{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 338,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002962962962962963,
      "grad_norm": 24.033334732055664,
      "learning_rate": 0.0,
      "loss": 1.234,
      "step": 1
    },
    {
      "epoch": 0.005925925925925926,
      "grad_norm": 24.785776138305664,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.4298,
      "step": 2
    },
    {
      "epoch": 0.008888888888888889,
      "grad_norm": 24.13324737548828,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2941,
      "step": 3
    },
    {
      "epoch": 0.011851851851851851,
      "grad_norm": 20.406665802001953,
      "learning_rate": 6e-06,
      "loss": 0.9558,
      "step": 4
    },
    {
      "epoch": 0.014814814814814815,
      "grad_norm": 16.233354568481445,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7493,
      "step": 5
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 12.92891788482666,
      "learning_rate": 1e-05,
      "loss": 0.7406,
      "step": 6
    },
    {
      "epoch": 0.02074074074074074,
      "grad_norm": 8.30112361907959,
      "learning_rate": 9.96996996996997e-06,
      "loss": 0.5776,
      "step": 7
    },
    {
      "epoch": 0.023703703703703703,
      "grad_norm": 5.0705342292785645,
      "learning_rate": 9.93993993993994e-06,
      "loss": 0.3864,
      "step": 8
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 3.8606483936309814,
      "learning_rate": 9.90990990990991e-06,
      "loss": 0.3938,
      "step": 9
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 4.1690263748168945,
      "learning_rate": 9.879879879879881e-06,
      "loss": 0.4182,
      "step": 10
    },
    {
      "epoch": 0.03259259259259259,
      "grad_norm": 2.7711541652679443,
      "learning_rate": 9.849849849849851e-06,
      "loss": 0.2851,
      "step": 11
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 2.9713804721832275,
      "learning_rate": 9.81981981981982e-06,
      "loss": 0.3678,
      "step": 12
    },
    {
      "epoch": 0.03851851851851852,
      "grad_norm": 2.3790831565856934,
      "learning_rate": 9.78978978978979e-06,
      "loss": 0.2089,
      "step": 13
    },
    {
      "epoch": 0.04148148148148148,
      "grad_norm": 2.877018690109253,
      "learning_rate": 9.75975975975976e-06,
      "loss": 0.3593,
      "step": 14
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 2.321021556854248,
      "learning_rate": 9.729729729729732e-06,
      "loss": 0.2233,
      "step": 15
    },
    {
      "epoch": 0.047407407407407405,
      "grad_norm": 2.887695550918579,
      "learning_rate": 9.699699699699701e-06,
      "loss": 0.2789,
      "step": 16
    },
    {
      "epoch": 0.05037037037037037,
      "grad_norm": 2.472564458847046,
      "learning_rate": 9.669669669669671e-06,
      "loss": 0.2389,
      "step": 17
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 1.8199663162231445,
      "learning_rate": 9.63963963963964e-06,
      "loss": 0.1555,
      "step": 18
    },
    {
      "epoch": 0.056296296296296296,
      "grad_norm": 2.281066417694092,
      "learning_rate": 9.60960960960961e-06,
      "loss": 0.2479,
      "step": 19
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 2.2606992721557617,
      "learning_rate": 9.57957957957958e-06,
      "loss": 0.2718,
      "step": 20
    },
    {
      "epoch": 0.06222222222222222,
      "grad_norm": 1.6966127157211304,
      "learning_rate": 9.54954954954955e-06,
      "loss": 0.147,
      "step": 21
    },
    {
      "epoch": 0.06518518518518518,
      "grad_norm": 2.5363636016845703,
      "learning_rate": 9.51951951951952e-06,
      "loss": 0.259,
      "step": 22
    },
    {
      "epoch": 0.06814814814814815,
      "grad_norm": 2.410266876220703,
      "learning_rate": 9.489489489489491e-06,
      "loss": 0.2756,
      "step": 23
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 2.55072283744812,
      "learning_rate": 9.45945945945946e-06,
      "loss": 0.2886,
      "step": 24
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.9554929733276367,
      "learning_rate": 9.42942942942943e-06,
      "loss": 0.1685,
      "step": 25
    },
    {
      "epoch": 0.07703703703703704,
      "grad_norm": 2.17787504196167,
      "learning_rate": 9.3993993993994e-06,
      "loss": 0.2274,
      "step": 26
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.6718087196350098,
      "learning_rate": 9.36936936936937e-06,
      "loss": 0.2807,
      "step": 27
    },
    {
      "epoch": 0.08296296296296296,
      "grad_norm": 2.3547708988189697,
      "learning_rate": 9.339339339339341e-06,
      "loss": 0.2855,
      "step": 28
    },
    {
      "epoch": 0.08592592592592592,
      "grad_norm": 2.1649510860443115,
      "learning_rate": 9.30930930930931e-06,
      "loss": 0.2221,
      "step": 29
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 1.9821112155914307,
      "learning_rate": 9.27927927927928e-06,
      "loss": 0.1829,
      "step": 30
    },
    {
      "epoch": 0.09185185185185185,
      "grad_norm": 1.6550806760787964,
      "learning_rate": 9.24924924924925e-06,
      "loss": 0.1391,
      "step": 31
    },
    {
      "epoch": 0.09481481481481481,
      "grad_norm": 1.3130732774734497,
      "learning_rate": 9.21921921921922e-06,
      "loss": 0.0927,
      "step": 32
    },
    {
      "epoch": 0.09777777777777778,
      "grad_norm": 1.5026895999908447,
      "learning_rate": 9.189189189189191e-06,
      "loss": 0.1335,
      "step": 33
    },
    {
      "epoch": 0.10074074074074074,
      "grad_norm": 1.9520760774612427,
      "learning_rate": 9.15915915915916e-06,
      "loss": 0.184,
      "step": 34
    },
    {
      "epoch": 0.1037037037037037,
      "grad_norm": 2.0884082317352295,
      "learning_rate": 9.129129129129129e-06,
      "loss": 0.2472,
      "step": 35
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 2.053196668624878,
      "learning_rate": 9.0990990990991e-06,
      "loss": 0.1687,
      "step": 36
    },
    {
      "epoch": 0.10962962962962963,
      "grad_norm": 2.03136944770813,
      "learning_rate": 9.06906906906907e-06,
      "loss": 0.2171,
      "step": 37
    },
    {
      "epoch": 0.11259259259259259,
      "grad_norm": 2.1041648387908936,
      "learning_rate": 9.03903903903904e-06,
      "loss": 0.2062,
      "step": 38
    },
    {
      "epoch": 0.11555555555555555,
      "grad_norm": 1.5398188829421997,
      "learning_rate": 9.00900900900901e-06,
      "loss": 0.1348,
      "step": 39
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 1.5641947984695435,
      "learning_rate": 8.97897897897898e-06,
      "loss": 0.1464,
      "step": 40
    },
    {
      "epoch": 0.12148148148148148,
      "grad_norm": 1.834839105606079,
      "learning_rate": 8.94894894894895e-06,
      "loss": 0.193,
      "step": 41
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 2.2916324138641357,
      "learning_rate": 8.91891891891892e-06,
      "loss": 0.252,
      "step": 42
    },
    {
      "epoch": 0.1274074074074074,
      "grad_norm": 1.4242668151855469,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.1072,
      "step": 43
    },
    {
      "epoch": 0.13037037037037036,
      "grad_norm": 1.5289603471755981,
