trainer_state.json

{
  "best_metric": 0.9018666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0090/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": 8.006006006006006e-05,
      "loss": 1.4901,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7922666666666667,
      "eval_loss": 0.709791362285614,
      "eval_runtime": 12.8059,
      "eval_samples_per_second": 292.835,
      "eval_steps_per_second": 4.607,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.966662883758545,
      "learning_rate": 6.0060060060060066e-05,
      "loss": 0.4837,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.5055909156799316,
      "eval_runtime": 12.509,
      "eval_samples_per_second": 299.784,
      "eval_steps_per_second": 4.717,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6543020606040955,
      "learning_rate": 4.006006006006006e-05,
      "loss": 0.283,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.39790311455726624,
      "eval_runtime": 12.7735,
      "eval_samples_per_second": 293.578,
      "eval_steps_per_second": 4.619,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.15494704246520996,
      "learning_rate": 2.006006006006006e-05,
      "loss": 0.1597,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8893333333333333,
      "eval_loss": 0.3660403788089752,
      "eval_runtime": 13.0364,
      "eval_samples_per_second": 287.656,
      "eval_steps_per_second": 4.526,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.14163607358932495,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.0853,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9018666666666667,
      "eval_loss": 0.341339647769928,
      "eval_runtime": 12.7349,
      "eval_samples_per_second": 294.466,
      "eval_steps_per_second": 4.633,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}