trainer_state.json

{
  "best_metric": 0.9466666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0357/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": 0.5424749255180359,
      "learning_rate": 5.6e-05,
      "loss": 0.7317,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.25172117352485657,
      "eval_runtime": 7.0154,
      "eval_samples_per_second": 534.538,
      "eval_steps_per_second": 8.41,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.46938806772232056,
      "learning_rate": 4.2e-05,
      "loss": 0.1348,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.2186284065246582,
      "eval_runtime": 7.2886,
      "eval_samples_per_second": 514.505,
      "eval_steps_per_second": 8.095,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.035771001130342484,
      "learning_rate": 2.8e-05,
      "loss": 0.0587,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.20090746879577637,
      "eval_runtime": 7.3213,
      "eval_samples_per_second": 512.204,
      "eval_steps_per_second": 8.059,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.02882409654557705,
      "learning_rate": 1.4e-05,
      "loss": 0.025,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9448,
      "eval_loss": 0.18671512603759766,
      "eval_runtime": 6.8207,
      "eval_samples_per_second": 549.795,
      "eval_steps_per_second": 8.65,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.022893613204360008,
      "learning_rate": 0.0,
      "loss": 0.0109,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9466666666666667,
      "eval_loss": 0.19892120361328125,
      "eval_runtime": 7.374,
      "eval_samples_per_second": 508.543,
      "eval_steps_per_second": 8.001,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}