{
  "best_metric": 1.3606982231140137,
  "best_model_checkpoint": "output/slava-marlow/checkpoint-333",
  "epoch": 3.0,
  "global_step": 333,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.00013669982876312649,
      "loss": 2.5046,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013520660867542716,
      "loss": 2.1374,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00013274211424821946,
      "loss": 2.2201,
      "step": 15
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00012934228335981018,
      "loss": 1.9548,
      "step": 20
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00012505669320030482,
      "loss": 2.0656,
      "step": 25
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00011994783732453754,
      "loss": 1.9398,
      "step": 30
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00011409021435531856,
      "loss": 2.1725,
      "step": 35
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010756924162575728,
      "loss": 1.8872,
      "step": 40
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00010048000960220252,
      "loss": 1.9796,
      "step": 45
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.292589525111794e-05,
      "loss": 1.8577,
      "step": 50
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.501705457012647e-05,
      "loss": 1.7766,
      "step": 55
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.686881626551515e-05,
      "loss": 1.8008,
      "step": 60
    },
    {
      "epoch": 0.5,
      "learning_rate": 6.86e-05,
      "loss": 1.8354,
      "step": 65
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.033118373448485e-05,
      "loss": 1.9892,
      "step": 70
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.218294542987356e-05,
      "loss": 1.8204,
      "step": 75
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.427410474888205e-05,
      "loss": 1.8009,
      "step": 80
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.671999039779748e-05,
      "loss": 1.7768,
      "step": 85
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.963075837424272e-05,
      "loss": 1.7438,
      "step": 90
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.3109785644681465e-05,
      "loss": 1.7175,
      "step": 95
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.725216267546246e-05,
      "loss": 1.9227,
      "step": 100
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2143306799695174e-05,
      "loss": 1.9182,
      "step": 105
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.857716640189809e-06,
      "loss": 1.8767,
      "step": 110
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.45788575178055e-06,
      "loss": 1.8175,
      "step": 115
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.993391324572832e-06,
      "loss": 1.727,
      "step": 120
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.001712368734975e-07,
      "loss": 1.6829,
      "step": 125
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.8023,
      "step": 130
    },
    {
      "epoch": 1.04,
      "learning_rate": 5.001712368734975e-07,
      "loss": 1.7351,
      "step": 135
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.9933913245728244e-06,
      "loss": 1.7454,
      "step": 140
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.457885751780542e-06,
      "loss": 1.9051,
      "step": 145
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.857716640189785e-06,
      "loss": 1.818,
      "step": 150
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.2143306799695167e-05,
      "loss": 1.707,
      "step": 155
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.7252162675462473e-05,
      "loss": 1.7507,
      "step": 160
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.3109785644681427e-05,
      "loss": 1.8168,
      "step": 165
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.9630758374242703e-05,
      "loss": 1.7313,
      "step": 170
    },
    {
      "epoch": 1.35,
      "learning_rate": 3.671999039779749e-05,
      "loss": 1.6952,
      "step": 175
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.427410474888204e-05,
      "loss": 1.7249,
      "step": 180
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.218294542987354e-05,
      "loss": 1.6855,
      "step": 185
    },
    {
      "epoch": 1.46,
      "learning_rate": 6.03311837344848e-05,
      "loss": 1.5632,
      "step": 190
    },
    {
      "epoch": 1.5,
      "learning_rate": 6.859999999999999e-05,
      "loss": 1.7108,
      "step": 195
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.686881626551516e-05,
      "loss": 1.816,
      "step": 200
    },
    {
      "epoch": 1.58,
      "learning_rate": 8.501705457012643e-05,
      "loss": 1.8067,
      "step": 205
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.292589525111794e-05,
      "loss": 1.7471,
      "step": 210
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00010048000960220248,
      "loss": 1.8035,
      "step": 215
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00010756924162575728,
      "loss": 1.7207,
      "step": 220
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00011409021435531856,
      "loss": 1.7529,
      "step": 225
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001199478373245375,
      "loss": 1.7625,
      "step": 230
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00012505669320030482,
      "loss": 1.7044,
      "step": 235
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001293422833598102,
      "loss": 1.6402,
      "step": 240
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00013274211424821946,
      "loss": 1.7453,
      "step": 245
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00013520660867542716,
      "loss": 1.7462,
      "step": 250
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013669982876312649,
      "loss": 1.7852,
      "step": 255
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001372,
      "loss": 1.7608,
      "step": 260
    },
    {
      "epoch": 2.43,
      "learning_rate": 8.331367795957333e-05,
      "loss": 1.7155,
      "step": 265
    },
    {
      "epoch": 2.48,
      "learning_rate": 7.353868846414889e-05,
      "loss": 1.6697,
      "step": 270
    },
    {
      "epoch": 2.52,
      "learning_rate": 6.366131153585115e-05,
      "loss": 1.5567,
      "step": 275
    },
    {
      "epoch": 2.57,
      "learning_rate": 5.3886322040426775e-05,
      "loss": 1.5568,
      "step": 280
    },
    {
      "epoch": 2.61,
      "learning_rate": 4.441637217755689e-05,
      "loss": 1.678,
      "step": 285
    },
    {
      "epoch": 2.66,
      "learning_rate": 3.544779015521354e-05,
      "loss": 1.5895,
      "step": 290
    },
    {
      "epoch": 2.71,
      "learning_rate": 2.716650997114681e-05,
      "loss": 1.6833,
      "step": 295
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.9744216684073583e-05,
      "loss": 1.5874,
      "step": 300
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.333478708966784e-05,
      "loss": 1.5961,
      "step": 305
    },
    {
      "epoch": 2.84,
      "learning_rate": 8.071099592209943e-06,
      "loss": 1.6268,
      "step": 310
    },
    {
      "epoch": 2.89,
      "learning_rate": 4.062279408693099e-06,
      "loss": 1.5704,
      "step": 315
    },
    {
      "epoch": 2.94,
      "learning_rate": 1.3914362170045804e-06,
      "loss": 1.5144,
      "step": 320
    },
    {
      "epoch": 2.98,
      "learning_rate": 1.139411505919223e-07,
      "loss": 1.753,
      "step": 325
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.5765409469604492,
      "eval_runtime": 8.0085,
      "eval_samples_per_second": 21.227,
      "eval_steps_per_second": 2.747,
      "step": 327
    },
    {
      "epoch": 2.97,
      "learning_rate": 2.4713228598268823e-07,
      "loss": 1.5213,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3606982231140137,
      "eval_runtime": 7.4703,
      "eval_samples_per_second": 20.883,
      "eval_steps_per_second": 2.677,
      "step": 333
    }
  ],
  "max_steps": 444,
  "num_train_epochs": 4,
  "total_flos": 346081296384000.0,
  "trial_name": null,
  "trial_params": null
}