{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.8615384615384616,
  "eval_steps": 500,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08205128205128205,
      "grad_norm": 11.399080276489258,
      "learning_rate": 0.00019583333333333334,
      "loss": 75.6247,
      "step": 2
    },
    {
      "epoch": 0.1641025641025641,
      "grad_norm": 17.320436477661133,
      "learning_rate": 0.00019166666666666667,
      "loss": 71.7205,
      "step": 4
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": NaN,
      "learning_rate": 0.00018958333333333332,
      "loss": 65.3071,
      "step": 6
    },
    {
      "epoch": 0.3282051282051282,
      "grad_norm": 17.457279205322266,
      "learning_rate": 0.00018541666666666668,
      "loss": 63.1094,
      "step": 8
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 20.812185287475586,
      "learning_rate": 0.00018125000000000001,
      "loss": 60.4665,
      "step": 10
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 23.849903106689453,
      "learning_rate": 0.00017708333333333335,
      "loss": 56.8296,
      "step": 12
    },
    {
      "epoch": 0.5743589743589743,
      "grad_norm": 14.324117660522461,
      "learning_rate": 0.00017291666666666668,
      "loss": 55.1421,
      "step": 14
    },
    {
      "epoch": 0.6564102564102564,
      "grad_norm": 8.510538101196289,
      "learning_rate": 0.00016875,
      "loss": 54.8105,
      "step": 16
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 6.031883239746094,
      "learning_rate": 0.00016458333333333334,
      "loss": 52.9411,
      "step": 18
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 6.2261061668396,
      "learning_rate": 0.00016041666666666667,
      "loss": 53.788,
      "step": 20
    },
    {
      "epoch": 0.9025641025641026,
      "grad_norm": 8.355509757995605,
      "learning_rate": 0.00015625,
      "loss": 52.0403,
      "step": 22
    },
    {
      "epoch": 0.9846153846153847,
      "grad_norm": 10.010218620300293,
      "learning_rate": 0.00015208333333333333,
      "loss": 53.6758,
      "step": 24
    },
    {
      "epoch": 1.041025641025641,
      "grad_norm": 5.320664882659912,
      "learning_rate": 0.0001479166666666667,
      "loss": 35.4336,
      "step": 26
    },
    {
      "epoch": 1.123076923076923,
      "grad_norm": 6.9148478507995605,
      "learning_rate": 0.00014375,
      "loss": 52.6291,
      "step": 28
    },
    {
      "epoch": 1.205128205128205,
      "grad_norm": 4.67191743850708,
      "learning_rate": 0.00013958333333333333,
      "loss": 52.2121,
      "step": 30
    },
    {
      "epoch": 1.287179487179487,
      "grad_norm": 7.0961689949035645,
      "learning_rate": 0.0001354166666666667,
      "loss": 51.0249,
      "step": 32
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 11.30848217010498,
      "learning_rate": 0.00013125000000000002,
      "loss": 53.0805,
      "step": 34
    },
    {
      "epoch": 1.4512820512820512,
      "grad_norm": 6.0200419425964355,
      "learning_rate": 0.00012708333333333332,
      "loss": 52.6946,
      "step": 36
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 5.744126319885254,
      "learning_rate": 0.00012291666666666668,
      "loss": 51.4448,
      "step": 38
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 4.301318645477295,
      "learning_rate": 0.00011875,
      "loss": 51.0796,
      "step": 40
    },
    {
      "epoch": 1.6974358974358974,
      "grad_norm": 6.739460468292236,
      "learning_rate": 0.00011458333333333333,
      "loss": 52.3609,
      "step": 42
    },
    {
      "epoch": 1.7794871794871794,
      "grad_norm": 3.347414493560791,
      "learning_rate": 0.00011041666666666668,
      "loss": 51.6531,
      "step": 44
    },
    {
      "epoch": 1.8615384615384616,
      "grad_norm": 7.933114528656006,
      "learning_rate": 0.00010625000000000001,
      "loss": 51.9316,
      "step": 46
    },
    {
      "epoch": 1.9435897435897436,
      "grad_norm": 4.68740177154541,
      "learning_rate": 0.00010208333333333333,
      "loss": 53.1193,
      "step": 48
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.4068479537963867,
      "learning_rate": 9.791666666666667e-05,
      "loss": 35.3235,
      "step": 50
