trainer_state.json

{
  "best_metric": 0.5056,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0980/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": 0.00041691691691691694,
      "loss": 3.2875,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.23173333333333335,
      "eval_loss": 2.883394718170166,
      "eval_runtime": 6.4972,
      "eval_samples_per_second": 577.174,
      "eval_steps_per_second": 9.081,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00033383383383383386,
      "loss": 2.7501,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3072,
      "eval_loss": 2.539987802505493,
      "eval_runtime": 6.0753,
      "eval_samples_per_second": 617.249,
      "eval_steps_per_second": 9.711,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.977213859558105,
      "learning_rate": 0.0002505005005005005,
      "loss": 2.3767,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.38906666666666667,
      "eval_loss": 2.2095041275024414,
      "eval_runtime": 5.8429,
      "eval_samples_per_second": 641.807,
      "eval_steps_per_second": 10.098,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.92343807220459,
      "learning_rate": 0.00016716716716716717,
      "loss": 1.9882,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.42506666666666665,
      "eval_loss": 2.0708136558532715,
      "eval_runtime": 5.4509,
      "eval_samples_per_second": 687.962,
      "eval_steps_per_second": 10.824,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 8.408408408408409e-05,
      "loss": 1.5515,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4872,
      "eval_loss": 1.865002989768982,
      "eval_runtime": 5.9252,
      "eval_samples_per_second": 632.89,
      "eval_steps_per_second": 9.957,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 38.75450134277344,
      "learning_rate": 7.507507507507508e-07,
      "loss": 1.0298,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5056,
      "eval_loss": 1.79682195186615,
      "eval_runtime": 6.1984,
      "eval_samples_per_second": 604.992,
      "eval_steps_per_second": 9.519,
      "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
}