{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 480,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03125,
      "grad_norm": 2.25,
      "learning_rate": 5.208333333333334e-06,
      "loss": 2.3536,
      "step": 5
    },
    {
      "epoch": 0.0625,
      "grad_norm": 1.546875,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 2.3694,
      "step": 10
    },
    {
      "epoch": 0.09375,
      "grad_norm": 1.7421875,
      "learning_rate": 1.5625e-05,
      "loss": 2.3358,
      "step": 15
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 2.3675,
      "step": 20
    },
    {
      "epoch": 0.15625,
      "grad_norm": 1.4375,
      "learning_rate": 2.604166666666667e-05,
      "loss": 2.339,
      "step": 25
    },
    {
      "epoch": 0.1875,
      "grad_norm": 1.5390625,
      "learning_rate": 3.125e-05,
      "loss": 2.3121,
      "step": 30
    },
    {
      "epoch": 0.21875,
      "grad_norm": 1.4609375,
      "learning_rate": 3.6458333333333336e-05,
      "loss": 2.3198,
      "step": 35
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.59375,
      "learning_rate": 4.166666666666667e-05,
      "loss": 2.3085,
      "step": 40
    },
    {
      "epoch": 0.28125,
      "grad_norm": 1.859375,
      "learning_rate": 4.6875e-05,
      "loss": 2.3422,
      "step": 45
    },
    {
      "epoch": 0.3125,
      "grad_norm": 1.640625,
      "learning_rate": 4.976851851851852e-05,
      "loss": 2.2933,
      "step": 50
    },
    {
      "epoch": 0.34375,
      "grad_norm": 1.7265625,
      "learning_rate": 4.9189814814814815e-05,
      "loss": 2.278,
      "step": 55
    },
    {
      "epoch": 0.375,
      "grad_norm": 1.8046875,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 2.2502,
      "step": 60
    },
    {
      "epoch": 0.40625,
      "grad_norm": 1.8515625,
      "learning_rate": 4.803240740740741e-05,
      "loss": 2.3312,
      "step": 65
    },
    {
      "epoch": 0.4375,
      "grad_norm": 1.7109375,
      "learning_rate": 4.745370370370371e-05,
      "loss": 2.2619,
      "step": 70
    },
    {
      "epoch": 0.46875,
      "grad_norm": 1.5546875,
      "learning_rate": 4.6875e-05,
      "loss": 2.2527,
      "step": 75
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.5234375,
      "learning_rate": 4.62962962962963e-05,
      "loss": 2.3142,
      "step": 80
    },
    {
      "epoch": 0.53125,
      "grad_norm": 1.4609375,
      "learning_rate": 4.5717592592592594e-05,
      "loss": 2.2887,
      "step": 85
    },
    {
      "epoch": 0.5625,
      "grad_norm": 1.609375,
      "learning_rate": 4.5138888888888894e-05,
      "loss": 2.2449,
      "step": 90
    },
    {
      "epoch": 0.59375,
      "grad_norm": 1.453125,
      "learning_rate": 4.456018518518519e-05,
      "loss": 2.2605,
      "step": 95
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.65625,
      "learning_rate": 4.3981481481481486e-05,
      "loss": 2.2888,
      "step": 100
    },
    {
      "epoch": 0.65625,
      "grad_norm": 1.53125,
      "learning_rate": 4.340277777777778e-05,
      "loss": 2.3326,
      "step": 105
    },
    {
      "epoch": 0.6875,
      "grad_norm": 1.46875,
      "learning_rate": 4.282407407407408e-05,
      "loss": 2.2427,
      "step": 110
    },
    {
      "epoch": 0.71875,
      "grad_norm": 1.484375,
      "learning_rate": 4.224537037037037e-05,
      "loss": 2.2691,
      "step": 115
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.3828125,
      "learning_rate": 4.166666666666667e-05,
      "loss": 2.274,
      "step": 120
    },
    {
      "epoch": 0.78125,
      "grad_norm": 1.46875,
      "learning_rate": 4.1087962962962965e-05,
      "loss": 2.2769,
