{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.951768488745981,
  "eval_steps": 500,
  "global_step": 385,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012861736334405145,
      "grad_norm": 577.1012573242188,
      "learning_rate": 8.333333333333335e-09,
      "loss": 13.9619,
      "num_input_tokens_seen": 15136,
      "step": 1
    },
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 552.5532836914062,
      "learning_rate": 1.666666666666667e-08,
      "loss": 13.7129,
      "num_input_tokens_seen": 30208,
      "step": 2
    },
    {
      "epoch": 0.03858520900321544,
      "grad_norm": 562.699462890625,
      "learning_rate": 2.5000000000000002e-08,
      "loss": 13.8474,
      "num_input_tokens_seen": 45376,
      "step": 3
    },
    {
      "epoch": 0.05144694533762058,
      "grad_norm": 585.796630859375,
      "learning_rate": 3.333333333333334e-08,
      "loss": 13.8844,
      "num_input_tokens_seen": 59968,
      "step": 4
    },
    {
      "epoch": 0.06430868167202572,
      "grad_norm": 592.56689453125,
      "learning_rate": 4.166666666666667e-08,
      "loss": 14.138,
      "num_input_tokens_seen": 75136,
      "step": 5
    },
    {
      "epoch": 0.07717041800643087,
      "grad_norm": 569.5825805664062,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 13.9077,
      "num_input_tokens_seen": 90816,
      "step": 6
    },
    {
      "epoch": 0.09003215434083602,
      "grad_norm": 578.7579956054688,
      "learning_rate": 5.833333333333334e-08,
      "loss": 13.8396,
      "num_input_tokens_seen": 105600,
      "step": 7
    },
    {
      "epoch": 0.10289389067524116,
      "grad_norm": 577.330322265625,
      "learning_rate": 6.666666666666668e-08,
      "loss": 13.9828,
      "num_input_tokens_seen": 119872,
      "step": 8
    },
    {
      "epoch": 0.1157556270096463,
      "grad_norm": 575.2134399414062,
      "learning_rate": 7.500000000000001e-08,
      "loss": 14.0361,
      "num_input_tokens_seen": 135104,
      "step": 9
    },
    {
      "epoch": 0.12861736334405144,
      "grad_norm": 579.0157470703125,
      "learning_rate": 8.333333333333334e-08,
      "loss": 13.9392,
      "num_input_tokens_seen": 150016,
      "step": 10
    },
    {
      "epoch": 0.1414790996784566,
      "grad_norm": 585.5687255859375,
      "learning_rate": 9.166666666666668e-08,
      "loss": 14.0256,
      "num_input_tokens_seen": 165216,
      "step": 11
    },
    {
      "epoch": 0.15434083601286175,
      "grad_norm": 566.5042114257812,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 13.6693,
      "num_input_tokens_seen": 179296,
      "step": 12
    },
    {
      "epoch": 0.16720257234726688,
      "grad_norm": 574.4198608398438,
      "learning_rate": 1.0833333333333335e-07,
      "loss": 13.9031,
      "num_input_tokens_seen": 193312,
      "step": 13
    },
    {
      "epoch": 0.18006430868167203,
      "grad_norm": 588.1041259765625,
      "learning_rate": 1.1666666666666668e-07,
      "loss": 13.8575,
      "num_input_tokens_seen": 208768,
      "step": 14
    },
    {
      "epoch": 0.19292604501607716,
      "grad_norm": 573.4750366210938,
      "learning_rate": 1.2500000000000002e-07,
      "loss": 13.8366,
      "num_input_tokens_seen": 223456,
      "step": 15
    },
    {
      "epoch": 0.2057877813504823,
      "grad_norm": 572.26220703125,
      "learning_rate": 1.3333333333333336e-07,
      "loss": 13.8705,
      "num_input_tokens_seen": 238656,
      "step": 16
    },
    {
      "epoch": 0.21864951768488747,
      "grad_norm": 566.3518676757812,
      "learning_rate": 1.4166666666666668e-07,
      "loss": 13.1816,
      "num_input_tokens_seen": 253312,
      "step": 17
    },
    {
      "epoch": 0.2315112540192926,
      "grad_norm": 560.5255126953125,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 13.2292,
      "num_input_tokens_seen": 268352,
      "step": 18
    },
    {
      "epoch": 0.24437299035369775,
      "grad_norm": 583.0404663085938,
      "learning_rate": 1.5833333333333336e-07,
      "loss": 13.4366,
      "num_input_tokens_seen": 282560,
      "step": 19
    },
    {
      "epoch": 0.2572347266881029,
      "grad_norm": 555.8986206054688,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 12.9904,
      "num_input_tokens_seen": 297120,
      "step": 20
    },
    {
      "epoch": 0.27009646302250806,
      "grad_norm": 557.931396484375,
      "learning_rate": 1.7500000000000002e-07,
      "loss": 12.878,
      "num_input_tokens_seen": 312416,
      "step": 21
    },
    {
      "epoch": 0.2829581993569132,
      "grad_norm": 562.4014282226562,
      "learning_rate": 1.8333333333333336e-07,
      "loss": 12.7794,
      "num_input_tokens_seen": 327968,
      "step": 22
    },
    {
      "epoch": 0.2958199356913183,
      "grad_norm": 548.7069702148438,
      "learning_rate": 1.9166666666666668e-07,
      "loss": 11.3144,
      "num_input_tokens_seen": 342880,
      "step": 23
    },
    {
      "epoch": 0.3086816720257235,
      "grad_norm": 511.2892761230469,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 10.8531,
      "num_input_tokens_seen": 358848,
      "step": 24
    },
    {
      "epoch": 0.3215434083601286,
      "grad_norm": 496.71868896484375,
      "learning_rate": 2.0833333333333333e-07,
      "loss": 10.7149,
      "num_input_tokens_seen": 373792,
      "step": 25
    },
    {
      "epoch": 0.33440514469453375,
      "grad_norm": 504.7909851074219,
      "learning_rate": 2.166666666666667e-07,
      "loss": 10.5802,
      "num_input_tokens_seen": 389248,
      "step": 26
    },
    {
      "epoch": 0.34726688102893893,
      "grad_norm": 495.0346984863281,
      "learning_rate": 2.2500000000000002e-07,
      "loss": 10.3671,
      "num_input_tokens_seen": 404320,
      "step": 27
    },
    {
      "epoch": 0.36012861736334406,
      "grad_norm": 482.26318359375,
      "learning_rate": 2.3333333333333336e-07,
      "loss": 10.1751,
      "num_input_tokens_seen": 419296,
      "step": 28
    },
    {
      "epoch": 0.3729903536977492,
      "grad_norm": 480.48193359375,
      "learning_rate": 2.416666666666667e-07,
      "loss": 9.7707,
      "num_input_tokens_seen": 433632,
      "step": 29
    },
    {
      "epoch": 0.3858520900321543,
      "grad_norm": 467.7600402832031,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 9.6489,
      "num_input_tokens_seen": 448736,
      "step": 30
    },
    {
      "epoch": 0.3987138263665595,
      "grad_norm": 468.9175720214844,
      "learning_rate": 2.5833333333333333e-07,
      "loss": 8.6805,
      "num_input_tokens_seen": 463840,
      "step": 31
    },
    {
      "epoch": 0.4115755627009646,
      "grad_norm": 394.77691650390625,
      "learning_rate": 2.666666666666667e-07,
      "loss": 5.9207,
      "num_input_tokens_seen": 478816,
      "step": 32
    },
    {
      "epoch": 0.42443729903536975,
      "grad_norm": 440.14697265625,
      "learning_rate": 2.75e-07,
      "loss": 5.7661,
      "num_input_tokens_seen": 494464,
      "step": 33
    },
    {
      "epoch": 0.43729903536977494,
      "grad_norm": 436.6060791015625,
      "learning_rate": 2.8333333333333336e-07,
      "loss": 5.6168,
      "num_input_tokens_seen": 510080,
      "step": 34
    },
    {
      "epoch": 0.45016077170418006,
      "grad_norm": 388.576416015625,
      "learning_rate": 2.916666666666667e-07,
      "loss": 5.3367,
      "num_input_tokens_seen": 525216,
      "step": 35
    },
    {
      "epoch": 0.4630225080385852,
      "grad_norm": 327.9267272949219,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 4.9751,
      "num_input_tokens_seen": 539648,
      "step": 36
    },
    {
      "epoch": 0.4758842443729904,
      "grad_norm": 322.6181335449219,
      "learning_rate": 3.083333333333334e-07,
      "loss": 4.7041,
      "num_input_tokens_seen": 554080,
      "step": 37
    },
    {
      "epoch": 0.4887459807073955,
      "grad_norm": 313.6160888671875,
      "learning_rate": 3.166666666666667e-07,
      "loss": 4.4631,
      "num_input_tokens_seen": 568960,
      "step": 38
    },
    {
      "epoch": 0.5016077170418006,
      "grad_norm": 299.7319641113281,
      "learning_rate": 3.25e-07,
      "loss": 4.1912,
      "num_input_tokens_seen": 583904,
      "step": 39
    },
    {
      "epoch": 0.5144694533762058,
      "grad_norm": 308.4530944824219,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 3.9146,
      "num_input_tokens_seen": 598848,
      "step": 40
    },
    {
      "epoch": 0.5273311897106109,
      "grad_norm": 315.37396240234375,
      "learning_rate": 3.416666666666667e-07,
      "loss": 3.053,
      "num_input_tokens_seen": 614208,
      "step": 41
    },
    {
      "epoch": 0.5401929260450161,
      "grad_norm": 263.33258056640625,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 1.5544,
      "num_input_tokens_seen": 629280,
      "step": 42
    },
    {
      "epoch": 0.5530546623794212,
      "grad_norm": 177.95458984375,
      "learning_rate": 3.583333333333334e-07,
      "loss": 1.0549,
      "num_input_tokens_seen": 643968,
      "step": 43
    },
    {
      "epoch": 0.5659163987138264,
      "grad_norm": 142.09307861328125,
      "learning_rate": 3.666666666666667e-07,
      "loss": 0.711,
      "num_input_tokens_seen": 659040,
      "step": 44
    },
    {
      "epoch": 0.5787781350482315,
      "grad_norm": 93.70928192138672,
      "learning_rate": 3.75e-07,
      "loss": 0.5127,
      "num_input_tokens_seen": 674464,
      "step": 45
    },
    {
      "epoch": 0.5916398713826366,
      "grad_norm": 65.4582290649414,
      "learning_rate": 3.8333333333333335e-07,
      "loss": 0.4143,
      "num_input_tokens_seen": 689216,
      "step": 46
    },
    {
      "epoch": 0.6045016077170418,
      "grad_norm": 51.321414947509766,
      "learning_rate": 3.9166666666666675e-07,
      "loss": 0.4014,
      "num_input_tokens_seen": 704448,
      "step": 47
    },
    {
      "epoch": 0.617363344051447,
      "grad_norm": 38.20650100708008,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.384,
      "num_input_tokens_seen": 719520,