      "learning_rate": 8.85885885885886e-06,
      "loss": 0.1304,
      "step": 44
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 2.1311769485473633,
      "learning_rate": 8.82882882882883e-06,
      "loss": 0.1965,
      "step": 45
    },
    {
      "epoch": 0.1362962962962963,
      "grad_norm": 2.0346412658691406,
      "learning_rate": 8.798798798798799e-06,
      "loss": 0.2199,
      "step": 46
    },
    {
      "epoch": 0.13925925925925925,
      "grad_norm": 2.6739606857299805,
      "learning_rate": 8.768768768768769e-06,
      "loss": 0.2969,
      "step": 47
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 1.5655385255813599,
      "learning_rate": 8.738738738738739e-06,
      "loss": 0.1091,
      "step": 48
    },
    {
      "epoch": 0.1451851851851852,
      "grad_norm": 1.651969313621521,
      "learning_rate": 8.70870870870871e-06,
      "loss": 0.149,
      "step": 49
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.3254390954971313,
      "learning_rate": 8.67867867867868e-06,
      "loss": 0.1317,
      "step": 50
    },
    {
      "epoch": 0.14814814814814814,
      "eval_loss": 0.16429173946380615,
      "eval_runtime": 35.7973,
      "eval_samples_per_second": 16.761,
      "eval_steps_per_second": 8.381,
      "step": 50
    },
    {
      "epoch": 0.1511111111111111,
      "grad_norm": 2.0785887241363525,
      "learning_rate": 8.64864864864865e-06,
      "loss": 0.2277,
      "step": 51
    },
    {
      "epoch": 0.15407407407407409,
      "grad_norm": 1.935077428817749,
      "learning_rate": 8.618618618618619e-06,
      "loss": 0.189,
      "step": 52
    },
    {
      "epoch": 0.15703703703703703,
      "grad_norm": 1.9624170064926147,
      "learning_rate": 8.588588588588589e-06,
      "loss": 0.222,
      "step": 53
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.1484665870666504,
      "learning_rate": 8.55855855855856e-06,
      "loss": 0.1972,
      "step": 54
    },
    {
      "epoch": 0.16296296296296298,
      "grad_norm": 1.2270996570587158,
      "learning_rate": 8.52852852852853e-06,
      "loss": 0.1012,
      "step": 55
    },
    {
      "epoch": 0.16592592592592592,
      "grad_norm": 1.9261056184768677,
      "learning_rate": 8.4984984984985e-06,
      "loss": 0.1693,
      "step": 56
    },
    {
      "epoch": 0.1688888888888889,
      "grad_norm": 1.5654529333114624,
      "learning_rate": 8.46846846846847e-06,
      "loss": 0.1365,
      "step": 57
    },
    {
      "epoch": 0.17185185185185184,
      "grad_norm": 1.418778657913208,
      "learning_rate": 8.438438438438439e-06,
      "loss": 0.1134,
      "step": 58
    },
    {
      "epoch": 0.1748148148148148,
      "grad_norm": 1.7882100343704224,
      "learning_rate": 8.408408408408409e-06,
      "loss": 0.1809,
      "step": 59
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 1.6592146158218384,
      "learning_rate": 8.378378378378378e-06,
      "loss": 0.1698,
      "step": 60
    },
    {
      "epoch": 0.18074074074074073,
      "grad_norm": 1.5762512683868408,
      "learning_rate": 8.348348348348348e-06,
      "loss": 0.1486,
      "step": 61
    },
    {
      "epoch": 0.1837037037037037,
      "grad_norm": 1.3590905666351318,
      "learning_rate": 8.31831831831832e-06,
      "loss": 0.1251,
      "step": 62
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 1.9860204458236694,
      "learning_rate": 8.288288288288289e-06,
      "loss": 0.2232,
      "step": 63
    },
    {
      "epoch": 0.18962962962962962,
      "grad_norm": 1.4706617593765259,
      "learning_rate": 8.258258258258259e-06,
      "loss": 0.151,
      "step": 64
    },
    {
      "epoch": 0.1925925925925926,
      "grad_norm": 1.7846999168395996,
      "learning_rate": 8.228228228228229e-06,
      "loss": 0.1747,
      "step": 65
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 1.836977481842041,
      "learning_rate": 8.198198198198198e-06,
      "loss": 0.1505,
      "step": 66
    },
    {
      "epoch": 0.1985185185185185,
      "grad_norm": 1.8636958599090576,
      "learning_rate": 8.16816816816817e-06,
      "loss": 0.2128,
      "step": 67
    },
    {
      "epoch": 0.20148148148148148,
      "grad_norm": 2.6715590953826904,
      "learning_rate": 8.13813813813814e-06,
      "loss": 0.2791,
      "step": 68
    },
    {
      "epoch": 0.20444444444444446,
      "grad_norm": 1.9791332483291626,
      "learning_rate": 8.108108108108109e-06,
      "loss": 0.2095,
      "step": 69
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 1.1906194686889648,
      "learning_rate": 8.078078078078079e-06,
      "loss": 0.1083,
      "step": 70
    },
    {
      "epoch": 0.21037037037037037,
      "grad_norm": 2.013612747192383,
      "learning_rate": 8.048048048048048e-06,
      "loss": 0.1957,
      "step": 71
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 2.03743577003479,
      "learning_rate": 8.018018018018018e-06,
      "loss": 0.1843,
      "step": 72
    },
    {
      "epoch": 0.2162962962962963,
      "grad_norm": 1.5015028715133667,
      "learning_rate": 7.987987987987988e-06,
      "loss": 0.1298,
      "step": 73
    },
    {
      "epoch": 0.21925925925925926,
      "grad_norm": 1.4761093854904175,
      "learning_rate": 7.95795795795796e-06,
      "loss": 0.1098,
      "step": 74
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.5150935649871826,
      "learning_rate": 7.927927927927929e-06,
      "loss": 0.1327,
      "step": 75
    },
    {
      "epoch": 0.22518518518518518,
      "grad_norm": 1.636572003364563,
      "learning_rate": 7.897897897897899e-06,
      "loss": 0.1623,
      "step": 76
    },
    {
      "epoch": 0.22814814814814816,
      "grad_norm": 2.0918989181518555,
      "learning_rate": 7.867867867867868e-06,
      "loss": 0.2167,
      "step": 77
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 1.6946781873703003,
      "learning_rate": 7.837837837837838e-06,
      "loss": 0.1673,
      "step": 78
    },
    {
      "epoch": 0.23407407407407407,
      "grad_norm": 1.3498488664627075,
      "learning_rate": 7.807807807807808e-06,
      "loss": 0.1226,
      "step": 79
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.6973378658294678,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.163,
      "step": 80
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.5480597019195557,
      "learning_rate": 7.747747747747749e-06,
      "loss": 0.1612,
      "step": 81
    },
    {
      "epoch": 0.24296296296296296,
      "grad_norm": 1.6320154666900635,
      "learning_rate": 7.717717717717719e-06,
      "loss": 0.1362,
      "step": 82
    },
    {
      "epoch": 0.24592592592592594,
      "grad_norm": 1.3256680965423584,
      "learning_rate": 7.687687687687688e-06,
      "loss": 0.1144,
      "step": 83
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 1.5343090295791626,
      "learning_rate": 7.657657657657658e-06,
      "loss": 0.1384,
      "step": 84
    },
    {
      "epoch": 0.2518518518518518,
      "grad_norm": 1.6446950435638428,
      "learning_rate": 7.6276276276276285e-06,
      "loss": 0.172,
      "step": 85
    },
    {
      "epoch": 0.2548148148148148,
      "grad_norm": 1.349584937095642,
      "learning_rate": 7.597597597597598e-06,
      "loss": 0.1495,
