{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 9565,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "eval_loss": 2.4315900802612305,
      "eval_runtime": 4.6765,
      "eval_samples_per_second": 171.069,
      "eval_steps_per_second": 21.384,
      "step": 100
    },
    {
      "epoch": 0.1,
      "eval_loss": 2.3032939434051514,
      "eval_runtime": 4.6682,
      "eval_samples_per_second": 171.373,
      "eval_steps_per_second": 21.422,
      "step": 200
    },
    {
      "epoch": 0.16,
      "eval_loss": 2.217759609222412,
      "eval_runtime": 4.6679,
      "eval_samples_per_second": 171.381,
      "eval_steps_per_second": 21.423,
      "step": 300
    },
    {
      "epoch": 0.21,
      "eval_loss": 2.14911150932312,
      "eval_runtime": 4.6757,
      "eval_samples_per_second": 171.099,
      "eval_steps_per_second": 21.387,
      "step": 400
    },
    {
      "epoch": 0.26,
      "eval_loss": 2.155996322631836,
      "eval_runtime": 4.6665,
      "eval_samples_per_second": 171.433,
      "eval_steps_per_second": 21.429,
      "step": 500
    },
    {
      "epoch": 0.31,
      "eval_loss": 2.01924991607666,
      "eval_runtime": 4.6796,
      "eval_samples_per_second": 170.956,
      "eval_steps_per_second": 21.37,
      "step": 600
    },
    {
      "epoch": 0.37,
      "eval_loss": 2.0464463233947754,
      "eval_runtime": 4.6799,
      "eval_samples_per_second": 170.944,
      "eval_steps_per_second": 21.368,
      "step": 700
    },
    {
      "epoch": 0.42,
      "eval_loss": 1.977142333984375,
      "eval_runtime": 4.6707,
      "eval_samples_per_second": 171.279,
      "eval_steps_per_second": 21.41,
      "step": 800
    },
    {
      "epoch": 0.47,
      "eval_loss": 1.967787504196167,
      "eval_runtime": 4.6743,
      "eval_samples_per_second": 171.148,
      "eval_steps_per_second": 21.393,
      "step": 900
    },
    {
      "epoch": 0.52,
      "learning_rate": 8.954521693674857e-06,
      "loss": 2.2574,
      "step": 1000
    },
    {
      "epoch": 0.52,
      "eval_loss": 1.9178065061569214,
      "eval_runtime": 4.721,
      "eval_samples_per_second": 169.457,
      "eval_steps_per_second": 21.182,
      "step": 1000
    },
    {
      "epoch": 0.58,
      "eval_loss": 1.8966461420059204,
      "eval_runtime": 4.6821,
      "eval_samples_per_second": 170.864,
      "eval_steps_per_second": 21.358,
      "step": 1100
    },
    {
      "epoch": 0.63,
      "eval_loss": 1.818562626838684,
      "eval_runtime": 4.6827,
      "eval_samples_per_second": 170.841,
      "eval_steps_per_second": 21.355,
      "step": 1200
    },
    {
      "epoch": 0.68,
      "eval_loss": 1.8336358070373535,
      "eval_runtime": 4.6864,
      "eval_samples_per_second": 170.708,
      "eval_steps_per_second": 21.339,
      "step": 1300
    },
    {
      "epoch": 0.73,
      "eval_loss": 1.8185982704162598,
      "eval_runtime": 4.673,
      "eval_samples_per_second": 171.196,
      "eval_steps_per_second": 21.399,
      "step": 1400
    },
    {
      "epoch": 0.78,
      "eval_loss": 1.8159518241882324,
      "eval_runtime": 4.6851,
      "eval_samples_per_second": 170.755,
      "eval_steps_per_second": 21.344,
      "step": 1500
    },
    {
      "epoch": 0.84,
      "eval_loss": 1.806492567062378,
      "eval_runtime": 4.6846,
      "eval_samples_per_second": 170.771,
      "eval_steps_per_second": 21.346,
      "step": 1600
    },
    {
      "epoch": 0.89,
