trainer_state.json

{
  "best_metric": 0.8424,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0910/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": 0.0001,
      "loss": 2.2376,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7288,
      "eval_loss": 0.9398003816604614,
      "eval_runtime": 6.4992,
      "eval_samples_per_second": 576.993,
      "eval_steps_per_second": 9.078,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.7093,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7930666666666667,
      "eval_loss": 0.677649974822998,
      "eval_runtime": 6.416,
      "eval_samples_per_second": 584.475,
      "eval_steps_per_second": 9.196,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4000376760959625,
      "learning_rate": 0.0001,
      "loss": 0.4424,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8237333333333333,
      "eval_loss": 0.5821743011474609,
      "eval_runtime": 6.3616,
      "eval_samples_per_second": 589.473,
      "eval_steps_per_second": 9.274,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.11397849023342133,
      "learning_rate": 0.0001,
      "loss": 0.322,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8234666666666667,
      "eval_loss": 0.5964834094047546,
      "eval_runtime": 6.2532,
      "eval_samples_per_second": 599.691,
      "eval_steps_per_second": 9.435,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.2383,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5369557738304138,
      "eval_runtime": 7.8963,
      "eval_samples_per_second": 474.905,
      "eval_steps_per_second": 7.472,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2635841965675354,
      "learning_rate": 0.0001,
      "loss": 0.1768,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8424,
      "eval_loss": 0.5633807182312012,
      "eval_runtime": 6.6837,
      "eval_samples_per_second": 561.063,
      "eval_steps_per_second": 8.827,
      "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
}