trainer_state.json

{
  "best_metric": 0.5074666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0733/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 3.258,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20906666666666668,
      "eval_loss": 2.958405017852783,
      "eval_runtime": 13.5056,
      "eval_samples_per_second": 277.662,
      "eval_steps_per_second": 4.369,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.6556,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.33013333333333333,
      "eval_loss": 2.4403469562530518,
      "eval_runtime": 13.5496,
      "eval_samples_per_second": 276.762,
      "eval_steps_per_second": 4.354,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.679930686950684,
      "learning_rate": 0.0005,
      "loss": 2.2322,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3552,
      "eval_loss": 2.315427780151367,
      "eval_runtime": 13.4905,
      "eval_samples_per_second": 277.972,
      "eval_steps_per_second": 4.373,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.9072,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.43733333333333335,
      "eval_loss": 1.972715973854065,
      "eval_runtime": 13.5251,
      "eval_samples_per_second": 277.262,
      "eval_steps_per_second": 4.362,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.668185234069824,
      "learning_rate": 0.0005,
      "loss": 1.6421,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.48533333333333334,
      "eval_loss": 1.8231148719787598,
      "eval_runtime": 14.5254,
      "eval_samples_per_second": 258.169,
      "eval_steps_per_second": 4.062,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 11.400856971740723,
      "learning_rate": 0.0005,
      "loss": 1.411,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5074666666666666,
      "eval_loss": 1.698462724685669,
      "eval_runtime": 13.14,
      "eval_samples_per_second": 285.389,
      "eval_steps_per_second": 4.49,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}