{
  "best_metric": 0.8011033681765389,
  "best_model_checkpoint": "./output_4/checkpoint-270",
  "epoch": 16.451612903225808,
  "eval_steps": 30,
  "global_step": 510,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.97,
      "learning_rate": 9.758064516129034e-06,
      "loss": 0.4653,
      "step": 30
    },
    {
      "epoch": 0.97,
      "eval_f1": 0.47104247104247104,
      "eval_loss": 0.34549078345298767,
      "eval_precision": 0.44525547445255476,
      "eval_recall": 0.5,
      "eval_runtime": 0.8351,
      "eval_samples_per_second": 164.048,
      "eval_steps_per_second": 5.987,
      "step": 30
    },
    {
      "epoch": 1.94,
      "learning_rate": 9.516129032258065e-06,
      "loss": 0.3365,
      "step": 60
    },
    {
      "epoch": 1.94,
      "eval_f1": 0.47104247104247104,
      "eval_loss": 0.33970290422439575,
      "eval_precision": 0.44525547445255476,
      "eval_recall": 0.5,
      "eval_runtime": 0.8593,
      "eval_samples_per_second": 159.439,
      "eval_steps_per_second": 5.819,
      "step": 60
    },
    {
      "epoch": 2.9,
      "learning_rate": 9.274193548387097e-06,
      "loss": 0.3174,
      "step": 90
    },
    {
      "epoch": 2.9,
      "eval_f1": 0.47104247104247104,
      "eval_loss": 0.3178149461746216,
      "eval_precision": 0.44525547445255476,
      "eval_recall": 0.5,
      "eval_runtime": 0.8461,
      "eval_samples_per_second": 161.924,
      "eval_steps_per_second": 5.91,
      "step": 90
    },
    {
      "epoch": 3.87,
      "learning_rate": 9.03225806451613e-06,
      "loss": 0.3154,
      "step": 120
    },
    {
      "epoch": 3.87,
      "eval_f1": 0.787531017369727,
      "eval_loss": 0.27127787470817566,
      "eval_precision": 0.8358585858585859,
      "eval_recall": 0.7543715846994535,
      "eval_runtime": 0.8477,
      "eval_samples_per_second": 161.61,
      "eval_steps_per_second": 5.898,
      "step": 120
    },
    {
      "epoch": 4.84,
      "learning_rate": 8.790322580645163e-06,
      "loss": 0.2477,
      "step": 150
    },
    {
      "epoch": 4.84,
      "eval_f1": 0.7579116465863454,
      "eval_loss": 0.2217591255903244,
      "eval_precision": 0.8185039370078739,
      "eval_recall": 0.7210382513661202,
      "eval_runtime": 0.8342,
      "eval_samples_per_second": 164.232,
      "eval_steps_per_second": 5.994,
      "step": 150
    },
    {
      "epoch": 5.81,
      "learning_rate": 8.548387096774194e-06,
      "loss": 0.1818,
      "step": 180
    },
    {
      "epoch": 5.81,
      "eval_f1": 0.7754098360655737,
      "eval_loss": 0.2334146499633789,
      "eval_precision": 0.7754098360655737,
      "eval_recall": 0.7754098360655737,
      "eval_runtime": 0.833,
      "eval_samples_per_second": 164.466,
      "eval_steps_per_second": 6.002,
      "step": 180
    },
    {
      "epoch": 6.77,
      "learning_rate": 8.306451612903227e-06,
      "loss": 0.1681,
      "step": 210
    },
    {
      "epoch": 6.77,
      "eval_f1": 0.6914948900051966,
      "eval_loss": 0.28801918029785156,
      "eval_precision": 0.7737403100775193,
      "eval_recall": 0.6543715846994536,
      "eval_runtime": 0.8432,
      "eval_samples_per_second": 162.485,
      "eval_steps_per_second": 5.93,
      "step": 210
    },
    {
      "epoch": 7.74,
      "learning_rate": 8.064516129032258e-06,
      "loss": 0.1128,
      "step": 240
    },
    {
      "epoch": 7.74,
      "eval_f1": 0.726,
      "eval_loss": 0.2648162841796875,
      "eval_precision": 0.7981770833333333,
      "eval_recall": 0.6877049180327869,
      "eval_runtime": 0.8446,
      "eval_samples_per_second": 162.204,
      "eval_steps_per_second": 5.92,
      "step": 240
    },
    {
      "epoch": 8.71,
      "learning_rate": 7.822580645161291e-06,
      "loss": 0.0989,
      "step": 270
    },
    {
      "epoch": 8.71,
      "eval_f1": 0.8011033681765389,
      "eval_loss": 0.2688542306423187,
