{
  "best_metric": 0.08335956186056137,
  "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": 1.0150203704833984,
      "learning_rate": 1e-05,
      "loss": 0.7291,
      "step": 1
    },
    {
      "epoch": 0.017467248908296942,
      "eval_loss": 1.4666682481765747,
      "eval_runtime": 2.9027,
      "eval_samples_per_second": 33.417,
      "eval_steps_per_second": 8.613,
      "step": 1
    },
    {
      "epoch": 0.034934497816593885,
      "grad_norm": 1.6312181949615479,
      "learning_rate": 2e-05,
      "loss": 0.9125,
      "step": 2
    },
    {
      "epoch": 0.05240174672489083,
      "grad_norm": 1.6606181859970093,
      "learning_rate": 3e-05,
      "loss": 1.0164,
      "step": 3
    },
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 1.8427821397781372,
      "learning_rate": 4e-05,
      "loss": 1.1878,
      "step": 4
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 1.8938854932785034,
      "learning_rate": 5e-05,
      "loss": 1.0719,
      "step": 5
    },
    {
      "epoch": 0.10480349344978165,
      "grad_norm": 1.6704180240631104,
      "learning_rate": 6e-05,
      "loss": 1.1482,
      "step": 6
    },
    {
      "epoch": 0.1222707423580786,
      "grad_norm": 1.6908645629882812,
      "learning_rate": 7e-05,
      "loss": 0.9746,
      "step": 7
    },
    {
      "epoch": 0.13973799126637554,
      "grad_norm": 1.744346261024475,
      "learning_rate": 8e-05,
      "loss": 1.1686,
      "step": 8
    },
    {
      "epoch": 0.1572052401746725,
      "grad_norm": 1.9767279624938965,
      "learning_rate": 9e-05,
      "loss": 1.0338,
      "step": 9
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 1.2403647899627686,
      "learning_rate": 0.0001,
      "loss": 0.895,
      "step": 10
    },
    {
      "epoch": 0.19213973799126638,
      "grad_norm": 2.6359500885009766,
      "learning_rate": 9.999059852242507e-05,
      "loss": 0.9552,
      "step": 11
    },
    {
      "epoch": 0.2096069868995633,
      "grad_norm": 1.7321456670761108,
      "learning_rate": 9.996239762521151e-05,
      "loss": 1.127,
      "step": 12
    },
    {
      "epoch": 0.22707423580786026,
      "grad_norm": 2.320572853088379,
      "learning_rate": 9.991540791356342e-05,
      "loss": 1.1839,
      "step": 13
    },
    {
      "epoch": 0.2445414847161572,
      "grad_norm": 2.7635228633880615,
      "learning_rate": 9.98496470583896e-05,
      "loss": 1.1559,
      "step": 14
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 0.8590458035469055,
      "learning_rate": 9.976513978965829e-05,
      "loss": 0.6596,
      "step": 15
    },
    {
      "epoch": 0.2794759825327511,
      "grad_norm": 1.0409654378890991,
      "learning_rate": 9.966191788709716e-05,
      "loss": 0.6509,
      "step": 16
    },
    {
      "epoch": 0.29694323144104806,
      "grad_norm": 0.8696012496948242,
      "learning_rate": 9.954002016824227e-05,
      "loss": 0.7372,
      "step": 17
    },
    {
      "epoch": 0.314410480349345,
      "grad_norm": 0.9967894554138184,
      "learning_rate": 9.939949247384046e-05,
      "loss": 0.6979,
      "step": 18
    },
    {
      "epoch": 0.3318777292576419,
      "grad_norm": 0.8892637491226196,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7706,
      "step": 19
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 0.9137187004089355,
      "learning_rate": 9.906276553136923e-05,
      "loss": 0.7256,
      "step": 20
    },
    {
      "epoch": 0.36681222707423583,
      "grad_norm": 1.0746030807495117,
      "learning_rate": 9.88666929125318e-05,
      "loss": 0.7775,
      "step": 21
    },
    {
      "epoch": 0.38427947598253276,
      "grad_norm": 1.112693428993225,
      "learning_rate": 9.865224352899119e-05,
