{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.53257790368272,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 1.9974521146102535e-05,
      "loss": 1.0269,
      "step": 10
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.989821441880933e-05,
      "loss": 0.9778,
      "step": 20
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9771468659711595e-05,
      "loss": 0.9404,
      "step": 30
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.9594929736144978e-05,
      "loss": 0.8988,
      "step": 40
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.936949724999762e-05,
      "loss": 0.8994,
      "step": 50
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.9096319953545186e-05,
      "loss": 0.8785,
      "step": 60
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.8776789895672557e-05,
      "loss": 0.8423,
      "step": 70
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.8412535328311813e-05,
      "loss": 0.8139,
      "step": 80
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.8005412409243604e-05,
      "loss": 0.8333,
      "step": 90
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.7557495743542586e-05,
      "loss": 0.8056,
      "step": 100
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.8051,
      "step": 110
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.6548607339452853e-05,
      "loss": 0.7923,
      "step": 120
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.599277666511347e-05,
      "loss": 0.8327,
      "step": 130
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.5406408174555978e-05,
      "loss": 0.7954,
      "step": 140
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.479248986720057e-05,
      "loss": 0.797,
      "step": 150
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.4154150130018867e-05,
      "loss": 0.7754,
      "step": 160
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.3494641795990986e-05,
      "loss": 0.7847,
      "step": 170
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.2817325568414299e-05,
      "loss": 0.7779,
      "step": 180
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.2125652895529766e-05,
      "loss": 0.7569,
      "step": 190
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.1423148382732854e-05,
      "loss": 0.7688,
      "step": 200
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.0713391831992324e-05,
      "loss": 0.7734,
      "step": 210
    },
    {
      "epoch": 2.49,
      "learning_rate": 1e-05,
      "loss": 0.7668,
      "step": 220
    },
    {
      "epoch": 2.61,
      "learning_rate": 9.286608168007678e-06,
      "loss": 0.7951,
      "step": 230
    },
    {
      "epoch": 2.72,
      "learning_rate": 8.576851617267151e-06,
      "loss": 0.7616,
      "step": 240
    },
    {
      "epoch": 2.83,
      "learning_rate": 7.874347104470234e-06,
      "loss": 0.7619,
      "step": 250
    },
    {
      "epoch": 2.95,
      "learning_rate": 7.182674431585703e-06,
      "loss": 0.7701,
      "step": 260
    },
    {
      "epoch": 3.06,
      "learning_rate": 6.505358204009018e-06,
      "loss": 0.7985,
      "step": 270
    },
    {
      "epoch": 3.17,
      "learning_rate": 5.845849869981137e-06,
      "loss": 0.75,
      "step": 280
    },
    {
      "epoch": 3.29,
      "learning_rate": 5.207510132799436e-06,
      "loss": 0.7508,
      "step": 290
    },
    {
      "epoch": 3.4,
      "learning_rate": 4.593591825444028e-06,
      "loss": 0.7655,
      "step": 300
    },
    {
      "epoch": 3.51,
      "learning_rate": 4.007223334886531e-06,
      "loss": 0.7686,
      "step": 310
    },
    {
      "epoch": 3.63,
      "learning_rate": 3.4513926605471504e-06,
      "loss": 0.7551,
      "step": 320
    },
    {
      "epoch": 3.74,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.7524,
      "step": 330
    },
    {
      "epoch": 3.85,
      "learning_rate": 2.4425042564574186e-06,
      "loss": 0.7722,
      "step": 340
    },
    {
      "epoch": 3.97,
      "learning_rate": 1.994587590756397e-06,
      "loss": 0.7471,
      "step": 350
    },
    {
      "epoch": 4.08,
      "learning_rate": 1.587464671688187e-06,
      "loss": 0.754,
      "step": 360
    },
    {
      "epoch": 4.19,
      "learning_rate": 1.2232101043274437e-06,
      "loss": 0.7549,
      "step": 370
    },
    {
      "epoch": 4.31,
      "learning_rate": 9.036800464548157e-07,
      "loss": 0.7678,
      "step": 380
    },
    {
      "epoch": 4.42,
      "learning_rate": 6.305027500023841e-07,
      "loss": 0.7584,
      "step": 390
    },
    {
      "epoch": 4.53,
      "learning_rate": 4.0507026385502747e-07,
      "loss": 0.7613,
      "step": 400
    }
  ],
  "max_steps": 440,
  "num_train_epochs": 5,
  "total_flos": 3.127602400495534e+17,
  "trial_name": null,
  "trial_params": null
}