trainer_state.json

{
  "best_metric": 0.9333333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0835/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": 0.16416391730308533,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6705,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9069333333333334,
      "eval_loss": 0.2974901497364044,
      "eval_runtime": 7.2575,
      "eval_samples_per_second": 516.706,
      "eval_steps_per_second": 8.13,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.07420966774225235,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1801,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.912,
      "eval_loss": 0.28495562076568604,
      "eval_runtime": 7.375,
      "eval_samples_per_second": 508.473,
      "eval_steps_per_second": 8.0,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.08075325191020966,
      "learning_rate": 5e-05,
      "loss": 0.0879,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9090666666666667,
      "eval_loss": 0.3224937915802002,
      "eval_runtime": 8.0755,
      "eval_samples_per_second": 464.369,
      "eval_steps_per_second": 7.306,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.023187773302197456,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0376,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9266666666666666,
      "eval_loss": 0.27509814500808716,
      "eval_runtime": 7.4651,
      "eval_samples_per_second": 502.335,
      "eval_steps_per_second": 7.903,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5813816785812378,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0141,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9293333333333333,
      "eval_loss": 0.26587092876434326,
      "eval_runtime": 7.2329,
      "eval_samples_per_second": 518.466,
      "eval_steps_per_second": 8.157,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.015966249629855156,
      "learning_rate": 0.0,
      "loss": 0.0076,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_loss": 0.2559289336204529,
      "eval_runtime": 7.7823,
      "eval_samples_per_second": 481.865,
      "eval_steps_per_second": 7.581,
      "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
}