trainer_state.json

{
  "best_metric": 0.8477333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0781/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": 9e-05,
      "loss": 1.5714,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7914666666666667,
      "eval_loss": 0.710265576839447,
      "eval_runtime": 10.573,
      "eval_samples_per_second": 354.678,
      "eval_steps_per_second": 5.58,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.3021433353424072,
      "learning_rate": 9e-05,
      "loss": 0.5049,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8221333333333334,
      "eval_loss": 0.5992218852043152,
      "eval_runtime": 10.5938,
      "eval_samples_per_second": 353.98,
      "eval_steps_per_second": 5.569,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.2893,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8309333333333333,
      "eval_loss": 0.5661541223526001,
      "eval_runtime": 10.4818,
      "eval_samples_per_second": 357.762,
      "eval_steps_per_second": 5.629,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.1634,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8432,
      "eval_loss": 0.5523934960365295,
      "eval_runtime": 11.2578,
      "eval_samples_per_second": 333.104,
      "eval_steps_per_second": 5.241,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.10646358877420425,
      "learning_rate": 9e-05,
      "loss": 0.1154,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8432,
      "eval_loss": 0.5905243754386902,
      "eval_runtime": 10.8737,
      "eval_samples_per_second": 344.869,
      "eval_steps_per_second": 5.426,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.03248392418026924,
      "learning_rate": 9e-05,
      "loss": 0.0824,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8477333333333333,
      "eval_loss": 0.6012825965881348,
      "eval_runtime": 10.6267,
      "eval_samples_per_second": 352.886,
      "eval_steps_per_second": 5.552,
      "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
}