      "eval_loss": 1.7608861923217773,
      "eval_runtime": 4.6877,
      "eval_samples_per_second": 170.659,
      "eval_steps_per_second": 21.332,
      "step": 1700
    },
    {
      "epoch": 0.94,
      "eval_loss": 1.7618434429168701,
      "eval_runtime": 4.6769,
      "eval_samples_per_second": 171.055,
      "eval_steps_per_second": 21.382,
      "step": 1800
    },
    {
      "epoch": 0.99,
      "eval_loss": 1.7498806715011597,
      "eval_runtime": 4.6908,
      "eval_samples_per_second": 170.546,
      "eval_steps_per_second": 21.318,
      "step": 1900
    },
    {
      "epoch": 1.05,
      "learning_rate": 7.909043387349713e-06,
      "loss": 1.871,
      "step": 2000
    },
    {
      "epoch": 1.05,
      "eval_loss": 1.816186547279358,
      "eval_runtime": 4.7307,
      "eval_samples_per_second": 169.107,
      "eval_steps_per_second": 21.138,
      "step": 2000
    },
    {
      "epoch": 1.1,
      "eval_loss": 1.7303450107574463,
      "eval_runtime": 4.6832,
      "eval_samples_per_second": 170.822,
      "eval_steps_per_second": 21.353,
      "step": 2100
    },
    {
      "epoch": 1.15,
      "eval_loss": 1.6595067977905273,
      "eval_runtime": 4.6808,
      "eval_samples_per_second": 170.912,
      "eval_steps_per_second": 21.364,
      "step": 2200
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.7004770040512085,
      "eval_runtime": 4.6859,
      "eval_samples_per_second": 170.726,
      "eval_steps_per_second": 21.341,
      "step": 2300
    },
    {
      "epoch": 1.25,
      "eval_loss": 1.6547716856002808,
      "eval_runtime": 4.6729,
      "eval_samples_per_second": 171.199,
      "eval_steps_per_second": 21.4,
      "step": 2400
    },
    {
      "epoch": 1.31,
      "eval_loss": 1.6392831802368164,
      "eval_runtime": 4.6758,
      "eval_samples_per_second": 171.094,
      "eval_steps_per_second": 21.387,
      "step": 2500
    },
    {
      "epoch": 1.36,
      "eval_loss": 1.6230372190475464,
      "eval_runtime": 4.6697,
      "eval_samples_per_second": 171.318,
      "eval_steps_per_second": 21.415,
      "step": 2600
    },
    {
      "epoch": 1.41,
      "eval_loss": 1.63216233253479,
      "eval_runtime": 4.6753,
      "eval_samples_per_second": 171.111,
      "eval_steps_per_second": 21.389,
      "step": 2700
    },
    {
      "epoch": 1.46,
      "eval_loss": 1.627321720123291,
      "eval_runtime": 4.6653,
      "eval_samples_per_second": 171.477,
      "eval_steps_per_second": 21.435,
      "step": 2800
    },
    {
      "epoch": 1.52,
      "eval_loss": 1.6078392267227173,
      "eval_runtime": 4.6673,
      "eval_samples_per_second": 171.404,
      "eval_steps_per_second": 21.425,
      "step": 2900
    },
    {
      "epoch": 1.57,
      "learning_rate": 6.863565081024569e-06,
      "loss": 1.7234,
      "step": 3000
    },
    {
      "epoch": 1.57,
      "eval_loss": 1.6030551195144653,
      "eval_runtime": 4.6964,
      "eval_samples_per_second": 170.344,
      "eval_steps_per_second": 21.293,
      "step": 3000
    },
    {
      "epoch": 1.62,
      "eval_loss": 1.553316593170166,
      "eval_runtime": 4.6663,
      "eval_samples_per_second": 171.442,
      "eval_steps_per_second": 21.43,
      "step": 3100
    },
    {
      "epoch": 1.67,
      "eval_loss": 1.6135989427566528,
      "eval_runtime": 4.6687,
      "eval_samples_per_second": 171.355,
      "eval_steps_per_second": 21.419,
      "step": 3200
    },
    {
