{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 76,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013157894736842105,
      "grad_norm": 34.99433898925781,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.595,
      "step": 1
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 35.6848258972168,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.6447,
      "step": 2
    },
    {
      "epoch": 0.039473684210526314,
      "grad_norm": 35.07997512817383,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.5819,
      "step": 3
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 34.3863525390625,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.5739,
      "step": 4
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 35.443077087402344,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.6071,
      "step": 5
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 34.70173263549805,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.5487,
      "step": 6
    },
    {
      "epoch": 0.09210526315789473,
      "grad_norm": 34.421295166015625,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.5494,
      "step": 7
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 35.152748107910156,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.5936,
      "step": 8
    },
    {
      "epoch": 0.11842105263157894,
      "grad_norm": 34.947021484375,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.5574,
      "step": 9
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 34.67315673828125,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.4894,
      "step": 10
    },
    {
      "epoch": 0.14473684210526316,
      "grad_norm": 34.679954528808594,
      "learning_rate": 5.5e-07,
      "loss": 2.4985,
      "step": 11
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 33.57002258300781,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.4339,
      "step": 12
    },
    {
      "epoch": 0.17105263157894737,
      "grad_norm": 33.517276763916016,
      "learning_rate": 6.5e-07,
      "loss": 2.4055,
      "step": 13
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 33.5312385559082,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.3806,
      "step": 14
    },
    {
      "epoch": 0.19736842105263158,
      "grad_norm": 32.01276779174805,
      "learning_rate": 7.5e-07,
      "loss": 2.2505,
      "step": 15
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 31.827980041503906,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.1359,
      "step": 16
    },
    {
      "epoch": 0.2236842105263158,
      "grad_norm": 31.437101364135742,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.1117,
      "step": 17
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 30.315187454223633,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.9795,
      "step": 18
    },
    {
      "epoch": 0.25,
      "grad_norm": 29.622655868530273,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.8472,
      "step": 19
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 28.628408432006836,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7283,
      "step": 20
    },
    {
      "epoch": 0.27631578947368424,
      "grad_norm": 27.83180046081543,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.5942,
      "step": 21
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 26.911596298217773,
      "learning_rate": 1.1e-06,
      "loss": 1.4467,
      "step": 22
    },
    {
      "epoch": 0.3026315789473684,
      "grad_norm": 25.88102149963379,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.3007,
      "step": 23
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 25.146381378173828,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.1319,
      "step": 24
    },
    {
      "epoch": 0.32894736842105265,
      "grad_norm": 24.800382614135742,
      "learning_rate": 1.25e-06,
      "loss": 0.9359,
      "step": 25
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 24.648332595825195,
      "learning_rate": 1.3e-06,
      "loss": 0.7054,
      "step": 26
    },
    {
      "epoch": 0.35526315789473684,
      "grad_norm": 22.947620391845703,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.5209,
      "step": 27
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 17.80010414123535,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.3546,
      "step": 28
    },
    {
      "epoch": 0.3815789473684211,
      "grad_norm": 11.841789245605469,
      "learning_rate": 1.45e-06,
      "loss": 0.26,
      "step": 29
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 7.275839805603027,
      "learning_rate": 1.5e-06,
      "loss": 0.1808,
      "step": 30
    },
    {
      "epoch": 0.40789473684210525,
      "grad_norm": 4.6324543952941895,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.1464,
      "step": 31
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 3.1281485557556152,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.1079,
      "step": 32
    },
    {
      "epoch": 0.4342105263157895,
      "grad_norm": 2.062562942504883,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0966,
      "step": 33
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 2.1343328952789307,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.088,
      "step": 34
    },
    {
      "epoch": 0.4605263157894737,
      "grad_norm": 1.6768524646759033,
      "learning_rate": 1.75e-06,
      "loss": 0.0783,
      "step": 35
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 1.0879229307174683,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0623,
      "step": 36
    },
    {
      "epoch": 0.4868421052631579,
      "grad_norm": 0.83177649974823,
      "learning_rate": 1.85e-06,
      "loss": 0.0655,
      "step": 37
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5678385496139526,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0565,
      "step": 38
    },
    {
      "epoch": 0.5131578947368421,
