{
  "best_metric": 0.3108000159263611,
  "best_model_checkpoint": "gal_en_XLM-R/checkpoint-1500",
  "epoch": 7.0,
  "global_step": 1750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8780973994111875,
      "eval_f1": 0.5202514522161216,
      "eval_loss": 0.44004401564598083,
      "eval_precision": 0.579507179578089,
      "eval_recall": 0.47198960438925786,
      "eval_runtime": 5.0934,
      "eval_samples_per_second": 195.743,
      "eval_steps_per_second": 12.369,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.5654,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9008218842001963,
      "eval_f1": 0.6336264719034134,
      "eval_loss": 0.35249266028404236,
      "eval_precision": 0.6548059149722736,
      "eval_recall": 0.6137741842333237,
      "eval_runtime": 5.0461,
      "eval_samples_per_second": 197.579,
      "eval_steps_per_second": 12.485,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8969271344455348,
      "eval_f1": 0.6431970884658454,
      "eval_loss": 0.3467901349067688,
      "eval_precision": 0.6241510459114371,
      "eval_recall": 0.6634421022235056,
      "eval_runtime": 5.0701,
      "eval_samples_per_second": 196.643,
      "eval_steps_per_second": 12.426,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.2931,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9097767419038273,
      "eval_f1": 0.6826355817755348,
      "eval_loss": 0.32281672954559326,
      "eval_precision": 0.6722665546689066,
      "eval_recall": 0.6933294831071325,
      "eval_runtime": 5.0717,
      "eval_samples_per_second": 196.581,
      "eval_steps_per_second": 12.422,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9145915112855741,
      "eval_f1": 0.6925381860703063,
      "eval_loss": 0.31136175990104675,
      "eval_precision": 0.7011987568447536,
      "eval_recall": 0.6840889402252383,
      "eval_runtime": 5.0357,
      "eval_samples_per_second": 197.986,
      "eval_steps_per_second": 12.511,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.2226,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9143768400392541,
      "eval_f1": 0.6987883107626515,
      "eval_loss": 0.3108000159263611,
      "eval_precision": 0.6900337837837838,
      "eval_recall": 0.7077678313600924,
      "eval_runtime": 5.0908,
      "eval_samples_per_second": 195.845,
      "eval_steps_per_second": 12.375,
      "step": 1500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9163088812561334,
      "eval_f1": 0.7023861171366594,
      "eval_loss": 0.3187449276447296,
      "eval_precision": 0.703505214368482,
      "eval_recall": 0.7012705746462604,
      "eval_runtime": 5.1654,
      "eval_samples_per_second": 193.016,
      "eval_steps_per_second": 12.197,
      "step": 1750
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 1079380891402800.0,
  "trial_name": null,
  "trial_params": null
}