{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03385168729503861,
  "eval_steps": 20,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004231460911879826,
      "grad_norm": 1.6363259553909302,
      "learning_rate": 2e-05,
      "loss": 2.4891,
      "step": 1
    },
    {
      "epoch": 0.0004231460911879826,
      "eval_loss": 2.7103111743927,
      "eval_runtime": 25.5407,
      "eval_samples_per_second": 77.915,
      "eval_steps_per_second": 19.498,
      "step": 1
    },
    {
      "epoch": 0.0008462921823759652,
      "grad_norm": 1.6588494777679443,
      "learning_rate": 4e-05,
      "loss": 2.6718,
      "step": 2
    },
    {
      "epoch": 0.0012694382735639479,
      "grad_norm": 1.7058560848236084,
      "learning_rate": 6e-05,
      "loss": 2.6474,
      "step": 3
    },
    {
      "epoch": 0.0016925843647519305,
      "grad_norm": 1.6588222980499268,
      "learning_rate": 8e-05,
      "loss": 2.6717,
      "step": 4
    },
    {
      "epoch": 0.002115730455939913,
      "grad_norm": 1.5508973598480225,
      "learning_rate": 0.0001,
      "loss": 2.5936,
      "step": 5
    },
    {
      "epoch": 0.0025388765471278957,
      "grad_norm": 1.4414312839508057,
      "learning_rate": 0.00012,
      "loss": 2.6166,
      "step": 6
    },
    {
      "epoch": 0.0029620226383158784,
      "grad_norm": 1.3356502056121826,
      "learning_rate": 0.00014,
      "loss": 2.6361,
      "step": 7
    },
    {
      "epoch": 0.003385168729503861,
      "grad_norm": 1.3982197046279907,
      "learning_rate": 0.00016,
      "loss": 2.5908,
      "step": 8
    },
    {
      "epoch": 0.003808314820691844,
      "grad_norm": 1.4515146017074585,
      "learning_rate": 0.00018,
      "loss": 2.5478,
      "step": 9
    },
    {
      "epoch": 0.004231460911879826,
      "grad_norm": 1.5462111234664917,
      "learning_rate": 0.0002,
      "loss": 2.5379,
      "step": 10
    },
    {
      "epoch": 0.004654607003067809,
      "grad_norm": 1.5184928178787231,
      "learning_rate": 0.00019989930665413147,
      "loss": 2.5466,
      "step": 11
    },
    {
      "epoch": 0.0050777530942557915,
      "grad_norm": 1.452031135559082,
      "learning_rate": 0.00019959742939952392,
      "loss": 2.4949,
      "step": 12
    },
    {
      "epoch": 0.005500899185443774,
      "grad_norm": 1.4936366081237793,
      "learning_rate": 0.00019909497617679348,
      "loss": 2.3631,
      "step": 13
    },
    {
      "epoch": 0.005924045276631757,
      "grad_norm": 1.3953323364257812,
      "learning_rate": 0.00019839295885986296,
      "loss": 2.3978,
      "step": 14
    },
    {
      "epoch": 0.006347191367819739,
      "grad_norm": 1.361305594444275,
      "learning_rate": 0.00019749279121818235,
      "loss": 2.4401,
      "step": 15
    },
    {
      "epoch": 0.006770337459007722,
      "grad_norm": 1.3678853511810303,
      "learning_rate": 0.00019639628606958533,
      "loss": 2.437,
      "step": 16
    },
    {
      "epoch": 0.0071934835501957055,
      "grad_norm": 1.3215718269348145,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.389,
      "step": 17
    },
    {
      "epoch": 0.007616629641383688,
      "grad_norm": 1.285584568977356,
      "learning_rate": 0.00019362348706397373,
      "loss": 2.3646,
      "step": 18
    },
    {
      "epoch": 0.00803977573257167,
      "grad_norm": 1.2454744577407837,
      "learning_rate": 0.0001919527772551451,
      "loss": 2.2511,
      "step": 19
    },
    {
      "epoch": 0.008462921823759652,
      "grad_norm": 1.3071717023849487,
