{
  "best_metric": 0.07863566279411316,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 3.004366812227074,
  "eval_steps": 50,
  "global_step": 172,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017467248908296942,
      "grad_norm": 1.0100444555282593,
      "learning_rate": 1e-05,
      "loss": 0.7291,
      "step": 1
    },
    {
      "epoch": 0.017467248908296942,
      "eval_loss": 1.4666682481765747,
      "eval_runtime": 2.8998,
      "eval_samples_per_second": 33.451,
      "eval_steps_per_second": 8.621,
      "step": 1
    },
    {
      "epoch": 0.034934497816593885,
      "grad_norm": 1.6248141527175903,
      "learning_rate": 2e-05,
      "loss": 0.9125,
      "step": 2
    },
    {
      "epoch": 0.05240174672489083,
      "grad_norm": 1.6520636081695557,
      "learning_rate": 3e-05,
      "loss": 1.0164,
      "step": 3
    },
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 1.8291550874710083,
      "learning_rate": 4e-05,
      "loss": 1.1878,
      "step": 4
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 1.8957704305648804,
      "learning_rate": 5e-05,
      "loss": 1.0702,
      "step": 5
    },
    {
      "epoch": 0.10480349344978165,
      "grad_norm": 1.6647785902023315,
      "learning_rate": 6e-05,
      "loss": 1.1481,
      "step": 6
    },
    {
      "epoch": 0.1222707423580786,
      "grad_norm": 1.678140640258789,
      "learning_rate": 7e-05,
      "loss": 0.9731,
      "step": 7
    },
    {
      "epoch": 0.13973799126637554,
      "grad_norm": 1.7518115043640137,
      "learning_rate": 8e-05,
      "loss": 1.1692,
      "step": 8
    },
    {
      "epoch": 0.1572052401746725,
      "grad_norm": 1.968929648399353,
      "learning_rate": 9e-05,
      "loss": 1.0349,
      "step": 9
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 1.2481895685195923,
      "learning_rate": 0.0001,
      "loss": 0.8936,
      "step": 10
    },
    {
      "epoch": 0.19213973799126638,
      "grad_norm": 2.483721971511841,
      "learning_rate": 9.999059852242507e-05,
      "loss": 0.9547,
      "step": 11
    },
    {
      "epoch": 0.2096069868995633,
      "grad_norm": 1.7359554767608643,
      "learning_rate": 9.996239762521151e-05,
      "loss": 1.1258,
      "step": 12
    },
    {
      "epoch": 0.22707423580786026,
      "grad_norm": 2.3270020484924316,
      "learning_rate": 9.991540791356342e-05,
      "loss": 1.1838,
      "step": 13
    },
    {
      "epoch": 0.2445414847161572,
      "grad_norm": 2.784715175628662,
      "learning_rate": 9.98496470583896e-05,
      "loss": 1.1575,
      "step": 14
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 0.8565568923950195,
      "learning_rate": 9.976513978965829e-05,
      "loss": 0.6597,
      "step": 15
    },
    {
      "epoch": 0.2794759825327511,
      "grad_norm": 1.0250848531723022,
      "learning_rate": 9.966191788709716e-05,
      "loss": 0.6515,
      "step": 16
    },
    {
      "epoch": 0.29694323144104806,
      "grad_norm": 0.8767344355583191,
      "learning_rate": 9.954002016824227e-05,
      "loss": 0.738,
      "step": 17
    },
    {
      "epoch": 0.314410480349345,
      "grad_norm": 1.0085071325302124,
      "learning_rate": 9.939949247384046e-05,
      "loss": 0.6975,
      "step": 18
    },
    {
      "epoch": 0.3318777292576419,
      "grad_norm": 0.8842006325721741,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7691,
      "step": 19
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 0.9122969508171082,
      "learning_rate": 9.906276553136923e-05,
      "loss": 0.7258,
      "step": 20
    },
    {
      "epoch": 0.36681222707423583,
      "grad_norm": 1.0844351053237915,
      "learning_rate": 9.88666929125318e-05,
      "loss": 0.7773,
      "step": 21
    },
    {
