trainer_state.json

{
  "best_metric": 0.8533333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0325/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": 66.35484313964844,
      "learning_rate": 4.665063509461097e-05,
      "loss": 3.6379,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5424,
      "eval_loss": 2.9283246994018555,
      "eval_runtime": 8.3776,
      "eval_samples_per_second": 447.623,
      "eval_steps_per_second": 7.043,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 113.98226165771484,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.5813,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7813333333333333,
      "eval_loss": 0.870978593826294,
      "eval_runtime": 7.6209,
      "eval_samples_per_second": 492.068,
      "eval_steps_per_second": 7.742,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 308.8931884765625,
      "learning_rate": 2.5e-05,
      "loss": 0.7027,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8328,
      "eval_loss": 0.6315880417823792,
      "eval_runtime": 7.6952,
      "eval_samples_per_second": 487.314,
      "eval_steps_per_second": 7.667,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 182.27096557617188,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.5243,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8482666666666666,
      "eval_loss": 0.5308772921562195,
      "eval_runtime": 7.7308,
      "eval_samples_per_second": 485.073,
      "eval_steps_per_second": 7.632,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 117.05422973632812,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.4402,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8514666666666667,
      "eval_loss": 0.5204060077667236,
      "eval_runtime": 7.6587,
      "eval_samples_per_second": 489.642,
      "eval_steps_per_second": 7.704,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 104.51191711425781,
      "learning_rate": 0.0,
      "loss": 0.4191,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8533333333333334,
      "eval_loss": 0.5149610042572021,
      "eval_runtime": 7.7905,
      "eval_samples_per_second": 481.354,
      "eval_steps_per_second": 7.573,
      "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
}