      "step": 48
    },
    {
      "epoch": 0.6302250803858521,
      "grad_norm": 70.43089294433594,
      "learning_rate": 4.083333333333334e-07,
      "loss": 0.3017,
      "num_input_tokens_seen": 735520,
      "step": 49
    },
    {
      "epoch": 0.6430868167202572,
      "grad_norm": 47.982505798339844,
      "learning_rate": 4.1666666666666667e-07,
      "loss": 0.3031,
      "num_input_tokens_seen": 750976,
      "step": 50
    },
    {
      "epoch": 0.6559485530546624,
      "grad_norm": 27.063344955444336,
      "learning_rate": 4.2500000000000006e-07,
      "loss": 0.2818,
      "num_input_tokens_seen": 765728,
      "step": 51
    },
    {
      "epoch": 0.6688102893890675,
      "grad_norm": 60.75875473022461,
      "learning_rate": 4.333333333333334e-07,
      "loss": 0.2881,
      "num_input_tokens_seen": 780608,
      "step": 52
    },
    {
      "epoch": 0.6816720257234726,
      "grad_norm": 56.81061935424805,
      "learning_rate": 4.416666666666667e-07,
      "loss": 0.2943,
      "num_input_tokens_seen": 796192,
      "step": 53
    },
    {
      "epoch": 0.6945337620578779,
      "grad_norm": 31.529571533203125,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 0.2781,
      "num_input_tokens_seen": 810496,
      "step": 54
    },
    {
      "epoch": 0.707395498392283,
      "grad_norm": 33.71590805053711,
      "learning_rate": 4.583333333333333e-07,
      "loss": 0.2724,
      "num_input_tokens_seen": 826048,
      "step": 55
    },
    {
      "epoch": 0.7202572347266881,
      "grad_norm": 26.352554321289062,
      "learning_rate": 4.666666666666667e-07,
      "loss": 0.252,
      "num_input_tokens_seen": 840512,
      "step": 56
    },
    {
      "epoch": 0.7331189710610932,
      "grad_norm": 15.606438636779785,
      "learning_rate": 4.7500000000000006e-07,
      "loss": 0.2482,
      "num_input_tokens_seen": 855808,
      "step": 57
    },
    {
      "epoch": 0.7459807073954984,
      "grad_norm": 31.445789337158203,
      "learning_rate": 4.833333333333334e-07,
      "loss": 0.2212,
      "num_input_tokens_seen": 871520,
      "step": 58
    },
    {
      "epoch": 0.7588424437299035,
      "grad_norm": 9.967268943786621,
      "learning_rate": 4.916666666666667e-07,
      "loss": 0.2408,
      "num_input_tokens_seen": 886144,
      "step": 59
    },
    {
      "epoch": 0.7717041800643086,
      "grad_norm": 23.841659545898438,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.2133,
      "num_input_tokens_seen": 901408,
      "step": 60
    },
    {
      "epoch": 0.7845659163987139,
      "grad_norm": 16.51668357849121,
      "learning_rate": 5.083333333333334e-07,
      "loss": 0.2319,
      "num_input_tokens_seen": 916672,
      "step": 61
    },
    {
      "epoch": 0.797427652733119,
      "grad_norm": 51.05732345581055,
      "learning_rate": 5.166666666666667e-07,
      "loss": 0.2703,
      "num_input_tokens_seen": 931168,
      "step": 62
    },
    {
      "epoch": 0.8102893890675241,
      "grad_norm": 61.92572784423828,
      "learning_rate": 5.250000000000001e-07,
      "loss": 0.2647,
      "num_input_tokens_seen": 946816,
      "step": 63
    },
    {
      "epoch": 0.8231511254019293,
      "grad_norm": 10.283011436462402,
      "learning_rate": 5.333333333333335e-07,
      "loss": 0.2288,
      "num_input_tokens_seen": 961248,
      "step": 64
    },
    {
      "epoch": 0.8360128617363344,
      "grad_norm": 45.712772369384766,
      "learning_rate": 5.416666666666667e-07,
      "loss": 0.2426,
      "num_input_tokens_seen": 976736,
      "step": 65
    },
    {
      "epoch": 0.8488745980707395,
      "grad_norm": 22.493711471557617,
      "learning_rate": 5.5e-07,
      "loss": 0.1936,
      "num_input_tokens_seen": 992192,
      "step": 66
    },
    {
      "epoch": 0.8617363344051447,
      "grad_norm": 10.771052360534668,
      "learning_rate": 5.583333333333333e-07,
      "loss": 0.192,
      "num_input_tokens_seen": 1007808,
      "step": 67
    },
    {
      "epoch": 0.8745980707395499,
      "grad_norm": 11.903575897216797,
      "learning_rate": 5.666666666666667e-07,
      "loss": 0.1956,
      "num_input_tokens_seen": 1022176,
      "step": 68
    },
    {
      "epoch": 0.887459807073955,
      "grad_norm": 23.1299991607666,
      "learning_rate": 5.750000000000001e-07,
      "loss": 0.1862,
      "num_input_tokens_seen": 1037280,
      "step": 69
    },
    {
      "epoch": 0.9003215434083601,
      "grad_norm": 11.018325805664062,
      "learning_rate": 5.833333333333334e-07,
      "loss": 0.195,
      "num_input_tokens_seen": 1051392,
      "step": 70
    },
    {
      "epoch": 0.9131832797427653,
      "grad_norm": 27.96196174621582,
      "learning_rate": 5.916666666666667e-07,
      "loss": 0.1971,
      "num_input_tokens_seen": 1066432,
      "step": 71
    },
    {
      "epoch": 0.9260450160771704,
      "grad_norm": 14.441658020019531,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.1683,
      "num_input_tokens_seen": 1081696,
      "step": 72
    },
    {
      "epoch": 0.9389067524115756,
      "grad_norm": 17.725786209106445,
      "learning_rate": 6.083333333333334e-07,
      "loss": 0.2003,
      "num_input_tokens_seen": 1096672,
      "step": 73
    },
    {
      "epoch": 0.9517684887459807,
      "grad_norm": 26.286319732666016,
      "learning_rate": 6.166666666666668e-07,
      "loss": 0.1543,
      "num_input_tokens_seen": 1111488,
      "step": 74
    },
    {
      "epoch": 0.9646302250803859,
      "grad_norm": 38.698097229003906,
      "learning_rate": 6.25e-07,
      "loss": 0.1982,
      "num_input_tokens_seen": 1126368,
      "step": 75
    },
    {
      "epoch": 0.977491961414791,
      "grad_norm": 8.287293434143066,
      "learning_rate": 6.333333333333334e-07,
      "loss": 0.1545,
      "num_input_tokens_seen": 1141536,
      "step": 76
    },
    {
      "epoch": 0.9903536977491961,
      "grad_norm": 44.253807067871094,
      "learning_rate": 6.416666666666667e-07,
      "loss": 0.1573,
      "num_input_tokens_seen": 1156320,
      "step": 77
    },
    {
      "epoch": 1.0032154340836013,
      "grad_norm": 57.11432647705078,
      "learning_rate": 6.5e-07,
      "loss": 0.1788,
      "num_input_tokens_seen": 1171904,
      "step": 78
    },
    {
      "epoch": 1.0160771704180065,
      "grad_norm": 21.049449920654297,
      "learning_rate": 6.583333333333333e-07,
      "loss": 0.187,
      "num_input_tokens_seen": 1187232,
      "step": 79
    },
    {
      "epoch": 1.0289389067524115,
      "grad_norm": 67.61766052246094,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.2009,
      "num_input_tokens_seen": 1201632,
      "step": 80
    },
    {
      "epoch": 1.0418006430868167,
      "grad_norm": 91.35673522949219,
      "learning_rate": 6.750000000000001e-07,
      "loss": 0.2655,
      "num_input_tokens_seen": 1216832,
      "step": 81
    },
    {
      "epoch": 1.0546623794212218,
      "grad_norm": 54.41016387939453,
      "learning_rate": 6.833333333333334e-07,
      "loss": 0.2041,
      "num_input_tokens_seen": 1232128,
      "step": 82
    },
    {
      "epoch": 1.067524115755627,
      "grad_norm": 10.082817077636719,
      "learning_rate": 6.916666666666668e-07,
      "loss": 0.1675,
      "num_input_tokens_seen": 1246944,
      "step": 83
    },
    {
      "epoch": 1.0803858520900322,
      "grad_norm": 43.82609558105469,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.2097,
      "num_input_tokens_seen": 1262624,
      "step": 84
    },
    {
      "epoch": 1.0932475884244373,
      "grad_norm": 51.51130676269531,
      "learning_rate": 7.083333333333334e-07,
      "loss": 0.2171,
      "num_input_tokens_seen": 1278080,
      "step": 85
    },
    {
      "epoch": 1.1061093247588425,
      "grad_norm": 35.92145538330078,
      "learning_rate": 7.166666666666668e-07,
      "loss": 0.1702,
      "num_input_tokens_seen": 1293280,
      "step": 86
    },
    {
      "epoch": 1.1189710610932475,
      "grad_norm": 8.067242622375488,
      "learning_rate": 7.25e-07,
      "loss": 0.1255,
      "num_input_tokens_seen": 1307456,
      "step": 87
    },
    {
      "epoch": 1.1318327974276527,
      "grad_norm": 28.8727970123291,
      "learning_rate": 7.333333333333334e-07,
      "loss": 0.1826,
      "num_input_tokens_seen": 1323168,
      "step": 88
    },
    {
      "epoch": 1.144694533762058,
      "grad_norm": 45.813865661621094,
      "learning_rate": 7.416666666666668e-07,
      "loss": 0.2039,
      "num_input_tokens_seen": 1337984,
      "step": 89
    },
    {
      "epoch": 1.157556270096463,
      "grad_norm": 53.024105072021484,
      "learning_rate": 7.5e-07,
      "loss": 0.2337,
      "num_input_tokens_seen": 1353568,
      "step": 90
    },
    {
      "epoch": 1.1704180064308682,
      "grad_norm": 17.642776489257812,
      "learning_rate": 7.583333333333334e-07,
      "loss": 0.1466,
      "num_input_tokens_seen": 1368800,
      "step": 91
    },
    {
      "epoch": 1.1832797427652733,
      "grad_norm": 17.741811752319336,
      "learning_rate": 7.666666666666667e-07,
      "loss": 0.1295,
      "num_input_tokens_seen": 1384192,
      "step": 92
    },
    {
      "epoch": 1.1961414790996785,
      "grad_norm": 24.114030838012695,
      "learning_rate": 7.750000000000001e-07,
      "loss": 0.1525,
      "num_input_tokens_seen": 1398784,
      "step": 93
    },
    {
      "epoch": 1.2090032154340835,
      "grad_norm": 27.668102264404297,
      "learning_rate": 7.833333333333335e-07,
      "loss": 0.1735,
      "num_input_tokens_seen": 1414304,
      "step": 94
    },
    {
      "epoch": 1.2218649517684887,
      "grad_norm": 7.892695426940918,
      "learning_rate": 7.916666666666667e-07,
      "loss": 0.1484,
      "num_input_tokens_seen": 1430880,
      "step": 95
    },
    {
      "epoch": 1.234726688102894,
      "grad_norm": 12.985011100769043,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.1517,
      "num_input_tokens_seen": 1445760,
      "step": 96
    },
    {
      "epoch": 1.247588424437299,
      "grad_norm": 20.373502731323242,