      "epoch": 0.38427947598253276,
      "grad_norm": 1.1110165119171143,
      "learning_rate": 9.865224352899119e-05,
      "loss": 0.7144,
      "step": 22
    },
    {
      "epoch": 0.4017467248908297,
      "grad_norm": 1.1816184520721436,
      "learning_rate": 9.84194980263903e-05,
      "loss": 0.785,
      "step": 23
    },
    {
      "epoch": 0.4192139737991266,
      "grad_norm": 1.3115167617797852,
      "learning_rate": 9.816854393079403e-05,
      "loss": 0.8229,
      "step": 24
    },
    {
      "epoch": 0.4366812227074236,
      "grad_norm": 1.1766431331634521,
      "learning_rate": 9.789947561577445e-05,
      "loss": 0.7382,
      "step": 25
    },
    {
      "epoch": 0.45414847161572053,
      "grad_norm": 1.5775043964385986,
      "learning_rate": 9.761239426692077e-05,
      "loss": 0.8968,
      "step": 26
    },
    {
      "epoch": 0.47161572052401746,
      "grad_norm": 1.766829490661621,
      "learning_rate": 9.730740784378753e-05,
      "loss": 0.863,
      "step": 27
    },
    {
      "epoch": 0.4890829694323144,
      "grad_norm": 2.7797858715057373,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.899,
      "step": 28
    },
    {
      "epoch": 0.5065502183406113,
      "grad_norm": 0.5734480023384094,
      "learning_rate": 9.664418523660004e-05,
      "loss": 0.5252,
      "step": 29
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 0.7527353763580322,
      "learning_rate": 9.628619846344454e-05,
      "loss": 0.5005,
      "step": 30
    },
    {
      "epoch": 0.5414847161572053,
      "grad_norm": 0.9429885149002075,
      "learning_rate": 9.591080534401371e-05,
      "loss": 0.6192,
      "step": 31
    },
    {
      "epoch": 0.5589519650655022,
      "grad_norm": 0.797751247882843,
      "learning_rate": 9.551814704830734e-05,
      "loss": 0.6492,
      "step": 32
    },
    {
      "epoch": 0.5764192139737991,
      "grad_norm": 0.7790107131004333,
      "learning_rate": 9.51083712390519e-05,
      "loss": 0.5706,
      "step": 33
    },
    {
      "epoch": 0.5938864628820961,
      "grad_norm": 0.8417590856552124,
      "learning_rate": 9.468163201617062e-05,
      "loss": 0.5481,
      "step": 34
    },
    {
      "epoch": 0.611353711790393,
      "grad_norm": 0.9345868229866028,
      "learning_rate": 9.423808985883289e-05,
      "loss": 0.626,
      "step": 35
    },
    {
      "epoch": 0.62882096069869,
      "grad_norm": 1.1942213773727417,
      "learning_rate": 9.377791156510455e-05,
      "loss": 0.6025,
      "step": 36
    },
    {
      "epoch": 0.6462882096069869,
      "grad_norm": 0.9529750943183899,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5216,
      "step": 37
    },
    {
      "epoch": 0.6637554585152838,
      "grad_norm": 1.2015634775161743,
      "learning_rate": 9.280834497651334e-05,
      "loss": 0.6232,
      "step": 38
    },
    {
      "epoch": 0.6812227074235808,
      "grad_norm": 1.266699194908142,
      "learning_rate": 9.229932129599205e-05,
      "loss": 0.6139,
      "step": 39
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 1.4141474962234497,
      "learning_rate": 9.177439057064683e-05,
      "loss": 0.7265,
      "step": 40
    },
    {
      "epoch": 0.7161572052401747,
      "grad_norm": 1.8044284582138062,
      "learning_rate": 9.123375020545535e-05,
      "loss": 0.6337,
      "step": 41
    },
    {
      "epoch": 0.7336244541484717,
      "grad_norm": 1.9032659530639648,
      "learning_rate": 9.067760351314838e-05,
      "loss": 0.8511,
      "step": 42
    },
    {
      "epoch": 0.7510917030567685,
      "grad_norm": 0.765811026096344,
      "learning_rate": 9.01061596377522e-05,
      "loss": 0.444,
      "step": 43
    },
    {
      "epoch": 0.7685589519650655,
      "grad_norm": 0.8824454545974731,
