{
  "best_metric": 0.9397333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0288/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.701103687286377,
      "learning_rate": 6.733578363789503e-05,
      "loss": 0.7512,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9106666666666666,
      "eval_loss": 0.31429043412208557,
      "eval_runtime": 6.8269,
      "eval_samples_per_second": 549.295,
      "eval_steps_per_second": 8.642,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.08144065737724304,
      "learning_rate": 5.974873734152915e-05,
      "loss": 0.1481,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9245333333333333,
      "eval_loss": 0.2713143527507782,
      "eval_runtime": 6.7183,
      "eval_samples_per_second": 558.175,
      "eval_steps_per_second": 8.782,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0727672427892685,
      "learning_rate": 4.839392013277814e-05,
      "loss": 0.066,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9216,
      "eval_loss": 0.2852186858654022,
      "eval_runtime": 6.7336,
      "eval_samples_per_second": 556.906,
      "eval_steps_per_second": 8.762,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.065272755920887,
      "learning_rate": 3.5e-05,
      "loss": 0.0293,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9197333333333333,
      "eval_loss": 0.30466628074645996,
      "eval_runtime": 6.8017,
      "eval_samples_per_second": 551.336,
      "eval_steps_per_second": 8.674,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.024211270734667778,
      "learning_rate": 2.1606079867221858e-05,
      "loss": 0.0138,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_loss": 0.26452139019966125,
      "eval_runtime": 6.714,
      "eval_samples_per_second": 558.532,
      "eval_steps_per_second": 8.788,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.03639209643006325,
      "learning_rate": 1.0251262658470837e-05,
      "loss": 0.0055,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9330666666666667,
      "eval_loss": 0.27491283416748047,
      "eval_runtime": 6.8773,
      "eval_samples_per_second": 545.272,
      "eval_steps_per_second": 8.579,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 2.6800339785621635e-06,
      "loss": 0.0033,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.252615749835968,
      "eval_runtime": 6.7365,
      "eval_samples_per_second": 556.669,
      "eval_steps_per_second": 8.758,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.09721231460571289,
      "learning_rate": 2.4337126681706066e-11,
      "loss": 0.0027,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9397333333333333,
      "eval_loss": 0.25482192635536194,
      "eval_runtime": 6.6873,
      "eval_samples_per_second": 560.766,
      "eval_steps_per_second": 8.823,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}