      "learning_rate": 8.083333333333334e-07,
      "loss": 0.1429,
      "num_input_tokens_seen": 1460576,
      "step": 97
    },
    {
      "epoch": 1.2604501607717042,
      "grad_norm": 8.579370498657227,
      "learning_rate": 8.166666666666668e-07,
      "loss": 0.151,
      "num_input_tokens_seen": 1476032,
      "step": 98
    },
    {
      "epoch": 1.2733118971061093,
      "grad_norm": 6.366987705230713,
      "learning_rate": 8.250000000000001e-07,
      "loss": 0.1217,
      "num_input_tokens_seen": 1491008,
      "step": 99
    },
    {
      "epoch": 1.2861736334405145,
      "grad_norm": 19.89562225341797,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.1366,
      "num_input_tokens_seen": 1505120,
      "step": 100
    },
    {
      "epoch": 1.2990353697749195,
      "grad_norm": 10.997241020202637,
      "learning_rate": 8.416666666666667e-07,
      "loss": 0.1534,
      "num_input_tokens_seen": 1520736,
      "step": 101
    },
    {
      "epoch": 1.3118971061093248,
      "grad_norm": 17.20572280883789,
      "learning_rate": 8.500000000000001e-07,
      "loss": 0.141,
      "num_input_tokens_seen": 1535424,
      "step": 102
    },
    {
      "epoch": 1.32475884244373,
      "grad_norm": 10.88858413696289,
      "learning_rate": 8.583333333333334e-07,
      "loss": 0.1238,
      "num_input_tokens_seen": 1549856,
      "step": 103
    },
    {
      "epoch": 1.337620578778135,
      "grad_norm": 6.872950077056885,
      "learning_rate": 8.666666666666668e-07,
      "loss": 0.1241,
      "num_input_tokens_seen": 1564512,
      "step": 104
    },
    {
      "epoch": 1.3504823151125402,
      "grad_norm": 6.931344509124756,
      "learning_rate": 8.75e-07,
      "loss": 0.1414,
      "num_input_tokens_seen": 1578976,
      "step": 105
    },
    {
      "epoch": 1.3633440514469453,
      "grad_norm": 12.237205505371094,
      "learning_rate": 8.833333333333334e-07,
      "loss": 0.1296,
      "num_input_tokens_seen": 1593952,
      "step": 106
    },
    {
      "epoch": 1.3762057877813505,
      "grad_norm": 13.147500991821289,
      "learning_rate": 8.916666666666668e-07,
      "loss": 0.1232,
      "num_input_tokens_seen": 1608704,
      "step": 107
    },
    {
      "epoch": 1.3890675241157555,
      "grad_norm": 23.525880813598633,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.1625,
      "num_input_tokens_seen": 1623936,
      "step": 108
    },
    {
      "epoch": 1.4019292604501608,
      "grad_norm": 25.576210021972656,
      "learning_rate": 9.083333333333335e-07,
      "loss": 0.1509,
      "num_input_tokens_seen": 1639264,
      "step": 109
    },
    {
      "epoch": 1.414790996784566,
      "grad_norm": 18.12908935546875,
      "learning_rate": 9.166666666666666e-07,
      "loss": 0.1416,
      "num_input_tokens_seen": 1654528,
      "step": 110
    },
    {
      "epoch": 1.427652733118971,
      "grad_norm": 14.664992332458496,
      "learning_rate": 9.25e-07,
      "loss": 0.1481,
      "num_input_tokens_seen": 1669824,
      "step": 111
    },
    {
      "epoch": 1.4405144694533762,
      "grad_norm": 17.804119110107422,
      "learning_rate": 9.333333333333334e-07,
      "loss": 0.1303,
      "num_input_tokens_seen": 1684800,
      "step": 112
    },
    {
      "epoch": 1.4533762057877815,
      "grad_norm": 10.886981964111328,
      "learning_rate": 9.416666666666667e-07,
      "loss": 0.116,
      "num_input_tokens_seen": 1699712,
      "step": 113
    },
    {
      "epoch": 1.4662379421221865,
      "grad_norm": 14.883463859558105,
      "learning_rate": 9.500000000000001e-07,
      "loss": 0.0981,
      "num_input_tokens_seen": 1714208,
      "step": 114
    },
    {
      "epoch": 1.4790996784565915,
      "grad_norm": 9.800952911376953,
      "learning_rate": 9.583333333333334e-07,
      "loss": 0.1174,
      "num_input_tokens_seen": 1728672,
      "step": 115
    },
    {
      "epoch": 1.4919614147909968,
      "grad_norm": 8.804801940917969,
      "learning_rate": 9.666666666666668e-07,
      "loss": 0.1458,
      "num_input_tokens_seen": 1743008,
      "step": 116
    },
    {
      "epoch": 1.504823151125402,
      "grad_norm": 9.836427688598633,
      "learning_rate": 9.750000000000002e-07,
      "loss": 0.0952,
      "num_input_tokens_seen": 1758016,
      "step": 117
    },
    {
      "epoch": 1.517684887459807,
      "grad_norm": 7.373986721038818,
      "learning_rate": 9.833333333333334e-07,
      "loss": 0.1233,
      "num_input_tokens_seen": 1772512,
      "step": 118
    },
    {
      "epoch": 1.5305466237942122,
      "grad_norm": 16.394031524658203,
      "learning_rate": 9.916666666666668e-07,
      "loss": 0.127,
      "num_input_tokens_seen": 1787808,
      "step": 119
    },
    {
      "epoch": 1.5434083601286175,
      "grad_norm": 8.336946487426758,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.1121,
      "num_input_tokens_seen": 1803104,
      "step": 120
    },
    {
      "epoch": 1.5562700964630225,
      "grad_norm": 28.298938751220703,
      "learning_rate": 1.0083333333333333e-06,
      "loss": 0.1432,
      "num_input_tokens_seen": 1817632,
      "step": 121
    },
    {
      "epoch": 1.5691318327974275,
      "grad_norm": 25.474973678588867,
      "learning_rate": 1.0166666666666667e-06,
      "loss": 0.1446,
      "num_input_tokens_seen": 1832576,
      "step": 122
    },
    {
      "epoch": 1.5819935691318328,
      "grad_norm": 12.33470630645752,
      "learning_rate": 1.025e-06,
      "loss": 0.1056,
      "num_input_tokens_seen": 1847872,
      "step": 123
    },
    {
      "epoch": 1.594855305466238,
      "grad_norm": 16.17420768737793,
      "learning_rate": 1.0333333333333333e-06,
      "loss": 0.1193,
      "num_input_tokens_seen": 1863008,
      "step": 124
    },
    {
      "epoch": 1.607717041800643,
      "grad_norm": 23.109798431396484,
      "learning_rate": 1.0416666666666667e-06,
      "loss": 0.1409,
      "num_input_tokens_seen": 1878688,
      "step": 125
    },
    {
      "epoch": 1.6205787781350482,
      "grad_norm": 15.091007232666016,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 0.1154,
      "num_input_tokens_seen": 1894144,
      "step": 126
    },
    {
      "epoch": 1.6334405144694535,
      "grad_norm": 7.409396171569824,
      "learning_rate": 1.0583333333333335e-06,
      "loss": 0.1046,
      "num_input_tokens_seen": 1909504,
      "step": 127
    },
    {
      "epoch": 1.6463022508038585,
      "grad_norm": 12.553366661071777,
      "learning_rate": 1.066666666666667e-06,
      "loss": 0.09,
      "num_input_tokens_seen": 1924896,
      "step": 128
    },
    {
      "epoch": 1.6591639871382635,
      "grad_norm": 10.23271369934082,
      "learning_rate": 1.075e-06,
      "loss": 0.0858,
      "num_input_tokens_seen": 1939232,
      "step": 129
    },
    {
      "epoch": 1.6720257234726688,
      "grad_norm": 6.091500282287598,
      "learning_rate": 1.0833333333333335e-06,
      "loss": 0.0782,
      "num_input_tokens_seen": 1954720,
      "step": 130
    },
    {
      "epoch": 1.684887459807074,
      "grad_norm": 12.670690536499023,
      "learning_rate": 1.0916666666666667e-06,
      "loss": 0.1429,
      "num_input_tokens_seen": 1969632,
      "step": 131
    },
    {
      "epoch": 1.697749196141479,
      "grad_norm": 12.42375659942627,
      "learning_rate": 1.1e-06,
      "loss": 0.1121,
      "num_input_tokens_seen": 1984544,
      "step": 132
    },
    {
      "epoch": 1.7106109324758842,
      "grad_norm": 4.910019874572754,
      "learning_rate": 1.1083333333333335e-06,
      "loss": 0.0458,
      "num_input_tokens_seen": 1999584,
      "step": 133
    },
    {
      "epoch": 1.7234726688102895,
      "grad_norm": 8.262114524841309,
      "learning_rate": 1.1166666666666666e-06,
      "loss": 0.1217,
      "num_input_tokens_seen": 2014048,
      "step": 134
    },
    {
      "epoch": 1.7363344051446945,
      "grad_norm": 21.927522659301758,
      "learning_rate": 1.125e-06,
      "loss": 0.1253,
      "num_input_tokens_seen": 2029312,
      "step": 135
    },
    {
      "epoch": 1.7491961414790995,
      "grad_norm": 8.816388130187988,
      "learning_rate": 1.1333333333333334e-06,
      "loss": 0.077,
      "num_input_tokens_seen": 2044192,
      "step": 136
    },
    {
      "epoch": 1.762057877813505,
      "grad_norm": 6.877133846282959,
      "learning_rate": 1.1416666666666668e-06,
      "loss": 0.0719,
      "num_input_tokens_seen": 2059552,
      "step": 137
    },
    {
      "epoch": 1.77491961414791,
      "grad_norm": 5.565485000610352,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 0.0916,
      "num_input_tokens_seen": 2074336,
      "step": 138
    },
    {
      "epoch": 1.787781350482315,
      "grad_norm": 11.287223815917969,
      "learning_rate": 1.1583333333333334e-06,
      "loss": 0.0812,
      "num_input_tokens_seen": 2089280,
      "step": 139
    },
    {
      "epoch": 1.8006430868167203,
      "grad_norm": 7.971100807189941,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 0.1176,
      "num_input_tokens_seen": 2104256,
      "step": 140
    },
    {
      "epoch": 1.8135048231511255,
      "grad_norm": 7.78786563873291,
      "learning_rate": 1.175e-06,
      "loss": 0.0631,
      "num_input_tokens_seen": 2119232,
      "step": 141
    },
    {
      "epoch": 1.8263665594855305,
      "grad_norm": 8.365852355957031,
      "learning_rate": 1.1833333333333334e-06,
      "loss": 0.1137,
      "num_input_tokens_seen": 2133824,
      "step": 142
    },
    {
      "epoch": 1.8392282958199357,
      "grad_norm": 16.2335262298584,
      "learning_rate": 1.1916666666666668e-06,
      "loss": 0.0958,
      "num_input_tokens_seen": 2148480,
      "step": 143
    },
    {
      "epoch": 1.852090032154341,
      "grad_norm": 8.455872535705566,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.1343,
      "num_input_tokens_seen": 2163328,
      "step": 144
    },
    {
      "epoch": 1.864951768488746,
      "grad_norm": 13.241278648376465,
      "learning_rate": 1.2083333333333333e-06,
      "loss": 0.1101,
      "num_input_tokens_seen": 2177568,
