{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 24.0,
  "eval_steps": 500,
  "global_step": 5088,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 9.95e-05,
      "loss": 6.3597,
      "step": 212
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.853069305419922,
      "eval_runtime": 3.5937,
      "eval_samples_per_second": 188.106,
      "eval_steps_per_second": 23.652,
      "step": 212
    },
    {
      "epoch": 2.0,
      "learning_rate": 9.900000000000001e-05,
      "loss": 5.5629,
      "step": 424
    },
    {
      "epoch": 2.0,
      "eval_loss": 4.915834903717041,
      "eval_runtime": 3.704,
      "eval_samples_per_second": 182.506,
      "eval_steps_per_second": 22.948,
      "step": 424
    },
    {
      "epoch": 3.0,
      "learning_rate": 9.850000000000001e-05,
      "loss": 4.8228,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_loss": 4.177055835723877,
      "eval_runtime": 3.7104,
      "eval_samples_per_second": 182.193,
      "eval_steps_per_second": 22.909,
      "step": 636
    },
    {
      "epoch": 4.0,
      "learning_rate": 9.8e-05,
      "loss": 4.1035,
      "step": 848
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.462527275085449,
      "eval_runtime": 3.1205,
      "eval_samples_per_second": 216.633,
      "eval_steps_per_second": 27.239,
      "step": 848
    },
    {
      "epoch": 5.0,
      "learning_rate": 9.75e-05,
      "loss": 3.467,
      "step": 1060
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.8398332595825195,
      "eval_runtime": 3.3235,
      "eval_samples_per_second": 203.402,
      "eval_steps_per_second": 25.576,
      "step": 1060
    },
    {
      "epoch": 6.0,
      "learning_rate": 9.7e-05,
      "loss": 2.8887,
      "step": 1272
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.3201420307159424,
      "eval_runtime": 3.4255,
      "eval_samples_per_second": 197.342,
      "eval_steps_per_second": 24.814,
      "step": 1272
    },
    {
      "epoch": 7.0,
      "learning_rate": 9.65e-05,
      "loss": 2.4003,
      "step": 1484
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.8698177337646484,
      "eval_runtime": 3.5218,
      "eval_samples_per_second": 191.945,
      "eval_steps_per_second": 24.135,
      "step": 1484
    },
    {
      "epoch": 8.0,
      "learning_rate": 9.6e-05,
      "loss": 1.9919,
      "step": 1696
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.532776951789856,
      "eval_runtime": 3.5514,
      "eval_samples_per_second": 190.345,
      "eval_steps_per_second": 23.934,
      "step": 1696
    },
    {
      "epoch": 9.0,
      "learning_rate": 9.55e-05,
      "loss": 1.6656,
      "step": 1908
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.2841078042984009,
      "eval_runtime": 3.622,
      "eval_samples_per_second": 186.637,
      "eval_steps_per_second": 23.468,
      "step": 1908
    },
    {
      "epoch": 10.0,
      "learning_rate": 9.5e-05,
      "loss": 1.4036,
      "step": 2120
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.107720971107483,
      "eval_runtime": 3.6471,
      "eval_samples_per_second": 185.353,
      "eval_steps_per_second": 23.306,
      "step": 2120
    },
    {
      "epoch": 11.0,
      "learning_rate": 9.449999999999999e-05,
      "loss": 1.2091,
      "step": 2332
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.9709760546684265,
      "eval_runtime": 3.7402,
      "eval_samples_per_second": 180.741,
      "eval_steps_per_second": 22.726,
      "step": 2332
    },
    {
      "epoch": 12.0,
      "learning_rate": 9.4e-05,
      "loss": 1.0379,
      "step": 2544
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.8528622984886169,
      "eval_runtime": 3.734,
      "eval_samples_per_second": 181.041,
      "eval_steps_per_second": 22.764,
      "step": 2544
    },
    {
      "epoch": 13.0,
      "learning_rate": 9.350000000000001e-05,
