trainer_state.json

{
  "best_metric": 0.9136,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0027/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": 54.02802276611328,
      "learning_rate": 0.0002799038105676658,
      "loss": 1.4358,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8498666666666667,
      "eval_loss": 0.5222064256668091,
      "eval_runtime": 7.6653,
      "eval_samples_per_second": 489.219,
      "eval_steps_per_second": 7.697,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 44.058349609375,
      "learning_rate": 0.000225,
      "loss": 0.3349,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8861333333333333,
      "eval_loss": 0.3764764070510864,
      "eval_runtime": 7.2708,
      "eval_samples_per_second": 515.761,
      "eval_steps_per_second": 8.115,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 45.33389663696289,
      "learning_rate": 0.00015,
      "loss": 0.1641,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9021333333333333,
      "eval_loss": 0.348573237657547,
      "eval_runtime": 7.1619,
      "eval_samples_per_second": 523.603,
      "eval_steps_per_second": 8.238,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 41.949241638183594,
      "learning_rate": 7.500000000000002e-05,
      "loss": 0.0737,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.3479224741458893,
      "eval_runtime": 7.2204,
      "eval_samples_per_second": 519.359,
      "eval_steps_per_second": 8.171,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 30.66214942932129,
      "learning_rate": 2.009618943233419e-05,
      "loss": 0.0377,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9114666666666666,
      "eval_loss": 0.33946913480758667,
      "eval_runtime": 7.1775,
      "eval_samples_per_second": 522.468,
      "eval_steps_per_second": 8.22,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 52.45071792602539,
      "learning_rate": 0.0,
      "loss": 0.0303,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9136,
      "eval_loss": 0.3411877751350403,
      "eval_runtime": 7.1606,
      "eval_samples_per_second": 523.699,
      "eval_steps_per_second": 8.24,
      "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
}