{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 95.33702850341797,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 5.3695,
      "step": 1
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 96.05199432373047,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 5.4178,
      "step": 2
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 92.71851348876953,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 5.4472,
      "step": 3
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 95.78789520263672,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 5.4114,
      "step": 4
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 95.62769317626953,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 5.3612,
      "step": 5
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 94.85267639160156,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 5.4065,
      "step": 6
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 93.81153869628906,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 5.364,
      "step": 7
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 95.33504486083984,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 5.4484,
      "step": 8
    },
    {
      "epoch": 0.125,
      "grad_norm": 94.11618041992188,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 5.3494,
      "step": 9
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 93.71621704101562,
      "learning_rate": 5.000000000000001e-07,
      "loss": 5.2325,
      "step": 10
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 92.6498031616211,
      "learning_rate": 5.5e-07,
      "loss": 5.1224,
      "step": 11
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 89.05821228027344,
      "learning_rate": 6.000000000000001e-07,
      "loss": 5.0484,
      "step": 12
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 87.52056884765625,
      "learning_rate": 6.5e-07,
      "loss": 4.8831,
      "step": 13
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 87.93170928955078,
      "learning_rate": 7.000000000000001e-07,
      "loss": 4.7723,
      "step": 14
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 84.07933044433594,
      "learning_rate": 7.5e-07,
      "loss": 4.5843,
      "step": 15
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 82.16165161132812,
      "learning_rate": 8.000000000000001e-07,
      "loss": 4.4273,
      "step": 16
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 78.94780731201172,
      "learning_rate": 8.500000000000001e-07,
      "loss": 4.155,
      "step": 17
    },
    {
      "epoch": 0.25,
      "grad_norm": 75.85335540771484,
      "learning_rate": 9.000000000000001e-07,
      "loss": 3.9005,
      "step": 18
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 71.74459075927734,
      "learning_rate": 9.500000000000001e-07,
      "loss": 3.5885,
      "step": 19
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 67.66385650634766,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.308,
      "step": 20
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 64.22036743164062,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 3.057,
      "step": 21
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 60.24971008300781,
      "learning_rate": 1.1e-06,
      "loss": 2.7939,
      "step": 22
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 57.68950271606445,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 2.5539,
      "step": 23
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 56.10525894165039,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.2688,
      "step": 24
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 54.84128189086914,
      "learning_rate": 1.25e-06,
      "loss": 2.009,
      "step": 25
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 53.96566390991211,
      "learning_rate": 1.3e-06,
      "loss": 1.6682,
      "step": 26
    },
    {
      "epoch": 0.375,
      "grad_norm": 53.859439849853516,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 1.3807,
      "step": 27
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 53.22216796875,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 1.1229,
      "step": 28
    },
    {
      "epoch": 0.4027777777777778,
      "grad_norm": 50.3905143737793,
      "learning_rate": 1.45e-06,
      "loss": 0.8454,
      "step": 29
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 40.14346694946289,
      "learning_rate": 1.5e-06,
      "loss": 0.5817,
      "step": 30
    },
    {
      "epoch": 0.4305555555555556,
      "grad_norm": 34.043235778808594,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.4234,
      "step": 31
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 28.703292846679688,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.3074,
      "step": 32
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 22.456626892089844,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.2146,
      "step": 33
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 15.350156784057617,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.1103,
      "step": 34
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 6.5175580978393555,
      "learning_rate": 1.75e-06,
      "loss": 0.0574,
      "step": 35
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.813859939575195,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0497,
      "step": 36
    },
    {
      "epoch": 0.5138888888888888,
      "grad_norm": 3.5350818634033203,
      "learning_rate": 1.85e-06,
      "loss": 0.0199,
