trainer_state.json

{
  "best_metric": 0.8949333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0932/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": 8.404170694504206e-05,
      "loss": 1.5716,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7944,
      "eval_loss": 0.7472613453865051,
      "eval_runtime": 7.4492,
      "eval_samples_per_second": 503.412,
      "eval_steps_per_second": 7.92,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 43.333919525146484,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.4943,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8538666666666667,
      "eval_loss": 0.5044140219688416,
      "eval_runtime": 7.0171,
      "eval_samples_per_second": 534.409,
      "eval_steps_per_second": 8.408,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3883391320705414,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.2613,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8626666666666667,
      "eval_loss": 0.45636817812919617,
      "eval_runtime": 6.2526,
      "eval_samples_per_second": 599.75,
      "eval_steps_per_second": 9.436,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5637422800064087,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.1229,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8834666666666666,
      "eval_loss": 0.4139169454574585,
      "eval_runtime": 6.0611,
      "eval_samples_per_second": 618.699,
      "eval_steps_per_second": 9.734,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4455867409706116,
      "learning_rate": 6.099806004306081e-06,
      "loss": 0.0531,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.39703983068466187,
      "eval_runtime": 6.4079,
      "eval_samples_per_second": 585.213,
      "eval_steps_per_second": 9.207,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.3999329209327698,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0261,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.3788720369338989,
      "eval_runtime": 6.0957,
      "eval_samples_per_second": 615.188,
      "eval_steps_per_second": 9.679,
      "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
}