      "step": 86
    },
    {
      "epoch": 0.2577777777777778,
      "grad_norm": 1.8881844282150269,
      "learning_rate": 7.567567567567569e-06,
      "loss": 0.2317,
      "step": 87
    },
    {
      "epoch": 0.2607407407407407,
      "grad_norm": 1.9484448432922363,
      "learning_rate": 7.5375375375375385e-06,
      "loss": 0.2067,
      "step": 88
    },
    {
      "epoch": 0.2637037037037037,
      "grad_norm": 1.367071509361267,
      "learning_rate": 7.507507507507507e-06,
      "loss": 0.128,
      "step": 89
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.7493239641189575,
      "learning_rate": 7.477477477477479e-06,
      "loss": 0.1566,
      "step": 90
    },
    {
      "epoch": 0.2696296296296296,
      "grad_norm": 1.7188656330108643,
      "learning_rate": 7.447447447447448e-06,
      "loss": 0.208,
      "step": 91
    },
    {
      "epoch": 0.2725925925925926,
      "grad_norm": 1.3538898229599,
      "learning_rate": 7.417417417417418e-06,
      "loss": 0.1218,
      "step": 92
    },
    {
      "epoch": 0.27555555555555555,
      "grad_norm": 1.2056565284729004,
      "learning_rate": 7.387387387387388e-06,
      "loss": 0.0933,
      "step": 93
    },
    {
      "epoch": 0.2785185185185185,
      "grad_norm": 2.1674771308898926,
      "learning_rate": 7.3573573573573575e-06,
      "loss": 0.2478,
      "step": 94
    },
    {
      "epoch": 0.2814814814814815,
      "grad_norm": 1.480126142501831,
      "learning_rate": 7.327327327327328e-06,
      "loss": 0.1496,
      "step": 95
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 1.7292470932006836,
      "learning_rate": 7.297297297297298e-06,
      "loss": 0.181,
      "step": 96
    },
    {
      "epoch": 0.2874074074074074,
      "grad_norm": 1.65279221534729,
      "learning_rate": 7.267267267267268e-06,
      "loss": 0.1999,
      "step": 97
    },
    {
      "epoch": 0.2903703703703704,
      "grad_norm": 1.5619298219680786,
      "learning_rate": 7.237237237237238e-06,
      "loss": 0.1599,
      "step": 98
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 2.3449010848999023,
      "learning_rate": 7.207207207207208e-06,
      "loss": 0.253,
      "step": 99
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.5473984479904175,
      "learning_rate": 7.177177177177178e-06,
      "loss": 0.1872,
      "step": 100
    },
    {
      "epoch": 0.2962962962962963,
      "eval_loss": 0.1522752195596695,
      "eval_runtime": 33.9954,
      "eval_samples_per_second": 17.649,
      "eval_steps_per_second": 8.825,
      "step": 100
    },
    {
      "epoch": 0.2992592592592593,
      "grad_norm": 1.6290215253829956,
      "learning_rate": 7.147147147147148e-06,
      "loss": 0.1192,
      "step": 101
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 1.7432998418807983,
      "learning_rate": 7.117117117117117e-06,
      "loss": 0.1714,
      "step": 102
    },
    {
      "epoch": 0.30518518518518517,
      "grad_norm": 2.3427700996398926,
      "learning_rate": 7.087087087087087e-06,
      "loss": 0.2504,
      "step": 103
    },
    {
      "epoch": 0.30814814814814817,
      "grad_norm": 1.6693565845489502,
      "learning_rate": 7.057057057057057e-06,
      "loss": 0.1488,
      "step": 104
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 1.9224562644958496,
      "learning_rate": 7.027027027027028e-06,
      "loss": 0.2395,
      "step": 105
    },
    {
      "epoch": 0.31407407407407406,
      "grad_norm": 1.2403017282485962,
      "learning_rate": 6.996996996996997e-06,
      "loss": 0.1241,
      "step": 106
    },
    {
      "epoch": 0.31703703703703706,
      "grad_norm": 1.642490267753601,
      "learning_rate": 6.966966966966967e-06,
      "loss": 0.1328,
      "step": 107
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.317170262336731,
      "learning_rate": 6.936936936936938e-06,
      "loss": 0.138,
      "step": 108
    },
    {
      "epoch": 0.32296296296296295,
      "grad_norm": 1.804448127746582,
      "learning_rate": 6.906906906906907e-06,
      "loss": 0.1851,
      "step": 109
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 1.5860779285430908,
      "learning_rate": 6.876876876876878e-06,
      "loss": 0.1702,
      "step": 110
    },
    {
      "epoch": 0.3288888888888889,
      "grad_norm": 1.9532153606414795,
      "learning_rate": 6.846846846846848e-06,
      "loss": 0.2166,
      "step": 111
    },
    {
      "epoch": 0.33185185185185184,
      "grad_norm": 1.447892665863037,
      "learning_rate": 6.816816816816817e-06,
      "loss": 0.1488,
      "step": 112
    },
    {
      "epoch": 0.3348148148148148,
      "grad_norm": 1.4653080701828003,
      "learning_rate": 6.786786786786788e-06,
      "loss": 0.1511,
      "step": 113
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 1.8791394233703613,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 0.1998,
      "step": 114
    },
    {
      "epoch": 0.34074074074074073,
      "grad_norm": 1.5998536348342896,
      "learning_rate": 6.726726726726728e-06,
      "loss": 0.151,
      "step": 115
    },
    {
      "epoch": 0.3437037037037037,
      "grad_norm": 2.376225709915161,
      "learning_rate": 6.696696696696697e-06,
      "loss": 0.2597,
      "step": 116
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 1.9098881483078003,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1543,
      "step": 117
    },
    {
      "epoch": 0.3496296296296296,
      "grad_norm": 1.9297055006027222,
      "learning_rate": 6.636636636636637e-06,
      "loss": 0.2076,
      "step": 118
    },
    {
      "epoch": 0.35259259259259257,
      "grad_norm": 1.8386934995651245,
      "learning_rate": 6.606606606606607e-06,
      "loss": 0.2081,
      "step": 119
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.5386666059494019,
      "learning_rate": 6.5765765765765775e-06,
      "loss": 0.1681,
      "step": 120
    },
    {
      "epoch": 0.3585185185185185,
      "grad_norm": 1.5739247798919678,
      "learning_rate": 6.546546546546547e-06,
      "loss": 0.1653,
      "step": 121
    },
    {
      "epoch": 0.36148148148148146,
      "grad_norm": 1.2610325813293457,
      "learning_rate": 6.516516516516517e-06,
      "loss": 0.1342,
      "step": 122
    },
    {
      "epoch": 0.36444444444444446,
      "grad_norm": 1.6013598442077637,
      "learning_rate": 6.486486486486487e-06,
      "loss": 0.146,
      "step": 123
    },
    {
      "epoch": 0.3674074074074074,
      "grad_norm": 2.0538859367370605,
      "learning_rate": 6.456456456456457e-06,
      "loss": 0.2546,
      "step": 124
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.7231699228286743,
      "learning_rate": 6.426426426426427e-06,
      "loss": 0.1573,
      "step": 125
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 1.9862395524978638,
      "learning_rate": 6.396396396396397e-06,
      "loss": 0.212,
      "step": 126
    },
    {
      "epoch": 0.3762962962962963,
      "grad_norm": 1.9520001411437988,
      "learning_rate": 6.366366366366366e-06,
      "loss": 0.1317,
      "step": 127
    },
    {
      "epoch": 0.37925925925925924,
      "grad_norm": 1.237856149673462,
      "learning_rate": 6.336336336336338e-06,
      "loss": 0.1061,
      "step": 128
    },
