trainer_state.json

{
  "best_metric": 0.9074666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0809/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 47.30839920043945,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.1709,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.4874499440193176,
      "eval_runtime": 7.9676,
      "eval_samples_per_second": 470.658,
      "eval_steps_per_second": 7.405,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 26.652305603027344,
      "learning_rate": 0.000375,
      "loss": 0.3431,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8765333333333334,
      "eval_loss": 0.4035748243331909,
      "eval_runtime": 7.8477,
      "eval_samples_per_second": 477.848,
      "eval_steps_per_second": 7.518,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 33.44648361206055,
      "learning_rate": 0.00025,
      "loss": 0.1662,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8984,
      "eval_loss": 0.37462857365608215,
      "eval_runtime": 7.8505,
      "eval_samples_per_second": 477.678,
      "eval_steps_per_second": 7.515,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 21.38155174255371,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.073,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9053333333333333,
      "eval_loss": 0.3692944049835205,
      "eval_runtime": 7.8072,
      "eval_samples_per_second": 480.325,
      "eval_steps_per_second": 7.557,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 20.22939109802246,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.0334,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9074666666666666,
      "eval_loss": 0.3719710409641266,
      "eval_runtime": 7.807,
      "eval_samples_per_second": 480.338,
      "eval_steps_per_second": 7.557,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}