trainer_state.json

{
  "best_metric": 0.8962666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0978/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": 63.72509002685547,
      "learning_rate": 0.0003,
      "loss": 1.6046,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8362666666666667,
      "eval_loss": 0.5640226602554321,
      "eval_runtime": 7.5362,
      "eval_samples_per_second": 497.596,
      "eval_steps_per_second": 7.829,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 34.684120178222656,
      "learning_rate": 0.0003,
      "loss": 0.4612,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8768,
      "eval_loss": 0.43462520837783813,
      "eval_runtime": 10.5714,
      "eval_samples_per_second": 354.73,
      "eval_steps_per_second": 5.581,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 31.166889190673828,
      "learning_rate": 0.0003,
      "loss": 0.2792,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8784,
      "eval_loss": 0.43042242527008057,
      "eval_runtime": 7.5781,
      "eval_samples_per_second": 494.846,
      "eval_steps_per_second": 7.786,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.19539451599121,
      "learning_rate": 0.0003,
      "loss": 0.191,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8853333333333333,
      "eval_loss": 0.4280374050140381,
      "eval_runtime": 7.5176,
      "eval_samples_per_second": 498.832,
      "eval_steps_per_second": 7.848,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 51.59762954711914,
      "learning_rate": 0.0003,
      "loss": 0.1412,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8928,
      "eval_loss": 0.40242862701416016,
      "eval_runtime": 7.7756,
      "eval_samples_per_second": 482.277,
      "eval_steps_per_second": 7.588,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 25.331348419189453,
      "learning_rate": 0.0003,
      "loss": 0.1124,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8912,
      "eval_loss": 0.4451484978199005,
      "eval_runtime": 7.8383,
      "eval_samples_per_second": 478.419,
      "eval_steps_per_second": 7.527,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 32.85719680786133,
      "learning_rate": 0.0003,
      "loss": 0.0913,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8938666666666667,
      "eval_loss": 0.47252288460731506,
      "eval_runtime": 7.8038,
      "eval_samples_per_second": 480.538,
      "eval_steps_per_second": 7.56,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 23.29495620727539,
      "learning_rate": 0.0003,
      "loss": 0.0706,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8962666666666667,
      "eval_loss": 0.45104479789733887,
      "eval_runtime": 7.5744,
      "eval_samples_per_second": 495.088,
      "eval_steps_per_second": 7.789,
      "step": 2664
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.5411433916416e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}