trainer_state.json

{
  "best_metric": 0.8581333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0228/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": 24.97613525390625,
      "learning_rate": 0.0005,
      "loss": 1.3527,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8210666666666666,
      "eval_loss": 0.6060730218887329,
      "eval_runtime": 15.6616,
      "eval_samples_per_second": 239.44,
      "eval_steps_per_second": 3.767,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 33.604461669921875,
      "learning_rate": 0.0005,
      "loss": 0.4951,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8581333333333333,
      "eval_loss": 0.4794051945209503,
      "eval_runtime": 15.8339,
      "eval_samples_per_second": 236.834,
      "eval_steps_per_second": 3.726,
      "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
}