trainer_state.json

{
  "best_metric": 0.904,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0333/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": 153.74017333984375,
      "learning_rate": 0.0001,
      "loss": 2.5307,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7965333333333333,
      "eval_loss": 0.7427641749382019,
      "eval_runtime": 13.7159,
      "eval_samples_per_second": 273.406,
      "eval_steps_per_second": 4.302,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 300.6634216308594,
      "learning_rate": 0.0001,
      "loss": 0.5466,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8653333333333333,
      "eval_loss": 0.44248929619789124,
      "eval_runtime": 13.5008,
      "eval_samples_per_second": 277.762,
      "eval_steps_per_second": 4.37,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 180.1179962158203,
      "learning_rate": 0.0001,
      "loss": 0.3188,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.35773855447769165,
      "eval_runtime": 13.54,
      "eval_samples_per_second": 276.958,
      "eval_steps_per_second": 4.357,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 103.33956909179688,
      "learning_rate": 0.0001,
      "loss": 0.2043,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8965333333333333,
      "eval_loss": 0.340351939201355,
      "eval_runtime": 13.4456,
      "eval_samples_per_second": 278.902,
      "eval_steps_per_second": 4.388,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 110.30799102783203,
      "learning_rate": 0.0001,
      "loss": 0.1318,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9013333333333333,
      "eval_loss": 0.3447939157485962,
      "eval_runtime": 13.4649,
      "eval_samples_per_second": 278.503,
      "eval_steps_per_second": 4.382,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 139.0595703125,
      "learning_rate": 0.0001,
      "loss": 0.0908,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.904,
      "eval_loss": 0.34927335381507874,
      "eval_runtime": 13.4637,
      "eval_samples_per_second": 278.526,
      "eval_steps_per_second": 4.382,
      "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
}