trainer_state.json

{
  "best_metric": 0.8930666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0793/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": 2.7151869176294504e-05,
      "loss": 2.136,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7925333333333333,
      "eval_loss": 0.9663940072059631,
      "eval_runtime": 12.674,
      "eval_samples_per_second": 295.881,
      "eval_steps_per_second": 4.655,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 1.968905659703686e-05,
      "loss": 0.6295,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8626666666666667,
      "eval_loss": 0.5589256286621094,
      "eval_runtime": 12.0701,
      "eval_samples_per_second": 310.685,
      "eval_steps_per_second": 4.888,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.789754331111908,
      "learning_rate": 1.041861277497315e-05,
      "loss": 0.3035,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8816,
      "eval_loss": 0.44396281242370605,
      "eval_runtime": 11.9555,
      "eval_samples_per_second": 313.662,
      "eval_steps_per_second": 4.935,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.2037582397460938,
      "learning_rate": 2.89810315724514e-06,
      "loss": 0.1589,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8909333333333334,
      "eval_loss": 0.40557777881622314,
      "eval_runtime": 11.7173,
      "eval_samples_per_second": 320.04,
      "eval_steps_per_second": 5.035,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 2.403111285115278e-10,
      "loss": 0.1074,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.397757887840271,
      "eval_runtime": 11.8731,
      "eval_samples_per_second": 315.841,
      "eval_steps_per_second": 4.969,
      "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
}