trainer_state.json

{
  "best_metric": 0.9256,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0512/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": 2.153527021408081,
      "learning_rate": 0.0001,
      "loss": 0.6088,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9216,
      "eval_loss": 0.26184388995170593,
      "eval_runtime": 5.1685,
      "eval_samples_per_second": 725.552,
      "eval_steps_per_second": 11.415,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.415332794189453,
      "learning_rate": 0.0001,
      "loss": 0.1553,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9181333333333334,
      "eval_loss": 0.28409796953201294,
      "eval_runtime": 4.4479,
      "eval_samples_per_second": 843.102,
      "eval_steps_per_second": 13.265,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.1408755779266357,
      "learning_rate": 0.0001,
      "loss": 0.0907,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.912,
      "eval_loss": 0.3484141528606415,
      "eval_runtime": 4.8993,
      "eval_samples_per_second": 765.412,
      "eval_steps_per_second": 12.042,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0561603419482708,
      "learning_rate": 0.0001,
      "loss": 0.065,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9229333333333334,
      "eval_loss": 0.2979372441768646,
      "eval_runtime": 11.3344,
      "eval_samples_per_second": 330.851,
      "eval_steps_per_second": 5.205,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.010615554638206959,
      "learning_rate": 0.0001,
      "loss": 0.0514,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9256,
      "eval_loss": 0.3034835159778595,
      "eval_runtime": 5.6622,
      "eval_samples_per_second": 662.286,
      "eval_steps_per_second": 10.42,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}