trainer_state.json

{
  "best_metric": 0.7253333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0634/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": 99.33712005615234,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 3.8484,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3450666666666667,
      "eval_loss": 3.7095947265625,
      "eval_runtime": 8.6345,
      "eval_samples_per_second": 434.302,
      "eval_steps_per_second": 6.833,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 171.49215698242188,
      "learning_rate": 2.25e-05,
      "loss": 3.2602,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5448,
      "eval_loss": 2.764118194580078,
      "eval_runtime": 8.4876,
      "eval_samples_per_second": 441.82,
      "eval_steps_per_second": 6.951,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 198.27008056640625,
      "learning_rate": 1.5e-05,
      "loss": 2.0815,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6661333333333334,
      "eval_loss": 1.6156272888183594,
      "eval_runtime": 8.4634,
      "eval_samples_per_second": 443.082,
      "eval_steps_per_second": 6.971,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 232.23292541503906,
      "learning_rate": 7.500000000000004e-06,
      "loss": 1.3872,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7098666666666666,
      "eval_loss": 1.2579318284988403,
      "eval_runtime": 8.4758,
      "eval_samples_per_second": 442.437,
      "eval_steps_per_second": 6.961,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 109.50861358642578,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 1.1835,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7253333333333334,
      "eval_loss": 1.131042718887329,
      "eval_runtime": 8.556,
      "eval_samples_per_second": 438.287,
      "eval_steps_per_second": 6.896,
      "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
}