{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9967637540453075,
  "eval_steps": 500,
  "global_step": 154,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006472491909385114,
      "grad_norm": 5.306360721588135,
      "learning_rate": 0.0,
      "loss": 1.1501,
      "num_tokens": 963559.0,
      "step": 1
    },
    {
      "epoch": 0.012944983818770227,
      "grad_norm": 5.30866003036499,
      "learning_rate": 6.25e-08,
      "loss": 1.1455,
      "num_tokens": 1927760.0,
      "step": 2
    },
    {
      "epoch": 0.019417475728155338,
      "grad_norm": 5.259037971496582,
      "learning_rate": 1.25e-07,
      "loss": 1.1393,
      "num_tokens": 2896369.0,
      "step": 3
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 5.178048610687256,
      "learning_rate": 1.875e-07,
      "loss": 1.133,
      "num_tokens": 3886583.0,
      "step": 4
    },
    {
      "epoch": 0.032362459546925564,
      "grad_norm": 5.211574554443359,
      "learning_rate": 2.5e-07,
      "loss": 1.1368,
      "num_tokens": 4864476.0,
      "step": 5
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 5.201828479766846,
      "learning_rate": 3.1249999999999997e-07,
      "loss": 1.1455,
      "num_tokens": 5873295.0,
      "step": 6
    },
    {
      "epoch": 0.045307443365695796,
      "grad_norm": 5.131554126739502,
      "learning_rate": 3.75e-07,
      "loss": 1.1259,
      "num_tokens": 6876484.0,
      "step": 7
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": 5.083103179931641,
      "learning_rate": 4.375e-07,
      "loss": 1.1167,
      "num_tokens": 7871664.0,
      "step": 8
    },
    {
      "epoch": 0.05825242718446602,
      "grad_norm": 5.106949806213379,
      "learning_rate": 5e-07,
      "loss": 1.1324,
      "num_tokens": 8869931.0,
      "step": 9
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 4.861895561218262,
      "learning_rate": 5.625e-07,
      "loss": 1.1082,
      "num_tokens": 9874687.0,
      "step": 10
    },
    {
      "epoch": 0.07119741100323625,
      "grad_norm": 4.900995254516602,
      "learning_rate": 6.249999999999999e-07,
      "loss": 1.1035,
      "num_tokens": 10842628.0,
      "step": 11
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": 4.93906307220459,
      "learning_rate": 6.875e-07,
      "loss": 1.1207,
      "num_tokens": 11815438.0,
      "step": 12
    },
    {
      "epoch": 0.08414239482200647,
      "grad_norm": 4.3877153396606445,
      "learning_rate": 7.5e-07,
      "loss": 1.0708,
      "num_tokens": 12788222.0,
      "step": 13
    },
    {
      "epoch": 0.09061488673139159,
      "grad_norm": 4.357248306274414,
      "learning_rate": 8.125e-07,
      "loss": 1.0679,
      "num_tokens": 13756270.0,
      "step": 14
    },
    {
      "epoch": 0.0970873786407767,
      "grad_norm": 4.3989644050598145,
      "learning_rate": 8.75e-07,
      "loss": 1.068,
      "num_tokens": 14689813.0,
      "step": 15
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": 4.206644535064697,
      "learning_rate": 9.374999999999999e-07,
      "loss": 1.0545,
      "num_tokens": 15670657.0,
      "step": 16
    },
    {
      "epoch": 0.11003236245954692,
      "grad_norm": 4.120600700378418,
      "learning_rate": 1e-06,
      "loss": 1.0357,
      "num_tokens": 16640491.0,
      "step": 17
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": 3.066406011581421,
      "learning_rate": 1e-06,
      "loss": 0.9571,
      "num_tokens": 17611388.0,
      "step": 18
    },
    {
      "epoch": 0.12297734627831715,
      "grad_norm": 3.0390701293945312,
      "learning_rate": 1e-06,
      "loss": 0.9557,
      "num_tokens": 18582653.0,
      "step": 19