      "loss": 0.7126,
      "step": 22
    },
    {
      "epoch": 0.4017467248908297,
      "grad_norm": 1.1786601543426514,
      "learning_rate": 9.84194980263903e-05,
      "loss": 0.7844,
      "step": 23
    },
    {
      "epoch": 0.4192139737991266,
      "grad_norm": 1.3309204578399658,
      "learning_rate": 9.816854393079403e-05,
      "loss": 0.8217,
      "step": 24
    },
    {
      "epoch": 0.4366812227074236,
      "grad_norm": 1.180550217628479,
      "learning_rate": 9.789947561577445e-05,
      "loss": 0.7397,
      "step": 25
    },
    {
      "epoch": 0.45414847161572053,
      "grad_norm": 1.602713942527771,
      "learning_rate": 9.761239426692077e-05,
      "loss": 0.8979,
      "step": 26
    },
    {
      "epoch": 0.47161572052401746,
      "grad_norm": 1.7447450160980225,
      "learning_rate": 9.730740784378753e-05,
      "loss": 0.8654,
      "step": 27
    },
    {
      "epoch": 0.4890829694323144,
      "grad_norm": 2.8003647327423096,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.8954,
      "step": 28
    },
    {
      "epoch": 0.5065502183406113,
      "grad_norm": 0.5731148719787598,
      "learning_rate": 9.664418523660004e-05,
      "loss": 0.5257,
      "step": 29
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 0.7524777054786682,
      "learning_rate": 9.628619846344454e-05,
      "loss": 0.4996,
      "step": 30
    },
    {
      "epoch": 0.5414847161572053,
      "grad_norm": 0.931867778301239,
      "learning_rate": 9.591080534401371e-05,
      "loss": 0.6164,
      "step": 31
    },
    {
      "epoch": 0.5589519650655022,
      "grad_norm": 0.7929329872131348,
      "learning_rate": 9.551814704830734e-05,
      "loss": 0.6483,
      "step": 32
    },
    {
      "epoch": 0.5764192139737991,
      "grad_norm": 0.7793125510215759,
      "learning_rate": 9.51083712390519e-05,
      "loss": 0.5689,
      "step": 33
    },
    {
      "epoch": 0.5938864628820961,
      "grad_norm": 0.8453607559204102,
      "learning_rate": 9.468163201617062e-05,
      "loss": 0.546,
      "step": 34
    },
    {
      "epoch": 0.611353711790393,
      "grad_norm": 0.9560432434082031,
      "learning_rate": 9.423808985883289e-05,
      "loss": 0.6277,
      "step": 35
    },
    {
      "epoch": 0.62882096069869,
      "grad_norm": 1.192608118057251,
      "learning_rate": 9.377791156510455e-05,
      "loss": 0.6021,
      "step": 36
    },
    {
      "epoch": 0.6462882096069869,
      "grad_norm": 0.9529364109039307,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5185,
      "step": 37
    },
    {
      "epoch": 0.6637554585152838,
      "grad_norm": 1.2152981758117676,
      "learning_rate": 9.280834497651334e-05,
      "loss": 0.6219,
      "step": 38
    },
    {
      "epoch": 0.6812227074235808,
      "grad_norm": 1.2711488008499146,
      "learning_rate": 9.229932129599205e-05,
      "loss": 0.6143,
      "step": 39
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 1.4244954586029053,
      "learning_rate": 9.177439057064683e-05,
      "loss": 0.7323,
      "step": 40
    },
    {
      "epoch": 0.7161572052401747,
      "grad_norm": 1.7837212085723877,
      "learning_rate": 9.123375020545535e-05,
      "loss": 0.6341,
      "step": 41
    },
    {
      "epoch": 0.7336244541484717,
      "grad_norm": 1.9221779108047485,
      "learning_rate": 9.067760351314838e-05,
      "loss": 0.8552,
      "step": 42
    },
    {
      "epoch": 0.7510917030567685,
      "grad_norm": 0.7614825367927551,
      "learning_rate": 9.01061596377522e-05,
      "loss": 0.4449,
      "step": 43
    },
    {
      "epoch": 0.7685589519650655,
      "grad_norm": 0.8698350191116333,
      "learning_rate": 8.951963347593797e-05,
      "loss": 0.468,
      "step": 44
