trainer_state.json

{
  "best_metric": 0.8842666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0790/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": 209.1461944580078,
      "learning_rate": 0.0001,
      "loss": 2.8873,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7122666666666667,
      "eval_loss": 1.1274263858795166,
      "eval_runtime": 7.35,
      "eval_samples_per_second": 510.203,
      "eval_steps_per_second": 8.027,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 41.21769714355469,
      "learning_rate": 0.0001,
      "loss": 0.797,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8277333333333333,
      "eval_loss": 0.582065999507904,
      "eval_runtime": 7.5598,
      "eval_samples_per_second": 496.046,
      "eval_steps_per_second": 7.804,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 114.63006591796875,
      "learning_rate": 0.0001,
      "loss": 0.4944,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8685333333333334,
      "eval_loss": 0.4570496380329132,
      "eval_runtime": 7.5591,
      "eval_samples_per_second": 496.094,
      "eval_steps_per_second": 7.805,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 82.4994125366211,
      "learning_rate": 0.0001,
      "loss": 0.3476,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8776,
      "eval_loss": 0.4039926528930664,
      "eval_runtime": 7.558,
      "eval_samples_per_second": 496.163,
      "eval_steps_per_second": 7.806,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 64.44688415527344,
      "learning_rate": 0.0001,
      "loss": 0.2494,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8842666666666666,
      "eval_loss": 0.41334474086761475,
      "eval_runtime": 7.6288,
      "eval_samples_per_second": 491.559,
      "eval_steps_per_second": 7.734,
      "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
}