{
  "best_metric": 0.9770992366412214,
  "best_model_checkpoint": "runs/checkpoint-100",
  "epoch": 47.61904761904762,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.761904761904762,
      "eval_accuracy": 0.9848484848484849,
      "eval_f1": 0.9770992366412214,
      "eval_loss": 0.41740721464157104,
      "eval_precision": 0.9696969696969697,
      "eval_recall": 0.9846153846153847,
      "eval_runtime": 1.0787,
      "eval_samples_per_second": 10.198,
      "eval_steps_per_second": 5.562,
      "step": 100
    },
    {
      "epoch": 9.523809523809524,
      "eval_accuracy": 0.9848484848484849,
      "eval_f1": 0.9770992366412214,
      "eval_loss": 0.13825227320194244,
      "eval_precision": 0.9696969696969697,
      "eval_recall": 0.9846153846153847,
      "eval_runtime": 1.0798,
      "eval_samples_per_second": 10.187,
      "eval_steps_per_second": 5.557,
      "step": 200
    },
    {
      "epoch": 14.285714285714286,
      "eval_accuracy": 0.9848484848484849,
      "eval_f1": 0.9770992366412214,
      "eval_loss": 0.12092168629169464,
      "eval_precision": 0.9696969696969697,
      "eval_recall": 0.9846153846153847,
      "eval_runtime": 1.0872,
      "eval_samples_per_second": 10.118,
      "eval_steps_per_second": 5.519,
      "step": 300
    },
    {
      "epoch": 19.047619047619047,
      "eval_accuracy": 0.9848484848484849,
      "eval_f1": 0.9770992366412214,
      "eval_loss": 0.1149166151881218,
      "eval_precision": 0.9696969696969697,
      "eval_recall": 0.9846153846153847,
      "eval_runtime": 1.0776,
      "eval_samples_per_second": 10.207,
      "eval_steps_per_second": 5.568,
      "step": 400
    },
    {
      "epoch": 23.80952380952381,
      "grad_norm": 0.193642720580101,
      "learning_rate": 5e-06,
      "loss": 0.4353,
      "step": 500
    },
    {
      "epoch": 23.80952380952381,
      "eval_accuracy": 0.9848484848484849,
      "eval_f1": 0.9770992366412214,
      "eval_loss": 0.11741998791694641,
      "eval_precision": 0.9696969696969697,
      "eval_recall": 0.9846153846153847,
      "eval_runtime": 1.0827,
      "eval_samples_per_second": 10.16,
      "eval_steps_per_second": 5.542,
      "step": 500
    },
    {
      "epoch": 28.571428571428573,
      "eval_accuracy": 0.9797979797979798,
      "eval_f1": 0.9720101781170484,
      "eval_loss": 0.12016713619232178,
      "eval_precision": 0.9646464646464646,
      "eval_recall": 0.9794871794871794,
      "eval_runtime": 1.0882,
      "eval_samples_per_second": 10.109,
      "eval_steps_per_second": 5.514,
      "step": 600
    },
    {
      "epoch": 33.333333333333336,
      "eval_accuracy": 0.9797979797979798,
      "eval_f1": 0.9720101781170484,
      "eval_loss": 0.12300793826580048,
      "eval_precision": 0.9646464646464646,
      "eval_recall": 0.9794871794871794,
      "eval_runtime": 1.0808,
      "eval_samples_per_second": 10.177,
      "eval_steps_per_second": 5.551,
      "step": 700
    },
    {
      "epoch": 38.095238095238095,
      "eval_accuracy": 0.9797979797979798,
      "eval_f1": 0.9720101781170484,
      "eval_loss": 0.1282433569431305,
      "eval_precision": 0.9646464646464646,
      "eval_recall": 0.9794871794871794,
      "eval_runtime": 1.0811,
      "eval_samples_per_second": 10.175,
      "eval_steps_per_second": 5.55,
      "step": 800
    },
    {
      "epoch": 42.857142857142854,
      "eval_accuracy": 0.9797979797979798,
      "eval_f1": 0.9720101781170484,
      "eval_loss": 0.13098198175430298,
      "eval_precision": 0.9646464646464646,
      "eval_recall": 0.9794871794871794,
      "eval_runtime": 1.0833,
      "eval_samples_per_second": 10.154,
      "eval_steps_per_second": 5.539,
      "step": 900
    },
    {
      "epoch": 47.61904761904762,
      "grad_norm": 0.1277465969324112,
      "learning_rate": 0.0,
      "loss": 0.0298,
      "step": 1000
    },
    {
      "epoch": 47.61904761904762,
      "eval_accuracy": 0.9797979797979798,
      "eval_f1": 0.9720101781170484,
      "eval_loss": 0.13182279467582703,
      "eval_precision": 0.9646464646464646,
      "eval_recall": 0.9794871794871794,
      "eval_runtime": 1.1394,
      "eval_samples_per_second": 9.654,
      "eval_steps_per_second": 5.266,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 48,
  "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": 518410697591808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}