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 2.996507406234741,
      "learning_rate": 1e-06,
      "loss": 0.9467,
      "num_tokens": 19557459.0,
      "step": 20
    },
    {
      "epoch": 0.13592233009708737,
      "grad_norm": 2.852745771408081,
      "learning_rate": 1e-06,
      "loss": 0.9414,
      "num_tokens": 20524158.0,
      "step": 21
    },
    {
      "epoch": 0.1423948220064725,
      "grad_norm": 2.7312402725219727,
      "learning_rate": 1e-06,
      "loss": 0.9161,
      "num_tokens": 21502674.0,
      "step": 22
    },
    {
      "epoch": 0.1488673139158576,
      "grad_norm": 2.712592124938965,
      "learning_rate": 1e-06,
      "loss": 0.9201,
      "num_tokens": 22446294.0,
      "step": 23
    },
    {
      "epoch": 0.1553398058252427,
      "grad_norm": 2.51646089553833,
      "learning_rate": 1e-06,
      "loss": 0.8971,
      "num_tokens": 23430225.0,
      "step": 24
    },
    {
      "epoch": 0.16181229773462782,
      "grad_norm": 1.9695550203323364,
      "learning_rate": 1e-06,
      "loss": 0.8188,
      "num_tokens": 24380419.0,
      "step": 25
    },
    {
      "epoch": 0.16828478964401294,
      "grad_norm": 1.7356574535369873,
      "learning_rate": 1e-06,
      "loss": 0.7798,
      "num_tokens": 25343499.0,
      "step": 26
    },
    {
      "epoch": 0.17475728155339806,
      "grad_norm": 1.5638344287872314,
      "learning_rate": 1e-06,
      "loss": 0.7747,
      "num_tokens": 26315921.0,
      "step": 27
    },
    {
      "epoch": 0.18122977346278318,
      "grad_norm": 1.524434208869934,
      "learning_rate": 1e-06,
      "loss": 0.7787,
      "num_tokens": 27255686.0,
      "step": 28
    },
    {
      "epoch": 0.18770226537216828,
      "grad_norm": 1.3938937187194824,
      "learning_rate": 1e-06,
      "loss": 0.7647,
      "num_tokens": 28232449.0,
      "step": 29
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 1.3155360221862793,
      "learning_rate": 1e-06,
      "loss": 0.7544,
      "num_tokens": 29213099.0,
      "step": 30
    },
    {
      "epoch": 0.20064724919093851,
      "grad_norm": 1.1851674318313599,
      "learning_rate": 1e-06,
      "loss": 0.751,
      "num_tokens": 30210546.0,
      "step": 31
    },
    {
      "epoch": 0.20711974110032363,
      "grad_norm": 1.0744044780731201,
      "learning_rate": 1e-06,
      "loss": 0.7319,
      "num_tokens": 31190215.0,
      "step": 32
    },
    {
      "epoch": 0.21359223300970873,
      "grad_norm": 1.027134895324707,
      "learning_rate": 1e-06,
      "loss": 0.7286,
      "num_tokens": 32152368.0,
      "step": 33
    },
    {
      "epoch": 0.22006472491909385,
      "grad_norm": 0.9877621531486511,
      "learning_rate": 1e-06,
      "loss": 0.7382,
      "num_tokens": 33138410.0,
      "step": 34
    },
    {
      "epoch": 0.22653721682847897,
      "grad_norm": 0.9485065937042236,
      "learning_rate": 1e-06,
      "loss": 0.7276,
      "num_tokens": 34103559.0,
      "step": 35
    },
    {
      "epoch": 0.23300970873786409,
      "grad_norm": 0.8876718282699585,
      "learning_rate": 1e-06,
      "loss": 0.7243,
      "num_tokens": 35099702.0,
      "step": 36
    },
    {
      "epoch": 0.23948220064724918,
      "grad_norm": 0.781726598739624,
      "learning_rate": 1e-06,
      "loss": 0.715,
      "num_tokens": 36067246.0,
      "step": 37
    },
    {
      "epoch": 0.2459546925566343,
      "grad_norm": 0.6435908675193787,
      "learning_rate": 1e-06,
      "loss": 0.6923,
      "num_tokens": 37074157.0,
      "step": 38
    },
    {
      "epoch": 0.2524271844660194,
      "grad_norm": 0.5644338130950928,
      "learning_rate": 1e-06,
      "loss": 0.6791,
      "num_tokens": 38026864.0,
