trainer_state.json

{
  "best_metric": 0.8928,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0139/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": 108.7696762084961,
      "learning_rate": 0.0002799038105676658,
      "loss": 1.5212,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8365333333333334,
      "eval_loss": 0.5152277946472168,
      "eval_runtime": 14.1668,
      "eval_samples_per_second": 264.703,
      "eval_steps_per_second": 4.165,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 75.5882797241211,
      "learning_rate": 0.000225,
      "loss": 0.4028,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8733333333333333,
      "eval_loss": 0.40600311756134033,
      "eval_runtime": 14.1482,
      "eval_samples_per_second": 265.051,
      "eval_steps_per_second": 4.17,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 48.938629150390625,
      "learning_rate": 0.00015,
      "loss": 0.2013,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8834666666666666,
      "eval_loss": 0.37761157751083374,
      "eval_runtime": 14.2154,
      "eval_samples_per_second": 263.798,
      "eval_steps_per_second": 4.15,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 46.66848373413086,
      "learning_rate": 7.500000000000002e-05,
      "loss": 0.0924,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.3942330777645111,
      "eval_runtime": 14.1526,
      "eval_samples_per_second": 264.969,
      "eval_steps_per_second": 4.169,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 37.652069091796875,
      "learning_rate": 2.009618943233419e-05,
      "loss": 0.0487,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8925333333333333,
      "eval_loss": 0.37461891770362854,
      "eval_runtime": 15.6199,
      "eval_samples_per_second": 240.079,
      "eval_steps_per_second": 3.777,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 40.50080871582031,
      "learning_rate": 0.0,
      "loss": 0.0355,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8928,
      "eval_loss": 0.3830954432487488,
      "eval_runtime": 14.2144,
      "eval_samples_per_second": 263.817,
      "eval_steps_per_second": 4.151,
      "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
}