      "step": 125
    },
    {
      "epoch": 0.8125,
      "grad_norm": 1.515625,
      "learning_rate": 4.0509259259259265e-05,
      "loss": 2.1991,
      "step": 130
    },
    {
      "epoch": 0.84375,
      "grad_norm": 1.4140625,
      "learning_rate": 3.993055555555556e-05,
      "loss": 2.2433,
      "step": 135
    },
    {
      "epoch": 0.875,
      "grad_norm": 1.546875,
      "learning_rate": 3.935185185185186e-05,
      "loss": 2.2614,
      "step": 140
    },
    {
      "epoch": 0.90625,
      "grad_norm": 1.46875,
      "learning_rate": 3.877314814814815e-05,
      "loss": 2.2938,
      "step": 145
    },
    {
      "epoch": 0.9375,
      "grad_norm": 1.3515625,
      "learning_rate": 3.8194444444444444e-05,
      "loss": 2.2696,
      "step": 150
    },
    {
      "epoch": 0.96875,
      "grad_norm": 1.3828125,
      "learning_rate": 3.7615740740740744e-05,
      "loss": 2.2715,
      "step": 155
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.4453125,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 2.2377,
      "step": 160
    },
    {
      "epoch": 1.03125,
      "grad_norm": 2.375,
      "learning_rate": 3.6458333333333336e-05,
      "loss": 2.0091,
      "step": 165
    },
    {
      "epoch": 1.0625,
      "grad_norm": 1.4609375,
      "learning_rate": 3.587962962962963e-05,
      "loss": 1.9842,
      "step": 170
    },
    {
      "epoch": 1.09375,
      "grad_norm": 1.453125,
      "learning_rate": 3.530092592592593e-05,
      "loss": 1.9515,
      "step": 175
    },
    {
      "epoch": 1.125,
      "grad_norm": 1.7109375,
      "learning_rate": 3.472222222222222e-05,
      "loss": 1.9648,
      "step": 180
    },
    {
      "epoch": 1.15625,
      "grad_norm": 1.4453125,
      "learning_rate": 3.414351851851852e-05,
      "loss": 1.9811,
      "step": 185
    },
    {
      "epoch": 1.1875,
      "grad_norm": 1.4375,
      "learning_rate": 3.3564814814814815e-05,
      "loss": 1.9638,
      "step": 190
    },
    {
      "epoch": 1.21875,
      "grad_norm": 1.4921875,
      "learning_rate": 3.2986111111111115e-05,
      "loss": 1.9788,
      "step": 195
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.4375,
      "learning_rate": 3.240740740740741e-05,
      "loss": 2.014,
      "step": 200
    },
    {
      "epoch": 1.28125,
      "grad_norm": 1.4140625,
      "learning_rate": 3.182870370370371e-05,
      "loss": 1.9551,
      "step": 205
    },
    {
      "epoch": 1.3125,
      "grad_norm": 1.4296875,
      "learning_rate": 3.125e-05,
      "loss": 1.995,
      "step": 210
    },
    {
      "epoch": 1.34375,
      "grad_norm": 1.4296875,
      "learning_rate": 3.06712962962963e-05,
      "loss": 1.9717,
      "step": 215
    },
    {
      "epoch": 1.375,
      "grad_norm": 1.4375,
      "learning_rate": 3.0092592592592593e-05,
      "loss": 2.0301,
      "step": 220
    },
    {
      "epoch": 1.40625,
      "grad_norm": 1.34375,
      "learning_rate": 2.951388888888889e-05,
      "loss": 1.9311,
      "step": 225
    },
    {
      "epoch": 1.4375,
      "grad_norm": 1.390625,
      "learning_rate": 2.8935185185185186e-05,
      "loss": 2.0162,
      "step": 230
    },
    {
      "epoch": 1.46875,
      "grad_norm": 1.421875,
      "learning_rate": 2.8356481481481483e-05,
      "loss": 1.9227,
      "step": 235
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.4140625,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.9816,
      "step": 240
    },
    {
      "epoch": 1.53125,
      "grad_norm": 1.421875,
      "learning_rate": 2.7199074074074076e-05,
      "loss": 1.9684,
      "step": 245
    },
    {
      "epoch": 1.5625,
      "grad_norm": 1.3828125,
