trainer_state.json

{
  "best_metric": 0.8648,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0498/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": 2.4242,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7106666666666667,
      "eval_loss": 1.318773627281189,
      "eval_runtime": 7.2381,
      "eval_samples_per_second": 518.095,
      "eval_steps_per_second": 8.151,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.001290321350098,
      "learning_rate": 2.0015015015015016e-05,
      "loss": 0.9285,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7858666666666667,
      "eval_loss": 0.817764937877655,
      "eval_runtime": 7.7929,
      "eval_samples_per_second": 481.207,
      "eval_steps_per_second": 7.571,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 1.5030030030030029e-05,
      "loss": 0.5596,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8306666666666667,
      "eval_loss": 0.6217007040977478,
      "eval_runtime": 7.0355,
      "eval_samples_per_second": 533.014,
      "eval_steps_per_second": 8.386,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.3165316581726074,
      "learning_rate": 1.0030030030030031e-05,
      "loss": 0.3743,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8448,
      "eval_loss": 0.5546784996986389,
      "eval_runtime": 7.3654,
      "eval_samples_per_second": 509.14,
      "eval_steps_per_second": 8.01,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.832029104232788,
      "learning_rate": 5.03003003003003e-06,
      "loss": 0.2677,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.5043249130249023,
      "eval_runtime": 7.3743,
      "eval_samples_per_second": 508.521,
      "eval_steps_per_second": 8.001,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.2956626415252686,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.2055,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8648,
      "eval_loss": 0.4805319905281067,
      "eval_runtime": 7.2296,
      "eval_samples_per_second": 518.698,
      "eval_steps_per_second": 8.161,
      "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
}