checkpoint-54/trainer_state.json

{
  "best_metric": 0.7919463087248322,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-54",
  "epoch": 2.899328859060403,
  "eval_steps": 500,
  "global_step": 54,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9664429530201343,
      "eval_accuracy": 0.7583892617449665,
      "eval_loss": 0.7078245878219604,
      "eval_runtime": 3.2791,
      "eval_samples_per_second": 90.879,
      "eval_steps_per_second": 11.589,
      "step": 18
    },
    {
      "epoch": 1.9865771812080537,
      "eval_accuracy": 0.785234899328859,
      "eval_loss": 0.5109438300132751,
      "eval_runtime": 3.2689,
      "eval_samples_per_second": 91.162,
      "eval_steps_per_second": 11.625,
      "step": 37
    },
    {
      "epoch": 2.899328859060403,
      "eval_accuracy": 0.7919463087248322,
      "eval_loss": 0.4952092468738556,
      "eval_runtime": 3.2798,
      "eval_samples_per_second": 90.86,
      "eval_steps_per_second": 11.586,
      "step": 54
    }
  ],
  "logging_steps": 500,
  "max_steps": 54,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7850630085120000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}