      "epoch": 1.73,
      "eval_loss": 1.5696121454238892,
      "eval_runtime": 4.6764,
      "eval_samples_per_second": 171.072,
      "eval_steps_per_second": 21.384,
      "step": 3300
    },
    {
      "epoch": 1.78,
      "eval_loss": 1.565152883529663,
      "eval_runtime": 4.6699,
      "eval_samples_per_second": 171.31,
      "eval_steps_per_second": 21.414,
      "step": 3400
    },
    {
      "epoch": 1.83,
      "eval_loss": 1.522884488105774,
      "eval_runtime": 4.6578,
      "eval_samples_per_second": 171.755,
      "eval_steps_per_second": 21.469,
      "step": 3500
    },
    {
      "epoch": 1.88,
      "eval_loss": 1.5707228183746338,
      "eval_runtime": 4.6663,
      "eval_samples_per_second": 171.44,
      "eval_steps_per_second": 21.43,
      "step": 3600
    },
    {
      "epoch": 1.93,
      "eval_loss": 1.587827444076538,
      "eval_runtime": 4.6655,
      "eval_samples_per_second": 171.473,
      "eval_steps_per_second": 21.434,
      "step": 3700
    },
    {
      "epoch": 1.99,
      "eval_loss": 1.5495318174362183,
      "eval_runtime": 4.6751,
      "eval_samples_per_second": 171.121,
      "eval_steps_per_second": 21.39,
      "step": 3800
    },
    {
      "epoch": 2.04,
      "eval_loss": 1.5380765199661255,
      "eval_runtime": 4.6613,
      "eval_samples_per_second": 171.627,
      "eval_steps_per_second": 21.453,
      "step": 3900
    },
    {
      "epoch": 2.09,
      "learning_rate": 5.8180867746994255e-06,
      "loss": 1.611,
      "step": 4000
    },
    {
      "epoch": 2.09,
      "eval_loss": 1.52095627784729,
      "eval_runtime": 4.7023,
      "eval_samples_per_second": 170.13,
      "eval_steps_per_second": 21.266,
      "step": 4000
    },
    {
      "epoch": 2.14,
      "eval_loss": 1.511513113975525,
      "eval_runtime": 4.6667,
      "eval_samples_per_second": 171.428,
      "eval_steps_per_second": 21.428,
      "step": 4100
    },
    {
      "epoch": 2.2,
      "eval_loss": 1.511332392692566,
      "eval_runtime": 4.6592,
      "eval_samples_per_second": 171.703,
      "eval_steps_per_second": 21.463,
      "step": 4200
    },
    {
      "epoch": 2.25,
      "eval_loss": 1.4714492559432983,
      "eval_runtime": 4.6645,
      "eval_samples_per_second": 171.508,
      "eval_steps_per_second": 21.438,
      "step": 4300
    },
    {
      "epoch": 2.3,
      "eval_loss": 1.5099194049835205,
      "eval_runtime": 4.6633,
      "eval_samples_per_second": 171.551,
      "eval_steps_per_second": 21.444,
      "step": 4400
    },
    {
      "epoch": 2.35,
      "eval_loss": 1.4862964153289795,
      "eval_runtime": 4.6767,
      "eval_samples_per_second": 171.061,
      "eval_steps_per_second": 21.383,
      "step": 4500
    },
    {
      "epoch": 2.4,
      "eval_loss": 1.5304350852966309,
      "eval_runtime": 4.6709,
      "eval_samples_per_second": 171.275,
      "eval_steps_per_second": 21.409,
      "step": 4600
    },
    {
      "epoch": 2.46,
      "eval_loss": 1.4990843534469604,
      "eval_runtime": 4.6619,
      "eval_samples_per_second": 171.605,
      "eval_steps_per_second": 21.451,
      "step": 4700
    },
    {
      "epoch": 2.51,
      "eval_loss": 1.5017355680465698,
      "eval_runtime": 4.6598,
      "eval_samples_per_second": 171.682,
      "eval_steps_per_second": 21.46,
      "step": 4800
    },
    {
      "epoch": 2.56,
      "eval_loss": 1.4134238958358765,
      "eval_runtime": 4.6698,
      "eval_samples_per_second": 171.313,