    },
    {
      "epoch": 0.7860262008733624,
      "grad_norm": 0.7544025182723999,
      "learning_rate": 8.891824559620801e-05,
      "loss": 0.4263,
      "step": 45
    },
    {
      "epoch": 0.8034934497816594,
      "grad_norm": 1.096413493156433,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.5457,
      "step": 46
    },
    {
      "epoch": 0.8209606986899564,
      "grad_norm": 0.8501629829406738,
      "learning_rate": 8.767179481638303e-05,
      "loss": 0.4508,
      "step": 47
    },
    {
      "epoch": 0.8384279475982532,
      "grad_norm": 0.9768447875976562,
      "learning_rate": 8.702720065545024e-05,
      "loss": 0.4,
      "step": 48
    },
    {
      "epoch": 0.8558951965065502,
      "grad_norm": 1.1103242635726929,
      "learning_rate": 8.636868207865244e-05,
      "loss": 0.4616,
      "step": 49
    },
    {
      "epoch": 0.8733624454148472,
      "grad_norm": 1.2032922506332397,
      "learning_rate": 8.569648672789497e-05,
      "loss": 0.3951,
      "step": 50
    },
    {
      "epoch": 0.8733624454148472,
      "eval_loss": 0.4165593981742859,
      "eval_runtime": 2.92,
      "eval_samples_per_second": 33.219,
      "eval_steps_per_second": 8.562,
      "step": 50
    },
    {
      "epoch": 0.8908296943231441,
      "grad_norm": 1.121232271194458,
      "learning_rate": 8.501086738835843e-05,
      "loss": 0.3865,
      "step": 51
    },
    {
      "epoch": 0.9082969432314411,
      "grad_norm": 1.3548880815505981,
      "learning_rate": 8.43120818934367e-05,
      "loss": 0.493,
      "step": 52
    },
    {
      "epoch": 0.925764192139738,
      "grad_norm": 1.6399530172348022,
      "learning_rate": 8.360039302777612e-05,
      "loss": 0.4454,
      "step": 53
    },
    {
      "epoch": 0.9432314410480349,
      "grad_norm": 2.1539204120635986,
      "learning_rate": 8.28760684284532e-05,
      "loss": 0.5806,
      "step": 54
    },
    {
      "epoch": 0.9606986899563319,
      "grad_norm": 1.3799574375152588,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.3791,
      "step": 55
    },
    {
      "epoch": 0.9781659388646288,
      "grad_norm": 1.6386706829071045,
      "learning_rate": 8.139060623360493e-05,
      "loss": 0.3788,
      "step": 56
    },
    {
      "epoch": 0.9956331877729258,
      "grad_norm": 1.8362394571304321,
      "learning_rate": 8.063002725966015e-05,
      "loss": 0.3617,
      "step": 57
    },
    {
      "epoch": 1.0131004366812226,
      "grad_norm": 4.955390453338623,
      "learning_rate": 7.985792958513931e-05,
      "loss": 0.7963,
      "step": 58
    },
    {
      "epoch": 1.0305676855895196,
      "grad_norm": 1.039722204208374,
      "learning_rate": 7.907460356440133e-05,
      "loss": 0.2566,
      "step": 59
    },
    {
      "epoch": 1.0480349344978166,
      "grad_norm": 0.9322420358657837,
      "learning_rate": 7.828034377432693e-05,
      "loss": 0.3009,
      "step": 60
    },
    {
      "epoch": 1.0655021834061136,
      "grad_norm": 1.1808615922927856,
      "learning_rate": 7.74754489035403e-05,
      "loss": 0.3358,
      "step": 61
    },
    {
      "epoch": 1.0829694323144106,
      "grad_norm": 0.9506165981292725,
      "learning_rate": 7.666022164008457e-05,
      "loss": 0.2231,
      "step": 62
    },
    {
      "epoch": 1.1004366812227073,
      "grad_norm": 1.2802693843841553,
      "learning_rate": 7.583496855759316e-05,
      "loss": 0.2601,
      "step": 63
    },
    {
      "epoch": 1.1179039301310043,
      "grad_norm": 1.6419092416763306,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2622,
      "step": 64
    },
    {
      "epoch": 1.1353711790393013,
      "grad_norm": 0.9867280125617981,
      "learning_rate": 7.415562996483192e-05,
      "loss": 0.2306,
