trainer_state.json

{
  "best_metric": 0.9026666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0752/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 196.6171875,
      "learning_rate": 0.0001,
      "loss": 2.6941,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7549333333333333,
      "eval_loss": 0.8945394158363342,
      "eval_runtime": 15.3475,
      "eval_samples_per_second": 244.34,
      "eval_steps_per_second": 3.844,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 116.71843719482422,
      "learning_rate": 0.0001,
      "loss": 0.6501,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.4688388705253601,
      "eval_runtime": 15.4495,
      "eval_samples_per_second": 242.726,
      "eval_steps_per_second": 3.819,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 46.888519287109375,
      "learning_rate": 0.0001,
      "loss": 0.4115,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8834666666666666,
      "eval_loss": 0.4000551402568817,
      "eval_runtime": 15.4122,
      "eval_samples_per_second": 243.314,
      "eval_steps_per_second": 3.828,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 91.77472686767578,
      "learning_rate": 0.0001,
      "loss": 0.3065,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.3776249885559082,
      "eval_runtime": 15.419,
      "eval_samples_per_second": 243.207,
      "eval_steps_per_second": 3.826,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 33.21451187133789,
      "learning_rate": 0.0001,
      "loss": 0.2386,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.35203179717063904,
      "eval_runtime": 15.3873,
      "eval_samples_per_second": 243.707,
      "eval_steps_per_second": 3.834,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 75.54466247558594,
      "learning_rate": 0.0001,
      "loss": 0.1795,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9026666666666666,
      "eval_loss": 0.33782488107681274,
      "eval_runtime": 15.5079,
      "eval_samples_per_second": 241.812,
      "eval_steps_per_second": 3.805,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}