trainer_state.json

{
  "best_metric": 0.8754666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0081/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": 5e-05,
      "loss": 0.7974,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8541333333333333,
      "eval_loss": 0.48191913962364197,
      "eval_runtime": 4.4592,
      "eval_samples_per_second": 840.952,
      "eval_steps_per_second": 13.231,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 47.398380279541016,
      "learning_rate": 5e-05,
      "loss": 0.2763,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.45935294032096863,
      "eval_runtime": 4.3169,
      "eval_samples_per_second": 868.686,
      "eval_steps_per_second": 13.667,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 8.391192436218262,
      "learning_rate": 5e-05,
      "loss": 0.1537,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8576,
      "eval_loss": 0.5240299105644226,
      "eval_runtime": 4.3307,
      "eval_samples_per_second": 865.909,
      "eval_steps_per_second": 13.624,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3177042007446289,
      "learning_rate": 5e-05,
      "loss": 0.1095,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8746666666666667,
      "eval_loss": 0.4827200174331665,
      "eval_runtime": 4.3965,
      "eval_samples_per_second": 852.96,
      "eval_steps_per_second": 13.42,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.38675621151924133,
      "learning_rate": 5e-05,
      "loss": 0.0837,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.5795453190803528,
      "eval_runtime": 4.3331,
      "eval_samples_per_second": 865.43,
      "eval_steps_per_second": 13.616,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.38072511553764343,
      "learning_rate": 5e-05,
      "loss": 0.0728,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.5458551049232483,
      "eval_runtime": 4.8073,
      "eval_samples_per_second": 780.062,
      "eval_steps_per_second": 12.273,
      "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
}