      "step": 65
    },
    {
      "epoch": 1.1528384279475983,
      "grad_norm": 1.1051852703094482,
      "learning_rate": 7.330217598512695e-05,
      "loss": 0.2497,
      "step": 66
    },
    {
      "epoch": 1.1703056768558953,
      "grad_norm": 1.6345847845077515,
      "learning_rate": 7.243995901002312e-05,
      "loss": 0.2628,
      "step": 67
    },
    {
      "epoch": 1.1877729257641922,
      "grad_norm": 1.4212472438812256,
      "learning_rate": 7.156930328406268e-05,
      "loss": 0.2629,
      "step": 68
    },
    {
      "epoch": 1.205240174672489,
      "grad_norm": 1.264844536781311,
      "learning_rate": 7.069053622525696e-05,
      "loss": 0.2389,
      "step": 69
    },
    {
      "epoch": 1.222707423580786,
      "grad_norm": 1.098765254020691,
      "learning_rate": 6.980398830195785e-05,
      "loss": 0.1724,
      "step": 70
    },
    {
      "epoch": 1.240174672489083,
      "grad_norm": 4.439842224121094,
      "learning_rate": 6.890999290858214e-05,
      "loss": 0.3221,
      "step": 71
    },
    {
      "epoch": 1.25764192139738,
      "grad_norm": 1.4293755292892456,
      "learning_rate": 6.800888624023553e-05,
      "loss": 0.2996,
      "step": 72
    },
    {
      "epoch": 1.2751091703056767,
      "grad_norm": 1.592860460281372,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2456,
      "step": 73
    },
    {
      "epoch": 1.2925764192139737,
      "grad_norm": 1.2025070190429688,
      "learning_rate": 6.618669710291606e-05,
      "loss": 0.2663,
      "step": 74
    },
    {
      "epoch": 1.3100436681222707,
      "grad_norm": 0.9999786019325256,
      "learning_rate": 6.526629988475567e-05,
      "loss": 0.2102,
      "step": 75
    },
    {
      "epoch": 1.3275109170305677,
      "grad_norm": 1.3882269859313965,
      "learning_rate": 6.434016163555452e-05,
      "loss": 0.1725,
      "step": 76
    },
    {
      "epoch": 1.3449781659388647,
      "grad_norm": 1.0446701049804688,
      "learning_rate": 6.340863063803188e-05,
      "loss": 0.1511,
      "step": 77
    },
    {
      "epoch": 1.3624454148471616,
      "grad_norm": 1.5679444074630737,
      "learning_rate": 6.247205720289907e-05,
      "loss": 0.217,
      "step": 78
    },
    {
      "epoch": 1.3799126637554586,
      "grad_norm": 1.159275770187378,
      "learning_rate": 6.153079353712201e-05,
      "loss": 0.142,
      "step": 79
    },
    {
      "epoch": 1.3973799126637554,
      "grad_norm": 1.1023359298706055,
      "learning_rate": 6.058519361147055e-05,
      "loss": 0.1504,
      "step": 80
    },
    {
      "epoch": 1.4148471615720524,
      "grad_norm": 1.6043438911437988,
      "learning_rate": 5.963561302740449e-05,
      "loss": 0.1497,
      "step": 81
    },
    {
      "epoch": 1.4323144104803494,
      "grad_norm": 1.2015390396118164,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2159,
      "step": 82
    },
    {
      "epoch": 1.4497816593886463,
      "grad_norm": 1.9150855541229248,
      "learning_rate": 5.772593964039203e-05,
      "loss": 0.2409,
      "step": 83
    },
    {
      "epoch": 1.467248908296943,
      "grad_norm": 1.2557482719421387,
      "learning_rate": 5.6766564987506566e-05,
      "loss": 0.1594,
      "step": 84
    },
    {
      "epoch": 1.48471615720524,
      "grad_norm": 3.442033052444458,
      "learning_rate": 5.5804645706261514e-05,
      "loss": 0.1946,
      "step": 85
    },
    {
      "epoch": 1.502183406113537,
      "grad_norm": 1.3177473545074463,
      "learning_rate": 5.484054353515896e-05,
      "loss": 0.3011,
      "step": 86
    },
    {
      "epoch": 1.519650655021834,
      "grad_norm": 0.811776340007782,
      "learning_rate": 5.387462103359655e-05,
      "loss": 0.1271,