      "step": 145
    },
    {
      "epoch": 1.877813504823151,
      "grad_norm": 13.46755313873291,
      "learning_rate": 1.2166666666666667e-06,
      "loss": 0.0914,
      "num_input_tokens_seen": 2192384,
      "step": 146
    },
    {
      "epoch": 1.8906752411575563,
      "grad_norm": 7.21525764465332,
      "learning_rate": 1.2250000000000001e-06,
      "loss": 0.1114,
      "num_input_tokens_seen": 2207584,
      "step": 147
    },
    {
      "epoch": 1.9035369774919615,
      "grad_norm": 5.000830173492432,
      "learning_rate": 1.2333333333333335e-06,
      "loss": 0.083,
      "num_input_tokens_seen": 2222208,
      "step": 148
    },
    {
      "epoch": 1.9163987138263665,
      "grad_norm": 8.995044708251953,
      "learning_rate": 1.2416666666666667e-06,
      "loss": 0.1095,
      "num_input_tokens_seen": 2237760,
      "step": 149
    },
    {
      "epoch": 1.9292604501607717,
      "grad_norm": 7.872910976409912,
      "learning_rate": 1.25e-06,
      "loss": 0.0662,
      "num_input_tokens_seen": 2252768,
      "step": 150
    },
    {
      "epoch": 1.942122186495177,
      "grad_norm": 11.594476699829102,
      "learning_rate": 1.2583333333333333e-06,
      "loss": 0.0979,
      "num_input_tokens_seen": 2268736,
      "step": 151
    },
    {
      "epoch": 1.954983922829582,
      "grad_norm": 14.245850563049316,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 0.0847,
      "num_input_tokens_seen": 2283840,
      "step": 152
    },
    {
      "epoch": 1.967845659163987,
      "grad_norm": 12.000141143798828,
      "learning_rate": 1.275e-06,
      "loss": 0.0949,
      "num_input_tokens_seen": 2297696,
      "step": 153
    },
    {
      "epoch": 1.9807073954983923,
      "grad_norm": 16.763721466064453,
      "learning_rate": 1.2833333333333335e-06,
      "loss": 0.1206,
      "num_input_tokens_seen": 2311936,
      "step": 154
    },
    {
      "epoch": 1.9935691318327975,
      "grad_norm": 22.926712036132812,
      "learning_rate": 1.2916666666666669e-06,
      "loss": 0.139,
      "num_input_tokens_seen": 2327392,
      "step": 155
    },
    {
      "epoch": 2.0064308681672025,
      "grad_norm": 7.715733528137207,
      "learning_rate": 1.3e-06,
      "loss": 0.07,
      "num_input_tokens_seen": 2341952,
      "step": 156
    },
    {
      "epoch": 2.0192926045016075,
      "grad_norm": 5.047181129455566,
      "learning_rate": 1.3083333333333334e-06,
      "loss": 0.0562,
      "num_input_tokens_seen": 2356768,
      "step": 157
    },
    {
      "epoch": 2.032154340836013,
      "grad_norm": 10.79956340789795,
      "learning_rate": 1.3166666666666666e-06,
      "loss": 0.0456,
      "num_input_tokens_seen": 2371584,
      "step": 158
    },
    {
      "epoch": 2.045016077170418,
      "grad_norm": 13.864229202270508,
      "learning_rate": 1.3250000000000002e-06,
      "loss": 0.0582,
      "num_input_tokens_seen": 2386880,
      "step": 159
    },
    {
      "epoch": 2.057877813504823,
      "grad_norm": 7.294124603271484,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.0452,
      "num_input_tokens_seen": 2401248,
      "step": 160
    },
    {
      "epoch": 2.0707395498392285,
      "grad_norm": 5.838871479034424,
      "learning_rate": 1.3416666666666666e-06,
      "loss": 0.0553,
      "num_input_tokens_seen": 2415968,
      "step": 161
    },
    {
      "epoch": 2.0836012861736335,
      "grad_norm": 20.286243438720703,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.1108,
      "num_input_tokens_seen": 2430368,
      "step": 162
    },
    {
      "epoch": 2.0964630225080385,
      "grad_norm": 12.720942497253418,
      "learning_rate": 1.3583333333333334e-06,
      "loss": 0.0791,
      "num_input_tokens_seen": 2445056,
      "step": 163
    },
    {
      "epoch": 2.1093247588424435,
      "grad_norm": 9.107832908630371,
      "learning_rate": 1.3666666666666668e-06,
      "loss": 0.0637,
      "num_input_tokens_seen": 2459744,
      "step": 164
    },
    {
      "epoch": 2.122186495176849,
      "grad_norm": 6.473385334014893,
      "learning_rate": 1.3750000000000002e-06,
      "loss": 0.0404,
      "num_input_tokens_seen": 2474400,
      "step": 165
    },
    {
      "epoch": 2.135048231511254,
      "grad_norm": 6.510437488555908,
      "learning_rate": 1.3833333333333336e-06,
      "loss": 0.0372,
      "num_input_tokens_seen": 2489280,
      "step": 166
    },
    {
      "epoch": 2.147909967845659,
      "grad_norm": 8.90833854675293,
      "learning_rate": 1.3916666666666668e-06,
      "loss": 0.045,
      "num_input_tokens_seen": 2503776,
      "step": 167
    },
    {
      "epoch": 2.1607717041800645,
      "grad_norm": 11.84021282196045,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.0964,
      "num_input_tokens_seen": 2518752,
      "step": 168
    },
    {
      "epoch": 2.1736334405144695,
      "grad_norm": 5.904385566711426,
      "learning_rate": 1.4083333333333335e-06,
      "loss": 0.0543,
      "num_input_tokens_seen": 2533568,
      "step": 169
    },
    {
      "epoch": 2.1864951768488745,
      "grad_norm": 6.935682773590088,
      "learning_rate": 1.4166666666666667e-06,
      "loss": 0.071,
      "num_input_tokens_seen": 2548640,
      "step": 170
    },
    {
      "epoch": 2.19935691318328,
      "grad_norm": 3.85262131690979,
      "learning_rate": 1.425e-06,
      "loss": 0.0285,
      "num_input_tokens_seen": 2563232,
      "step": 171
    },
    {
      "epoch": 2.212218649517685,
      "grad_norm": 5.231224060058594,
      "learning_rate": 1.4333333333333335e-06,
      "loss": 0.0399,
      "num_input_tokens_seen": 2578336,
      "step": 172
    },
    {
      "epoch": 2.22508038585209,
      "grad_norm": 6.751733779907227,
      "learning_rate": 1.4416666666666667e-06,
      "loss": 0.067,
      "num_input_tokens_seen": 2594336,
      "step": 173
    },
    {
      "epoch": 2.237942122186495,
      "grad_norm": 4.619236469268799,
      "learning_rate": 1.45e-06,
      "loss": 0.0436,
      "num_input_tokens_seen": 2609408,
      "step": 174
    },
    {
      "epoch": 2.2508038585209005,
      "grad_norm": 4.799732685089111,
      "learning_rate": 1.4583333333333335e-06,
      "loss": 0.0522,
      "num_input_tokens_seen": 2624288,
      "step": 175
    },
    {
      "epoch": 2.2636655948553055,
      "grad_norm": 7.050292015075684,
      "learning_rate": 1.4666666666666669e-06,
      "loss": 0.0521,
      "num_input_tokens_seen": 2639296,
      "step": 176
    },
    {
      "epoch": 2.2765273311897105,
      "grad_norm": 6.788993835449219,
      "learning_rate": 1.475e-06,
      "loss": 0.0446,
      "num_input_tokens_seen": 2653856,
      "step": 177
    },
    {
      "epoch": 2.289389067524116,
      "grad_norm": 7.368555545806885,
      "learning_rate": 1.4833333333333337e-06,
      "loss": 0.0378,
      "num_input_tokens_seen": 2669216,
      "step": 178
    },
    {
      "epoch": 2.302250803858521,
      "grad_norm": 6.674912452697754,
      "learning_rate": 1.4916666666666669e-06,
      "loss": 0.0387,
      "num_input_tokens_seen": 2683264,
      "step": 179
    },
    {
      "epoch": 2.315112540192926,
      "grad_norm": 4.754708766937256,
      "learning_rate": 1.5e-06,
      "loss": 0.036,
      "num_input_tokens_seen": 2698112,
      "step": 180
    },
    {
      "epoch": 2.327974276527331,
      "grad_norm": 11.09841251373291,
      "learning_rate": 1.5083333333333336e-06,
      "loss": 0.0765,
      "num_input_tokens_seen": 2712800,
      "step": 181
    },
    {
      "epoch": 2.3408360128617365,
      "grad_norm": 13.097764015197754,
      "learning_rate": 1.5166666666666668e-06,
      "loss": 0.0884,
      "num_input_tokens_seen": 2728032,
      "step": 182
    },
    {
      "epoch": 2.3536977491961415,
      "grad_norm": 14.366617202758789,
      "learning_rate": 1.525e-06,
      "loss": 0.0801,
      "num_input_tokens_seen": 2742432,
      "step": 183
    },
    {
      "epoch": 2.3665594855305465,
      "grad_norm": 6.947451591491699,
      "learning_rate": 1.5333333333333334e-06,
      "loss": 0.0276,
      "num_input_tokens_seen": 2758176,
      "step": 184
    },
    {
      "epoch": 2.379421221864952,
      "grad_norm": 11.02580738067627,
      "learning_rate": 1.5416666666666668e-06,
      "loss": 0.0778,
      "num_input_tokens_seen": 2772768,
      "step": 185
    },
    {
      "epoch": 2.392282958199357,
      "grad_norm": 15.404431343078613,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.0726,
      "num_input_tokens_seen": 2787968,
      "step": 186
    },
    {
      "epoch": 2.405144694533762,
      "grad_norm": 19.688905715942383,
      "learning_rate": 1.5583333333333334e-06,
      "loss": 0.1381,
      "num_input_tokens_seen": 2802560,
      "step": 187
    },
    {
      "epoch": 2.418006430868167,
      "grad_norm": 5.732620716094971,
      "learning_rate": 1.566666666666667e-06,
      "loss": 0.0408,
      "num_input_tokens_seen": 2817856,
      "step": 188
    },
    {
      "epoch": 2.4308681672025725,
      "grad_norm": 9.736536026000977,
      "learning_rate": 1.5750000000000002e-06,
      "loss": 0.1066,
      "num_input_tokens_seen": 2833408,
      "step": 189
    },
    {
      "epoch": 2.4437299035369775,
      "grad_norm": 9.312838554382324,
      "learning_rate": 1.5833333333333333e-06,
      "loss": 0.0686,
      "num_input_tokens_seen": 2848832,
      "step": 190
    },
    {
      "epoch": 2.4565916398713825,
      "grad_norm": 7.711926460266113,
      "learning_rate": 1.591666666666667e-06,
      "loss": 0.0428,
      "num_input_tokens_seen": 2863968,
      "step": 191
    },
    {
      "epoch": 2.469453376205788,
      "grad_norm": 6.855398654937744,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0387,
      "num_input_tokens_seen": 2878944,
      "step": 192
    },
    {
      "epoch": 2.482315112540193,
      "grad_norm": 3.374630928039551,
      "learning_rate": 1.6083333333333333e-06,
      "loss": 0.0489,
      "num_input_tokens_seen": 2894112,
      "step": 193
    },
    {
      "epoch": 2.495176848874598,
