{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25252525252525254,
  "eval_steps": 38,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003367003367003367,
      "grad_norm": 2.0,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.0833,
      "step": 1
    },
    {
      "epoch": 0.003367003367003367,
      "eval_loss": 1.032954454421997,
      "eval_runtime": 8.7786,
      "eval_samples_per_second": 56.957,
      "eval_steps_per_second": 3.645,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 2.265625,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.996,
      "step": 2
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 1.6484375,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 1.0487,
      "step": 3
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 2.046875,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 1.0554,
      "step": 4
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 2.4375,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 1.0341,
      "step": 5
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 1.9609375,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 1.0132,
      "step": 6
    },
    {
      "epoch": 0.02356902356902357,
      "grad_norm": 2.625,
      "learning_rate": 3.181818181818182e-06,
      "loss": 1.0298,
      "step": 7
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 2.296875,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 1.0216,
      "step": 8
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.234375,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 1.0736,
      "step": 9
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 2.1875,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.0216,
      "step": 10
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 2.359375,
      "learning_rate": 5e-06,
      "loss": 1.0075,
      "step": 11
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 1.890625,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.051,
      "step": 12
    },
    {
      "epoch": 0.04377104377104377,
      "grad_norm": 1.90625,
      "learning_rate": 5.90909090909091e-06,
      "loss": 1.0655,
      "step": 13
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 1.6484375,
      "learning_rate": 6.363636363636364e-06,
      "loss": 1.0297,
      "step": 14
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 1.6953125,
      "learning_rate": 6.818181818181818e-06,
      "loss": 1.0411,
      "step": 15
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 1.9921875,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.0618,
      "step": 16
    },
    {
      "epoch": 0.05723905723905724,
      "grad_norm": 1.4453125,
      "learning_rate": 7.727272727272727e-06,
      "loss": 1.0052,
      "step": 17
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.390625,
      "learning_rate": 8.181818181818183e-06,
      "loss": 1.0053,
      "step": 18
    },
    {
      "epoch": 0.06397306397306397,
      "grad_norm": 1.2734375,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.9786,
      "step": 19
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 1.234375,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.0419,
      "step": 20
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 1.1484375,
      "learning_rate": 9.545454545454547e-06,
      "loss": 1.0356,
      "step": 21
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.28125,
      "learning_rate": 1e-05,
      "loss": 0.9778,
      "step": 22
    },
    {
      "epoch": 0.07744107744107744,
      "grad_norm": 1.1875,
      "learning_rate": 1.0454545454545455e-05,
      "loss": 0.9691,
      "step": 23
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.1953125,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 1.0408,
      "step": 24
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 1.078125,
      "learning_rate": 1.1363636363636366e-05,
      "loss": 0.9799,
      "step": 25
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 1.0390625,
      "learning_rate": 1.181818181818182e-05,
      "loss": 0.9756,
      "step": 26
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.1875,
      "learning_rate": 1.2272727272727274e-05,
      "loss": 1.0451,
      "step": 27
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 1.0546875,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 1.0093,
      "step": 28
    },
    {
      "epoch": 0.09764309764309764,
      "grad_norm": 0.96484375,
      "learning_rate": 1.3181818181818183e-05,
      "loss": 0.99,
      "step": 29
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.0703125,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 1.0079,
      "step": 30
    },
    {
      "epoch": 0.10437710437710437,
      "grad_norm": 0.89453125,
      "learning_rate": 1.4090909090909092e-05,
      "loss": 0.9653,
      "step": 31
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 1.0546875,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 0.9926,
      "step": 32
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.96875,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.9857,
      "step": 33
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 1.1484375,
      "learning_rate": 1.5454545454545454e-05,
      "loss": 0.9676,
      "step": 34
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 1.078125,
      "learning_rate": 1.590909090909091e-05,
      "loss": 0.9686,
      "step": 35
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.8203125,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.9182,
      "step": 36
    },
    {
      "epoch": 0.12457912457912458,
      "grad_norm": 0.8515625,
      "learning_rate": 1.681818181818182e-05,
      "loss": 0.9506,
      "step": 37
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 0.86328125,
      "learning_rate": 1.7272727272727274e-05,
      "loss": 0.9533,
      "step": 38
    },
    {
      "epoch": 0.12794612794612795,
      "eval_loss": 0.9329763054847717,
