{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 1.9574642181396484,
      "learning_rate": 4.901e-05,
      "loss": 4.8716,
      "step": 100
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.562890648841858,
      "learning_rate": 4.801e-05,
      "loss": 2.5735,
      "step": 200
    },
    {
      "epoch": 0.06,
      "grad_norm": 2.5503687858581543,
      "learning_rate": 4.7010000000000006e-05,
      "loss": 2.2182,
      "step": 300
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.3021109104156494,
      "learning_rate": 4.601e-05,
      "loss": 1.9191,
      "step": 400
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.3246175050735474,
      "learning_rate": 4.5010000000000004e-05,
      "loss": 1.8126,
      "step": 500
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.04691481590271,
      "learning_rate": 4.401e-05,
      "loss": 1.7728,
      "step": 600
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.9935975670814514,
      "learning_rate": 4.301e-05,
      "loss": 1.6751,
      "step": 700
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.1450852155685425,
      "learning_rate": 4.201e-05,
      "loss": 1.5686,
      "step": 800
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.1858118772506714,
      "learning_rate": 4.101e-05,
      "loss": 1.6261,
      "step": 900
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.2318594455718994,
      "learning_rate": 4.0010000000000005e-05,
      "loss": 1.6018,
      "step": 1000
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.0691641569137573,
      "learning_rate": 3.901e-05,
      "loss": 1.5865,
      "step": 1100
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.8661352396011353,
      "learning_rate": 3.8010000000000004e-05,
      "loss": 1.4648,
      "step": 1200
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.9778139591217041,
      "learning_rate": 3.701e-05,
      "loss": 1.4765,
      "step": 1300
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.3476413488388062,
      "learning_rate": 3.601e-05,
      "loss": 1.5541,
      "step": 1400
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.7631675004959106,
      "learning_rate": 3.5010000000000005e-05,
      "loss": 1.5048,
      "step": 1500
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.1490070819854736,
      "learning_rate": 3.401e-05,
      "loss": 1.5052,
      "step": 1600
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.077760934829712,
      "learning_rate": 3.3010000000000004e-05,
      "loss": 1.5638,
      "step": 1700
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.8567506670951843,
      "learning_rate": 3.201e-05,
      "loss": 1.5387,
      "step": 1800
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.842096209526062,
      "learning_rate": 3.101e-05,
      "loss": 1.5037,
      "step": 1900
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8851768374443054,
      "learning_rate": 3.001e-05,
      "loss": 1.5145,
      "step": 2000
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.7667313814163208,
      "learning_rate": 2.9010000000000005e-05,
      "loss": 1.526,
      "step": 2100
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.079816460609436,
      "learning_rate": 2.8010000000000005e-05,
      "loss": 1.5332,
      "step": 2200
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.9301439523696899,
      "learning_rate": 2.701e-05,
      "loss": 1.4011,
      "step": 2300
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.9722267985343933,
      "learning_rate": 2.601e-05,
      "loss": 1.4697,
      "step": 2400
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.8725349307060242,
      "learning_rate": 2.501e-05,
      "loss": 1.4873,
      "step": 2500
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.0267070531845093,
      "learning_rate": 2.4010000000000002e-05,
      "loss": 1.4103,
      "step": 2600
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.70062655210495,
      "learning_rate": 2.301e-05,
      "loss": 1.3659,
      "step": 2700
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.8035644888877869,
      "learning_rate": 2.201e-05,
      "loss": 1.4009,
      "step": 2800
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.8089845776557922,
      "learning_rate": 2.101e-05,
      "loss": 1.4293,
      "step": 2900
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.8427271246910095,
      "learning_rate": 2.001e-05,
      "loss": 1.4011,
      "step": 3000
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.994111180305481,
      "learning_rate": 1.901e-05,
      "loss": 1.3785,
      "step": 3100
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.0096153020858765,
      "learning_rate": 1.8010000000000002e-05,
      "loss": 1.4122,
      "step": 3200
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.7762922644615173,
      "learning_rate": 1.701e-05,
      "loss": 1.3849,
      "step": 3300
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.1585968732833862,
      "learning_rate": 1.601e-05,
      "loss": 1.3961,
      "step": 3400
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.9618488550186157,
      "learning_rate": 1.5010000000000002e-05,
      "loss": 1.3458,
      "step": 3500
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.007106065750122,
      "learning_rate": 1.4010000000000001e-05,
      "loss": 1.3952,
      "step": 3600
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.9712181091308594,
      "learning_rate": 1.301e-05,
      "loss": 1.3275,
      "step": 3700
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.9360325336456299,
      "learning_rate": 1.201e-05,
      "loss": 1.3479,
      "step": 3800
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.889412522315979,
      "learning_rate": 1.1010000000000001e-05,
      "loss": 1.4002,
      "step": 3900
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4792468547821045,
      "learning_rate": 1.001e-05,
      "loss": 1.2896,
      "step": 4000
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.8564038276672363,
      "learning_rate": 9.01e-06,
      "loss": 1.3501,
      "step": 4100
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.8316518664360046,
      "learning_rate": 8.010000000000001e-06,
      "loss": 1.3673,
      "step": 4200
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8671555519104004,
      "learning_rate": 7.01e-06,
      "loss": 1.328,
      "step": 4300
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.9001341462135315,
      "learning_rate": 6.01e-06,
      "loss": 1.3363,
      "step": 4400
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.8028829097747803,
      "learning_rate": 5.01e-06,
      "loss": 1.3272,
      "step": 4500
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.923729419708252,
      "learning_rate": 4.01e-06,
      "loss": 1.3645,
      "step": 4600
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.2373661994934082,
      "learning_rate": 3.01e-06,
      "loss": 1.3762,
      "step": 4700
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.1914544105529785,
      "learning_rate": 2.0100000000000002e-06,
      "loss": 1.2622,
      "step": 4800
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.8515170216560364,
      "learning_rate": 1.01e-06,
      "loss": 1.3327,
      "step": 4900
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9752984046936035,
      "learning_rate": 1e-08,
      "loss": 1.2896,
      "step": 5000
    }
  ],
  "logging_steps": 100,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.464359559168e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}