trainer_state.json

{
  "best_metric": 0.9184,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0332/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": 12.299928665161133,
      "learning_rate": 0.0001,
      "loss": 0.6316,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9045333333333333,
      "eval_loss": 0.31089189648628235,
      "eval_runtime": 6.538,
      "eval_samples_per_second": 573.572,
      "eval_steps_per_second": 9.024,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09956754744052887,
      "learning_rate": 0.0001,
      "loss": 0.175,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9176,
      "eval_loss": 0.2819674611091614,
      "eval_runtime": 5.9307,
      "eval_samples_per_second": 632.301,
      "eval_steps_per_second": 9.948,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.06042176112532616,
      "learning_rate": 0.0001,
      "loss": 0.0985,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9125333333333333,
      "eval_loss": 0.32142090797424316,
      "eval_runtime": 5.8436,
      "eval_samples_per_second": 641.726,
      "eval_steps_per_second": 10.096,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.3259437084198,
      "learning_rate": 0.0001,
      "loss": 0.067,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9106666666666666,
      "eval_loss": 0.36214497685432434,
      "eval_runtime": 5.7897,
      "eval_samples_per_second": 647.702,
      "eval_steps_per_second": 10.191,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.007399913854897022,
      "learning_rate": 0.0001,
      "loss": 0.0551,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9184,
      "eval_loss": 0.33451008796691895,
      "eval_runtime": 5.832,
      "eval_samples_per_second": 643.001,
      "eval_steps_per_second": 10.117,
      "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
}