trainer_state.json

{
  "best_metric": 0.9154666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0205/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "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": 9.334052586261965e-05,
      "loss": 1.4766,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8229333333333333,
      "eval_loss": 0.6381331086158752,
      "eval_runtime": 8.994,
      "eval_samples_per_second": 416.947,
      "eval_steps_per_second": 6.56,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.460555076599121,
      "learning_rate": 7.506805462938029e-05,
      "loss": 0.4773,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8453333333333334,
      "eval_loss": 0.515312135219574,
      "eval_runtime": 7.2921,
      "eval_samples_per_second": 514.258,
      "eval_steps_per_second": 8.091,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7851970195770264,
      "learning_rate": 5.007861840237923e-05,
      "loss": 0.2656,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.39872846007347107,
      "eval_runtime": 8.5955,
      "eval_samples_per_second": 436.273,
      "eval_steps_per_second": 6.864,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.10811267793178558,
      "learning_rate": 2.506811643795042e-05,
      "loss": 0.1409,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9101333333333333,
      "eval_loss": 0.3156787157058716,
      "eval_runtime": 8.1902,
      "eval_samples_per_second": 457.862,
      "eval_steps_per_second": 7.204,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2761382758617401,
      "learning_rate": 6.738092539759589e-06,
      "loss": 0.066,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9146666666666666,
      "eval_loss": 0.29083430767059326,
      "eval_runtime": 8.0122,
      "eval_samples_per_second": 468.034,
      "eval_steps_per_second": 7.364,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.07646141946315765,
      "learning_rate": 6.180857012871855e-11,
      "loss": 0.0362,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.2839570939540863,
      "eval_runtime": 7.4593,
      "eval_samples_per_second": 502.727,
      "eval_steps_per_second": 7.91,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}