trainer_state.json

{
  "best_metric": 0.8826666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0343/checkpoints/checkpoint-999",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 999,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 6.437816619873047,
      "learning_rate": 0.0003,
      "loss": 0.6289,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.4279367923736572,
      "eval_runtime": 5.7369,
      "eval_samples_per_second": 653.66,
      "eval_steps_per_second": 10.284,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.33238303661346436,
      "learning_rate": 0.0003,
      "loss": 0.2915,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.44390612840652466,
      "eval_runtime": 5.9621,
      "eval_samples_per_second": 628.97,
      "eval_steps_per_second": 9.896,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 0.2166,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8826666666666667,
      "eval_loss": 0.41818171739578247,
      "eval_runtime": 5.624,
      "eval_samples_per_second": 666.78,
      "eval_steps_per_second": 10.491,
      "step": 999
    }
  ],
  "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": 4.94223961867776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}