{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 8.8125,
      "learning_rate": 1.9931428571428572e-05,
      "loss": 2.0244,
      "step": 10
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 12.4375,
      "learning_rate": 1.9855238095238097e-05,
      "loss": 2.0268,
      "step": 20
    },
    {
      "epoch": 0.03428571428571429,
      "grad_norm": 5.6875,
      "learning_rate": 1.977904761904762e-05,
      "loss": 2.0396,
      "step": 30
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 6.03125,
      "learning_rate": 1.9702857142857144e-05,
      "loss": 1.8937,
      "step": 40
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 10.0,
      "learning_rate": 1.9626666666666666e-05,
      "loss": 1.8841,
      "step": 50
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 8.625,
      "learning_rate": 1.955047619047619e-05,
      "loss": 1.8955,
      "step": 60
    },
    {
      "epoch": 0.08,
      "grad_norm": 8.1875,
      "learning_rate": 1.9474285714285717e-05,
      "loss": 1.8829,
      "step": 70
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 5.5625,
      "learning_rate": 1.9398095238095242e-05,
      "loss": 1.9389,
      "step": 80
    },
    {
      "epoch": 0.10285714285714286,
      "grad_norm": 5.625,
      "learning_rate": 1.9321904761904764e-05,
      "loss": 1.9335,
      "step": 90
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 11.4375,
      "learning_rate": 1.924571428571429e-05,
      "loss": 1.8842,
      "step": 100
    },
    {
      "epoch": 0.12571428571428572,
      "grad_norm": 6.03125,
      "learning_rate": 1.916952380952381e-05,
      "loss": 1.9089,
      "step": 110
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 9.625,
      "learning_rate": 1.9093333333333336e-05,
      "loss": 1.7602,
      "step": 120
    },
    {
      "epoch": 0.14857142857142858,
      "grad_norm": 9.4375,
      "learning_rate": 1.9017142857142858e-05,
      "loss": 1.721,
      "step": 130
    },
    {
      "epoch": 0.16,
      "grad_norm": 10.375,
      "learning_rate": 1.8940952380952383e-05,
      "loss": 1.8059,
      "step": 140
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 9.0625,
      "learning_rate": 1.8864761904761905e-05,
      "loss": 1.7363,
      "step": 150
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 11.0625,
      "learning_rate": 1.878857142857143e-05,
      "loss": 1.7634,
      "step": 160
    },
    {
      "epoch": 0.19428571428571428,
      "grad_norm": 5.46875,
      "learning_rate": 1.871238095238095e-05,
      "loss": 1.7298,
      "step": 170
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 5.375,
      "learning_rate": 1.8636190476190477e-05,
      "loss": 1.7439,
      "step": 180
    },
    {
      "epoch": 0.21714285714285714,
      "grad_norm": 8.125,
      "learning_rate": 1.8560000000000002e-05,
      "loss": 1.8381,
      "step": 190
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 7.65625,
      "learning_rate": 1.8483809523809527e-05,
      "loss": 1.6778,
      "step": 200
    },
    {
      "epoch": 0.24,
      "grad_norm": 9.25,
      "learning_rate": 1.840761904761905e-05,
      "loss": 1.6378,
      "step": 210
    },
    {
      "epoch": 0.25142857142857145,
      "grad_norm": 8.25,
      "learning_rate": 1.8331428571428574e-05,
      "loss": 1.6447,
      "step": 220
    },
    {
      "epoch": 0.26285714285714284,
      "grad_norm": 10.9375,
      "learning_rate": 1.8255238095238096e-05,
      "loss": 1.7685,
      "step": 230
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 11.0,
      "learning_rate": 1.817904761904762e-05,
      "loss": 1.6609,
      "step": 240
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 4.75,
      "learning_rate": 1.8102857142857143e-05,
      "loss": 1.6822,
      "step": 250
    },
    {
      "epoch": 0.29714285714285715,
      "grad_norm": 7.28125,
      "learning_rate": 1.8026666666666668e-05,
      "loss": 1.6153,
      "step": 260
    },
    {
      "epoch": 0.30857142857142855,
      "grad_norm": 7.9375,
      "learning_rate": 1.7950476190476193e-05,
      "loss": 1.7153,
      "step": 270
    },
    {
      "epoch": 0.32,
      "grad_norm": 9.0625,
      "learning_rate": 1.7874285714285715e-05,
      "loss": 1.7104,
      "step": 280
    },
    {
      "epoch": 0.3314285714285714,
      "grad_norm": 7.90625,
      "learning_rate": 1.779809523809524e-05,
      "loss": 1.6752,
      "step": 290
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 7.03125,
      "learning_rate": 1.7721904761904762e-05,
      "loss": 1.6701,
