{
  "best_metric": 0.8605333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0358/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": 123.05419158935547,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.7869,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6941333333333334,
      "eval_loss": 1.096413254737854,
      "eval_runtime": 12.2511,
      "eval_samples_per_second": 306.096,
      "eval_steps_per_second": 4.816,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 127.63580322265625,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8277,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8181333333333334,
      "eval_loss": 0.6002026796340942,
      "eval_runtime": 12.3491,
      "eval_samples_per_second": 303.665,
      "eval_steps_per_second": 4.778,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 89.41055297851562,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4888,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8432,
      "eval_loss": 0.5089566111564636,
      "eval_runtime": 12.3163,
      "eval_samples_per_second": 304.475,
      "eval_steps_per_second": 4.79,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 151.60887145996094,
      "learning_rate": 5e-05,
      "loss": 0.3261,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8541333333333333,
      "eval_loss": 0.4775138199329376,
      "eval_runtime": 12.1918,
      "eval_samples_per_second": 307.583,
      "eval_steps_per_second": 4.839,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 81.08171844482422,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2365,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8581333333333333,
      "eval_loss": 0.4748378396034241,
      "eval_runtime": 12.1882,
      "eval_samples_per_second": 307.676,
      "eval_steps_per_second": 4.841,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 111.4124526977539,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1818,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.4692835211753845,
      "eval_runtime": 12.3429,
      "eval_samples_per_second": 303.818,
      "eval_steps_per_second": 4.78,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 122.20268249511719,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1562,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.46515220403671265,
      "eval_runtime": 12.4492,
      "eval_samples_per_second": 301.224,
      "eval_steps_per_second": 4.739,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 59.389976501464844,
      "learning_rate": 0.0,
      "loss": 0.144,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8605333333333334,
      "eval_loss": 0.45601600408554077,
      "eval_runtime": 12.2772,
      "eval_samples_per_second": 305.444,
      "eval_steps_per_second": 4.806,
      "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": 6.5411433916416e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}