trainer_state.json

{
  "best_metric": 0.836,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0802/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "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": 0.00027168440174204405,
      "loss": 2.6754,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5469333333333334,
      "eval_loss": 1.5820661783218384,
      "eval_runtime": 6.2573,
      "eval_samples_per_second": 599.303,
      "eval_steps_per_second": 9.429,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00019715932444832964,
      "loss": 1.0787,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7138666666666666,
      "eval_loss": 0.9243953227996826,
      "eval_runtime": 7.3246,
      "eval_samples_per_second": 511.976,
      "eval_steps_per_second": 8.055,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.210020065307617,
      "learning_rate": 0.00010445571134029838,
      "loss": 0.5154,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7906666666666666,
      "eval_loss": 0.6684121489524841,
      "eval_runtime": 6.8075,
      "eval_samples_per_second": 550.86,
      "eval_steps_per_second": 8.667,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.23784585297107697,
      "learning_rate": 2.9148468506836763e-05,
      "loss": 0.2041,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8256,
      "eval_loss": 0.5682529807090759,
      "eval_runtime": 6.2658,
      "eval_samples_per_second": 598.486,
      "eval_steps_per_second": 9.416,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7714911699295044,
      "learning_rate": 2.4031112851152778e-09,
      "loss": 0.0757,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.836,
      "eval_loss": 0.5437429547309875,
      "eval_runtime": 6.3244,
      "eval_samples_per_second": 592.937,
      "eval_steps_per_second": 9.329,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}