{
  "best_metric": 0.1858806610107422,
  "best_model_checkpoint": "./models/results_one_liners_977/checkpoint-325",
  "epoch": 0.9374436632413917,
  "global_step": 325,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6981,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6942,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.2e-05,
      "loss": 0.6922,
      "step": 24
    },
    {
      "epoch": 0.07,
      "eval_accuracy": 0.5154574132492113,
      "eval_f1": 0.6695352839931153,
      "eval_loss": 0.6819674968719482,
      "eval_precision": 0.5032341526520052,
      "eval_recall": 1.0,
      "eval_runtime": 20.0554,
      "eval_samples_per_second": 158.062,
      "eval_steps_per_second": 19.795,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.6758,
      "step": 32
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.6063,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.4e-05,
      "loss": 0.4676,
      "step": 48
    },
    {
      "epoch": 0.14,
      "eval_accuracy": 0.8643533123028391,
      "eval_f1": 0.8701690821256038,
      "eval_loss": 0.32924458384513855,
      "eval_precision": 0.820615034168565,
      "eval_recall": 0.9260925449871465,
      "eval_runtime": 19.9782,
      "eval_samples_per_second": 158.673,
      "eval_steps_per_second": 19.872,
      "step": 50
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.3596,
      "step": 56
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.3063,
      "step": 64
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.6e-05,
      "loss": 0.3641,
      "step": 72
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.886435331230284,
      "eval_f1": 0.8778833107191316,
      "eval_loss": 0.28779253363609314,
      "eval_precision": 0.9295977011494253,
      "eval_recall": 0.8316195372750642,
      "eval_runtime": 20.0332,
      "eval_samples_per_second": 158.237,
      "eval_steps_per_second": 19.817,
      "step": 75
    },
    {
      "epoch": 0.23,
      "learning_rate": 4e-05,
      "loss": 0.3659,
      "step": 80
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.256,
      "step": 88
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.8e-05,
      "loss": 0.2936,
      "step": 96
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.8936908517350157,
      "eval_f1": 0.8964669738863287,
      "eval_loss": 0.26408979296684265,
      "eval_precision": 0.8587404355503238,
      "eval_recall": 0.9376606683804627,
      "eval_runtime": 19.9923,
      "eval_samples_per_second": 158.561,
      "eval_steps_per_second": 19.858,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.9186991869918704e-05,
      "loss": 0.3169,
      "step": 104
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.75609756097561e-05,
      "loss": 0.2808,
      "step": 112
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.59349593495935e-05,
      "loss": 0.2615,
      "step": 120
    },
    {
      "epoch": 0.36,
      "eval_accuracy": 0.9066246056782334,
      "eval_f1": 0.9083591331269351,
      "eval_loss": 0.2332078069448471,
      "eval_precision": 0.8763440860215054,
      "eval_recall": 0.9428020565552699,
      "eval_runtime": 20.0114,
      "eval_samples_per_second": 158.41,
      "eval_steps_per_second": 19.839,
      "step": 125
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.43089430894309e-05,
      "loss": 0.2801,
      "step": 128
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.26829268292683e-05,
      "loss": 0.2454,
      "step": 136
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.105691056910569e-05,
      "loss": 0.2407,
      "step": 144
    },
    {
      "epoch": 0.43,
      "eval_accuracy": 0.8965299684542587,
      "eval_f1": 0.9015606242496998,
      "eval_loss": 0.25834545493125916,
      "eval_precision": 0.8457207207207207,
      "eval_recall": 0.9652956298200515,
      "eval_runtime": 19.9859,
      "eval_samples_per_second": 158.611,
      "eval_steps_per_second": 19.864,
      "step": 150
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.943089430894309e-05,
      "loss": 0.2835,
      "step": 152
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.780487804878049e-05,
      "loss": 0.2684,
      "step": 160
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.617886178861789e-05,
      "loss": 0.2493,
      "step": 168
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.9018927444794953,
      "eval_f1": 0.895180316818335,
      "eval_loss": 0.25140437483787537,
      "eval_precision": 0.9411764705882353,
      "eval_recall": 0.8534704370179949,
      "eval_runtime": 19.9806,