      "step": 39
    },
    {
      "epoch": 0.2588996763754045,
      "grad_norm": 0.5346189141273499,
      "learning_rate": 1e-06,
      "loss": 0.6658,
      "num_tokens": 39007950.0,
      "step": 40
    },
    {
      "epoch": 0.26537216828478966,
      "grad_norm": 0.536400556564331,
      "learning_rate": 1e-06,
      "loss": 0.673,
      "num_tokens": 40004404.0,
      "step": 41
    },
    {
      "epoch": 0.27184466019417475,
      "grad_norm": 0.5293827652931213,
      "learning_rate": 1e-06,
      "loss": 0.6625,
      "num_tokens": 40979367.0,
      "step": 42
    },
    {
      "epoch": 0.2783171521035599,
      "grad_norm": 0.5181026458740234,
      "learning_rate": 1e-06,
      "loss": 0.6512,
      "num_tokens": 41954716.0,
      "step": 43
    },
    {
      "epoch": 0.284789644012945,
      "grad_norm": 0.4992174506187439,
      "learning_rate": 1e-06,
      "loss": 0.6621,
      "num_tokens": 42927994.0,
      "step": 44
    },
    {
      "epoch": 0.2912621359223301,
      "grad_norm": 0.47395315766334534,
      "learning_rate": 1e-06,
      "loss": 0.6478,
      "num_tokens": 43870458.0,
      "step": 45
    },
    {
      "epoch": 0.2977346278317152,
      "grad_norm": 0.41670018434524536,
      "learning_rate": 1e-06,
      "loss": 0.6411,
      "num_tokens": 44845205.0,
      "step": 46
    },
    {
      "epoch": 0.3042071197411003,
      "grad_norm": 0.3809607923030853,
      "learning_rate": 1e-06,
      "loss": 0.6372,
      "num_tokens": 45817785.0,
      "step": 47
    },
    {
      "epoch": 0.3106796116504854,
      "grad_norm": 0.36747702956199646,
      "learning_rate": 1e-06,
      "loss": 0.6403,
      "num_tokens": 46768552.0,
      "step": 48
    },
    {
      "epoch": 0.31715210355987056,
      "grad_norm": 0.34375864267349243,
      "learning_rate": 1e-06,
      "loss": 0.6193,
      "num_tokens": 47720390.0,
      "step": 49
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 0.3278081715106964,
      "learning_rate": 1e-06,
      "loss": 0.6277,
      "num_tokens": 48659119.0,
      "step": 50
    },
    {
      "epoch": 0.3300970873786408,
      "grad_norm": 0.3173641860485077,
      "learning_rate": 1e-06,
      "loss": 0.6262,
      "num_tokens": 49635896.0,
      "step": 51
    },
    {
      "epoch": 0.3365695792880259,
      "grad_norm": 0.3114546239376068,
      "learning_rate": 1e-06,
      "loss": 0.6229,
      "num_tokens": 50617481.0,
      "step": 52
    },
    {
      "epoch": 0.343042071197411,
      "grad_norm": 0.31268301606178284,
      "learning_rate": 1e-06,
      "loss": 0.6187,
      "num_tokens": 51580322.0,
      "step": 53
    },
    {
      "epoch": 0.34951456310679613,
      "grad_norm": 0.29753509163856506,
      "learning_rate": 1e-06,
      "loss": 0.6176,
      "num_tokens": 52544983.0,
      "step": 54
    },
    {
      "epoch": 0.3559870550161812,
      "grad_norm": 0.2916501760482788,
      "learning_rate": 1e-06,
      "loss": 0.6086,
      "num_tokens": 53538431.0,
      "step": 55
    },
    {
      "epoch": 0.36245954692556637,
      "grad_norm": 0.2825452983379364,
      "learning_rate": 1e-06,
      "loss": 0.6077,
      "num_tokens": 54497097.0,
      "step": 56
    },
    {
      "epoch": 0.36893203883495146,
      "grad_norm": 0.264753133058548,
      "learning_rate": 1e-06,
      "loss": 0.5966,
      "num_tokens": 55515695.0,
      "step": 57
    },
    {
      "epoch": 0.37540453074433655,
      "grad_norm": 0.25653982162475586,
      "learning_rate": 1e-06,
      "loss": 0.5997,
      "num_tokens": 56471100.0,
      "step": 58
    },
    {
      "epoch": 0.3818770226537217,
      "grad_norm": 0.2426663488149643,