      "step": 87
    },
    {
      "epoch": 1.537117903930131,
      "grad_norm": 1.0938807725906372,
      "learning_rate": 5.290724144552379e-05,
      "loss": 0.1645,
      "step": 88
    },
    {
      "epoch": 1.554585152838428,
      "grad_norm": 0.7474001049995422,
      "learning_rate": 5.193876856284085e-05,
      "loss": 0.1091,
      "step": 89
    },
    {
      "epoch": 1.572052401746725,
      "grad_norm": 1.4519085884094238,
      "learning_rate": 5.096956658859122e-05,
      "loss": 0.2083,
      "step": 90
    },
    {
      "epoch": 1.589519650655022,
      "grad_norm": 1.1171748638153076,
      "learning_rate": 5e-05,
      "loss": 0.1567,
      "step": 91
    },
    {
      "epoch": 1.6069868995633187,
      "grad_norm": 1.226719856262207,
      "learning_rate": 4.903043341140879e-05,
      "loss": 0.1468,
      "step": 92
    },
    {
      "epoch": 1.6244541484716157,
      "grad_norm": 1.6665370464324951,
      "learning_rate": 4.806123143715916e-05,
      "loss": 0.215,
      "step": 93
    },
    {
      "epoch": 1.6419213973799127,
      "grad_norm": 1.3081082105636597,
      "learning_rate": 4.709275855447621e-05,
      "loss": 0.1094,
      "step": 94
    },
    {
      "epoch": 1.6593886462882095,
      "grad_norm": 1.3947356939315796,
      "learning_rate": 4.612537896640346e-05,
      "loss": 0.1714,
      "step": 95
    },
    {
      "epoch": 1.6768558951965065,
      "grad_norm": 1.4104937314987183,
      "learning_rate": 4.515945646484105e-05,
      "loss": 0.1227,
      "step": 96
    },
    {
      "epoch": 1.6943231441048034,
      "grad_norm": 1.774125337600708,
      "learning_rate": 4.4195354293738484e-05,
      "loss": 0.152,
      "step": 97
    },
    {
      "epoch": 1.7117903930131004,
      "grad_norm": 2.2607905864715576,
      "learning_rate": 4.323343501249346e-05,
      "loss": 0.0859,
      "step": 98
    },
    {
      "epoch": 1.7292576419213974,
      "grad_norm": 1.8278192281723022,
      "learning_rate": 4.227406035960798e-05,
      "loss": 0.1364,
      "step": 99
    },
    {
      "epoch": 1.7467248908296944,
      "grad_norm": 1.3324322700500488,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2195,
      "step": 100
    },
    {
      "epoch": 1.7467248908296944,
      "eval_loss": 0.16824179887771606,
      "eval_runtime": 2.9465,
      "eval_samples_per_second": 32.921,
      "eval_steps_per_second": 8.485,
      "step": 100
    },
    {
      "epoch": 1.7641921397379914,
      "grad_norm": 1.0157638788223267,
      "learning_rate": 4.036438697259551e-05,
      "loss": 0.1246,
      "step": 101
    },
    {
      "epoch": 1.7816593886462884,
      "grad_norm": 1.0742075443267822,
      "learning_rate": 3.941480638852948e-05,
      "loss": 0.1228,
      "step": 102
    },
    {
      "epoch": 1.7991266375545851,
      "grad_norm": 1.666223168373108,
      "learning_rate": 3.846920646287799e-05,
      "loss": 0.135,
      "step": 103
    },
    {
      "epoch": 1.8165938864628821,
      "grad_norm": 0.8187023997306824,
      "learning_rate": 3.752794279710094e-05,
      "loss": 0.1066,
      "step": 104
    },
    {
      "epoch": 1.8340611353711789,
      "grad_norm": 1.2794800996780396,
      "learning_rate": 3.6591369361968124e-05,
      "loss": 0.0715,
      "step": 105
    },
    {
      "epoch": 1.8515283842794759,
      "grad_norm": 0.7151631116867065,
      "learning_rate": 3.5659838364445505e-05,
      "loss": 0.088,
      "step": 106
    },
    {
      "epoch": 1.8689956331877728,
      "grad_norm": 1.6745882034301758,
      "learning_rate": 3.473370011524435e-05,
      "loss": 0.1362,
      "step": 107
    },
    {
      "epoch": 1.8864628820960698,
      "grad_norm": 0.7424354553222656,
      "learning_rate": 3.381330289708396e-05,
