trainer_state.json

{
  "best_metric": 0.8792,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0789/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": Infinity,
      "learning_rate": 9e-05,
      "loss": 1.4628,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8293333333333334,
      "eval_loss": 0.636850118637085,
      "eval_runtime": 6.3717,
      "eval_samples_per_second": 588.541,
      "eval_steps_per_second": 9.26,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.4584,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8608,
      "eval_loss": 0.48297494649887085,
      "eval_runtime": 6.3942,
      "eval_samples_per_second": 586.468,
      "eval_steps_per_second": 9.227,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.21803274750709534,
      "learning_rate": 9e-05,
      "loss": 0.2673,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8792,
      "eval_loss": 0.42867910861968994,
      "eval_runtime": 6.379,
      "eval_samples_per_second": 587.871,
      "eval_steps_per_second": 9.249,
      "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
}