trainer_state.json

{
  "best_metric": 0.8642666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0079/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": 2.4542,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7056,
      "eval_loss": 1.347408413887024,
      "eval_runtime": 5.7186,
      "eval_samples_per_second": 655.757,
      "eval_steps_per_second": 10.317,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.259007453918457,
      "learning_rate": 2.0015015015015016e-05,
      "loss": 0.9045,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8125333333333333,
      "eval_loss": 0.7439080476760864,
      "eval_runtime": 5.8713,
      "eval_samples_per_second": 638.697,
      "eval_steps_per_second": 10.049,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.484918475151062,
      "learning_rate": 1.5015015015015016e-05,
      "loss": 0.4763,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8392,
      "eval_loss": 0.5776037573814392,
      "eval_runtime": 5.7609,
      "eval_samples_per_second": 650.945,
      "eval_steps_per_second": 10.242,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 1.0030030030030031e-05,
      "loss": 0.2769,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8536,
      "eval_loss": 0.5271886587142944,
      "eval_runtime": 6.1645,
      "eval_samples_per_second": 608.323,
      "eval_steps_per_second": 9.571,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.03402328491211,
      "learning_rate": 5.03003003003003e-06,
      "loss": 0.1645,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8624,
      "eval_loss": 0.4890667200088501,
      "eval_runtime": 5.7138,
      "eval_samples_per_second": 656.308,
      "eval_steps_per_second": 10.326,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.2885102033615112,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.1038,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.48265957832336426,
      "eval_runtime": 5.6736,
      "eval_samples_per_second": 660.958,
      "eval_steps_per_second": 10.399,
      "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
}