trainer_state.json

{
  "best_metric": 0.8584,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0904/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 101.41272735595703,
      "learning_rate": 7e-05,
      "loss": 3.237,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6205333333333334,
      "eval_loss": 1.535476803779602,
      "eval_runtime": 14.226,
      "eval_samples_per_second": 263.602,
      "eval_steps_per_second": 4.147,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 276.74456787109375,
      "learning_rate": 7e-05,
      "loss": 0.9611,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7829333333333334,
      "eval_loss": 0.7302079200744629,
      "eval_runtime": 14.1504,
      "eval_samples_per_second": 265.01,
      "eval_steps_per_second": 4.169,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 78.06999206542969,
      "learning_rate": 7e-05,
      "loss": 0.5538,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8216,
      "eval_loss": 0.5830641984939575,
      "eval_runtime": 14.1448,
      "eval_samples_per_second": 265.116,
      "eval_steps_per_second": 4.171,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 136.34625244140625,
      "learning_rate": 7e-05,
      "loss": 0.3661,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8410666666666666,
      "eval_loss": 0.5375491976737976,
      "eval_runtime": 13.6279,
      "eval_samples_per_second": 275.171,
      "eval_steps_per_second": 4.329,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 91.94203186035156,
      "learning_rate": 7e-05,
      "loss": 0.2578,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.5064823031425476,
      "eval_runtime": 13.988,
      "eval_samples_per_second": 268.086,
      "eval_steps_per_second": 4.218,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 66.75792694091797,
      "learning_rate": 7e-05,
      "loss": 0.1797,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8514666666666667,
      "eval_loss": 0.5206940174102783,
      "eval_runtime": 13.8635,
      "eval_samples_per_second": 270.494,
      "eval_steps_per_second": 4.256,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 121.04263305664062,
      "learning_rate": 7e-05,
      "loss": 0.1291,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8525333333333334,
      "eval_loss": 0.5376853942871094,
      "eval_runtime": 13.2318,
      "eval_samples_per_second": 283.409,
      "eval_steps_per_second": 4.459,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 157.86659240722656,
      "learning_rate": 7e-05,
      "loss": 0.0998,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.5366576910018921,
      "eval_runtime": 13.2771,
      "eval_samples_per_second": 282.442,
      "eval_steps_per_second": 4.444,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 6.5411433916416e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}