trainer_state.json

{
  "best_metric": 0.9512,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0626/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": NaN,
      "learning_rate": 6.335436141135384e-05,
      "loss": 0.7442,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9221333333333334,
      "eval_loss": 0.25632309913635254,
      "eval_runtime": 13.4551,
      "eval_samples_per_second": 278.704,
      "eval_steps_per_second": 4.385,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7789638042449951,
      "learning_rate": 4.587838279590199e-05,
      "loss": 0.1463,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9352,
      "eval_loss": 0.21495740115642548,
      "eval_runtime": 13.5215,
      "eval_samples_per_second": 277.336,
      "eval_steps_per_second": 4.363,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.08210282772779465,
      "learning_rate": 2.4247231695047696e-05,
      "loss": 0.063,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9413333333333334,
      "eval_loss": 0.2061334252357483,
      "eval_runtime": 13.4322,
      "eval_samples_per_second": 279.18,
      "eval_steps_per_second": 4.392,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.988694190979004,
      "learning_rate": 6.723272613532589e-06,
      "loss": 0.0231,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.948,
      "eval_loss": 0.19474463164806366,
      "eval_runtime": 13.516,
      "eval_samples_per_second": 277.448,
      "eval_steps_per_second": 4.365,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.10302536189556122,
      "learning_rate": 6.230303304433081e-11,
      "loss": 0.0122,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9512,
      "eval_loss": 0.18517674505710602,
      "eval_runtime": 13.5348,
      "eval_samples_per_second": 277.064,
      "eval_steps_per_second": 4.359,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}