trainer_state.json

{
  "best_metric": 0.8842666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0190/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": 295.95098876953125,
      "learning_rate": 8.397114317029975e-05,
      "loss": 2.8394,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7442666666666666,
      "eval_loss": 1.0247621536254883,
      "eval_runtime": 13.7657,
      "eval_samples_per_second": 272.416,
      "eval_steps_per_second": 4.286,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 77.05818176269531,
      "learning_rate": 6.75e-05,
      "loss": 0.7514,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8408,
      "eval_loss": 0.5286438465118408,
      "eval_runtime": 13.436,
      "eval_samples_per_second": 279.102,
      "eval_steps_per_second": 4.391,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 46.172672271728516,
      "learning_rate": 4.5e-05,
      "loss": 0.4629,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8714666666666666,
      "eval_loss": 0.40172266960144043,
      "eval_runtime": 13.5657,
      "eval_samples_per_second": 276.433,
      "eval_steps_per_second": 4.349,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 197.79446411132812,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.3562,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8738666666666667,
      "eval_loss": 0.39912110567092896,
      "eval_runtime": 13.4985,
      "eval_samples_per_second": 277.809,
      "eval_steps_per_second": 4.371,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 99.44869232177734,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.298,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8842666666666666,
      "eval_loss": 0.37280866503715515,
      "eval_runtime": 13.3999,
      "eval_samples_per_second": 279.853,
      "eval_steps_per_second": 4.403,
      "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
}