trainer_state.json

{
  "best_global_step": 288,
  "best_metric": 0.797161758429364,
  "best_model_checkpoint": "./results/PlanTL-GOB-ES/roberta-base-ca_fold_4/checkpoint-288",
  "epoch": 11.0,
  "eval_steps": 500,
  "global_step": 396,
  "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": 1.1232081651687622,
      "eval_precision": 0.6445149771870662,
      "eval_recall": 0.8028169014084507,
      "eval_runtime": 0.2182,
      "eval_samples_per_second": 325.347,
      "eval_steps_per_second": 41.241,
      "step": 36
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8028169014084507,
      "eval_f1": 0.7150088028169014,
      "eval_loss": 1.0172744989395142,
      "eval_precision": 0.6445149771870662,
      "eval_recall": 0.8028169014084507,
      "eval_runtime": 0.2206,
      "eval_samples_per_second": 321.846,
      "eval_steps_per_second": 40.797,
      "step": 72
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8169014084507042,
      "eval_f1": 0.7441129717940187,
      "eval_loss": 0.9590336680412292,
      "eval_precision": 0.7241448692152918,
      "eval_recall": 0.8169014084507042,
      "eval_runtime": 0.212,
      "eval_samples_per_second": 334.874,
      "eval_steps_per_second": 42.449,
      "step": 108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8169014084507042,
      "eval_f1": 0.763924882629108,
      "eval_loss": 0.9801038503646851,
      "eval_precision": 0.7738193869096934,
      "eval_recall": 0.8169014084507042,
      "eval_runtime": 0.2113,
      "eval_samples_per_second": 335.988,
      "eval_steps_per_second": 42.59,
      "step": 144
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8309859154929577,
      "eval_f1": 0.7912162493090686,
      "eval_loss": 1.087168574333191,
      "eval_precision": 0.7958829902491874,
      "eval_recall": 0.8309859154929577,
      "eval_runtime": 0.2229,
      "eval_samples_per_second": 318.576,
      "eval_steps_per_second": 40.383,
      "step": 180
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8028169014084507,
      "eval_f1": 0.7427981220657277,
      "eval_loss": 1.1407651901245117,
      "eval_precision": 0.7315658657829328,
      "eval_recall": 0.8028169014084507,
      "eval_runtime": 0.2223,
      "eval_samples_per_second": 319.435,
      "eval_steps_per_second": 40.492,
      "step": 216
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8309859154929577,
      "eval_f1": 0.7900410593643159,
      "eval_loss": 1.1042982339859009,
      "eval_precision": 0.7797695262483996,
      "eval_recall": 0.8309859154929577,
      "eval_runtime": 0.2108,
      "eval_samples_per_second": 336.738,
      "eval_steps_per_second": 42.685,
      "step": 252
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8028169014084507,
      "eval_f1": 0.797161758429364,
      "eval_loss": 1.0862349271774292,
      "eval_precision": 0.7999999999999999,
      "eval_recall": 0.8028169014084507,
      "eval_runtime": 0.21,
      "eval_samples_per_second": 338.028,
      "eval_steps_per_second": 42.849,
      "step": 288
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8169014084507042,
      "eval_f1": 0.7595653923541248,
      "eval_loss": 1.1429076194763184,
      "eval_precision": 0.7315658657829328,
      "eval_recall": 0.8169014084507042,
      "eval_runtime": 0.2217,
      "eval_samples_per_second": 320.319,
      "eval_steps_per_second": 40.604,
      "step": 324
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8309859154929577,
      "eval_f1": 0.7900410593643159,
      "eval_loss": 1.116995096206665,
      "eval_precision": 0.7797695262483996,
      "eval_recall": 0.8309859154929577,
      "eval_runtime": 0.2201,
      "eval_samples_per_second": 322.653,
      "eval_steps_per_second": 40.9,
      "step": 360
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.8309859154929577,
      "eval_f1": 0.7900410593643159,
      "eval_loss": 1.1153522729873657,
      "eval_precision": 0.7797695262483996,
      "eval_recall": 0.8309859154929577,
      "eval_runtime": 0.2164,
      "eval_samples_per_second": 328.08,
      "eval_steps_per_second": 41.588,
      "step": 396
    }
  ],
  "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": 66520402573086.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}