trainer_state.json

{
  "best_metric": 0.896,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0868/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": 4.1691691691691694e-05,
      "loss": 2.0524,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7712,
      "eval_loss": 0.9292265176773071,
      "eval_runtime": 6.3533,
      "eval_samples_per_second": 590.247,
      "eval_steps_per_second": 9.287,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.62899398803711,
      "learning_rate": 3.335835835835836e-05,
      "loss": 0.6388,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8533333333333334,
      "eval_loss": 0.5532671213150024,
      "eval_runtime": 6.7936,
      "eval_samples_per_second": 551.989,
      "eval_steps_per_second": 8.685,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.308444976806641,
      "learning_rate": 2.502502502502503e-05,
      "loss": 0.337,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8746666666666667,
      "eval_loss": 0.4616018831729889,
      "eval_runtime": 6.3263,
      "eval_samples_per_second": 592.759,
      "eval_steps_per_second": 9.326,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3468104600906372,
      "learning_rate": 1.6691691691691692e-05,
      "loss": 0.1881,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8810666666666667,
      "eval_loss": 0.42683514952659607,
      "eval_runtime": 6.3016,
      "eval_samples_per_second": 595.082,
      "eval_steps_per_second": 9.363,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.6624195575714111,
      "learning_rate": 8.358358358358359e-06,
      "loss": 0.1044,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.397498220205307,
      "eval_runtime": 6.3243,
      "eval_samples_per_second": 592.954,
      "eval_steps_per_second": 9.329,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 5.005005005005005e-08,
      "loss": 0.0613,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.3841020166873932,
      "eval_runtime": 6.2808,
      "eval_samples_per_second": 597.058,
      "eval_steps_per_second": 9.394,
      "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
}