{
  "best_metric": 0.9333333333333333,
  "best_model_checkpoint": "checkpoint-llm-dist-llm-label/checkpoint-620",
  "epoch": 5.0,
  "global_step": 620,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 9.806451612903226e-05,
      "loss": 1.4271,
      "step": 12
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.612903225806452e-05,
      "loss": 1.4115,
      "step": 24
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.419354838709677e-05,
      "loss": 1.3136,
      "step": 36
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.225806451612904e-05,
      "loss": 1.0853,
      "step": 48
    },
    {
      "epoch": 0.48,
      "learning_rate": 9.032258064516129e-05,
      "loss": 1.0351,
      "step": 60
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.838709677419355e-05,
      "loss": 1.0471,
      "step": 72
    },
    {
      "epoch": 0.68,
      "learning_rate": 8.645161290322581e-05,
      "loss": 0.7519,
      "step": 84
    },
    {
      "epoch": 0.77,
      "learning_rate": 8.451612903225808e-05,
      "loss": 0.6824,
      "step": 96
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.258064516129033e-05,
      "loss": 0.4936,
      "step": 108
    },
    {
      "epoch": 0.97,
      "learning_rate": 8.064516129032258e-05,
      "loss": 0.5984,
      "step": 120
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8769230769230769,
      "eval_loss": 0.5207357406616211,
      "eval_runtime": 5.3806,
      "eval_samples_per_second": 36.241,
      "eval_steps_per_second": 4.646,
      "step": 124
    },
    {
      "epoch": 1.06,
      "learning_rate": 7.870967741935484e-05,
      "loss": 0.7002,
      "step": 132
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.67741935483871e-05,
      "loss": 0.5281,
      "step": 144
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.483870967741936e-05,
      "loss": 0.4103,
      "step": 156
    },
    {
      "epoch": 1.35,
      "learning_rate": 7.290322580645161e-05,
      "loss": 0.2259,
      "step": 168
    },
    {
      "epoch": 1.45,
      "learning_rate": 7.096774193548388e-05,
      "loss": 0.7418,
      "step": 180
    },
    {
      "epoch": 1.55,
      "learning_rate": 6.903225806451613e-05,
      "loss": 0.8794,
      "step": 192
    },
    {
      "epoch": 1.65,
      "learning_rate": 6.709677419354839e-05,
      "loss": 0.3744,
      "step": 204
    },
    {
      "epoch": 1.74,
      "learning_rate": 6.516129032258065e-05,
      "loss": 0.5089,
      "step": 216
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.32258064516129e-05,
      "loss": 0.438,
      "step": 228
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.129032258064517e-05,
      "loss": 0.6729,
      "step": 240
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9230769230769231,
      "eval_loss": 0.3991715610027313,
      "eval_runtime": 5.4603,
      "eval_samples_per_second": 35.712,
      "eval_steps_per_second": 4.578,
      "step": 248
    },
    {
      "epoch": 2.03,
      "learning_rate": 5.935483870967742e-05,
      "loss": 0.466,
      "step": 252
    },
    {
      "epoch": 2.13,
      "learning_rate": 5.7419354838709685e-05,
      "loss": 0.3185,
      "step": 264
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.5483870967741936e-05,
      "loss": 0.6499,
      "step": 276
    },
    {
      "epoch": 2.32,
      "learning_rate": 5.35483870967742e-05,
      "loss": 0.2163,
      "step": 288
    },
    {
      "epoch": 2.42,
      "learning_rate": 5.161290322580645e-05,
      "loss": 0.4336,
      "step": 300
    },
    {
      "epoch": 2.52,
      "learning_rate": 4.967741935483871e-05,
      "loss": 0.3656,
      "step": 312
    },
    {
      "epoch": 2.61,
      "learning_rate": 4.774193548387097e-05,
      "loss": 0.5974,
      "step": 324
    },
    {
      "epoch": 2.71,
      "learning_rate": 4.580645161290323e-05,