      "learning_rate": 8.951963347593797e-05,
      "loss": 0.4689,
      "step": 44
    },
    {
      "epoch": 0.7860262008733624,
      "grad_norm": 0.7503276467323303,
      "learning_rate": 8.891824559620801e-05,
      "loss": 0.426,
      "step": 45
    },
    {
      "epoch": 0.8034934497816594,
      "grad_norm": 1.1007099151611328,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.5502,
      "step": 46
    },
    {
      "epoch": 0.8209606986899564,
      "grad_norm": 0.8477142453193665,
      "learning_rate": 8.767179481638303e-05,
      "loss": 0.451,
      "step": 47
    },
    {
      "epoch": 0.8384279475982532,
      "grad_norm": 0.9551414847373962,
      "learning_rate": 8.702720065545024e-05,
      "loss": 0.3994,
      "step": 48
    },
    {
      "epoch": 0.8558951965065502,
      "grad_norm": 1.0447505712509155,
      "learning_rate": 8.636868207865244e-05,
      "loss": 0.4649,
      "step": 49
    },
    {
      "epoch": 0.8733624454148472,
      "grad_norm": 1.1280784606933594,
      "learning_rate": 8.569648672789497e-05,
      "loss": 0.395,
      "step": 50
    },
    {
      "epoch": 0.8733624454148472,
      "eval_loss": 0.4161189794540405,
      "eval_runtime": 2.9162,
      "eval_samples_per_second": 33.263,
      "eval_steps_per_second": 8.573,
      "step": 50
    },
    {
      "epoch": 0.8908296943231441,
      "grad_norm": 1.1243302822113037,
      "learning_rate": 8.501086738835843e-05,
      "loss": 0.3851,
      "step": 51
    },
    {
      "epoch": 0.9082969432314411,
      "grad_norm": 1.348684549331665,
      "learning_rate": 8.43120818934367e-05,
      "loss": 0.4908,
      "step": 52
    },
    {
      "epoch": 0.925764192139738,
      "grad_norm": 1.6293962001800537,
      "learning_rate": 8.360039302777612e-05,
      "loss": 0.4444,
      "step": 53
    },
    {
      "epoch": 0.9432314410480349,
      "grad_norm": 2.103517770767212,
      "learning_rate": 8.28760684284532e-05,
      "loss": 0.574,
      "step": 54
    },
    {
      "epoch": 0.9606986899563319,
      "grad_norm": 1.4056304693222046,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.3752,
      "step": 55
    },
    {
      "epoch": 0.9781659388646288,
      "grad_norm": 1.6228885650634766,
      "learning_rate": 8.139060623360493e-05,
      "loss": 0.3766,
      "step": 56
    },
    {
      "epoch": 0.9956331877729258,
      "grad_norm": 1.6813204288482666,
      "learning_rate": 8.063002725966015e-05,
      "loss": 0.3613,
      "step": 57
    },
    {
      "epoch": 1.0131004366812226,
      "grad_norm": 5.2064619064331055,
      "learning_rate": 7.985792958513931e-05,
      "loss": 0.788,
      "step": 58
    },
    {
      "epoch": 1.0305676855895196,
      "grad_norm": 0.968858003616333,
      "learning_rate": 7.907460356440133e-05,
      "loss": 0.2553,
      "step": 59
    },
    {
      "epoch": 1.0480349344978166,
      "grad_norm": 0.8971614837646484,
      "learning_rate": 7.828034377432693e-05,
      "loss": 0.2998,
      "step": 60
    },
    {
      "epoch": 1.0655021834061136,
      "grad_norm": 1.2629083395004272,
      "learning_rate": 7.74754489035403e-05,
      "loss": 0.3353,
      "step": 61
    },
    {
      "epoch": 1.0829694323144106,
      "grad_norm": 1.0545297861099243,
      "learning_rate": 7.666022164008457e-05,
      "loss": 0.2211,
      "step": 62
    },
    {
      "epoch": 1.1004366812227073,
      "grad_norm": 1.3016352653503418,
      "learning_rate": 7.583496855759316e-05,
      "loss": 0.2633,
      "step": 63
    },
    {
      "epoch": 1.1179039301310043,
      "grad_norm": 1.4473152160644531,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.246,
      "step": 64
    },
    {
      "epoch": 1.1353711790393013,
      "grad_norm": 1.0543831586837769,
