trainer_state.json

{
  "best_metric": 0.8741333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0370/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": 125.57463073730469,
      "learning_rate": 8.397114317029975e-05,
      "loss": 2.9737,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7293333333333333,
      "eval_loss": 1.1690486669540405,
      "eval_runtime": 8.0804,
      "eval_samples_per_second": 464.088,
      "eval_steps_per_second": 7.302,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 86.65471649169922,
      "learning_rate": 6.75e-05,
      "loss": 0.8242,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8336,
      "eval_loss": 0.5640621781349182,
      "eval_runtime": 7.6005,
      "eval_samples_per_second": 493.388,
      "eval_steps_per_second": 7.763,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 83.28816223144531,
      "learning_rate": 4.5e-05,
      "loss": 0.5328,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8501333333333333,
      "eval_loss": 0.4889858067035675,
      "eval_runtime": 7.5745,
      "eval_samples_per_second": 495.081,
      "eval_steps_per_second": 7.789,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 41.60493087768555,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.4223,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8672,
      "eval_loss": 0.4302750527858734,
      "eval_runtime": 8.1434,
      "eval_samples_per_second": 460.494,
      "eval_steps_per_second": 7.245,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 78.5144271850586,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.3673,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8738666666666667,
      "eval_loss": 0.41483113169670105,
      "eval_runtime": 7.5766,
      "eval_samples_per_second": 494.947,
      "eval_steps_per_second": 7.787,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 46.333412170410156,
      "learning_rate": 0.0,
      "loss": 0.3489,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8741333333333333,
      "eval_loss": 0.4182087481021881,
      "eval_runtime": 8.4717,
      "eval_samples_per_second": 442.652,
      "eval_steps_per_second": 6.964,
      "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
}