      "learning_rate": 0.0001900968867902419,
      "loss": 2.3198,
      "step": 20
    },
    {
      "epoch": 0.008462921823759652,
      "eval_loss": 2.341797351837158,
      "eval_runtime": 25.0254,
      "eval_samples_per_second": 79.519,
      "eval_steps_per_second": 19.9,
      "step": 20
    },
    {
      "epoch": 0.008886067914947636,
      "grad_norm": 1.375653862953186,
      "learning_rate": 0.0001880595531856738,
      "loss": 2.3413,
      "step": 21
    },
    {
      "epoch": 0.009309214006135618,
      "grad_norm": 1.3680791854858398,
      "learning_rate": 0.00018584487936018661,
      "loss": 2.4474,
      "step": 22
    },
    {
      "epoch": 0.009732360097323601,
      "grad_norm": 1.444303035736084,
      "learning_rate": 0.00018345732537213027,
      "loss": 2.4309,
      "step": 23
    },
    {
      "epoch": 0.010155506188511583,
      "grad_norm": 1.3316677808761597,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.3091,
      "step": 24
    },
    {
      "epoch": 0.010578652279699566,
      "grad_norm": 1.206446647644043,
      "learning_rate": 0.000178183148246803,
      "loss": 2.325,
      "step": 25
    },
    {
      "epoch": 0.011001798370887548,
      "grad_norm": 1.2919548749923706,
      "learning_rate": 0.00017530714660036112,
      "loss": 2.2293,
      "step": 26
    },
    {
      "epoch": 0.011424944462075532,
      "grad_norm": 1.4091441631317139,
      "learning_rate": 0.00017227948638273916,
      "loss": 2.2388,
      "step": 27
    },
    {
      "epoch": 0.011848090553263513,
      "grad_norm": 1.4587730169296265,
      "learning_rate": 0.00016910626489868649,
      "loss": 2.3036,
      "step": 28
    },
    {
      "epoch": 0.012271236644451497,
      "grad_norm": 1.8615366220474243,
      "learning_rate": 0.00016579387259397127,
      "loss": 2.3368,
      "step": 29
    },
    {
      "epoch": 0.012694382735639479,
      "grad_norm": 1.4323437213897705,
      "learning_rate": 0.00016234898018587337,
      "loss": 2.3043,
      "step": 30
    },
    {
      "epoch": 0.013117528826827462,
      "grad_norm": 1.3786976337432861,
      "learning_rate": 0.00015877852522924732,
      "loss": 2.2584,
      "step": 31
    },
    {
      "epoch": 0.013540674918015444,
      "grad_norm": 1.3786307573318481,
      "learning_rate": 0.00015508969814521025,
      "loss": 2.3891,
      "step": 32
    },
    {
      "epoch": 0.013963821009203427,
      "grad_norm": 1.3032869100570679,
      "learning_rate": 0.00015128992774059063,
      "loss": 2.2714,
      "step": 33
    },
    {
      "epoch": 0.014386967100391411,
      "grad_norm": 1.7123363018035889,
      "learning_rate": 0.00014738686624729986,
      "loss": 2.2354,
      "step": 34
    },
    {
      "epoch": 0.014810113191579393,
      "grad_norm": 1.4017690420150757,
      "learning_rate": 0.00014338837391175582,
      "loss": 2.1773,
      "step": 35
    },
    {
      "epoch": 0.015233259282767376,
      "grad_norm": 1.4052975177764893,
      "learning_rate": 0.00013930250316539238,
      "loss": 2.1841,
      "step": 36
    },
    {
      "epoch": 0.015656405373955358,
      "grad_norm": 1.3908483982086182,
      "learning_rate": 0.0001351374824081343,
      "loss": 2.2708,
      "step": 37
    },
    {
      "epoch": 0.01607955146514334,
      "grad_norm": 1.3868993520736694,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2283,
      "step": 38
    },
    {
      "epoch": 0.016502697556331325,
      "grad_norm": 1.2704371213912964,
      "learning_rate": 0.00012660368455666752,