    {
      "epoch": 0.38222222222222224,
      "grad_norm": 1.6110222339630127,
      "learning_rate": 6.3063063063063065e-06,
      "loss": 0.1295,
      "step": 129
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 1.534177541732788,
      "learning_rate": 6.276276276276276e-06,
      "loss": 0.1125,
      "step": 130
    },
    {
      "epoch": 0.38814814814814813,
      "grad_norm": 1.8280926942825317,
      "learning_rate": 6.246246246246247e-06,
      "loss": 0.1864,
      "step": 131
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 1.446161150932312,
      "learning_rate": 6.2162162162162164e-06,
      "loss": 0.1453,
      "step": 132
    },
    {
      "epoch": 0.3940740740740741,
      "grad_norm": 1.9907567501068115,
      "learning_rate": 6.186186186186187e-06,
      "loss": 0.2072,
      "step": 133
    },
    {
      "epoch": 0.397037037037037,
      "grad_norm": 2.0564229488372803,
      "learning_rate": 6.156156156156157e-06,
      "loss": 0.1981,
      "step": 134
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.549771785736084,
      "learning_rate": 6.126126126126126e-06,
      "loss": 0.1605,
      "step": 135
    },
    {
      "epoch": 0.40296296296296297,
      "grad_norm": 1.7392505407333374,
      "learning_rate": 6.096096096096097e-06,
      "loss": 0.1246,
      "step": 136
    },
    {
      "epoch": 0.4059259259259259,
      "grad_norm": 1.1892446279525757,
      "learning_rate": 6.066066066066067e-06,
      "loss": 0.0881,
      "step": 137
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 1.7165716886520386,
      "learning_rate": 6.036036036036037e-06,
      "loss": 0.1457,
      "step": 138
    },
    {
      "epoch": 0.41185185185185186,
      "grad_norm": 1.6729187965393066,
      "learning_rate": 6.006006006006007e-06,
      "loss": 0.1616,
      "step": 139
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 2.1714892387390137,
      "learning_rate": 5.975975975975976e-06,
      "loss": 0.2431,
      "step": 140
    },
    {
      "epoch": 0.4177777777777778,
      "grad_norm": 1.7493237257003784,
      "learning_rate": 5.945945945945947e-06,
      "loss": 0.1969,
      "step": 141
    },
    {
      "epoch": 0.42074074074074075,
      "grad_norm": 1.335331916809082,
      "learning_rate": 5.915915915915916e-06,
      "loss": 0.1187,
      "step": 142
    },
    {
      "epoch": 0.4237037037037037,
      "grad_norm": 1.7979439496994019,
      "learning_rate": 5.885885885885886e-06,
      "loss": 0.208,
      "step": 143
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 1.6909199953079224,
      "learning_rate": 5.855855855855856e-06,
      "loss": 0.1678,
      "step": 144
    },
    {
      "epoch": 0.42962962962962964,
      "grad_norm": 1.7193958759307861,
      "learning_rate": 5.825825825825826e-06,
      "loss": 0.1286,
      "step": 145
    },
    {
      "epoch": 0.4325925925925926,
      "grad_norm": 1.172631025314331,
      "learning_rate": 5.7957957957957965e-06,
      "loss": 0.0884,
      "step": 146
    },
    {
      "epoch": 0.43555555555555553,
      "grad_norm": 1.5364516973495483,
      "learning_rate": 5.765765765765766e-06,
      "loss": 0.1293,
      "step": 147
    },
    {
      "epoch": 0.43851851851851853,
      "grad_norm": 1.5921229124069214,
      "learning_rate": 5.735735735735736e-06,
      "loss": 0.1601,
      "step": 148
    },
    {
      "epoch": 0.4414814814814815,
      "grad_norm": 1.6460239887237549,
      "learning_rate": 5.7057057057057065e-06,
      "loss": 0.1611,
      "step": 149
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.8740227222442627,
      "learning_rate": 5.675675675675676e-06,
      "loss": 0.204,
      "step": 150
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 0.14475242793560028,
      "eval_runtime": 34.2625,
      "eval_samples_per_second": 17.512,
      "eval_steps_per_second": 8.756,
      "step": 150
    },
    {
      "epoch": 0.4474074074074074,
      "grad_norm": 2.7496047019958496,
      "learning_rate": 5.645645645645647e-06,
      "loss": 0.2191,
      "step": 151
    },
    {
      "epoch": 0.45037037037037037,
      "grad_norm": 1.2643390893936157,
      "learning_rate": 5.615615615615616e-06,
      "loss": 0.1174,
      "step": 152
    },
    {
      "epoch": 0.4533333333333333,
      "grad_norm": 1.740463376045227,
      "learning_rate": 5.585585585585585e-06,
      "loss": 0.1446,
      "step": 153
    },
    {
      "epoch": 0.4562962962962963,
      "grad_norm": 1.8941044807434082,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.1689,
      "step": 154
    },
    {
      "epoch": 0.45925925925925926,
      "grad_norm": 1.1730859279632568,
      "learning_rate": 5.5255255255255255e-06,
      "loss": 0.0916,
      "step": 155
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.85221266746521,
      "learning_rate": 5.495495495495496e-06,
      "loss": 0.0401,
      "step": 156
    },
    {
      "epoch": 0.4651851851851852,
      "grad_norm": 1.9675599336624146,
      "learning_rate": 5.465465465465466e-06,
      "loss": 0.1848,
      "step": 157
    },
    {
      "epoch": 0.46814814814814815,
      "grad_norm": 1.3493690490722656,
      "learning_rate": 5.4354354354354355e-06,
      "loss": 0.1318,
      "step": 158
    },
    {
      "epoch": 0.4711111111111111,
      "grad_norm": 1.7957578897476196,
      "learning_rate": 5.405405405405406e-06,
      "loss": 0.1866,
      "step": 159
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.4094411134719849,
      "learning_rate": 5.375375375375376e-06,
      "loss": 0.1045,
      "step": 160
    },
    {
      "epoch": 0.47703703703703704,
      "grad_norm": 1.7062647342681885,
      "learning_rate": 5.345345345345346e-06,
      "loss": 0.1644,
      "step": 161
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.3317080736160278,
      "learning_rate": 5.315315315315316e-06,
      "loss": 0.1033,
      "step": 162
    },
    {
      "epoch": 0.482962962962963,
      "grad_norm": 1.5942299365997314,
      "learning_rate": 5.285285285285286e-06,
      "loss": 0.1493,
      "step": 163
    },
    {
      "epoch": 0.48592592592592593,
      "grad_norm": 1.4245496988296509,
      "learning_rate": 5.255255255255256e-06,
      "loss": 0.0946,
      "step": 164
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 1.7023518085479736,
      "learning_rate": 5.225225225225226e-06,
      "loss": 0.168,
      "step": 165
    },
    {
      "epoch": 0.4918518518518519,
      "grad_norm": 1.4187322854995728,
      "learning_rate": 5.195195195195195e-06,
      "loss": 0.1143,
      "step": 166
    },
    {
      "epoch": 0.4948148148148148,
      "grad_norm": 1.6067007780075073,
      "learning_rate": 5.165165165165165e-06,
      "loss": 0.1301,
      "step": 167
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 2.2152934074401855,
      "learning_rate": 5.135135135135135e-06,
      "loss": 0.2485,
      "step": 168
    },
    {
      "epoch": 0.5007407407407407,
      "grad_norm": 1.3675384521484375,
      "learning_rate": 5.105105105105106e-06,
      "loss": 0.1319,
      "step": 169
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 1.805308222770691,
      "learning_rate": 5.075075075075075e-06,
      "loss": 0.1907,
      "step": 170