      "learning_rate": 7.415562996483192e-05,
      "loss": 0.2277,
      "step": 65
    },
    {
      "epoch": 1.1528384279475983,
      "grad_norm": 1.0669910907745361,
      "learning_rate": 7.330217598512695e-05,
      "loss": 0.2476,
      "step": 66
    },
    {
      "epoch": 1.1703056768558953,
      "grad_norm": 1.5889818668365479,
      "learning_rate": 7.243995901002312e-05,
      "loss": 0.2648,
      "step": 67
    },
    {
      "epoch": 1.1877729257641922,
      "grad_norm": 1.4110018014907837,
      "learning_rate": 7.156930328406268e-05,
      "loss": 0.2575,
      "step": 68
    },
    {
      "epoch": 1.205240174672489,
      "grad_norm": 1.1937973499298096,
      "learning_rate": 7.069053622525696e-05,
      "loss": 0.2309,
      "step": 69
    },
    {
      "epoch": 1.222707423580786,
      "grad_norm": 1.118398666381836,
      "learning_rate": 6.980398830195785e-05,
      "loss": 0.1686,
      "step": 70
    },
    {
      "epoch": 1.240174672489083,
      "grad_norm": 5.387632846832275,
      "learning_rate": 6.890999290858214e-05,
      "loss": 0.3197,
      "step": 71
    },
    {
      "epoch": 1.25764192139738,
      "grad_norm": 1.4671061038970947,
      "learning_rate": 6.800888624023553e-05,
      "loss": 0.3027,
      "step": 72
    },
    {
      "epoch": 1.2751091703056767,
      "grad_norm": 1.4483202695846558,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2432,
      "step": 73
    },
    {
      "epoch": 1.2925764192139737,
      "grad_norm": 1.154068946838379,
      "learning_rate": 6.618669710291606e-05,
      "loss": 0.2641,
      "step": 74
    },
    {
      "epoch": 1.3100436681222707,
      "grad_norm": 0.9692803621292114,
      "learning_rate": 6.526629988475567e-05,
      "loss": 0.2105,
      "step": 75
    },
    {
      "epoch": 1.3275109170305677,
      "grad_norm": 1.334222674369812,
      "learning_rate": 6.434016163555452e-05,
      "loss": 0.1716,
      "step": 76
    },
    {
      "epoch": 1.3449781659388647,
      "grad_norm": 1.1230826377868652,
      "learning_rate": 6.340863063803188e-05,
      "loss": 0.1533,
      "step": 77
    },
    {
      "epoch": 1.3624454148471616,
      "grad_norm": 1.4789968729019165,
      "learning_rate": 6.247205720289907e-05,
      "loss": 0.2085,
      "step": 78
    },
    {
      "epoch": 1.3799126637554586,
      "grad_norm": 1.0231616497039795,
      "learning_rate": 6.153079353712201e-05,
      "loss": 0.1325,
      "step": 79
    },
    {
      "epoch": 1.3973799126637554,
      "grad_norm": 1.1890296936035156,
      "learning_rate": 6.058519361147055e-05,
      "loss": 0.1489,
      "step": 80
    },
    {
      "epoch": 1.4148471615720524,
      "grad_norm": 1.5673424005508423,
      "learning_rate": 5.963561302740449e-05,
      "loss": 0.1368,
      "step": 81
    },
    {
      "epoch": 1.4323144104803494,
      "grad_norm": 1.3184294700622559,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2192,
      "step": 82
    },
    {
      "epoch": 1.4497816593886463,
      "grad_norm": 1.7077476978302002,
      "learning_rate": 5.772593964039203e-05,
      "loss": 0.2395,
      "step": 83
    },
    {
      "epoch": 1.467248908296943,
      "grad_norm": 1.303192138671875,
      "learning_rate": 5.6766564987506566e-05,
      "loss": 0.1591,
      "step": 84
    },
    {
      "epoch": 1.48471615720524,
      "grad_norm": 1.891233205795288,
      "learning_rate": 5.5804645706261514e-05,
      "loss": 0.181,
      "step": 85
    },
    {
      "epoch": 1.502183406113537,
      "grad_norm": 1.065505862236023,
      "learning_rate": 5.484054353515896e-05,
      "loss": 0.2988,
      "step": 86
    },
    {
      "epoch": 1.519650655021834,
      "grad_norm": 0.8333722352981567,
      "learning_rate": 5.387462103359655e-05,
      "loss": 0.1231,