      "learning_rate": 2.6620370370370372e-05,
      "loss": 1.9591,
      "step": 250
    },
    {
      "epoch": 1.59375,
      "grad_norm": 2.734375,
      "learning_rate": 2.604166666666667e-05,
      "loss": 1.997,
      "step": 255
    },
    {
      "epoch": 1.625,
      "grad_norm": 1.421875,
      "learning_rate": 2.5462962962962965e-05,
      "loss": 1.9312,
      "step": 260
    },
    {
      "epoch": 1.65625,
      "grad_norm": 1.375,
      "learning_rate": 2.488425925925926e-05,
      "loss": 1.9073,
      "step": 265
    },
    {
      "epoch": 1.6875,
      "grad_norm": 1.328125,
      "learning_rate": 2.4305555555555558e-05,
      "loss": 1.9367,
      "step": 270
    },
    {
      "epoch": 1.71875,
      "grad_norm": 1.34375,
      "learning_rate": 2.3726851851851854e-05,
      "loss": 1.9933,
      "step": 275
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.40625,
      "learning_rate": 2.314814814814815e-05,
      "loss": 1.9843,
      "step": 280
    },
    {
      "epoch": 1.78125,
      "grad_norm": 1.40625,
      "learning_rate": 2.2569444444444447e-05,
      "loss": 1.9439,
      "step": 285
    },
    {
      "epoch": 1.8125,
      "grad_norm": 1.359375,
      "learning_rate": 2.1990740740740743e-05,
      "loss": 1.9441,
      "step": 290
    },
    {
      "epoch": 1.84375,
      "grad_norm": 1.3359375,
      "learning_rate": 2.141203703703704e-05,
      "loss": 1.9521,
      "step": 295
    },
    {
      "epoch": 1.875,
      "grad_norm": 1.359375,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 1.9585,
      "step": 300
    },
    {
      "epoch": 1.90625,
      "grad_norm": 1.296875,
      "learning_rate": 2.0254629629629632e-05,
      "loss": 1.9464,
      "step": 305
    },
    {
      "epoch": 1.9375,
      "grad_norm": 1.3125,
      "learning_rate": 1.967592592592593e-05,
      "loss": 1.8949,
      "step": 310
    },
    {
      "epoch": 1.96875,
      "grad_norm": 1.390625,
      "learning_rate": 1.9097222222222222e-05,
      "loss": 1.9655,
      "step": 315
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.1875,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.9846,
      "step": 320
    },
    {
      "epoch": 2.03125,
      "grad_norm": 1.75,
      "learning_rate": 1.7939814814814815e-05,
      "loss": 1.7054,
      "step": 325
    },
    {
      "epoch": 2.0625,
      "grad_norm": 2.6875,
      "learning_rate": 1.736111111111111e-05,
      "loss": 1.7147,
      "step": 330
    },
    {
      "epoch": 2.09375,
      "grad_norm": 1.8125,
      "learning_rate": 1.6782407407407408e-05,
      "loss": 1.7225,
      "step": 335
    },
    {
      "epoch": 2.125,
      "grad_norm": 1.71875,
      "learning_rate": 1.6203703703703704e-05,
      "loss": 1.7715,
      "step": 340
    },
    {
      "epoch": 2.15625,
      "grad_norm": 1.6953125,
      "learning_rate": 1.5625e-05,
      "loss": 1.6884,
      "step": 345
    },
    {
      "epoch": 2.1875,
      "grad_norm": 1.6171875,
      "learning_rate": 1.5046296296296297e-05,
      "loss": 1.7029,
      "step": 350
    },
    {
      "epoch": 2.21875,
      "grad_norm": 1.640625,
      "learning_rate": 1.4467592592592593e-05,
      "loss": 1.6946,
      "step": 355
    },
    {
      "epoch": 2.25,
      "grad_norm": 1.765625,
      "learning_rate": 1.388888888888889e-05,
      "loss": 1.7329,
      "step": 360
    },
    {
      "epoch": 2.28125,
      "grad_norm": 1.546875,
      "learning_rate": 1.3310185185185186e-05,
      "loss": 1.7032,
      "step": 365
    },
    {
      "epoch": 2.3125,
      "grad_norm": 1.6953125,
      "learning_rate": 1.2731481481481482e-05,
      "loss": 1.7113,
      "step": 370
    },
    {