    },
    {
      "epoch": 0.5066666666666667,
      "grad_norm": 1.6984533071517944,
      "learning_rate": 5.045045045045045e-06,
      "loss": 0.1797,
      "step": 171
    },
    {
      "epoch": 0.5096296296296297,
      "grad_norm": 5.009469509124756,
      "learning_rate": 5.0150150150150156e-06,
      "loss": 0.2013,
      "step": 172
    },
    {
      "epoch": 0.5125925925925926,
      "grad_norm": 1.6677497625350952,
      "learning_rate": 4.984984984984985e-06,
      "loss": 0.1836,
      "step": 173
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 1.8382097482681274,
      "learning_rate": 4.954954954954955e-06,
      "loss": 0.168,
      "step": 174
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.7375690937042236,
      "learning_rate": 4.9249249249249255e-06,
      "loss": 0.1575,
      "step": 175
    },
    {
      "epoch": 0.5214814814814814,
      "grad_norm": 1.7565760612487793,
      "learning_rate": 4.894894894894895e-06,
      "loss": 0.1735,
      "step": 176
    },
    {
      "epoch": 0.5244444444444445,
      "grad_norm": 1.3788102865219116,
      "learning_rate": 4.864864864864866e-06,
      "loss": 0.1089,
      "step": 177
    },
    {
      "epoch": 0.5274074074074074,
      "grad_norm": 1.752877116203308,
      "learning_rate": 4.8348348348348355e-06,
      "loss": 0.1519,
      "step": 178
    },
    {
      "epoch": 0.5303703703703704,
      "grad_norm": 1.6364109516143799,
      "learning_rate": 4.804804804804805e-06,
      "loss": 0.1653,
      "step": 179
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.351488709449768,
      "learning_rate": 4.774774774774775e-06,
      "loss": 0.1328,
      "step": 180
    },
    {
      "epoch": 0.5362962962962963,
      "grad_norm": 1.332228660583496,
      "learning_rate": 4.7447447447447454e-06,
      "loss": 0.1319,
      "step": 181
    },
    {
      "epoch": 0.5392592592592592,
      "grad_norm": 1.8058677911758423,
      "learning_rate": 4.714714714714715e-06,
      "loss": 0.1465,
      "step": 182
    },
    {
      "epoch": 0.5422222222222223,
      "grad_norm": 1.4140504598617554,
      "learning_rate": 4.684684684684685e-06,
      "loss": 0.1112,
      "step": 183
    },
    {
      "epoch": 0.5451851851851852,
      "grad_norm": 1.766536831855774,
      "learning_rate": 4.654654654654655e-06,
      "loss": 0.2038,
      "step": 184
    },
    {
      "epoch": 0.5481481481481482,
      "grad_norm": 1.3968453407287598,
      "learning_rate": 4.624624624624625e-06,
      "loss": 0.1047,
      "step": 185
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 1.8765852451324463,
      "learning_rate": 4.594594594594596e-06,
      "loss": 0.1807,
      "step": 186
    },
    {
      "epoch": 0.554074074074074,
      "grad_norm": 2.030606269836426,
      "learning_rate": 4.5645645645645645e-06,
      "loss": 0.2144,
      "step": 187
    },
    {
      "epoch": 0.557037037037037,
      "grad_norm": 1.326214075088501,
      "learning_rate": 4.534534534534535e-06,
      "loss": 0.1435,
      "step": 188
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.719833493232727,
      "learning_rate": 4.504504504504505e-06,
      "loss": 0.1758,
      "step": 189
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 1.7908629179000854,
      "learning_rate": 4.474474474474475e-06,
      "loss": 0.1629,
      "step": 190
    },
    {
      "epoch": 0.5659259259259259,
      "grad_norm": 1.4920756816864014,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.1571,
      "step": 191
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 1.3115179538726807,
      "learning_rate": 4.414414414414415e-06,
      "loss": 0.108,
      "step": 192
    },
    {
      "epoch": 0.5718518518518518,
      "grad_norm": 1.6319407224655151,
      "learning_rate": 4.384384384384384e-06,
      "loss": 0.1952,
      "step": 193
    },
    {
      "epoch": 0.5748148148148148,
      "grad_norm": 1.6394829750061035,
      "learning_rate": 4.354354354354355e-06,
      "loss": 0.1878,
      "step": 194
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 1.522870421409607,
      "learning_rate": 4.324324324324325e-06,
      "loss": 0.1236,
      "step": 195
    },
    {
      "epoch": 0.5807407407407408,
      "grad_norm": 1.42640221118927,
      "learning_rate": 4.294294294294294e-06,
      "loss": 0.1369,
      "step": 196
    },
    {
      "epoch": 0.5837037037037037,
      "grad_norm": 1.57705557346344,
      "learning_rate": 4.264264264264265e-06,
      "loss": 0.1624,
      "step": 197
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 1.5470460653305054,
      "learning_rate": 4.234234234234235e-06,
      "loss": 0.1587,
      "step": 198
    },
    {
      "epoch": 0.5896296296296296,
      "grad_norm": 1.5842163562774658,
      "learning_rate": 4.204204204204204e-06,
      "loss": 0.1365,
      "step": 199
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.403318166732788,
      "learning_rate": 4.174174174174174e-06,
      "loss": 0.1186,
      "step": 200
    },
    {
      "epoch": 0.5925925925925926,
      "eval_loss": 0.14084728062152863,
      "eval_runtime": 33.9865,
      "eval_samples_per_second": 17.654,
      "eval_steps_per_second": 8.827,
      "step": 200
    },
    {
      "epoch": 0.5955555555555555,
      "grad_norm": 1.6167008876800537,
      "learning_rate": 4.1441441441441446e-06,
      "loss": 0.1896,
      "step": 201
    },
    {
      "epoch": 0.5985185185185186,
      "grad_norm": 1.6228059530258179,
      "learning_rate": 4.114114114114114e-06,
      "loss": 0.1482,
      "step": 202
    },
    {
      "epoch": 0.6014814814814815,
      "grad_norm": 1.2341673374176025,
      "learning_rate": 4.084084084084085e-06,
      "loss": 0.1026,
      "step": 203
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 2.117696762084961,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 0.2104,
      "step": 204
    },
    {
      "epoch": 0.6074074074074074,
      "grad_norm": 1.814539909362793,
      "learning_rate": 4.024024024024024e-06,
      "loss": 0.1683,
      "step": 205
    },
    {
      "epoch": 0.6103703703703703,
      "grad_norm": 1.158748984336853,
      "learning_rate": 3.993993993993994e-06,
      "loss": 0.1141,
      "step": 206
    },
    {
      "epoch": 0.6133333333333333,
      "grad_norm": 1.3233363628387451,
      "learning_rate": 3.9639639639639645e-06,
      "loss": 0.0829,
      "step": 207
    },
    {
      "epoch": 0.6162962962962963,
      "grad_norm": 1.2880805730819702,
      "learning_rate": 3.933933933933934e-06,
      "loss": 0.1131,
      "step": 208
    },
    {
      "epoch": 0.6192592592592593,
      "grad_norm": 1.4403434991836548,
      "learning_rate": 3.903903903903904e-06,
      "loss": 0.1535,
      "step": 209
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 1.690941572189331,
      "learning_rate": 3.8738738738738744e-06,
      "loss": 0.1689,
      "step": 210
    },
    {
      "epoch": 0.6251851851851852,
      "grad_norm": 1.5820523500442505,
      "learning_rate": 3.843843843843844e-06,
      "loss": 0.1661,
      "step": 211
    },
    {
      "epoch": 0.6281481481481481,
      "grad_norm": 1.5057729482650757,
      "learning_rate": 3.8138138138138143e-06,
      "loss": 0.1456,
      "step": 212
