{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "global_step": 1196,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 2.874581939799331e-05,
      "loss": 1.3059,
      "step": 50
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.7491638795986622e-05,
      "loss": 1.2769,
      "step": 100
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.6237458193979933e-05,
      "loss": 1.2016,
      "step": 150
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.4983277591973243e-05,
      "loss": 1.2823,
      "step": 200
    },
    {
      "epoch": 0.84,
      "learning_rate": 2.3729096989966557e-05,
      "loss": 1.2613,
      "step": 250
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.2474916387959865e-05,
      "loss": 1.2375,
      "step": 300
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.122073578595318e-05,
      "loss": 1.2233,
      "step": 350
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.996655518394649e-05,
      "loss": 1.2468,
      "step": 400
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.87123745819398e-05,
      "loss": 1.1199,
      "step": 450
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.745819397993311e-05,
      "loss": 1.0252,
      "step": 500
    },
    {
      "epoch": 1.67,
      "eval_accuracy": 0.55625,
      "eval_f1_macro": 0.31421845574387947,
      "eval_f1_micro": 0.55625,
      "eval_f1_unweighted_diskutierend": 0.0,
      "eval_f1_unweighted_ja-daf\u00fcr": 0.5111111111111111,
      "eval_f1_unweighted_kein-bezug": 0.7457627118644068,
      "eval_f1_unweighted_nein-dagegen": 0.0,
      "eval_f1_weighted": 0.4473987758945386,
      "eval_loss": 1.1650867462158203,
      "eval_runtime": 23.2791,
      "eval_samples_per_second": 6.873,
      "eval_steps_per_second": 0.859,
      "step": 500
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.620401337792642e-05,
      "loss": 1.0867,
      "step": 550
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.4949832775919733e-05,
      "loss": 1.0217,
      "step": 600
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.3695652173913042e-05,
      "loss": 0.8828,
      "step": 650
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.2441471571906355e-05,
      "loss": 0.9718,
      "step": 700
    },
    {
      "epoch": 2.51,
      "learning_rate": 1.1187290969899665e-05,
      "loss": 0.9971,
      "step": 750
    },
    {
      "epoch": 2.68,
      "learning_rate": 9.933110367892978e-06,
      "loss": 0.8862,
      "step": 800
    },
    {
      "epoch": 2.84,
      "learning_rate": 8.678929765886286e-06,
      "loss": 0.9743,
      "step": 850
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.424749163879599e-06,
      "loss": 0.9939,
      "step": 900
    },
    {
      "epoch": 3.18,
      "learning_rate": 6.17056856187291e-06,
      "loss": 0.7587,
      "step": 950
    },
    {
      "epoch": 3.34,
      "learning_rate": 4.916387959866221e-06,
      "loss": 0.8624,
      "step": 1000
    },
    {
      "epoch": 3.34,
      "eval_accuracy": 0.6625,
      "eval_f1_macro": 0.4798663717403574,
      "eval_f1_micro": 0.6625,
      "eval_f1_unweighted_diskutierend": 0.5569620253164557,
      "eval_f1_unweighted_ja-daf\u00fcr": 0.5217391304347826,
      "eval_f1_unweighted_kein-bezug": 0.8407643312101911,
      "eval_f1_unweighted_nein-dagegen": 0.0,
      "eval_f1_weighted": 0.6282338774980808,
      "eval_loss": 0.8862520456314087,
      "eval_runtime": 23.317,
      "eval_samples_per_second": 6.862,
      "eval_steps_per_second": 0.858,
      "step": 1000
    },
    {
      "epoch": 3.51,
      "learning_rate": 3.662207357859532e-06,
      "loss": 0.8056,
      "step": 1050
    },
    {
      "epoch": 3.68,
      "learning_rate": 2.408026755852843e-06,
      "loss": 0.8175,
      "step": 1100
    },
    {
      "epoch": 3.85,
      "learning_rate": 1.153846153846154e-06,
      "loss": 0.7386,
      "step": 1150
    },
    {
      "epoch": 4.0,
      "step": 1196,
      "total_flos": 2.0142135211720704e+16,
      "train_loss": 1.0348390400609044,
      "train_runtime": 5404.336,
      "train_samples_per_second": 1.77,
      "train_steps_per_second": 0.221
    }
  ],
  "max_steps": 1196,
  "num_train_epochs": 4,
  "total_flos": 2.0142135211720704e+16,
  "trial_name": null,
  "trial_params": null
}