      "loss": 2.2096,
      "step": 39
    },
    {
      "epoch": 0.016925843647519305,
      "grad_norm": 1.3375109434127808,
      "learning_rate": 0.00012225209339563145,
      "loss": 2.1863,
      "step": 40
    },
    {
      "epoch": 0.016925843647519305,
      "eval_loss": 2.2113733291625977,
      "eval_runtime": 25.1253,
      "eval_samples_per_second": 79.203,
      "eval_steps_per_second": 19.821,
      "step": 40
    },
    {
      "epoch": 0.01734898973870729,
      "grad_norm": 1.2191954851150513,
      "learning_rate": 0.00011785568947986367,
      "loss": 2.2794,
      "step": 41
    },
    {
      "epoch": 0.017772135829895272,
      "grad_norm": 6.1313605308532715,
      "learning_rate": 0.00011342332658176555,
      "loss": 2.3205,
      "step": 42
    },
    {
      "epoch": 0.018195281921083255,
      "grad_norm": 1.338478446006775,
      "learning_rate": 0.00010896393089034336,
      "loss": 2.1809,
      "step": 43
    },
    {
      "epoch": 0.018618428012271235,
      "grad_norm": 1.3417049646377563,
      "learning_rate": 0.00010448648303505151,
      "loss": 2.2497,
      "step": 44
    },
    {
      "epoch": 0.01904157410345922,
      "grad_norm": 1.32805335521698,
      "learning_rate": 0.0001,
      "loss": 2.1696,
      "step": 45
    },
    {
      "epoch": 0.019464720194647202,
      "grad_norm": 1.2384742498397827,
      "learning_rate": 9.551351696494854e-05,
      "loss": 2.1888,
      "step": 46
    },
    {
      "epoch": 0.019887866285835186,
      "grad_norm": 1.4238135814666748,
      "learning_rate": 9.103606910965666e-05,
      "loss": 2.3193,
      "step": 47
    },
    {
      "epoch": 0.020311012377023166,
      "grad_norm": 1.3317970037460327,
      "learning_rate": 8.657667341823448e-05,
      "loss": 2.1241,
      "step": 48
    },
    {
      "epoch": 0.02073415846821115,
      "grad_norm": 5.128082275390625,
      "learning_rate": 8.214431052013634e-05,
      "loss": 2.3208,
      "step": 49
    },
    {
      "epoch": 0.021157304559399133,
      "grad_norm": 1.5404480695724487,
      "learning_rate": 7.774790660436858e-05,
      "loss": 2.4014,
      "step": 50
    },
    {
      "epoch": 0.021580450650587116,
      "grad_norm": 1.2230170965194702,
      "learning_rate": 7.339631544333249e-05,
      "loss": 2.1396,
      "step": 51
    },
    {
      "epoch": 0.022003596741775096,
      "grad_norm": 1.3236002922058105,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.1162,
      "step": 52
    },
    {
      "epoch": 0.02242674283296308,
      "grad_norm": 1.2597148418426514,
      "learning_rate": 6.486251759186572e-05,
      "loss": 2.0798,
      "step": 53
    },
    {
      "epoch": 0.022849888924151063,
      "grad_norm": 1.177053689956665,
      "learning_rate": 6.069749683460765e-05,
      "loss": 2.1683,
      "step": 54
    },
    {
      "epoch": 0.023273035015339047,
      "grad_norm": 1.136125922203064,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 2.0631,
      "step": 55
    },
    {
      "epoch": 0.023696181106527027,
      "grad_norm": 1.4012868404388428,
      "learning_rate": 5.261313375270014e-05,
      "loss": 2.2295,
      "step": 56
    },
    {
      "epoch": 0.02411932719771501,
      "grad_norm": 1.1680681705474854,
      "learning_rate": 4.87100722594094e-05,
      "loss": 2.2061,
      "step": 57
    },
    {
      "epoch": 0.024542473288902994,
      "grad_norm": 1.1918954849243164,
      "learning_rate": 4.491030185478976e-05,
      "loss": 2.07,
      "step": 58
    },
    {
