{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 5453,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6418485237483954,
      "grad_norm": 9.85666561126709,
      "learning_rate": 1.8169814780854577e-05,
      "loss": 0.5294,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8421842184218422,
      "eval_f1": 0.7176287051482059,
      "eval_loss": 0.42669883370399475,
      "eval_precision": 0.6764705882352942,
      "eval_recall": 0.7641196013289037,
      "eval_runtime": 0.5577,
      "eval_samples_per_second": 421.34,
      "eval_steps_per_second": 53.788,
      "step": 779
    },
    {
      "epoch": 1.2836970474967908,
      "grad_norm": 14.279178619384766,
      "learning_rate": 1.633596185585916e-05,
      "loss": 0.3251,
      "step": 1000
    },
    {
      "epoch": 1.925545571245186,
      "grad_norm": 3.289396047592163,
      "learning_rate": 1.4502108930863745e-05,
      "loss": 0.2522,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.882988298829883,
      "eval_f1": 0.7681549220010758,
      "eval_loss": 0.34702780842781067,
      "eval_precision": 0.7468619246861925,
      "eval_recall": 0.7906976744186046,
      "eval_runtime": 0.4659,
      "eval_samples_per_second": 504.441,
      "eval_steps_per_second": 64.397,
      "step": 1558
    },
    {
      "epoch": 2.5673940949935816,
      "grad_norm": 2.985898733139038,
      "learning_rate": 1.266825600586833e-05,
      "loss": 0.1615,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8852385238523852,
      "eval_f1": 0.7855183763027976,
      "eval_loss": 0.40044641494750977,
      "eval_precision": 0.7782608695652173,
      "eval_recall": 0.7929125138427464,
      "eval_runtime": 0.5454,
      "eval_samples_per_second": 430.843,
      "eval_steps_per_second": 55.001,
      "step": 2337
    },
    {
      "epoch": 3.209242618741977,
      "grad_norm": 3.132018804550171,
      "learning_rate": 1.0834403080872916e-05,
      "loss": 0.1346,
      "step": 2500
    },
    {
      "epoch": 3.851091142490372,
      "grad_norm": 23.86431121826172,
      "learning_rate": 9.0005501558775e-06,
      "loss": 0.093,
      "step": 3000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8876387638763876,
      "eval_f1": 0.7800875273522976,
      "eval_loss": 0.4634242355823517,
      "eval_precision": 0.7708108108108108,
      "eval_recall": 0.7895902547065338,
      "eval_runtime": 0.5241,
      "eval_samples_per_second": 448.366,
      "eval_steps_per_second": 57.238,
      "step": 3116
    },
    {
      "epoch": 4.492939666238768,
      "grad_norm": 10.69092845916748,
      "learning_rate": 7.166697230882084e-06,
      "loss": 0.0695,
      "step": 3500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8912391239123912,
      "eval_f1": 0.7937024972855592,
      "eval_loss": 0.512829601764679,
      "eval_precision": 0.7784877529286475,
      "eval_recall": 0.8095238095238095,
      "eval_runtime": 0.5735,
      "eval_samples_per_second": 409.733,
      "eval_steps_per_second": 52.306,
      "step": 3895
    },
    {
      "epoch": 5.134788189987163,
      "grad_norm": 0.8048956990242004,
      "learning_rate": 5.332844305886668e-06,
      "loss": 0.0601,
      "step": 4000
    },
    {
      "epoch": 5.7766367137355585,
      "grad_norm": 2.4991579055786133,
      "learning_rate": 3.498991380891253e-06,
      "loss": 0.0413,
      "step": 4500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8915391539153915,
      "eval_f1": 0.7760702524698133,
      "eval_loss": 0.5404914021492004,
      "eval_precision": 0.7693144722524483,
      "eval_recall": 0.7829457364341085,
      "eval_runtime": 0.5644,
      "eval_samples_per_second": 416.369,
      "eval_steps_per_second": 53.154,
      "step": 4674
    },
    {
      "epoch": 6.418485237483954,
      "grad_norm": 18.92781639099121,
      "learning_rate": 1.6651384558958373e-06,
      "loss": 0.0341,
      "step": 5000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8921392139213922,
      "eval_f1": 0.7840349917987972,
      "eval_loss": 0.5803054571151733,
      "eval_precision": 0.7742980561555075,
      "eval_recall": 0.7940199335548173,
      "eval_runtime": 0.5542,
      "eval_samples_per_second": 424.041,
      "eval_steps_per_second": 54.133,
      "step": 5453
    }
  ],
  "logging_steps": 500,
  "max_steps": 5453,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1159775675802900.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}