{
  "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": 26.44416046142578,
      "learning_rate": 0.0,
      "loss": 1.3597,
      "step": 1
    },
    {
      "epoch": 0.005925925925925926,
      "grad_norm": 28.08013153076172,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.5545,
      "step": 2
    },
    {
      "epoch": 0.008888888888888889,
      "grad_norm": 23.91691780090332,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3591,
      "step": 3
    },
    {
      "epoch": 0.011851851851851851,
      "grad_norm": 19.01311492919922,
      "learning_rate": 6e-06,
      "loss": 0.9705,
      "step": 4
    },
    {
      "epoch": 0.014814814814814815,
      "grad_norm": 14.860604286193848,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7355,
      "step": 5
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 11.52336311340332,
      "learning_rate": 1e-05,
      "loss": 0.7603,
      "step": 6
    },
    {
      "epoch": 0.02074074074074074,
      "grad_norm": 8.616632461547852,
      "learning_rate": 9.96996996996997e-06,
      "loss": 0.5912,
      "step": 7
    },
    {
      "epoch": 0.023703703703703703,
      "grad_norm": 5.334316253662109,
      "learning_rate": 9.93993993993994e-06,
      "loss": 0.4196,
      "step": 8
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 4.436995983123779,
      "learning_rate": 9.90990990990991e-06,
      "loss": 0.4224,
      "step": 9
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 4.784731388092041,
      "learning_rate": 9.879879879879881e-06,
      "loss": 0.467,
      "step": 10
    },
    {
      "epoch": 0.03259259259259259,
      "grad_norm": 3.332075834274292,
      "learning_rate": 9.849849849849851e-06,
      "loss": 0.3298,
      "step": 11
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 3.727847099304199,
      "learning_rate": 9.81981981981982e-06,
      "loss": 0.4192,
      "step": 12
    },
    {
      "epoch": 0.03851851851851852,
      "grad_norm": 2.771514415740967,
      "learning_rate": 9.78978978978979e-06,
      "loss": 0.2594,
      "step": 13
    },
    {
      "epoch": 0.04148148148148148,
      "grad_norm": 3.6246445178985596,
      "learning_rate": 9.75975975975976e-06,
      "loss": 0.4158,
      "step": 14
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 2.8906850814819336,
      "learning_rate": 9.729729729729732e-06,
      "loss": 0.2859,
      "step": 15
    },
    {
      "epoch": 0.047407407407407405,
      "grad_norm": 3.2873337268829346,
      "learning_rate": 9.699699699699701e-06,
      "loss": 0.3402,
      "step": 16
    },
    {
      "epoch": 0.05037037037037037,
      "grad_norm": 3.2758312225341797,
      "learning_rate": 9.669669669669671e-06,
      "loss": 0.3357,
      "step": 17
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 2.9508113861083984,
      "learning_rate": 9.63963963963964e-06,
      "loss": 0.2085,
      "step": 18
    },
    {
      "epoch": 0.056296296296296296,
      "grad_norm": 3.4131903648376465,
      "learning_rate": 9.60960960960961e-06,
      "loss": 0.3073,
      "step": 19
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 3.453920602798462,
      "learning_rate": 9.57957957957958e-06,
      "loss": 0.3302,
      "step": 20
    },
    {
      "epoch": 0.06222222222222222,
      "grad_norm": 2.6370601654052734,
      "learning_rate": 9.54954954954955e-06,
      "loss": 0.1966,
      "step": 21
    },
    {
      "epoch": 0.06518518518518518,
      "grad_norm": 3.9872822761535645,
      "learning_rate": 9.51951951951952e-06,
      "loss": 0.3199,
      "step": 22
    },
    {
      "epoch": 0.06814814814814815,
      "grad_norm": 3.395547866821289,
      "learning_rate": 9.489489489489491e-06,
      "loss": 0.3266,
      "step": 23
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 3.6167054176330566,
      "learning_rate": 9.45945945945946e-06,
      "loss": 0.3396,
      "step": 24
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.9201512336730957,
      "learning_rate": 9.42942942942943e-06,
      "loss": 0.2085,
      "step": 25
    },
    {
      "epoch": 0.07703703703703704,
      "grad_norm": 3.313473701477051,
      "learning_rate": 9.3993993993994e-06,
      "loss": 0.273,
      "step": 26
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.8894965648651123,
      "learning_rate": 9.36936936936937e-06,
      "loss": 0.3202,
      "step": 27
    },
    {
      "epoch": 0.08296296296296296,
      "grad_norm": 3.1225433349609375,
      "learning_rate": 9.339339339339341e-06,
      "loss": 0.3266,
      "step": 28
    },
    {
      "epoch": 0.08592592592592592,
      "grad_norm": 2.905473470687866,
      "learning_rate": 9.30930930930931e-06,
      "loss": 0.2482,
      "step": 29
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 2.949242115020752,
      "learning_rate": 9.27927927927928e-06,
      "loss": 0.2173,
      "step": 30
    },
    {
      "epoch": 0.09185185185185185,
      "grad_norm": 2.3390250205993652,
      "learning_rate": 9.24924924924925e-06,
      "loss": 0.1552,
      "step": 31
    },
    {
      "epoch": 0.09481481481481481,
      "grad_norm": 1.7570362091064453,
      "learning_rate": 9.21921921921922e-06,
      "loss": 0.1014,
      "step": 32
    },
    {
      "epoch": 0.09777777777777778,
      "grad_norm": 2.382965087890625,
      "learning_rate": 9.189189189189191e-06,
      "loss": 0.1524,
      "step": 33
    },
    {
      "epoch": 0.10074074074074074,
      "grad_norm": 2.7648448944091797,
      "learning_rate": 9.15915915915916e-06,
      "loss": 0.2089,
      "step": 34
    },
    {
      "epoch": 0.1037037037037037,
      "grad_norm": 3.020594835281372,
      "learning_rate": 9.129129129129129e-06,
      "loss": 0.2803,
      "step": 35
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 2.8902881145477295,
      "learning_rate": 9.0990990990991e-06,
      "loss": 0.2031,
      "step": 36
    },
    {
      "epoch": 0.10962962962962963,
      "grad_norm": 3.1051557064056396,
      "learning_rate": 9.06906906906907e-06,
      "loss": 0.2589,
      "step": 37
    },
    {
      "epoch": 0.11259259259259259,
      "grad_norm": 2.8094022274017334,
      "learning_rate": 9.03903903903904e-06,
      "loss": 0.2376,
      "step": 38
    },
    {
      "epoch": 0.11555555555555555,
      "grad_norm": 2.272177219390869,
      "learning_rate": 9.00900900900901e-06,
      "loss": 0.1473,
      "step": 39
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 2.1578891277313232,
      "learning_rate": 8.97897897897898e-06,
      "loss": 0.1617,
      "step": 40
    },
    {
      "epoch": 0.12148148148148148,
      "grad_norm": 2.8987979888916016,
      "learning_rate": 8.94894894894895e-06,
      "loss": 0.22,
      "step": 41
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 3.255148410797119,
      "learning_rate": 8.91891891891892e-06,
      "loss": 0.285,
      "step": 42
    },
    {
      "epoch": 0.1274074074074074,
      "grad_norm": 2.061232805252075,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.1238,
      "step": 43
    },
    {
      "epoch": 0.13037037037037036,
      "grad_norm": 2.4083471298217773,
      "learning_rate": 8.85885885885886e-06,
      "loss": 0.1589,
      "step": 44