      "learning_rate": 1e-06,
      "loss": 0.603,
      "num_tokens": 57460948.0,
      "step": 59
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.22974367439746857,
      "learning_rate": 1e-06,
      "loss": 0.5993,
      "num_tokens": 58450663.0,
      "step": 60
    },
    {
      "epoch": 0.3948220064724919,
      "grad_norm": 0.21884475648403168,
      "learning_rate": 1e-06,
      "loss": 0.5884,
      "num_tokens": 59407638.0,
      "step": 61
    },
    {
      "epoch": 0.40129449838187703,
      "grad_norm": 0.21299949288368225,
      "learning_rate": 1e-06,
      "loss": 0.5862,
      "num_tokens": 60358388.0,
      "step": 62
    },
    {
      "epoch": 0.4077669902912621,
      "grad_norm": 0.21099086105823517,
      "learning_rate": 1e-06,
      "loss": 0.5787,
      "num_tokens": 61306137.0,
      "step": 63
    },
    {
      "epoch": 0.41423948220064727,
      "grad_norm": 0.20446249842643738,
      "learning_rate": 1e-06,
      "loss": 0.5888,
      "num_tokens": 62298616.0,
      "step": 64
    },
    {
      "epoch": 0.42071197411003236,
      "grad_norm": 0.20021338760852814,
      "learning_rate": 1e-06,
      "loss": 0.5759,
      "num_tokens": 63242620.0,
      "step": 65
    },
    {
      "epoch": 0.42718446601941745,
      "grad_norm": 0.20259256660938263,
      "learning_rate": 1e-06,
      "loss": 0.5939,
      "num_tokens": 64231555.0,
      "step": 66
    },
    {
      "epoch": 0.4336569579288026,
      "grad_norm": 0.19663812220096588,
      "learning_rate": 1e-06,
      "loss": 0.5788,
      "num_tokens": 65190302.0,
      "step": 67
    },
    {
      "epoch": 0.4401294498381877,
      "grad_norm": 0.1927073448896408,
      "learning_rate": 1e-06,
      "loss": 0.5755,
      "num_tokens": 66175194.0,
      "step": 68
    },
    {
      "epoch": 0.44660194174757284,
      "grad_norm": 0.18935494124889374,
      "learning_rate": 1e-06,
      "loss": 0.573,
      "num_tokens": 67146659.0,
      "step": 69
    },
    {
      "epoch": 0.45307443365695793,
      "grad_norm": 0.18019847571849823,
      "learning_rate": 1e-06,
      "loss": 0.5539,
      "num_tokens": 68115421.0,
      "step": 70
    },
    {
      "epoch": 0.459546925566343,
      "grad_norm": 0.17649590969085693,
      "learning_rate": 1e-06,
      "loss": 0.5506,
      "num_tokens": 69078962.0,
      "step": 71
    },
    {
      "epoch": 0.46601941747572817,
      "grad_norm": 0.16998673975467682,
      "learning_rate": 1e-06,
      "loss": 0.573,
      "num_tokens": 70056552.0,
      "step": 72
    },
    {
      "epoch": 0.47249190938511326,
      "grad_norm": 0.16949011385440826,
      "learning_rate": 1e-06,
      "loss": 0.5674,
      "num_tokens": 71056405.0,
      "step": 73
    },
    {
      "epoch": 0.47896440129449835,
      "grad_norm": 0.1706332266330719,
      "learning_rate": 1e-06,
      "loss": 0.5755,
      "num_tokens": 72011963.0,
      "step": 74
    },
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 0.16622762382030487,
      "learning_rate": 1e-06,
      "loss": 0.563,
      "num_tokens": 72974088.0,
      "step": 75
    },
    {
      "epoch": 0.4919093851132686,
      "grad_norm": 0.16113753616809845,
      "learning_rate": 1e-06,
      "loss": 0.5545,
      "num_tokens": 73963066.0,
      "step": 76
    },
    {
      "epoch": 0.49838187702265374,
      "grad_norm": 0.15716572105884552,
      "learning_rate": 1e-06,
      "loss": 0.5465,
      "num_tokens": 74927507.0,
      "step": 77
    },
    {
      "epoch": 0.5048543689320388,
      "grad_norm": 0.15952879190444946,
      "learning_rate": 1e-06,
      "loss": 0.5513,
      "num_tokens": 75913302.0,
      "step": 78
    },
    {
      "epoch": 0.511326860841424,
