trainer_state.json

{
  "best_metric": 0.9325333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0942/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": 0.7698686122894287,
      "learning_rate": 0.0001,
      "loss": 0.5732,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.2668743431568146,
      "eval_runtime": 10.9324,
      "eval_samples_per_second": 343.017,
      "eval_steps_per_second": 5.397,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1905512809753418,
      "learning_rate": 0.0001,
      "loss": 0.1237,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9274666666666667,
      "eval_loss": 0.2584403455257416,
      "eval_runtime": 10.99,
      "eval_samples_per_second": 341.22,
      "eval_steps_per_second": 5.369,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.040098052471876144,
      "learning_rate": 0.0001,
      "loss": 0.0662,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9258666666666666,
      "eval_loss": 0.28911256790161133,
      "eval_runtime": 10.7512,
      "eval_samples_per_second": 348.798,
      "eval_steps_per_second": 5.488,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.013192861340939999,
      "learning_rate": 0.0001,
      "loss": 0.0505,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9248,
      "eval_loss": 0.31010761857032776,
      "eval_runtime": 10.887,
      "eval_samples_per_second": 344.449,
      "eval_steps_per_second": 5.419,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.14166486263275146,
      "learning_rate": 0.0001,
      "loss": 0.0355,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9282666666666667,
      "eval_loss": 0.3165966868400574,
      "eval_runtime": 10.9106,
      "eval_samples_per_second": 343.703,
      "eval_steps_per_second": 5.408,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.005280105397105217,
      "learning_rate": 0.0001,
      "loss": 0.0353,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9325333333333333,
      "eval_loss": 0.3016417324542999,
      "eval_runtime": 10.8976,
      "eval_samples_per_second": 344.114,
      "eval_steps_per_second": 5.414,
      "step": 1998
    }
  ],
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}