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 2.89790940284729,
      "learning_rate": 8.82882882882883e-06,
      "loss": 0.2312,
      "step": 45
    },
    {
      "epoch": 0.1362962962962963,
      "grad_norm": 3.102193593978882,
      "learning_rate": 8.798798798798799e-06,
      "loss": 0.2564,
      "step": 46
    },
    {
      "epoch": 0.13925925925925925,
      "grad_norm": 3.834934949874878,
      "learning_rate": 8.768768768768769e-06,
      "loss": 0.3415,
      "step": 47
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 2.1779191493988037,
      "learning_rate": 8.738738738738739e-06,
      "loss": 0.1333,
      "step": 48
    },
    {
      "epoch": 0.1451851851851852,
      "grad_norm": 2.6279008388519287,
      "learning_rate": 8.70870870870871e-06,
      "loss": 0.1786,
      "step": 49
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.8918596506118774,
      "learning_rate": 8.67867867867868e-06,
      "loss": 0.1485,
      "step": 50
    },
    {
      "epoch": 0.14814814814814814,
      "eval_loss": 0.18624834716320038,
      "eval_runtime": 26.2732,
      "eval_samples_per_second": 22.837,
      "eval_steps_per_second": 11.418,
      "step": 50
    },
    {
      "epoch": 0.1511111111111111,
      "grad_norm": 3.2005956172943115,
      "learning_rate": 8.64864864864865e-06,
      "loss": 0.2538,
      "step": 51
    },
    {
      "epoch": 0.15407407407407409,
      "grad_norm": 2.7147748470306396,
      "learning_rate": 8.618618618618619e-06,
      "loss": 0.2231,
      "step": 52
    },
    {
      "epoch": 0.15703703703703703,
      "grad_norm": 3.01159405708313,
      "learning_rate": 8.588588588588589e-06,
      "loss": 0.2686,
      "step": 53
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.2265002727508545,
      "learning_rate": 8.55855855855856e-06,
      "loss": 0.222,
      "step": 54
    },
    {
      "epoch": 0.16296296296296298,
      "grad_norm": 1.8302077054977417,
      "learning_rate": 8.52852852852853e-06,
      "loss": 0.1154,
      "step": 55
    },
    {
      "epoch": 0.16592592592592592,
      "grad_norm": 2.789992332458496,
      "learning_rate": 8.4984984984985e-06,
      "loss": 0.1905,
      "step": 56
    },
    {
      "epoch": 0.1688888888888889,
      "grad_norm": 2.2926018238067627,
      "learning_rate": 8.46846846846847e-06,
      "loss": 0.1598,
      "step": 57
    },
    {
      "epoch": 0.17185185185185184,
      "grad_norm": 2.055452346801758,
      "learning_rate": 8.438438438438439e-06,
      "loss": 0.1335,
      "step": 58
    },
    {
      "epoch": 0.1748148148148148,
      "grad_norm": 2.694594621658325,
      "learning_rate": 8.408408408408409e-06,
      "loss": 0.2127,
      "step": 59
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.497568130493164,
      "learning_rate": 8.378378378378378e-06,
      "loss": 0.1962,
      "step": 60
    },
    {
      "epoch": 0.18074074074074073,
      "grad_norm": 2.3539998531341553,
      "learning_rate": 8.348348348348348e-06,
      "loss": 0.1658,
      "step": 61
    },
    {
      "epoch": 0.1837037037037037,
      "grad_norm": 2.0217926502227783,
      "learning_rate": 8.31831831831832e-06,
      "loss": 0.135,
      "step": 62
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 2.7960245609283447,
      "learning_rate": 8.288288288288289e-06,
      "loss": 0.2565,
      "step": 63
    },
    {
      "epoch": 0.18962962962962962,
      "grad_norm": 1.9953153133392334,
      "learning_rate": 8.258258258258259e-06,
      "loss": 0.1625,
      "step": 64
    },
    {
      "epoch": 0.1925925925925926,
      "grad_norm": 2.6107969284057617,
      "learning_rate": 8.228228228228229e-06,
      "loss": 0.2047,
      "step": 65
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 2.60530161857605,
      "learning_rate": 8.198198198198198e-06,
      "loss": 0.1755,
      "step": 66
    },
    {
      "epoch": 0.1985185185185185,
      "grad_norm": 2.6039392948150635,
      "learning_rate": 8.16816816816817e-06,
      "loss": 0.2346,
      "step": 67
    },
    {
      "epoch": 0.20148148148148148,
      "grad_norm": 3.7214717864990234,
      "learning_rate": 8.13813813813814e-06,
      "loss": 0.3074,
      "step": 68
    },
    {
      "epoch": 0.20444444444444446,
      "grad_norm": 2.9203999042510986,
      "learning_rate": 8.108108108108109e-06,
      "loss": 0.2276,
      "step": 69
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 1.9092843532562256,
      "learning_rate": 8.078078078078079e-06,
      "loss": 0.1242,
      "step": 70
    },
    {
      "epoch": 0.21037037037037037,
      "grad_norm": 3.042041301727295,
      "learning_rate": 8.048048048048048e-06,
      "loss": 0.2137,
      "step": 71
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 2.7207822799682617,
      "learning_rate": 8.018018018018018e-06,
      "loss": 0.2151,
      "step": 72
    },
    {
      "epoch": 0.2162962962962963,
      "grad_norm": 2.345594882965088,
      "learning_rate": 7.987987987987988e-06,
      "loss": 0.1509,
      "step": 73
    },
    {
      "epoch": 0.21925925925925926,
      "grad_norm": 2.5641767978668213,
      "learning_rate": 7.95795795795796e-06,
      "loss": 0.1245,
      "step": 74
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.251359224319458,
      "learning_rate": 7.927927927927929e-06,
      "loss": 0.1489,
      "step": 75
    },
    {
      "epoch": 0.22518518518518518,
      "grad_norm": 2.5570273399353027,
      "learning_rate": 7.897897897897899e-06,
      "loss": 0.1915,
      "step": 76
    },
    {
      "epoch": 0.22814814814814816,
      "grad_norm": 3.1146445274353027,
      "learning_rate": 7.867867867867868e-06,
      "loss": 0.2532,
      "step": 77
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 2.732043743133545,
      "learning_rate": 7.837837837837838e-06,
      "loss": 0.1942,
      "step": 78
    },
    {
      "epoch": 0.23407407407407407,
      "grad_norm": 2.11357045173645,
      "learning_rate": 7.807807807807808e-06,
      "loss": 0.1423,
      "step": 79
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 2.436385154724121,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.1936,
      "step": 80
    },
    {
      "epoch": 0.24,
      "grad_norm": 2.1624011993408203,
      "learning_rate": 7.747747747747749e-06,
      "loss": 0.1826,
      "step": 81
    },
    {
      "epoch": 0.24296296296296296,
      "grad_norm": 2.590324878692627,
      "learning_rate": 7.717717717717719e-06,
      "loss": 0.1498,
      "step": 82
    },
    {
      "epoch": 0.24592592592592594,
      "grad_norm": 1.898289442062378,
      "learning_rate": 7.687687687687688e-06,
      "loss": 0.1295,
      "step": 83
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 2.4974863529205322,
      "learning_rate": 7.657657657657658e-06,
      "loss": 0.1612,
      "step": 84
    },
    {
      "epoch": 0.2518518518518518,
      "grad_norm": 2.5593483448028564,
      "learning_rate": 7.6276276276276285e-06,
      "loss": 0.2022,
      "step": 85
    },
    {
      "epoch": 0.2548148148148148,
      "grad_norm": 2.065596103668213,
      "learning_rate": 7.597597597597598e-06,
      "loss": 0.1825,
      "step": 86
    },
    {
      "epoch": 0.2577777777777778,
