{
  "best_metric": 0.5109333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0955/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 3.2209,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22933333333333333,
      "eval_loss": 2.816185474395752,
      "eval_runtime": 6.1164,
      "eval_samples_per_second": 613.102,
      "eval_steps_per_second": 9.646,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.5763,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.32133333333333336,
      "eval_loss": 2.4535651206970215,
      "eval_runtime": 6.1359,
      "eval_samples_per_second": 611.155,
      "eval_steps_per_second": 9.616,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 17.522342681884766,
      "learning_rate": 0.0005,
      "loss": 2.2056,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.37306666666666666,
      "eval_loss": 2.245544195175171,
      "eval_runtime": 6.6697,
      "eval_samples_per_second": 562.24,
      "eval_steps_per_second": 8.846,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 13.784343719482422,
      "learning_rate": 0.0005,
      "loss": 1.9072,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.416,
      "eval_loss": 2.0452396869659424,
      "eval_runtime": 6.2176,
      "eval_samples_per_second": 603.126,
      "eval_steps_per_second": 9.489,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.065598487854004,
      "learning_rate": 0.0005,
      "loss": 1.649,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4613333333333333,
      "eval_loss": 1.9154818058013916,
      "eval_runtime": 6.0828,
      "eval_samples_per_second": 616.49,
      "eval_steps_per_second": 9.699,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 15.944914817810059,
      "learning_rate": 0.0005,
      "loss": 1.4019,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5074666666666666,
      "eval_loss": 1.7350648641586304,
      "eval_runtime": 6.1775,
      "eval_samples_per_second": 607.045,
      "eval_steps_per_second": 9.551,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.1493,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5109333333333334,
      "eval_loss": 1.7197198867797852,
      "eval_runtime": 6.4104,
      "eval_samples_per_second": 584.983,
      "eval_steps_per_second": 9.204,
      "step": 2331
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}