      "step": 87
    },
    {
      "epoch": 1.537117903930131,
      "grad_norm": 0.8929618000984192,
      "learning_rate": 5.290724144552379e-05,
      "loss": 0.1581,
      "step": 88
    },
    {
      "epoch": 1.554585152838428,
      "grad_norm": 0.6446655988693237,
      "learning_rate": 5.193876856284085e-05,
      "loss": 0.103,
      "step": 89
    },
    {
      "epoch": 1.572052401746725,
      "grad_norm": 1.5530974864959717,
      "learning_rate": 5.096956658859122e-05,
      "loss": 0.2085,
      "step": 90
    },
    {
      "epoch": 1.589519650655022,
      "grad_norm": 1.2184090614318848,
      "learning_rate": 5e-05,
      "loss": 0.1611,
      "step": 91
    },
    {
      "epoch": 1.6069868995633187,
      "grad_norm": 1.355815052986145,
      "learning_rate": 4.903043341140879e-05,
      "loss": 0.1425,
      "step": 92
    },
    {
      "epoch": 1.6244541484716157,
      "grad_norm": 2.162626266479492,
      "learning_rate": 4.806123143715916e-05,
      "loss": 0.228,
      "step": 93
    },
    {
      "epoch": 1.6419213973799127,
      "grad_norm": 1.2516330480575562,
      "learning_rate": 4.709275855447621e-05,
      "loss": 0.0985,
      "step": 94
    },
    {
      "epoch": 1.6593886462882095,
      "grad_norm": 1.455117106437683,
      "learning_rate": 4.612537896640346e-05,
      "loss": 0.169,
      "step": 95
    },
    {
      "epoch": 1.6768558951965065,
      "grad_norm": 1.3163059949874878,
      "learning_rate": 4.515945646484105e-05,
      "loss": 0.1206,
      "step": 96
    },
    {
      "epoch": 1.6943231441048034,
      "grad_norm": 1.735390067100525,
      "learning_rate": 4.4195354293738484e-05,
      "loss": 0.1459,
      "step": 97
    },
    {
      "epoch": 1.7117903930131004,
      "grad_norm": 1.2925852537155151,
      "learning_rate": 4.323343501249346e-05,
      "loss": 0.0877,
      "step": 98
    },
    {
      "epoch": 1.7292576419213974,
      "grad_norm": 1.971182942390442,
      "learning_rate": 4.227406035960798e-05,
      "loss": 0.1316,
      "step": 99
    },
    {
      "epoch": 1.7467248908296944,
      "grad_norm": 0.9830079078674316,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2094,
      "step": 100
    },
    {
      "epoch": 1.7467248908296944,
      "eval_loss": 0.16238145530223846,
      "eval_runtime": 2.9208,
      "eval_samples_per_second": 33.21,
      "eval_steps_per_second": 8.559,
      "step": 100
    },
    {
      "epoch": 1.7641921397379914,
      "grad_norm": 0.9521262049674988,
      "learning_rate": 4.036438697259551e-05,
      "loss": 0.1226,
      "step": 101
    },
    {
      "epoch": 1.7816593886462884,
      "grad_norm": 0.912953794002533,
      "learning_rate": 3.941480638852948e-05,
      "loss": 0.1147,
      "step": 102
    },
    {
      "epoch": 1.7991266375545851,
      "grad_norm": 1.0413082838058472,
      "learning_rate": 3.846920646287799e-05,
      "loss": 0.131,
      "step": 103
    },
    {
      "epoch": 1.8165938864628821,
      "grad_norm": 1.115757703781128,
      "learning_rate": 3.752794279710094e-05,
      "loss": 0.1041,
      "step": 104
    },
    {
      "epoch": 1.8340611353711789,
      "grad_norm": 0.8693847060203552,
      "learning_rate": 3.6591369361968124e-05,
      "loss": 0.065,
      "step": 105
    },
    {
      "epoch": 1.8515283842794759,
      "grad_norm": 0.7901813983917236,
      "learning_rate": 3.5659838364445505e-05,
      "loss": 0.0864,
      "step": 106
    },
    {
      "epoch": 1.8689956331877728,
      "grad_norm": 1.1693010330200195,
      "learning_rate": 3.473370011524435e-05,
      "loss": 0.1329,
      "step": 107
    },
    {
      "epoch": 1.8864628820960698,
      "grad_norm": 0.6798319816589355,
      "learning_rate": 3.381330289708396e-05,
      "loss": 0.0583,