      "grad_norm": 2.937304973602295,
      "learning_rate": 7.567567567567569e-06,
      "loss": 0.263,
      "step": 87
    },
    {
      "epoch": 0.2607407407407407,
      "grad_norm": 2.7244033813476562,
      "learning_rate": 7.5375375375375385e-06,
      "loss": 0.2435,
      "step": 88
    },
    {
      "epoch": 0.2637037037037037,
      "grad_norm": 2.0811917781829834,
      "learning_rate": 7.507507507507507e-06,
      "loss": 0.1383,
      "step": 89
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.5907349586486816,
      "learning_rate": 7.477477477477479e-06,
      "loss": 0.1788,
      "step": 90
    },
    {
      "epoch": 0.2696296296296296,
      "grad_norm": 2.3869409561157227,
      "learning_rate": 7.447447447447448e-06,
      "loss": 0.2255,
      "step": 91
    },
    {
      "epoch": 0.2725925925925926,
      "grad_norm": 1.945121169090271,
      "learning_rate": 7.417417417417418e-06,
      "loss": 0.1355,
      "step": 92
    },
    {
      "epoch": 0.27555555555555555,
      "grad_norm": 1.9447613954544067,
      "learning_rate": 7.387387387387388e-06,
      "loss": 0.1162,
      "step": 93
    },
    {
      "epoch": 0.2785185185185185,
      "grad_norm": 3.1521899700164795,
      "learning_rate": 7.3573573573573575e-06,
      "loss": 0.2814,
      "step": 94
    },
    {
      "epoch": 0.2814814814814815,
      "grad_norm": 2.165618658065796,
      "learning_rate": 7.327327327327328e-06,
      "loss": 0.1773,
      "step": 95
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 2.6660573482513428,
      "learning_rate": 7.297297297297298e-06,
      "loss": 0.2083,
      "step": 96
    },
    {
      "epoch": 0.2874074074074074,
      "grad_norm": 2.5318708419799805,
      "learning_rate": 7.267267267267268e-06,
      "loss": 0.2286,
      "step": 97
    },
    {
      "epoch": 0.2903703703703704,
      "grad_norm": 2.430417060852051,
      "learning_rate": 7.237237237237238e-06,
      "loss": 0.1875,
      "step": 98
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 2.8864619731903076,
      "learning_rate": 7.207207207207208e-06,
      "loss": 0.2792,
      "step": 99
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 2.333770990371704,
      "learning_rate": 7.177177177177178e-06,
      "loss": 0.2119,
      "step": 100
    },
    {
      "epoch": 0.2962962962962963,
      "eval_loss": 0.17042042315006256,
      "eval_runtime": 18.802,
      "eval_samples_per_second": 31.912,
      "eval_steps_per_second": 15.956,
      "step": 100
    },
    {
      "epoch": 0.2992592592592593,
      "grad_norm": 2.0401771068573,
      "learning_rate": 7.147147147147148e-06,
      "loss": 0.1213,
      "step": 101
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 2.6263272762298584,
      "learning_rate": 7.117117117117117e-06,
      "loss": 0.188,
      "step": 102
    },
    {
      "epoch": 0.30518518518518517,
      "grad_norm": 3.291285753250122,
      "learning_rate": 7.087087087087087e-06,
      "loss": 0.2894,
      "step": 103
    },
    {
      "epoch": 0.30814814814814817,
      "grad_norm": 2.306898355484009,
      "learning_rate": 7.057057057057057e-06,
      "loss": 0.1659,
      "step": 104
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 2.6213221549987793,
      "learning_rate": 7.027027027027028e-06,
      "loss": 0.2534,
      "step": 105
    },
    {
      "epoch": 0.31407407407407406,
      "grad_norm": 1.8068263530731201,
      "learning_rate": 6.996996996996997e-06,
      "loss": 0.1307,
      "step": 106
    },
    {
      "epoch": 0.31703703703703706,
      "grad_norm": 2.3400890827178955,
      "learning_rate": 6.966966966966967e-06,
      "loss": 0.1494,
      "step": 107
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.9755533933639526,
      "learning_rate": 6.936936936936938e-06,
      "loss": 0.1638,
      "step": 108
    },
    {
      "epoch": 0.32296296296296295,
      "grad_norm": 2.7602009773254395,
      "learning_rate": 6.906906906906907e-06,
      "loss": 0.2177,
      "step": 109
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 2.491269588470459,
      "learning_rate": 6.876876876876878e-06,
      "loss": 0.186,
      "step": 110
    },
    {
      "epoch": 0.3288888888888889,
      "grad_norm": 3.040412425994873,
      "learning_rate": 6.846846846846848e-06,
      "loss": 0.252,
      "step": 111
    },
    {
      "epoch": 0.33185185185185184,
      "grad_norm": 2.050868511199951,
      "learning_rate": 6.816816816816817e-06,
      "loss": 0.17,
      "step": 112
    },
    {
      "epoch": 0.3348148148148148,
      "grad_norm": 2.239346981048584,
      "learning_rate": 6.786786786786788e-06,
      "loss": 0.1657,
      "step": 113
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 2.940706729888916,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 0.2354,
      "step": 114
    },
    {
      "epoch": 0.34074074074074073,
      "grad_norm": 2.4436991214752197,
      "learning_rate": 6.726726726726728e-06,
      "loss": 0.1677,
      "step": 115
    },
    {
      "epoch": 0.3437037037037037,
      "grad_norm": 3.806905746459961,
      "learning_rate": 6.696696696696697e-06,
      "loss": 0.3089,
      "step": 116
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 2.538794755935669,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1726,
      "step": 117
    },
    {
      "epoch": 0.3496296296296296,
      "grad_norm": 2.8000705242156982,
      "learning_rate": 6.636636636636637e-06,
      "loss": 0.2349,
      "step": 118
    },
    {
      "epoch": 0.35259259259259257,
      "grad_norm": 2.584963321685791,
      "learning_rate": 6.606606606606607e-06,
      "loss": 0.2346,
      "step": 119
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.4167683124542236,
      "learning_rate": 6.5765765765765775e-06,
      "loss": 0.1881,
      "step": 120
    },
    {
      "epoch": 0.3585185185185185,
      "grad_norm": 2.219799757003784,
      "learning_rate": 6.546546546546547e-06,
      "loss": 0.1929,
      "step": 121
    },
    {
      "epoch": 0.36148148148148146,
      "grad_norm": 2.0561611652374268,
      "learning_rate": 6.516516516516517e-06,
      "loss": 0.1582,
      "step": 122
    },
    {
      "epoch": 0.36444444444444446,
      "grad_norm": 2.4856772422790527,
      "learning_rate": 6.486486486486487e-06,
      "loss": 0.1663,
      "step": 123
    },
    {
      "epoch": 0.3674074074074074,
      "grad_norm": 2.9053843021392822,
      "learning_rate": 6.456456456456457e-06,
      "loss": 0.2727,
      "step": 124
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 2.555812120437622,
      "learning_rate": 6.426426426426427e-06,
      "loss": 0.1819,
      "step": 125
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 2.7268261909484863,
      "learning_rate": 6.396396396396397e-06,
      "loss": 0.2324,
      "step": 126
    },
    {
      "epoch": 0.3762962962962963,
      "grad_norm": 2.1161725521087646,
      "learning_rate": 6.366366366366366e-06,
      "loss": 0.1542,
      "step": 127
    },
    {
      "epoch": 0.37925925925925924,
      "grad_norm": 1.7776397466659546,
      "learning_rate": 6.336336336336338e-06,
      "loss": 0.1229,
      "step": 128
    },
    {