      "grad_norm": 7.452945709228516,
      "learning_rate": 1.6166666666666667e-06,
      "loss": 0.0621,
      "num_input_tokens_seen": 2908928,
      "step": 194
    },
    {
      "epoch": 2.508038585209003,
      "grad_norm": 12.478065490722656,
      "learning_rate": 1.6250000000000001e-06,
      "loss": 0.0651,
      "num_input_tokens_seen": 2923680,
      "step": 195
    },
    {
      "epoch": 2.5209003215434085,
      "grad_norm": 4.181528091430664,
      "learning_rate": 1.6333333333333335e-06,
      "loss": 0.0398,
      "num_input_tokens_seen": 2939136,
      "step": 196
    },
    {
      "epoch": 2.5337620578778135,
      "grad_norm": 5.443283557891846,
      "learning_rate": 1.6416666666666667e-06,
      "loss": 0.0369,
      "num_input_tokens_seen": 2953760,
      "step": 197
    },
    {
      "epoch": 2.5466237942122185,
      "grad_norm": 7.586729526519775,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0582,
      "num_input_tokens_seen": 2968640,
      "step": 198
    },
    {
      "epoch": 2.559485530546624,
      "grad_norm": 6.357609272003174,
      "learning_rate": 1.6583333333333335e-06,
      "loss": 0.0479,
      "num_input_tokens_seen": 2983456,
      "step": 199
    },
    {
      "epoch": 2.572347266881029,
      "grad_norm": 8.761418342590332,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0561,
      "num_input_tokens_seen": 2998144,
      "step": 200
    },
    {
      "epoch": 2.585209003215434,
      "grad_norm": 7.058523654937744,
      "learning_rate": 1.6750000000000003e-06,
      "loss": 0.0497,
      "num_input_tokens_seen": 3013248,
      "step": 201
    },
    {
      "epoch": 2.598070739549839,
      "grad_norm": 8.091582298278809,
      "learning_rate": 1.6833333333333335e-06,
      "loss": 0.063,
      "num_input_tokens_seen": 3028320,
      "step": 202
    },
    {
      "epoch": 2.6109324758842445,
      "grad_norm": 9.102255821228027,
      "learning_rate": 1.6916666666666666e-06,
      "loss": 0.054,
      "num_input_tokens_seen": 3043232,
      "step": 203
    },
    {
      "epoch": 2.6237942122186495,
      "grad_norm": 9.521942138671875,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0729,
      "num_input_tokens_seen": 3058848,
      "step": 204
    },
    {
      "epoch": 2.6366559485530545,
      "grad_norm": 7.026569843292236,
      "learning_rate": 1.7083333333333334e-06,
      "loss": 0.0685,
      "num_input_tokens_seen": 3074080,
      "step": 205
    },
    {
      "epoch": 2.64951768488746,
      "grad_norm": 13.492867469787598,
      "learning_rate": 1.7166666666666668e-06,
      "loss": 0.0823,
      "num_input_tokens_seen": 3089152,
      "step": 206
    },
    {
      "epoch": 2.662379421221865,
      "grad_norm": 6.880157947540283,
      "learning_rate": 1.725e-06,
      "loss": 0.0322,
      "num_input_tokens_seen": 3103616,
      "step": 207
    },
    {
      "epoch": 2.67524115755627,
      "grad_norm": 8.232446670532227,
      "learning_rate": 1.7333333333333336e-06,
      "loss": 0.0821,
      "num_input_tokens_seen": 3119200,
      "step": 208
    },
    {
      "epoch": 2.688102893890675,
      "grad_norm": 7.365771293640137,
      "learning_rate": 1.7416666666666668e-06,
      "loss": 0.0561,
      "num_input_tokens_seen": 3134400,
      "step": 209
    },
    {
      "epoch": 2.7009646302250805,
      "grad_norm": 9.879140853881836,
      "learning_rate": 1.75e-06,
      "loss": 0.0468,
      "num_input_tokens_seen": 3149248,
      "step": 210
    },
    {
      "epoch": 2.7138263665594855,
      "grad_norm": 8.636083602905273,
      "learning_rate": 1.7583333333333336e-06,
      "loss": 0.0593,
      "num_input_tokens_seen": 3164800,
      "step": 211
    },
    {
      "epoch": 2.7266881028938905,
      "grad_norm": 5.015254497528076,
      "learning_rate": 1.7666666666666668e-06,
      "loss": 0.0403,
      "num_input_tokens_seen": 3179520,
      "step": 212
    },
    {
      "epoch": 2.739549839228296,
      "grad_norm": 7.730808258056641,
      "learning_rate": 1.7750000000000002e-06,
      "loss": 0.0459,
      "num_input_tokens_seen": 3194016,
      "step": 213
    },
    {
      "epoch": 2.752411575562701,
      "grad_norm": 6.433826923370361,
      "learning_rate": 1.7833333333333336e-06,
      "loss": 0.0509,
      "num_input_tokens_seen": 3208608,
      "step": 214
    },
    {
      "epoch": 2.765273311897106,
      "grad_norm": 7.32877779006958,
      "learning_rate": 1.7916666666666667e-06,
      "loss": 0.0873,
      "num_input_tokens_seen": 3224096,
      "step": 215
    },
    {
      "epoch": 2.778135048231511,
      "grad_norm": 7.283654689788818,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0618,
      "num_input_tokens_seen": 3239136,
      "step": 216
    },
    {
      "epoch": 2.7909967845659165,
      "grad_norm": 11.044650077819824,
      "learning_rate": 1.8083333333333335e-06,
      "loss": 0.1025,
      "num_input_tokens_seen": 3253184,
      "step": 217
    },
    {
      "epoch": 2.8038585209003215,
      "grad_norm": 7.287780284881592,
      "learning_rate": 1.816666666666667e-06,
      "loss": 0.0669,
      "num_input_tokens_seen": 3268000,
      "step": 218
    },
    {
      "epoch": 2.816720257234727,
      "grad_norm": 7.542795658111572,
      "learning_rate": 1.825e-06,
      "loss": 0.0447,
      "num_input_tokens_seen": 3282528,
      "step": 219
    },
    {
      "epoch": 2.829581993569132,
      "grad_norm": 9.812615394592285,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 0.0635,
      "num_input_tokens_seen": 3297824,
      "step": 220
    },
    {
      "epoch": 2.842443729903537,
      "grad_norm": 5.7050580978393555,
      "learning_rate": 1.8416666666666669e-06,
      "loss": 0.0614,
      "num_input_tokens_seen": 3312480,
      "step": 221
    },
    {
      "epoch": 2.855305466237942,
      "grad_norm": 13.298068046569824,
      "learning_rate": 1.85e-06,
      "loss": 0.0646,
      "num_input_tokens_seen": 3327392,
      "step": 222
    },
    {
      "epoch": 2.868167202572347,
      "grad_norm": 13.815607070922852,
      "learning_rate": 1.8583333333333335e-06,
      "loss": 0.0893,
      "num_input_tokens_seen": 3342944,
      "step": 223
    },
    {
      "epoch": 2.8810289389067525,
      "grad_norm": 6.954331398010254,
      "learning_rate": 1.8666666666666669e-06,
      "loss": 0.0653,
      "num_input_tokens_seen": 3358112,
      "step": 224
    },
    {
      "epoch": 2.8938906752411575,
      "grad_norm": 5.133541584014893,
      "learning_rate": 1.8750000000000003e-06,
      "loss": 0.0402,
      "num_input_tokens_seen": 3373472,
      "step": 225
    },
    {
      "epoch": 2.906752411575563,
      "grad_norm": 7.754403114318848,
      "learning_rate": 1.8833333333333334e-06,
      "loss": 0.0407,
      "num_input_tokens_seen": 3389088,
      "step": 226
    },
    {
      "epoch": 2.919614147909968,
      "grad_norm": 9.570775985717773,
      "learning_rate": 1.8916666666666668e-06,
      "loss": 0.0949,
      "num_input_tokens_seen": 3403616,
      "step": 227
    },
    {
      "epoch": 2.932475884244373,
      "grad_norm": 9.21279525756836,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0789,
      "num_input_tokens_seen": 3418944,
      "step": 228
    },
    {
      "epoch": 2.945337620578778,
      "grad_norm": 4.255781650543213,
      "learning_rate": 1.9083333333333334e-06,
      "loss": 0.0438,
      "num_input_tokens_seen": 3434048,
      "step": 229
    },
    {
      "epoch": 2.958199356913183,
      "grad_norm": 10.596036911010742,
      "learning_rate": 1.916666666666667e-06,
      "loss": 0.0905,
      "num_input_tokens_seen": 3449952,
      "step": 230
    },
    {
      "epoch": 2.9710610932475885,
      "grad_norm": 9.656909942626953,
      "learning_rate": 1.925e-06,
      "loss": 0.0495,
      "num_input_tokens_seen": 3464736,
      "step": 231
    },
    {
      "epoch": 2.9839228295819935,
      "grad_norm": 9.526041984558105,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 0.0642,
      "num_input_tokens_seen": 3480416,
      "step": 232
    },
    {
      "epoch": 2.996784565916399,
      "grad_norm": 5.788015365600586,
      "learning_rate": 1.9416666666666666e-06,
      "loss": 0.0607,
      "num_input_tokens_seen": 3495264,
      "step": 233
    },
    {
      "epoch": 3.009646302250804,
      "grad_norm": 6.213415145874023,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0363,
      "num_input_tokens_seen": 3510080,
      "step": 234
    },
    {
      "epoch": 3.022508038585209,
      "grad_norm": 7.382534980773926,
      "learning_rate": 1.9583333333333334e-06,
      "loss": 0.0492,
      "num_input_tokens_seen": 3524736,
      "step": 235
    },
    {
      "epoch": 3.035369774919614,
      "grad_norm": 9.54261302947998,
      "learning_rate": 1.9666666666666668e-06,
      "loss": 0.0373,
      "num_input_tokens_seen": 3539968,
      "step": 236
    },
    {
      "epoch": 3.0482315112540195,
      "grad_norm": 3.8869571685791016,
      "learning_rate": 1.975e-06,
      "loss": 0.0203,
      "num_input_tokens_seen": 3554464,
      "step": 237
    },
    {
      "epoch": 3.0610932475884245,
      "grad_norm": 2.183758497238159,
      "learning_rate": 1.9833333333333335e-06,
      "loss": 0.0175,
      "num_input_tokens_seen": 3569664,
      "step": 238
    },
    {
      "epoch": 3.0739549839228295,
      "grad_norm": 3.851379871368408,
      "learning_rate": 1.991666666666667e-06,
      "loss": 0.0497,
      "num_input_tokens_seen": 3585248,
      "step": 239
    },
    {
      "epoch": 3.0868167202572345,
      "grad_norm": 6.622572898864746,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0361,
      "num_input_tokens_seen": 3600160,
      "step": 240
    },
    {
      "epoch": 3.09967845659164,
      "grad_norm": 3.4328978061676025,
      "learning_rate": 2.0083333333333337e-06,
      "loss": 0.0193,
      "num_input_tokens_seen": 3615232,
      "step": 241
    },
    {
      "epoch": 3.112540192926045,
      "grad_norm": 8.150415420532227,
      "learning_rate": 2.0166666666666667e-06,
      "loss": 0.0142,
