{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9215686274509802,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.5924,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.4347,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.2385,
      "step": 15
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.0533,
      "step": 20
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.964,
      "step": 25
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.9148,
      "step": 30
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.8783,
      "step": 35
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.9033,
      "step": 40
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.8137,
      "step": 45
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.8156,
      "step": 50
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.8076,
      "step": 55
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.6955,
      "step": 60
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.7675,
      "step": 65
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.7195,
      "step": 70
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.6537,
      "step": 75
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.7573,
      "step": 80
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.7327,
      "step": 85
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.6761,
      "step": 90
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.6961,
      "step": 95
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.7175,
      "step": 100
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.7002,
      "step": 105
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.6312,
      "step": 110
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.6407,
      "step": 115
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.6514,
      "step": 120
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.6612,
      "step": 125
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.6577,
      "step": 130
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.6884,
      "step": 135
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 0.6752,
      "step": 140
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.7016,
      "step": 145
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.6581,
      "step": 150
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.686,
      "step": 155
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.6226,
      "step": 160
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.6379,
      "step": 165
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.6378,
      "step": 170
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 0.6072,
      "step": 175
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 0.6809,
      "step": 180
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 0.6157,
      "step": 185
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 0.6624,
      "step": 190
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 0.6259,
      "step": 195
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 0.6699,
      "step": 200
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0002,
      "loss": 0.6384,
      "step": 205
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 0.5782,
      "step": 210
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 0.5969,
      "step": 215
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0002,
      "loss": 0.6542,
      "step": 220
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 0.6709,
      "step": 225
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0002,
      "loss": 0.6428,
      "step": 230
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0002,
      "loss": 0.6348,
      "step": 235
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 0.7218,
      "step": 240
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0002,
      "loss": 0.6717,
      "step": 245
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0002,
      "loss": 0.5902,
      "step": 250
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002,
      "loss": 0.5442,
      "step": 255
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0002,
      "loss": 0.6592,
      "step": 260
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0002,
      "loss": 0.6402,
      "step": 265
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0002,
      "loss": 0.6211,
      "step": 270
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0002,
      "loss": 0.5764,
      "step": 275
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0002,
      "loss": 0.5981,
      "step": 280
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0002,
      "loss": 0.6265,
      "step": 285
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0002,
      "loss": 0.5404,
      "step": 290
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0002,
      "loss": 0.6331,
      "step": 295
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0002,
      "loss": 0.5695,
      "step": 300
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0002,
      "loss": 0.5621,
      "step": 305
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0002,
      "loss": 0.5629,
      "step": 310
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0002,
      "loss": 0.6017,
      "step": 315
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0002,
      "loss": 0.6198,
      "step": 320
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0002,
      "loss": 0.591,
      "step": 325
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0002,
      "loss": 0.5915,
      "step": 330
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0002,
      "loss": 0.5562,
      "step": 335
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0002,
      "loss": 0.599,
      "step": 340
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0002,
      "loss": 0.613,
      "step": 345
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0002,
      "loss": 0.5082,
      "step": 350
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0002,
      "loss": 0.562,
      "step": 355
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0002,
      "loss": 0.6301,
      "step": 360
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0002,
      "loss": 0.5913,
      "step": 365
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0002,
      "loss": 0.5582,
      "step": 370
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0002,
      "loss": 0.587,
      "step": 375
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0002,
      "loss": 0.5286,
      "step": 380
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0002,
      "loss": 0.5204,
      "step": 385
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0002,
      "loss": 0.5629,
      "step": 390
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0002,
      "loss": 0.4857,
      "step": 395
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.0002,
      "loss": 0.5976,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 6.75916585893888e+16,
  "trial_name": null,
  "trial_params": null
}