      "epoch": 0.38222222222222224,
      "grad_norm": 2.321500778198242,
      "learning_rate": 6.3063063063063065e-06,
      "loss": 0.1462,
      "step": 129
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 2.191991090774536,
      "learning_rate": 6.276276276276276e-06,
      "loss": 0.1287,
      "step": 130
    },
    {
      "epoch": 0.38814814814814813,
      "grad_norm": 2.700402021408081,
      "learning_rate": 6.246246246246247e-06,
      "loss": 0.2105,
      "step": 131
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 2.095440149307251,
      "learning_rate": 6.2162162162162164e-06,
      "loss": 0.1647,
      "step": 132
    },
    {
      "epoch": 0.3940740740740741,
      "grad_norm": 2.8083035945892334,
      "learning_rate": 6.186186186186187e-06,
      "loss": 0.2348,
      "step": 133
    },
    {
      "epoch": 0.397037037037037,
      "grad_norm": 2.6933581829071045,
      "learning_rate": 6.156156156156157e-06,
      "loss": 0.2165,
      "step": 134
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.2427587509155273,
      "learning_rate": 6.126126126126126e-06,
      "loss": 0.1772,
      "step": 135
    },
    {
      "epoch": 0.40296296296296297,
      "grad_norm": 2.072312116622925,
      "learning_rate": 6.096096096096097e-06,
      "loss": 0.148,
      "step": 136
    },
    {
      "epoch": 0.4059259259259259,
      "grad_norm": 2.029669761657715,
      "learning_rate": 6.066066066066067e-06,
      "loss": 0.1079,
      "step": 137
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 2.396289825439453,
      "learning_rate": 6.036036036036037e-06,
      "loss": 0.1656,
      "step": 138
    },
    {
      "epoch": 0.41185185185185186,
      "grad_norm": 2.4869959354400635,
      "learning_rate": 6.006006006006007e-06,
      "loss": 0.1928,
      "step": 139
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 3.3093760013580322,
      "learning_rate": 5.975975975975976e-06,
      "loss": 0.2751,
      "step": 140
    },
    {
      "epoch": 0.4177777777777778,
      "grad_norm": 2.489239454269409,
      "learning_rate": 5.945945945945947e-06,
      "loss": 0.2184,
      "step": 141
    },
    {
      "epoch": 0.42074074074074075,
      "grad_norm": 2.0152416229248047,
      "learning_rate": 5.915915915915916e-06,
      "loss": 0.137,
      "step": 142
    },
    {
      "epoch": 0.4237037037037037,
      "grad_norm": 2.7887892723083496,
      "learning_rate": 5.885885885885886e-06,
      "loss": 0.2433,
      "step": 143
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 2.661060333251953,
      "learning_rate": 5.855855855855856e-06,
      "loss": 0.1887,
      "step": 144
    },
    {
      "epoch": 0.42962962962962964,
      "grad_norm": 2.2275123596191406,
      "learning_rate": 5.825825825825826e-06,
      "loss": 0.1431,
      "step": 145
    },
    {
      "epoch": 0.4325925925925926,
      "grad_norm": 1.5605024099349976,
      "learning_rate": 5.7957957957957965e-06,
      "loss": 0.0927,
      "step": 146
    },
    {
      "epoch": 0.43555555555555553,
      "grad_norm": 2.1205263137817383,
      "learning_rate": 5.765765765765766e-06,
      "loss": 0.1438,
      "step": 147
    },
    {
      "epoch": 0.43851851851851853,
      "grad_norm": 2.250562906265259,
      "learning_rate": 5.735735735735736e-06,
      "loss": 0.1729,
      "step": 148
    },
    {
      "epoch": 0.4414814814814815,
      "grad_norm": 2.6525464057922363,
      "learning_rate": 5.7057057057057065e-06,
      "loss": 0.1806,
      "step": 149
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.825739860534668,
      "learning_rate": 5.675675675675676e-06,
      "loss": 0.2419,
      "step": 150
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 0.16204985976219177,
      "eval_runtime": 18.8245,
      "eval_samples_per_second": 31.873,
      "eval_steps_per_second": 15.937,
      "step": 150
    },
    {
      "epoch": 0.4474074074074074,
      "grad_norm": 3.0488762855529785,
      "learning_rate": 5.645645645645647e-06,
      "loss": 0.2474,
      "step": 151
    },
    {
      "epoch": 0.45037037037037037,
      "grad_norm": 1.806776762008667,
      "learning_rate": 5.615615615615616e-06,
      "loss": 0.1296,
      "step": 152
    },
    {
      "epoch": 0.4533333333333333,
      "grad_norm": 2.6570334434509277,
      "learning_rate": 5.585585585585585e-06,
      "loss": 0.1689,
      "step": 153
    },
    {
      "epoch": 0.4562962962962963,
      "grad_norm": 2.5444271564483643,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.1723,
      "step": 154
    },
    {
      "epoch": 0.45925925925925926,
      "grad_norm": 1.777822494506836,
      "learning_rate": 5.5255255255255255e-06,
      "loss": 0.1019,
      "step": 155
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 1.320265531539917,
      "learning_rate": 5.495495495495496e-06,
      "loss": 0.048,
      "step": 156
    },
    {
      "epoch": 0.4651851851851852,
      "grad_norm": 3.115108013153076,
      "learning_rate": 5.465465465465466e-06,
      "loss": 0.2088,
      "step": 157
    },
    {
      "epoch": 0.46814814814814815,
      "grad_norm": 1.917275309562683,
      "learning_rate": 5.4354354354354355e-06,
      "loss": 0.1432,
      "step": 158
    },
    {
      "epoch": 0.4711111111111111,
      "grad_norm": 2.612023115158081,
      "learning_rate": 5.405405405405406e-06,
      "loss": 0.2236,
      "step": 159
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 2.0786612033843994,
      "learning_rate": 5.375375375375376e-06,
      "loss": 0.1277,
      "step": 160
    },
    {
      "epoch": 0.47703703703703704,
      "grad_norm": 2.443786382675171,
      "learning_rate": 5.345345345345346e-06,
      "loss": 0.1843,
      "step": 161
    },
    {
      "epoch": 0.48,
      "grad_norm": 2.088369131088257,
      "learning_rate": 5.315315315315316e-06,
      "loss": 0.1172,
      "step": 162
    },
    {
      "epoch": 0.482962962962963,
      "grad_norm": 2.6522440910339355,
      "learning_rate": 5.285285285285286e-06,
      "loss": 0.1681,
      "step": 163
    },
    {
      "epoch": 0.48592592592592593,
      "grad_norm": 2.1072304248809814,
      "learning_rate": 5.255255255255256e-06,
      "loss": 0.117,
      "step": 164
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 2.364665985107422,
      "learning_rate": 5.225225225225226e-06,
      "loss": 0.1743,
      "step": 165
    },
    {
      "epoch": 0.4918518518518519,
      "grad_norm": 2.0782034397125244,
      "learning_rate": 5.195195195195195e-06,
      "loss": 0.1368,
      "step": 166
    },
    {
      "epoch": 0.4948148148148148,
      "grad_norm": 2.4548680782318115,
      "learning_rate": 5.165165165165165e-06,
      "loss": 0.152,
      "step": 167
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 3.1544837951660156,
      "learning_rate": 5.135135135135135e-06,
      "loss": 0.2807,
      "step": 168
    },
    {
      "epoch": 0.5007407407407407,
      "grad_norm": 2.1156868934631348,
      "learning_rate": 5.105105105105106e-06,
      "loss": 0.1521,
      "step": 169
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 2.852797746658325,
      "learning_rate": 5.075075075075075e-06,
      "loss": 0.2171,
      "step": 170
    },
