trainer_state.json

{
  "best_metric": 0.8568,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0501/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": 92.92230224609375,
      "learning_rate": 8.397114317029975e-05,
      "loss": 3.1073,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6605333333333333,
      "eval_loss": 1.3202406167984009,
      "eval_runtime": 8.2383,
      "eval_samples_per_second": 455.191,
      "eval_steps_per_second": 7.162,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 136.97714233398438,
      "learning_rate": 6.75e-05,
      "loss": 0.8996,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8056,
      "eval_loss": 0.6646373867988586,
      "eval_runtime": 7.4564,
      "eval_samples_per_second": 502.924,
      "eval_steps_per_second": 7.913,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 43.169532775878906,
      "learning_rate": 4.5e-05,
      "loss": 0.563,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8349333333333333,
      "eval_loss": 0.543608546257019,
      "eval_runtime": 7.4643,
      "eval_samples_per_second": 502.388,
      "eval_steps_per_second": 7.904,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 57.093868255615234,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.4368,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8501333333333333,
      "eval_loss": 0.4873361885547638,
      "eval_runtime": 7.5283,
      "eval_samples_per_second": 498.121,
      "eval_steps_per_second": 7.837,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 132.63845825195312,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.3901,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.47414055466651917,
      "eval_runtime": 7.9702,
      "eval_samples_per_second": 470.5,
      "eval_steps_per_second": 7.403,
      "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
}