trainer_state.json

{
  "best_metric": 0.7624,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0925/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": 0.0002501501501501501,
      "loss": 3.0905,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.30693333333333334,
      "eval_loss": 2.5363521575927734,
      "eval_runtime": 6.9973,
      "eval_samples_per_second": 535.921,
      "eval_steps_per_second": 8.432,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002003003003003003,
      "loss": 2.1547,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4816,
      "eval_loss": 1.8049699068069458,
      "eval_runtime": 6.9075,
      "eval_samples_per_second": 542.891,
      "eval_steps_per_second": 8.541,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00015045045045045046,
      "loss": 1.3852,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6221333333333333,
      "eval_loss": 1.2156215906143188,
      "eval_runtime": 6.9318,
      "eval_samples_per_second": 540.987,
      "eval_steps_per_second": 8.512,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.565257728099823,
      "learning_rate": 0.00010045045045045045,
      "loss": 0.8025,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6978666666666666,
      "eval_loss": 0.9716242551803589,
      "eval_runtime": 7.3165,
      "eval_samples_per_second": 512.54,
      "eval_steps_per_second": 8.064,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.57371997833252,
      "learning_rate": 5.045045045045045e-05,
      "loss": 0.4375,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7429333333333333,
      "eval_loss": 0.8533737659454346,
      "eval_runtime": 6.861,
      "eval_samples_per_second": 546.57,
      "eval_steps_per_second": 8.599,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.719642639160156,
      "learning_rate": 4.5045045045045043e-07,
      "loss": 0.2015,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7624,
      "eval_loss": 0.797028660774231,
      "eval_runtime": 6.947,
      "eval_samples_per_second": 539.8,
      "eval_steps_per_second": 8.493,
      "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
}