trainer_state.json

{
  "best_metric": 0.8704,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0862/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": 1.8869,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.796,
      "eval_loss": 0.7422537803649902,
      "eval_runtime": 5.5668,
      "eval_samples_per_second": 673.64,
      "eval_steps_per_second": 10.599,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.821219444274902,
      "learning_rate": 9e-05,
      "loss": 0.4905,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8448,
      "eval_loss": 0.5212185382843018,
      "eval_runtime": 5.6714,
      "eval_samples_per_second": 661.209,
      "eval_steps_per_second": 10.403,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.6742874383926392,
      "learning_rate": 9e-05,
      "loss": 0.2582,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.4544771909713745,
      "eval_runtime": 5.7326,
      "eval_samples_per_second": 654.149,
      "eval_steps_per_second": 10.292,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2981984317302704,
      "learning_rate": 9e-05,
      "loss": 0.149,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8666666666666667,
      "eval_loss": 0.47022607922554016,
      "eval_runtime": 5.9603,
      "eval_samples_per_second": 629.158,
      "eval_steps_per_second": 9.899,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 14.40675163269043,
      "learning_rate": 9e-05,
      "loss": 0.104,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8704,
      "eval_loss": 0.49645671248435974,
      "eval_runtime": 5.7084,
      "eval_samples_per_second": 656.929,
      "eval_steps_per_second": 10.336,
      "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
}