{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 42,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 9.980156898498535,
      "learning_rate": 2e-05,
      "loss": 2.1337890625,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 7.115320205688477,
      "learning_rate": 1.9972037971811802e-05,
      "loss": 1.4287109375,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 10.563518524169922,
      "learning_rate": 1.9888308262251286e-05,
      "loss": 1.23828125,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 2.9927895069122314,
      "learning_rate": 1.9749279121818235e-05,
      "loss": 1.14501953125,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 3.276383399963379,
      "learning_rate": 1.955572805786141e-05,
      "loss": 1.09228515625,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.283390760421753,
      "learning_rate": 1.9308737486442045e-05,
      "loss": 1.0439453125,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.6059461832046509,
      "learning_rate": 1.900968867902419e-05,
      "loss": 1.0419921875,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.7341160774230957,
      "learning_rate": 1.866025403784439e-05,
      "loss": 1.01220703125,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.2254583835601807,
      "learning_rate": 1.826238774315995e-05,
      "loss": 1.013671875,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 1.5042554140090942,
      "learning_rate": 1.78183148246803e-05,
      "loss": 1.013671875,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 1.213415503501892,
      "learning_rate": 1.7330518718298263e-05,
      "loss": 1.03662109375,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.2206931114196777,
      "learning_rate": 1.6801727377709195e-05,
      "loss": 1.00732421875,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 1.0425015687942505,
      "learning_rate": 1.6234898018587336e-05,
      "loss": 0.974609375,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.1242820024490356,
      "learning_rate": 1.563320058063622e-05,
      "loss": 0.9814453125,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.9458146691322327,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.96875,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.9981818795204163,
      "learning_rate": 1.4338837391175582e-05,
      "loss": 0.96142578125,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.9959944486618042,
      "learning_rate": 1.3653410243663953e-05,
      "loss": 0.9775390625,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.9807628989219666,
      "learning_rate": 1.2947551744109044e-05,
      "loss": 0.95849609375,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.964298665523529,
      "learning_rate": 1.2225209339563144e-05,
      "loss": 0.94970703125,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.9234592914581299,
      "learning_rate": 1.1490422661761744e-05,
      "loss": 0.91455078125,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1632379293441772,
      "learning_rate": 1.0747300935864245e-05,
      "loss": 0.8896484375,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 1.1696614027023315,
      "learning_rate": 1e-05,
      "loss": 0.833984375,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 1.0527235269546509,
      "learning_rate": 9.252699064135759e-06,
      "loss": 0.83251953125,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.2121893167495728,
      "learning_rate": 8.509577338238255e-06,
      "loss": 0.87744140625,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 1.0663219690322876,
      "learning_rate": 7.774790660436857e-06,
      "loss": 0.783203125,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 1.0903716087341309,
      "learning_rate": 7.052448255890958e-06,
      "loss": 0.791015625,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.0819926261901855,
      "learning_rate": 6.34658975633605e-06,
      "loss": 0.7333984375,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.158378005027771,
      "learning_rate": 5.66116260882442e-06,
      "loss": 0.7041015625,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 1.0132827758789062,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.72119140625,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.042487382888794,
      "learning_rate": 4.3667994193637794e-06,
      "loss": 0.68017578125,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 1.0347169637680054,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 0.71728515625,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 1.0562595129013062,
      "learning_rate": 3.1982726222908046e-06,
      "loss": 0.71826171875,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.991810142993927,
      "learning_rate": 2.669481281701739e-06,
      "loss": 0.70751953125,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 1.035168170928955,
      "learning_rate": 2.1816851753197023e-06,
      "loss": 0.667236328125,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.1264833211898804,
      "learning_rate": 1.7376122568400533e-06,
      "loss": 0.71240234375,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.9847052693367004,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.69384765625,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.9455327391624451,
      "learning_rate": 9.903113209758098e-07,
      "loss": 0.70068359375,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 1.0034749507904053,
      "learning_rate": 6.912625135579587e-07,
      "loss": 0.736328125,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.0284539461135864,
      "learning_rate": 4.4427194213859216e-07,
      "loss": 0.73876953125,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 1.0030890703201294,
      "learning_rate": 2.507208781817638e-07,
      "loss": 0.74560546875,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.9933129549026489,
      "learning_rate": 1.1169173774871478e-07,
      "loss": 0.73046875,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.860466718673706,
      "learning_rate": 2.796202818819871e-08,
      "loss": 0.654296875,
      "step": 42
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5107421875,
      "eval_runtime": 12.404,
      "eval_samples_per_second": 0.161,
      "eval_steps_per_second": 0.081,
      "step": 42
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0636117736043315e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}