trainer_state.json

{
  "best_metric": 0.8976,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0467/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": 4.838174819946289,
      "learning_rate": 6.531088913245535e-05,
      "loss": 1.5021,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8141333333333334,
      "eval_loss": 0.6579926013946533,
      "eval_runtime": 6.4881,
      "eval_samples_per_second": 577.981,
      "eval_steps_per_second": 9.094,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.5673065185546875,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.4109,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8552,
      "eval_loss": 0.47385793924331665,
      "eval_runtime": 6.1323,
      "eval_samples_per_second": 611.511,
      "eval_steps_per_second": 9.621,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.14920677244663239,
      "learning_rate": 3.5e-05,
      "loss": 0.1898,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.4382529854774475,
      "eval_runtime": 6.286,
      "eval_samples_per_second": 596.567,
      "eval_steps_per_second": 9.386,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.1603538542985916,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0787,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8936,
      "eval_loss": 0.3501591682434082,
      "eval_runtime": 6.4576,
      "eval_samples_per_second": 580.708,
      "eval_steps_per_second": 9.136,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.09407216310501099,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0284,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8952,
      "eval_loss": 0.3434438407421112,
      "eval_runtime": 6.6341,
      "eval_samples_per_second": 565.257,
      "eval_steps_per_second": 8.893,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.2326997518539429,
      "learning_rate": 0.0,
      "loss": 0.0144,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8976,
      "eval_loss": 0.34454357624053955,
      "eval_runtime": 6.7304,
      "eval_samples_per_second": 557.17,
      "eval_steps_per_second": 8.766,
      "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
}