trainer_state.json

{
  "best_metric": 0.8282666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0355/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": 374.0075988769531,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.7336,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5288,
      "eval_loss": 3.2723114490509033,
      "eval_runtime": 15.356,
      "eval_samples_per_second": 244.204,
      "eval_steps_per_second": 3.842,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 245.7043914794922,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.1477,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7101333333333333,
      "eval_loss": 1.2068617343902588,
      "eval_runtime": 15.1464,
      "eval_samples_per_second": 247.583,
      "eval_steps_per_second": 3.895,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 76.65019226074219,
      "learning_rate": 2.5e-05,
      "loss": 0.9898,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7978666666666666,
      "eval_loss": 0.7633285522460938,
      "eval_runtime": 15.1307,
      "eval_samples_per_second": 247.84,
      "eval_steps_per_second": 3.899,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 101.59283447265625,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.7202,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8128,
      "eval_loss": 0.655270516872406,
      "eval_runtime": 15.1411,
      "eval_samples_per_second": 247.67,
      "eval_steps_per_second": 3.897,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 196.94046020507812,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.6218,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8282666666666667,
      "eval_loss": 0.5884909629821777,
      "eval_runtime": 15.1074,
      "eval_samples_per_second": 248.223,
      "eval_steps_per_second": 3.905,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}