trainer_state.json

{
  "best_metric": 0.7688896035898256,
  "best_model_checkpoint": "../../checkpoint/unlearn/nlvr2/vilt/neggrad/4.0/42/checkpoint-216",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 216,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "df_accuracy": 0.7047563805104409,
      "dt_accuracy": 0.633772558006302,
      "epoch": 1.0,
      "eval_accuracy": 0.633772558006302,
      "eval_loss": -2.188958168029785,
      "eval_runtime": 116.9837,
      "eval_samples_per_second": 59.684,
      "eval_steps_per_second": 0.94,
      "eval_unlearn_overall_accuracy": 0.7293464134713471,
      "step": 108,
      "unlearn_overall_accuracy": 0.7293464134713471,
      "unlearn_time": null
    },
    {
      "df_accuracy": 0.599477958236659,
      "dt_accuracy": 0.5726152964766542,
      "epoch": 2.0,
      "eval_accuracy": 0.5726152964766542,
      "eval_loss": -4.517490386962891,
      "eval_runtime": 111.3878,
      "eval_samples_per_second": 62.682,
      "eval_steps_per_second": 0.988,
      "eval_unlearn_overall_accuracy": 0.7688896035898256,
      "step": 216,
      "unlearn_overall_accuracy": 0.7688896035898256,
      "unlearn_time": null
    },
    {
      "epoch": 2.0,
      "step": 216,
      "total_flos": 132920773473312.0,
      "train_loss": -1.7315052173755787,
      "train_runtime": 553.6478,
      "train_samples_per_second": 12.456,
      "train_steps_per_second": 0.39
    }
  ],
  "logging_steps": 500,
  "max_steps": 216,
  "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": 132920773473312.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}