trainer_state.json

{
  "best_metric": 0.8989333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0182/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": Infinity,
      "learning_rate": 0.00046670262931309826,
      "loss": 0.8674,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7776,
      "eval_loss": 0.7325747609138489,
      "eval_runtime": 8.9402,
      "eval_samples_per_second": 419.455,
      "eval_steps_per_second": 6.599,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.10464098304510117,
      "learning_rate": 0.00037534027314690147,
      "loss": 0.4834,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8296,
      "eval_loss": 0.5839143395423889,
      "eval_runtime": 6.9632,
      "eval_samples_per_second": 538.548,
      "eval_steps_per_second": 8.473,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.4285571575164795,
      "learning_rate": 0.00025039309201189616,
      "loss": 0.2774,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8352,
      "eval_loss": 0.5620728135108948,
      "eval_runtime": 8.4923,
      "eval_samples_per_second": 441.578,
      "eval_steps_per_second": 6.947,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0774449110031128,
      "learning_rate": 0.00012534058218975207,
      "loss": 0.1265,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8837333333333334,
      "eval_loss": 0.42050468921661377,
      "eval_runtime": 6.7572,
      "eval_samples_per_second": 554.965,
      "eval_steps_per_second": 8.731,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0028630979359149933,
      "learning_rate": 3.369046269879794e-05,
      "loss": 0.0357,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8957333333333334,
      "eval_loss": 0.392072468996048,
      "eval_runtime": 7.2693,
      "eval_samples_per_second": 515.865,
      "eval_steps_per_second": 8.116,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.004645175766199827,
      "learning_rate": 3.090428506435927e-10,
      "loss": 0.0104,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8989333333333334,
      "eval_loss": 0.37872010469436646,
      "eval_runtime": 7.0781,
      "eval_samples_per_second": 529.807,
      "eval_steps_per_second": 8.336,
      "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
}