{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.45454545454545453,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007575757575757576,
      "grad_norm": 0.09537188708782196,
      "learning_rate": 5e-05,
      "loss": 2.6905,
      "step": 1
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 0.11260437220335007,
      "learning_rate": 4.9242424242424245e-05,
      "loss": 2.7568,
      "step": 2
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 0.10646557807922363,
      "learning_rate": 4.848484848484849e-05,
      "loss": 2.6741,
      "step": 3
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 0.13714808225631714,
      "learning_rate": 4.772727272727273e-05,
      "loss": 2.7554,
      "step": 4
    },
    {
      "epoch": 0.03787878787878788,
      "grad_norm": 0.10070829093456268,
      "learning_rate": 4.696969696969697e-05,
      "loss": 2.5577,
      "step": 5
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.1274138242006302,
      "learning_rate": 4.621212121212121e-05,
      "loss": 2.511,
      "step": 6
    },
    {
      "epoch": 0.05303030303030303,
      "grad_norm": 0.12040433287620544,
      "learning_rate": 4.545454545454546e-05,
      "loss": 2.6901,
      "step": 7
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 0.12598344683647156,
      "learning_rate": 4.46969696969697e-05,
      "loss": 2.7296,
      "step": 8
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 0.11921223253011703,
      "learning_rate": 4.3939393939393944e-05,
      "loss": 2.4968,
      "step": 9
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 0.15551121532917023,
      "learning_rate": 4.318181818181819e-05,
      "loss": 2.8515,
      "step": 10
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.14377211034297943,
      "learning_rate": 4.242424242424243e-05,
      "loss": 2.8905,
      "step": 11
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.10209552943706512,
      "learning_rate": 4.166666666666667e-05,
      "loss": 2.6593,
      "step": 12
    },
    {
      "epoch": 0.09848484848484848,
      "grad_norm": 0.13147519528865814,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 2.6413,
      "step": 13
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 0.12913918495178223,
      "learning_rate": 4.015151515151515e-05,
      "loss": 2.7072,
      "step": 14
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.1154194250702858,
      "learning_rate": 3.939393939393939e-05,
      "loss": 2.7163,
      "step": 15
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.12849478423595428,
      "learning_rate": 3.8636363636363636e-05,
      "loss": 2.7094,
      "step": 16
    },
    {
      "epoch": 0.12878787878787878,
      "grad_norm": 0.13727141916751862,
      "learning_rate": 3.787878787878788e-05,
      "loss": 2.6256,
      "step": 17
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.1416122019290924,
      "learning_rate": 3.712121212121212e-05,
      "loss": 2.5419,
      "step": 18
    },
    {
      "epoch": 0.14393939393939395,
      "grad_norm": 0.12187984585762024,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 2.4036,
      "step": 19
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.15144124627113342,
      "learning_rate": 3.560606060606061e-05,
      "loss": 2.7657,
      "step": 20
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 0.16624559462070465,
      "learning_rate": 3.484848484848485e-05,
      "loss": 2.7616,
      "step": 21
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.13778212666511536,
      "learning_rate": 3.409090909090909e-05,
      "loss": 2.6763,
      "step": 22
    },
    {
      "epoch": 0.17424242424242425,
      "grad_norm": 0.13686427474021912,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.5902,
      "step": 23
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.15202738344669342,
      "learning_rate": 3.257575757575758e-05,
      "loss": 2.414,
      "step": 24
    },
    {
      "epoch": 0.1893939393939394,
      "grad_norm": 0.1230149045586586,
      "learning_rate": 3.181818181818182e-05,
      "loss": 2.3264,
      "step": 25
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 0.15694740414619446,
      "learning_rate": 3.106060606060606e-05,
      "loss": 2.673,
      "step": 26
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 0.14588165283203125,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 2.5204,
      "step": 27
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.11643742769956589,
      "learning_rate": 2.954545454545455e-05,
      "loss": 2.4545,
      "step": 28
    },
    {
      "epoch": 0.2196969696969697,
      "grad_norm": 0.13210788369178772,
      "learning_rate": 2.878787878787879e-05,
      "loss": 2.3838,
      "step": 29
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.14757853746414185,
      "learning_rate": 2.803030303030303e-05,
      "loss": 2.5976,
      "step": 30
    },
    {
