{
  "best_metric": 0.6536160707473755,
  "best_model_checkpoint": "./SDG/checkpoint-1614",
  "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": 26.18483543395996,
      "learning_rate": 8.266666666666667e-06,
      "loss": 1.7444,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7685770625858339,
      "eval_loss": 0.8148266077041626,
      "eval_runtime": 22.0031,
      "eval_samples_per_second": 391.081,
      "eval_steps_per_second": 6.136,
      "step": 538
    },
    {
      "epoch": 1.858736059479554,
      "grad_norm": 14.726641654968262,
      "learning_rate": 8.105263157894736e-06,
      "loss": 0.7749,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.7999964392111495,
      "eval_loss": 0.7103919982910156,
      "eval_runtime": 22.0431,
      "eval_samples_per_second": 390.371,
      "eval_steps_per_second": 6.124,
      "step": 1076
    },
    {
      "epoch": 2.7881040892193307,
      "grad_norm": 18.681787490844727,
      "learning_rate": 5.717703349282297e-06,
      "loss": 0.6165,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.8113637968918935,
      "eval_loss": 0.6536160707473755,
      "eval_runtime": 22.0131,
      "eval_samples_per_second": 390.904,
      "eval_steps_per_second": 6.133,
      "step": 1614
    },
    {
      "epoch": 3.717472118959108,
      "grad_norm": 15.741679191589355,
      "learning_rate": 3.3253588516746417e-06,
      "loss": 0.5044,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.8140234226099499,
      "eval_loss": 0.6571179628372192,
      "eval_runtime": 22.0192,
      "eval_samples_per_second": 390.795,
      "eval_steps_per_second": 6.131,
      "step": 2152
    },
    {
      "epoch": 4.646840148698884,
      "grad_norm": 12.586956024169922,
      "learning_rate": 9.330143540669858e-07,
      "loss": 0.4217,
      "step": 2500
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.8154414212199751,
      "eval_loss": 0.6651344299316406,
      "eval_runtime": 21.8841,
      "eval_samples_per_second": 393.209,
      "eval_steps_per_second": 6.169,
      "step": 2690
    },
    {
      "epoch": 5.0,
      "step": 2690,
      "total_flos": 1.603929743474688e+17,
      "train_loss": 0.0,
      "train_runtime": 0.2765,
      "train_samples_per_second": 622394.733,
      "train_steps_per_second": 9728.308
    }
  ],
  "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": 1.603929743474688e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}