      "grad_norm": 0.1577850878238678,
      "learning_rate": 1e-06,
      "loss": 0.559,
      "num_tokens": 76871637.0,
      "step": 79
    },
    {
      "epoch": 0.517799352750809,
      "grad_norm": 0.1505461186170578,
      "learning_rate": 1e-06,
      "loss": 0.5509,
      "num_tokens": 77844738.0,
      "step": 80
    },
    {
      "epoch": 0.5242718446601942,
      "grad_norm": 0.1514582335948944,
      "learning_rate": 1e-06,
      "loss": 0.5453,
      "num_tokens": 78789735.0,
      "step": 81
    },
    {
      "epoch": 0.5307443365695793,
      "grad_norm": 0.15150229632854462,
      "learning_rate": 1e-06,
      "loss": 0.5417,
      "num_tokens": 79740057.0,
      "step": 82
    },
    {
      "epoch": 0.5372168284789643,
      "grad_norm": 0.14974889159202576,
      "learning_rate": 1e-06,
      "loss": 0.5498,
      "num_tokens": 80691344.0,
      "step": 83
    },
    {
      "epoch": 0.5436893203883495,
      "grad_norm": 0.14659319818019867,
      "learning_rate": 1e-06,
      "loss": 0.5456,
      "num_tokens": 81695065.0,
      "step": 84
    },
    {
      "epoch": 0.5501618122977346,
      "grad_norm": 0.14839723706245422,
      "learning_rate": 1e-06,
      "loss": 0.5446,
      "num_tokens": 82670591.0,
      "step": 85
    },
    {
      "epoch": 0.5566343042071198,
      "grad_norm": 0.1449030339717865,
      "learning_rate": 1e-06,
      "loss": 0.5434,
      "num_tokens": 83619525.0,
      "step": 86
    },
    {
      "epoch": 0.5631067961165048,
      "grad_norm": 0.14636728167533875,
      "learning_rate": 1e-06,
      "loss": 0.5427,
      "num_tokens": 84583829.0,
      "step": 87
    },
    {
      "epoch": 0.56957928802589,
      "grad_norm": 0.14410880208015442,
      "learning_rate": 1e-06,
      "loss": 0.54,
      "num_tokens": 85554557.0,
      "step": 88
    },
    {
      "epoch": 0.5760517799352751,
      "grad_norm": 0.14123332500457764,
      "learning_rate": 1e-06,
      "loss": 0.5412,
      "num_tokens": 86534800.0,
      "step": 89
    },
    {
      "epoch": 0.5825242718446602,
      "grad_norm": 0.14631222188472748,
      "learning_rate": 1e-06,
      "loss": 0.5451,
      "num_tokens": 87479322.0,
      "step": 90
    },
    {
      "epoch": 0.5889967637540453,
      "grad_norm": 0.141328364610672,
      "learning_rate": 1e-06,
      "loss": 0.543,
      "num_tokens": 88440604.0,
      "step": 91
    },
    {
      "epoch": 0.5954692556634305,
      "grad_norm": 0.14410269260406494,
      "learning_rate": 1e-06,
      "loss": 0.5389,
      "num_tokens": 89440902.0,
      "step": 92
    },
    {
      "epoch": 0.6019417475728155,
      "grad_norm": 0.14109647274017334,
      "learning_rate": 1e-06,
      "loss": 0.5312,
      "num_tokens": 90420292.0,
      "step": 93
    },
    {
      "epoch": 0.6084142394822006,
      "grad_norm": 0.14093320071697235,
      "learning_rate": 1e-06,
      "loss": 0.5432,
      "num_tokens": 91365927.0,
      "step": 94
    },
    {
      "epoch": 0.6148867313915858,
      "grad_norm": 0.1392253190279007,
      "learning_rate": 1e-06,
      "loss": 0.5342,
      "num_tokens": 92339481.0,
      "step": 95
    },
    {
      "epoch": 0.6213592233009708,
      "grad_norm": 0.14118197560310364,
      "learning_rate": 1e-06,
      "loss": 0.5291,
      "num_tokens": 93277920.0,
      "step": 96
    },
    {
      "epoch": 0.627831715210356,
      "grad_norm": 0.14340411126613617,
      "learning_rate": 1e-06,
      "loss": 0.527,
      "num_tokens": 94233058.0,
      "step": 97
    },
    {
      "epoch": 0.6343042071197411,
      "grad_norm": 0.13777285814285278,
      "learning_rate": 1e-06,
      "loss": 0.5407,
      "num_tokens": 95195865.0,
