trainer_state.json

{
  "best_metric": 0.8688,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0816/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "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": 0.0001,
      "loss": 1.64,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7994666666666667,
      "eval_loss": 0.7275334000587463,
      "eval_runtime": 10.6154,
      "eval_samples_per_second": 353.261,
      "eval_steps_per_second": 5.558,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5458444952964783,
      "learning_rate": 0.0001,
      "loss": 0.5209,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8282666666666667,
      "eval_loss": 0.560183584690094,
      "eval_runtime": 10.527,
      "eval_samples_per_second": 356.226,
      "eval_steps_per_second": 5.605,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.3218,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8552,
      "eval_loss": 0.4948236048221588,
      "eval_runtime": 11.1202,
      "eval_samples_per_second": 337.224,
      "eval_steps_per_second": 5.306,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2560613453388214,
      "learning_rate": 0.0001,
      "loss": 0.2194,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8653333333333333,
      "eval_loss": 0.46796751022338867,
      "eval_runtime": 10.589,
      "eval_samples_per_second": 354.142,
      "eval_steps_per_second": 5.572,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.8315297365188599,
      "learning_rate": 0.0001,
      "loss": 0.1639,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8688,
      "eval_loss": 0.464568555355072,
      "eval_runtime": 11.0521,
      "eval_samples_per_second": 339.303,
      "eval_steps_per_second": 5.338,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}