      "step": 300
    },
    {
      "epoch": 0.35428571428571426,
      "grad_norm": 7.5625,
      "learning_rate": 1.7645714285714287e-05,
      "loss": 1.6393,
      "step": 310
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 7.65625,
      "learning_rate": 1.7569523809523812e-05,
      "loss": 1.5169,
      "step": 320
    },
    {
      "epoch": 0.37714285714285717,
      "grad_norm": 4.6875,
      "learning_rate": 1.7493333333333334e-05,
      "loss": 1.5707,
      "step": 330
    },
    {
      "epoch": 0.38857142857142857,
      "grad_norm": 4.78125,
      "learning_rate": 1.741714285714286e-05,
      "loss": 1.5962,
      "step": 340
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.59375,
      "learning_rate": 1.734095238095238e-05,
      "loss": 1.7404,
      "step": 350
    },
    {
      "epoch": 0.4114285714285714,
      "grad_norm": 5.21875,
      "learning_rate": 1.7264761904761906e-05,
      "loss": 1.6232,
      "step": 360
    },
    {
      "epoch": 0.4228571428571429,
      "grad_norm": 4.46875,
      "learning_rate": 1.718857142857143e-05,
      "loss": 1.7321,
      "step": 370
    },
    {
      "epoch": 0.4342857142857143,
      "grad_norm": 4.40625,
      "learning_rate": 1.7112380952380953e-05,
      "loss": 1.5638,
      "step": 380
    },
    {
      "epoch": 0.44571428571428573,
      "grad_norm": 4.625,
      "learning_rate": 1.703619047619048e-05,
      "loss": 1.6591,
      "step": 390
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 9.0625,
      "learning_rate": 1.696e-05,
      "loss": 1.5868,
      "step": 400
    },
    {
      "epoch": 0.4685714285714286,
      "grad_norm": 9.125,
      "learning_rate": 1.6883809523809525e-05,
      "loss": 1.6323,
      "step": 410
    },
    {
      "epoch": 0.48,
      "grad_norm": 7.5,
      "learning_rate": 1.6807619047619047e-05,
      "loss": 1.6079,
      "step": 420
    },
    {
      "epoch": 0.49142857142857144,
      "grad_norm": 9.9375,
      "learning_rate": 1.6731428571428572e-05,
      "loss": 1.6279,
      "step": 430
    },
    {
      "epoch": 0.5028571428571429,
      "grad_norm": 4.90625,
      "learning_rate": 1.6655238095238098e-05,
      "loss": 1.6033,
      "step": 440
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 9.375,
      "learning_rate": 1.6579047619047623e-05,
      "loss": 1.5813,
      "step": 450
    },
    {
      "epoch": 0.5257142857142857,
      "grad_norm": 12.625,
      "learning_rate": 1.6502857142857145e-05,
      "loss": 1.7047,
      "step": 460
    },
    {
      "epoch": 0.5371428571428571,
      "grad_norm": 7.75,
      "learning_rate": 1.642666666666667e-05,
      "loss": 1.6662,
      "step": 470
    },
    {
      "epoch": 0.5485714285714286,
      "grad_norm": 7.03125,
      "learning_rate": 1.635047619047619e-05,
      "loss": 1.618,
      "step": 480
    },
    {
      "epoch": 0.56,
      "grad_norm": 5.1875,
      "learning_rate": 1.6274285714285717e-05,
      "loss": 1.5469,
      "step": 490
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 11.0625,
      "learning_rate": 1.619809523809524e-05,
      "loss": 1.5454,
      "step": 500
    },
    {
      "epoch": 0.5828571428571429,
      "grad_norm": 7.84375,
      "learning_rate": 1.6121904761904764e-05,
      "loss": 1.4719,
      "step": 510
    },
    {
      "epoch": 0.5942857142857143,
      "grad_norm": 4.53125,
      "learning_rate": 1.6045714285714286e-05,
      "loss": 1.4144,
      "step": 520
    },
    {
      "epoch": 0.6057142857142858,
      "grad_norm": 8.125,
      "learning_rate": 1.596952380952381e-05,
      "loss": 1.5868,
      "step": 530
    },
    {
      "epoch": 0.6171428571428571,
      "grad_norm": 6.9375,
      "learning_rate": 1.5893333333333333e-05,
      "loss": 1.5727,
      "step": 540
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 9.3125,
      "learning_rate": 1.5817142857142858e-05,
      "loss": 1.6083,
      "step": 550
    },
    {
      "epoch": 0.64,
      "grad_norm": 11.6875,
      "learning_rate": 1.5740952380952383e-05,
      "loss": 1.6169,
      "step": 560
    },
    {
      "epoch": 0.6514285714285715,
      "grad_norm": 7.84375,
      "learning_rate": 1.5664761904761908e-05,
      "loss": 1.6161,
      "step": 570
    },
    {
      "epoch": 0.6628571428571428,
      "grad_norm": 7.5,
      "learning_rate": 1.558857142857143e-05,
      "loss": 1.5572,
      "step": 580
    },
    {
      "epoch": 0.6742857142857143,
      "grad_norm": 11.375,
      "learning_rate": 1.5512380952380955e-05,
      "loss": 1.4882,
      "step": 590