      "loss": 0.8994,
      "step": 2756
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.7617917060852051,
      "eval_runtime": 3.7153,
      "eval_samples_per_second": 181.95,
      "eval_steps_per_second": 22.878,
      "step": 2756
    },
    {
      "epoch": 14.0,
      "learning_rate": 9.300000000000001e-05,
      "loss": 0.7828,
      "step": 2968
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.6774648427963257,
      "eval_runtime": 3.6994,
      "eval_samples_per_second": 182.734,
      "eval_steps_per_second": 22.977,
      "step": 2968
    },
    {
      "epoch": 15.0,
      "learning_rate": 9.250000000000001e-05,
      "loss": 0.6788,
      "step": 3180
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.6361714005470276,
      "eval_runtime": 3.6581,
      "eval_samples_per_second": 184.796,
      "eval_steps_per_second": 23.236,
      "step": 3180
    },
    {
      "epoch": 16.0,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.5819,
      "step": 3392
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.5761357545852661,
      "eval_runtime": 3.7378,
      "eval_samples_per_second": 180.853,
      "eval_steps_per_second": 22.74,
      "step": 3392
    },
    {
      "epoch": 17.0,
      "learning_rate": 9.15e-05,
      "loss": 0.5104,
      "step": 3604
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.5219044089317322,
      "eval_runtime": 3.7453,
      "eval_samples_per_second": 180.495,
      "eval_steps_per_second": 22.695,
      "step": 3604
    },
    {
      "epoch": 18.0,
      "learning_rate": 9.1e-05,
      "loss": 0.4343,
      "step": 3816
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.4844624102115631,
      "eval_runtime": 3.7695,
      "eval_samples_per_second": 179.335,
      "eval_steps_per_second": 22.55,
      "step": 3816
    },
    {
      "epoch": 19.0,
      "learning_rate": 9.05e-05,
      "loss": 0.3784,
      "step": 4028
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.44724151492118835,
      "eval_runtime": 3.7703,
      "eval_samples_per_second": 179.296,
      "eval_steps_per_second": 22.545,
      "step": 4028
    },
    {
      "epoch": 20.0,
      "learning_rate": 9e-05,
      "loss": 0.3224,
      "step": 4240
    },
    {
      "epoch": 20.0,
      "eval_loss": 0.45848363637924194,
      "eval_runtime": 3.6822,
      "eval_samples_per_second": 183.584,
      "eval_steps_per_second": 23.084,
      "step": 4240
    },
    {
      "epoch": 21.0,
      "learning_rate": 8.950000000000001e-05,
      "loss": 0.2768,
      "step": 4452
    },
    {
      "epoch": 21.0,
      "eval_loss": 0.4251560866832733,
      "eval_runtime": 3.9348,
      "eval_samples_per_second": 171.802,
      "eval_steps_per_second": 21.602,
      "step": 4452
    },
    {
      "epoch": 22.0,
      "learning_rate": 8.900000000000001e-05,
      "loss": 0.2269,
      "step": 4664
    },
    {
      "epoch": 22.0,
      "eval_loss": 0.39140933752059937,
      "eval_runtime": 3.6907,
      "eval_samples_per_second": 183.165,
      "eval_steps_per_second": 23.031,
      "step": 4664
    },
    {
      "epoch": 23.0,
      "learning_rate": 8.850000000000001e-05,
      "loss": 0.1868,
      "step": 4876
    },
    {
      "epoch": 23.0,
      "eval_loss": 0.4142400920391083,
      "eval_runtime": 3.8669,
      "eval_samples_per_second": 174.815,
      "eval_steps_per_second": 21.981,
      "step": 4876
    },
    {
      "epoch": 24.0,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.1539,
      "step": 5088
    },
    {
      "epoch": 24.0,
      "eval_loss": 0.3828276991844177,
      "eval_runtime": 3.7873,
      "eval_samples_per_second": 178.493,
      "eval_steps_per_second": 22.444,
      "step": 5088
    }
  ],
  "logging_steps": 500,
  "max_steps": 42400,
  "num_train_epochs": 200,
  "save_steps": 500,
  "total_flos": 6408782646142500.0,
  "trial_name": null,
  "trial_params": null
}