trainer_state.json

{
  "best_metric": 0.9346666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0106/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": 14.516469955444336,
      "learning_rate": 3e-05,
      "loss": 1.2001,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9197333333333333,
      "eval_loss": 0.32719290256500244,
      "eval_runtime": 8.1714,
      "eval_samples_per_second": 458.916,
      "eval_steps_per_second": 7.22,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.982287406921387,
      "learning_rate": 3e-05,
      "loss": 0.1942,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9256,
      "eval_loss": 0.2570750415325165,
      "eval_runtime": 6.3586,
      "eval_samples_per_second": 589.748,
      "eval_steps_per_second": 9.279,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.07817139476537704,
      "learning_rate": 3e-05,
      "loss": 0.0943,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9293333333333333,
      "eval_loss": 0.24465496838092804,
      "eval_runtime": 6.7294,
      "eval_samples_per_second": 557.253,
      "eval_steps_per_second": 8.767,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7455075979232788,
      "learning_rate": 3e-05,
      "loss": 0.0484,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9301333333333334,
      "eval_loss": 0.2799505889415741,
      "eval_runtime": 6.1823,
      "eval_samples_per_second": 606.574,
      "eval_steps_per_second": 9.543,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0670977309346199,
      "learning_rate": 3e-05,
      "loss": 0.0272,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9346666666666666,
      "eval_loss": 0.2551446259021759,
      "eval_runtime": 6.3241,
      "eval_samples_per_second": 592.967,
      "eval_steps_per_second": 9.329,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}