      "grad_norm": 0.6994458436965942,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0491,
      "step": 39
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.711387038230896,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0507,
      "step": 40
    },
    {
      "epoch": 0.5394736842105263,
      "grad_norm": 0.7169735431671143,
      "learning_rate": 2.05e-06,
      "loss": 0.0478,
      "step": 41
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 0.603631317615509,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0507,
      "step": 42
    },
    {
      "epoch": 0.5657894736842105,
      "grad_norm": 0.617487907409668,
      "learning_rate": 2.15e-06,
      "loss": 0.043,
      "step": 43
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.4638065993785858,
      "learning_rate": 2.2e-06,
      "loss": 0.0472,
      "step": 44
    },
    {
      "epoch": 0.5921052631578947,
      "grad_norm": 0.5996385216712952,
      "learning_rate": 2.25e-06,
      "loss": 0.0429,
      "step": 45
    },
    {
      "epoch": 0.6052631578947368,
      "grad_norm": 0.39118286967277527,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0421,
      "step": 46
    },
    {
      "epoch": 0.618421052631579,
      "grad_norm": 0.3118075728416443,
      "learning_rate": 2.35e-06,
      "loss": 0.0383,
      "step": 47
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.31731992959976196,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.041,
      "step": 48
    },
    {
      "epoch": 0.6447368421052632,
      "grad_norm": 0.5413194298744202,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0397,
      "step": 49
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 0.32958006858825684,
      "learning_rate": 2.5e-06,
      "loss": 0.0355,
      "step": 50
    },
    {
      "epoch": 0.6710526315789473,
      "grad_norm": 0.596309244632721,
      "learning_rate": 2.55e-06,
      "loss": 0.0413,
      "step": 51
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.4557362496852875,
      "learning_rate": 2.6e-06,
      "loss": 0.0461,
      "step": 52
    },
    {
      "epoch": 0.6973684210526315,
      "grad_norm": 0.3345410227775574,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0385,
      "step": 53
    },
    {
      "epoch": 0.7105263157894737,
      "grad_norm": 0.3047848343849182,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0383,
      "step": 54
    },
    {
      "epoch": 0.7236842105263158,
      "grad_norm": 0.43763449788093567,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.038,
      "step": 55
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.26870036125183105,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0374,
      "step": 56
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.38762542605400085,
      "learning_rate": 2.85e-06,
      "loss": 0.0349,
      "step": 57
    },
    {
      "epoch": 0.7631578947368421,
      "grad_norm": 0.27517396211624146,
      "learning_rate": 2.9e-06,
      "loss": 0.0398,
      "step": 58
    },
    {
      "epoch": 0.7763157894736842,
      "grad_norm": 0.30815261602401733,
      "learning_rate": 2.95e-06,
      "loss": 0.0364,
      "step": 59
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.30011361837387085,
      "learning_rate": 3e-06,
      "loss": 0.0307,
      "step": 60
    },
    {
      "epoch": 0.8026315789473685,
      "grad_norm": 0.3269154727458954,
      "learning_rate": 3.05e-06,
      "loss": 0.0344,
      "step": 61
    },
    {
      "epoch": 0.8157894736842105,
      "grad_norm": 0.3750869333744049,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0339,
      "step": 62
    },
    {
      "epoch": 0.8289473684210527,
      "grad_norm": 0.29285815358161926,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.034,
      "step": 63
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.4157550632953644,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0348,
      "step": 64
    },
    {
      "epoch": 0.8552631578947368,
      "grad_norm": 0.2852867543697357,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0319,
      "step": 65
    },
    {
      "epoch": 0.868421052631579,
      "grad_norm": 0.4384031593799591,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0319,
      "step": 66
    },
    {
      "epoch": 0.881578947368421,
      "grad_norm": 0.4003254771232605,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0347,
      "step": 67
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.49913832545280457,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0347,
      "step": 68
    },
    {
      "epoch": 0.9078947368421053,
      "grad_norm": 0.22642269730567932,
      "learning_rate": 3.45e-06,
      "loss": 0.0306,
      "step": 69
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 0.34004101157188416,
      "learning_rate": 3.5e-06,
      "loss": 0.0337,
      "step": 70
    },
    {
      "epoch": 0.9342105263157895,
      "grad_norm": 0.21503636240959167,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0311,
      "step": 71
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.33802086114883423,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0293,
      "step": 72
    },
    {
      "epoch": 0.9605263157894737,
      "grad_norm": 0.2488064169883728,
      "learning_rate": 3.65e-06,
      "loss": 0.0318,
      "step": 73
    },
    {
      "epoch": 0.9736842105263158,
      "grad_norm": 0.21124528348445892,
      "learning_rate": 3.7e-06,
      "loss": 0.0293,
      "step": 74
    },
    {
      "epoch": 0.9868421052631579,
      "grad_norm": 0.3108712136745453,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0288,
      "step": 75
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.33483418822288513,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.031,
      "step": 76
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 76,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.889219280312205e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}