trainer_state.json

{
  "best_metric": 0.2869763970375061,
  "best_model_checkpoint": "gal_sp_XLM-R/checkpoint-1250",
  "epoch": 6.0,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8985218351324828,
      "eval_f1": 0.6311757348342715,
      "eval_loss": 0.3683431148529053,
      "eval_precision": 0.6882032049096488,
      "eval_recall": 0.5828761189719897,
      "eval_runtime": 5.2404,
      "eval_samples_per_second": 190.252,
      "eval_steps_per_second": 12.022,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.4521,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9153888616290481,
      "eval_f1": 0.7093653817968636,
      "eval_loss": 0.3080022931098938,
      "eval_precision": 0.7202380952380952,
      "eval_recall": 0.6988160554432573,
      "eval_runtime": 5.2307,
      "eval_samples_per_second": 190.605,
      "eval_steps_per_second": 12.044,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9145608439646713,
      "eval_f1": 0.7130997607992121,
      "eval_loss": 0.3053981065750122,
      "eval_precision": 0.6953896816684961,
      "eval_recall": 0.7317354894600058,
      "eval_runtime": 5.3687,
      "eval_samples_per_second": 185.707,
      "eval_steps_per_second": 11.735,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.2426,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.919191609421001,
      "eval_f1": 0.7231791866199699,
      "eval_loss": 0.3031836450099945,
      "eval_precision": 0.7160651096956829,
      "eval_recall": 0.7304360381172393,
      "eval_runtime": 5.2453,
      "eval_samples_per_second": 190.075,
      "eval_steps_per_second": 12.011,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9235157016683022,
      "eval_f1": 0.7326776277157957,
      "eval_loss": 0.2869763970375061,
      "eval_precision": 0.7451478053150195,
      "eval_recall": 0.7206179613052267,
      "eval_runtime": 5.215,
      "eval_samples_per_second": 191.179,
      "eval_steps_per_second": 12.081,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.1812,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9199889597644749,
      "eval_f1": 0.729057033138956,
      "eval_loss": 0.3071407973766327,
      "eval_precision": 0.718329596412556,
      "eval_recall": 0.7401097314467225,
      "eval_runtime": 5.2244,
      "eval_samples_per_second": 190.835,
      "eval_steps_per_second": 12.059,
      "step": 1500
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 925793237842200.0,
  "trial_name": null,
  "trial_params": null
}