trainer_state.json

{
  "best_metric": 0.8642666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0788/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "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": 9e-05,
      "loss": 1.7319,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7949333333333334,
      "eval_loss": 0.7424951791763306,
      "eval_runtime": 7.5354,
      "eval_samples_per_second": 497.651,
      "eval_steps_per_second": 7.83,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.475248336791992,
      "learning_rate": 9e-05,
      "loss": 0.5641,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8274666666666667,
      "eval_loss": 0.568708062171936,
      "eval_runtime": 7.806,
      "eval_samples_per_second": 480.399,
      "eval_steps_per_second": 7.558,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.3518,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.47895196080207825,
      "eval_runtime": 6.8263,
      "eval_samples_per_second": 549.348,
      "eval_steps_per_second": 8.643,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 97.95305633544922,
      "learning_rate": 9e-05,
      "loss": 0.2497,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.856,
      "eval_loss": 0.5023444890975952,
      "eval_runtime": 7.2697,
      "eval_samples_per_second": 515.839,
      "eval_steps_per_second": 8.116,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.21913205087184906,
      "learning_rate": 9e-05,
      "loss": 0.1839,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.4832301735877991,
      "eval_runtime": 7.2445,
      "eval_samples_per_second": 517.634,
      "eval_steps_per_second": 8.144,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}