    {
      "epoch": 0.5066666666666667,
      "grad_norm": 2.580721855163574,
      "learning_rate": 5.045045045045045e-06,
      "loss": 0.1974,
      "step": 171
    },
    {
      "epoch": 0.5096296296296297,
      "grad_norm": 3.234027862548828,
      "learning_rate": 5.0150150150150156e-06,
      "loss": 0.234,
      "step": 172
    },
    {
      "epoch": 0.5125925925925926,
      "grad_norm": 2.471285343170166,
      "learning_rate": 4.984984984984985e-06,
      "loss": 0.2014,
      "step": 173
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 2.7432644367218018,
      "learning_rate": 4.954954954954955e-06,
      "loss": 0.1934,
      "step": 174
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 2.529627561569214,
      "learning_rate": 4.9249249249249255e-06,
      "loss": 0.1747,
      "step": 175
    },
    {
      "epoch": 0.5214814814814814,
      "grad_norm": 2.459336519241333,
      "learning_rate": 4.894894894894895e-06,
      "loss": 0.2035,
      "step": 176
    },
    {
      "epoch": 0.5244444444444445,
      "grad_norm": 1.9938182830810547,
      "learning_rate": 4.864864864864866e-06,
      "loss": 0.1165,
      "step": 177
    },
    {
      "epoch": 0.5274074074074074,
      "grad_norm": 2.380720853805542,
      "learning_rate": 4.8348348348348355e-06,
      "loss": 0.1744,
      "step": 178
    },
    {
      "epoch": 0.5303703703703704,
      "grad_norm": 2.382479190826416,
      "learning_rate": 4.804804804804805e-06,
      "loss": 0.1802,
      "step": 179
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.0551960468292236,
      "learning_rate": 4.774774774774775e-06,
      "loss": 0.1485,
      "step": 180
    },
    {
      "epoch": 0.5362962962962963,
      "grad_norm": 1.9511905908584595,
      "learning_rate": 4.7447447447447454e-06,
      "loss": 0.1462,
      "step": 181
    },
    {
      "epoch": 0.5392592592592592,
      "grad_norm": 2.7153124809265137,
      "learning_rate": 4.714714714714715e-06,
      "loss": 0.1652,
      "step": 182
    },
    {
      "epoch": 0.5422222222222223,
      "grad_norm": 2.1475372314453125,
      "learning_rate": 4.684684684684685e-06,
      "loss": 0.1247,
      "step": 183
    },
    {
      "epoch": 0.5451851851851852,
      "grad_norm": 2.583651304244995,
      "learning_rate": 4.654654654654655e-06,
      "loss": 0.2297,
      "step": 184
    },
    {
      "epoch": 0.5481481481481482,
      "grad_norm": 2.108767032623291,
      "learning_rate": 4.624624624624625e-06,
      "loss": 0.1099,
      "step": 185
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 2.9994611740112305,
      "learning_rate": 4.594594594594596e-06,
      "loss": 0.2094,
      "step": 186
    },
    {
      "epoch": 0.554074074074074,
      "grad_norm": 3.321688652038574,
      "learning_rate": 4.5645645645645645e-06,
      "loss": 0.2526,
      "step": 187
    },
    {
      "epoch": 0.557037037037037,
      "grad_norm": 2.593113660812378,
      "learning_rate": 4.534534534534535e-06,
      "loss": 0.1566,
      "step": 188
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.545966386795044,
      "learning_rate": 4.504504504504505e-06,
      "loss": 0.2073,
      "step": 189
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 2.7435529232025146,
      "learning_rate": 4.474474474474475e-06,
      "loss": 0.1803,
      "step": 190
    },
    {
      "epoch": 0.5659259259259259,
      "grad_norm": 2.347872257232666,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.1877,
      "step": 191
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 1.9816969633102417,
      "learning_rate": 4.414414414414415e-06,
      "loss": 0.1242,
      "step": 192
    },
    {
      "epoch": 0.5718518518518518,
      "grad_norm": 2.399693727493286,
      "learning_rate": 4.384384384384384e-06,
      "loss": 0.2213,
      "step": 193
    },
    {
      "epoch": 0.5748148148148148,
      "grad_norm": 2.447413444519043,
      "learning_rate": 4.354354354354355e-06,
      "loss": 0.2114,
      "step": 194
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 2.2283434867858887,
      "learning_rate": 4.324324324324325e-06,
      "loss": 0.142,
      "step": 195
    },
    {
      "epoch": 0.5807407407407408,
      "grad_norm": 1.9958397150039673,
      "learning_rate": 4.294294294294294e-06,
      "loss": 0.1498,
      "step": 196
    },
    {
      "epoch": 0.5837037037037037,
      "grad_norm": 2.253139019012451,
      "learning_rate": 4.264264264264265e-06,
      "loss": 0.1877,
      "step": 197
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 2.2726593017578125,
      "learning_rate": 4.234234234234235e-06,
      "loss": 0.1763,
      "step": 198
    },
    {
      "epoch": 0.5896296296296296,
      "grad_norm": 2.5664706230163574,
      "learning_rate": 4.204204204204204e-06,
      "loss": 0.166,
      "step": 199
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.8938143253326416,
      "learning_rate": 4.174174174174174e-06,
      "loss": 0.1322,
      "step": 200
    },
    {
      "epoch": 0.5925925925925926,
      "eval_loss": 0.15719713270664215,
      "eval_runtime": 18.9181,
      "eval_samples_per_second": 31.716,
      "eval_steps_per_second": 15.858,
      "step": 200
    },
    {
      "epoch": 0.5955555555555555,
      "grad_norm": 2.330968141555786,
      "learning_rate": 4.1441441441441446e-06,
      "loss": 0.2141,
      "step": 201
    },
    {
      "epoch": 0.5985185185185186,
      "grad_norm": 2.51415753364563,
      "learning_rate": 4.114114114114114e-06,
      "loss": 0.1627,
      "step": 202
    },
    {
      "epoch": 0.6014814814814815,
      "grad_norm": 1.9164345264434814,
      "learning_rate": 4.084084084084085e-06,
      "loss": 0.1176,
      "step": 203
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 3.183730125427246,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 0.2431,
      "step": 204
    },
    {
      "epoch": 0.6074074074074074,
      "grad_norm": 2.5296268463134766,
      "learning_rate": 4.024024024024024e-06,
      "loss": 0.1958,
      "step": 205
    },
    {
      "epoch": 0.6103703703703703,
      "grad_norm": 1.842099905014038,
      "learning_rate": 3.993993993993994e-06,
      "loss": 0.1304,
      "step": 206
    },
    {
      "epoch": 0.6133333333333333,
      "grad_norm": 1.931595802307129,
      "learning_rate": 3.9639639639639645e-06,
      "loss": 0.0947,
      "step": 207
    },
    {
      "epoch": 0.6162962962962963,
      "grad_norm": 1.942159652709961,
      "learning_rate": 3.933933933933934e-06,
      "loss": 0.1324,
      "step": 208
    },
    {
      "epoch": 0.6192592592592593,
      "grad_norm": 2.1932191848754883,
      "learning_rate": 3.903903903903904e-06,
      "loss": 0.1787,
      "step": 209
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.3052737712860107,
      "learning_rate": 3.8738738738738744e-06,
      "loss": 0.188,
      "step": 210
    },
    {
      "epoch": 0.6251851851851852,
      "grad_norm": 2.41378116607666,
      "learning_rate": 3.843843843843844e-06,
      "loss": 0.1904,
      "step": 211
    },
    {
      "epoch": 0.6281481481481481,
      "grad_norm": 2.1568689346313477,
      "learning_rate": 3.8138138138138143e-06,
      "loss": 0.1705,