      "loss": 0.0615,
      "step": 108
    },
    {
      "epoch": 1.9039301310043668,
      "grad_norm": 1.122255563735962,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0812,
      "step": 109
    },
    {
      "epoch": 1.9213973799126638,
      "grad_norm": 2.3225650787353516,
      "learning_rate": 3.199111375976449e-05,
      "loss": 0.1281,
      "step": 110
    },
    {
      "epoch": 1.9388646288209608,
      "grad_norm": 1.1841471195220947,
      "learning_rate": 3.109000709141788e-05,
      "loss": 0.1178,
      "step": 111
    },
    {
      "epoch": 1.9563318777292578,
      "grad_norm": 1.6408817768096924,
      "learning_rate": 3.019601169804216e-05,
      "loss": 0.1156,
      "step": 112
    },
    {
      "epoch": 1.9737991266375547,
      "grad_norm": 1.8442050218582153,
      "learning_rate": 2.9309463774743046e-05,
      "loss": 0.184,
      "step": 113
    },
    {
      "epoch": 1.9912663755458515,
      "grad_norm": 1.5312315225601196,
      "learning_rate": 2.8430696715937337e-05,
      "loss": 0.1173,
      "step": 114
    },
    {
      "epoch": 2.0087336244541483,
      "grad_norm": 2.971773624420166,
      "learning_rate": 2.7560040989976892e-05,
      "loss": 0.2291,
      "step": 115
    },
    {
      "epoch": 2.0262008733624453,
      "grad_norm": 0.3828129768371582,
      "learning_rate": 2.6697824014873075e-05,
      "loss": 0.0673,
      "step": 116
    },
    {
      "epoch": 2.0436681222707422,
      "grad_norm": 0.8585243821144104,
      "learning_rate": 2.5844370035168073e-05,
      "loss": 0.0667,
      "step": 117
    },
    {
      "epoch": 2.061135371179039,
      "grad_norm": 0.7909578084945679,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0569,
      "step": 118
    },
    {
      "epoch": 2.078602620087336,
      "grad_norm": 0.5592768788337708,
      "learning_rate": 2.4165031442406855e-05,
      "loss": 0.0664,
      "step": 119
    },
    {
      "epoch": 2.096069868995633,
      "grad_norm": 0.9716861844062805,
      "learning_rate": 2.333977835991545e-05,
      "loss": 0.0454,
      "step": 120
    },
    {
      "epoch": 2.11353711790393,
      "grad_norm": 0.6158682107925415,
      "learning_rate": 2.25245510964597e-05,
      "loss": 0.0409,
      "step": 121
    },
    {
      "epoch": 2.131004366812227,
      "grad_norm": 0.5465672612190247,
      "learning_rate": 2.171965622567308e-05,
      "loss": 0.0429,
      "step": 122
    },
    {
      "epoch": 2.148471615720524,
      "grad_norm": 2.4121029376983643,
      "learning_rate": 2.0925396435598664e-05,
      "loss": 0.0533,
      "step": 123
    },
    {
      "epoch": 2.165938864628821,
      "grad_norm": 2.363229990005493,
      "learning_rate": 2.0142070414860704e-05,
      "loss": 0.065,
      "step": 124
    },
    {
      "epoch": 2.183406113537118,
      "grad_norm": 0.7529873847961426,
      "learning_rate": 1.936997274033986e-05,
      "loss": 0.0447,
      "step": 125
    },
    {
      "epoch": 2.2008733624454146,
      "grad_norm": 0.9575099945068359,
      "learning_rate": 1.8609393766395085e-05,
      "loss": 0.0638,
      "step": 126
    },
    {
      "epoch": 2.2183406113537116,
      "grad_norm": 0.6782347559928894,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0385,
      "step": 127
    },
    {
      "epoch": 2.2358078602620086,
      "grad_norm": 1.4730333089828491,
      "learning_rate": 1.7123931571546827e-05,
      "loss": 0.0518,
      "step": 128
    },
    {
      "epoch": 2.2532751091703056,
      "grad_norm": 0.9120597839355469,
      "learning_rate": 1.639960697222388e-05,
      "loss": 0.0866,
      "step": 129
    },
    {
      "epoch": 2.2707423580786026,
      "grad_norm": 0.5575978755950928,
      "learning_rate": 1.5687918106563326e-05,