      "step": 98
    },
    {
      "epoch": 0.6407766990291263,
      "grad_norm": 0.14087024331092834,
      "learning_rate": 1e-06,
      "loss": 0.5219,
      "num_tokens": 96165533.0,
      "step": 99
    },
    {
      "epoch": 0.6472491909385113,
      "grad_norm": 0.13480006158351898,
      "learning_rate": 1e-06,
      "loss": 0.5229,
      "num_tokens": 97128908.0,
      "step": 100
    },
    {
      "epoch": 0.6537216828478964,
      "grad_norm": 0.13443224132061005,
      "learning_rate": 1e-06,
      "loss": 0.5235,
      "num_tokens": 98137812.0,
      "step": 101
    },
    {
      "epoch": 0.6601941747572816,
      "grad_norm": 0.13486695289611816,
      "learning_rate": 1e-06,
      "loss": 0.521,
      "num_tokens": 99133445.0,
      "step": 102
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.13491222262382507,
      "learning_rate": 1e-06,
      "loss": 0.5118,
      "num_tokens": 100106034.0,
      "step": 103
    },
    {
      "epoch": 0.6731391585760518,
      "grad_norm": 0.13977712392807007,
      "learning_rate": 1e-06,
      "loss": 0.5394,
      "num_tokens": 101060830.0,
      "step": 104
    },
    {
      "epoch": 0.6796116504854369,
      "grad_norm": 0.1345338374376297,
      "learning_rate": 1e-06,
      "loss": 0.5226,
      "num_tokens": 102032708.0,
      "step": 105
    },
    {
      "epoch": 0.686084142394822,
      "grad_norm": 0.13142578303813934,
      "learning_rate": 1e-06,
      "loss": 0.5061,
      "num_tokens": 103020888.0,
      "step": 106
    },
    {
      "epoch": 0.6925566343042071,
      "grad_norm": 0.14058642089366913,
      "learning_rate": 1e-06,
      "loss": 0.5315,
      "num_tokens": 103986883.0,
      "step": 107
    },
    {
      "epoch": 0.6990291262135923,
      "grad_norm": 0.13689804077148438,
      "learning_rate": 1e-06,
      "loss": 0.5275,
      "num_tokens": 104978514.0,
      "step": 108
    },
    {
      "epoch": 0.7055016181229773,
      "grad_norm": 0.1382923722267151,
      "learning_rate": 1e-06,
      "loss": 0.5159,
      "num_tokens": 105938542.0,
      "step": 109
    },
    {
      "epoch": 0.7119741100323624,
      "grad_norm": 0.13341419398784637,
      "learning_rate": 1e-06,
      "loss": 0.5175,
      "num_tokens": 106909993.0,
      "step": 110
    },
    {
      "epoch": 0.7184466019417476,
      "grad_norm": 0.13735052943229675,
      "learning_rate": 1e-06,
      "loss": 0.5204,
      "num_tokens": 107872313.0,
      "step": 111
    },
    {
      "epoch": 0.7249190938511327,
      "grad_norm": 0.14685890078544617,
      "learning_rate": 1e-06,
      "loss": 0.5154,
      "num_tokens": 108876000.0,
      "step": 112
    },
    {
      "epoch": 0.7313915857605178,
      "grad_norm": 0.13520538806915283,
      "learning_rate": 1e-06,
      "loss": 0.5163,
      "num_tokens": 109857790.0,
      "step": 113
    },
    {
      "epoch": 0.7378640776699029,
      "grad_norm": 0.1330995261669159,
      "learning_rate": 1e-06,
      "loss": 0.5155,
      "num_tokens": 110826497.0,
      "step": 114
    },
    {
      "epoch": 0.7443365695792881,
      "grad_norm": 0.134913370013237,
      "learning_rate": 1e-06,
      "loss": 0.5142,
      "num_tokens": 111775780.0,
      "step": 115
    },
    {
      "epoch": 0.7508090614886731,
      "grad_norm": 0.13504451513290405,
      "learning_rate": 1e-06,
      "loss": 0.5161,
      "num_tokens": 112755203.0,
      "step": 116
    },
    {
      "epoch": 0.7572815533980582,
      "grad_norm": 0.13805583119392395,
      "learning_rate": 1e-06,
      "loss": 0.5166,
      "num_tokens": 113720983.0,
      "step": 117
    },
    {
      "epoch": 0.7637540453074434,
      "grad_norm": 0.137771874666214,