      "step": 37
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 4.9657135009765625,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0245,
      "step": 38
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 1.2266570329666138,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0087,
      "step": 39
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 4.982794761657715,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.048,
      "step": 40
    },
    {
      "epoch": 0.5694444444444444,
      "grad_norm": 7.6967387199401855,
      "learning_rate": 2.05e-06,
      "loss": 0.0449,
      "step": 41
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 2.9466323852539062,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0098,
      "step": 42
    },
    {
      "epoch": 0.5972222222222222,
      "grad_norm": 2.191035747528076,
      "learning_rate": 2.15e-06,
      "loss": 0.0087,
      "step": 43
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 7.3228840827941895,
      "learning_rate": 2.2e-06,
      "loss": 0.0339,
      "step": 44
    },
    {
      "epoch": 0.625,
      "grad_norm": 4.737412929534912,
      "learning_rate": 2.25e-06,
      "loss": 0.0149,
      "step": 45
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 1.7612887620925903,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0071,
      "step": 46
    },
    {
      "epoch": 0.6527777777777778,
      "grad_norm": 3.344369649887085,
      "learning_rate": 2.35e-06,
      "loss": 0.0196,
      "step": 47
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.2957704067230225,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0216,
      "step": 48
    },
    {
      "epoch": 0.6805555555555556,
      "grad_norm": 1.83970308303833,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0221,
      "step": 49
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 1.547287106513977,
      "learning_rate": 2.5e-06,
      "loss": 0.0061,
      "step": 50
    },
    {
      "epoch": 0.7083333333333334,
      "grad_norm": 1.6580262184143066,
      "learning_rate": 2.55e-06,
      "loss": 0.0127,
      "step": 51
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 1.8863849639892578,
      "learning_rate": 2.6e-06,
      "loss": 0.0124,
      "step": 52
    },
    {
      "epoch": 0.7361111111111112,
      "grad_norm": 1.2086963653564453,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0085,
      "step": 53
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.4265427589416504,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0255,
      "step": 54
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 2.0333855152130127,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0145,
      "step": 55
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 2.9129791259765625,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0228,
      "step": 56
    },
    {
      "epoch": 0.7916666666666666,
      "grad_norm": 0.8359552621841431,
      "learning_rate": 2.85e-06,
      "loss": 0.0109,
      "step": 57
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 1.677287220954895,
      "learning_rate": 2.9e-06,
      "loss": 0.0246,
      "step": 58
    },
    {
      "epoch": 0.8194444444444444,
      "grad_norm": 1.0761189460754395,
      "learning_rate": 2.95e-06,
      "loss": 0.0058,
      "step": 59
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 1.1098495721817017,
      "learning_rate": 3e-06,
      "loss": 0.0167,
      "step": 60
    },
    {
      "epoch": 0.8472222222222222,
      "grad_norm": 1.0377463102340698,
      "learning_rate": 3.05e-06,
      "loss": 0.007,
      "step": 61
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 0.6554276347160339,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0039,
      "step": 62
    },
    {
      "epoch": 0.875,
      "grad_norm": 1.279077410697937,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0199,
      "step": 63
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.7709833979606628,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0043,
      "step": 64
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 1.3619827032089233,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0067,
      "step": 65
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 1.3849765062332153,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0091,
      "step": 66
    },
    {
      "epoch": 0.9305555555555556,
      "grad_norm": 1.1380351781845093,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0143,
      "step": 67
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 1.9759573936462402,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0231,
      "step": 68
    },
    {
      "epoch": 0.9583333333333334,
      "grad_norm": 0.5920725464820862,
      "learning_rate": 3.45e-06,
      "loss": 0.0063,
      "step": 69
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 1.2489631175994873,
      "learning_rate": 3.5e-06,
      "loss": 0.0149,
      "step": 70
    },
    {
      "epoch": 0.9861111111111112,
      "grad_norm": 1.5553513765335083,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0085,
      "step": 71
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0278698205947876,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0061,
      "step": 72
    }
  ],
  "logging_steps": 1,
  "max_steps": 432,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 72,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8124313299255296e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}