      "step": 108
    },
    {
      "epoch": 1.9039301310043668,
      "grad_norm": 0.8059512972831726,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.079,
      "step": 109
    },
    {
      "epoch": 1.9213973799126638,
      "grad_norm": 2.1519033908843994,
      "learning_rate": 3.199111375976449e-05,
      "loss": 0.1282,
      "step": 110
    },
    {
      "epoch": 1.9388646288209608,
      "grad_norm": 1.3084039688110352,
      "learning_rate": 3.109000709141788e-05,
      "loss": 0.1078,
      "step": 111
    },
    {
      "epoch": 1.9563318777292578,
      "grad_norm": 1.7590997219085693,
      "learning_rate": 3.019601169804216e-05,
      "loss": 0.088,
      "step": 112
    },
    {
      "epoch": 1.9737991266375547,
      "grad_norm": 2.152207612991333,
      "learning_rate": 2.9309463774743046e-05,
      "loss": 0.1825,
      "step": 113
    },
    {
      "epoch": 1.9912663755458515,
      "grad_norm": 1.6330548524856567,
      "learning_rate": 2.8430696715937337e-05,
      "loss": 0.1104,
      "step": 114
    },
    {
      "epoch": 2.0087336244541483,
      "grad_norm": 3.343381404876709,
      "learning_rate": 2.7560040989976892e-05,
      "loss": 0.2211,
      "step": 115
    },
    {
      "epoch": 2.0262008733624453,
      "grad_norm": 0.38313835859298706,
      "learning_rate": 2.6697824014873075e-05,
      "loss": 0.0646,
      "step": 116
    },
    {
      "epoch": 2.0436681222707422,
      "grad_norm": 0.9553971886634827,
      "learning_rate": 2.5844370035168073e-05,
      "loss": 0.064,
      "step": 117
    },
    {
      "epoch": 2.061135371179039,
      "grad_norm": 0.6309722065925598,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0499,
      "step": 118
    },
    {
      "epoch": 2.078602620087336,
      "grad_norm": 0.5666458010673523,
      "learning_rate": 2.4165031442406855e-05,
      "loss": 0.0624,
      "step": 119
    },
    {
      "epoch": 2.096069868995633,
      "grad_norm": 0.8651885390281677,
      "learning_rate": 2.333977835991545e-05,
      "loss": 0.0405,
      "step": 120
    },
    {
      "epoch": 2.11353711790393,
      "grad_norm": 0.6641396880149841,
      "learning_rate": 2.25245510964597e-05,
      "loss": 0.0363,
      "step": 121
    },
    {
      "epoch": 2.131004366812227,
      "grad_norm": 0.7574361562728882,
      "learning_rate": 2.171965622567308e-05,
      "loss": 0.0423,
      "step": 122
    },
    {
      "epoch": 2.148471615720524,
      "grad_norm": 1.8589038848876953,
      "learning_rate": 2.0925396435598664e-05,
      "loss": 0.0724,
      "step": 123
    },
    {
      "epoch": 2.165938864628821,
      "grad_norm": 1.456919550895691,
      "learning_rate": 2.0142070414860704e-05,
      "loss": 0.0459,
      "step": 124
    },
    {
      "epoch": 2.183406113537118,
      "grad_norm": 0.9130675792694092,
      "learning_rate": 1.936997274033986e-05,
      "loss": 0.0442,
      "step": 125
    },
    {
      "epoch": 2.2008733624454146,
      "grad_norm": 1.0100352764129639,
      "learning_rate": 1.8609393766395085e-05,
      "loss": 0.0608,
      "step": 126
    },
    {
      "epoch": 2.2183406113537116,
      "grad_norm": 0.5539523959159851,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0303,
      "step": 127
    },
    {
      "epoch": 2.2358078602620086,
      "grad_norm": 1.8237937688827515,
      "learning_rate": 1.7123931571546827e-05,
      "loss": 0.0489,
      "step": 128
    },
    {
      "epoch": 2.2532751091703056,
      "grad_norm": 0.9342569708824158,
      "learning_rate": 1.639960697222388e-05,
      "loss": 0.0792,
      "step": 129
    },
    {
      "epoch": 2.2707423580786026,
      "grad_norm": 0.4814267158508301,
      "learning_rate": 1.5687918106563326e-05,
      "loss": 0.0559,
      "step": 130
    },