    },
    {
      "epoch": 2.082051282051282,
      "grad_norm": 8.956518173217773,
      "learning_rate": 9.375e-05,
      "loss": 51.9865,
      "step": 52
    },
    {
      "epoch": 2.164102564102564,
      "grad_norm": 6.310459613800049,
      "learning_rate": 8.958333333333335e-05,
      "loss": 51.7456,
      "step": 54
    },
    {
      "epoch": 2.246153846153846,
      "grad_norm": 8.6781644821167,
      "learning_rate": 8.541666666666666e-05,
      "loss": 52.5304,
      "step": 56
    },
    {
      "epoch": 2.3282051282051284,
      "grad_norm": 3.7787671089172363,
      "learning_rate": 8.125000000000001e-05,
      "loss": 51.84,
      "step": 58
    },
    {
      "epoch": 2.41025641025641,
      "grad_norm": 7.715843200683594,
      "learning_rate": 7.708333333333334e-05,
      "loss": 51.1438,
      "step": 60
    },
    {
      "epoch": 2.4923076923076923,
      "grad_norm": 9.50344181060791,
      "learning_rate": 7.291666666666667e-05,
      "loss": 50.2017,
      "step": 62
    },
    {
      "epoch": 2.574358974358974,
      "grad_norm": 5.091357231140137,
      "learning_rate": 6.875e-05,
      "loss": 52.1048,
      "step": 64
    },
    {
      "epoch": 2.6564102564102563,
      "grad_norm": 6.4015421867370605,
      "learning_rate": 6.458333333333334e-05,
      "loss": 52.0365,
      "step": 66
    },
    {
      "epoch": 2.7384615384615385,
      "grad_norm": 3.156503438949585,
      "learning_rate": 6.041666666666667e-05,
      "loss": 51.8669,
      "step": 68
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 5.185201644897461,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 50.7857,
      "step": 70
    },
    {
      "epoch": 2.9025641025641025,
      "grad_norm": 3.295457601547241,
      "learning_rate": 5.208333333333334e-05,
      "loss": 51.0927,
      "step": 72
    },
    {
      "epoch": 2.9846153846153847,
      "grad_norm": 5.918073654174805,
      "learning_rate": 4.791666666666667e-05,
      "loss": 52.483,
      "step": 74
    },
    {
      "epoch": 3.041025641025641,
      "grad_norm": 6.10349702835083,
      "learning_rate": 4.375e-05,
      "loss": 35.2321,
      "step": 76
    },
    {
      "epoch": 3.123076923076923,
      "grad_norm": 4.493152618408203,
      "learning_rate": 3.958333333333333e-05,
      "loss": 51.6482,
      "step": 78
    },
    {
      "epoch": 3.2051282051282053,
      "grad_norm": 3.8696682453155518,
      "learning_rate": 3.541666666666667e-05,
      "loss": 52.3785,
      "step": 80
    },
    {
      "epoch": 3.287179487179487,
      "grad_norm": 4.229553699493408,
      "learning_rate": 3.125e-05,
      "loss": 51.059,
      "step": 82
    },
    {
      "epoch": 3.3692307692307693,
      "grad_norm": 5.5054779052734375,
      "learning_rate": 2.7083333333333332e-05,
      "loss": 52.1417,
      "step": 84
    },
    {
      "epoch": 3.4512820512820515,
      "grad_norm": 8.53302001953125,
      "learning_rate": 2.2916666666666667e-05,
      "loss": 51.1943,
      "step": 86
    },
    {
      "epoch": 3.533333333333333,
      "grad_norm": 6.278346538543701,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 51.0593,
      "step": 88
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 3.9308125972747803,
      "learning_rate": 1.4583333333333335e-05,
      "loss": 51.8184,
      "step": 90
    },
    {
      "epoch": 3.6974358974358976,
      "grad_norm": 4.1439971923828125,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 52.4379,
      "step": 92
    },
    {
      "epoch": 3.7794871794871794,
      "grad_norm": 5.464842796325684,
      "learning_rate": 6.25e-06,
      "loss": 51.1109,
      "step": 94
    },
    {
      "epoch": 3.8615384615384616,
      "grad_norm": 2.955758571624756,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 50.9587,
      "step": 96
    },
    {
      "epoch": 3.8615384615384616,
      "step": 96,
      "total_flos": 943340021512272.0,
      "train_loss": 52.71458212534586,
      "train_runtime": 1936.9788,
      "train_samples_per_second": 0.805,
      "train_steps_per_second": 0.05
    }
  ],
  "logging_steps": 2,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 943340021512272.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}