trainer_state.json

{
  "best_metric": 0.8930666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0135/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": 2.2410314083099365,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.8534,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8010666666666667,
      "eval_loss": 0.7784974575042725,
      "eval_runtime": 6.6611,
      "eval_samples_per_second": 562.969,
      "eval_steps_per_second": 8.857,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3.335835835835836e-05,
      "loss": 0.5231,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8565333333333334,
      "eval_loss": 0.49984100461006165,
      "eval_runtime": 6.5791,
      "eval_samples_per_second": 569.988,
      "eval_steps_per_second": 8.968,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5583040118217468,
      "learning_rate": 2.502502502502503e-05,
      "loss": 0.2495,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8768,
      "eval_loss": 0.42053815722465515,
      "eval_runtime": 6.5781,
      "eval_samples_per_second": 570.075,
      "eval_steps_per_second": 8.969,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.634411811828613,
      "learning_rate": 1.6691691691691692e-05,
      "loss": 0.1164,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8904,
      "eval_loss": 0.38084638118743896,
      "eval_runtime": 6.7935,
      "eval_samples_per_second": 552.001,
      "eval_steps_per_second": 8.685,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3123990595340729,
      "learning_rate": 8.358358358358359e-06,
      "loss": 0.0492,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.37690624594688416,
      "eval_runtime": 10.9399,
      "eval_samples_per_second": 342.781,
      "eval_steps_per_second": 5.393,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.17627021670341492,
      "learning_rate": 2.5025025025025025e-08,
      "loss": 0.0211,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.3695661425590515,
      "eval_runtime": 6.643,
      "eval_samples_per_second": 564.505,
      "eval_steps_per_second": 8.882,
      "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
}