{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.980891719745223,
  "global_step": 351,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 4.997496987311431e-05,
      "loss": 4.067,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.989992961303738e-05,
      "loss": 4.1952,
      "step": 10
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.977502948114772e-05,
      "loss": 3.8727,
      "step": 15
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.960051957873725e-05,
      "loss": 3.894,
      "step": 20
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.9376749346206006e-05,
      "loss": 3.7174,
      "step": 25
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.910416686333906e-05,
      "loss": 3.7136,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.878331795206705e-05,
      "loss": 3.4754,
      "step": 35
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.841484508350679e-05,
      "loss": 3.6711,
      "step": 40
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.799948609147061e-05,
      "loss": 3.4796,
      "step": 45
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.753807269502041e-05,
      "loss": 3.4441,
      "step": 50
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.7031528833024976e-05,
      "loss": 3.603,
      "step": 55
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.6480868814055424e-05,
      "loss": 3.4614,
      "step": 60
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.588719528532342e-05,
      "loss": 3.4613,
      "step": 65
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.5251697024729165e-05,
      "loss": 3.55,
      "step": 70
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.457564656044056e-05,
      "loss": 3.3352,
      "step": 75
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.3860397622769756e-05,
      "loss": 3.3781,
      "step": 80
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.310738243344996e-05,
      "loss": 3.3805,
      "step": 85
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.231810883773999e-05,
      "loss": 3.2995,
      "step": 90
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.149415728509971e-05,
      "loss": 3.1648,
      "step": 95
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.063717766448194e-05,
      "loss": 3.3295,
      "step": 100
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.974888600057808e-05,
      "loss": 3.2847,
      "step": 105
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.883106101763285e-05,
      "loss": 3.25,
      "step": 110
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.7885540577708804e-05,
      "loss": 3.2399,
      "step": 115
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.69142180005327e-05,
      "loss": 3.2125,
      "step": 120
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.591903827229282e-05,
      "loss": 3.3815,
      "step": 125
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.490199415097892e-05,
      "loss": 3.2365,
      "step": 130
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.386512217606339e-05,
      "loss": 3.2755,
      "step": 135
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.281049859051394e-05,
      "loss": 3.17,
      "step": 140
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.17402351833036e-05,
      "loss": 3.1125,
      "step": 145
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.0656475060743055e-05,
      "loss": 3.3456,
      "step": 150
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.956138835510282e-05,
      "loss": 3.294,
      "step": 155
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.845716787911833e-05,
      "loss": 3.1764,
      "step": 160
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.7346024735079486e-05,
      "loss": 3.3249,
      "step": 165
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.6230183887296955e-05,
      "loss": 3.1499,
      "step": 170
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.5111879706811087e-05,
      "loss": 3.1101,
      "step": 175
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.399335149726463e-05,
      "loss": 3.266,
      "step": 180
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.2876839010898377e-05,
      "loss": 3.2329,
      "step": 185
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.1764577963648614e-05,
      "loss": 3.2465,
      "step": 190
    },
    {
      "epoch": 1.66,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 3.2541,
      "step": 195
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.956170602484582e-05,
      "loss": 3.3382,
      "step": 200
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.8475506186424074e-05,
      "loss": 3.3049,
      "step": 205
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.740237106064383e-05,
      "loss": 3.048,
      "step": 210
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.6344449504174193e-05,
      "loss": 3.2414,
      "step": 215
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.530385990987863e-05,
      "loss": 3.291,
      "step": 220
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.4282685964923642e-05,
      "loss": 3.2234,
      "step": 225
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.328297247838241e-05,
      "loss": 3.3281,
      "step": 230
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.230672128668831e-05,
      "loss": 3.0808,
      "step": 235
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.1355887245137383e-05,
      "loss": 3.0843,
      "step": 240
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.043237431346622e-05,
      "loss": 3.263,
      "step": 245
    },
    {
      "epoch": 2.12,
      "learning_rate": 9.538031743343628e-06,
      "loss": 3.0803,
      "step": 250
    },
    {
      "epoch": 2.17,
      "learning_rate": 8.67465037541038e-06,
      "loss": 3.1773,
      "step": 255
    },
    {
      "epoch": 2.21,
      "learning_rate": 7.843959053281663e-06,
      "loss": 3.2543,
      "step": 260
    },
    {
      "epoch": 2.25,
      "learning_rate": 7.047621161693152e-06,
      "loss": 3.1697,
      "step": 265
    },
    {
      "epoch": 2.29,
      "learning_rate": 6.28723129572247e-06,
      "loss": 3.2204,
      "step": 270
    },
    {
      "epoch": 2.34,
      "learning_rate": 5.564312067755856e-06,
      "loss": 3.1626,
      "step": 275
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.880311058593617e-06,
      "loss": 3.2122,
      "step": 280
    },
    {
      "epoch": 2.42,
      "learning_rate": 4.236597918799706e-06,
      "loss": 3.2038,
      "step": 285
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.6344616260994946e-06,
      "loss": 3.0183,
      "step": 290
    },
    {
      "epoch": 2.51,
      "learning_rate": 3.07510790431767e-06,
      "loss": 3.3333,
      "step": 295
    },
    {
      "epoch": 2.55,
      "learning_rate": 2.5596568090246548e-06,
      "loss": 3.1501,
      "step": 300
    },
    {
      "epoch": 2.59,
      "learning_rate": 2.0891404847259267e-06,
      "loss": 3.2576,
      "step": 305
    },
    {
      "epoch": 2.63,
      "learning_rate": 1.664501098085408e-06,
      "loss": 3.2306,
      "step": 310
    },
    {
      "epoch": 2.68,
      "learning_rate": 1.286588951321363e-06,
      "loss": 2.9963,
      "step": 315
    },
    {
      "epoch": 2.72,
      "learning_rate": 9.561607795526007e-07,
      "loss": 3.2718,
      "step": 320
    },
    {
      "epoch": 2.76,
      "learning_rate": 6.738782355044049e-07,
      "loss": 3.2774,
      "step": 325
    },
    {
      "epoch": 2.8,
      "learning_rate": 4.403065646083809e-07,
      "loss": 3.1737,
      "step": 330
    },
    {
      "epoch": 2.85,
      "learning_rate": 2.559134731492857e-07,
      "loss": 3.2095,
      "step": 335
    },
    {
      "epoch": 2.89,
      "learning_rate": 1.2106819172520434e-07,
      "loss": 3.2731,
      "step": 340
    },
    {
      "epoch": 2.93,
      "learning_rate": 3.604073589645596e-08,
      "loss": 3.0926,
      "step": 345
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.0013655036916759e-09,
      "loss": 3.0457,
      "step": 350
    },
    {
      "epoch": 2.98,
      "step": 351,
      "total_flos": 1.0467902716796928e+17,
      "train_loss": 3.3144316109496983,
      "train_runtime": 2560.536,
      "train_samples_per_second": 2.207,
      "train_steps_per_second": 0.137
    }
  ],
  "max_steps": 351,
  "num_train_epochs": 3,
  "total_flos": 1.0467902716796928e+17,
  "trial_name": null,
  "trial_params": null
}