    },
    {
      "epoch": 0.6311111111111111,
      "grad_norm": 1.7173206806182861,
      "learning_rate": 3.7837837837837844e-06,
      "loss": 0.1639,
      "step": 213
    },
    {
      "epoch": 0.6340740740740741,
      "grad_norm": 1.3639731407165527,
      "learning_rate": 3.7537537537537537e-06,
      "loss": 0.1296,
      "step": 214
    },
    {
      "epoch": 0.6370370370370371,
      "grad_norm": 1.4805443286895752,
      "learning_rate": 3.723723723723724e-06,
      "loss": 0.1074,
      "step": 215
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.4697860479354858,
      "learning_rate": 3.693693693693694e-06,
      "loss": 0.1351,
      "step": 216
    },
    {
      "epoch": 0.642962962962963,
      "grad_norm": 1.4628665447235107,
      "learning_rate": 3.663663663663664e-06,
      "loss": 0.1332,
      "step": 217
    },
    {
      "epoch": 0.6459259259259259,
      "grad_norm": 1.3456974029541016,
      "learning_rate": 3.633633633633634e-06,
      "loss": 0.1002,
      "step": 218
    },
    {
      "epoch": 0.6488888888888888,
      "grad_norm": 1.984555721282959,
      "learning_rate": 3.603603603603604e-06,
      "loss": 0.1932,
      "step": 219
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 1.488616704940796,
      "learning_rate": 3.573573573573574e-06,
      "loss": 0.1324,
      "step": 220
    },
    {
      "epoch": 0.6548148148148148,
      "grad_norm": 1.1784634590148926,
      "learning_rate": 3.5435435435435437e-06,
      "loss": 0.1372,
      "step": 221
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 1.5055599212646484,
      "learning_rate": 3.513513513513514e-06,
      "loss": 0.1249,
      "step": 222
    },
    {
      "epoch": 0.6607407407407407,
      "grad_norm": 1.5000940561294556,
      "learning_rate": 3.4834834834834835e-06,
      "loss": 0.1251,
      "step": 223
    },
    {
      "epoch": 0.6637037037037037,
      "grad_norm": 1.4260419607162476,
      "learning_rate": 3.4534534534534537e-06,
      "loss": 0.0938,
      "step": 224
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.3946462869644165,
      "learning_rate": 3.423423423423424e-06,
      "loss": 0.1011,
      "step": 225
    },
    {
      "epoch": 0.6696296296296296,
      "grad_norm": 1.6293145418167114,
      "learning_rate": 3.393393393393394e-06,
      "loss": 0.1187,
      "step": 226
    },
    {
      "epoch": 0.6725925925925926,
      "grad_norm": 1.781611442565918,
      "learning_rate": 3.363363363363364e-06,
      "loss": 0.1944,
      "step": 227
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 1.1268196105957031,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0873,
      "step": 228
    },
    {
      "epoch": 0.6785185185185185,
      "grad_norm": 1.1559783220291138,
      "learning_rate": 3.3033033033033035e-06,
      "loss": 0.0824,
      "step": 229
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 1.1809353828430176,
      "learning_rate": 3.2732732732732736e-06,
      "loss": 0.1087,
      "step": 230
    },
    {
      "epoch": 0.6844444444444444,
      "grad_norm": 2.1987335681915283,
      "learning_rate": 3.2432432432432437e-06,
      "loss": 0.1974,
      "step": 231
    },
    {
      "epoch": 0.6874074074074074,
      "grad_norm": 1.6860929727554321,
      "learning_rate": 3.2132132132132134e-06,
      "loss": 0.1464,
      "step": 232
    },
    {
      "epoch": 0.6903703703703704,
      "grad_norm": 1.423671007156372,
      "learning_rate": 3.183183183183183e-06,
      "loss": 0.1197,
      "step": 233
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 1.3567653894424438,
      "learning_rate": 3.1531531531531532e-06,
      "loss": 0.1028,
      "step": 234
    },
    {
      "epoch": 0.6962962962962963,
      "grad_norm": 1.8558002710342407,
      "learning_rate": 3.1231231231231234e-06,
      "loss": 0.1377,
      "step": 235
    },
    {
      "epoch": 0.6992592592592592,
      "grad_norm": 1.9765708446502686,
      "learning_rate": 3.0930930930930935e-06,
      "loss": 0.1683,
      "step": 236
    },
    {
      "epoch": 0.7022222222222222,
      "grad_norm": 1.6394944190979004,
      "learning_rate": 3.063063063063063e-06,
      "loss": 0.1567,
      "step": 237
    },
    {
      "epoch": 0.7051851851851851,
      "grad_norm": 1.7090219259262085,
      "learning_rate": 3.0330330330330333e-06,
      "loss": 0.1413,
      "step": 238
    },
    {
      "epoch": 0.7081481481481482,
      "grad_norm": 1.329350471496582,
      "learning_rate": 3.0030030030030034e-06,
      "loss": 0.1056,
      "step": 239
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.749627947807312,
      "learning_rate": 2.9729729729729736e-06,
      "loss": 0.1677,
      "step": 240
    },
    {
      "epoch": 0.7140740740740741,
      "grad_norm": 1.5342552661895752,
      "learning_rate": 2.942942942942943e-06,
      "loss": 0.1507,
      "step": 241
    },
    {
      "epoch": 0.717037037037037,
      "grad_norm": 1.544425129890442,
      "learning_rate": 2.912912912912913e-06,
      "loss": 0.1319,
      "step": 242
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.8567659854888916,
      "learning_rate": 2.882882882882883e-06,
      "loss": 0.1925,
      "step": 243
    },
    {
      "epoch": 0.7229629629629629,
      "grad_norm": 1.3521531820297241,
      "learning_rate": 2.8528528528528532e-06,
      "loss": 0.1109,
      "step": 244
    },
    {
      "epoch": 0.725925925925926,
      "grad_norm": 1.265822172164917,
      "learning_rate": 2.8228228228228234e-06,
      "loss": 0.0859,
      "step": 245
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 1.8512970209121704,
      "learning_rate": 2.7927927927927926e-06,
      "loss": 0.1774,
      "step": 246
    },
    {
      "epoch": 0.7318518518518519,
      "grad_norm": 1.3815727233886719,
      "learning_rate": 2.7627627627627628e-06,
      "loss": 0.0974,
      "step": 247
    },
    {
      "epoch": 0.7348148148148148,
      "grad_norm": 1.4234230518341064,
      "learning_rate": 2.732732732732733e-06,
      "loss": 0.1094,
      "step": 248
    },
    {
      "epoch": 0.7377777777777778,
      "grad_norm": 1.7458223104476929,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.1692,
      "step": 249
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.7223281860351562,
      "learning_rate": 2.672672672672673e-06,
      "loss": 0.1644,
      "step": 250
    },
    {
      "epoch": 0.7407407407407407,
      "eval_loss": 0.13829512894153595,
      "eval_runtime": 33.8605,
      "eval_samples_per_second": 17.72,
      "eval_steps_per_second": 8.86,
      "step": 250
    },
    {
      "epoch": 0.7437037037037038,
      "grad_norm": 1.5829962491989136,
      "learning_rate": 2.642642642642643e-06,
      "loss": 0.1372,
      "step": 251
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 1.3847887516021729,
      "learning_rate": 2.612612612612613e-06,
      "loss": 0.1214,
      "step": 252
    },
    {
      "epoch": 0.7496296296296296,
      "grad_norm": 1.9174615144729614,
      "learning_rate": 2.5825825825825827e-06,
      "loss": 0.1687,
      "step": 253
    },
    {
      "epoch": 0.7525925925925926,
      "grad_norm": 1.5940123796463013,
      "learning_rate": 2.552552552552553e-06,
      "loss": 0.1281,