      "step": 212
    },
    {
      "epoch": 0.6311111111111111,
      "grad_norm": 2.751380205154419,
      "learning_rate": 3.7837837837837844e-06,
      "loss": 0.1923,
      "step": 213
    },
    {
      "epoch": 0.6340740740740741,
      "grad_norm": 2.0356202125549316,
      "learning_rate": 3.7537537537537537e-06,
      "loss": 0.1487,
      "step": 214
    },
    {
      "epoch": 0.6370370370370371,
      "grad_norm": 2.0040347576141357,
      "learning_rate": 3.723723723723724e-06,
      "loss": 0.1302,
      "step": 215
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.1415553092956543,
      "learning_rate": 3.693693693693694e-06,
      "loss": 0.1608,
      "step": 216
    },
    {
      "epoch": 0.642962962962963,
      "grad_norm": 2.281193256378174,
      "learning_rate": 3.663663663663664e-06,
      "loss": 0.1581,
      "step": 217
    },
    {
      "epoch": 0.6459259259259259,
      "grad_norm": 1.8913451433181763,
      "learning_rate": 3.633633633633634e-06,
      "loss": 0.1043,
      "step": 218
    },
    {
      "epoch": 0.6488888888888888,
      "grad_norm": 2.9472875595092773,
      "learning_rate": 3.603603603603604e-06,
      "loss": 0.2136,
      "step": 219
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 2.1848208904266357,
      "learning_rate": 3.573573573573574e-06,
      "loss": 0.154,
      "step": 220
    },
    {
      "epoch": 0.6548148148148148,
      "grad_norm": 1.8700780868530273,
      "learning_rate": 3.5435435435435437e-06,
      "loss": 0.1603,
      "step": 221
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 2.0721077919006348,
      "learning_rate": 3.513513513513514e-06,
      "loss": 0.1417,
      "step": 222
    },
    {
      "epoch": 0.6607407407407407,
      "grad_norm": 2.1762733459472656,
      "learning_rate": 3.4834834834834835e-06,
      "loss": 0.1458,
      "step": 223
    },
    {
      "epoch": 0.6637037037037037,
      "grad_norm": 2.4199893474578857,
      "learning_rate": 3.4534534534534537e-06,
      "loss": 0.1082,
      "step": 224
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.066798210144043,
      "learning_rate": 3.423423423423424e-06,
      "loss": 0.1214,
      "step": 225
    },
    {
      "epoch": 0.6696296296296296,
      "grad_norm": 2.5422122478485107,
      "learning_rate": 3.393393393393394e-06,
      "loss": 0.1393,
      "step": 226
    },
    {
      "epoch": 0.6725925925925926,
      "grad_norm": 2.617987871170044,
      "learning_rate": 3.363363363363364e-06,
      "loss": 0.2183,
      "step": 227
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 1.7141070365905762,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.1094,
      "step": 228
    },
    {
      "epoch": 0.6785185185185185,
      "grad_norm": 1.7786457538604736,
      "learning_rate": 3.3033033033033035e-06,
      "loss": 0.0929,
      "step": 229
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 1.7540638446807861,
      "learning_rate": 3.2732732732732736e-06,
      "loss": 0.1218,
      "step": 230
    },
    {
      "epoch": 0.6844444444444444,
      "grad_norm": 2.6888673305511475,
      "learning_rate": 3.2432432432432437e-06,
      "loss": 0.2506,
      "step": 231
    },
    {
      "epoch": 0.6874074074074074,
      "grad_norm": 2.213644027709961,
      "learning_rate": 3.2132132132132134e-06,
      "loss": 0.1514,
      "step": 232
    },
    {
      "epoch": 0.6903703703703704,
      "grad_norm": 2.0085294246673584,
      "learning_rate": 3.183183183183183e-06,
      "loss": 0.1336,
      "step": 233
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 2.0390026569366455,
      "learning_rate": 3.1531531531531532e-06,
      "loss": 0.1105,
      "step": 234
    },
    {
      "epoch": 0.6962962962962963,
      "grad_norm": 2.7348194122314453,
      "learning_rate": 3.1231231231231234e-06,
      "loss": 0.1579,
      "step": 235
    },
    {
      "epoch": 0.6992592592592592,
      "grad_norm": 2.7980740070343018,
      "learning_rate": 3.0930930930930935e-06,
      "loss": 0.1963,
      "step": 236
    },
    {
      "epoch": 0.7022222222222222,
      "grad_norm": 2.466264486312866,
      "learning_rate": 3.063063063063063e-06,
      "loss": 0.1735,
      "step": 237
    },
    {
      "epoch": 0.7051851851851851,
      "grad_norm": 2.3503952026367188,
      "learning_rate": 3.0330330330330333e-06,
      "loss": 0.1651,
      "step": 238
    },
    {
      "epoch": 0.7081481481481482,
      "grad_norm": 1.990291953086853,
      "learning_rate": 3.0030030030030034e-06,
      "loss": 0.1267,
      "step": 239
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.484708786010742,
      "learning_rate": 2.9729729729729736e-06,
      "loss": 0.1894,
      "step": 240
    },
    {
      "epoch": 0.7140740740740741,
      "grad_norm": 2.303131103515625,
      "learning_rate": 2.942942942942943e-06,
      "loss": 0.1699,
      "step": 241
    },
    {
      "epoch": 0.717037037037037,
      "grad_norm": 2.2463326454162598,
      "learning_rate": 2.912912912912913e-06,
      "loss": 0.1641,
      "step": 242
    },
    {
      "epoch": 0.72,
      "grad_norm": 2.747182607650757,
      "learning_rate": 2.882882882882883e-06,
      "loss": 0.2127,
      "step": 243
    },
    {
      "epoch": 0.7229629629629629,
      "grad_norm": 2.1243135929107666,
      "learning_rate": 2.8528528528528532e-06,
      "loss": 0.1274,
      "step": 244
    },
    {
      "epoch": 0.725925925925926,
      "grad_norm": 1.8795485496520996,
      "learning_rate": 2.8228228228228234e-06,
      "loss": 0.0915,
      "step": 245
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 2.598935604095459,
      "learning_rate": 2.7927927927927926e-06,
      "loss": 0.1951,
      "step": 246
    },
    {
      "epoch": 0.7318518518518519,
      "grad_norm": 1.8523262739181519,
      "learning_rate": 2.7627627627627628e-06,
      "loss": 0.111,
      "step": 247
    },
    {
      "epoch": 0.7348148148148148,
      "grad_norm": 2.13834547996521,
      "learning_rate": 2.732732732732733e-06,
      "loss": 0.1309,
      "step": 248
    },
    {
      "epoch": 0.7377777777777778,
      "grad_norm": 2.51226544380188,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.2001,
      "step": 249
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 2.38637113571167,
      "learning_rate": 2.672672672672673e-06,
      "loss": 0.1818,
      "step": 250
    },
    {
      "epoch": 0.7407407407407407,
      "eval_loss": 0.15431299805641174,
      "eval_runtime": 18.8251,
      "eval_samples_per_second": 31.872,
      "eval_steps_per_second": 15.936,
      "step": 250
    },
    {
      "epoch": 0.7437037037037038,
      "grad_norm": 2.230959177017212,
      "learning_rate": 2.642642642642643e-06,
      "loss": 0.1546,
      "step": 251
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 1.9361540079116821,
      "learning_rate": 2.612612612612613e-06,
      "loss": 0.1304,
      "step": 252
    },
    {
      "epoch": 0.7496296296296296,
      "grad_norm": 2.8404579162597656,
      "learning_rate": 2.5825825825825827e-06,
      "loss": 0.195,
      "step": 253
    },
    {
      "epoch": 0.7525925925925926,
      "grad_norm": 2.246924877166748,
      "learning_rate": 2.552552552552553e-06,
