trainer_state.json

{
  "best_metric": 0.86,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0879/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": 7.470448017120361,
      "learning_rate": 5e-05,
      "loss": 2.0555,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7584,
      "eval_loss": 0.9076303839683533,
      "eval_runtime": 6.3908,
      "eval_samples_per_second": 586.784,
      "eval_steps_per_second": 9.232,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.982215404510498,
      "learning_rate": 5e-05,
      "loss": 0.6784,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8154666666666667,
      "eval_loss": 0.6091476678848267,
      "eval_runtime": 5.7982,
      "eval_samples_per_second": 646.752,
      "eval_steps_per_second": 10.176,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 11.981606483459473,
      "learning_rate": 5e-05,
      "loss": 0.4339,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8344,
      "eval_loss": 0.5416943430900574,
      "eval_runtime": 5.7915,
      "eval_samples_per_second": 647.501,
      "eval_steps_per_second": 10.187,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.410874366760254,
      "learning_rate": 5e-05,
      "loss": 0.3109,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8269333333333333,
      "eval_loss": 0.5532939434051514,
      "eval_runtime": 5.8876,
      "eval_samples_per_second": 636.936,
      "eval_steps_per_second": 10.021,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5327204465866089,
      "learning_rate": 5e-05,
      "loss": 0.2307,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8509333333333333,
      "eval_loss": 0.498602032661438,
      "eval_runtime": 6.3542,
      "eval_samples_per_second": 590.164,
      "eval_steps_per_second": 9.285,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.582382082939148,
      "learning_rate": 5e-05,
      "loss": 0.182,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.486460417509079,
      "eval_runtime": 5.9404,
      "eval_samples_per_second": 631.272,
      "eval_steps_per_second": 9.932,
      "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
}