      "eval_steps_per_second": 21.414,
      "step": 4900
    },
    {
      "epoch": 2.61,
      "learning_rate": 4.7726084683742815e-06,
      "loss": 1.5455,
      "step": 5000
    },
    {
      "epoch": 2.61,
      "eval_loss": 1.4892077445983887,
      "eval_runtime": 4.693,
      "eval_samples_per_second": 170.468,
      "eval_steps_per_second": 21.308,
      "step": 5000
    },
    {
      "epoch": 2.67,
      "eval_loss": 1.4631962776184082,
      "eval_runtime": 4.6718,
      "eval_samples_per_second": 171.242,
      "eval_steps_per_second": 21.405,
      "step": 5100
    },
    {
      "epoch": 2.72,
      "eval_loss": 1.4686871767044067,
      "eval_runtime": 4.6795,
      "eval_samples_per_second": 170.959,
      "eval_steps_per_second": 21.37,
      "step": 5200
    },
    {
      "epoch": 2.77,
      "eval_loss": 1.444468379020691,
      "eval_runtime": 4.6722,
      "eval_samples_per_second": 171.227,
      "eval_steps_per_second": 21.403,
      "step": 5300
    },
    {
      "epoch": 2.82,
      "eval_loss": 1.434273362159729,
      "eval_runtime": 4.6709,
      "eval_samples_per_second": 171.273,
      "eval_steps_per_second": 21.409,
      "step": 5400
    },
    {
      "epoch": 2.88,
      "eval_loss": 1.4033972024917603,
      "eval_runtime": 4.674,
      "eval_samples_per_second": 171.159,
      "eval_steps_per_second": 21.395,
      "step": 5500
    },
    {
      "epoch": 2.93,
      "eval_loss": 1.3725674152374268,
      "eval_runtime": 4.658,
      "eval_samples_per_second": 171.746,
      "eval_steps_per_second": 21.468,
      "step": 5600
    },
    {
      "epoch": 2.98,
      "eval_loss": 1.4471670389175415,
      "eval_runtime": 4.6706,
      "eval_samples_per_second": 171.284,
      "eval_steps_per_second": 21.411,
      "step": 5700
    },
    {
      "epoch": 3.03,
      "eval_loss": 1.3971011638641357,
      "eval_runtime": 4.6665,
      "eval_samples_per_second": 171.433,
      "eval_steps_per_second": 21.429,
      "step": 5800
    },
    {
      "epoch": 3.08,
      "eval_loss": 1.4093689918518066,
      "eval_runtime": 4.6837,
      "eval_samples_per_second": 170.804,
      "eval_steps_per_second": 21.351,
      "step": 5900
    },
    {
      "epoch": 3.14,
      "learning_rate": 3.727130162049138e-06,
      "loss": 1.4815,
      "step": 6000
    },
    {
      "epoch": 3.14,
      "eval_loss": 1.434360384941101,
      "eval_runtime": 4.7117,
      "eval_samples_per_second": 169.79,
      "eval_steps_per_second": 21.224,
      "step": 6000
    },
    {
      "epoch": 3.19,
      "eval_loss": 1.412831425666809,
      "eval_runtime": 4.678,
      "eval_samples_per_second": 171.013,
      "eval_steps_per_second": 21.377,
      "step": 6100
    },
    {
      "epoch": 3.24,
      "eval_loss": 1.4168850183486938,
      "eval_runtime": 4.6653,
      "eval_samples_per_second": 171.478,
      "eval_steps_per_second": 21.435,
      "step": 6200
    },
    {
      "epoch": 3.29,
      "eval_loss": 1.399338960647583,
      "eval_runtime": 4.6686,
      "eval_samples_per_second": 171.359,
      "eval_steps_per_second": 21.42,
      "step": 6300
    },
    {
      "epoch": 3.35,
      "eval_loss": 1.4034981727600098,
      "eval_runtime": 4.6638,
      "eval_samples_per_second": 171.535,
      "eval_steps_per_second": 21.442,
      "step": 6400
    },
    {
      "epoch": 3.4,
      "eval_loss": 1.3951754570007324,
      "eval_runtime": 4.6788,
