trainer_state.json

{
  "best_metric": 0.8128,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0133/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": 0.0003,
      "loss": 1.9552,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7285333333333334,
      "eval_loss": 0.9197421669960022,
      "eval_runtime": 12.1017,
      "eval_samples_per_second": 309.874,
      "eval_steps_per_second": 4.875,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3020102977752686,
      "learning_rate": 0.0003,
      "loss": 0.702,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.756,
      "eval_loss": 0.8105168342590332,
      "eval_runtime": 12.5131,
      "eval_samples_per_second": 299.685,
      "eval_steps_per_second": 4.715,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.242972373962402,
      "learning_rate": 0.0003,
      "loss": 0.4121,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7816,
      "eval_loss": 0.7222737669944763,
      "eval_runtime": 12.0895,
      "eval_samples_per_second": 310.187,
      "eval_steps_per_second": 4.88,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04993444308638573,
      "learning_rate": 0.0003,
      "loss": 0.2764,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7970666666666667,
      "eval_loss": 0.7434040307998657,
      "eval_runtime": 12.3232,
      "eval_samples_per_second": 304.303,
      "eval_steps_per_second": 4.788,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.1096830368041992,
      "learning_rate": 0.0003,
      "loss": 0.2093,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8128,
      "eval_loss": 0.6784113645553589,
      "eval_runtime": 11.0945,
      "eval_samples_per_second": 338.005,
      "eval_steps_per_second": 5.318,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}