{
  "best_metric": 0.2436869889497757,
  "best_model_checkpoint": "spa_pt_XLM-R/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": 1.0286,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9020316565050742,
      "eval_f1": 0.7198845715052681,
      "eval_loss": 0.38969677686691284,
      "eval_precision": 0.7306225309903283,
      "eval_recall": 0.709457671957672,
      "eval_runtime": 5.2836,
      "eval_samples_per_second": 313.047,
      "eval_steps_per_second": 19.684,
      "step": 896
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.9776785714285716e-05,
      "loss": 0.4838,
      "step": 1000
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.9665178571428575e-05,
      "loss": 0.3644,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.920521120886541,
      "eval_f1": 0.7758597970747134,
      "eval_loss": 0.29738813638687134,
      "eval_precision": 0.7729062746127593,
      "eval_recall": 0.7788359788359789,
      "eval_runtime": 5.3407,
      "eval_samples_per_second": 309.696,
      "eval_steps_per_second": 19.473,
      "step": 1792
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.955357142857143e-05,
      "loss": 0.3066,
      "step": 2000
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.944196428571429e-05,
      "loss": 0.266,
      "step": 2500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9277103648243401,
      "eval_f1": 0.7969262362955849,
      "eval_loss": 0.26725220680236816,
      "eval_precision": 0.7982217503815274,
      "eval_recall": 0.7956349206349206,
      "eval_runtime": 5.3773,
      "eval_samples_per_second": 307.591,
      "eval_steps_per_second": 19.341,
      "step": 2688
    },
    {
      "epoch": 3.35,
      "learning_rate": 1.9330357142857144e-05,
      "loss": 0.2281,
      "step": 3000
    },
    {
      "epoch": 3.91,
      "learning_rate": 1.9218750000000003e-05,
      "loss": 0.2053,
      "step": 3500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9287430738982781,
      "eval_f1": 0.7990359536465382,
      "eval_loss": 0.2716098129749298,
      "eval_precision": 0.7977454018063155,
      "eval_recall": 0.8003306878306878,
      "eval_runtime": 5.3092,
      "eval_samples_per_second": 311.533,
      "eval_steps_per_second": 19.589,
      "step": 3584
    },
    {
      "epoch": 4.46,
      "learning_rate": 1.910714285714286e-05,
      "loss": 0.1846,
      "step": 4000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9368657279605982,
      "eval_f1": 0.8260755163794238,
      "eval_loss": 0.24669457972049713,
      "eval_precision": 0.8216435488092122,
      "eval_recall": 0.8305555555555556,
      "eval_runtime": 5.3537,
      "eval_samples_per_second": 308.944,
      "eval_steps_per_second": 19.426,
      "step": 4480
    },
    {
      "epoch": 5.02,
      "learning_rate": 1.8995535714285717e-05,
      "loss": 0.1739,
      "step": 4500
    },
    {
      "epoch": 5.58,
      "learning_rate": 1.8883928571428573e-05,
      "loss": 0.1475,
      "step": 5000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9384743709411555,
      "eval_f1": 0.8293472515856237,
      "eval_loss": 0.2436869889497757,
      "eval_precision": 0.8284714889123548,
      "eval_recall": 0.8302248677248677,
      "eval_runtime": 5.3954,
      "eval_samples_per_second": 306.557,
      "eval_steps_per_second": 19.276,
      "step": 5376
    },
    {
      "epoch": 6.14,
      "learning_rate": 1.8772321428571428e-05,
      "loss": 0.1427,
      "step": 5500
    },
    {
      "epoch": 6.7,
      "learning_rate": 1.8660714285714287e-05,
      "loss": 0.1285,
      "step": 6000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9372430639683832,
      "eval_f1": 0.827834276184559,
      "eval_loss": 0.25498533248901367,
      "eval_precision": 0.8187051290343444,
      "eval_recall": 0.8371693121693121,
      "eval_runtime": 5.3539,
      "eval_samples_per_second": 308.934,
      "eval_steps_per_second": 19.425,
      "step": 6272
    }
  ],
  "max_steps": 89600,
  "num_train_epochs": 100,
  "total_flos": 4856704636063104.0,
  "trial_name": null,
  "trial_params": null
}