trainer_state.json

{
  "best_metric": 0.908,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0845/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": 9.334052586261965e-05,
      "loss": 1.4694,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8144,
      "eval_loss": 0.6641395688056946,
      "eval_runtime": 12.4634,
      "eval_samples_per_second": 300.882,
      "eval_steps_per_second": 4.734,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2965881824493408,
      "learning_rate": 7.506805462938029e-05,
      "loss": 0.4377,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.48361608386039734,
      "eval_runtime": 12.4609,
      "eval_samples_per_second": 300.941,
      "eval_steps_per_second": 4.735,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.34195148944854736,
      "learning_rate": 5.007861840237923e-05,
      "loss": 0.2319,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.423612117767334,
      "eval_runtime": 12.3469,
      "eval_samples_per_second": 303.719,
      "eval_steps_per_second": 4.779,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.676865100860596,
      "learning_rate": 2.506811643795042e-05,
      "loss": 0.1104,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8968,
      "eval_loss": 0.3474545478820801,
      "eval_runtime": 12.3069,
      "eval_samples_per_second": 304.707,
      "eval_steps_per_second": 4.794,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.110002800822258,
      "learning_rate": 6.738092539759589e-06,
      "loss": 0.0442,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9066666666666666,
      "eval_loss": 0.3390645384788513,
      "eval_runtime": 12.1511,
      "eval_samples_per_second": 308.614,
      "eval_steps_per_second": 4.856,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.6407166123390198,
      "learning_rate": 6.180857012871855e-11,
      "loss": 0.024,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.908,
      "eval_loss": 0.3385367691516876,
      "eval_runtime": 12.2786,
      "eval_samples_per_second": 305.41,
      "eval_steps_per_second": 4.805,
      "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
}