trainer_state.json

{
  "best_metric": 0.8573333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0457/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": 0.0002501501501501501,
      "loss": 2.7894,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4976,
      "eval_loss": 1.7845780849456787,
      "eval_runtime": 4.4948,
      "eval_samples_per_second": 834.3,
      "eval_steps_per_second": 13.126,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002003003003003003,
      "loss": 1.1776,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7237333333333333,
      "eval_loss": 0.9345966577529907,
      "eval_runtime": 7.7952,
      "eval_samples_per_second": 481.063,
      "eval_steps_per_second": 7.569,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.049973964691162,
      "learning_rate": 0.00015030030030030027,
      "loss": 0.6227,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7842666666666667,
      "eval_loss": 0.7131213545799255,
      "eval_runtime": 5.73,
      "eval_samples_per_second": 654.447,
      "eval_steps_per_second": 10.297,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.492241382598877,
      "learning_rate": 0.00010030030030030029,
      "loss": 0.3464,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8226666666666667,
      "eval_loss": 0.5808796286582947,
      "eval_runtime": 4.5883,
      "eval_samples_per_second": 817.293,
      "eval_steps_per_second": 12.859,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.11807632446289,
      "learning_rate": 5.0300300300300295e-05,
      "loss": 0.1683,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8416,
      "eval_loss": 0.5357543230056763,
      "eval_runtime": 4.6145,
      "eval_samples_per_second": 812.65,
      "eval_steps_per_second": 12.786,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.4961423873901367,
      "learning_rate": 3.0030030030030027e-07,
      "loss": 0.0676,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.49083730578422546,
      "eval_runtime": 4.4879,
      "eval_samples_per_second": 835.589,
      "eval_steps_per_second": 13.147,
      "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
}