trainer_state.json

{
  "best_metric": 0.8669333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0702/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": 252.95956420898438,
      "learning_rate": 7e-05,
      "loss": 3.3278,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6173333333333333,
      "eval_loss": 1.7155051231384277,
      "eval_runtime": 15.2348,
      "eval_samples_per_second": 246.147,
      "eval_steps_per_second": 3.873,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 67.90617370605469,
      "learning_rate": 7e-05,
      "loss": 1.0371,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8125333333333333,
      "eval_loss": 0.6649861931800842,
      "eval_runtime": 15.2427,
      "eval_samples_per_second": 246.019,
      "eval_steps_per_second": 3.871,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 127.89303588867188,
      "learning_rate": 7e-05,
      "loss": 0.5874,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8442666666666667,
      "eval_loss": 0.5196150541305542,
      "eval_runtime": 15.4514,
      "eval_samples_per_second": 242.696,
      "eval_steps_per_second": 3.818,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 71.48004150390625,
      "learning_rate": 7e-05,
      "loss": 0.4345,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8546666666666667,
      "eval_loss": 0.4765242040157318,
      "eval_runtime": 15.2798,
      "eval_samples_per_second": 245.422,
      "eval_steps_per_second": 3.861,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 119.4044418334961,
      "learning_rate": 7e-05,
      "loss": 0.3552,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8669333333333333,
      "eval_loss": 0.440817266702652,
      "eval_runtime": 15.2362,
      "eval_samples_per_second": 246.125,
      "eval_steps_per_second": 3.872,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}