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 7.59375,
      "learning_rate": 1.5436190476190477e-05,
      "loss": 1.6175,
      "step": 600
    },
    {
      "epoch": 0.6971428571428572,
      "grad_norm": 4.59375,
      "learning_rate": 1.5360000000000002e-05,
      "loss": 1.5326,
      "step": 610
    },
    {
      "epoch": 0.7085714285714285,
      "grad_norm": 4.3125,
      "learning_rate": 1.5283809523809524e-05,
      "loss": 1.5323,
      "step": 620
    },
    {
      "epoch": 0.72,
      "grad_norm": 4.53125,
      "learning_rate": 1.5207619047619049e-05,
      "loss": 1.5665,
      "step": 630
    },
    {
      "epoch": 0.7314285714285714,
      "grad_norm": 11.25,
      "learning_rate": 1.5131428571428572e-05,
      "loss": 1.4393,
      "step": 640
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 7.03125,
      "learning_rate": 1.5055238095238096e-05,
      "loss": 1.528,
      "step": 650
    },
    {
      "epoch": 0.7542857142857143,
      "grad_norm": 7.40625,
      "learning_rate": 1.497904761904762e-05,
      "loss": 1.5457,
      "step": 660
    },
    {
      "epoch": 0.7657142857142857,
      "grad_norm": 9.4375,
      "learning_rate": 1.4902857142857143e-05,
      "loss": 1.5291,
      "step": 670
    },
    {
      "epoch": 0.7771428571428571,
      "grad_norm": 9.375,
      "learning_rate": 1.4826666666666666e-05,
      "loss": 1.5229,
      "step": 680
    },
    {
      "epoch": 0.7885714285714286,
      "grad_norm": 4.46875,
      "learning_rate": 1.475047619047619e-05,
      "loss": 1.4647,
      "step": 690
    },
    {
      "epoch": 0.8,
      "grad_norm": 4.03125,
      "learning_rate": 1.4674285714285717e-05,
      "loss": 1.5565,
      "step": 700
    },
    {
      "epoch": 0.8114285714285714,
      "grad_norm": 7.375,
      "learning_rate": 1.459809523809524e-05,
      "loss": 1.5298,
      "step": 710
    },
    {
      "epoch": 0.8228571428571428,
      "grad_norm": 9.625,
      "learning_rate": 1.4521904761904764e-05,
      "loss": 1.5642,
      "step": 720
    },
    {
      "epoch": 0.8342857142857143,
      "grad_norm": 7.4375,
      "learning_rate": 1.4445714285714287e-05,
      "loss": 1.5435,
      "step": 730
    },
    {
      "epoch": 0.8457142857142858,
      "grad_norm": 12.375,
      "learning_rate": 1.436952380952381e-05,
      "loss": 1.4951,
      "step": 740
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 7.9375,
      "learning_rate": 1.4293333333333334e-05,
      "loss": 1.5446,
      "step": 750
    },
    {
      "epoch": 0.8685714285714285,
      "grad_norm": 7.21875,
      "learning_rate": 1.4217142857142858e-05,
      "loss": 1.5318,
      "step": 760
    },
    {
      "epoch": 0.88,
      "grad_norm": 7.1875,
      "learning_rate": 1.4140952380952381e-05,
      "loss": 1.5279,
      "step": 770
    },
    {
      "epoch": 0.8914285714285715,
      "grad_norm": 7.09375,
      "learning_rate": 1.4064761904761905e-05,
      "loss": 1.4712,
      "step": 780
    },
    {
      "epoch": 0.9028571428571428,
      "grad_norm": 7.46875,
      "learning_rate": 1.398857142857143e-05,
      "loss": 1.566,
      "step": 790
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 6.40625,
      "learning_rate": 1.3912380952380953e-05,
      "loss": 1.4607,
      "step": 800
    },
    {
      "epoch": 0.9257142857142857,
      "grad_norm": 7.6875,
      "learning_rate": 1.3836190476190477e-05,
      "loss": 1.4935,
      "step": 810
    },
    {
      "epoch": 0.9371428571428572,
      "grad_norm": 4.84375,
      "learning_rate": 1.376e-05,
      "loss": 1.4306,
      "step": 820
    },
    {
      "epoch": 0.9485714285714286,
      "grad_norm": 9.75,
      "learning_rate": 1.3683809523809526e-05,
      "loss": 1.4454,
      "step": 830
    },
    {
      "epoch": 0.96,
      "grad_norm": 7.5,
      "learning_rate": 1.3607619047619049e-05,
      "loss": 1.4285,
      "step": 840
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 4.25,
      "learning_rate": 1.3531428571428573e-05,
      "loss": 1.5716,
      "step": 850
    },
    {
      "epoch": 0.9828571428571429,
      "grad_norm": 10.8125,
      "learning_rate": 1.3455238095238096e-05,
      "loss": 1.5742,
      "step": 860
    },
    {
      "epoch": 0.9942857142857143,
      "grad_norm": 4.375,
      "learning_rate": 1.3379047619047621e-05,
      "loss": 1.5958,
      "step": 870
    }
  ],
  "logging_steps": 10,
  "max_steps": 2625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.391407485288448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}