      "loss": 0.0619,
      "step": 130
    },
    {
      "epoch": 2.2882096069868996,
      "grad_norm": 0.6944248676300049,
      "learning_rate": 1.4989132611641576e-05,
      "loss": 0.0769,
      "step": 131
    },
    {
      "epoch": 2.3056768558951966,
      "grad_norm": 0.5566210746765137,
      "learning_rate": 1.4303513272105057e-05,
      "loss": 0.0656,
      "step": 132
    },
    {
      "epoch": 2.3231441048034935,
      "grad_norm": 0.3767731785774231,
      "learning_rate": 1.3631317921347563e-05,
      "loss": 0.0436,
      "step": 133
    },
    {
      "epoch": 2.3406113537117905,
      "grad_norm": 0.7124356627464294,
      "learning_rate": 1.297279934454978e-05,
      "loss": 0.0454,
      "step": 134
    },
    {
      "epoch": 2.3580786026200875,
      "grad_norm": 1.0094614028930664,
      "learning_rate": 1.2328205183616965e-05,
      "loss": 0.0529,
      "step": 135
    },
    {
      "epoch": 2.3755458515283845,
      "grad_norm": 0.7214720845222473,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0482,
      "step": 136
    },
    {
      "epoch": 2.393013100436681,
      "grad_norm": 0.43886321783065796,
      "learning_rate": 1.1081754403791999e-05,
      "loss": 0.0199,
      "step": 137
    },
    {
      "epoch": 2.410480349344978,
      "grad_norm": 0.5449000000953674,
      "learning_rate": 1.0480366524062042e-05,
      "loss": 0.0244,
      "step": 138
    },
    {
      "epoch": 2.427947598253275,
      "grad_norm": 0.7334902882575989,
      "learning_rate": 9.893840362247809e-06,
      "loss": 0.0368,
      "step": 139
    },
    {
      "epoch": 2.445414847161572,
      "grad_norm": 0.6182017922401428,
      "learning_rate": 9.322396486851626e-06,
      "loss": 0.0406,
      "step": 140
    },
    {
      "epoch": 2.462882096069869,
      "grad_norm": 0.47970086336135864,
      "learning_rate": 8.766249794544662e-06,
      "loss": 0.0241,
      "step": 141
    },
    {
      "epoch": 2.480349344978166,
      "grad_norm": 1.3502711057662964,
      "learning_rate": 8.225609429353187e-06,
      "loss": 0.0638,
      "step": 142
    },
    {
      "epoch": 2.497816593886463,
      "grad_norm": 1.8579151630401611,
      "learning_rate": 7.700678704007947e-06,
      "loss": 0.1778,
      "step": 143
    },
    {
      "epoch": 2.51528384279476,
      "grad_norm": 0.498096227645874,
      "learning_rate": 7.191655023486682e-06,
      "loss": 0.037,
      "step": 144
    },
    {
      "epoch": 2.532751091703057,
      "grad_norm": 0.4153275191783905,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0469,
      "step": 145
    },
    {
      "epoch": 2.5502183406113534,
      "grad_norm": 0.3408838212490082,
      "learning_rate": 6.222088434895462e-06,
      "loss": 0.0235,
      "step": 146
    },
    {
      "epoch": 2.567685589519651,
      "grad_norm": 0.401105672121048,
      "learning_rate": 5.7619101411671095e-06,
      "loss": 0.0402,
      "step": 147
    },
    {
      "epoch": 2.5851528384279474,
      "grad_norm": 0.4758196175098419,
      "learning_rate": 5.318367983829392e-06,
      "loss": 0.0227,
      "step": 148
    },
    {
      "epoch": 2.6026200873362444,
      "grad_norm": 0.5934529304504395,
      "learning_rate": 4.891628760948114e-06,
      "loss": 0.0374,
      "step": 149
    },
    {
      "epoch": 2.6200873362445414,
      "grad_norm": 0.7455284595489502,
      "learning_rate": 4.4818529516926726e-06,
      "loss": 0.0425,
      "step": 150
    },
    {
      "epoch": 2.6200873362445414,
      "eval_loss": 0.08335956186056137,
      "eval_runtime": 2.9173,
      "eval_samples_per_second": 33.25,
      "eval_steps_per_second": 8.57,
      "step": 150
    },
    {
      "epoch": 2.6375545851528384,