      "eval_samples_per_second": 170.982,
      "eval_steps_per_second": 21.373,
      "step": 6500
    },
    {
      "epoch": 3.45,
      "eval_loss": 1.3877923488616943,
      "eval_runtime": 4.6855,
      "eval_samples_per_second": 170.739,
      "eval_steps_per_second": 21.342,
      "step": 6600
    },
    {
      "epoch": 3.5,
      "eval_loss": 1.3673046827316284,
      "eval_runtime": 4.6699,
      "eval_samples_per_second": 171.31,
      "eval_steps_per_second": 21.414,
      "step": 6700
    },
    {
      "epoch": 3.55,
      "eval_loss": 1.3622443675994873,
      "eval_runtime": 4.671,
      "eval_samples_per_second": 171.271,
      "eval_steps_per_second": 21.409,
      "step": 6800
    },
    {
      "epoch": 3.61,
      "eval_loss": 1.374872088432312,
      "eval_runtime": 4.6712,
      "eval_samples_per_second": 171.263,
      "eval_steps_per_second": 21.408,
      "step": 6900
    },
    {
      "epoch": 3.66,
      "learning_rate": 2.681651855723994e-06,
      "loss": 1.4492,
      "step": 7000
    },
    {
      "epoch": 3.66,
      "eval_loss": 1.4481711387634277,
      "eval_runtime": 4.6991,
      "eval_samples_per_second": 170.247,
      "eval_steps_per_second": 21.281,
      "step": 7000
    },
    {
      "epoch": 3.71,
      "eval_loss": 1.3453810214996338,
      "eval_runtime": 4.6891,
      "eval_samples_per_second": 170.607,
      "eval_steps_per_second": 21.326,
      "step": 7100
    },
    {
      "epoch": 3.76,
      "eval_loss": 1.3628772497177124,
      "eval_runtime": 4.691,
      "eval_samples_per_second": 170.54,
      "eval_steps_per_second": 21.317,
      "step": 7200
    },
    {
      "epoch": 3.82,
      "eval_loss": 1.4115179777145386,
      "eval_runtime": 4.6842,
      "eval_samples_per_second": 170.787,
      "eval_steps_per_second": 21.348,
      "step": 7300
    },
    {
      "epoch": 3.87,
      "eval_loss": 1.3432800769805908,
      "eval_runtime": 4.69,
      "eval_samples_per_second": 170.576,
      "eval_steps_per_second": 21.322,
      "step": 7400
    },
    {
      "epoch": 3.92,
      "eval_loss": 1.368696928024292,
      "eval_runtime": 4.6923,
      "eval_samples_per_second": 170.493,
      "eval_steps_per_second": 21.312,
      "step": 7500
    },
    {
      "epoch": 3.97,
      "eval_loss": 1.4239104986190796,
      "eval_runtime": 4.6873,
      "eval_samples_per_second": 170.674,
      "eval_steps_per_second": 21.334,
      "step": 7600
    },
    {
      "epoch": 4.03,
      "eval_loss": 1.3071486949920654,
      "eval_runtime": 4.6827,
      "eval_samples_per_second": 170.843,
      "eval_steps_per_second": 21.355,
      "step": 7700
    },
    {
      "epoch": 4.08,
      "eval_loss": 1.353852391242981,
      "eval_runtime": 4.6839,
      "eval_samples_per_second": 170.798,
      "eval_steps_per_second": 21.35,
      "step": 7800
    },
    {
      "epoch": 4.13,
      "eval_loss": 1.3432263135910034,
      "eval_runtime": 4.6946,
      "eval_samples_per_second": 170.409,
      "eval_steps_per_second": 21.301,
      "step": 7900
    },
    {
      "epoch": 4.18,
      "learning_rate": 1.63617354939885e-06,
      "loss": 1.4208,
      "step": 8000
    },
    {
      "epoch": 4.18,
      "eval_loss": 1.3502365350723267,
      "eval_runtime": 4.7172,
      "eval_samples_per_second": 169.592,
      "eval_steps_per_second": 21.199,
      "step": 8000
    },
    {
      "epoch": 4.23,
      "eval_loss": 1.363999605178833,
