trainer_state.json

{
  "best_metric": 0.8365333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0404/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": 119.89279174804688,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.6489,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5557333333333333,
      "eval_loss": 3.126965045928955,
      "eval_runtime": 7.3725,
      "eval_samples_per_second": 508.65,
      "eval_steps_per_second": 8.003,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 142.5276336669922,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8778,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7493333333333333,
      "eval_loss": 1.062234878540039,
      "eval_runtime": 7.2138,
      "eval_samples_per_second": 519.839,
      "eval_steps_per_second": 8.179,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 138.70289611816406,
      "learning_rate": 2.5e-05,
      "loss": 0.8176,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8058666666666666,
      "eval_loss": 0.684458315372467,
      "eval_runtime": 7.2545,
      "eval_samples_per_second": 516.923,
      "eval_steps_per_second": 8.133,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 223.24932861328125,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5838,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8218666666666666,
      "eval_loss": 0.5960735082626343,
      "eval_runtime": 7.2036,
      "eval_samples_per_second": 520.576,
      "eval_steps_per_second": 8.19,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 80.33967590332031,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.4916,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8290666666666666,
      "eval_loss": 0.5685665607452393,
      "eval_runtime": 7.675,
      "eval_samples_per_second": 488.597,
      "eval_steps_per_second": 7.687,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 213.7762451171875,
      "learning_rate": 0.0,
      "loss": 0.4441,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8365333333333334,
      "eval_loss": 0.545439600944519,
      "eval_runtime": 7.266,
      "eval_samples_per_second": 516.105,
      "eval_steps_per_second": 8.12,
      "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
}