{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.746938775510204,
  "eval_steps": 50.0,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 1.2891,
      "step": 1
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 4.6526,
      "step": 2
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.8841,
      "step": 3
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.9659,
      "step": 4
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.9394,
      "step": 5
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 6.3749,
      "step": 6
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 2.021,
      "step": 7
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.998582695676762e-05,
      "loss": 1.8688,
      "step": 8
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.9943348002101374e-05,
      "loss": 0.8039,
      "step": 9
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.9872683547213446e-05,
      "loss": 0.8166,
      "step": 10
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.9774033898178668e-05,
      "loss": 2.644,
      "step": 11
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.9647678688145163e-05,
      "loss": 1.6254,
      "step": 12
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.9493976084683814e-05,
      "loss": 1.0999,
      "step": 13
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.9313361774523387e-05,
      "loss": 1.4098,
      "step": 14
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.9106347728549134e-05,
      "loss": 0.6272,
      "step": 15
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.8873520750565716e-05,
      "loss": 1.1149,
      "step": 16
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.8615540813938063e-05,
      "loss": 2.0887,
      "step": 17
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.833313919082515e-05,
      "loss": 2.8401,
      "step": 18
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.8027116379309637e-05,
      "loss": 1.1174,
      "step": 19
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.7698339834299064e-05,
      "loss": 1.1134,
      "step": 20
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.7347741508630673e-05,
      "loss": 0.7405,
      "step": 21
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.6976315211349848e-05,
      "loss": 1.4709,
      "step": 22
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.658511379065039e-05,
      "loss": 1.9613,
      "step": 23
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.617524614946192e-05,
      "loss": 0.7757,
      "step": 24
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.5747874102144073e-05,
      "loss": 2.8759,
      "step": 25
    },
    {
      "epoch": 2.26,
      "learning_rate": 1.5304209081197425e-05,
      "loss": 0.5396,
      "step": 26
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.4845508703326504e-05,
      "loss": 0.5796,
      "step": 27
    },
    {
      "epoch": 2.44,
      "learning_rate": 1.4373073204588556e-05,
      "loss": 0.648,
      "step": 28
    },
    {
      "epoch": 2.53,
      "learning_rate": 1.388824175473321e-05,
      "loss": 3.6827,
      "step": 29
    },
    {
      "epoch": 2.61,
      "learning_rate": 1.3392388661180303e-05,
      "loss": 1.2732,
      "step": 30
    },
    {
      "epoch": 2.7,
      "learning_rate": 1.2886919473396212e-05,
      "loss": 1.0651,
      "step": 31
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.2373266998711152e-05,
      "loss": 0.4438,
      "step": 32
    },
    {
      "epoch": 2.87,
      "learning_rate": 1.1852887240871145e-05,
      "loss": 0.5061,
      "step": 33
    },
    {
      "epoch": 2.96,
      "learning_rate": 1.1327255272837221e-05,
      "loss": 1.9549,
      "step": 34
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.0797861055530832e-05,
      "loss": 0.7918,
      "step": 35
    },
    {
      "epoch": 3.13,
      "learning_rate": 1.026620521437775e-05,
      "loss": 0.5697,
