trainer_state.json

{
  "best_metric": 0.8544,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0402/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": 2.5015015015015015e-05,
      "loss": 2.5358,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.692,
      "eval_loss": 1.4224685430526733,
      "eval_runtime": 6.6993,
      "eval_samples_per_second": 559.761,
      "eval_steps_per_second": 8.807,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.9832863807678223,
      "learning_rate": 2.0015015015015016e-05,
      "loss": 0.9693,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8037333333333333,
      "eval_loss": 0.7945117354393005,
      "eval_runtime": 6.7665,
      "eval_samples_per_second": 554.202,
      "eval_steps_per_second": 8.719,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 1.5030030030030029e-05,
      "loss": 0.5671,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8298666666666666,
      "eval_loss": 0.6402751207351685,
      "eval_runtime": 6.8785,
      "eval_samples_per_second": 545.173,
      "eval_steps_per_second": 8.577,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.192055702209473,
      "learning_rate": 1.0030030030030031e-05,
      "loss": 0.3877,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8517333333333333,
      "eval_loss": 0.548041582107544,
      "eval_runtime": 6.7974,
      "eval_samples_per_second": 551.682,
      "eval_steps_per_second": 8.68,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.935380220413208,
      "learning_rate": 5.03003003003003e-06,
      "loss": 0.2739,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8504,
      "eval_loss": 0.5326976180076599,
      "eval_runtime": 6.9321,
      "eval_samples_per_second": 540.964,
      "eval_steps_per_second": 8.511,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.547995090484619,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.2091,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8544,
      "eval_loss": 0.5099339485168457,
      "eval_runtime": 7.6378,
      "eval_samples_per_second": 490.978,
      "eval_steps_per_second": 7.725,
      "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
}