      "eval_runtime": 4.685,
      "eval_samples_per_second": 170.758,
      "eval_steps_per_second": 21.345,
      "step": 8100
    },
    {
      "epoch": 4.29,
      "eval_loss": 1.382441520690918,
      "eval_runtime": 4.6847,
      "eval_samples_per_second": 170.769,
      "eval_steps_per_second": 21.346,
      "step": 8200
    },
    {
      "epoch": 4.34,
      "eval_loss": 1.3818987607955933,
      "eval_runtime": 4.6986,
      "eval_samples_per_second": 170.265,
      "eval_steps_per_second": 21.283,
      "step": 8300
    },
    {
      "epoch": 4.39,
      "eval_loss": 1.340713620185852,
      "eval_runtime": 4.6878,
      "eval_samples_per_second": 170.655,
      "eval_steps_per_second": 21.332,
      "step": 8400
    },
    {
      "epoch": 4.44,
      "eval_loss": 1.3344806432724,
      "eval_runtime": 4.6958,
      "eval_samples_per_second": 170.364,
      "eval_steps_per_second": 21.295,
      "step": 8500
    },
    {
      "epoch": 4.5,
      "eval_loss": 1.3563097715377808,
      "eval_runtime": 4.6877,
      "eval_samples_per_second": 170.66,
      "eval_steps_per_second": 21.333,
      "step": 8600
    },
    {
      "epoch": 4.55,
      "eval_loss": 1.3303130865097046,
      "eval_runtime": 4.6903,
      "eval_samples_per_second": 170.565,
      "eval_steps_per_second": 21.321,
      "step": 8700
    },
    {
      "epoch": 4.6,
      "eval_loss": 1.3454128503799438,
      "eval_runtime": 4.6828,
      "eval_samples_per_second": 170.838,
      "eval_steps_per_second": 21.355,
      "step": 8800
    },
    {
      "epoch": 4.65,
      "eval_loss": 1.3808575868606567,
      "eval_runtime": 4.6966,
      "eval_samples_per_second": 170.335,
      "eval_steps_per_second": 21.292,
      "step": 8900
    },
    {
      "epoch": 4.7,
      "learning_rate": 5.906952430737063e-07,
      "loss": 1.4013,
      "step": 9000
    },
    {
      "epoch": 4.7,
      "eval_loss": 1.3647897243499756,
      "eval_runtime": 4.7177,
      "eval_samples_per_second": 169.575,
      "eval_steps_per_second": 21.197,
      "step": 9000
    },
    {
      "epoch": 4.76,
      "eval_loss": 1.34979248046875,
      "eval_runtime": 4.6998,
      "eval_samples_per_second": 170.221,
      "eval_steps_per_second": 21.278,
      "step": 9100
    },
    {
      "epoch": 4.81,
      "eval_loss": 1.3509832620620728,
      "eval_runtime": 4.685,
      "eval_samples_per_second": 170.758,
      "eval_steps_per_second": 21.345,
      "step": 9200
    },
    {
      "epoch": 4.86,
      "eval_loss": 1.3402700424194336,
      "eval_runtime": 4.6979,
      "eval_samples_per_second": 170.289,
      "eval_steps_per_second": 21.286,
      "step": 9300
    },
    {
      "epoch": 4.91,
      "eval_loss": 1.2718613147735596,
      "eval_runtime": 4.6876,
      "eval_samples_per_second": 170.662,
      "eval_steps_per_second": 21.333,
      "step": 9400
    },
    {
      "epoch": 4.97,
      "eval_loss": 1.3347008228302002,
      "eval_runtime": 4.6849,
      "eval_samples_per_second": 170.762,
      "eval_steps_per_second": 21.345,
      "step": 9500
    },
    {
      "epoch": 5.0,
      "step": 9565,
      "total_flos": 1.1622564417918384e+16,
      "train_loss": 1.626130136269521,
      "train_runtime": 5849.5407,
      "train_samples_per_second": 13.078,
      "train_steps_per_second": 1.635
    }
  ],
  "max_steps": 9565,
  "num_train_epochs": 5,
  "total_flos": 1.1622564417918384e+16,
  "trial_name": null,
  "trial_params": null
}