      "num_input_tokens_seen": 3629312,
      "step": 242
    },
    {
      "epoch": 3.12540192926045,
      "grad_norm": 5.3073835372924805,
      "learning_rate": 2.025e-06,
      "loss": 0.0415,
      "num_input_tokens_seen": 3644064,
      "step": 243
    },
    {
      "epoch": 3.1382636655948555,
      "grad_norm": 4.33547830581665,
      "learning_rate": 2.0333333333333335e-06,
      "loss": 0.0178,
      "num_input_tokens_seen": 3659328,
      "step": 244
    },
    {
      "epoch": 3.1511254019292605,
      "grad_norm": 2.770535469055176,
      "learning_rate": 2.041666666666667e-06,
      "loss": 0.0166,
      "num_input_tokens_seen": 3674720,
      "step": 245
    },
    {
      "epoch": 3.1639871382636655,
      "grad_norm": 8.939215660095215,
      "learning_rate": 2.05e-06,
      "loss": 0.0424,
      "num_input_tokens_seen": 3689984,
      "step": 246
    },
    {
      "epoch": 3.176848874598071,
      "grad_norm": 4.35013484954834,
      "learning_rate": 2.0583333333333337e-06,
      "loss": 0.0464,
      "num_input_tokens_seen": 3705216,
      "step": 247
    },
    {
      "epoch": 3.189710610932476,
      "grad_norm": 4.8758368492126465,
      "learning_rate": 2.0666666666666666e-06,
      "loss": 0.0235,
      "num_input_tokens_seen": 3719712,
      "step": 248
    },
    {
      "epoch": 3.202572347266881,
      "grad_norm": 2.769258499145508,
      "learning_rate": 2.075e-06,
      "loss": 0.0128,
      "num_input_tokens_seen": 3734272,
      "step": 249
    },
    {
      "epoch": 3.215434083601286,
      "grad_norm": 4.699342727661133,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 0.0319,
      "num_input_tokens_seen": 3750240,
      "step": 250
    },
    {
      "epoch": 3.2282958199356915,
      "grad_norm": 3.377748966217041,
      "learning_rate": 2.091666666666667e-06,
      "loss": 0.0196,
      "num_input_tokens_seen": 3764736,
      "step": 251
    },
    {
      "epoch": 3.2411575562700965,
      "grad_norm": 2.9469077587127686,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0326,
      "num_input_tokens_seen": 3779744,
      "step": 252
    },
    {
      "epoch": 3.2540192926045015,
      "grad_norm": 3.4729647636413574,
      "learning_rate": 2.1083333333333336e-06,
      "loss": 0.017,
      "num_input_tokens_seen": 3794208,
      "step": 253
    },
    {
      "epoch": 3.266881028938907,
      "grad_norm": 3.1130521297454834,
      "learning_rate": 2.116666666666667e-06,
      "loss": 0.0372,
      "num_input_tokens_seen": 3809376,
      "step": 254
    },
    {
      "epoch": 3.279742765273312,
      "grad_norm": 3.0094053745269775,
      "learning_rate": 2.125e-06,
      "loss": 0.0165,
      "num_input_tokens_seen": 3824384,
      "step": 255
    },
    {
      "epoch": 3.292604501607717,
      "grad_norm": 2.0758721828460693,
      "learning_rate": 2.133333333333334e-06,
      "loss": 0.0142,
      "num_input_tokens_seen": 3840000,
      "step": 256
    },
    {
      "epoch": 3.305466237942122,
      "grad_norm": 2.0254931449890137,
      "learning_rate": 2.1416666666666668e-06,
      "loss": 0.0117,
      "num_input_tokens_seen": 3854240,
      "step": 257
    },
    {
      "epoch": 3.3183279742765275,
      "grad_norm": 5.01600980758667,
      "learning_rate": 2.15e-06,
      "loss": 0.0264,
      "num_input_tokens_seen": 3869792,
      "step": 258
    },
    {
      "epoch": 3.3311897106109325,
      "grad_norm": 7.374160289764404,
      "learning_rate": 2.1583333333333336e-06,
      "loss": 0.034,
      "num_input_tokens_seen": 3885152,
      "step": 259
    },
    {
      "epoch": 3.3440514469453375,
      "grad_norm": 7.036656856536865,
      "learning_rate": 2.166666666666667e-06,
      "loss": 0.031,
      "num_input_tokens_seen": 3900032,
      "step": 260
    },
    {
      "epoch": 3.356913183279743,
      "grad_norm": 4.439852237701416,
      "learning_rate": 2.1750000000000004e-06,
      "loss": 0.018,
      "num_input_tokens_seen": 3914432,
      "step": 261
    },
    {
      "epoch": 3.369774919614148,
      "grad_norm": 8.757259368896484,
      "learning_rate": 2.1833333333333333e-06,
      "loss": 0.0461,
      "num_input_tokens_seen": 3929600,
      "step": 262
    },
    {
      "epoch": 3.382636655948553,
      "grad_norm": 4.993197917938232,
      "learning_rate": 2.191666666666667e-06,
      "loss": 0.0372,
      "num_input_tokens_seen": 3944032,
      "step": 263
    },
    {
      "epoch": 3.395498392282958,
      "grad_norm": 5.627339839935303,
      "learning_rate": 2.2e-06,
      "loss": 0.0471,
      "num_input_tokens_seen": 3958464,
      "step": 264
    },
    {
      "epoch": 3.4083601286173635,
      "grad_norm": 6.644600868225098,
      "learning_rate": 2.2083333333333335e-06,
      "loss": 0.037,
      "num_input_tokens_seen": 3973024,
      "step": 265
    },
    {
      "epoch": 3.4212218649517685,
      "grad_norm": 4.708102703094482,
      "learning_rate": 2.216666666666667e-06,
      "loss": 0.0245,
      "num_input_tokens_seen": 3987520,
      "step": 266
    },
    {
      "epoch": 3.4340836012861735,
      "grad_norm": 3.4480528831481934,
      "learning_rate": 2.2250000000000003e-06,
      "loss": 0.0233,
      "num_input_tokens_seen": 4002656,
      "step": 267
    },
    {
      "epoch": 3.446945337620579,
      "grad_norm": 5.0224175453186035,
      "learning_rate": 2.2333333333333333e-06,
      "loss": 0.0256,
      "num_input_tokens_seen": 4017824,
      "step": 268
    },
    {
      "epoch": 3.459807073954984,
      "grad_norm": 9.12070369720459,
      "learning_rate": 2.2416666666666667e-06,
      "loss": 0.0345,
      "num_input_tokens_seen": 4032480,
      "step": 269
    },
    {
      "epoch": 3.472668810289389,
      "grad_norm": 5.336618900299072,
      "learning_rate": 2.25e-06,
      "loss": 0.0656,
      "num_input_tokens_seen": 4047648,
      "step": 270
    },
    {
      "epoch": 3.485530546623794,
      "grad_norm": 4.003684997558594,
      "learning_rate": 2.2583333333333335e-06,
      "loss": 0.0247,
      "num_input_tokens_seen": 4062688,
      "step": 271
    },
    {
      "epoch": 3.4983922829581995,
      "grad_norm": 5.631625175476074,
      "learning_rate": 2.266666666666667e-06,
      "loss": 0.051,
      "num_input_tokens_seen": 4077856,
      "step": 272
    },
    {
      "epoch": 3.5112540192926045,
      "grad_norm": 4.748563766479492,
      "learning_rate": 2.2750000000000002e-06,
      "loss": 0.0417,
      "num_input_tokens_seen": 4092864,
      "step": 273
    },
    {
      "epoch": 3.5241157556270095,
      "grad_norm": 3.368995189666748,
      "learning_rate": 2.2833333333333336e-06,
      "loss": 0.0176,
      "num_input_tokens_seen": 4107584,
      "step": 274
    },
    {
      "epoch": 3.536977491961415,
      "grad_norm": 3.463752508163452,
      "learning_rate": 2.2916666666666666e-06,
      "loss": 0.0155,
      "num_input_tokens_seen": 4122080,
      "step": 275
    },
    {
      "epoch": 3.54983922829582,
      "grad_norm": 4.7195234298706055,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0135,
      "num_input_tokens_seen": 4137600,
      "step": 276
    },
    {
      "epoch": 3.562700964630225,
      "grad_norm": 6.3303680419921875,
      "learning_rate": 2.3083333333333334e-06,
      "loss": 0.0222,
      "num_input_tokens_seen": 4152960,
      "step": 277
    },
    {
      "epoch": 3.57556270096463,
      "grad_norm": 3.4051268100738525,
      "learning_rate": 2.316666666666667e-06,
      "loss": 0.0289,
      "num_input_tokens_seen": 4168640,
      "step": 278
    },
    {
      "epoch": 3.5884244372990355,
      "grad_norm": 3.971222162246704,
      "learning_rate": 2.325e-06,
      "loss": 0.0314,
      "num_input_tokens_seen": 4183616,
      "step": 279
    },
    {
      "epoch": 3.6012861736334405,
      "grad_norm": 5.509104251861572,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 0.0582,
      "num_input_tokens_seen": 4197536,
      "step": 280
    },
    {
      "epoch": 3.6141479099678455,
      "grad_norm": 4.121878623962402,
      "learning_rate": 2.341666666666667e-06,
      "loss": 0.0339,
      "num_input_tokens_seen": 4213152,
      "step": 281
    },
    {
      "epoch": 3.627009646302251,
      "grad_norm": 6.977634429931641,
      "learning_rate": 2.35e-06,
      "loss": 0.0656,
      "num_input_tokens_seen": 4228320,
      "step": 282
    },
    {
      "epoch": 3.639871382636656,
      "grad_norm": 3.6625123023986816,
      "learning_rate": 2.3583333333333338e-06,
      "loss": 0.0355,
      "num_input_tokens_seen": 4243680,
      "step": 283
    },
    {
      "epoch": 3.652733118971061,
      "grad_norm": 4.691339492797852,
      "learning_rate": 2.3666666666666667e-06,
      "loss": 0.037,
      "num_input_tokens_seen": 4258464,
      "step": 284
    },
    {
      "epoch": 3.665594855305466,
      "grad_norm": 3.1770055294036865,
      "learning_rate": 2.375e-06,
      "loss": 0.0206,
      "num_input_tokens_seen": 4273728,
      "step": 285
    },
    {
      "epoch": 3.6784565916398715,
      "grad_norm": 2.424788475036621,
      "learning_rate": 2.3833333333333335e-06,
      "loss": 0.0286,
      "num_input_tokens_seen": 4288416,
      "step": 286
    },
    {
      "epoch": 3.6913183279742765,
      "grad_norm": 5.731730937957764,
      "learning_rate": 2.391666666666667e-06,
      "loss": 0.0316,
      "num_input_tokens_seen": 4303712,
      "step": 287
    },
    {
      "epoch": 3.7041800643086815,
      "grad_norm": 4.939082622528076,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0263,
      "num_input_tokens_seen": 4319104,
      "step": 288
    },
    {
      "epoch": 3.717041800643087,
      "grad_norm": 2.817589521408081,
      "learning_rate": 2.4083333333333337e-06,
      "loss": 0.0265,
      "num_input_tokens_seen": 4334912,
      "step": 289
    },
    {
      "epoch": 3.729903536977492,
      "grad_norm": 2.6983306407928467,
      "learning_rate": 2.4166666666666667e-06,
      "loss": 0.0251,
      "num_input_tokens_seen": 4349280,
      "step": 290
    },
    {
      "epoch": 3.742765273311897,
