trainer_state.json

{
  "best_metric": 0.7753855683267761,
  "best_model_checkpoint": "../../checkpoint/unlearn/nlvr2/vilt/neggrad/6.0/42/checkpoint-324",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 324,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "df_accuracy": 0.6167826759474091,
      "dt_accuracy": 0.5743340017187052,
      "epoch": 1.0,
      "eval_accuracy": 0.5743340017187052,
      "eval_loss": -6.072656631469727,
      "eval_runtime": 133.2462,
      "eval_samples_per_second": 52.399,
      "eval_steps_per_second": 0.826,
      "eval_unlearn_overall_accuracy": 0.7600426019888966,
      "step": 162,
      "unlearn_overall_accuracy": 0.7600426019888966,
      "unlearn_time": null
    },
    {
      "df_accuracy": 0.5251353441608662,
      "dt_accuracy": 0.510312231452306,
      "epoch": 2.0,
      "eval_accuracy": 0.510312231452306,
      "eval_loss": -9.328475952148438,
      "eval_runtime": 142.9741,
      "eval_samples_per_second": 48.834,
      "eval_steps_per_second": 0.769,
      "eval_unlearn_overall_accuracy": 0.7753855683267761,
      "step": 324,
      "unlearn_overall_accuracy": 0.7753855683267761,
      "unlearn_time": null
    },
    {
      "epoch": 2.0,
      "step": 324,
      "total_flos": 202934053478640.0,
      "train_loss": -5.162847448278357,
      "train_runtime": 710.5088,
      "train_samples_per_second": 14.559,
      "train_steps_per_second": 0.456
    }
  ],
  "logging_steps": 500,
  "max_steps": 324,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 202934053478640.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}