trainer_state.json

{
  "best_metric": 0.8482666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0366/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": 0.0001,
      "loss": 1.675,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7714666666666666,
      "eval_loss": 0.792111873626709,
      "eval_runtime": 6.0812,
      "eval_samples_per_second": 616.657,
      "eval_steps_per_second": 9.702,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2579768896102905,
      "learning_rate": 0.0001,
      "loss": 0.5154,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8005333333333333,
      "eval_loss": 0.6609722375869751,
      "eval_runtime": 7.2598,
      "eval_samples_per_second": 516.546,
      "eval_steps_per_second": 8.127,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.757699966430664,
      "learning_rate": 0.0001,
      "loss": 0.3211,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8394666666666667,
      "eval_loss": 0.5632932782173157,
      "eval_runtime": 6.2091,
      "eval_samples_per_second": 603.948,
      "eval_steps_per_second": 9.502,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.12245410680770874,
      "learning_rate": 0.0001,
      "loss": 0.2141,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8461333333333333,
      "eval_loss": 0.5328806042671204,
      "eval_runtime": 6.4269,
      "eval_samples_per_second": 583.481,
      "eval_steps_per_second": 9.18,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.099757194519043,
      "learning_rate": 0.0001,
      "loss": 0.149,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8373333333333334,
      "eval_loss": 0.5904111862182617,
      "eval_runtime": 7.2006,
      "eval_samples_per_second": 520.789,
      "eval_steps_per_second": 8.194,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.1694109439849854,
      "learning_rate": 0.0001,
      "loss": 0.1195,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8482666666666666,
      "eval_loss": 0.55458003282547,
      "eval_runtime": 7.0687,
      "eval_samples_per_second": 530.506,
      "eval_steps_per_second": 8.347,
      "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
}