trainer_state.json

{
  "best_metric": 0.8946666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0107/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": 67.47323608398438,
      "learning_rate": 9e-05,
      "loss": 2.8884,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7042666666666667,
      "eval_loss": 1.135634422302246,
      "eval_runtime": 5.3995,
      "eval_samples_per_second": 694.515,
      "eval_steps_per_second": 10.927,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 64.94908905029297,
      "learning_rate": 9e-05,
      "loss": 0.7639,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.5320410132408142,
      "eval_runtime": 5.4046,
      "eval_samples_per_second": 693.851,
      "eval_steps_per_second": 10.917,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 100.99279022216797,
      "learning_rate": 9e-05,
      "loss": 0.4616,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.4059027135372162,
      "eval_runtime": 5.374,
      "eval_samples_per_second": 697.801,
      "eval_steps_per_second": 10.979,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 105.75826263427734,
      "learning_rate": 9e-05,
      "loss": 0.3473,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8824,
      "eval_loss": 0.38451504707336426,
      "eval_runtime": 5.438,
      "eval_samples_per_second": 689.596,
      "eval_steps_per_second": 10.85,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 50.78847122192383,
      "learning_rate": 9e-05,
      "loss": 0.2619,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.34052473306655884,
      "eval_runtime": 5.4087,
      "eval_samples_per_second": 693.333,
      "eval_steps_per_second": 10.908,
      "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}