      "grad_norm": 5.260397434234619,
      "learning_rate": 2.425e-06,
      "loss": 0.0293,
      "num_input_tokens_seen": 4363872,
      "step": 291
    },
    {
      "epoch": 3.755627009646302,
      "grad_norm": 4.8456034660339355,
      "learning_rate": 2.4333333333333335e-06,
      "loss": 0.0278,
      "num_input_tokens_seen": 4378752,
      "step": 292
    },
    {
      "epoch": 3.7684887459807075,
      "grad_norm": 4.560141563415527,
      "learning_rate": 2.441666666666667e-06,
      "loss": 0.035,
      "num_input_tokens_seen": 4393792,
      "step": 293
    },
    {
      "epoch": 3.7813504823151125,
      "grad_norm": 6.035860538482666,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0455,
      "num_input_tokens_seen": 4408192,
      "step": 294
    },
    {
      "epoch": 3.7942122186495175,
      "grad_norm": 6.634167194366455,
      "learning_rate": 2.4583333333333332e-06,
      "loss": 0.0429,
      "num_input_tokens_seen": 4422432,
      "step": 295
    },
    {
      "epoch": 3.807073954983923,
      "grad_norm": 9.78260326385498,
      "learning_rate": 2.466666666666667e-06,
      "loss": 0.056,
      "num_input_tokens_seen": 4437728,
      "step": 296
    },
    {
      "epoch": 3.819935691318328,
      "grad_norm": 6.473577499389648,
      "learning_rate": 2.475e-06,
      "loss": 0.0325,
      "num_input_tokens_seen": 4452928,
      "step": 297
    },
    {
      "epoch": 3.832797427652733,
      "grad_norm": 8.688652992248535,
      "learning_rate": 2.4833333333333334e-06,
      "loss": 0.0401,
      "num_input_tokens_seen": 4468096,
      "step": 298
    },
    {
      "epoch": 3.845659163987138,
      "grad_norm": 4.41790771484375,
      "learning_rate": 2.491666666666667e-06,
      "loss": 0.0182,
      "num_input_tokens_seen": 4482976,
      "step": 299
    },
    {
      "epoch": 3.8585209003215435,
      "grad_norm": 3.7182106971740723,
      "learning_rate": 2.5e-06,
      "loss": 0.0344,
      "num_input_tokens_seen": 4497952,
      "step": 300
    },
    {
      "epoch": 3.8713826366559485,
      "grad_norm": 4.0538225173950195,
      "learning_rate": 2.5083333333333336e-06,
      "loss": 0.0111,
      "num_input_tokens_seen": 4512896,
      "step": 301
    },
    {
      "epoch": 3.884244372990354,
      "grad_norm": 3.3492507934570312,
      "learning_rate": 2.5166666666666666e-06,
      "loss": 0.0088,
      "num_input_tokens_seen": 4528448,
      "step": 302
    },
    {
      "epoch": 3.897106109324759,
      "grad_norm": 3.518641710281372,
      "learning_rate": 2.5250000000000004e-06,
      "loss": 0.013,
      "num_input_tokens_seen": 4543712,
      "step": 303
    },
    {
      "epoch": 3.909967845659164,
      "grad_norm": 5.015272617340088,
      "learning_rate": 2.5333333333333338e-06,
      "loss": 0.0433,
      "num_input_tokens_seen": 4559008,
      "step": 304
    },
    {
      "epoch": 3.922829581993569,
      "grad_norm": 3.2924585342407227,
      "learning_rate": 2.5416666666666668e-06,
      "loss": 0.0214,
      "num_input_tokens_seen": 4573696,
      "step": 305
    },
    {
      "epoch": 3.935691318327974,
      "grad_norm": 8.486410140991211,
      "learning_rate": 2.55e-06,
      "loss": 0.0416,
      "num_input_tokens_seen": 4588384,
      "step": 306
    },
    {
      "epoch": 3.9485530546623795,
      "grad_norm": 6.4795002937316895,
      "learning_rate": 2.558333333333334e-06,
      "loss": 0.0321,
      "num_input_tokens_seen": 4602944,
      "step": 307
    },
    {
      "epoch": 3.9614147909967845,
      "grad_norm": 6.211554050445557,
      "learning_rate": 2.566666666666667e-06,
      "loss": 0.0526,
      "num_input_tokens_seen": 4618336,
      "step": 308
    },
    {
      "epoch": 3.97427652733119,
      "grad_norm": 5.602302074432373,
      "learning_rate": 2.5750000000000003e-06,
      "loss": 0.025,
      "num_input_tokens_seen": 4633472,
      "step": 309
    },
    {
      "epoch": 3.987138263665595,
      "grad_norm": 9.136455535888672,
      "learning_rate": 2.5833333333333337e-06,
      "loss": 0.0787,
      "num_input_tokens_seen": 4649472,
      "step": 310
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.398818969726562,
      "learning_rate": 2.5916666666666667e-06,
      "loss": 0.0559,
      "num_input_tokens_seen": 4664384,
      "step": 311
    },
    {
      "epoch": 4.012861736334405,
      "grad_norm": 2.286210536956787,
      "learning_rate": 2.6e-06,
      "loss": 0.0259,
      "num_input_tokens_seen": 4679200,
      "step": 312
    },
    {
      "epoch": 4.02572347266881,
      "grad_norm": 6.477627754211426,
      "learning_rate": 2.608333333333333e-06,
      "loss": 0.037,
      "num_input_tokens_seen": 4693696,
      "step": 313
    },
    {
      "epoch": 4.038585209003215,
      "grad_norm": 4.953974723815918,
      "learning_rate": 2.616666666666667e-06,
      "loss": 0.0293,
      "num_input_tokens_seen": 4708608,
      "step": 314
    },
    {
      "epoch": 4.051446945337621,
      "grad_norm": 2.7035064697265625,
      "learning_rate": 2.6250000000000003e-06,
      "loss": 0.0153,
      "num_input_tokens_seen": 4722944,
      "step": 315
    },
    {
      "epoch": 4.064308681672026,
      "grad_norm": 3.8599040508270264,
      "learning_rate": 2.6333333333333332e-06,
      "loss": 0.0234,
      "num_input_tokens_seen": 4739296,
      "step": 316
    },
    {
      "epoch": 4.077170418006431,
      "grad_norm": 5.4720072746276855,
      "learning_rate": 2.6416666666666666e-06,
      "loss": 0.0212,
      "num_input_tokens_seen": 4754048,
      "step": 317
    },
    {
      "epoch": 4.090032154340836,
      "grad_norm": 3.8060128688812256,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0187,
      "num_input_tokens_seen": 4769376,
      "step": 318
    },
    {
      "epoch": 4.102893890675241,
      "grad_norm": 5.436901092529297,
      "learning_rate": 2.6583333333333334e-06,
      "loss": 0.0245,
      "num_input_tokens_seen": 4784640,
      "step": 319
    },
    {
      "epoch": 4.115755627009646,
      "grad_norm": 1.5260390043258667,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.0032,
      "num_input_tokens_seen": 4799392,
      "step": 320
    },
    {
      "epoch": 4.128617363344051,
      "grad_norm": 11.145827293395996,
      "learning_rate": 2.6750000000000002e-06,
      "loss": 0.0367,
      "num_input_tokens_seen": 4813696,
      "step": 321
    },
    {
      "epoch": 4.141479099678457,
      "grad_norm": 5.737987518310547,
      "learning_rate": 2.683333333333333e-06,
      "loss": 0.038,
      "num_input_tokens_seen": 4828928,
      "step": 322
    },
    {
      "epoch": 4.154340836012862,
      "grad_norm": 12.955948829650879,
      "learning_rate": 2.691666666666667e-06,
      "loss": 0.0194,
      "num_input_tokens_seen": 4843232,
      "step": 323
    },
    {
      "epoch": 4.167202572347267,
      "grad_norm": 2.663821220397949,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0262,
      "num_input_tokens_seen": 4858592,
      "step": 324
    },
    {
      "epoch": 4.180064308681672,
      "grad_norm": 7.183210372924805,
      "learning_rate": 2.7083333333333334e-06,
      "loss": 0.0151,
      "num_input_tokens_seen": 4872928,
      "step": 325
    },
    {
      "epoch": 4.192926045016077,
      "grad_norm": 5.024378776550293,
      "learning_rate": 2.7166666666666668e-06,
      "loss": 0.0267,
      "num_input_tokens_seen": 4887968,
      "step": 326
    },
    {
      "epoch": 4.205787781350482,
      "grad_norm": 1.0667839050292969,
      "learning_rate": 2.7250000000000006e-06,
      "loss": 0.0041,
      "num_input_tokens_seen": 4902752,
      "step": 327
    },
    {
      "epoch": 4.218649517684887,
      "grad_norm": 6.243584632873535,
      "learning_rate": 2.7333333333333336e-06,
      "loss": 0.0365,
      "num_input_tokens_seen": 4917280,
      "step": 328
    },
    {
      "epoch": 4.231511254019293,
      "grad_norm": 3.255237579345703,
      "learning_rate": 2.741666666666667e-06,
      "loss": 0.0151,
      "num_input_tokens_seen": 4933088,
      "step": 329
    },
    {
      "epoch": 4.244372990353698,
      "grad_norm": 1.9820326566696167,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.006,
      "num_input_tokens_seen": 4948128,
      "step": 330
    },
    {
      "epoch": 4.257234726688103,
      "grad_norm": 4.553264141082764,
      "learning_rate": 2.7583333333333333e-06,
      "loss": 0.0247,
      "num_input_tokens_seen": 4962752,
      "step": 331
    },
    {
      "epoch": 4.270096463022508,
      "grad_norm": 3.139723062515259,
      "learning_rate": 2.766666666666667e-06,
      "loss": 0.0147,
      "num_input_tokens_seen": 4978272,
      "step": 332
    },
    {
      "epoch": 4.282958199356913,
      "grad_norm": 9.011144638061523,
      "learning_rate": 2.7750000000000005e-06,
      "loss": 0.0413,
      "num_input_tokens_seen": 4992384,
      "step": 333
    },
    {
      "epoch": 4.295819935691318,
      "grad_norm": 11.36248779296875,
      "learning_rate": 2.7833333333333335e-06,
      "loss": 0.0318,
      "num_input_tokens_seen": 5007136,
      "step": 334
    },
    {
      "epoch": 4.308681672025724,
      "grad_norm": 7.9140305519104,
      "learning_rate": 2.791666666666667e-06,
      "loss": 0.0513,
      "num_input_tokens_seen": 5021600,
      "step": 335
    },
    {
      "epoch": 4.321543408360129,
      "grad_norm": 4.12211799621582,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0165,
      "num_input_tokens_seen": 5037216,
      "step": 336
    },
    {
      "epoch": 4.334405144694534,
      "grad_norm": 4.724823951721191,
      "learning_rate": 2.8083333333333333e-06,
      "loss": 0.0131,
      "num_input_tokens_seen": 5052320,
      "step": 337
    },
    {
      "epoch": 4.347266881028939,
      "grad_norm": 6.9196085929870605,
      "learning_rate": 2.816666666666667e-06,
      "loss": 0.0246,
      "num_input_tokens_seen": 5067552,
      "step": 338
    },
    {
      "epoch": 4.360128617363344,
      "grad_norm": 5.785276412963867,
      "learning_rate": 2.825e-06,
      "loss": 0.0465,
