{
  "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": 2.2727272727272729e-07,
      "loss": 1.0833,
      "step": 1
    },
    {
      "epoch": 0.003367003367003367,
      "eval_loss": 1.032954454421997,
      "eval_runtime": 8.7985,
      "eval_samples_per_second": 56.828,
      "eval_steps_per_second": 3.637,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 2.265625,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.996,
      "step": 2
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 1.640625,
      "learning_rate": 6.818181818181818e-07,
      "loss": 1.0489,
      "step": 3
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 2.0625,
      "learning_rate": 9.090909090909091e-07,
      "loss": 1.0546,
      "step": 4
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 2.453125,
      "learning_rate": 1.1363636363636364e-06,
      "loss": 1.0341,
      "step": 5
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 1.9921875,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 1.0136,
      "step": 6
    },
    {
      "epoch": 0.02356902356902357,
      "grad_norm": 2.640625,
      "learning_rate": 1.590909090909091e-06,
      "loss": 1.0305,
      "step": 7
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 2.359375,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 1.0226,
      "step": 8
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.3125,
      "learning_rate": 2.0454545454545457e-06,
      "loss": 1.0745,
      "step": 9
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 2.359375,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 1.0232,
      "step": 10
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 2.53125,
      "learning_rate": 2.5e-06,
      "loss": 1.0106,
      "step": 11
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 2.125,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 1.0541,
      "step": 12
    },
    {
      "epoch": 0.04377104377104377,
      "grad_norm": 2.15625,
      "learning_rate": 2.954545454545455e-06,
      "loss": 1.0693,
      "step": 13
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 1.8359375,
      "learning_rate": 3.181818181818182e-06,
      "loss": 1.0338,
      "step": 14
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 2.0,
      "learning_rate": 3.409090909090909e-06,
      "loss": 1.0464,
      "step": 15
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 2.34375,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 1.0684,
      "step": 16
    },
    {
      "epoch": 0.05723905723905724,
      "grad_norm": 1.8125,
      "learning_rate": 3.863636363636364e-06,
      "loss": 1.0117,
      "step": 17
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.90625,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 1.0138,
      "step": 18
    },
    {
      "epoch": 0.06397306397306397,
      "grad_norm": 1.59375,
      "learning_rate": 4.3181818181818185e-06,
      "loss": 0.9873,
      "step": 19
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 1.59375,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.0524,
      "step": 20
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 1.3984375,
      "learning_rate": 4.772727272727273e-06,
      "loss": 1.0479,
      "step": 21
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.609375,
      "learning_rate": 5e-06,
      "loss": 0.9894,
      "step": 22
    },
    {
      "epoch": 0.07744107744107744,
      "grad_norm": 1.3671875,
      "learning_rate": 5.2272727272727274e-06,
      "loss": 0.983,
      "step": 23
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.6328125,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.0563,
      "step": 24
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 1.34375,
      "learning_rate": 5.681818181818183e-06,
      "loss": 0.9966,
      "step": 25
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 1.25,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.9922,
      "step": 26
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.3984375,
      "learning_rate": 6.136363636363637e-06,
      "loss": 1.0677,
      "step": 27
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 1.3828125,
      "learning_rate": 6.363636363636364e-06,
      "loss": 1.0325,
      "step": 28
    },
    {
      "epoch": 0.09764309764309764,
      "grad_norm": 1.1953125,
      "learning_rate": 6.590909090909091e-06,
      "loss": 1.0159,
      "step": 29
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.3125,
      "learning_rate": 6.818181818181818e-06,
      "loss": 1.0384,
      "step": 30
    },
    {
      "epoch": 0.10437710437710437,
      "grad_norm": 1.1171875,
      "learning_rate": 7.045454545454546e-06,
      "loss": 0.9949,
      "step": 31
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 1.2421875,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.0284,
      "step": 32
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.15625,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.0245,
      "step": 33
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 1.1875,
      "learning_rate": 7.727272727272727e-06,
      "loss": 1.0103,
      "step": 34
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 1.125,
      "learning_rate": 7.954545454545455e-06,
      "loss": 1.0129,
      "step": 35
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 1.03125,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.965,
      "step": 36
    },
    {
      "epoch": 0.12457912457912458,
      "grad_norm": 1.109375,
      "learning_rate": 8.40909090909091e-06,
      "loss": 1.0027,
      "step": 37
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 1.0859375,
      "learning_rate": 8.636363636363637e-06,
      "loss": 1.0093,
      "step": 38
    },
    {
      "epoch": 0.12794612794612795,
