trainer_state.json

{
  "best_metric": 0.9026666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0374/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": 179.6405029296875,
      "learning_rate": 0.0001,
      "loss": 2.7648,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7552,
      "eval_loss": 0.8993169665336609,
      "eval_runtime": 15.1475,
      "eval_samples_per_second": 247.566,
      "eval_steps_per_second": 3.895,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 88.00188446044922,
      "learning_rate": 0.0001,
      "loss": 0.6564,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.48493096232414246,
      "eval_runtime": 15.1357,
      "eval_samples_per_second": 247.759,
      "eval_steps_per_second": 3.898,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 106.76029205322266,
      "learning_rate": 0.0001,
      "loss": 0.4067,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8776,
      "eval_loss": 0.4107557237148285,
      "eval_runtime": 15.2355,
      "eval_samples_per_second": 246.136,
      "eval_steps_per_second": 3.873,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 91.82406616210938,
      "learning_rate": 0.0001,
      "loss": 0.287,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8861333333333333,
      "eval_loss": 0.394770085811615,
      "eval_runtime": 15.0936,
      "eval_samples_per_second": 248.45,
      "eval_steps_per_second": 3.909,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 105.50287628173828,
      "learning_rate": 0.0001,
      "loss": 0.2193,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8917333333333334,
      "eval_loss": 0.38539645075798035,
      "eval_runtime": 15.207,
      "eval_samples_per_second": 246.597,
      "eval_steps_per_second": 3.88,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 45.24867630004883,
      "learning_rate": 0.0001,
      "loss": 0.1535,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9026666666666666,
      "eval_loss": 0.35766807198524475,
      "eval_runtime": 15.0637,
      "eval_samples_per_second": 248.943,
      "eval_steps_per_second": 3.917,
      "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": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}