{
  "best_metric": 0.7055376768112183,
  "best_model_checkpoint": "./bert-sdg-classification/checkpoint-2690",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 2690,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.929368029739777,
      "grad_norm": 6.427302360534668,
      "learning_rate": 8.3e-06,
      "loss": 2.2299,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.711832686368243,
      "eval_loss": 1.0520464181900024,
      "eval_runtime": 10.5177,
      "eval_samples_per_second": 818.142,
      "eval_steps_per_second": 12.835,
      "step": 538
    },
    {
      "epoch": 1.858736059479554,
      "grad_norm": 4.113575458526611,
      "learning_rate": 8.095693779904307e-06,
      "loss": 0.9383,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.7794402559050377,
      "eval_loss": 0.7799968719482422,
      "eval_runtime": 10.5039,
      "eval_samples_per_second": 819.222,
      "eval_steps_per_second": 12.852,
      "step": 1076
    },
    {
      "epoch": 2.7881040892193307,
      "grad_norm": 6.160844802856445,
      "learning_rate": 5.70334928229665e-06,
      "loss": 0.7379,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.794722683984857,
      "eval_loss": 0.7253227233886719,
      "eval_runtime": 10.4924,
      "eval_samples_per_second": 820.119,
      "eval_steps_per_second": 12.866,
      "step": 1614
    },
    {
      "epoch": 3.717472118959108,
      "grad_norm": 6.640861511230469,
      "learning_rate": 3.3110047846889954e-06,
      "loss": 0.6362,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.7964522651875893,
      "eval_loss": 0.7107406854629517,
      "eval_runtime": 10.5173,
      "eval_samples_per_second": 818.179,
      "eval_steps_per_second": 12.836,
      "step": 2152
    },
    {
      "epoch": 4.646840148698884,
      "grad_norm": 5.86486291885376,
      "learning_rate": 9.186602870813398e-07,
      "loss": 0.5779,
      "step": 2500
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.7979962127908091,
      "eval_loss": 0.7055376768112183,
      "eval_runtime": 10.5314,
      "eval_samples_per_second": 817.079,
      "eval_steps_per_second": 12.819,
      "step": 2690
    },
    {
      "epoch": 5.0,
      "step": 2690,
      "total_flos": 4.52871045169152e+16,
      "train_loss": 0.9906343055923632,
      "train_runtime": 639.5262,
      "train_samples_per_second": 269.105,
      "train_steps_per_second": 4.206
    }
  ],
  "logging_steps": 500,
  "max_steps": 2690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.52871045169152e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}