{
  "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": 1.5959,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.4327,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.2348,
      "step": 15
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.0496,
      "step": 20
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.9628,
      "step": 25
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.9141,
      "step": 30
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.8776,
      "step": 35
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.9028,
      "step": 40
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.8117,
      "step": 45
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.8124,
      "step": 50
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.8083,
      "step": 55
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.695,
      "step": 60
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.7658,
      "step": 65
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.7177,
      "step": 70
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.6523,
      "step": 75
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.7557,
      "step": 80
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.7329,
      "step": 85
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.6756,
      "step": 90
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.6953,
      "step": 95
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.717,
      "step": 100
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.7002,
      "step": 105
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.6305,
      "step": 110
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.6396,
      "step": 115
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.6512,
      "step": 120
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.6607,
      "step": 125
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.657,
      "step": 130
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.6881,
      "step": 135
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 0.6747,
      "step": 140
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.7008,
      "step": 145
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.6573,
      "step": 150
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.685,
      "step": 155
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.6225,
      "step": 160
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.6361,
      "step": 165
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.6369,
      "step": 170
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 0.6068,
      "step": 175
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 0.6794,
      "step": 180
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 0.6158,
      "step": 185
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 0.6618,
      "step": 190
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 0.6256,
      "step": 195
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 0.6689,
      "step": 200
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0002,
      "loss": 0.637,
      "step": 205
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 0.5772,
      "step": 210
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 0.5954,
      "step": 215
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0002,
      "loss": 0.6525,
      "step": 220
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 0.6702,
      "step": 225
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0002,
      "loss": 0.6412,
      "step": 230
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0002,
      "loss": 0.6331,
      "step": 235
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 0.7214,
      "step": 240
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0002,
      "loss": 0.6701,
      "step": 245
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0002,
      "loss": 0.5892,
      "step": 250
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002,
      "loss": 0.5427,
      "step": 255
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0002,
      "loss": 0.6579,
      "step": 260
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0002,
      "loss": 0.639,
      "step": 265
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0002,
      "loss": 0.6198,
      "step": 270
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0002,
      "loss": 0.5747,
      "step": 275
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0002,
      "loss": 0.5971,
      "step": 280
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0002,
      "loss": 0.6257,
      "step": 285
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0002,
      "loss": 0.5401,
      "step": 290
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0002,
      "loss": 0.6317,
      "step": 295
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0002,
      "loss": 0.568,
      "step": 300
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0002,
      "loss": 0.5611,
      "step": 305
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0002,
      "loss": 0.5615,
      "step": 310
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0002,
      "loss": 0.6005,
      "step": 315
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0002,
      "loss": 0.6186,
      "step": 320
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0002,
      "loss": 0.5887,
      "step": 325
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0002,
      "loss": 0.5908,
      "step": 330
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0002,
      "loss": 0.5549,
      "step": 335
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0002,
      "loss": 0.5982,
      "step": 340
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0002,
      "loss": 0.6121,
      "step": 345
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0002,
      "loss": 0.5061,
      "step": 350
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0002,
      "loss": 0.5607,
      "step": 355
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0002,
      "loss": 0.6293,
      "step": 360
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0002,
      "loss": 0.5907,
      "step": 365
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0002,
      "loss": 0.5571,
      "step": 370
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0002,
      "loss": 0.5865,
      "step": 375
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0002,
      "loss": 0.5276,
      "step": 380
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0002,
      "loss": 0.5197,
      "step": 385
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0002,
      "loss": 0.5613,
      "step": 390
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0002,
      "loss": 0.4841,
      "step": 395
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.0002,
      "loss": 0.5957,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 6.52826841710592e+16,
  "trial_name": null,
  "trial_params": null
}