trainer_state.json

{
  "best_metric": 0.7432105595024853,
  "best_model_checkpoint": "../../checkpoint/unlearn/nlvr2/vilt/neggrad/2.0/42/checkpoint-108",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 108,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "df_accuracy": 0.7894431554524362,
      "dt_accuracy": 0.6675737610999714,
      "epoch": 1.0,
      "eval_accuracy": 0.6675737610999714,
      "eval_loss": -1.414046287536621,
      "eval_runtime": 130.7248,
      "eval_samples_per_second": 53.41,
      "eval_steps_per_second": 0.841,
      "eval_unlearn_overall_accuracy": 0.6787095617894726,
      "step": 54,
      "unlearn_overall_accuracy": 0.6787095617894726,
      "unlearn_time": null
    },
    {
      "df_accuracy": 0.6554524361948956,
      "dt_accuracy": 0.5876539673446004,
      "epoch": 2.0,
      "eval_accuracy": 0.5876539673446004,
      "eval_loss": -2.8545327186584473,
      "eval_runtime": 123.4384,
      "eval_samples_per_second": 56.563,
      "eval_steps_per_second": 0.891,
      "eval_unlearn_overall_accuracy": 0.7432105595024853,
      "step": 108,
      "unlearn_overall_accuracy": 0.7432105595024853,
      "unlearn_time": null
    },
    {
      "epoch": 2.0,
      "step": 108,
      "total_flos": 65947866680784.0,
      "train_loss": -0.9861393681278935,
      "train_runtime": 459.1948,
      "train_samples_per_second": 7.509,
      "train_steps_per_second": 0.235
    }
  ],
  "logging_steps": 500,
  "max_steps": 108,
  "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": 65947866680784.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}