{
  "best_metric": 0.24114194512367249,
  "best_model_checkpoint": "spa_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": 1.1371,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9048716064584037,
      "eval_f1": 0.7243551088777219,
      "eval_loss": 0.3775480389595032,
      "eval_precision": 0.7339443312966735,
      "eval_recall": 0.7150132275132275,
      "eval_runtime": 6.0582,
      "eval_samples_per_second": 273.02,
      "eval_steps_per_second": 17.167,
      "step": 896
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.9776785714285716e-05,
      "loss": 0.4693,
      "step": 1000
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.9665178571428575e-05,
      "loss": 0.3471,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9221297638670983,
      "eval_f1": 0.777262180974478,
      "eval_loss": 0.2830303907394409,
      "eval_precision": 0.7790697674418605,
      "eval_recall": 0.7754629629629629,
      "eval_runtime": 6.1806,
      "eval_samples_per_second": 267.611,
      "eval_steps_per_second": 16.827,
      "step": 1792
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.955357142857143e-05,
      "loss": 0.2956,
      "step": 2000
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.944196428571429e-05,
      "loss": 0.2577,
      "step": 2500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9305503147776697,
      "eval_f1": 0.804476281649226,
      "eval_loss": 0.25689932703971863,
      "eval_precision": 0.803071244974626,
      "eval_recall": 0.8058862433862434,
      "eval_runtime": 6.3829,
      "eval_samples_per_second": 259.131,
      "eval_steps_per_second": 16.294,
      "step": 2688
    },
    {
      "epoch": 3.35,
      "learning_rate": 1.9330357142857144e-05,
      "loss": 0.2208,
      "step": 3000
    },
    {
      "epoch": 3.91,
      "learning_rate": 1.9218750000000003e-05,
      "loss": 0.2027,
      "step": 3500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9369451671201319,
      "eval_f1": 0.8246549041676321,
      "eval_loss": 0.24307304620742798,
      "eval_precision": 0.825502021340049,
      "eval_recall": 0.8238095238095238,
      "eval_runtime": 6.3445,
      "eval_samples_per_second": 260.7,
      "eval_steps_per_second": 16.392,
      "step": 3584
    },
    {
      "epoch": 4.46,
      "learning_rate": 1.910714285714286e-05,
      "loss": 0.1789,
      "step": 4000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9379977359839533,
      "eval_f1": 0.8279601891346758,
      "eval_loss": 0.24357271194458008,
      "eval_precision": 0.8278780665211929,
      "eval_recall": 0.828042328042328,
      "eval_runtime": 6.293,
      "eval_samples_per_second": 262.831,
      "eval_steps_per_second": 16.526,
      "step": 4480
    },
    {
      "epoch": 5.02,
      "learning_rate": 1.8995535714285717e-05,
      "loss": 0.1675,
      "step": 4500
    },
    {
      "epoch": 5.58,
      "learning_rate": 1.8883928571428573e-05,
      "loss": 0.1444,
      "step": 5000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9377594185053522,
      "eval_f1": 0.8251822398939694,
      "eval_loss": 0.24114194512367249,
      "eval_precision": 0.8268260292164674,
      "eval_recall": 0.8235449735449736,
      "eval_runtime": 6.2867,
      "eval_samples_per_second": 263.095,
      "eval_steps_per_second": 16.543,
      "step": 5376
    },
    {
      "epoch": 6.14,
      "learning_rate": 1.8772321428571428e-05,
      "loss": 0.142,
      "step": 5500
    },
    {
      "epoch": 6.7,
      "learning_rate": 1.8660714285714287e-05,
      "loss": 0.1281,
      "step": 6000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9338073203185511,
      "eval_f1": 0.8128755364806866,
      "eval_loss": 0.2639632821083069,
      "eval_precision": 0.8115359261700725,
      "eval_recall": 0.8142195767195767,
      "eval_runtime": 6.1519,
      "eval_samples_per_second": 268.861,
      "eval_steps_per_second": 16.905,
      "step": 6272
    }
  ],
  "max_steps": 89600,
  "num_train_epochs": 100,
  "total_flos": 4856704636063104.0,
  "trial_name": null,
  "trial_params": null
}