trainer_state.json

{
  "best_metric": 0.46453333333333335,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0355/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": 3.2261,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2248,
      "eval_loss": 2.8628854751586914,
      "eval_runtime": 7.0381,
      "eval_samples_per_second": 532.812,
      "eval_steps_per_second": 8.383,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.6098,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2981333333333333,
      "eval_loss": 2.523923873901367,
      "eval_runtime": 6.8518,
      "eval_samples_per_second": 547.301,
      "eval_steps_per_second": 8.611,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 14.214115142822266,
      "learning_rate": 0.0005,
      "loss": 2.2546,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.37706666666666666,
      "eval_loss": 2.2176637649536133,
      "eval_runtime": 6.8731,
      "eval_samples_per_second": 545.605,
      "eval_steps_per_second": 8.584,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.310651779174805,
      "learning_rate": 0.0005,
      "loss": 1.9884,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.388,
      "eval_loss": 2.110666036605835,
      "eval_runtime": 6.8802,
      "eval_samples_per_second": 545.04,
      "eval_steps_per_second": 8.575,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 6.332479953765869,
      "learning_rate": 0.0005,
      "loss": 1.7588,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.42746666666666666,
      "eval_loss": 2.0655078887939453,
      "eval_runtime": 6.8791,
      "eval_samples_per_second": 545.125,
      "eval_steps_per_second": 8.577,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 10.911093711853027,
      "learning_rate": 0.0005,
      "loss": 1.5248,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.46453333333333335,
      "eval_loss": 1.9194852113723755,
      "eval_runtime": 6.8549,
      "eval_samples_per_second": 547.057,
      "eval_steps_per_second": 8.607,
      "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
}