trainer_state.json

{
  "best_metric": 0.9602666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0984/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": 12.864246368408203,
      "learning_rate": 3e-05,
      "loss": 1.0771,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9442666666666667,
      "eval_loss": 0.23461750149726868,
      "eval_runtime": 5.2979,
      "eval_samples_per_second": 707.83,
      "eval_steps_per_second": 11.137,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2045728862285614,
      "learning_rate": 3e-05,
      "loss": 0.12,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9493333333333334,
      "eval_loss": 0.18337689340114594,
      "eval_runtime": 5.2569,
      "eval_samples_per_second": 713.354,
      "eval_steps_per_second": 11.223,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.10092521458864212,
      "learning_rate": 3e-05,
      "loss": 0.0389,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9568,
      "eval_loss": 0.1677301824092865,
      "eval_runtime": 5.2562,
      "eval_samples_per_second": 713.449,
      "eval_steps_per_second": 11.225,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.21213065087795258,
      "learning_rate": 3e-05,
      "loss": 0.0161,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.952,
      "eval_loss": 0.19155709445476532,
      "eval_runtime": 5.2873,
      "eval_samples_per_second": 709.243,
      "eval_steps_per_second": 11.159,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.019069114699959755,
      "learning_rate": 3e-05,
      "loss": 0.0069,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.956,
      "eval_loss": 0.1859481930732727,
      "eval_runtime": 5.7161,
      "eval_samples_per_second": 656.037,
      "eval_steps_per_second": 10.322,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0895339697599411,
      "learning_rate": 3e-05,
      "loss": 0.0032,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9602666666666667,
      "eval_loss": 0.18632957339286804,
      "eval_runtime": 5.3132,
      "eval_samples_per_second": 705.795,
      "eval_steps_per_second": 11.105,
      "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
}