      "learning_rate": 1e-06,
      "loss": 0.5057,
      "num_tokens": 114690500.0,
      "step": 118
    },
    {
      "epoch": 0.7702265372168284,
      "grad_norm": 0.13603690266609192,
      "learning_rate": 1e-06,
      "loss": 0.5059,
      "num_tokens": 115663752.0,
      "step": 119
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.1295483261346817,
      "learning_rate": 1e-06,
      "loss": 0.5031,
      "num_tokens": 116656118.0,
      "step": 120
    },
    {
      "epoch": 0.7831715210355987,
      "grad_norm": 0.13289949297904968,
      "learning_rate": 1e-06,
      "loss": 0.5127,
      "num_tokens": 117647006.0,
      "step": 121
    },
    {
      "epoch": 0.7896440129449838,
      "grad_norm": 0.13150979578495026,
      "learning_rate": 1e-06,
      "loss": 0.5023,
      "num_tokens": 118637898.0,
      "step": 122
    },
    {
      "epoch": 0.7961165048543689,
      "grad_norm": 0.13312214612960815,
      "learning_rate": 1e-06,
      "loss": 0.5143,
      "num_tokens": 119611539.0,
      "step": 123
    },
    {
      "epoch": 0.8025889967637541,
      "grad_norm": 0.13679178059101105,
      "learning_rate": 1e-06,
      "loss": 0.5149,
      "num_tokens": 120576485.0,
      "step": 124
    },
    {
      "epoch": 0.8090614886731392,
      "grad_norm": 0.13002805411815643,
      "learning_rate": 1e-06,
      "loss": 0.5143,
      "num_tokens": 121567862.0,
      "step": 125
    },
    {
      "epoch": 0.8155339805825242,
      "grad_norm": 0.13436037302017212,
      "learning_rate": 1e-06,
      "loss": 0.5028,
      "num_tokens": 122530893.0,
      "step": 126
    },
    {
      "epoch": 0.8220064724919094,
      "grad_norm": 0.13467973470687866,
      "learning_rate": 1e-06,
      "loss": 0.5069,
      "num_tokens": 123480227.0,
      "step": 127
    },
    {
      "epoch": 0.8284789644012945,
      "grad_norm": 0.13601741194725037,
      "learning_rate": 1e-06,
      "loss": 0.5194,
      "num_tokens": 124462070.0,
      "step": 128
    },
    {
      "epoch": 0.8349514563106796,
      "grad_norm": 0.1381833255290985,
      "learning_rate": 1e-06,
      "loss": 0.5142,
      "num_tokens": 125440428.0,
      "step": 129
    },
    {
      "epoch": 0.8414239482200647,
      "grad_norm": 0.1346794068813324,
      "learning_rate": 1e-06,
      "loss": 0.5115,
      "num_tokens": 126416310.0,
      "step": 130
    },
    {
      "epoch": 0.8478964401294499,
      "grad_norm": 0.13682374358177185,
      "learning_rate": 1e-06,
      "loss": 0.512,
      "num_tokens": 127406436.0,
      "step": 131
    },
    {
      "epoch": 0.8543689320388349,
      "grad_norm": 0.13239574432373047,
      "learning_rate": 1e-06,
      "loss": 0.5068,
      "num_tokens": 128372197.0,
      "step": 132
    },
    {
      "epoch": 0.86084142394822,
      "grad_norm": 0.13347913324832916,
      "learning_rate": 1e-06,
      "loss": 0.5062,
      "num_tokens": 129371264.0,
      "step": 133
    },
    {
      "epoch": 0.8673139158576052,
      "grad_norm": 0.1342724710702896,
      "learning_rate": 1e-06,
      "loss": 0.4917,
      "num_tokens": 130306080.0,
      "step": 134
    },
    {
      "epoch": 0.8737864077669902,
      "grad_norm": 0.13179434835910797,
      "learning_rate": 1e-06,
      "loss": 0.5107,
      "num_tokens": 131261937.0,
      "step": 135
    },
    {
      "epoch": 0.8802588996763754,
      "grad_norm": 0.13348270952701569,
      "learning_rate": 1e-06,
      "loss": 0.5044,
      "num_tokens": 132223182.0,
      "step": 136
    },
    {
      "epoch": 0.8867313915857605,
      "grad_norm": 0.22263851761817932,
      "learning_rate": 1e-06,
      "loss": 0.5082,
      "num_tokens": 133211562.0,