      "loss": 0.1457,
      "step": 254
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 2.3188321590423584,
      "learning_rate": 2.5225225225225225e-06,
      "loss": 0.1711,
      "step": 255
    },
    {
      "epoch": 0.7585185185185185,
      "grad_norm": 2.3491628170013428,
      "learning_rate": 2.4924924924924926e-06,
      "loss": 0.1658,
      "step": 256
    },
    {
      "epoch": 0.7614814814814815,
      "grad_norm": 2.427833080291748,
      "learning_rate": 2.4624624624624628e-06,
      "loss": 0.211,
      "step": 257
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 2.2920594215393066,
      "learning_rate": 2.432432432432433e-06,
      "loss": 0.1745,
      "step": 258
    },
    {
      "epoch": 0.7674074074074074,
      "grad_norm": 2.707094669342041,
      "learning_rate": 2.4024024024024026e-06,
      "loss": 0.1889,
      "step": 259
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 2.210993766784668,
      "learning_rate": 2.3723723723723727e-06,
      "loss": 0.1519,
      "step": 260
    },
    {
      "epoch": 0.7733333333333333,
      "grad_norm": 2.7194671630859375,
      "learning_rate": 2.3423423423423424e-06,
      "loss": 0.2105,
      "step": 261
    },
    {
      "epoch": 0.7762962962962963,
      "grad_norm": 3.0573675632476807,
      "learning_rate": 2.3123123123123125e-06,
      "loss": 0.2057,
      "step": 262
    },
    {
      "epoch": 0.7792592592592592,
      "grad_norm": 3.092182159423828,
      "learning_rate": 2.2822822822822822e-06,
      "loss": 0.2355,
      "step": 263
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 2.1236793994903564,
      "learning_rate": 2.2522522522522524e-06,
      "loss": 0.1212,
      "step": 264
    },
    {
      "epoch": 0.7851851851851852,
      "grad_norm": 2.1027090549468994,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.114,
      "step": 265
    },
    {
      "epoch": 0.7881481481481482,
      "grad_norm": 1.7916721105575562,
      "learning_rate": 2.192192192192192e-06,
      "loss": 0.1198,
      "step": 266
    },
    {
      "epoch": 0.7911111111111111,
      "grad_norm": 2.6954166889190674,
      "learning_rate": 2.1621621621621623e-06,
      "loss": 0.21,
      "step": 267
    },
    {
      "epoch": 0.794074074074074,
      "grad_norm": 2.217022180557251,
      "learning_rate": 2.1321321321321325e-06,
      "loss": 0.1332,
      "step": 268
    },
    {
      "epoch": 0.797037037037037,
      "grad_norm": 2.8066651821136475,
      "learning_rate": 2.102102102102102e-06,
      "loss": 0.1816,
      "step": 269
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.666680335998535,
      "learning_rate": 2.0720720720720723e-06,
      "loss": 0.2768,
      "step": 270
    },
    {
      "epoch": 0.802962962962963,
      "grad_norm": 2.1979265213012695,
      "learning_rate": 2.0420420420420424e-06,
      "loss": 0.1352,
      "step": 271
    },
    {
      "epoch": 0.8059259259259259,
      "grad_norm": 2.9469351768493652,
      "learning_rate": 2.012012012012012e-06,
      "loss": 0.1921,
      "step": 272
    },
    {
      "epoch": 0.8088888888888889,
      "grad_norm": 3.1440281867980957,
      "learning_rate": 1.9819819819819822e-06,
      "loss": 0.235,
      "step": 273
    },
    {
      "epoch": 0.8118518518518518,
      "grad_norm": 1.5414925813674927,
      "learning_rate": 1.951951951951952e-06,
      "loss": 0.0812,
      "step": 274
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 2.479802131652832,
      "learning_rate": 1.921921921921922e-06,
      "loss": 0.1984,
      "step": 275
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 3.113929271697998,
      "learning_rate": 1.8918918918918922e-06,
      "loss": 0.2266,
      "step": 276
    },
    {
      "epoch": 0.8207407407407408,
      "grad_norm": 2.4488916397094727,
      "learning_rate": 1.861861861861862e-06,
      "loss": 0.1767,
      "step": 277
    },
    {
      "epoch": 0.8237037037037037,
      "grad_norm": 1.6866132020950317,
      "learning_rate": 1.831831831831832e-06,
      "loss": 0.0889,
      "step": 278
    },
    {
      "epoch": 0.8266666666666667,
      "grad_norm": 2.245986223220825,
      "learning_rate": 1.801801801801802e-06,
      "loss": 0.1371,
      "step": 279
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 2.399932384490967,
      "learning_rate": 1.7717717717717719e-06,
      "loss": 0.191,
      "step": 280
    },
    {
      "epoch": 0.8325925925925926,
      "grad_norm": 1.6557813882827759,
      "learning_rate": 1.7417417417417418e-06,
      "loss": 0.1,
      "step": 281
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 2.8569037914276123,
      "learning_rate": 1.711711711711712e-06,
      "loss": 0.1995,
      "step": 282
    },
    {
      "epoch": 0.8385185185185186,
      "grad_norm": 1.9244745969772339,
      "learning_rate": 1.681681681681682e-06,
      "loss": 0.1228,
      "step": 283
    },
    {
      "epoch": 0.8414814814814815,
      "grad_norm": 2.4045963287353516,
      "learning_rate": 1.6516516516516517e-06,
      "loss": 0.1621,
      "step": 284
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 2.210085153579712,
      "learning_rate": 1.6216216216216219e-06,
      "loss": 0.129,
      "step": 285
    },
    {
      "epoch": 0.8474074074074074,
      "grad_norm": 1.7496682405471802,
      "learning_rate": 1.5915915915915916e-06,
      "loss": 0.1083,
      "step": 286
    },
    {
      "epoch": 0.8503703703703703,
      "grad_norm": 2.0385987758636475,
      "learning_rate": 1.5615615615615617e-06,
      "loss": 0.1075,
      "step": 287
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 1.7718582153320312,
      "learning_rate": 1.5315315315315316e-06,
      "loss": 0.1115,
      "step": 288
    },
    {
      "epoch": 0.8562962962962963,
      "grad_norm": 2.1657755374908447,
      "learning_rate": 1.5015015015015017e-06,
      "loss": 0.1477,
      "step": 289
    },
    {
      "epoch": 0.8592592592592593,
      "grad_norm": 1.46700918674469,
      "learning_rate": 1.4714714714714714e-06,
      "loss": 0.0744,
      "step": 290
    },
    {
      "epoch": 0.8622222222222222,
      "grad_norm": 2.1144633293151855,
      "learning_rate": 1.4414414414414416e-06,
      "loss": 0.1248,
      "step": 291
    },
    {
      "epoch": 0.8651851851851852,
      "grad_norm": 1.9288382530212402,
      "learning_rate": 1.4114114114114117e-06,
      "loss": 0.1181,
      "step": 292
    },
    {
      "epoch": 0.8681481481481481,
      "grad_norm": 2.0071420669555664,
      "learning_rate": 1.3813813813813814e-06,
      "loss": 0.1003,
      "step": 293
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 2.8835299015045166,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 0.2269,
      "step": 294
    },
    {
      "epoch": 0.8740740740740741,
      "grad_norm": 1.6004083156585693,
      "learning_rate": 1.3213213213213214e-06,
      "loss": 0.1032,
      "step": 295
    },
    {
      "epoch": 0.8770370370370371,
      "grad_norm": 2.8284692764282227,
      "learning_rate": 1.2912912912912913e-06,
      "loss": 0.1631,
      "step": 296
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.6856770515441895,
      "learning_rate": 1.2612612612612613e-06,