      "eval_precision": 0.8219602977667494,
      "eval_recall": 0.7836065573770492,
      "eval_runtime": 0.8386,
      "eval_samples_per_second": 163.369,
      "eval_steps_per_second": 5.962,
      "step": 270
    },
    {
      "epoch": 9.68,
      "learning_rate": 7.580645161290323e-06,
      "loss": 0.09,
      "step": 300
    },
    {
      "epoch": 9.68,
      "eval_f1": 0.7716666666666667,
      "eval_loss": 0.27322623133659363,
      "eval_precision": 0.8576388888888888,
      "eval_recall": 0.7251366120218579,
      "eval_runtime": 0.8354,
      "eval_samples_per_second": 163.993,
      "eval_steps_per_second": 5.985,
      "step": 300
    },
    {
      "epoch": 10.65,
      "learning_rate": 7.338709677419356e-06,
      "loss": 0.0772,
      "step": 330
    },
    {
      "epoch": 10.65,
      "eval_f1": 0.7740290898185634,
      "eval_loss": 0.30010420083999634,
      "eval_precision": 0.8053333333333332,
      "eval_recall": 0.7502732240437158,
      "eval_runtime": 0.8358,
      "eval_samples_per_second": 163.909,
      "eval_steps_per_second": 5.982,
      "step": 330
    },
    {
      "epoch": 11.61,
      "learning_rate": 7.096774193548388e-06,
      "loss": 0.0616,
      "step": 360
    },
    {
      "epoch": 11.61,
      "eval_f1": 0.726,
      "eval_loss": 0.3184939920902252,
      "eval_precision": 0.7981770833333333,
      "eval_recall": 0.6877049180327869,
      "eval_runtime": 0.8427,
      "eval_samples_per_second": 162.575,
      "eval_steps_per_second": 5.933,
      "step": 360
    },
    {
      "epoch": 12.58,
      "learning_rate": 6.854838709677419e-06,
      "loss": 0.0476,
      "step": 390
    },
    {
      "epoch": 12.58,
      "eval_f1": 0.7215447154471545,
      "eval_loss": 0.36287298798561096,
      "eval_precision": 0.7369727047146402,
      "eval_recall": 0.708743169398907,
      "eval_runtime": 0.8413,
      "eval_samples_per_second": 162.849,
      "eval_steps_per_second": 5.943,
      "step": 390
    },
    {
      "epoch": 13.55,
      "learning_rate": 6.612903225806452e-06,
      "loss": 0.0331,
      "step": 420
    },
    {
      "epoch": 13.55,
      "eval_f1": 0.7878958479943701,
      "eval_loss": 0.3389006555080414,
      "eval_precision": 0.7970383275261324,
      "eval_recall": 0.7795081967213114,
      "eval_runtime": 0.8333,
      "eval_samples_per_second": 164.406,
      "eval_steps_per_second": 6.0,
      "step": 420
    },
    {
      "epoch": 14.52,
      "learning_rate": 6.370967741935485e-06,
      "loss": 0.0473,
      "step": 450
    },
    {
      "epoch": 14.52,
      "eval_f1": 0.7389572146197818,
      "eval_loss": 0.3224264681339264,
      "eval_precision": 0.8401162790697674,
      "eval_recall": 0.6918032786885246,
      "eval_runtime": 0.8344,
      "eval_samples_per_second": 164.2,
      "eval_steps_per_second": 5.993,
      "step": 450
    },
    {
      "epoch": 15.48,
      "learning_rate": 6.129032258064517e-06,
      "loss": 0.0342,
      "step": 480
    },
    {
      "epoch": 15.48,
      "eval_f1": 0.787531017369727,
      "eval_loss": 0.3013747036457062,
      "eval_precision": 0.8358585858585859,
      "eval_recall": 0.7543715846994535,
      "eval_runtime": 0.8339,
      "eval_samples_per_second": 164.295,
      "eval_steps_per_second": 5.996,
      "step": 480
    },
    {
      "epoch": 16.45,
      "learning_rate": 5.887096774193549e-06,
      "loss": 0.0374,
      "step": 510
    },
    {
      "epoch": 16.45,
      "eval_f1": 0.726,
      "eval_loss": 0.34248507022857666,
      "eval_precision": 0.7981770833333333,
      "eval_recall": 0.6877049180327869,
      "eval_runtime": 0.8368,
      "eval_samples_per_second": 163.722,
      "eval_steps_per_second": 5.975,
      "step": 510
    }
  ],
  "logging_steps": 30,
  "max_steps": 1240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 30,
  "total_flos": 415559245279680.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}