trainer_state.json

{
  "best_metric": 0.9064,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0055/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": 82.46541595458984,
      "learning_rate": 9e-05,
      "loss": 2.8134,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7730666666666667,
      "eval_loss": 0.8696352243423462,
      "eval_runtime": 14.2893,
      "eval_samples_per_second": 262.435,
      "eval_steps_per_second": 4.129,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 179.63124084472656,
      "learning_rate": 9e-05,
      "loss": 0.5962,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8722666666666666,
      "eval_loss": 0.42600664496421814,
      "eval_runtime": 14.5054,
      "eval_samples_per_second": 258.525,
      "eval_steps_per_second": 4.067,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 56.094303131103516,
      "learning_rate": 9e-05,
      "loss": 0.3293,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8813333333333333,
      "eval_loss": 0.3795141577720642,
      "eval_runtime": 14.544,
      "eval_samples_per_second": 257.838,
      "eval_steps_per_second": 4.057,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 124.39602661132812,
      "learning_rate": 9e-05,
      "loss": 0.212,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8984,
      "eval_loss": 0.31779685616493225,
      "eval_runtime": 14.512,
      "eval_samples_per_second": 258.406,
      "eval_steps_per_second": 4.066,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 79.77652740478516,
      "learning_rate": 9e-05,
      "loss": 0.1393,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9064,
      "eval_loss": 0.308061808347702,
      "eval_runtime": 14.4903,
      "eval_samples_per_second": 258.794,
      "eval_steps_per_second": 4.072,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}