{
  "best_metric": 0.2633977234363556,
  "best_model_checkpoint": "saved_model/checkpoint-14890",
  "epoch": 0.9999664215439374,
  "eval_steps": 500,
  "global_step": 14890,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1.986568166554735e-05,
      "loss": 0.3718,
      "step": 500
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9731363331094694e-05,
      "loss": 0.3007,
      "step": 1000
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.959704499664204e-05,
      "loss": 0.2808,
      "step": 1500
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.946272666218939e-05,
      "loss": 0.2593,
      "step": 2000
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9328408327736737e-05,
      "loss": 0.2444,
      "step": 2500
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9194089993284085e-05,
      "loss": 0.2381,
      "step": 3000
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9059771658831433e-05,
      "loss": 0.2374,
      "step": 3500
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.892545332437878e-05,
      "loss": 0.2278,
      "step": 4000
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.8791134989926128e-05,
      "loss": 0.2193,
      "step": 4500
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.8656816655473473e-05,
      "loss": 0.219,
      "step": 5000
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.852249832102082e-05,
      "loss": 0.2241,
      "step": 5500
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.8388179986568168e-05,
      "loss": 0.2268,
      "step": 6000
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8253861652115516e-05,
      "loss": 0.2135,
      "step": 6500
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.8119543317662864e-05,
      "loss": 0.2164,
      "step": 7000
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.798522498321021e-05,
      "loss": 0.214,
      "step": 7500
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.785090664875756e-05,
      "loss": 0.2042,
      "step": 8000
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.7716588314304904e-05,
      "loss": 0.2031,
      "step": 8500
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.758226997985225e-05,
      "loss": 0.2045,
      "step": 9000
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.74479516453996e-05,
      "loss": 0.1993,
      "step": 9500
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.7313633310946947e-05,
      "loss": 0.2012,
      "step": 10000
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.717931497649429e-05,
      "loss": 0.1971,
      "step": 10500
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.704499664204164e-05,
      "loss": 0.1918,
      "step": 11000
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.6910678307588987e-05,
      "loss": 0.1972,
      "step": 11500
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.6776359973136335e-05,
      "loss": 0.1855,
      "step": 12000
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.6642041638683682e-05,
      "loss": 0.1873,
      "step": 12500
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.650772330423103e-05,
      "loss": 0.1807,
      "step": 13000
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.6373404969778378e-05,
      "loss": 0.1842,
      "step": 13500
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6239086635325722e-05,
      "loss": 0.1968,
      "step": 14000
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.610476830087307e-05,
      "loss": 0.1786,
      "step": 14500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9212894560107455,
      "eval_loss": 0.2633977234363556,
      "eval_macro_f1": 0.9043313763923932,
      "eval_runtime": 742.0543,
      "eval_samples_per_second": 80.264,
      "eval_steps_per_second": 20.066,
      "step": 14890
    }
  ],
  "logging_steps": 500,
  "max_steps": 74450,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 6.268568271740928e+16,
  "trial_name": null,
  "trial_params": null
}