{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004449454200284765,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.932605600379687e-05,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 5.932605600379687e-05,
      "eval_loss": NaN,
      "eval_runtime": 2298.0875,
      "eval_samples_per_second": 3.089,
      "eval_steps_per_second": 0.386,
      "step": 1
    },
    {
      "epoch": 0.00011865211200759374,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0001779781680113906,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00023730422401518748,
      "grad_norm": NaN,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00029663028001898433,
      "grad_norm": NaN,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0003559563360227812,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0004152823920265781,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00047460844803037496,
      "grad_norm": NaN,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0005339345040341718,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0005932605600379687,
      "grad_norm": NaN,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0006525866160417656,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0007119126720455624,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0007712387280493592,
      "grad_norm": NaN,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0008305647840531562,
      "grad_norm": NaN,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.000889890840056953,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0009492168960607499,
      "grad_norm": NaN,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0010085429520645468,
      "grad_norm": NaN,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0010678690080683437,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0011271950640721405,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0011865211200759373,
      "grad_norm": NaN,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0012458471760797341,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0013051732320835312,
      "grad_norm": NaN,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.001364499288087328,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.0014238253440911248,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0014831514000949216,
      "grad_norm": NaN,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0014831514000949216,
      "eval_loss": NaN,
      "eval_runtime": 2298.0102,
      "eval_samples_per_second": 3.089,
      "eval_steps_per_second": 0.386,
      "step": 25
    },
    {
      "epoch": 0.0015424774560987185,
      "grad_norm": NaN,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.0016018035121025155,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0016611295681063123,
      "grad_norm": NaN,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.0017204556241101092,
      "grad_norm": NaN,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.001779781680113906,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0018391077361177028,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.0018984337921214998,
      "grad_norm": NaN,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.0019577598481252964,
      "grad_norm": NaN,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.0020170859041290937,
      "grad_norm": NaN,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0020764119601328905,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0021357380161366873,
      "grad_norm": NaN,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.002195064072140484,
      "grad_norm": NaN,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.002254390128144281,
      "grad_norm": NaN,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.002313716184148078,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.0023730422401518746,
      "grad_norm": NaN,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0024323682961556715,
      "grad_norm": NaN,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0024916943521594683,
      "grad_norm": NaN,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.002551020408163265,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0026103464641670624,
      "grad_norm": NaN,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.002669672520170859,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.002728998576174656,
      "grad_norm": NaN,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.002788324632178453,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.0028476506881822496,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0029069767441860465,
      "grad_norm": NaN,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.0029663028001898433,
      "grad_norm": NaN,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0029663028001898433,
      "eval_loss": NaN,
      "eval_runtime": 2297.7997,
      "eval_samples_per_second": 3.089,
      "eval_steps_per_second": 0.386,
      "step": 50
    },
    {
      "epoch": 0.00302562885619364,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.003084954912197437,
      "grad_norm": NaN,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.003144280968201234,
      "grad_norm": NaN,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.003203607024205031,
      "grad_norm": NaN,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.003262933080208828,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.0033222591362126247,
      "grad_norm": NaN,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.0033815851922164215,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.0034409112482202183,
      "grad_norm": NaN,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.003500237304224015,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.003559563360227812,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.0036188894162316088,
      "grad_norm": NaN,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.0036782154722354056,
      "grad_norm": NaN,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.003737541528239203,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.0037968675842429997,
      "grad_norm": NaN,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.0038561936402467965,
      "grad_norm": NaN,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.003915519696250593,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.00397484575225439,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.004034171808258187,
      "grad_norm": NaN,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.004093497864261984,
      "grad_norm": NaN,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.004152823920265781,
      "grad_norm": NaN,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.0042121499762695774,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.004271476032273375,
      "grad_norm": NaN,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.004330802088277171,
      "grad_norm": NaN,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.004390128144280968,
      "grad_norm": NaN,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.004449454200284765,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.004449454200284765,
      "eval_loss": NaN,
      "eval_runtime": 2298.5125,
      "eval_samples_per_second": 3.088,
      "eval_steps_per_second": 0.386,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.619338760192e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}