trainer_state.json

{
  "best_global_step": 2676,
  "best_metric": 0.8758664146187776,
  "best_model_checkpoint": "outputs/bartpho-spam-classification/checkpoint-2676",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 2676,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.313131093978882,
      "learning_rate": 4.998771926094749e-05,
      "loss": 0.5553,
      "step": 446
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8481411468178954,
      "eval_loss": 0.501715898513794,
      "eval_runtime": 19.5798,
      "eval_samples_per_second": 81.053,
      "eval_steps_per_second": 2.554,
      "step": 446
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.692811489105225,
      "learning_rate": 4.995077872180951e-05,
      "loss": 0.3899,
      "step": 892
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8714555765595463,
      "eval_loss": 0.3934585750102997,
      "eval_runtime": 19.1661,
      "eval_samples_per_second": 82.802,
      "eval_steps_per_second": 2.609,
      "step": 892
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.594137668609619,
      "learning_rate": 4.988921477641713e-05,
      "loss": 0.3215,
      "step": 1338
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8601134215500945,
      "eval_loss": 0.3846301734447479,
      "eval_runtime": 19.2177,
      "eval_samples_per_second": 82.58,
      "eval_steps_per_second": 2.602,
      "step": 1338
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.4350204467773438,
      "learning_rate": 4.980308818095173e-05,
      "loss": 0.2683,
      "step": 1784
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.870825456836799,
      "eval_loss": 0.3831605613231659,
      "eval_runtime": 19.1852,
      "eval_samples_per_second": 82.72,
      "eval_steps_per_second": 2.606,
      "step": 1784
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.810039222240448,
      "learning_rate": 4.9692483931964865e-05,
      "loss": 0.2299,
      "step": 2230
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8588531821045998,
      "eval_loss": 0.4099101722240448,
      "eval_runtime": 19.2163,
      "eval_samples_per_second": 82.586,
      "eval_steps_per_second": 2.602,
      "step": 2230
    },
    {
      "epoch": 6.0,
      "grad_norm": 13.190986633300781,
      "learning_rate": 4.9557511182496865e-05,
      "loss": 0.197,
      "step": 2676
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8758664146187776,
      "eval_loss": 0.4323248565196991,
      "eval_runtime": 19.3663,
      "eval_samples_per_second": 81.946,
      "eval_steps_per_second": 2.582,
      "step": 2676
    }
  ],
  "logging_steps": 446,
  "max_steps": 44600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.576050512345894e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}