trainer_state.json

{
  "best_metric": 0.9005333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0686/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": 3.2124204635620117,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4704,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8064,
      "eval_loss": 0.6769779920578003,
      "eval_runtime": 6.1695,
      "eval_samples_per_second": 607.831,
      "eval_steps_per_second": 9.563,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7.506805462938029e-05,
      "loss": 0.469,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8314666666666667,
      "eval_loss": 0.5644811391830444,
      "eval_runtime": 6.406,
      "eval_samples_per_second": 585.393,
      "eval_steps_per_second": 9.21,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.121593713760376,
      "learning_rate": 5.007861840237923e-05,
      "loss": 0.2472,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.4374672472476959,
      "eval_runtime": 5.9576,
      "eval_samples_per_second": 629.451,
      "eval_steps_per_second": 9.903,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07051648944616318,
      "learning_rate": 2.506811643795042e-05,
      "loss": 0.1169,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.4147394001483917,
      "eval_runtime": 5.9827,
      "eval_samples_per_second": 626.808,
      "eval_steps_per_second": 9.862,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.17112678289413452,
      "learning_rate": 6.738092539759589e-06,
      "loss": 0.0476,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8978666666666667,
      "eval_loss": 0.37628164887428284,
      "eval_runtime": 6.0883,
      "eval_samples_per_second": 615.932,
      "eval_steps_per_second": 9.691,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.865991115570068,
      "learning_rate": 6.180857012871855e-11,
      "loss": 0.0231,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9005333333333333,
      "eval_loss": 0.366828054189682,
      "eval_runtime": 6.0956,
      "eval_samples_per_second": 615.196,
      "eval_steps_per_second": 9.679,
      "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
}