trainer_state.json

{
  "best_metric": 0.47386666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0973/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": 0.00046670262931309826,
      "loss": 3.3302,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2224,
      "eval_loss": 2.8867478370666504,
      "eval_runtime": 6.3371,
      "eval_samples_per_second": 591.756,
      "eval_steps_per_second": 9.31,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 9.934107780456543,
      "learning_rate": 0.00037534027314690147,
      "loss": 2.7691,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2928,
      "eval_loss": 2.573863983154297,
      "eval_runtime": 6.3381,
      "eval_samples_per_second": 591.656,
      "eval_steps_per_second": 9.309,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00025078618305193415,
      "loss": 2.378,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3762666666666667,
      "eval_loss": 2.2550244331359863,
      "eval_runtime": 6.569,
      "eval_samples_per_second": 570.862,
      "eval_steps_per_second": 8.982,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00012602267032890265,
      "loss": 2.0057,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4226666666666667,
      "eval_loss": 2.0374138355255127,
      "eval_runtime": 6.3187,
      "eval_samples_per_second": 593.48,
      "eval_steps_per_second": 9.337,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.309032440185547,
      "learning_rate": 3.408569387468488e-05,
      "loss": 1.5928,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4613333333333333,
      "eval_loss": 1.9133983850479126,
      "eval_runtime": 6.4565,
      "eval_samples_per_second": 580.808,
      "eval_steps_per_second": 9.138,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 24.353790283203125,
      "learning_rate": 2.7813810714871766e-09,
      "loss": 1.2541,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.47386666666666666,
      "eval_loss": 1.8904255628585815,
      "eval_runtime": 6.6552,
      "eval_samples_per_second": 563.469,
      "eval_steps_per_second": 8.865,
      "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
}