trainer_state.json

{
  "best_metric": 0.9176,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0701/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": 90.13333892822266,
      "learning_rate": 0.00025,
      "loss": 1.4605,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.44930529594421387,
      "eval_runtime": 6.8989,
      "eval_samples_per_second": 543.564,
      "eval_steps_per_second": 8.552,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 34.4361686706543,
      "learning_rate": 0.00019999999999999998,
      "loss": 0.3482,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9008,
      "eval_loss": 0.3224843144416809,
      "eval_runtime": 7.3208,
      "eval_samples_per_second": 512.239,
      "eval_steps_per_second": 8.059,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 40.046348571777344,
      "learning_rate": 0.00015,
      "loss": 0.1706,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9024,
      "eval_loss": 0.33666157722473145,
      "eval_runtime": 7.3363,
      "eval_samples_per_second": 511.159,
      "eval_steps_per_second": 8.042,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 30.198915481567383,
      "learning_rate": 9.999999999999999e-05,
      "loss": 0.0877,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9056,
      "eval_loss": 0.33829498291015625,
      "eval_runtime": 6.886,
      "eval_samples_per_second": 544.583,
      "eval_steps_per_second": 8.568,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 65.19944763183594,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.0397,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.32488003373146057,
      "eval_runtime": 6.8704,
      "eval_samples_per_second": 545.823,
      "eval_steps_per_second": 8.588,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 51.864166259765625,
      "learning_rate": 0.0,
      "loss": 0.0291,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9176,
      "eval_loss": 0.33714136481285095,
      "eval_runtime": 6.866,
      "eval_samples_per_second": 546.17,
      "eval_steps_per_second": 8.593,
      "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
}