    {
      "epoch": 2.2882096069868996,
      "grad_norm": 0.5614648461341858,
      "learning_rate": 1.4989132611641576e-05,
      "loss": 0.0691,
      "step": 131
    },
    {
      "epoch": 2.3056768558951966,
      "grad_norm": 0.6089550852775574,
      "learning_rate": 1.4303513272105057e-05,
      "loss": 0.0603,
      "step": 132
    },
    {
      "epoch": 2.3231441048034935,
      "grad_norm": 0.39180800318717957,
      "learning_rate": 1.3631317921347563e-05,
      "loss": 0.0422,
      "step": 133
    },
    {
      "epoch": 2.3406113537117905,
      "grad_norm": 1.3804267644882202,
      "learning_rate": 1.297279934454978e-05,
      "loss": 0.044,
      "step": 134
    },
    {
      "epoch": 2.3580786026200875,
      "grad_norm": 1.0875520706176758,
      "learning_rate": 1.2328205183616965e-05,
      "loss": 0.0495,
      "step": 135
    },
    {
      "epoch": 2.3755458515283845,
      "grad_norm": 0.661360502243042,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.043,
      "step": 136
    },
    {
      "epoch": 2.393013100436681,
      "grad_norm": 0.48929262161254883,
      "learning_rate": 1.1081754403791999e-05,
      "loss": 0.0203,
      "step": 137
    },
    {
      "epoch": 2.410480349344978,
      "grad_norm": 0.6960212588310242,
      "learning_rate": 1.0480366524062042e-05,
      "loss": 0.0266,
      "step": 138
    },
    {
      "epoch": 2.427947598253275,
      "grad_norm": 0.7719947099685669,
      "learning_rate": 9.893840362247809e-06,
      "loss": 0.0367,
      "step": 139
    },
    {
      "epoch": 2.445414847161572,
      "grad_norm": 0.6129599213600159,
      "learning_rate": 9.322396486851626e-06,
      "loss": 0.0358,
      "step": 140
    },
    {
      "epoch": 2.462882096069869,
      "grad_norm": 0.8176167607307434,
      "learning_rate": 8.766249794544662e-06,
      "loss": 0.0227,
      "step": 141
    },
    {
      "epoch": 2.480349344978166,
      "grad_norm": 1.3852804899215698,
      "learning_rate": 8.225609429353187e-06,
      "loss": 0.0755,
      "step": 142
    },
    {
      "epoch": 2.497816593886463,
      "grad_norm": 1.7854435443878174,
      "learning_rate": 7.700678704007947e-06,
      "loss": 0.1555,
      "step": 143
    },
    {
      "epoch": 2.51528384279476,
      "grad_norm": 0.4705410301685333,
      "learning_rate": 7.191655023486682e-06,
      "loss": 0.0344,
      "step": 144
    },
    {
      "epoch": 2.532751091703057,
      "grad_norm": 0.40318259596824646,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0432,
      "step": 145
    },
    {
      "epoch": 2.5502183406113534,
      "grad_norm": 0.33191582560539246,
      "learning_rate": 6.222088434895462e-06,
      "loss": 0.0197,
      "step": 146
    },
    {
      "epoch": 2.567685589519651,
      "grad_norm": 0.3540843725204468,
      "learning_rate": 5.7619101411671095e-06,
      "loss": 0.0366,
      "step": 147
    },
    {
      "epoch": 2.5851528384279474,
      "grad_norm": 0.30799436569213867,
      "learning_rate": 5.318367983829392e-06,
      "loss": 0.0201,
      "step": 148
    },
    {
      "epoch": 2.6026200873362444,
      "grad_norm": 0.7724692225456238,
      "learning_rate": 4.891628760948114e-06,
      "loss": 0.0352,
      "step": 149
    },
    {
      "epoch": 2.6200873362445414,
      "grad_norm": 0.599810004234314,
      "learning_rate": 4.4818529516926726e-06,
      "loss": 0.0345,
      "step": 150
    },
    {
      "epoch": 2.6200873362445414,
      "eval_loss": 0.07863566279411316,
      "eval_runtime": 2.9153,
      "eval_samples_per_second": 33.272,
      "eval_steps_per_second": 8.575,
      "step": 150
    },
    {
      "epoch": 2.6375545851528384,
      "grad_norm": 0.7440508604049683,
      "learning_rate": 4.089194655986306e-06,
      "loss": 0.0413,