      "loss": 0.1081,
      "step": 297
    },
    {
      "epoch": 0.882962962962963,
      "grad_norm": 2.2329177856445312,
      "learning_rate": 1.2312312312312314e-06,
      "loss": 0.1676,
      "step": 298
    },
    {
      "epoch": 0.8859259259259259,
      "grad_norm": 1.8328256607055664,
      "learning_rate": 1.2012012012012013e-06,
      "loss": 0.1293,
      "step": 299
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.0162463188171387,
      "learning_rate": 1.1711711711711712e-06,
      "loss": 0.1278,
      "step": 300
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.15191876888275146,
      "eval_runtime": 19.1995,
      "eval_samples_per_second": 31.251,
      "eval_steps_per_second": 15.625,
      "step": 300
    },
    {
      "epoch": 0.8918518518518519,
      "grad_norm": 2.4668619632720947,
      "learning_rate": 1.1411411411411411e-06,
      "loss": 0.1702,
      "step": 301
    },
    {
      "epoch": 0.8948148148148148,
      "grad_norm": 2.692570447921753,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.1743,
      "step": 302
    },
    {
      "epoch": 0.8977777777777778,
      "grad_norm": 1.943791389465332,
      "learning_rate": 1.0810810810810812e-06,
      "loss": 0.1083,
      "step": 303
    },
    {
      "epoch": 0.9007407407407407,
      "grad_norm": 2.46787166595459,
      "learning_rate": 1.051051051051051e-06,
      "loss": 0.1964,
      "step": 304
    },
    {
      "epoch": 0.9037037037037037,
      "grad_norm": 2.13502836227417,
      "learning_rate": 1.0210210210210212e-06,
      "loss": 0.1209,
      "step": 305
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 2.954197883605957,
      "learning_rate": 9.909909909909911e-07,
      "loss": 0.1375,
      "step": 306
    },
    {
      "epoch": 0.9096296296296297,
      "grad_norm": 1.4838200807571411,
      "learning_rate": 9.60960960960961e-07,
      "loss": 0.1001,
      "step": 307
    },
    {
      "epoch": 0.9125925925925926,
      "grad_norm": 2.703058958053589,
      "learning_rate": 9.30930930930931e-07,
      "loss": 0.2116,
      "step": 308
    },
    {
      "epoch": 0.9155555555555556,
      "grad_norm": 2.7120769023895264,
      "learning_rate": 9.00900900900901e-07,
      "loss": 0.2045,
      "step": 309
    },
    {
      "epoch": 0.9185185185185185,
      "grad_norm": 1.9937574863433838,
      "learning_rate": 8.708708708708709e-07,
      "loss": 0.1381,
      "step": 310
    },
    {
      "epoch": 0.9214814814814815,
      "grad_norm": 1.4841877222061157,
      "learning_rate": 8.40840840840841e-07,
      "loss": 0.0885,
      "step": 311
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 1.9590015411376953,
      "learning_rate": 8.108108108108109e-07,
      "loss": 0.1038,
      "step": 312
    },
    {
      "epoch": 0.9274074074074075,
      "grad_norm": 2.5074450969696045,
      "learning_rate": 7.807807807807808e-07,
      "loss": 0.1884,
      "step": 313
    },
    {
      "epoch": 0.9303703703703704,
      "grad_norm": 1.7944597005844116,
      "learning_rate": 7.507507507507509e-07,
      "loss": 0.095,
      "step": 314
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 2.2381157875061035,
      "learning_rate": 7.207207207207208e-07,
      "loss": 0.1553,
      "step": 315
    },
    {
      "epoch": 0.9362962962962963,
      "grad_norm": 2.361530303955078,
      "learning_rate": 6.906906906906907e-07,
      "loss": 0.1984,
      "step": 316
    },
    {
      "epoch": 0.9392592592592592,
      "grad_norm": 2.248955488204956,
      "learning_rate": 6.606606606606607e-07,
      "loss": 0.139,
      "step": 317
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 2.5154507160186768,
      "learning_rate": 6.306306306306306e-07,
      "loss": 0.1527,
      "step": 318
    },
    {
      "epoch": 0.9451851851851852,
      "grad_norm": 2.0144166946411133,
      "learning_rate": 6.006006006006006e-07,
      "loss": 0.1503,
      "step": 319
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 2.069995164871216,
      "learning_rate": 5.705705705705706e-07,
      "loss": 0.1262,
      "step": 320
    },
    {
      "epoch": 0.9511111111111111,
      "grad_norm": 2.1001393795013428,
      "learning_rate": 5.405405405405406e-07,
      "loss": 0.1415,
      "step": 321
    },
    {
      "epoch": 0.9540740740740741,
      "grad_norm": 2.221561908721924,
      "learning_rate": 5.105105105105106e-07,
      "loss": 0.156,
      "step": 322
    },
    {
      "epoch": 0.957037037037037,
      "grad_norm": 1.888270378112793,
      "learning_rate": 4.804804804804805e-07,
      "loss": 0.1365,
      "step": 323
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.260899782180786,
      "learning_rate": 4.504504504504505e-07,
      "loss": 0.1112,
      "step": 324
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 1.708849310874939,
      "learning_rate": 4.204204204204205e-07,
      "loss": 0.1009,
      "step": 325
    },
    {
      "epoch": 0.965925925925926,
      "grad_norm": 2.422349691390991,
      "learning_rate": 3.903903903903904e-07,
      "loss": 0.1764,
      "step": 326
    },
    {
      "epoch": 0.9688888888888889,
      "grad_norm": 1.618794322013855,
      "learning_rate": 3.603603603603604e-07,
      "loss": 0.0967,
      "step": 327
    },
    {
      "epoch": 0.9718518518518519,
      "grad_norm": 2.431173086166382,
      "learning_rate": 3.3033033033033036e-07,
      "loss": 0.183,
      "step": 328
    },
    {
      "epoch": 0.9748148148148148,
      "grad_norm": 2.373152256011963,
      "learning_rate": 3.003003003003003e-07,
      "loss": 0.1644,
      "step": 329
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.9666945934295654,
      "learning_rate": 2.702702702702703e-07,
      "loss": 0.1078,
      "step": 330
    },
    {
      "epoch": 0.9807407407407407,
      "grad_norm": 2.7666008472442627,
      "learning_rate": 2.4024024024024026e-07,
      "loss": 0.2207,
      "step": 331
    },
    {
      "epoch": 0.9837037037037037,
      "grad_norm": 1.90410315990448,
      "learning_rate": 2.1021021021021025e-07,
      "loss": 0.1468,
      "step": 332
    },
    {
      "epoch": 0.9866666666666667,
      "grad_norm": 2.0891292095184326,
      "learning_rate": 1.801801801801802e-07,
      "loss": 0.1326,
      "step": 333
    },
    {
      "epoch": 0.9896296296296296,
      "grad_norm": 1.700302004814148,
      "learning_rate": 1.5015015015015016e-07,
      "loss": 0.1039,
      "step": 334
    },
    {
      "epoch": 0.9925925925925926,
      "grad_norm": 2.617330312728882,
      "learning_rate": 1.2012012012012013e-07,
      "loss": 0.1804,
      "step": 335
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 2.7526986598968506,
      "learning_rate": 9.00900900900901e-08,
      "loss": 0.197,
      "step": 336
    },
    {
      "epoch": 0.9985185185185185,
      "grad_norm": 2.4141345024108887,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.1566,
      "step": 337
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.5155301094055176,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.1676,
      "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": 2.1783808858622976e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}