      "eval_loss": 0.9909602999687195,
      "eval_runtime": 8.9064,
      "eval_samples_per_second": 56.139,
      "eval_steps_per_second": 3.593,
      "step": 38
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 0.96484375,
      "learning_rate": 8.863636363636365e-06,
      "loss": 0.98,
      "step": 39
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 1.0078125,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.0,
      "step": 40
    },
    {
      "epoch": 0.13804713804713806,
      "grad_norm": 1.109375,
      "learning_rate": 9.318181818181819e-06,
      "loss": 0.9658,
      "step": 41
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 0.95703125,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.9656,
      "step": 42
    },
    {
      "epoch": 0.1447811447811448,
      "grad_norm": 1.0,
      "learning_rate": 9.772727272727273e-06,
      "loss": 0.9528,
      "step": 43
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.88671875,
      "learning_rate": 1e-05,
      "loss": 0.9546,
      "step": 44
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.984375,
      "learning_rate": 9.999965606811854e-06,
      "loss": 0.9406,
      "step": 45
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 1.0625,
      "learning_rate": 9.99986242772057e-06,
      "loss": 0.9975,
      "step": 46
    },
    {
      "epoch": 0.15824915824915825,
      "grad_norm": 0.94140625,
      "learning_rate": 9.99969046414561e-06,
      "loss": 0.9567,
      "step": 47
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.96484375,
      "learning_rate": 9.999449718452724e-06,
      "loss": 0.9707,
      "step": 48
    },
    {
      "epoch": 0.16498316498316498,
      "grad_norm": 1.0,
      "learning_rate": 9.999140193953923e-06,
      "loss": 0.9559,
      "step": 49
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 0.99609375,
      "learning_rate": 9.998761894907414e-06,
      "loss": 0.9398,
      "step": 50
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 0.83203125,
      "learning_rate": 9.998314826517564e-06,
      "loss": 0.9329,
      "step": 51
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 0.91015625,
      "learning_rate": 9.997798994934812e-06,
      "loss": 0.9478,
      "step": 52
    },
    {
      "epoch": 0.17845117845117844,
      "grad_norm": 0.94140625,
      "learning_rate": 9.997214407255602e-06,
      "loss": 0.9062,
      "step": 53
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.83203125,
      "learning_rate": 9.996561071522264e-06,
      "loss": 0.9089,
      "step": 54
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.0078125,
      "learning_rate": 9.995838996722916e-06,
      "loss": 0.9561,
      "step": 55
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 0.796875,
      "learning_rate": 9.995048192791341e-06,
      "loss": 0.8948,
      "step": 56
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 0.91796875,
      "learning_rate": 9.994188670606845e-06,
      "loss": 0.9095,
      "step": 57
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 0.8515625,
      "learning_rate": 9.993260441994116e-06,
      "loss": 0.9137,
      "step": 58
    },
    {
      "epoch": 0.19865319865319866,
      "grad_norm": 0.8671875,
      "learning_rate": 9.992263519723046e-06,
      "loss": 0.9012,
      "step": 59
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.8046875,
      "learning_rate": 9.99119791750857e-06,
      "loss": 0.9074,
      "step": 60
    },
    {
      "epoch": 0.2053872053872054,
      "grad_norm": 1.0859375,
      "learning_rate": 9.990063650010473e-06,
      "loss": 0.9106,
      "step": 61
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 1.0625,
      "learning_rate": 9.988860732833183e-06,
      "loss": 0.9012,
      "step": 62
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.93359375,
      "learning_rate": 9.987589182525562e-06,
      "loss": 0.8928,
      "step": 63
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.921875,
      "learning_rate": 9.98624901658068e-06,
      "loss": 0.9487,
      "step": 64
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 0.92578125,
      "learning_rate": 9.984840253435569e-06,
      "loss": 0.8887,
      "step": 65
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.8671875,
      "learning_rate": 9.983362912470967e-06,
      "loss": 0.9152,
      "step": 66
    },
    {
      "epoch": 0.2255892255892256,
      "grad_norm": 0.83984375,
      "learning_rate": 9.981817014011066e-06,
      "loss": 0.8849,
      "step": 67
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 0.94921875,
      "learning_rate": 9.980202579323212e-06,
      "loss": 0.9386,
      "step": 68
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 0.8203125,
      "learning_rate": 9.978519630617632e-06,
      "loss": 0.8651,
      "step": 69
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 0.7109375,
      "learning_rate": 9.976768191047109e-06,
      "loss": 0.9044,
      "step": 70
    },
    {
      "epoch": 0.23905723905723905,
      "grad_norm": 1.03125,
      "learning_rate": 9.974948284706684e-06,
      "loss": 0.8702,
      "step": 71
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.91796875,
      "learning_rate": 9.973059936633308e-06,
      "loss": 0.8748,
      "step": 72
    },
    {
      "epoch": 0.24579124579124578,
      "grad_norm": 0.66796875,
      "learning_rate": 9.971103172805504e-06,
      "loss": 0.8443,
      "step": 73
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 0.671875,
      "learning_rate": 9.969078020143013e-06,
      "loss": 0.8605,
      "step": 74
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 0.6796875,
      "learning_rate": 9.966984506506415e-06,
      "loss": 0.8661,
      "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
}