      "epoch": 2.34375,
      "grad_norm": 1.5703125,
      "learning_rate": 1.2152777777777779e-05,
      "loss": 1.6568,
      "step": 375
    },
    {
      "epoch": 2.375,
      "grad_norm": 1.5703125,
      "learning_rate": 1.1574074074074075e-05,
      "loss": 1.7525,
      "step": 380
    },
    {
      "epoch": 2.40625,
      "grad_norm": 1.53125,
      "learning_rate": 1.0995370370370372e-05,
      "loss": 1.6914,
      "step": 385
    },
    {
      "epoch": 2.4375,
      "grad_norm": 1.5078125,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 1.6791,
      "step": 390
    },
    {
      "epoch": 2.46875,
      "grad_norm": 1.53125,
      "learning_rate": 9.837962962962964e-06,
      "loss": 1.7092,
      "step": 395
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.6015625,
      "learning_rate": 9.259259259259259e-06,
      "loss": 1.6663,
      "step": 400
    },
    {
      "epoch": 2.53125,
      "grad_norm": 1.5625,
      "learning_rate": 8.680555555555556e-06,
      "loss": 1.6959,
      "step": 405
    },
    {
      "epoch": 2.5625,
      "grad_norm": 1.53125,
      "learning_rate": 8.101851851851852e-06,
      "loss": 1.6847,
      "step": 410
    },
    {
      "epoch": 2.59375,
      "grad_norm": 1.5234375,
      "learning_rate": 7.523148148148148e-06,
      "loss": 1.6527,
      "step": 415
    },
    {
      "epoch": 2.625,
      "grad_norm": 1.546875,
      "learning_rate": 6.944444444444445e-06,
      "loss": 1.6578,
      "step": 420
    },
    {
      "epoch": 2.65625,
      "grad_norm": 1.4765625,
      "learning_rate": 6.365740740740741e-06,
      "loss": 1.7115,
      "step": 425
    },
    {
      "epoch": 2.6875,
      "grad_norm": 1.484375,
      "learning_rate": 5.787037037037038e-06,
      "loss": 1.7117,
      "step": 430
    },
    {
      "epoch": 2.71875,
      "grad_norm": 1.5078125,
      "learning_rate": 5.208333333333334e-06,
      "loss": 1.7297,
      "step": 435
    },
    {
      "epoch": 2.75,
      "grad_norm": 1.515625,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 1.7166,
      "step": 440
    },
    {
      "epoch": 2.78125,
      "grad_norm": 1.5078125,
      "learning_rate": 4.050925925925926e-06,
      "loss": 1.6857,
      "step": 445
    },
    {
      "epoch": 2.8125,
      "grad_norm": 1.5,
      "learning_rate": 3.4722222222222224e-06,
      "loss": 1.6657,
      "step": 450
    },
    {
      "epoch": 2.84375,
      "grad_norm": 1.5,
      "learning_rate": 2.893518518518519e-06,
      "loss": 1.708,
      "step": 455
    },
    {
      "epoch": 2.875,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3148148148148148e-06,
      "loss": 1.7472,
      "step": 460
    },
    {
      "epoch": 2.90625,
      "grad_norm": 1.5625,
      "learning_rate": 1.7361111111111112e-06,
      "loss": 1.6997,
      "step": 465
    },
    {
      "epoch": 2.9375,
      "grad_norm": 1.5546875,
      "learning_rate": 1.1574074074074074e-06,
      "loss": 1.7339,
      "step": 470
    },
    {
      "epoch": 2.96875,
      "grad_norm": 1.5078125,
      "learning_rate": 5.787037037037037e-07,
      "loss": 1.7217,
      "step": 475
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.6328125,
      "learning_rate": 0.0,
      "loss": 1.6548,
      "step": 480
    },
    {
      "epoch": 3.0,
      "step": 480,
      "total_flos": 2.1887812691715686e+18,
      "train_loss": 1.9862731973330179,
      "train_runtime": 8600.0121,
      "train_samples_per_second": 1.785,
      "train_steps_per_second": 0.056
    }
  ],
  "logging_steps": 5,
  "max_steps": 480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1887812691715686e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}