trainer_state.json

{
  "best_metric": 0.8898666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0648/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": 165.4031982421875,
      "learning_rate": 7e-05,
      "loss": 3.1186,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7072,
      "eval_loss": 1.4238874912261963,
      "eval_runtime": 8.8062,
      "eval_samples_per_second": 425.838,
      "eval_steps_per_second": 6.7,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 264.4362487792969,
      "learning_rate": 7e-05,
      "loss": 0.7998,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8498666666666667,
      "eval_loss": 0.5169614553451538,
      "eval_runtime": 8.771,
      "eval_samples_per_second": 427.547,
      "eval_steps_per_second": 6.727,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 279.8155517578125,
      "learning_rate": 7e-05,
      "loss": 0.4385,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.417682409286499,
      "eval_runtime": 8.745,
      "eval_samples_per_second": 428.816,
      "eval_steps_per_second": 6.747,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 95.25886535644531,
      "learning_rate": 7e-05,
      "loss": 0.2869,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.3853324353694916,
      "eval_runtime": 8.796,
      "eval_samples_per_second": 426.33,
      "eval_steps_per_second": 6.708,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 159.44073486328125,
      "learning_rate": 7e-05,
      "loss": 0.1953,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8893333333333333,
      "eval_loss": 0.38122835755348206,
      "eval_runtime": 8.9461,
      "eval_samples_per_second": 419.177,
      "eval_steps_per_second": 6.595,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 75.70846557617188,
      "learning_rate": 7e-05,
      "loss": 0.1401,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.37984076142311096,
      "eval_runtime": 8.9289,
      "eval_samples_per_second": 419.984,
      "eval_steps_per_second": 6.608,
      "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
}