      "step": 254
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 1.596480131149292,
      "learning_rate": 2.5225225225225225e-06,
      "loss": 0.1467,
      "step": 255
    },
    {
      "epoch": 0.7585185185185185,
      "grad_norm": 1.696172833442688,
      "learning_rate": 2.4924924924924926e-06,
      "loss": 0.1552,
      "step": 256
    },
    {
      "epoch": 0.7614814814814815,
      "grad_norm": 1.656582236289978,
      "learning_rate": 2.4624624624624628e-06,
      "loss": 0.1833,
      "step": 257
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 1.5243239402770996,
      "learning_rate": 2.432432432432433e-06,
      "loss": 0.1567,
      "step": 258
    },
    {
      "epoch": 0.7674074074074074,
      "grad_norm": 1.686184048652649,
      "learning_rate": 2.4024024024024026e-06,
      "loss": 0.167,
      "step": 259
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 1.6084699630737305,
      "learning_rate": 2.3723723723723727e-06,
      "loss": 0.1438,
      "step": 260
    },
    {
      "epoch": 0.7733333333333333,
      "grad_norm": 1.8537253141403198,
      "learning_rate": 2.3423423423423424e-06,
      "loss": 0.1844,
      "step": 261
    },
    {
      "epoch": 0.7762962962962963,
      "grad_norm": 2.1190059185028076,
      "learning_rate": 2.3123123123123125e-06,
      "loss": 0.1874,
      "step": 262
    },
    {
      "epoch": 0.7792592592592592,
      "grad_norm": 2.048433303833008,
      "learning_rate": 2.2822822822822822e-06,
      "loss": 0.211,
      "step": 263
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 1.3936806917190552,
      "learning_rate": 2.2522522522522524e-06,
      "loss": 0.099,
      "step": 264
    },
    {
      "epoch": 0.7851851851851852,
      "grad_norm": 1.4599746465682983,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.1031,
      "step": 265
    },
    {
      "epoch": 0.7881481481481482,
      "grad_norm": 1.2484382390975952,
      "learning_rate": 2.192192192192192e-06,
      "loss": 0.1074,
      "step": 266
    },
    {
      "epoch": 0.7911111111111111,
      "grad_norm": 1.8577090501785278,
      "learning_rate": 2.1621621621621623e-06,
      "loss": 0.1739,
      "step": 267
    },
    {
      "epoch": 0.794074074074074,
      "grad_norm": 1.6757045984268188,
      "learning_rate": 2.1321321321321325e-06,
      "loss": 0.1267,
      "step": 268
    },
    {
      "epoch": 0.797037037037037,
      "grad_norm": 2.0108957290649414,
      "learning_rate": 2.102102102102102e-06,
      "loss": 0.1675,
      "step": 269
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.3510375022888184,
      "learning_rate": 2.0720720720720723e-06,
      "loss": 0.2393,
      "step": 270
    },
    {
      "epoch": 0.802962962962963,
      "grad_norm": 1.5452089309692383,
      "learning_rate": 2.0420420420420424e-06,
      "loss": 0.1253,
      "step": 271
    },
    {
      "epoch": 0.8059259259259259,
      "grad_norm": 2.1613359451293945,
      "learning_rate": 2.012012012012012e-06,
      "loss": 0.1629,
      "step": 272
    },
    {
      "epoch": 0.8088888888888889,
      "grad_norm": 4.293635845184326,
      "learning_rate": 1.9819819819819822e-06,
      "loss": 0.2124,
      "step": 273
    },
    {
      "epoch": 0.8118518518518518,
      "grad_norm": 1.048204779624939,
      "learning_rate": 1.951951951951952e-06,
      "loss": 0.0747,
      "step": 274
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 1.699888825416565,
      "learning_rate": 1.921921921921922e-06,
      "loss": 0.182,
      "step": 275
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 2.0971546173095703,
      "learning_rate": 1.8918918918918922e-06,
      "loss": 0.2049,
      "step": 276
    },
    {
      "epoch": 0.8207407407407408,
      "grad_norm": 1.6869533061981201,
      "learning_rate": 1.861861861861862e-06,
      "loss": 0.1511,
      "step": 277
    },
    {
      "epoch": 0.8237037037037037,
      "grad_norm": 1.1655305624008179,
      "learning_rate": 1.831831831831832e-06,
      "loss": 0.0838,
      "step": 278
    },
    {
      "epoch": 0.8266666666666667,
      "grad_norm": 1.5409475564956665,
      "learning_rate": 1.801801801801802e-06,
      "loss": 0.1271,
      "step": 279
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 1.6859043836593628,
      "learning_rate": 1.7717717717717719e-06,
      "loss": 0.1765,
      "step": 280
    },
    {
      "epoch": 0.8325925925925926,
      "grad_norm": 1.1222418546676636,
      "learning_rate": 1.7417417417417418e-06,
      "loss": 0.085,
      "step": 281
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 2.0395545959472656,
      "learning_rate": 1.711711711711712e-06,
      "loss": 0.1778,
      "step": 282
    },
    {
      "epoch": 0.8385185185185186,
      "grad_norm": 1.2556045055389404,
      "learning_rate": 1.681681681681682e-06,
      "loss": 0.1107,
      "step": 283
    },
    {
      "epoch": 0.8414814814814815,
      "grad_norm": 1.6442242860794067,
      "learning_rate": 1.6516516516516517e-06,
      "loss": 0.1388,
      "step": 284
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 1.7732895612716675,
      "learning_rate": 1.6216216216216219e-06,
      "loss": 0.1132,
      "step": 285
    },
    {
      "epoch": 0.8474074074074074,
      "grad_norm": 1.2564475536346436,
      "learning_rate": 1.5915915915915916e-06,
      "loss": 0.0973,
      "step": 286
    },
    {
      "epoch": 0.8503703703703703,
      "grad_norm": 1.3318207263946533,
      "learning_rate": 1.5615615615615617e-06,
      "loss": 0.1025,
      "step": 287
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 1.3029829263687134,
      "learning_rate": 1.5315315315315316e-06,
      "loss": 0.1028,
      "step": 288
    },
    {
      "epoch": 0.8562962962962963,
      "grad_norm": 1.5696513652801514,
      "learning_rate": 1.5015015015015017e-06,
      "loss": 0.1389,
      "step": 289
    },
    {
      "epoch": 0.8592592592592593,
      "grad_norm": 0.9517642855644226,
      "learning_rate": 1.4714714714714714e-06,
      "loss": 0.0652,
      "step": 290
    },
    {
      "epoch": 0.8622222222222222,
      "grad_norm": 1.403417706489563,
      "learning_rate": 1.4414414414414416e-06,
      "loss": 0.1059,
      "step": 291
    },
    {
      "epoch": 0.8651851851851852,
      "grad_norm": 1.3065266609191895,
      "learning_rate": 1.4114114114114117e-06,
      "loss": 0.0961,
      "step": 292
    },
    {
      "epoch": 0.8681481481481481,
      "grad_norm": 1.44899320602417,
      "learning_rate": 1.3813813813813814e-06,
      "loss": 0.0941,
      "step": 293
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 1.9340436458587646,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 0.2028,
      "step": 294
    },
    {
      "epoch": 0.8740740740740741,
      "grad_norm": 1.1584372520446777,
      "learning_rate": 1.3213213213213214e-06,
      "loss": 0.092,
      "step": 295
    },
    {
      "epoch": 0.8770370370370371,
      "grad_norm": 1.6651279926300049,
      "learning_rate": 1.2912912912912913e-06,
      "loss": 0.1352,
      "step": 296
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.1857194900512695,
      "learning_rate": 1.2612612612612613e-06,
      "loss": 0.0945,
      "step": 297
