trainer_state.json

{
  "best_metric": 0.8930666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0022/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": 6.533836810383375e-05,
      "loss": 1.6946,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7762666666666667,
      "eval_loss": 0.8103317618370056,
      "eval_runtime": 4.959,
      "eval_samples_per_second": 756.203,
      "eval_steps_per_second": 11.898,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.259523309735526e-05,
      "loss": 0.5924,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5581600069999695,
      "eval_runtime": 4.7771,
      "eval_samples_per_second": 784.988,
      "eval_steps_per_second": 12.35,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.711901068687439,
      "learning_rate": 3.5110065627270776e-05,
      "loss": 0.3439,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8589333333333333,
      "eval_loss": 0.48407867550849915,
      "eval_runtime": 4.8609,
      "eval_samples_per_second": 771.459,
      "eval_steps_per_second": 12.138,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 39.62687301635742,
      "learning_rate": 1.7595406161244655e-05,
      "loss": 0.1969,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8810666666666667,
      "eval_loss": 0.416535347700119,
      "eval_runtime": 5.5648,
      "eval_samples_per_second": 673.879,
      "eval_steps_per_second": 10.602,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6531349420547485,
      "learning_rate": 4.744293558904729e-06,
      "loss": 0.1126,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8890666666666667,
      "eval_loss": 0.39090201258659363,
      "eval_runtime": 4.9075,
      "eval_samples_per_second": 764.139,
      "eval_steps_per_second": 12.022,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5789008140563965,
      "learning_rate": 1.7306388939264393e-10,
      "loss": 0.0729,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.36997082829475403,
      "eval_runtime": 5.1066,
      "eval_samples_per_second": 734.345,
      "eval_steps_per_second": 11.554,
      "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
}