trainer_state.json

{
  "best_metric": 0.896,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0248/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": 4.667026293130983e-05,
      "loss": 1.7431,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8106666666666666,
      "eval_loss": 0.7301185131072998,
      "eval_runtime": 10.6985,
      "eval_samples_per_second": 350.515,
      "eval_steps_per_second": 5.515,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.668601036071777,
      "learning_rate": 3.7534027314690145e-05,
      "loss": 0.5061,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8541333333333333,
      "eval_loss": 0.523736834526062,
      "eval_runtime": 10.9628,
      "eval_samples_per_second": 342.066,
      "eval_steps_per_second": 5.382,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.960692882537842,
      "learning_rate": 2.5039309201189614e-05,
      "loss": 0.2695,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8765333333333334,
      "eval_loss": 0.4273153245449066,
      "eval_runtime": 10.8768,
      "eval_samples_per_second": 344.769,
      "eval_steps_per_second": 5.424,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 1.2568147258031899e-05,
      "loss": 0.1375,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8912,
      "eval_loss": 0.3883265554904938,
      "eval_runtime": 10.8953,
      "eval_samples_per_second": 344.185,
      "eval_steps_per_second": 5.415,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.06047523021698,
      "learning_rate": 3.388781113503378e-06,
      "loss": 0.0703,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.3656786382198334,
      "eval_runtime": 10.9467,
      "eval_samples_per_second": 342.567,
      "eval_steps_per_second": 5.39,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.6487840414047241,
      "learning_rate": 1.2361706385188855e-10,
      "loss": 0.0433,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.36073243618011475,
      "eval_runtime": 10.7543,
      "eval_samples_per_second": 348.698,
      "eval_steps_per_second": 5.486,
      "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
}