      "epoch": 0.23484848484848486,
      "grad_norm": 0.15585793554782867,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 2.6754,
      "step": 31
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.1773393601179123,
      "learning_rate": 2.6515151515151516e-05,
      "loss": 2.875,
      "step": 32
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.16676630079746246,
      "learning_rate": 2.575757575757576e-05,
      "loss": 2.6134,
      "step": 33
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 0.18137340247631073,
      "learning_rate": 2.5e-05,
      "loss": 2.597,
      "step": 34
    },
    {
      "epoch": 0.26515151515151514,
      "grad_norm": 0.1503434181213379,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 2.4953,
      "step": 35
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.18666601181030273,
      "learning_rate": 2.3484848484848487e-05,
      "loss": 2.6068,
      "step": 36
    },
    {
      "epoch": 0.2803030303030303,
      "grad_norm": 0.1572176069021225,
      "learning_rate": 2.272727272727273e-05,
      "loss": 2.6932,
      "step": 37
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 0.17906226217746735,
      "learning_rate": 2.1969696969696972e-05,
      "loss": 2.6904,
      "step": 38
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 0.14453791081905365,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 2.6939,
      "step": 39
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.17917212843894958,
      "learning_rate": 2.0454545454545457e-05,
      "loss": 2.6053,
      "step": 40
    },
    {
      "epoch": 0.3106060606060606,
      "grad_norm": 0.13931894302368164,
      "learning_rate": 1.9696969696969697e-05,
      "loss": 2.4931,
      "step": 41
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.1697995960712433,
      "learning_rate": 1.893939393939394e-05,
      "loss": 2.7841,
      "step": 42
    },
    {
      "epoch": 0.32575757575757575,
      "grad_norm": 0.18437106907367706,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 2.8778,
      "step": 43
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.17622561752796173,
      "learning_rate": 1.7424242424242425e-05,
      "loss": 2.4296,
      "step": 44
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.1804683357477188,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.6399,
      "step": 45
    },
    {
      "epoch": 0.3484848484848485,
      "grad_norm": 0.18295425176620483,
      "learning_rate": 1.590909090909091e-05,
      "loss": 2.8005,
      "step": 46
    },
    {
      "epoch": 0.3560606060606061,
      "grad_norm": 0.15364795923233032,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 2.5525,
      "step": 47
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.16968029737472534,
      "learning_rate": 1.4393939393939396e-05,
      "loss": 2.6071,
      "step": 48
    },
    {
      "epoch": 0.3712121212121212,
      "grad_norm": 0.18445603549480438,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 2.6512,
      "step": 49
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 0.16352227330207825,
      "learning_rate": 1.287878787878788e-05,
      "loss": 2.5452,
      "step": 50
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 0.15646548569202423,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 2.4993,
      "step": 51
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 0.1422729194164276,
      "learning_rate": 1.1363636363636365e-05,
      "loss": 2.4923,
      "step": 52
    },
    {
      "epoch": 0.4015151515151515,
      "grad_norm": 0.1983378529548645,
      "learning_rate": 1.0606060606060607e-05,
      "loss": 2.5515,
      "step": 53
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.1466148942708969,
      "learning_rate": 9.848484848484848e-06,
      "loss": 2.5185,
      "step": 54
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.1356826275587082,
      "learning_rate": 9.090909090909091e-06,
      "loss": 2.4658,
      "step": 55
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.15932199358940125,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.4564,
      "step": 56
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 0.1498263031244278,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 2.4288,
      "step": 57
    },
    {
      "epoch": 0.4393939393939394,
      "grad_norm": 0.16778239607810974,
      "learning_rate": 6.818181818181818e-06,
      "loss": 2.378,
      "step": 58
    },
    {
      "epoch": 0.44696969696969696,
      "grad_norm": 0.1550946831703186,
      "learning_rate": 6.060606060606061e-06,
      "loss": 2.5211,
      "step": 59
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.15183551609516144,
      "learning_rate": 5.303030303030304e-06,
      "loss": 2.5247,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 30,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 804110362214400.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}