trainer_state.json

{
  "best_metric": 0.872,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0908/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": 45.90570068359375,
      "learning_rate": 0.0003,
      "loss": 1.6565,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8005333333333333,
      "eval_loss": 0.6361261606216431,
      "eval_runtime": 7.6807,
      "eval_samples_per_second": 488.234,
      "eval_steps_per_second": 7.682,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 35.996986389160156,
      "learning_rate": 0.0003,
      "loss": 0.5127,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8394666666666667,
      "eval_loss": 0.5160834193229675,
      "eval_runtime": 7.6726,
      "eval_samples_per_second": 488.754,
      "eval_steps_per_second": 7.69,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 35.17368698120117,
      "learning_rate": 0.0003,
      "loss": 0.3574,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8581333333333333,
      "eval_loss": 0.47224798798561096,
      "eval_runtime": 7.6502,
      "eval_samples_per_second": 490.181,
      "eval_steps_per_second": 7.712,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 32.656375885009766,
      "learning_rate": 0.0003,
      "loss": 0.2544,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.4403666853904724,
      "eval_runtime": 7.6718,
      "eval_samples_per_second": 488.806,
      "eval_steps_per_second": 7.691,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 47.244144439697266,
      "learning_rate": 0.0003,
      "loss": 0.1909,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.4635104238986969,
      "eval_runtime": 7.6192,
      "eval_samples_per_second": 492.175,
      "eval_steps_per_second": 7.744,
      "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
}