{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5561735261401557,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.944382647385984e-05,
      "loss": 2.044,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.888765294771969e-05,
      "loss": 1.9144,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.833147942157953e-05,
      "loss": 1.8029,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.777530589543938e-05,
      "loss": 1.6849,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.721913236929923e-05,
      "loss": 1.6895,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.671857619577308e-05,
      "loss": 1.7024,
      "step": 60
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.6162402669632924e-05,
      "loss": 1.6251,
      "step": 70
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.560622914349277e-05,
      "loss": 1.5079,
      "step": 80
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.505005561735261e-05,
      "loss": 1.5368,
      "step": 90
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.449388209121246e-05,
      "loss": 1.3431,
      "step": 100
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.393770856507231e-05,
      "loss": 1.4992,
      "step": 110
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.338153503893215e-05,
      "loss": 1.335,
      "step": 120
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.2825361512791996e-05,
      "loss": 1.3175,
      "step": 130
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.226918798665184e-05,
      "loss": 1.3414,
      "step": 140
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.171301446051168e-05,
      "loss": 1.215,
      "step": 150
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.1156840934371526e-05,
      "loss": 1.278,
      "step": 160
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.0600667408231366e-05,
      "loss": 1.2685,
      "step": 170
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.0044493882091214e-05,
      "loss": 1.3019,
      "step": 180
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.948832035595106e-05,
      "loss": 1.1352,
      "step": 190
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.89321468298109e-05,
      "loss": 1.3311,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 3.837597330367075e-05,
      "loss": 1.3117,
      "step": 210
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.781979977753059e-05,
      "loss": 1.1897,
      "step": 220
    },
    {
      "epoch": 0.26,
      "learning_rate": 3.726362625139044e-05,
      "loss": 1.3223,
      "step": 230
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.670745272525028e-05,
      "loss": 1.2783,
      "step": 240
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.615127919911012e-05,
      "loss": 1.335,
      "step": 250
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.559510567296997e-05,
      "loss": 1.2529,
      "step": 260
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.503893214682981e-05,
      "loss": 1.1731,
      "step": 270
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 1.1722,
      "step": 280
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.3926585094549504e-05,
      "loss": 1.2023,
      "step": 290
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.3370411568409345e-05,
      "loss": 1.1299,
      "step": 300
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.281423804226919e-05,
      "loss": 1.2606,
      "step": 310
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.2258064516129034e-05,
      "loss": 1.0815,
      "step": 320
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.170189098998888e-05,
      "loss": 1.3171,
      "step": 330
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.114571746384872e-05,
      "loss": 1.1747,
      "step": 340
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.058954393770856e-05,
      "loss": 1.1978,
      "step": 350
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.003337041156841e-05,
      "loss": 1.0724,
      "step": 360
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.9477196885428255e-05,
      "loss": 1.3055,
      "step": 370
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.8921023359288102e-05,
      "loss": 1.14,
      "step": 380
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.8364849833147943e-05,
      "loss": 1.1491,
      "step": 390
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.7808676307007788e-05,
      "loss": 0.9949,
      "step": 400
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7252502780867635e-05,
      "loss": 1.1629,
      "step": 410
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.6696329254727476e-05,
      "loss": 1.1127,
      "step": 420
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6140155728587317e-05,
      "loss": 1.2377,
      "step": 430
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.5583982202447165e-05,
      "loss": 1.1743,
      "step": 440
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.502780867630701e-05,
      "loss": 1.1584,
      "step": 450
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.4471635150166853e-05,
      "loss": 1.3628,
      "step": 460
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.3915461624026697e-05,
      "loss": 1.0802,
      "step": 470
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.335928809788654e-05,
      "loss": 1.1615,
      "step": 480
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.2803114571746386e-05,
      "loss": 1.2211,
      "step": 490
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.224694104560623e-05,
      "loss": 1.1019,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 899,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 6.433444984592794e+16,
  "trial_name": null,
  "trial_params": null
}