      "eval_samples_per_second": 158.654,
      "eval_steps_per_second": 19.869,
      "step": 175
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.4552845528455286e-05,
      "loss": 0.2957,
      "step": 176
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.292682926829269e-05,
      "loss": 0.2412,
      "step": 184
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.150406504065041e-05,
      "loss": 0.2066,
      "step": 192
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.9878048780487805e-05,
      "loss": 0.2657,
      "step": 200
    },
    {
      "epoch": 0.58,
      "eval_accuracy": 0.9201892744479495,
      "eval_f1": 0.9199620373299588,
      "eval_loss": 0.2050713449716568,
      "eval_precision": 0.9059190031152647,
      "eval_recall": 0.9344473007712082,
      "eval_runtime": 20.0006,
      "eval_samples_per_second": 158.495,
      "eval_steps_per_second": 19.849,
      "step": 200
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.8252032520325205e-05,
      "loss": 0.2702,
      "step": 208
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.66260162601626e-05,
      "loss": 0.2435,
      "step": 216
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.5e-05,
      "loss": 0.2281,
      "step": 224
    },
    {
      "epoch": 0.65,
      "eval_accuracy": 0.905993690851735,
      "eval_f1": 0.9101326899879373,
      "eval_loss": 0.23607869446277618,
      "eval_precision": 0.8573863636363637,
      "eval_recall": 0.9697943444730077,
      "eval_runtime": 19.9795,
      "eval_samples_per_second": 158.663,
      "eval_steps_per_second": 19.87,
      "step": 225
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.3373983739837398e-05,
      "loss": 0.233,
      "step": 232
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.1747967479674798e-05,
      "loss": 0.2294,
      "step": 240
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.0121951219512197e-05,
      "loss": 0.1933,
      "step": 248
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.9186119873817035,
      "eval_f1": 0.9201732673267328,
      "eval_loss": 0.206766277551651,
      "eval_precision": 0.8872315035799523,
      "eval_recall": 0.955655526992288,
      "eval_runtime": 19.9867,
      "eval_samples_per_second": 158.605,
      "eval_steps_per_second": 19.863,
      "step": 250
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.8495934959349594e-05,
      "loss": 0.2417,
      "step": 256
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.6869918699186994e-05,
      "loss": 0.213,
      "step": 264
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.524390243902439e-05,
      "loss": 0.1522,
      "step": 272
    },
    {
      "epoch": 0.79,
      "eval_accuracy": 0.9277602523659306,
      "eval_f1": 0.9273707580082461,
      "eval_loss": 0.21532806754112244,
      "eval_precision": 0.915466499686913,
      "eval_recall": 0.9395886889460154,
      "eval_runtime": 20.029,
      "eval_samples_per_second": 158.27,
      "eval_steps_per_second": 19.821,
      "step": 275
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.3617886178861788e-05,
      "loss": 0.2011,
      "step": 280
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.1991869918699188e-05,
      "loss": 0.2349,
      "step": 288
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0365853658536585e-05,
      "loss": 0.2403,
      "step": 296
    },
    {
      "epoch": 0.87,
      "eval_accuracy": 0.9271293375394322,
      "eval_f1": 0.9257473481195757,
      "eval_loss": 0.1873028576374054,
      "eval_precision": 0.9260450160771704,
      "eval_recall": 0.9254498714652957,
      "eval_runtime": 19.9617,
      "eval_samples_per_second": 158.804,
      "eval_steps_per_second": 19.888,
      "step": 300
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.739837398373985e-06,
      "loss": 0.1999,
      "step": 304
    },
    {
      "epoch": 0.9,
      "learning_rate": 7.113821138211382e-06,
      "loss": 0.1742,
      "step": 312
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.487804878048781e-06,
      "loss": 0.1809,
      "step": 320
    },
    {
      "epoch": 0.94,
      "eval_accuracy": 0.9277602523659306,
      "eval_f1": 0.9287713841368586,
      "eval_loss": 0.1858806610107422,
      "eval_precision": 0.8999397227245328,
      "eval_recall": 0.9595115681233933,
      "eval_runtime": 20.0389,
      "eval_samples_per_second": 158.192,
      "eval_steps_per_second": 19.811,
      "step": 325
    }
  ],
  "max_steps": 346,
  "num_train_epochs": 1,
  "total_flos": 619955424192000.0,
  "trial_name": null,
  "trial_params": null
}