trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.157894736842104,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.32,
      "eval_accuracy": 0.8087965089572806,
      "eval_f1": 0.8503675598766895,
      "eval_loss": 0.616326630115509,
      "eval_precision": 0.8087505638249888,
      "eval_recall": 0.8965,
      "eval_runtime": 2.4397,
      "eval_samples_per_second": 22.134,
      "eval_steps_per_second": 1.64,
      "step": 50
    },
    {
      "epoch": 2.63,
      "eval_accuracy": 0.8133899862195683,
      "eval_f1": 0.8346153846153846,
      "eval_loss": 0.541599690914154,
      "eval_precision": 0.8037037037037037,
      "eval_recall": 0.868,
      "eval_runtime": 2.2528,
      "eval_samples_per_second": 23.97,
      "eval_steps_per_second": 1.776,
      "step": 100
    },
    {
      "epoch": 3.95,
      "eval_accuracy": 0.8385392742305926,
      "eval_f1": 0.8659844054580897,
      "eval_loss": 0.5571682453155518,
      "eval_precision": 0.8445817490494296,
      "eval_recall": 0.8885,
      "eval_runtime": 2.2592,
      "eval_samples_per_second": 23.902,
      "eval_steps_per_second": 1.771,
      "step": 150
    },
    {
      "epoch": 5.26,
      "eval_accuracy": 0.8123564538355535,
      "eval_f1": 0.850608998260005,
      "eval_loss": 0.7317042350769043,
      "eval_precision": 0.8457736035590707,
      "eval_recall": 0.8555,
      "eval_runtime": 2.2554,
      "eval_samples_per_second": 23.943,
      "eval_steps_per_second": 1.774,
      "step": 200
    },
    {
      "epoch": 6.58,
      "eval_accuracy": 0.8385392742305926,
      "eval_f1": 0.8906055320209318,
      "eval_loss": 0.7219748497009277,
      "eval_precision": 0.8877297565822156,
      "eval_recall": 0.8935,
      "eval_runtime": 2.2283,
      "eval_samples_per_second": 24.234,
      "eval_steps_per_second": 1.795,
      "step": 250
    },
    {
      "epoch": 7.89,
      "eval_accuracy": 0.8435920992191088,
      "eval_f1": 0.8914595126753629,
      "eval_loss": 0.8069794774055481,
      "eval_precision": 0.8778477944740669,
      "eval_recall": 0.9055,
      "eval_runtime": 2.2476,
      "eval_samples_per_second": 24.025,
      "eval_steps_per_second": 1.78,
      "step": 300
    },
    {
      "epoch": 9.21,
      "eval_accuracy": 0.8477262287551677,
      "eval_f1": 0.9048562933597621,
      "eval_loss": 0.7895194888114929,
      "eval_precision": 0.8968565815324165,
      "eval_recall": 0.913,
      "eval_runtime": 2.3704,
      "eval_samples_per_second": 22.781,
      "eval_steps_per_second": 1.687,
      "step": 350
    },
    {
      "epoch": 10.53,
      "eval_accuracy": 0.8411805236564079,
      "eval_f1": 0.8912280701754386,
      "eval_loss": 0.8168221712112427,
      "eval_precision": 0.893467336683417,
      "eval_recall": 0.889,
      "eval_runtime": 2.4315,
      "eval_samples_per_second": 22.208,
      "eval_steps_per_second": 1.645,
      "step": 400
    },
    {
      "epoch": 11.84,
      "eval_accuracy": 0.8520900321543409,
      "eval_f1": 0.9061264822134387,
      "eval_loss": 0.8232607841491699,
      "eval_precision": 0.8955078125,
      "eval_recall": 0.917,
      "eval_runtime": 2.2665,
      "eval_samples_per_second": 23.825,
      "eval_steps_per_second": 1.765,
      "step": 450
    },
    {
      "epoch": 13.16,
      "learning_rate": 0.0,
      "loss": 0.2564,
      "step": 500
    },
    {
      "epoch": 13.16,
      "eval_accuracy": 0.8535829122645843,
      "eval_f1": 0.9075504610017443,
      "eval_loss": 0.8330431580543518,
      "eval_precision": 0.9046199701937406,
      "eval_recall": 0.9105,
      "eval_runtime": 2.224,
      "eval_samples_per_second": 24.281,
      "eval_steps_per_second": 1.799,
      "step": 500
    },
    {
      "epoch": 13.16,
      "step": 500,
      "total_flos": 520356947539968.0,
      "train_loss": 0.256378173828125,
      "train_runtime": 215.2806,
      "train_samples_per_second": 9.29,
      "train_steps_per_second": 2.323
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 14,
  "total_flos": 520356947539968.0,
  "trial_name": null,
  "trial_params": null
}