trainer_state.json

{
  "best_metric": 0.88,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0081/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": 233.40150451660156,
      "learning_rate": 7e-05,
      "loss": 3.2567,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6458666666666667,
      "eval_loss": 1.7204749584197998,
      "eval_runtime": 7.5764,
      "eval_samples_per_second": 494.957,
      "eval_steps_per_second": 7.787,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 105.51305389404297,
      "learning_rate": 7e-05,
      "loss": 0.9277,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8157333333333333,
      "eval_loss": 0.602063000202179,
      "eval_runtime": 7.2986,
      "eval_samples_per_second": 513.8,
      "eval_steps_per_second": 8.084,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 67.97893524169922,
      "learning_rate": 7e-05,
      "loss": 0.5038,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8517333333333333,
      "eval_loss": 0.46103382110595703,
      "eval_runtime": 7.3273,
      "eval_samples_per_second": 511.785,
      "eval_steps_per_second": 8.052,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 272.51373291015625,
      "learning_rate": 7e-05,
      "loss": 0.3646,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8648,
      "eval_loss": 0.4219033122062683,
      "eval_runtime": 7.0814,
      "eval_samples_per_second": 529.554,
      "eval_steps_per_second": 8.332,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 130.46458435058594,
      "learning_rate": 7e-05,
      "loss": 0.2752,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.3952251672744751,
      "eval_runtime": 7.9108,
      "eval_samples_per_second": 474.035,
      "eval_steps_per_second": 7.458,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 38.03357696533203,
      "learning_rate": 7e-05,
      "loss": 0.2132,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.3778655529022217,
      "eval_runtime": 7.6377,
      "eval_samples_per_second": 490.984,
      "eval_steps_per_second": 7.725,
      "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
}