trainer_state.json

{
  "best_metric": 0.8208,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0724/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": 0.0002501501501501501,
      "loss": 3.0156,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.31706666666666666,
      "eval_loss": 2.449779748916626,
      "eval_runtime": 8.1795,
      "eval_samples_per_second": 458.465,
      "eval_steps_per_second": 7.213,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002003003003003003,
      "loss": 1.9448,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5842666666666667,
      "eval_loss": 1.4168325662612915,
      "eval_runtime": 6.62,
      "eval_samples_per_second": 566.465,
      "eval_steps_per_second": 8.912,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00015045045045045046,
      "loss": 1.0513,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7146666666666667,
      "eval_loss": 0.9265748858451843,
      "eval_runtime": 6.1301,
      "eval_samples_per_second": 611.737,
      "eval_steps_per_second": 9.625,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.117168426513672,
      "learning_rate": 0.00010045045045045045,
      "loss": 0.5727,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7722666666666667,
      "eval_loss": 0.7340477108955383,
      "eval_runtime": 6.3511,
      "eval_samples_per_second": 590.45,
      "eval_steps_per_second": 9.29,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.743118286132812,
      "learning_rate": 5.045045045045045e-05,
      "loss": 0.286,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8013333333333333,
      "eval_loss": 0.6528049111366272,
      "eval_runtime": 6.0522,
      "eval_samples_per_second": 619.605,
      "eval_steps_per_second": 9.748,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5587590932846069,
      "learning_rate": 4.5045045045045043e-07,
      "loss": 0.1176,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8208,
      "eval_loss": 0.6041161417961121,
      "eval_runtime": 6.4573,
      "eval_samples_per_second": 580.737,
      "eval_steps_per_second": 9.137,
      "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
}