trainer_state.json

{
  "best_metric": 0.8877333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0503/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": 219.45872497558594,
      "learning_rate": 9e-05,
      "loss": 2.9427,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7074666666666667,
      "eval_loss": 1.117897629737854,
      "eval_runtime": 7.993,
      "eval_samples_per_second": 469.159,
      "eval_steps_per_second": 7.381,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 85.66268920898438,
      "learning_rate": 9e-05,
      "loss": 0.7761,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8338666666666666,
      "eval_loss": 0.5666635632514954,
      "eval_runtime": 7.8668,
      "eval_samples_per_second": 476.685,
      "eval_steps_per_second": 7.5,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 58.03054428100586,
      "learning_rate": 9e-05,
      "loss": 0.4823,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8517333333333333,
      "eval_loss": 0.4898325502872467,
      "eval_runtime": 7.9136,
      "eval_samples_per_second": 473.87,
      "eval_steps_per_second": 7.456,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 131.60684204101562,
      "learning_rate": 9e-05,
      "loss": 0.3458,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8664,
      "eval_loss": 0.44740527868270874,
      "eval_runtime": 8.1024,
      "eval_samples_per_second": 462.825,
      "eval_steps_per_second": 7.282,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 96.35740661621094,
      "learning_rate": 9e-05,
      "loss": 0.2615,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.40825626254081726,
      "eval_runtime": 7.9065,
      "eval_samples_per_second": 474.295,
      "eval_steps_per_second": 7.462,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 94.32246398925781,
      "learning_rate": 9e-05,
      "loss": 0.1959,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8877333333333334,
      "eval_loss": 0.39901742339134216,
      "eval_runtime": 7.9139,
      "eval_samples_per_second": 473.85,
      "eval_steps_per_second": 7.455,
      "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
}