trainer_state.json

{
  "best_metric": 0.8576,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0639/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": 183.95230102539062,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.6645,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5541333333333334,
      "eval_loss": 3.1514663696289062,
      "eval_runtime": 7.9792,
      "eval_samples_per_second": 469.974,
      "eval_steps_per_second": 7.394,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 328.8116760253906,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8499,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7402666666666666,
      "eval_loss": 1.0569822788238525,
      "eval_runtime": 8.0242,
      "eval_samples_per_second": 467.335,
      "eval_steps_per_second": 7.353,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 291.20794677734375,
      "learning_rate": 2.5e-05,
      "loss": 0.8094,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8194666666666667,
      "eval_loss": 0.6482560634613037,
      "eval_runtime": 8.015,
      "eval_samples_per_second": 467.875,
      "eval_steps_per_second": 7.361,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 221.61351013183594,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5672,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8466666666666667,
      "eval_loss": 0.5422224998474121,
      "eval_runtime": 8.4496,
      "eval_samples_per_second": 443.808,
      "eval_steps_per_second": 6.983,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 59.2332878112793,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.4767,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8576,
      "eval_loss": 0.5063601136207581,
      "eval_runtime": 7.9078,
      "eval_samples_per_second": 474.215,
      "eval_steps_per_second": 7.461,
      "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
}