trainer_state.json

{
  "best_metric": 0.8226666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0546/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": 218.62789916992188,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.7158,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4856,
      "eval_loss": 3.323789119720459,
      "eval_runtime": 12.9486,
      "eval_samples_per_second": 289.606,
      "eval_steps_per_second": 4.556,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 357.3421630859375,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.1406,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7045333333333333,
      "eval_loss": 1.199836254119873,
      "eval_runtime": 13.0656,
      "eval_samples_per_second": 287.014,
      "eval_steps_per_second": 4.516,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 451.36065673828125,
      "learning_rate": 2.5e-05,
      "loss": 1.0183,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7888,
      "eval_loss": 0.8178912997245789,
      "eval_runtime": 12.8335,
      "eval_samples_per_second": 292.204,
      "eval_steps_per_second": 4.597,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 97.43077850341797,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.766,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8117333333333333,
      "eval_loss": 0.6796938180923462,
      "eval_runtime": 12.9063,
      "eval_samples_per_second": 290.556,
      "eval_steps_per_second": 4.571,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 160.9631805419922,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.6654,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8226666666666667,
      "eval_loss": 0.6202513575553894,
      "eval_runtime": 13.0168,
      "eval_samples_per_second": 288.089,
      "eval_steps_per_second": 4.533,
      "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
}