trainer_state.json

{
  "best_metric": 0.8896,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0556/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": 5.224538803100586,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.9831,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7818666666666667,
      "eval_loss": 0.9287687540054321,
      "eval_runtime": 13.1743,
      "eval_samples_per_second": 284.644,
      "eval_steps_per_second": 4.478,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.5302629470825195,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.6139,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8434666666666667,
      "eval_loss": 0.588375449180603,
      "eval_runtime": 13.5758,
      "eval_samples_per_second": 276.227,
      "eval_steps_per_second": 4.346,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 2.5039309201189614e-05,
      "loss": 0.3276,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.4822461009025574,
      "eval_runtime": 13.25,
      "eval_samples_per_second": 283.02,
      "eval_steps_per_second": 4.453,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.163284301757812,
      "learning_rate": 1.253405821897521e-05,
      "loss": 0.174,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.876,
      "eval_loss": 0.4212430417537689,
      "eval_runtime": 13.4072,
      "eval_samples_per_second": 279.7,
      "eval_steps_per_second": 4.401,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.8725976943969727,
      "learning_rate": 3.3690462698797944e-06,
      "loss": 0.0938,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.4103996455669403,
      "eval_runtime": 13.1669,
      "eval_samples_per_second": 284.805,
      "eval_steps_per_second": 4.481,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.0114262104034424,
      "learning_rate": 3.0904285064359275e-11,
      "loss": 0.0624,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8896,
      "eval_loss": 0.39379850029945374,
      "eval_runtime": 13.1637,
      "eval_samples_per_second": 284.875,
      "eval_steps_per_second": 4.482,
      "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
}