{
  "best_metric": 1.7180215120315552,
  "best_model_checkpoint": "output/linkin-park/checkpoint-276",
  "epoch": 4.0,
  "global_step": 276,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0001354300570714007,
      "loss": 2.895,
      "step": 5
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00013021156058794955,
      "loss": 2.9711,
      "step": 10
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001218137945423232,
      "loss": 3.0184,
      "step": 15
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00011067009906946294,
      "loss": 2.635,
      "step": 20
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.735550930058317e-05,
      "loss": 2.6937,
      "step": 25
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.255708249541069e-05,
      "loss": 2.9303,
      "step": 30
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.703844462707114e-05,
      "loss": 2.5872,
      "step": 35
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.160038588088708e-05,
      "loss": 2.5982,
      "step": 40
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.703953841164296e-05,
      "loss": 2.5227,
      "step": 45
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.410726866285494e-05,
      "loss": 2.6876,
      "step": 50
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3470905479788493e-05,
      "loss": 2.8587,
      "step": 55
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.679304716725937e-06,
      "loss": 2.566,
      "step": 60
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.1345272679252971e-06,
      "loss": 2.6052,
      "step": 65
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.4942777156829834,
      "eval_runtime": 4.673,
      "eval_samples_per_second": 22.041,
      "eval_steps_per_second": 2.782,
      "step": 69
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.9438,
      "step": 70
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.463841438293457,
      "eval_runtime": 4.6348,
      "eval_samples_per_second": 20.929,
      "eval_steps_per_second": 2.805,
      "step": 70
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.7199452243268996e-06,
      "loss": 2.4952,
      "step": 75
    },
    {
      "epoch": 1.14,
      "learning_rate": 6.793535661894047e-06,
      "loss": 2.5481,
      "step": 80
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.4966360302693133e-05,
      "loss": 2.6492,
      "step": 85
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.582859959249087e-05,
      "loss": 2.3078,
      "step": 90
    },
    {
      "epoch": 1.36,
      "learning_rate": 3.88355754965355e-05,
      "loss": 2.6034,
      "step": 95
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.333506393059682e-05,
      "loss": 2.4777,
      "step": 100
    },
    {
      "epoch": 1.5,
      "learning_rate": 6.859999999999999e-05,
      "loss": 2.2842,
      "step": 105
    },
    {
      "epoch": 1.57,
      "learning_rate": 8.386493606940316e-05,
      "loss": 2.577,
      "step": 110
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.836442450346448e-05,
      "loss": 2.3194,
      "step": 115
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00011137140040750911,
      "loss": 2.3364,
      "step": 120
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00012223363969730684,
      "loss": 2.3984,
      "step": 125
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00013040646433810595,
      "loss": 2.2814,
      "step": 130
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001354800547756731,
      "loss": 2.2059,
      "step": 135
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001372,
      "loss": 1.9945,
      "step": 140
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.248004913330078,
      "eval_runtime": 4.6064,
      "eval_samples_per_second": 21.058,
      "eval_steps_per_second": 2.822,
      "step": 140
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001354800547756731,
      "loss": 2.1018,
      "step": 145
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00013040646433810595,
      "loss": 1.8963,
      "step": 150
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00012223363969730686,
      "loss": 2.1895,
      "step": 155
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011137140040750914,
      "loss": 2.0564,
      "step": 160
    },
    {
      "epoch": 2.36,
      "learning_rate": 9.836442450346452e-05,
      "loss": 2.1397,
      "step": 165
    },
    {
      "epoch": 2.43,
      "learning_rate": 8.386493606940326e-05,
      "loss": 2.3483,
      "step": 170
    },
    {
      "epoch": 2.5,
      "learning_rate": 6.860000000000001e-05,
      "loss": 1.9349,
      "step": 175
    },
    {
      "epoch": 2.57,
      "learning_rate": 5.333506393059685e-05,
      "loss": 1.8439,
      "step": 180
    },
    {
      "epoch": 2.64,
      "learning_rate": 3.8835575496535535e-05,
      "loss": 1.9104,
      "step": 185
    },
    {
      "epoch": 2.71,
      "learning_rate": 2.58285995924909e-05,
      "loss": 1.7206,
      "step": 190
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.496636030269317e-05,
      "loss": 2.2577,
      "step": 195
    },
    {
      "epoch": 2.86,
      "learning_rate": 6.793535661894062e-06,
      "loss": 1.8714,
      "step": 200
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.7199452243269073e-06,
      "loss": 2.2299,
      "step": 205
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 1.8604,
      "step": 210
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.0318267345428467,
      "eval_runtime": 4.5539,
      "eval_samples_per_second": 21.081,
      "eval_steps_per_second": 2.635,
      "step": 210
    },
    {
      "epoch": 3.12,
      "learning_rate": 4.500582770777967e-06,
      "loss": 1.8704,
      "step": 215
    },
    {
      "epoch": 3.19,
      "learning_rate": 1.166986896886688e-05,
      "loss": 1.6973,
      "step": 220
    },
    {
      "epoch": 3.26,
      "learning_rate": 2.177685437520025e-05,
      "loss": 1.9541,
      "step": 225
    },
    {
      "epoch": 3.33,
      "learning_rate": 3.4300000000000014e-05,
      "loss": 1.7097,
      "step": 230
    },
    {
      "epoch": 3.41,
      "learning_rate": 4.859308855339902e-05,
      "loss": 1.8994,
      "step": 235
    },
    {
      "epoch": 3.48,
      "learning_rate": 6.391857044318346e-05,
      "loss": 1.772,
      "step": 240
    },
    {
      "epoch": 3.55,
      "learning_rate": 7.948562268689874e-05,
      "loss": 1.7301,
      "step": 245
    },
    {
      "epoch": 3.62,
      "learning_rate": 9.449095682862937e-05,
      "loss": 2.1161,
      "step": 250
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.0001081602700970798,
      "loss": 1.876,
      "step": 255
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.00011978820084915117,
      "loss": 1.9729,
      "step": 260
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.00012877472652481797,
      "loss": 1.7309,
      "step": 265
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.00013465612591205902,
      "loss": 2.0053,
      "step": 270
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.00013712890801216552,
      "loss": 1.7362,
      "step": 275
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.7180215120315552,
      "eval_runtime": 4.7996,
      "eval_samples_per_second": 20.835,
      "eval_steps_per_second": 2.709,
      "step": 276
    }
  ],
  "max_steps": 276,
  "num_train_epochs": 4,
  "total_flos": 286245421056000.0,
  "trial_name": null,
  "trial_params": null
}