      "num_input_tokens_seen": 5082240,
      "step": 339
    },
    {
      "epoch": 4.372990353697749,
      "grad_norm": 1.6201478242874146,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 0.0084,
      "num_input_tokens_seen": 5097408,
      "step": 340
    },
    {
      "epoch": 4.385852090032154,
      "grad_norm": 5.511898994445801,
      "learning_rate": 2.841666666666667e-06,
      "loss": 0.0105,
      "num_input_tokens_seen": 5111680,
      "step": 341
    },
    {
      "epoch": 4.39871382636656,
      "grad_norm": 8.025418281555176,
      "learning_rate": 2.85e-06,
      "loss": 0.0388,
      "num_input_tokens_seen": 5127264,
      "step": 342
    },
    {
      "epoch": 4.411575562700965,
      "grad_norm": 12.538291931152344,
      "learning_rate": 2.8583333333333336e-06,
      "loss": 0.0486,
      "num_input_tokens_seen": 5142464,
      "step": 343
    },
    {
      "epoch": 4.42443729903537,
      "grad_norm": 10.100396156311035,
      "learning_rate": 2.866666666666667e-06,
      "loss": 0.0354,
      "num_input_tokens_seen": 5157376,
      "step": 344
    },
    {
      "epoch": 4.437299035369775,
      "grad_norm": 4.218758583068848,
      "learning_rate": 2.875e-06,
      "loss": 0.0464,
      "num_input_tokens_seen": 5171648,
      "step": 345
    },
    {
      "epoch": 4.45016077170418,
      "grad_norm": 5.751765251159668,
      "learning_rate": 2.8833333333333334e-06,
      "loss": 0.0312,
      "num_input_tokens_seen": 5186752,
      "step": 346
    },
    {
      "epoch": 4.463022508038585,
      "grad_norm": 6.100085258483887,
      "learning_rate": 2.8916666666666672e-06,
      "loss": 0.0352,
      "num_input_tokens_seen": 5202176,
      "step": 347
    },
    {
      "epoch": 4.47588424437299,
      "grad_norm": 6.4870991706848145,
      "learning_rate": 2.9e-06,
      "loss": 0.0116,
      "num_input_tokens_seen": 5216896,
      "step": 348
    },
    {
      "epoch": 4.488745980707396,
      "grad_norm": 1.8258070945739746,
      "learning_rate": 2.9083333333333336e-06,
      "loss": 0.0118,
      "num_input_tokens_seen": 5232448,
      "step": 349
    },
    {
      "epoch": 4.501607717041801,
      "grad_norm": 2.6930766105651855,
      "learning_rate": 2.916666666666667e-06,
      "loss": 0.0138,
      "num_input_tokens_seen": 5247296,
      "step": 350
    },
    {
      "epoch": 4.514469453376206,
      "grad_norm": 5.420289993286133,
      "learning_rate": 2.925e-06,
      "loss": 0.0344,
      "num_input_tokens_seen": 5262304,
      "step": 351
    },
    {
      "epoch": 4.527331189710611,
      "grad_norm": 4.682693958282471,
      "learning_rate": 2.9333333333333338e-06,
      "loss": 0.0231,
      "num_input_tokens_seen": 5277664,
      "step": 352
    },
    {
      "epoch": 4.540192926045016,
      "grad_norm": 4.194357872009277,
      "learning_rate": 2.941666666666667e-06,
      "loss": 0.0267,
      "num_input_tokens_seen": 5292576,
      "step": 353
    },
    {
      "epoch": 4.553054662379421,
      "grad_norm": 1.0653674602508545,
      "learning_rate": 2.95e-06,
      "loss": 0.0109,
      "num_input_tokens_seen": 5306304,
      "step": 354
    },
    {
      "epoch": 4.565916398713826,
      "grad_norm": 1.8720684051513672,
      "learning_rate": 2.9583333333333335e-06,
      "loss": 0.0444,
      "num_input_tokens_seen": 5320768,
      "step": 355
    },
    {
      "epoch": 4.578778135048232,
      "grad_norm": 4.005693435668945,
      "learning_rate": 2.9666666666666673e-06,
      "loss": 0.0142,
      "num_input_tokens_seen": 5336128,
      "step": 356
    },
    {
      "epoch": 4.591639871382637,
      "grad_norm": 5.997867107391357,
      "learning_rate": 2.9750000000000003e-06,
      "loss": 0.0361,
      "num_input_tokens_seen": 5351168,
      "step": 357
    },
    {
      "epoch": 4.604501607717042,
      "grad_norm": 3.8871259689331055,
      "learning_rate": 2.9833333333333337e-06,
      "loss": 0.0197,
      "num_input_tokens_seen": 5366112,
      "step": 358
    },
    {
      "epoch": 4.617363344051447,
      "grad_norm": 4.269320011138916,
      "learning_rate": 2.991666666666667e-06,
      "loss": 0.0373,
      "num_input_tokens_seen": 5381440,
      "step": 359
    },
    {
      "epoch": 4.630225080385852,
      "grad_norm": 3.6487338542938232,
      "learning_rate": 3e-06,
      "loss": 0.0469,
      "num_input_tokens_seen": 5397152,
      "step": 360
    },
    {
      "epoch": 4.643086816720257,
      "grad_norm": 3.9794583320617676,
      "learning_rate": 3.0083333333333335e-06,
      "loss": 0.0283,
      "num_input_tokens_seen": 5412128,
      "step": 361
    },
    {
      "epoch": 4.655948553054662,
      "grad_norm": 5.071774482727051,
      "learning_rate": 3.0166666666666673e-06,
      "loss": 0.0271,
      "num_input_tokens_seen": 5426816,
      "step": 362
    },
    {
      "epoch": 4.668810289389068,
      "grad_norm": 3.651871681213379,
      "learning_rate": 3.0250000000000003e-06,
      "loss": 0.0303,
      "num_input_tokens_seen": 5441760,
      "step": 363
    },
    {
      "epoch": 4.681672025723473,
      "grad_norm": 3.1399481296539307,
      "learning_rate": 3.0333333333333337e-06,
      "loss": 0.0207,
      "num_input_tokens_seen": 5457504,
      "step": 364
    },
    {
      "epoch": 4.694533762057878,
      "grad_norm": 3.089629888534546,
      "learning_rate": 3.0416666666666666e-06,
      "loss": 0.0157,
      "num_input_tokens_seen": 5473088,
      "step": 365
    },
    {
      "epoch": 4.707395498392283,
      "grad_norm": 1.4184813499450684,
      "learning_rate": 3.05e-06,
      "loss": 0.0128,
      "num_input_tokens_seen": 5487712,
      "step": 366
    },
    {
      "epoch": 4.720257234726688,
      "grad_norm": 5.21925687789917,
      "learning_rate": 3.058333333333334e-06,
      "loss": 0.0293,
      "num_input_tokens_seen": 5503680,
      "step": 367
    },
    {
      "epoch": 4.733118971061093,
      "grad_norm": 3.7801499366760254,
      "learning_rate": 3.066666666666667e-06,
      "loss": 0.0211,
      "num_input_tokens_seen": 5518464,
      "step": 368
    },
    {
      "epoch": 4.745980707395498,
      "grad_norm": 9.715234756469727,
      "learning_rate": 3.075e-06,
      "loss": 0.0929,
      "num_input_tokens_seen": 5533504,
      "step": 369
    },
    {
      "epoch": 4.758842443729904,
      "grad_norm": 6.241518974304199,
      "learning_rate": 3.0833333333333336e-06,
      "loss": 0.0195,
      "num_input_tokens_seen": 5548832,
      "step": 370
    },
    {
      "epoch": 4.771704180064309,
      "grad_norm": 2.6658706665039062,
      "learning_rate": 3.0916666666666666e-06,
      "loss": 0.0114,
      "num_input_tokens_seen": 5564256,
      "step": 371
    },
    {
      "epoch": 4.784565916398714,
      "grad_norm": 7.38095235824585,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0207,
      "num_input_tokens_seen": 5580064,
      "step": 372
    },
    {
      "epoch": 4.797427652733119,
      "grad_norm": 5.605347156524658,
      "learning_rate": 3.1083333333333338e-06,
      "loss": 0.0144,
      "num_input_tokens_seen": 5595008,
      "step": 373
    },
    {
      "epoch": 4.810289389067524,
      "grad_norm": 4.410486221313477,
      "learning_rate": 3.1166666666666668e-06,
      "loss": 0.0197,
      "num_input_tokens_seen": 5610304,
      "step": 374
    },
    {
      "epoch": 4.823151125401929,
      "grad_norm": 5.259794235229492,
      "learning_rate": 3.125e-06,
      "loss": 0.0669,
      "num_input_tokens_seen": 5626464,
      "step": 375
    },
    {
      "epoch": 4.836012861736334,
      "grad_norm": 5.21687650680542,
      "learning_rate": 3.133333333333334e-06,
      "loss": 0.0156,
      "num_input_tokens_seen": 5641216,
      "step": 376
    },
    {
      "epoch": 4.84887459807074,
      "grad_norm": 3.3515796661376953,
      "learning_rate": 3.141666666666667e-06,
      "loss": 0.018,
      "num_input_tokens_seen": 5656832,
      "step": 377
    },
    {
      "epoch": 4.861736334405145,
      "grad_norm": 7.488304138183594,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.064,
      "num_input_tokens_seen": 5671744,
      "step": 378
    },
    {
      "epoch": 4.87459807073955,
      "grad_norm": 2.625629186630249,
      "learning_rate": 3.1583333333333337e-06,
      "loss": 0.0263,
      "num_input_tokens_seen": 5686496,
      "step": 379
    },
    {
      "epoch": 4.887459807073955,
      "grad_norm": 3.379544496536255,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 0.0256,
      "num_input_tokens_seen": 5701216,
      "step": 380
    },
    {
      "epoch": 4.90032154340836,
      "grad_norm": 2.0447638034820557,
      "learning_rate": 3.175e-06,
      "loss": 0.0269,
      "num_input_tokens_seen": 5715904,
      "step": 381
    },
    {
      "epoch": 4.913183279742765,
      "grad_norm": 3.5290844440460205,
      "learning_rate": 3.183333333333334e-06,
      "loss": 0.0281,
      "num_input_tokens_seen": 5730976,
      "step": 382
    },
    {
      "epoch": 4.92604501607717,
      "grad_norm": 2.183229923248291,
      "learning_rate": 3.191666666666667e-06,
      "loss": 0.0199,
      "num_input_tokens_seen": 5745824,
      "step": 383
    },
    {
      "epoch": 4.938906752411576,
      "grad_norm": 1.9661577939987183,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0277,
      "num_input_tokens_seen": 5760160,
      "step": 384
    },
    {
      "epoch": 4.951768488745981,
      "grad_norm": 5.09304666519165,
      "learning_rate": 3.2083333333333337e-06,
      "loss": 0.0158,
      "num_input_tokens_seen": 5776160,
      "step": 385
    },
    {
      "epoch": 4.951768488745981,
      "num_input_tokens_seen": 5776160,
      "step": 385,
      "total_flos": 2.6009787341943603e+17,
      "train_loss": 1.2260490821160424,
      "train_runtime": 5290.2175,
      "train_samples_per_second": 18.789,
      "train_steps_per_second": 0.073
    }
  ],
  "logging_steps": 1,
  "max_steps": 385,
  "num_input_tokens_seen": 5776160,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6009787341943603e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}