{
  "best_metric": 0.1803661435842514,
  "best_model_checkpoint": "./models/results_one_liners_47/checkpoint-250",
  "epoch": 0.721110510185686,
  "global_step": 250,
  "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": 0.7024,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6948,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.2e-05,
      "loss": 0.6917,
      "step": 24
    },
    {
      "epoch": 0.07,
      "eval_accuracy": 0.5394321766561514,
      "eval_f1": 0.6806649168853892,
      "eval_loss": 0.6824995279312134,
      "eval_precision": 0.5159151193633952,
      "eval_recall": 1.0,
      "eval_runtime": 14.6819,
      "eval_samples_per_second": 215.912,
      "eval_steps_per_second": 27.04,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.6767,
      "step": 32
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.6376,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.4e-05,
      "loss": 0.4677,
      "step": 48
    },
    {
      "epoch": 0.14,
      "eval_accuracy": 0.8384858044164037,
      "eval_f1": 0.8515942028985507,
      "eval_loss": 0.37244707345962524,
      "eval_precision": 0.7756071805702217,
      "eval_recall": 0.9440874035989717,
      "eval_runtime": 14.4869,
      "eval_samples_per_second": 218.818,
      "eval_steps_per_second": 27.404,
      "step": 50
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.4309,
      "step": 56
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.3928,
      "step": 64
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.6e-05,
      "loss": 0.4007,
      "step": 72
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.8406940063091483,
      "eval_f1": 0.8573043232551568,
      "eval_loss": 0.36749163269996643,
      "eval_precision": 0.7650025214321735,
      "eval_recall": 0.9749357326478149,
      "eval_runtime": 14.6324,
      "eval_samples_per_second": 216.643,
      "eval_steps_per_second": 27.132,
      "step": 75
    },
    {
      "epoch": 0.23,
      "learning_rate": 4e-05,
      "loss": 0.3881,
      "step": 80
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3478,
      "step": 88
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.8e-05,
      "loss": 0.3324,
      "step": 96
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.9094637223974763,
      "eval_f1": 0.9070294784580499,
      "eval_loss": 0.2337632179260254,
      "eval_precision": 0.914435009797518,
      "eval_recall": 0.8997429305912596,
      "eval_runtime": 14.2433,
      "eval_samples_per_second": 222.561,
      "eval_steps_per_second": 27.873,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.9186991869918704e-05,
      "loss": 0.2844,
      "step": 104
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.75609756097561e-05,
      "loss": 0.3181,
      "step": 112
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.59349593495935e-05,
      "loss": 0.3595,
      "step": 120
    },
    {
      "epoch": 0.36,
      "eval_accuracy": 0.8353312302839117,
      "eval_f1": 0.8033157498116051,
      "eval_loss": 0.3661021888256073,
      "eval_precision": 0.970856102003643,
      "eval_recall": 0.6850899742930592,
      "eval_runtime": 15.0232,
      "eval_samples_per_second": 211.007,
      "eval_steps_per_second": 26.426,
      "step": 125
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.451219512195122e-05,
      "loss": 0.3999,
      "step": 128
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.2886178861788616e-05,
      "loss": 0.2809,
      "step": 136
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.126016260162602e-05,
      "loss": 0.2538,
      "step": 144
    },
    {
      "epoch": 0.43,
      "eval_accuracy": 0.8905362776025236,
      "eval_f1": 0.8962630792227205,
      "eval_loss": 0.2805730998516083,
      "eval_precision": 0.8378982671883733,
      "eval_recall": 0.9633676092544987,
      "eval_runtime": 15.3124,
      "eval_samples_per_second": 207.021,
      "eval_steps_per_second": 25.927,
      "step": 150
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.9634146341463416e-05,
      "loss": 0.2226,
      "step": 152
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.800813008130081e-05,
      "loss": 0.2722,
      "step": 160
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.6382113821138216e-05,
      "loss": 0.2625,
      "step": 168
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.9123028391167193,
      "eval_f1": 0.9135572139303482,
      "eval_loss": 0.2242085486650467,
      "eval_precision": 0.8849397590361445,
      "eval_recall": 0.9440874035989717,
      "eval_runtime": 15.1268,
      "eval_samples_per_second": 209.561,
      "eval_steps_per_second": 26.245,
      "step": 175
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.475609756097561e-05,
      "loss": 0.2097,
      "step": 176
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.313008130081301e-05,
      "loss": 0.2623,
      "step": 184
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.150406504065041e-05,
      "loss": 0.2493,
      "step": 192
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.9878048780487805e-05,
      "loss": 0.2118,
      "step": 200
    },
    {
      "epoch": 0.58,
      "eval_accuracy": 0.9242902208201893,
      "eval_f1": 0.9222797927461142,
      "eval_loss": 0.19594888389110565,
      "eval_precision": 0.9295039164490861,
      "eval_recall": 0.9151670951156813,
      "eval_runtime": 15.3657,
      "eval_samples_per_second": 206.304,
      "eval_steps_per_second": 25.837,
      "step": 200
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.8252032520325205e-05,
      "loss": 0.267,
      "step": 208
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.66260162601626e-05,
      "loss": 0.2188,
      "step": 216
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.5e-05,
      "loss": 0.2165,
      "step": 224
    },
    {
      "epoch": 0.65,
      "eval_accuracy": 0.9293375394321767,
      "eval_f1": 0.9271307742355238,
      "eval_loss": 0.191427543759346,
      "eval_precision": 0.9387351778656127,
      "eval_recall": 0.9158097686375322,
      "eval_runtime": 14.3922,
      "eval_samples_per_second": 220.258,
      "eval_steps_per_second": 27.584,
      "step": 225
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.3373983739837398e-05,
      "loss": 0.1911,
      "step": 232
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.1747967479674798e-05,
      "loss": 0.2288,
      "step": 240
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.0121951219512197e-05,
      "loss": 0.2024,
      "step": 248
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.9296529968454259,
      "eval_f1": 0.9278550630863798,
      "eval_loss": 0.1803661435842514,
      "eval_precision": 0.9342019543973942,
      "eval_recall": 0.9215938303341902,
      "eval_runtime": 14.3698,
      "eval_samples_per_second": 220.602,
      "eval_steps_per_second": 27.627,
      "step": 250
    }
  ],
  "max_steps": 346,
  "num_train_epochs": 1,
  "total_flos": 476888787840000.0,
  "trial_name": null,
  "trial_params": null
}