trainer_state.json

{
  "best_metric": 0.45386666666666664,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0803/checkpoints/checkpoint-666",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 666,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 42.93849182128906,
      "learning_rate": 1.5e-05,
      "loss": 3.8615,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.33866666666666667,
      "eval_loss": 3.7777183055877686,
      "eval_runtime": 8.268,
      "eval_samples_per_second": 453.555,
      "eval_steps_per_second": 7.136,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 105.0693588256836,
      "learning_rate": 0.0,
      "loss": 3.6744,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.45386666666666664,
      "eval_loss": 3.631685495376587,
      "eval_runtime": 8.0262,
      "eval_samples_per_second": 467.218,
      "eval_steps_per_second": 7.351,
      "step": 666
    }
  ],
  "logging_steps": 500,
  "max_steps": 666,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.6352858479104e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}