": 5.3109243697478995e-05,
      "loss": 1.8287,
      "step": 442
    },
    {
      "epoch": 0.6630495790458373,
      "grad_norm": 0.8949533104896545,
      "learning_rate": 5.277310924369748e-05,
      "loss": 1.7777,
      "step": 443
    },
    {
      "epoch": 0.6645463049579046,
      "grad_norm": 0.9890621900558472,
      "learning_rate": 5.243697478991597e-05,
      "loss": 1.8908,
      "step": 444
    },
    {
      "epoch": 0.666043030869972,
      "grad_norm": 1.141076683998108,
      "learning_rate": 5.210084033613446e-05,
      "loss": 1.7678,
      "step": 445
    },
    {
      "epoch": 0.6675397567820393,
      "grad_norm": 1.4433619976043701,
      "learning_rate": 5.176470588235295e-05,
      "loss": 1.7579,
      "step": 446
    },
    {
      "epoch": 0.6690364826941066,
      "grad_norm": 1.088409423828125,
      "learning_rate": 5.142857142857143e-05,
      "loss": 1.7632,
      "step": 447
    },
    {
      "epoch": 0.670533208606174,
      "grad_norm": 0.9711755514144897,
      "learning_rate": 5.1092436974789914e-05,
      "loss": 1.9189,
      "step": 448
    },
    {
      "epoch": 0.6720299345182413,
      "grad_norm": 1.2208515405654907,
      "learning_rate": 5.07563025210084e-05,
      "loss": 1.8619,
      "step": 449
    },
    {
      "epoch": 0.6735266604303087,
      "grad_norm": 1.202310562133789,
      "learning_rate": 5.042016806722689e-05,
      "loss": 1.7852,
      "step": 450
    },
    {
      "epoch": 0.6735266604303087,
      "eval_loss": 1.7230315208435059,
      "eval_runtime": 9.9156,
      "eval_samples_per_second": 6.454,
      "eval_steps_per_second": 3.227,
      "step": 450
    },
    {
      "epoch": 0.675023386342376,
      "grad_norm": 1.0285881757736206,
      "learning_rate": 5.008403361344538e-05,
      "loss": 1.8857,
      "step": 451
    },
    {
      "epoch": 0.6765201122544434,
      "grad_norm": 1.0473498106002808,
      "learning_rate": 4.974789915966387e-05,
      "loss": 1.8324,
      "step": 452
    },
    {
      "epoch": 0.6780168381665107,
      "grad_norm": 1.129944920539856,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 1.9199,
      "step": 453
    },
    {
      "epoch": 0.6795135640785781,
      "grad_norm": 0.9636753797531128,
      "learning_rate": 4.907563025210084e-05,
      "loss": 1.8929,
      "step": 454
    },
    {
      "epoch": 0.6810102899906455,
      "grad_norm": 1.014259934425354,
      "learning_rate": 4.8739495798319326e-05,
      "loss": 1.9402,
      "step": 455
    },
    {
      "epoch": 0.6825070159027128,
      "grad_norm": 1.033557415008545,
      "learning_rate": 4.840336134453782e-05,
      "loss": 1.7401,
      "step": 456
    },
    {
      "epoch": 0.6840037418147802,
      "grad_norm": 1.017338752746582,
      "learning_rate": 4.8067226890756304e-05,
      "loss": 1.7473,
      "step": 457
    },
    {
      "epoch": 0.6855004677268475,
      "grad_norm": 1.0434340238571167,
      "learning_rate": 4.7731092436974796e-05,
      "loss": 1.8009,
      "step": 458
    },
    {
      "epoch": 0.6869971936389149,
      "grad_norm": 1.1409871578216553,
      "learning_rate": 4.7394957983193275e-05,
      "loss": 1.7357,
      "step": 459
    },
    {
      "epoch": 0.6884939195509823,
      "grad_norm": 1.2012221813201904,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.6896,
      "step": 460
    },
    {
      "epoch": 0.6899906454630496,
      "grad_norm": 1.079777479171753,
      "learning_rate": 4.672268907563025e-05,
      "loss": 1.8386,
      "step": 461
    },
    {
      "epoch": 0.691487371375117,
