trainer_state.json

{
  "best_metric": 0.5746666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0572/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": 0.0005,
      "loss": 2.9948,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2925333333333333,
      "eval_loss": 2.6356117725372314,
      "eval_runtime": 13.6219,
      "eval_samples_per_second": 275.292,
      "eval_steps_per_second": 4.331,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.261077880859375,
      "learning_rate": 0.0005,
      "loss": 2.297,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.37333333333333335,
      "eval_loss": 2.2154715061187744,
      "eval_runtime": 13.718,
      "eval_samples_per_second": 273.363,
      "eval_steps_per_second": 4.301,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.9162,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.46746666666666664,
      "eval_loss": 1.8526101112365723,
      "eval_runtime": 14.3419,
      "eval_samples_per_second": 261.472,
      "eval_steps_per_second": 4.114,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.948707580566406,
      "learning_rate": 0.0005,
      "loss": 1.621,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.48533333333333334,
      "eval_loss": 1.8150765895843506,
      "eval_runtime": 13.4477,
      "eval_samples_per_second": 278.859,
      "eval_steps_per_second": 4.387,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.3701,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5504,
      "eval_loss": 1.5703709125518799,
      "eval_runtime": 13.0374,
      "eval_samples_per_second": 287.634,
      "eval_steps_per_second": 4.525,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 10.871530532836914,
      "learning_rate": 0.0005,
      "loss": 1.1431,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5746666666666667,
      "eval_loss": 1.5042002201080322,
      "eval_runtime": 13.5121,
      "eval_samples_per_second": 277.529,
      "eval_steps_per_second": 4.366,
      "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
}