trainer_state.json

{
  "best_metric": 0.8517333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0073/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": 3.819573402404785,
      "learning_rate": 9e-05,
      "loss": 1.9391,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7610666666666667,
      "eval_loss": 0.8554072976112366,
      "eval_runtime": 11.9929,
      "eval_samples_per_second": 312.684,
      "eval_steps_per_second": 4.92,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.5509,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8256,
      "eval_loss": 0.5863158702850342,
      "eval_runtime": 11.8392,
      "eval_samples_per_second": 316.745,
      "eval_steps_per_second": 4.983,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.2765,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.5313918590545654,
      "eval_runtime": 11.9385,
      "eval_samples_per_second": 314.109,
      "eval_steps_per_second": 4.942,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4682815074920654,
      "learning_rate": 9e-05,
      "loss": 0.1555,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8394666666666667,
      "eval_loss": 0.5979598164558411,
      "eval_runtime": 11.977,
      "eval_samples_per_second": 313.101,
      "eval_steps_per_second": 4.926,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.414962291717529,
      "learning_rate": 9e-05,
      "loss": 0.1035,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8434666666666667,
      "eval_loss": 0.5738069415092468,
      "eval_runtime": 11.844,
      "eval_samples_per_second": 316.617,
      "eval_steps_per_second": 4.981,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.33828893303871155,
      "learning_rate": 9e-05,
      "loss": 0.0789,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8517333333333333,
      "eval_loss": 0.5910093188285828,
      "eval_runtime": 12.2164,
      "eval_samples_per_second": 306.964,
      "eval_steps_per_second": 4.83,
      "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
}