      "step": 36
    },
    {
      "epoch": 3.22,
      "learning_rate": 9.733794785622254e-06,
      "loss": 0.6263,
      "step": 37
    },
    {
      "epoch": 3.31,
      "learning_rate": 9.202138944469168e-06,
      "loss": 0.2889,
      "step": 38
    },
    {
      "epoch": 3.4,
      "learning_rate": 8.672744727162782e-06,
      "loss": 0.4914,
      "step": 39
    },
    {
      "epoch": 3.48,
      "learning_rate": 8.147112759128859e-06,
      "loss": 1.0287,
      "step": 40
    },
    {
      "epoch": 3.57,
      "learning_rate": 7.626733001288852e-06,
      "loss": 1.5759,
      "step": 41
    },
    {
      "epoch": 3.66,
      "learning_rate": 7.113080526603793e-06,
      "loss": 0.5002,
      "step": 42
    },
    {
      "epoch": 3.74,
      "learning_rate": 6.607611338819697e-06,
      "loss": 0.4516,
      "step": 43
    },
    {
      "epoch": 3.83,
      "learning_rate": 6.111758245266795e-06,
      "loss": 0.2889,
      "step": 44
    },
    {
      "epoch": 3.92,
      "learning_rate": 5.626926795411447e-06,
      "loss": 0.7232,
      "step": 45
    },
    {
      "epoch": 4.01,
      "learning_rate": 5.1544912966735e-06,
      "loss": 0.8127,
      "step": 46
    },
    {
      "epoch": 4.09,
      "learning_rate": 4.695790918802577e-06,
      "loss": 0.3245,
      "step": 47
    },
    {
      "epoch": 4.18,
      "learning_rate": 4.2521258978559324e-06,
      "loss": 1.4068,
      "step": 48
    },
    {
      "epoch": 4.27,
      "learning_rate": 3.824753850538082e-06,
      "loss": 0.2379,
      "step": 49
    },
    {
      "epoch": 4.35,
      "learning_rate": 3.414886209349615e-06,
      "loss": 0.2479,
      "step": 50
    },
    {
      "epoch": 4.44,
      "learning_rate": 3.023684788650154e-06,
      "loss": 0.2701,
      "step": 51
    },
    {
      "epoch": 4.53,
      "learning_rate": 2.6522584913693295e-06,
      "loss": 1.6486,
      "step": 52
    },
    {
      "epoch": 4.61,
      "learning_rate": 2.3016601657009364e-06,
      "loss": 0.541,
      "step": 53
    },
    {
      "epoch": 4.7,
      "learning_rate": 1.972883620690366e-06,
      "loss": 0.487,
      "step": 54
    },
    {
      "epoch": 4.79,
      "learning_rate": 1.6668608091748495e-06,
      "loss": 0.1732,
      "step": 55
    },
    {
      "epoch": 4.88,
      "learning_rate": 1.3844591860619382e-06,
      "loss": 0.1897,
      "step": 56
    },
    {
      "epoch": 4.96,
      "learning_rate": 1.1264792494342858e-06,
      "loss": 0.8125,
      "step": 57
    },
    {
      "epoch": 5.05,
      "learning_rate": 8.936522714508678e-07,
      "loss": 0.3331,
      "step": 58
    },
    {
      "epoch": 5.14,
      "learning_rate": 6.866382254766158e-07,
      "loss": 0.2799,
      "step": 59
    },
    {
      "epoch": 5.22,
      "learning_rate": 5.060239153161872e-07,
      "loss": 0.2832,
      "step": 60
    },
    {
      "epoch": 5.31,
      "learning_rate": 3.5232131185484075e-07,
      "loss": 0.1354,
      "step": 61
    },
    {
      "epoch": 5.4,
      "learning_rate": 2.2596610182133328e-07,
      "loss": 0.2119,
      "step": 62
    },
    {
      "epoch": 5.49,
      "learning_rate": 1.2731645278655448e-07,
      "loss": 0.8729,
      "step": 63
    },
    {
      "epoch": 5.57,
      "learning_rate": 5.665199789862907e-08,
      "loss": 0.7975,
      "step": 64
    },
    {
      "epoch": 5.66,
      "learning_rate": 1.4173043232380557e-08,
      "loss": 0.2552,
      "step": 65
    },
    {
      "epoch": 5.75,
      "learning_rate": 0.0,
      "loss": 0.226,
      "step": 66
    },
    {
      "epoch": 5.75,
      "step": 66,
      "total_flos": 2.952602738246025e+18,
      "train_loss": 1.1014869393724385,
      "train_runtime": 5596.3811,
      "train_samples_per_second": 6.304,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 66,
  "num_train_epochs": 6,
  "save_steps": 100.0,
  "total_flos": 2.952602738246025e+18,
  "trial_name": null,
  "trial_params": null
}