      "step": 137
    },
    {
      "epoch": 0.8932038834951457,
      "grad_norm": 0.13348044455051422,
      "learning_rate": 1e-06,
      "loss": 0.5043,
      "num_tokens": 134208133.0,
      "step": 138
    },
    {
      "epoch": 0.8996763754045307,
      "grad_norm": 0.13663546741008759,
      "learning_rate": 1e-06,
      "loss": 0.5083,
      "num_tokens": 135194807.0,
      "step": 139
    },
    {
      "epoch": 0.9061488673139159,
      "grad_norm": 0.1293790638446808,
      "learning_rate": 1e-06,
      "loss": 0.5046,
      "num_tokens": 136175941.0,
      "step": 140
    },
    {
      "epoch": 0.912621359223301,
      "grad_norm": 0.13469921052455902,
      "learning_rate": 1e-06,
      "loss": 0.5183,
      "num_tokens": 137117638.0,
      "step": 141
    },
    {
      "epoch": 0.919093851132686,
      "grad_norm": 0.1336260437965393,
      "learning_rate": 1e-06,
      "loss": 0.4941,
      "num_tokens": 138102412.0,
      "step": 142
    },
    {
      "epoch": 0.9255663430420712,
      "grad_norm": 0.1314634084701538,
      "learning_rate": 1e-06,
      "loss": 0.497,
      "num_tokens": 139056304.0,
      "step": 143
    },
    {
      "epoch": 0.9320388349514563,
      "grad_norm": 0.13598428666591644,
      "learning_rate": 1e-06,
      "loss": 0.5026,
      "num_tokens": 140002988.0,
      "step": 144
    },
    {
      "epoch": 0.9385113268608414,
      "grad_norm": 0.13465505838394165,
      "learning_rate": 1e-06,
      "loss": 0.5051,
      "num_tokens": 140939323.0,
      "step": 145
    },
    {
      "epoch": 0.9449838187702265,
      "grad_norm": 0.13320808112621307,
      "learning_rate": 1e-06,
      "loss": 0.5007,
      "num_tokens": 141898246.0,
      "step": 146
    },
    {
      "epoch": 0.9514563106796117,
      "grad_norm": 0.13584767282009125,
      "learning_rate": 1e-06,
      "loss": 0.5074,
      "num_tokens": 142861118.0,
      "step": 147
    },
    {
      "epoch": 0.9579288025889967,
      "grad_norm": 0.13394641876220703,
      "learning_rate": 1e-06,
      "loss": 0.5002,
      "num_tokens": 143845628.0,
      "step": 148
    },
    {
      "epoch": 0.9644012944983819,
      "grad_norm": 0.13663163781166077,
      "learning_rate": 1e-06,
      "loss": 0.5129,
      "num_tokens": 144816454.0,
      "step": 149
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 0.12985925376415253,
      "learning_rate": 1e-06,
      "loss": 0.5006,
      "num_tokens": 145791528.0,
      "step": 150
    },
    {
      "epoch": 0.9773462783171522,
      "grad_norm": 0.1344696283340454,
      "learning_rate": 1e-06,
      "loss": 0.5136,
      "num_tokens": 146776225.0,
      "step": 151
    },
    {
      "epoch": 0.9838187702265372,
      "grad_norm": 0.1393062323331833,
      "learning_rate": 1e-06,
      "loss": 0.4963,
      "num_tokens": 147716038.0,
      "step": 152
    },
    {
      "epoch": 0.9902912621359223,
      "grad_norm": 0.13568711280822754,
      "learning_rate": 1e-06,
      "loss": 0.4935,
      "num_tokens": 148641036.0,
      "step": 153
    },
    {
      "epoch": 0.9967637540453075,
      "grad_norm": 0.12916181981563568,
      "learning_rate": 1e-06,
      "loss": 0.4964,
      "num_tokens": 149611850.0,
      "step": 154
    },
    {
      "epoch": 0.9967637540453075,
      "step": 154,
      "total_flos": 6.182777521931551e+18,
      "train_loss": 0.6460230693027571,
      "train_runtime": 6408.7951,
      "train_samples_per_second": 10.787,
      "train_steps_per_second": 0.024
    }
  ],
  "logging_steps": 1,
  "max_steps": 154,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.182777521931551e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}