{
  "best_metric": 0.9109333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0478/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": 91.47952270507812,
      "learning_rate": 5e-05,
      "loss": 3.578,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.608,
      "eval_loss": 2.7571327686309814,
      "eval_runtime": 14.7048,
      "eval_samples_per_second": 255.018,
      "eval_steps_per_second": 4.012,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 538.4880981445312,
      "learning_rate": 5e-05,
      "loss": 1.4112,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8154666666666667,
      "eval_loss": 0.7395215034484863,
      "eval_runtime": 15.0007,
      "eval_samples_per_second": 249.988,
      "eval_steps_per_second": 3.933,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 119.97044372558594,
      "learning_rate": 5e-05,
      "loss": 0.6258,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8653333333333333,
      "eval_loss": 0.49489733576774597,
      "eval_runtime": 14.5906,
      "eval_samples_per_second": 257.016,
      "eval_steps_per_second": 4.044,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 86.9740219116211,
      "learning_rate": 5e-05,
      "loss": 0.4365,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8928,
      "eval_loss": 0.39437082409858704,
      "eval_runtime": 14.5258,
      "eval_samples_per_second": 258.161,
      "eval_steps_per_second": 4.062,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 820.2091064453125,
      "learning_rate": 5e-05,
      "loss": 0.3406,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8938666666666667,
      "eval_loss": 0.3751886188983917,
      "eval_runtime": 14.5436,
      "eval_samples_per_second": 257.845,
      "eval_steps_per_second": 4.057,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 151.56661987304688,
      "learning_rate": 5e-05,
      "loss": 0.2619,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8981333333333333,
      "eval_loss": 0.35653412342071533,
      "eval_runtime": 14.5076,
      "eval_samples_per_second": 258.485,
      "eval_steps_per_second": 4.067,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 136.89627075195312,
      "learning_rate": 5e-05,
      "loss": 0.2028,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9048,
      "eval_loss": 0.3290266990661621,
      "eval_runtime": 14.4793,
      "eval_samples_per_second": 258.99,
      "eval_steps_per_second": 4.075,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 211.25003051757812,
      "learning_rate": 5e-05,
      "loss": 0.1716,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9101333333333333,
      "eval_loss": 0.3156541883945465,
      "eval_runtime": 13.8147,
      "eval_samples_per_second": 271.45,
      "eval_steps_per_second": 4.271,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 177.6565399169922,
      "learning_rate": 5e-05,
      "loss": 0.1435,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9109333333333334,
      "eval_loss": 0.31637707352638245,
      "eval_runtime": 14.6103,
      "eval_samples_per_second": 256.668,
      "eval_steps_per_second": 4.038,
      "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
}