trainer_state.json

{
  "best_metric": 0.8802666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0383/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 116.06025695800781,
      "learning_rate": 9e-05,
      "loss": 3.1647,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6181333333333333,
      "eval_loss": 1.5730739831924438,
      "eval_runtime": 13.4095,
      "eval_samples_per_second": 279.652,
      "eval_steps_per_second": 4.4,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 148.7941436767578,
      "learning_rate": 9e-05,
      "loss": 0.9641,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8064,
      "eval_loss": 0.6881924271583557,
      "eval_runtime": 13.1465,
      "eval_samples_per_second": 285.248,
      "eval_steps_per_second": 4.488,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 71.54553985595703,
      "learning_rate": 9e-05,
      "loss": 0.5603,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8434666666666667,
      "eval_loss": 0.5231713056564331,
      "eval_runtime": 13.2991,
      "eval_samples_per_second": 281.973,
      "eval_steps_per_second": 4.436,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 45.42745590209961,
      "learning_rate": 9e-05,
      "loss": 0.4037,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8594666666666667,
      "eval_loss": 0.4578052759170532,
      "eval_runtime": 13.3488,
      "eval_samples_per_second": 280.924,
      "eval_steps_per_second": 4.42,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 65.12864685058594,
      "learning_rate": 9e-05,
      "loss": 0.3088,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.4384918510913849,
      "eval_runtime": 13.2259,
      "eval_samples_per_second": 283.534,
      "eval_steps_per_second": 4.461,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 77.44757080078125,
      "learning_rate": 9e-05,
      "loss": 0.2387,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8757333333333334,
      "eval_loss": 0.4089867174625397,
      "eval_runtime": 13.7551,
      "eval_samples_per_second": 272.626,
      "eval_steps_per_second": 4.289,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 58.53445053100586,
      "learning_rate": 9e-05,
      "loss": 0.1908,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.876,
      "eval_loss": 0.43419837951660156,
      "eval_runtime": 13.5185,
      "eval_samples_per_second": 277.397,
      "eval_steps_per_second": 4.364,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 55.20626449584961,
      "learning_rate": 9e-05,
      "loss": 0.153,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.433310329914093,
      "eval_runtime": 13.2763,
      "eval_samples_per_second": 282.458,
      "eval_steps_per_second": 4.444,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 6.5411433916416e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}