trainer_state.json

{
  "best_global_step": 180,
  "best_metric": 0.828678970373968,
  "best_model_checkpoint": "./results/PlanTL-GOB-ES/roberta-base-ca_fold_3/checkpoint-180",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 288,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8028169014084507,
      "eval_f1": 0.7150088028169014,
      "eval_loss": 1.0922181606292725,
      "eval_precision": 0.6445149771870662,
      "eval_recall": 0.8028169014084507,
      "eval_runtime": 0.2188,
      "eval_samples_per_second": 324.445,
      "eval_steps_per_second": 41.127,
      "step": 36
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7887323943661971,
      "eval_f1": 0.7079960075413108,
      "eval_loss": 1.0135005712509155,
      "eval_precision": 0.6422535211267606,
      "eval_recall": 0.7887323943661971,
      "eval_runtime": 0.2202,
      "eval_samples_per_second": 322.46,
      "eval_steps_per_second": 40.875,
      "step": 72
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7887323943661971,
      "eval_f1": 0.7079960075413108,
      "eval_loss": 1.1309207677841187,
      "eval_precision": 0.6422535211267606,
      "eval_recall": 0.7887323943661971,
      "eval_runtime": 0.2145,
      "eval_samples_per_second": 330.977,
      "eval_steps_per_second": 41.955,
      "step": 108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7605633802816901,
      "eval_f1": 0.7323336571151045,
      "eval_loss": 1.131150484085083,
      "eval_precision": 0.7131665183706244,
      "eval_recall": 0.7605633802816901,
      "eval_runtime": 0.224,
      "eval_samples_per_second": 316.976,
      "eval_steps_per_second": 40.18,
      "step": 144
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8450704225352113,
      "eval_f1": 0.828678970373968,
      "eval_loss": 1.0597354173660278,
      "eval_precision": 0.8310336595846264,
      "eval_recall": 0.8450704225352113,
      "eval_runtime": 0.212,
      "eval_samples_per_second": 334.945,
      "eval_steps_per_second": 42.458,
      "step": 180
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8028169014084507,
      "eval_f1": 0.7588173670119893,
      "eval_loss": 1.1688655614852905,
      "eval_precision": 0.7196302816901409,
      "eval_recall": 0.8028169014084507,
      "eval_runtime": 0.2204,
      "eval_samples_per_second": 322.152,
      "eval_steps_per_second": 40.836,
      "step": 216
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8028169014084507,
      "eval_f1": 0.7742691442774294,
      "eval_loss": 1.1306501626968384,
      "eval_precision": 0.7496592457973649,
      "eval_recall": 0.8028169014084507,
      "eval_runtime": 0.2199,
      "eval_samples_per_second": 322.923,
      "eval_steps_per_second": 40.934,
      "step": 252
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8309859154929577,
      "eval_f1": 0.8088886258728845,
      "eval_loss": 1.171406865119934,
      "eval_precision": 0.8048614266242617,
      "eval_recall": 0.8309859154929577,
      "eval_runtime": 0.2194,
      "eval_samples_per_second": 323.676,
      "eval_steps_per_second": 41.029,
      "step": 288
    }
  ],
  "logging_steps": 500,
  "max_steps": 720,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 48378474598608.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}