      "eval_runtime": 8.7095,
      "eval_samples_per_second": 57.409,
      "eval_steps_per_second": 3.674,
      "step": 38
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 0.7890625,
      "learning_rate": 1.772727272727273e-05,
      "loss": 0.9225,
      "step": 39
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 0.890625,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.9378,
      "step": 40
    },
    {
      "epoch": 0.13804713804713806,
      "grad_norm": 1.046875,
      "learning_rate": 1.8636363636363638e-05,
      "loss": 0.8982,
      "step": 41
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 0.94921875,
      "learning_rate": 1.9090909090909094e-05,
      "loss": 0.8958,
      "step": 42
    },
    {
      "epoch": 0.1447811447811448,
      "grad_norm": 0.9765625,
      "learning_rate": 1.9545454545454546e-05,
      "loss": 0.8796,
      "step": 43
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.92578125,
      "learning_rate": 2e-05,
      "loss": 0.8808,
      "step": 44
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.94921875,
      "learning_rate": 1.9999931213623708e-05,
      "loss": 0.8638,
      "step": 45
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 1.0390625,
      "learning_rate": 1.999972485544114e-05,
      "loss": 0.9124,
      "step": 46
    },
    {
      "epoch": 0.15824915824915825,
      "grad_norm": 1.046875,
      "learning_rate": 1.999938092829122e-05,
      "loss": 0.8757,
      "step": 47
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.73046875,
      "learning_rate": 1.999889943690545e-05,
      "loss": 0.885,
      "step": 48
    },
    {
      "epoch": 0.16498316498316498,
      "grad_norm": 0.86328125,
      "learning_rate": 1.9998280387907845e-05,
      "loss": 0.8664,
      "step": 49
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 0.87109375,
      "learning_rate": 1.9997523789814827e-05,
      "loss": 0.8512,
      "step": 50
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 0.80859375,
      "learning_rate": 1.9996629653035128e-05,
      "loss": 0.8428,
      "step": 51
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 0.71875,
      "learning_rate": 1.9995597989869625e-05,
      "loss": 0.8536,
      "step": 52
    },
    {
      "epoch": 0.17845117845117844,
      "grad_norm": 0.6171875,
      "learning_rate": 1.9994428814511205e-05,
      "loss": 0.82,
      "step": 53
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.71875,
      "learning_rate": 1.999312214304453e-05,
      "loss": 0.8043,
      "step": 54
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.8046875,
      "learning_rate": 1.9991677993445832e-05,
      "loss": 0.8525,
      "step": 55
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 0.6015625,
      "learning_rate": 1.9990096385582682e-05,
      "loss": 0.7958,
      "step": 56
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 0.79296875,
      "learning_rate": 1.998837734121369e-05,
      "loss": 0.8001,
      "step": 57
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 0.7109375,
      "learning_rate": 1.9986520883988233e-05,
      "loss": 0.805,
      "step": 58
    },
    {
      "epoch": 0.19865319865319866,
      "grad_norm": 0.84375,
      "learning_rate": 1.9984527039446093e-05,
      "loss": 0.7821,
      "step": 59
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.1015625,
      "learning_rate": 1.998239583501714e-05,
      "loss": 0.7932,
      "step": 60
    },
    {
      "epoch": 0.2053872053872054,
      "grad_norm": 0.6953125,
      "learning_rate": 1.9980127300020946e-05,
      "loss": 0.7925,
      "step": 61
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 0.60546875,
      "learning_rate": 1.9977721465666365e-05,
      "loss": 0.7846,
      "step": 62
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.7265625,
      "learning_rate": 1.9975178365051123e-05,
      "loss": 0.7671,
      "step": 63
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.70703125,
      "learning_rate": 1.997249803316136e-05,
      "loss": 0.8194,
      "step": 64
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 0.81640625,
      "learning_rate": 1.9969680506871138e-05,
      "loss": 0.7607,
      "step": 65
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.61328125,
      "learning_rate": 1.9966725824941933e-05,
      "loss": 0.7858,
      "step": 66
    },
    {
      "epoch": 0.2255892255892256,
      "grad_norm": 0.66015625,
      "learning_rate": 1.9963634028022133e-05,
      "loss": 0.7546,
      "step": 67
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 0.6875,
      "learning_rate": 1.9960405158646425e-05,
      "loss": 0.7915,
      "step": 68
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 0.59765625,
      "learning_rate": 1.9957039261235263e-05,
      "loss": 0.7324,
      "step": 69
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 0.65625,
      "learning_rate": 1.9953536382094218e-05,
      "loss": 0.7735,
      "step": 70
    },
    {
      "epoch": 0.23905723905723905,
      "grad_norm": 0.984375,
      "learning_rate": 1.9949896569413368e-05,
      "loss": 0.7356,
      "step": 71
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.8125,
      "learning_rate": 1.9946119873266615e-05,
      "loss": 0.7407,
      "step": 72
    },
    {
      "epoch": 0.24579124579124578,
      "grad_norm": 0.76953125,
      "learning_rate": 1.9942206345611008e-05,
      "loss": 0.7124,
      "step": 73
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 0.6640625,
      "learning_rate": 1.9938156040286027e-05,
      "loss": 0.7295,
      "step": 74
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 0.5546875,
      "learning_rate": 1.993396901301283e-05,
      "loss": 0.733,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 891,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 75,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.36437672443904e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}