      "grad_norm": 1.0131338834762573,
      "learning_rate": 4.6386554621848745e-05,
      "loss": 1.8507,
      "step": 462
    },
    {
      "epoch": 0.6929840972871842,
      "grad_norm": 1.123460292816162,
      "learning_rate": 4.6050420168067224e-05,
      "loss": 1.7637,
      "step": 463
    },
    {
      "epoch": 0.6944808231992516,
      "grad_norm": 1.4412729740142822,
      "learning_rate": 4.5714285714285716e-05,
      "loss": 1.6948,
      "step": 464
    },
    {
      "epoch": 0.695977549111319,
      "grad_norm": 1.220767617225647,
      "learning_rate": 4.53781512605042e-05,
      "loss": 1.8524,
      "step": 465
    },
    {
      "epoch": 0.6974742750233863,
      "grad_norm": 1.0192736387252808,
      "learning_rate": 4.5042016806722694e-05,
      "loss": 1.8267,
      "step": 466
    },
    {
      "epoch": 0.6989710009354537,
      "grad_norm": 1.0492209196090698,
      "learning_rate": 4.470588235294118e-05,
      "loss": 1.6835,
      "step": 467
    },
    {
      "epoch": 0.700467726847521,
      "grad_norm": 0.9897292256355286,
      "learning_rate": 4.4369747899159665e-05,
      "loss": 1.6976,
      "step": 468
    },
    {
      "epoch": 0.7019644527595884,
      "grad_norm": 1.3974395990371704,
      "learning_rate": 4.403361344537815e-05,
      "loss": 1.7081,
      "step": 469
    },
    {
      "epoch": 0.7034611786716558,
      "grad_norm": 1.0798640251159668,
      "learning_rate": 4.369747899159664e-05,
      "loss": 1.5884,
      "step": 470
    },
    {
      "epoch": 0.7049579045837231,
      "grad_norm": 1.010471224784851,
      "learning_rate": 4.336134453781513e-05,
      "loss": 1.8187,
      "step": 471
    },
    {
      "epoch": 0.7064546304957905,
      "grad_norm": 1.2067906856536865,
      "learning_rate": 4.302521008403362e-05,
      "loss": 1.7909,
      "step": 472
    },
    {
      "epoch": 0.7079513564078578,
      "grad_norm": 0.9305792450904846,
      "learning_rate": 4.26890756302521e-05,
      "loss": 1.8915,
      "step": 473
    },
    {
      "epoch": 0.7094480823199252,
      "grad_norm": 0.9608831405639648,
      "learning_rate": 4.235294117647059e-05,
      "loss": 1.8287,
      "step": 474
    },
    {
      "epoch": 0.7109448082319925,
      "grad_norm": 1.055216908454895,
      "learning_rate": 4.201680672268908e-05,
      "loss": 1.8816,
      "step": 475
    },
    {
      "epoch": 0.7109448082319925,
      "eval_loss": 1.7186332941055298,
      "eval_runtime": 9.9278,
      "eval_samples_per_second": 6.447,
      "eval_steps_per_second": 3.223,
      "step": 475
    },
    {
      "epoch": 0.7124415341440599,
      "grad_norm": 1.1744225025177002,
      "learning_rate": 4.168067226890757e-05,
      "loss": 1.8259,
      "step": 476
    },
    {
      "epoch": 0.7139382600561273,
      "grad_norm": 1.0045477151870728,
      "learning_rate": 4.134453781512605e-05,
      "loss": 1.9401,
      "step": 477
    },
    {
      "epoch": 0.7154349859681945,
      "grad_norm": 1.0020571947097778,
      "learning_rate": 4.100840336134454e-05,
      "loss": 1.801,
      "step": 478
    },
    {
      "epoch": 0.716931711880262,
      "grad_norm": 1.0695722103118896,
      "learning_rate": 4.0672268907563026e-05,
      "loss": 1.7671,
      "step": 479
    },
    {
      "epoch": 0.7184284377923292,
      "grad_norm": 1.0022177696228027,
      "learning_rate": 4.033613445378152e-05,
      "loss": 1.9396,
      "step": 480
    },
    {
      "epoch": 0.7199251637043966,
      "grad_norm": 1.308337688446045,
      "learning_rate": 4e-05,
      "loss": 1.8176,
      "step": 481
    },
    {