      "grad_norm": 0.8464643359184265,
      "learning_rate": 4.089194655986306e-06,
      "loss": 0.0425,
      "step": 151
    },
    {
      "epoch": 2.6550218340611353,
      "grad_norm": 0.5147814750671387,
      "learning_rate": 3.7138015365554833e-06,
      "loss": 0.0333,
      "step": 152
    },
    {
      "epoch": 2.6724890829694323,
      "grad_norm": 0.486793577671051,
      "learning_rate": 3.3558147633999728e-06,
      "loss": 0.027,
      "step": 153
    },
    {
      "epoch": 2.6899563318777293,
      "grad_norm": 1.436091661453247,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0495,
      "step": 154
    },
    {
      "epoch": 2.7074235807860263,
      "grad_norm": 2.1560921669006348,
      "learning_rate": 2.692592156212487e-06,
      "loss": 0.0305,
      "step": 155
    },
    {
      "epoch": 2.7248908296943233,
      "grad_norm": 1.1343252658843994,
      "learning_rate": 2.3876057330792346e-06,
      "loss": 0.0429,
      "step": 156
    },
    {
      "epoch": 2.74235807860262,
      "grad_norm": 0.5252926349639893,
      "learning_rate": 2.100524384225555e-06,
      "loss": 0.0663,
      "step": 157
    },
    {
      "epoch": 2.7598253275109172,
      "grad_norm": 0.4776017665863037,
      "learning_rate": 1.8314560692059835e-06,
      "loss": 0.0578,
      "step": 158
    },
    {
      "epoch": 2.777292576419214,
      "grad_norm": 0.4830605983734131,
      "learning_rate": 1.5805019736097104e-06,
      "loss": 0.0531,
      "step": 159
    },
    {
      "epoch": 2.7947598253275108,
      "grad_norm": 0.4230193495750427,
      "learning_rate": 1.3477564710088098e-06,
      "loss": 0.0314,
      "step": 160
    },
    {
      "epoch": 2.8122270742358078,
      "grad_norm": 0.6493737101554871,
      "learning_rate": 1.1333070874682216e-06,
      "loss": 0.0523,
      "step": 161
    },
    {
      "epoch": 2.8296943231441047,
      "grad_norm": 0.2730914056301117,
      "learning_rate": 9.372344686307655e-07,
      "loss": 0.0168,
      "step": 162
    },
    {
      "epoch": 2.8471615720524017,
      "grad_norm": 0.42375174164772034,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0308,
      "step": 163
    },
    {
      "epoch": 2.8646288209606987,
      "grad_norm": 0.4749857783317566,
      "learning_rate": 6.005075261595494e-07,
      "loss": 0.0295,
      "step": 164
    },
    {
      "epoch": 2.8820960698689957,
      "grad_norm": 0.4455066919326782,
      "learning_rate": 4.5997983175773417e-07,
      "loss": 0.0275,
      "step": 165
    },
    {
      "epoch": 2.8995633187772927,
      "grad_norm": 0.6617838144302368,
      "learning_rate": 3.380821129028489e-07,
      "loss": 0.0339,
      "step": 166
    },
    {
      "epoch": 2.9170305676855897,
      "grad_norm": 0.3624148964881897,
      "learning_rate": 2.3486021034170857e-07,
      "loss": 0.0242,
      "step": 167
    },
    {
      "epoch": 2.934497816593886,
      "grad_norm": 0.6199899911880493,
      "learning_rate": 1.503529416103988e-07,
      "loss": 0.0337,
      "step": 168
    },
    {
      "epoch": 2.9519650655021836,
      "grad_norm": 0.24329711496829987,
      "learning_rate": 8.459208643659122e-08,
      "loss": 0.0109,
      "step": 169
    },
    {
      "epoch": 2.96943231441048,
      "grad_norm": 0.8114237189292908,
      "learning_rate": 3.760237478849793e-08,
      "loss": 0.05,
      "step": 170
    },
    {
      "epoch": 2.986899563318777,
      "grad_norm": 0.4971747100353241,
      "learning_rate": 9.401477574932926e-09,
      "loss": 0.0369,
      "step": 171
    },
    {
      "epoch": 3.004366812227074,
      "grad_norm": 0.4547681510448456,
      "learning_rate": 0.0,
      "loss": 0.0711,
      "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
}