{
  "best_metric": 0.9066666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0588/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 97.33380126953125,
      "learning_rate": 9e-05,
      "loss": 2.8076,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7506666666666667,
      "eval_loss": 0.9585511684417725,
      "eval_runtime": 7.7382,
      "eval_samples_per_second": 484.607,
      "eval_steps_per_second": 7.624,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 108.16813659667969,
      "learning_rate": 9e-05,
      "loss": 0.6805,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.4883612096309662,
      "eval_runtime": 7.6943,
      "eval_samples_per_second": 487.372,
      "eval_steps_per_second": 7.668,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 108.57462310791016,
      "learning_rate": 9e-05,
      "loss": 0.3678,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.3836047649383545,
      "eval_runtime": 7.7525,
      "eval_samples_per_second": 483.714,
      "eval_steps_per_second": 7.61,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 78.8430404663086,
      "learning_rate": 9e-05,
      "loss": 0.2308,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8896,
      "eval_loss": 0.3517357409000397,
      "eval_runtime": 7.6974,
      "eval_samples_per_second": 487.177,
      "eval_steps_per_second": 7.665,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 46.916133880615234,
      "learning_rate": 9e-05,
      "loss": 0.1537,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8978666666666667,
      "eval_loss": 0.35816413164138794,
      "eval_runtime": 7.6692,
      "eval_samples_per_second": 488.967,
      "eval_steps_per_second": 7.693,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 152.3602752685547,
      "learning_rate": 9e-05,
      "loss": 0.1,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8957333333333334,
      "eval_loss": 0.36731621623039246,
      "eval_runtime": 7.7582,
      "eval_samples_per_second": 483.36,
      "eval_steps_per_second": 7.605,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 94.79269409179688,
      "learning_rate": 9e-05,
      "loss": 0.0693,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8986666666666666,
      "eval_loss": 0.37170448899269104,
      "eval_runtime": 7.7299,
      "eval_samples_per_second": 485.131,
      "eval_steps_per_second": 7.633,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 131.6165771484375,
      "learning_rate": 9e-05,
      "loss": 0.0507,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9029333333333334,
      "eval_loss": 0.3868400454521179,
      "eval_runtime": 7.7699,
      "eval_samples_per_second": 482.631,
      "eval_steps_per_second": 7.593,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 173.9136962890625,
      "learning_rate": 9e-05,
      "loss": 0.0344,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9066666666666666,
      "eval_loss": 0.4204305410385132,
      "eval_runtime": 8.0957,
      "eval_samples_per_second": 463.211,
      "eval_steps_per_second": 7.288,
      "step": 2997
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 7.3587863155968e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}