      "epoch": 0.721421889616464,
      "grad_norm": 1.133042573928833,
      "learning_rate": 3.966386554621849e-05,
      "loss": 1.726,
      "step": 482
    },
    {
      "epoch": 0.7229186155285313,
      "grad_norm": 0.9932194352149963,
      "learning_rate": 3.9327731092436974e-05,
      "loss": 1.8504,
      "step": 483
    },
    {
      "epoch": 0.7244153414405987,
      "grad_norm": 1.0440658330917358,
      "learning_rate": 3.8991596638655467e-05,
      "loss": 1.7443,
      "step": 484
    },
    {
      "epoch": 0.725912067352666,
      "grad_norm": 1.0093355178833008,
      "learning_rate": 3.865546218487395e-05,
      "loss": 1.9789,
      "step": 485
    },
    {
      "epoch": 0.7274087932647334,
      "grad_norm": 1.0096389055252075,
      "learning_rate": 3.8319327731092444e-05,
      "loss": 1.7372,
      "step": 486
    },
    {
      "epoch": 0.7289055191768008,
      "grad_norm": 0.9682419300079346,
      "learning_rate": 3.798319327731092e-05,
      "loss": 1.8613,
      "step": 487
    },
    {
      "epoch": 0.7304022450888681,
      "grad_norm": 1.174164891242981,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 1.6717,
      "step": 488
    },
    {
      "epoch": 0.7318989710009355,
      "grad_norm": 1.0377211570739746,
      "learning_rate": 3.73109243697479e-05,
      "loss": 1.8994,
      "step": 489
    },
    {
      "epoch": 0.7333956969130028,
      "grad_norm": 1.137771725654602,
      "learning_rate": 3.697478991596639e-05,
      "loss": 1.6331,
      "step": 490
    },
    {
      "epoch": 0.7348924228250702,
      "grad_norm": 1.159590482711792,
      "learning_rate": 3.663865546218487e-05,
      "loss": 1.7866,
      "step": 491
    },
    {
      "epoch": 0.7363891487371376,
      "grad_norm": 1.0992891788482666,
      "learning_rate": 3.6302521008403364e-05,
      "loss": 1.6787,
      "step": 492
    },
    {
      "epoch": 0.7378858746492049,
      "grad_norm": 1.1458029747009277,
      "learning_rate": 3.596638655462185e-05,
      "loss": 1.8032,
      "step": 493
    },
    {
      "epoch": 0.7393826005612723,
      "grad_norm": 1.0241297483444214,
      "learning_rate": 3.563025210084034e-05,
      "loss": 1.8382,
      "step": 494
    },
    {
      "epoch": 0.7408793264733395,
      "grad_norm": 1.0229034423828125,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.6115,
      "step": 495
    },
    {
      "epoch": 0.7423760523854069,
      "grad_norm": 1.0173096656799316,
      "learning_rate": 3.495798319327731e-05,
      "loss": 1.719,
      "step": 496
    },
    {
      "epoch": 0.7438727782974742,
      "grad_norm": 1.0528109073638916,
      "learning_rate": 3.46218487394958e-05,
      "loss": 1.8406,
      "step": 497
    },
    {
      "epoch": 0.7453695042095416,
      "grad_norm": 1.131954312324524,
      "learning_rate": 3.428571428571429e-05,
      "loss": 1.7171,
      "step": 498
    },
    {
      "epoch": 0.746866230121609,
      "grad_norm": 1.2483571767807007,
      "learning_rate": 3.3949579831932776e-05,
      "loss": 1.6404,
      "step": 499
    },
    {
      "epoch": 0.7483629560336763,
      "grad_norm": 1.1184672117233276,
      "learning_rate": 3.361344537815127e-05,
      "loss": 1.7858,
      "step": 500
    },
    {
      "epoch": 0.7483629560336763,
      "eval_loss": 1.7139549255371094,
      "eval_runtime": 9.9252,
      "eval_samples_per_second": 6.448,
      "eval_steps_per_second": 3.224,
      "step": 500
    }
  ],
  "logging_steps": 1,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.418709572519199e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}