      "loss": 0.3766,
      "step": 336
    },
    {
      "epoch": 2.81,
      "learning_rate": 4.387096774193549e-05,
      "loss": 0.4473,
      "step": 348
    },
    {
      "epoch": 2.9,
      "learning_rate": 4.1935483870967746e-05,
      "loss": 0.4135,
      "step": 360
    },
    {
      "epoch": 3.0,
      "learning_rate": 4e-05,
      "loss": 0.173,
      "step": 372
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9282051282051282,
      "eval_loss": 0.37362906336784363,
      "eval_runtime": 5.5298,
      "eval_samples_per_second": 35.263,
      "eval_steps_per_second": 4.521,
      "step": 372
    },
    {
      "epoch": 3.1,
      "learning_rate": 3.8064516129032254e-05,
      "loss": 0.3401,
      "step": 384
    },
    {
      "epoch": 3.19,
      "learning_rate": 3.612903225806452e-05,
      "loss": 0.1776,
      "step": 396
    },
    {
      "epoch": 3.29,
      "learning_rate": 3.4193548387096776e-05,
      "loss": 0.2485,
      "step": 408
    },
    {
      "epoch": 3.39,
      "learning_rate": 3.2258064516129034e-05,
      "loss": 0.5576,
      "step": 420
    },
    {
      "epoch": 3.48,
      "learning_rate": 3.032258064516129e-05,
      "loss": 0.4437,
      "step": 432
    },
    {
      "epoch": 3.58,
      "learning_rate": 2.838709677419355e-05,
      "loss": 0.5132,
      "step": 444
    },
    {
      "epoch": 3.68,
      "learning_rate": 2.645161290322581e-05,
      "loss": 0.2877,
      "step": 456
    },
    {
      "epoch": 3.77,
      "learning_rate": 2.4516129032258064e-05,
      "loss": 0.4377,
      "step": 468
    },
    {
      "epoch": 3.87,
      "learning_rate": 2.258064516129032e-05,
      "loss": 0.1697,
      "step": 480
    },
    {
      "epoch": 3.97,
      "learning_rate": 2.0645161290322582e-05,
      "loss": 0.2741,
      "step": 492
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9282051282051282,
      "eval_loss": 0.377105176448822,
      "eval_runtime": 5.5428,
      "eval_samples_per_second": 35.181,
      "eval_steps_per_second": 4.51,
      "step": 496
    },
    {
      "epoch": 4.06,
      "learning_rate": 1.870967741935484e-05,
      "loss": 0.379,
      "step": 504
    },
    {
      "epoch": 4.16,
      "learning_rate": 1.6774193548387098e-05,
      "loss": 0.1826,
      "step": 516
    },
    {
      "epoch": 4.26,
      "learning_rate": 1.4838709677419355e-05,
      "loss": 0.3932,
      "step": 528
    },
    {
      "epoch": 4.35,
      "learning_rate": 1.2903225806451613e-05,
      "loss": 0.3326,
      "step": 540
    },
    {
      "epoch": 4.45,
      "learning_rate": 1.0967741935483872e-05,
      "loss": 0.1451,
      "step": 552
    },
    {
      "epoch": 4.55,
      "learning_rate": 9.03225806451613e-06,
      "loss": 0.3364,
      "step": 564
    },
    {
      "epoch": 4.65,
      "learning_rate": 7.096774193548387e-06,
      "loss": 0.2966,
      "step": 576
    },
    {
      "epoch": 4.74,
      "learning_rate": 5.161290322580646e-06,
      "loss": 0.3227,
      "step": 588
    },
    {
      "epoch": 4.84,
      "learning_rate": 3.225806451612903e-06,
      "loss": 0.3128,
      "step": 600
    },
    {
      "epoch": 4.94,
      "learning_rate": 1.2903225806451614e-06,
      "loss": 0.3511,
      "step": 612
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_loss": 0.33735406398773193,
      "eval_runtime": 5.5434,
      "eval_samples_per_second": 35.177,
      "eval_steps_per_second": 4.51,
      "step": 620
    },
    {
      "epoch": 5.0,
      "step": 620,
      "total_flos": 1298476374773760.0,
      "train_loss": 0.5101455471208018,
      "train_runtime": 502.263,
      "train_samples_per_second": 9.826,
      "train_steps_per_second": 1.234
    }
  ],
  "max_steps": 620,
  "num_train_epochs": 5,
  "total_flos": 1298476374773760.0,
  "trial_name": null,
  "trial_params": null
}