      "step": 151
    },
    {
      "epoch": 2.6550218340611353,
      "grad_norm": 0.4938758313655853,
      "learning_rate": 3.7138015365554833e-06,
      "loss": 0.0321,
      "step": 152
    },
    {
      "epoch": 2.6724890829694323,
      "grad_norm": 0.47660332918167114,
      "learning_rate": 3.3558147633999728e-06,
      "loss": 0.0272,
      "step": 153
    },
    {
      "epoch": 2.6899563318777293,
      "grad_norm": 0.7508668899536133,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0389,
      "step": 154
    },
    {
      "epoch": 2.7074235807860263,
      "grad_norm": 2.5183489322662354,
      "learning_rate": 2.692592156212487e-06,
      "loss": 0.0222,
      "step": 155
    },
    {
      "epoch": 2.7248908296943233,
      "grad_norm": 0.7234876751899719,
      "learning_rate": 2.3876057330792346e-06,
      "loss": 0.0377,
      "step": 156
    },
    {
      "epoch": 2.74235807860262,
      "grad_norm": 0.44617539644241333,
      "learning_rate": 2.100524384225555e-06,
      "loss": 0.0596,
      "step": 157
    },
    {
      "epoch": 2.7598253275109172,
      "grad_norm": 0.5034026503562927,
      "learning_rate": 1.8314560692059835e-06,
      "loss": 0.0542,
      "step": 158
    },
    {
      "epoch": 2.777292576419214,
      "grad_norm": 0.45781925320625305,
      "learning_rate": 1.5805019736097104e-06,
      "loss": 0.0488,
      "step": 159
    },
    {
      "epoch": 2.7947598253275108,
      "grad_norm": 0.39495936036109924,
      "learning_rate": 1.3477564710088098e-06,
      "loss": 0.0281,
      "step": 160
    },
    {
      "epoch": 2.8122270742358078,
      "grad_norm": 0.6215051412582397,
      "learning_rate": 1.1333070874682216e-06,
      "loss": 0.0502,
      "step": 161
    },
    {
      "epoch": 2.8296943231441047,
      "grad_norm": 0.27189934253692627,
      "learning_rate": 9.372344686307655e-07,
      "loss": 0.0157,
      "step": 162
    },
    {
      "epoch": 2.8471615720524017,
      "grad_norm": 0.4099377691745758,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0285,
      "step": 163
    },
    {
      "epoch": 2.8646288209606987,
      "grad_norm": 0.4258248209953308,
      "learning_rate": 6.005075261595494e-07,
      "loss": 0.0281,
      "step": 164
    },
    {
      "epoch": 2.8820960698689957,
      "grad_norm": 0.3853057026863098,
      "learning_rate": 4.5997983175773417e-07,
      "loss": 0.0248,
      "step": 165
    },
    {
      "epoch": 2.8995633187772927,
      "grad_norm": 0.503648042678833,
      "learning_rate": 3.380821129028489e-07,
      "loss": 0.0272,
      "step": 166
    },
    {
      "epoch": 2.9170305676855897,
      "grad_norm": 4.854583740234375,
      "learning_rate": 2.3486021034170857e-07,
      "loss": 0.0287,
      "step": 167
    },
    {
      "epoch": 2.934497816593886,
      "grad_norm": 0.6928201913833618,
      "learning_rate": 1.503529416103988e-07,
      "loss": 0.0327,
      "step": 168
    },
    {
      "epoch": 2.9519650655021836,
      "grad_norm": 0.25627920031547546,
      "learning_rate": 8.459208643659122e-08,
      "loss": 0.011,
      "step": 169
    },
    {
      "epoch": 2.96943231441048,
      "grad_norm": 0.8357424736022949,
      "learning_rate": 3.760237478849793e-08,
      "loss": 0.0533,
      "step": 170
    },
    {
      "epoch": 2.986899563318777,
      "grad_norm": 2.073831081390381,
      "learning_rate": 9.401477574932926e-09,
      "loss": 0.0415,
      "step": 171
    },
    {
      "epoch": 3.004366812227074,
      "grad_norm": 0.7584478259086609,
      "learning_rate": 0.0,
      "loss": 0.0659,
      "step": 172
    }
  ],
  "logging_steps": 1,
  "max_steps": 172,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.729365147942912e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}