{
  "best_metric": 0.27455607056617737,
  "best_model_checkpoint": "spa_pt_mBERT/checkpoint-5376",
  "epoch": 7.0,
  "global_step": 6272,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.56,
      "learning_rate": 1.988839285714286e-05,
      "loss": 1.0209,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8978809604194388,
      "eval_f1": 0.7095500646654416,
      "eval_loss": 0.40043166279792786,
      "eval_precision": 0.7308932828495303,
      "eval_recall": 0.6894179894179894,
      "eval_runtime": 5.9806,
      "eval_samples_per_second": 276.562,
      "eval_steps_per_second": 17.39,
      "step": 896
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.9776785714285716e-05,
      "loss": 0.4614,
      "step": 1000
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.9665178571428575e-05,
      "loss": 0.3426,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.89666951323655,
      "eval_f1": 0.6962397966010972,
      "eval_loss": 0.36208459734916687,
      "eval_precision": 0.7044408340102898,
      "eval_recall": 0.6882275132275132,
      "eval_runtime": 5.864,
      "eval_samples_per_second": 282.06,
      "eval_steps_per_second": 17.735,
      "step": 1792
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.955357142857143e-05,
      "loss": 0.2911,
      "step": 2000
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.944196428571429e-05,
      "loss": 0.2507,
      "step": 2500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9245327984429925,
      "eval_f1": 0.7879008024304065,
      "eval_loss": 0.2839251160621643,
      "eval_precision": 0.7867836180175427,
      "eval_recall": 0.7890211640211641,
      "eval_runtime": 5.9716,
      "eval_samples_per_second": 276.979,
      "eval_steps_per_second": 17.416,
      "step": 2688
    },
    {
      "epoch": 3.35,
      "learning_rate": 1.9330357142857144e-05,
      "loss": 0.2109,
      "step": 3000
    },
    {
      "epoch": 3.91,
      "learning_rate": 1.9218750000000003e-05,
      "loss": 0.191,
      "step": 3500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9295176057037317,
      "eval_f1": 0.8031677940933839,
      "eval_loss": 0.2753179669380188,
      "eval_precision": 0.8014487981560751,
      "eval_recall": 0.8048941798941799,
      "eval_runtime": 5.8922,
      "eval_samples_per_second": 280.709,
      "eval_steps_per_second": 17.65,
      "step": 3584
    },
    {
      "epoch": 4.46,
      "learning_rate": 1.910714285714286e-05,
      "loss": 0.168,
      "step": 4000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.932397275236828,
      "eval_f1": 0.8128352871051064,
      "eval_loss": 0.27723604440689087,
      "eval_precision": 0.8139673696776761,
      "eval_recall": 0.8117063492063492,
      "eval_runtime": 5.9959,
      "eval_samples_per_second": 275.857,
      "eval_steps_per_second": 17.345,
      "step": 4480
    },
    {
      "epoch": 5.02,
      "learning_rate": 1.8995535714285717e-05,
      "loss": 0.1551,
      "step": 4500
    },
    {
      "epoch": 5.58,
      "learning_rate": 1.8883928571428573e-05,
      "loss": 0.1323,
      "step": 5000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9337080213691339,
      "eval_f1": 0.8170909573057545,
      "eval_loss": 0.27455607056617737,
      "eval_precision": 0.8190457203615098,
      "eval_recall": 0.8151455026455027,
      "eval_runtime": 5.9697,
      "eval_samples_per_second": 277.067,
      "eval_steps_per_second": 17.421,
      "step": 5376
    },
    {
      "epoch": 6.14,
      "learning_rate": 1.8772321428571428e-05,
      "loss": 0.1276,
      "step": 5500
    },
    {
      "epoch": 6.7,
      "learning_rate": 1.8660714285714287e-05,
      "loss": 0.1112,
      "step": 6000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9358131590967768,
      "eval_f1": 0.823094688221709,
      "eval_loss": 0.28870320320129395,
      "eval_precision": 0.8211981566820277,
      "eval_recall": 0.825,
      "eval_runtime": 5.8998,
      "eval_samples_per_second": 280.348,
      "eval_steps_per_second": 17.628,
      "step": 6272
    }
  ],
  "max_steps": 89600,
  "num_train_epochs": 100,
  "total_flos": 4576312134542016.0,
  "trial_name": null,
  "trial_params": null
}