{
  "best_metric": 0.6828581526810108,
  "best_model_checkpoint": "trained/hebban-reviews/bert-base-multilingual-cased/checkpoint-1500",
  "epoch": 4.382997370727432,
  "global_step": 5001,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.44,
      "learning_rate": 4.504099180163968e-05,
      "loss": 0.8498,
      "step": 500
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.6671597633136095,
      "eval_f1": 0.6926558253677099,
      "eval_loss": 0.7364796996116638,
      "eval_precision": 0.7520529030378761,
      "eval_qwk": 0.5224288418460314,
      "eval_recall": 0.6671597633136095,
      "eval_runtime": 23.7829,
      "eval_samples_per_second": 682.171,
      "eval_steps_per_second": 5.34,
      "step": 500
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.0041991601679665e-05,
      "loss": 0.6918,
      "step": 1000
    },
    {
      "epoch": 0.88,
      "eval_accuracy": 0.7271942800788954,
      "eval_f1": 0.7414418295002464,
      "eval_loss": 0.6605744957923889,
      "eval_precision": 0.7743449767911329,
      "eval_qwk": 0.5976543204298063,
      "eval_recall": 0.7271942800788954,
      "eval_runtime": 23.6177,
      "eval_samples_per_second": 686.943,
      "eval_steps_per_second": 5.377,
      "step": 1000
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.504299140171966e-05,
      "loss": 0.621,
      "step": 1500
    },
    {
      "epoch": 1.31,
      "eval_accuracy": 0.7785996055226825,
      "eval_f1": 0.7848033042674865,
      "eval_loss": 0.6530709266662598,
      "eval_precision": 0.7942290484031055,
      "eval_qwk": 0.6828581526810108,
      "eval_recall": 0.7785996055226825,
      "eval_runtime": 23.6972,
      "eval_samples_per_second": 684.637,
      "eval_steps_per_second": 5.359,
      "step": 1500
    },
    {
      "epoch": 1.75,
      "learning_rate": 3.0043991201759648e-05,
      "loss": 0.5936,
      "step": 2000
    },
    {
      "epoch": 1.75,
      "eval_accuracy": 0.7501849112426036,
      "eval_f1": 0.7649773762321463,
      "eval_loss": 0.6148771643638611,
      "eval_precision": 0.7952109430358816,
      "eval_qwk": 0.6613885538385067,
      "eval_recall": 0.7501849112426036,
      "eval_runtime": 23.8294,
      "eval_samples_per_second": 680.838,
      "eval_steps_per_second": 5.33,
      "step": 2000
    },
    {
      "epoch": 2.19,
      "learning_rate": 2.504499100179964e-05,
      "loss": 0.5434,
      "step": 2500
    },
    {
      "epoch": 2.19,
      "eval_accuracy": 0.7548076923076923,
      "eval_f1": 0.7709100781310829,
      "eval_loss": 0.6947299242019653,
      "eval_precision": 0.8080766037849636,
      "eval_qwk": 0.6597495777741245,
      "eval_recall": 0.7548076923076923,
      "eval_runtime": 23.6425,
      "eval_samples_per_second": 686.22,
      "eval_steps_per_second": 5.372,
      "step": 2500
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.0045990801839633e-05,
      "loss": 0.4808,
      "step": 3000
    },
    {
      "epoch": 2.63,
      "eval_accuracy": 0.7347140039447732,
      "eval_f1": 0.7545089976363922,
      "eval_loss": 0.645616352558136,
      "eval_precision": 0.8030403955873724,
      "eval_qwk": 0.6513487818562542,
      "eval_recall": 0.7347140039447732,
      "eval_runtime": 23.8892,
      "eval_samples_per_second": 679.136,
      "eval_steps_per_second": 5.316,
      "step": 3000
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.5046990601879624e-05,
      "loss": 0.4643,
      "step": 3500
    },
    {
      "epoch": 3.07,
      "eval_accuracy": 0.7427268244575936,
      "eval_f1": 0.7611673940281857,
      "eval_loss": 0.7119439244270325,
      "eval_precision": 0.8053303788937228,
      "eval_qwk": 0.6549274566801152,
      "eval_recall": 0.7427268244575936,
      "eval_runtime": 23.6156,
      "eval_samples_per_second": 687.004,
      "eval_steps_per_second": 5.378,
      "step": 3500
    },
    {
      "epoch": 3.51,
      "learning_rate": 1.0047990401919617e-05,
      "loss": 0.3854,
      "step": 4000
    },
    {
      "epoch": 3.51,
      "eval_accuracy": 0.7685527613412229,
      "eval_f1": 0.7819273980616418,
      "eval_loss": 0.7430822253227234,
      "eval_precision": 0.8091264019259906,
      "eval_qwk": 0.6812961348271991,
      "eval_recall": 0.7685527613412229,
      "eval_runtime": 23.6906,
      "eval_samples_per_second": 684.828,
      "eval_steps_per_second": 5.361,
      "step": 4000
    },
    {
      "epoch": 3.94,
      "learning_rate": 5.048990201959608e-06,
      "loss": 0.3642,
      "step": 4500
    },
    {
      "epoch": 3.94,
      "eval_accuracy": 0.7693540433925049,
      "eval_f1": 0.7827174333765768,
      "eval_loss": 0.7832001447677612,
      "eval_precision": 0.8104759531984178,
      "eval_qwk": 0.6799731235431681,
      "eval_recall": 0.7693540433925049,
      "eval_runtime": 23.5733,
      "eval_samples_per_second": 688.237,
      "eval_steps_per_second": 5.387,
      "step": 4500
    },
    {
      "epoch": 4.38,
      "learning_rate": 4.999000199960008e-08,
      "loss": 0.3199,
      "step": 5000
    },
    {
      "epoch": 4.38,
      "eval_accuracy": 0.7682445759368837,
      "eval_f1": 0.7820013322186519,
      "eval_loss": 0.8646416664123535,
      "eval_precision": 0.8117448424467829,
      "eval_qwk": 0.6776167553082479,
      "eval_recall": 0.7682445759368837,
      "eval_runtime": 23.7003,
      "eval_samples_per_second": 684.547,
      "eval_steps_per_second": 5.359,
      "step": 5000
    },
    {
      "epoch": 4.38,
      "step": 5001,
      "total_flos": 1.6838837781764506e+17,
      "train_loss": 0.5313903366928219,
      "train_runtime": 2667.6757,
      "train_samples_per_second": 239.957,
      "train_steps_per_second": 1.875
    }
  ],
  "max_steps": 5001,
  "num_train_epochs": 5,
  "total_flos": 1.6838837781764506e+17,
  "trial_name": null,
  "trial_params": null
}