{
  "best_metric": 0.48976385684127843,
  "best_model_checkpoint": "mecha-tagger/checkpoint-847",
  "epoch": 7.0,
  "global_step": 847,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.437,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.06247574699262708,
      "eval_f1": 0.431281999799217,
      "eval_loss": 0.32573798298835754,
      "eval_roc_auc": 0.6429553592437186,
      "eval_runtime": 50.2381,
      "eval_samples_per_second": 51.296,
      "eval_steps_per_second": 0.537,
      "step": 121
    },
    {
      "epoch": 1.65,
      "learning_rate": 2e-05,
      "loss": 0.3211,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.055490880869227786,
      "eval_f1": 0.45432441820076414,
      "eval_loss": 0.3099991977214813,
      "eval_roc_auc": 0.6526660416613327,
      "eval_runtime": 50.3523,
      "eval_samples_per_second": 51.179,
      "eval_steps_per_second": 0.536,
      "step": 242
    },
    {
      "epoch": 2.48,
      "learning_rate": 2e-05,
      "loss": 0.309,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.05820721769499418,
      "eval_f1": 0.4483176720218248,
      "eval_loss": 0.30198442935943604,
      "eval_roc_auc": 0.6485457459740307,
      "eval_runtime": 50.3568,
      "eval_samples_per_second": 51.175,
      "eval_steps_per_second": 0.536,
      "step": 363
    },
    {
      "epoch": 3.31,
      "learning_rate": 2e-05,
      "loss": 0.303,
      "step": 400
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.05743112145906092,
      "eval_f1": 0.4746113989637306,
      "eval_loss": 0.295987069606781,
      "eval_roc_auc": 0.6608536486091969,
      "eval_runtime": 50.3091,
      "eval_samples_per_second": 51.223,
      "eval_steps_per_second": 0.537,
      "step": 484
    },
    {
      "epoch": 4.13,
      "learning_rate": 2e-05,
      "loss": 0.2965,
      "step": 500
    },
    {
      "epoch": 4.96,
      "learning_rate": 2e-05,
      "loss": 0.294,
      "step": 600
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.0682964687621265,
      "eval_f1": 0.4646505308710311,
      "eval_loss": 0.28789642453193665,
      "eval_roc_auc": 0.6549506720523524,
      "eval_runtime": 50.2808,
      "eval_samples_per_second": 51.252,
      "eval_steps_per_second": 0.537,
      "step": 605
    },
    {
      "epoch": 5.79,
      "learning_rate": 2e-05,
      "loss": 0.2879,
      "step": 700
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.06674427629025999,
      "eval_f1": 0.4727673207849419,
      "eval_loss": 0.2825814187526703,
      "eval_roc_auc": 0.658515066442945,
      "eval_runtime": 50.324,
      "eval_samples_per_second": 51.208,
      "eval_steps_per_second": 0.537,
      "step": 726
    },
    {
      "epoch": 6.61,
      "learning_rate": 2e-05,
      "loss": 0.2846,
      "step": 800
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.06984866123399301,
      "eval_f1": 0.48976385684127843,
      "eval_loss": 0.27861288189888,
      "eval_roc_auc": 0.6671462002192768,
      "eval_runtime": 50.1175,
      "eval_samples_per_second": 51.419,
      "eval_steps_per_second": 0.539,
      "step": 847
    }
  ],
  "max_steps": 6050,
  "num_train_epochs": 50,
  "total_flos": 3.7058226858424074e+19,
  "trial_name": null,
  "trial_params": null
}