    },
    {
      "epoch": 0.882962962962963,
      "grad_norm": 1.723954200744629,
      "learning_rate": 1.2312312312312314e-06,
      "loss": 0.1584,
      "step": 298
    },
    {
      "epoch": 0.8859259259259259,
      "grad_norm": 1.3261058330535889,
      "learning_rate": 1.2012012012012013e-06,
      "loss": 0.1128,
      "step": 299
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.422727346420288,
      "learning_rate": 1.1711711711711712e-06,
      "loss": 0.1043,
      "step": 300
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.13605371117591858,
      "eval_runtime": 33.9149,
      "eval_samples_per_second": 17.691,
      "eval_steps_per_second": 8.846,
      "step": 300
    },
    {
      "epoch": 0.8918518518518519,
      "grad_norm": 1.9120748043060303,
      "learning_rate": 1.1411411411411411e-06,
      "loss": 0.1597,
      "step": 301
    },
    {
      "epoch": 0.8948148148148148,
      "grad_norm": 1.813285231590271,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.1469,
      "step": 302
    },
    {
      "epoch": 0.8977777777777778,
      "grad_norm": 1.5811489820480347,
      "learning_rate": 1.0810810810810812e-06,
      "loss": 0.0924,
      "step": 303
    },
    {
      "epoch": 0.9007407407407407,
      "grad_norm": 1.667541265487671,
      "learning_rate": 1.051051051051051e-06,
      "loss": 0.1748,
      "step": 304
    },
    {
      "epoch": 0.9037037037037037,
      "grad_norm": 1.5224140882492065,
      "learning_rate": 1.0210210210210212e-06,
      "loss": 0.1087,
      "step": 305
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 1.9291738271713257,
      "learning_rate": 9.909909909909911e-07,
      "loss": 0.1194,
      "step": 306
    },
    {
      "epoch": 0.9096296296296297,
      "grad_norm": 1.0466184616088867,
      "learning_rate": 9.60960960960961e-07,
      "loss": 0.0896,
      "step": 307
    },
    {
      "epoch": 0.9125925925925926,
      "grad_norm": 1.743699073791504,
      "learning_rate": 9.30930930930931e-07,
      "loss": 0.1759,
      "step": 308
    },
    {
      "epoch": 0.9155555555555556,
      "grad_norm": 1.8747113943099976,
      "learning_rate": 9.00900900900901e-07,
      "loss": 0.1875,
      "step": 309
    },
    {
      "epoch": 0.9185185185185185,
      "grad_norm": 1.5167481899261475,
      "learning_rate": 8.708708708708709e-07,
      "loss": 0.1307,
      "step": 310
    },
    {
      "epoch": 0.9214814814814815,
      "grad_norm": 1.0149823427200317,
      "learning_rate": 8.40840840840841e-07,
      "loss": 0.0799,
      "step": 311
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 1.2748384475708008,
      "learning_rate": 8.108108108108109e-07,
      "loss": 0.0977,
      "step": 312
    },
    {
      "epoch": 0.9274074074074075,
      "grad_norm": 1.7352746725082397,
      "learning_rate": 7.807807807807808e-07,
      "loss": 0.1702,
      "step": 313
    },
    {
      "epoch": 0.9303703703703704,
      "grad_norm": 1.2555989027023315,
      "learning_rate": 7.507507507507509e-07,
      "loss": 0.0839,
      "step": 314
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 1.6147124767303467,
      "learning_rate": 7.207207207207208e-07,
      "loss": 0.1351,
      "step": 315
    },
    {
      "epoch": 0.9362962962962963,
      "grad_norm": 1.5490890741348267,
      "learning_rate": 6.906906906906907e-07,
      "loss": 0.1715,
      "step": 316
    },
    {
      "epoch": 0.9392592592592592,
      "grad_norm": 1.5066777467727661,
      "learning_rate": 6.606606606606607e-07,
      "loss": 0.1223,
      "step": 317
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 1.5662552118301392,
      "learning_rate": 6.306306306306306e-07,
      "loss": 0.1258,
      "step": 318
    },
    {
      "epoch": 0.9451851851851852,
      "grad_norm": 1.3202425241470337,
      "learning_rate": 6.006006006006006e-07,
      "loss": 0.1263,
      "step": 319
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 1.4874892234802246,
      "learning_rate": 5.705705705705706e-07,
      "loss": 0.116,
      "step": 320
    },
    {
      "epoch": 0.9511111111111111,
      "grad_norm": 1.4346815347671509,
      "learning_rate": 5.405405405405406e-07,
      "loss": 0.1245,
      "step": 321
    },
    {
      "epoch": 0.9540740740740741,
      "grad_norm": 1.4638997316360474,
      "learning_rate": 5.105105105105106e-07,
      "loss": 0.1401,
      "step": 322
    },
    {
      "epoch": 0.957037037037037,
      "grad_norm": 1.3077244758605957,
      "learning_rate": 4.804804804804805e-07,
      "loss": 0.1244,
      "step": 323
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.4237442016601562,
      "learning_rate": 4.504504504504505e-07,
      "loss": 0.0925,
      "step": 324
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 1.123674750328064,
      "learning_rate": 4.204204204204205e-07,
      "loss": 0.0865,
      "step": 325
    },
    {
      "epoch": 0.965925925925926,
      "grad_norm": 1.719851016998291,
      "learning_rate": 3.903903903903904e-07,
      "loss": 0.162,
      "step": 326
    },
    {
      "epoch": 0.9688888888888889,
      "grad_norm": 1.129430890083313,
      "learning_rate": 3.603603603603604e-07,
      "loss": 0.0854,
      "step": 327
    },
    {
      "epoch": 0.9718518518518519,
      "grad_norm": 1.782344937324524,
      "learning_rate": 3.3033033033033036e-07,
      "loss": 0.1602,
      "step": 328
    },
    {
      "epoch": 0.9748148148148148,
      "grad_norm": 1.7161186933517456,
      "learning_rate": 3.003003003003003e-07,
      "loss": 0.139,
      "step": 329
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.4477684497833252,
      "learning_rate": 2.702702702702703e-07,
      "loss": 0.0875,
      "step": 330
    },
    {
      "epoch": 0.9807407407407407,
      "grad_norm": 1.8811054229736328,
      "learning_rate": 2.4024024024024026e-07,
      "loss": 0.1888,
      "step": 331
    },
    {
      "epoch": 0.9837037037037037,
      "grad_norm": 1.2534470558166504,
      "learning_rate": 2.1021021021021025e-07,
      "loss": 0.1338,
      "step": 332
    },
    {
      "epoch": 0.9866666666666667,
      "grad_norm": 1.8485772609710693,
      "learning_rate": 1.801801801801802e-07,
      "loss": 0.1179,
      "step": 333
    },
    {
      "epoch": 0.9896296296296296,
      "grad_norm": 1.163386583328247,
      "learning_rate": 1.5015015015015016e-07,
      "loss": 0.093,
      "step": 334
    },
    {
      "epoch": 0.9925925925925926,
      "grad_norm": 1.8233240842819214,
      "learning_rate": 1.2012012012012013e-07,
      "loss": 0.1585,
      "step": 335
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 1.8938701152801514,
      "learning_rate": 9.00900900900901e-08,
      "loss": 0.1696,
      "step": 336
    },
    {
      "epoch": 0.9985185185185185,
      "grad_norm": 1.6436508893966675,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.1376,
      "step": 337
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.5030550956726074,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.1535,
      "step": 338
    }
  ],
  "logging_steps": 1,
  "max_steps": 338,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.890692118619136e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}