      "epoch": 0.024965619380090977,
      "grad_norm": 1.3730967044830322,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.1515,
      "step": 59
    },
    {
      "epoch": 0.025388765471278957,
      "grad_norm": 1.1280912160873413,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 2.156,
      "step": 60
    },
    {
      "epoch": 0.025388765471278957,
      "eval_loss": 2.168715715408325,
      "eval_runtime": 25.4328,
      "eval_samples_per_second": 78.245,
      "eval_steps_per_second": 19.581,
      "step": 60
    },
    {
      "epoch": 0.02581191156246694,
      "grad_norm": 1.1480927467346191,
      "learning_rate": 3.4206127406028745e-05,
      "loss": 2.231,
      "step": 61
    },
    {
      "epoch": 0.026235057653654924,
      "grad_norm": 1.1314619779586792,
      "learning_rate": 3.089373510131354e-05,
      "loss": 2.1425,
      "step": 62
    },
    {
      "epoch": 0.026658203744842908,
      "grad_norm": 1.1381090879440308,
      "learning_rate": 2.7720513617260856e-05,
      "loss": 2.1525,
      "step": 63
    },
    {
      "epoch": 0.027081349836030888,
      "grad_norm": 1.2480595111846924,
      "learning_rate": 2.4692853399638917e-05,
      "loss": 2.1493,
      "step": 64
    },
    {
      "epoch": 0.02750449592721887,
      "grad_norm": 1.112952709197998,
      "learning_rate": 2.181685175319702e-05,
      "loss": 2.0714,
      "step": 65
    },
    {
      "epoch": 0.027927642018406855,
      "grad_norm": 1.2665915489196777,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.1679,
      "step": 66
    },
    {
      "epoch": 0.02835078810959484,
      "grad_norm": 1.1438580751419067,
      "learning_rate": 1.6542674627869737e-05,
      "loss": 2.2069,
      "step": 67
    },
    {
      "epoch": 0.028773934200782822,
      "grad_norm": 1.0998873710632324,
      "learning_rate": 1.415512063981339e-05,
      "loss": 2.1404,
      "step": 68
    },
    {
      "epoch": 0.029197080291970802,
      "grad_norm": 1.0739041566848755,
      "learning_rate": 1.19404468143262e-05,
      "loss": 2.1207,
      "step": 69
    },
    {
      "epoch": 0.029620226383158785,
      "grad_norm": 1.206387996673584,
      "learning_rate": 9.903113209758096e-06,
      "loss": 2.2733,
      "step": 70
    },
    {
      "epoch": 0.03004337247434677,
      "grad_norm": 1.1807301044464111,
      "learning_rate": 8.047222744854943e-06,
      "loss": 2.1562,
      "step": 71
    },
    {
      "epoch": 0.030466518565534752,
      "grad_norm": 1.1681818962097168,
      "learning_rate": 6.37651293602628e-06,
      "loss": 2.1226,
      "step": 72
    },
    {
      "epoch": 0.030889664656722732,
      "grad_norm": 1.1383371353149414,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 2.2101,
      "step": 73
    },
    {
      "epoch": 0.031312810747910716,
      "grad_norm": 1.1326333284378052,
      "learning_rate": 3.6037139304146762e-06,
      "loss": 2.0855,
      "step": 74
    },
    {
      "epoch": 0.031735956839098696,
      "grad_norm": 1.1640607118606567,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 2.1586,
      "step": 75
    },
    {
      "epoch": 0.03215910293028668,
      "grad_norm": 1.2493934631347656,
      "learning_rate": 1.6070411401370334e-06,
      "loss": 2.1355,
      "step": 76
    },
    {
      "epoch": 0.03258224902147466,
      "grad_norm": 1.3628870248794556,
      "learning_rate": 9.0502382320653e-07,
      "loss": 2.1629,
      "step": 77
    },
    {
      "epoch": 0.03300539511266265,
      "grad_norm": 1.1996616125106812,
      "learning_rate": 4.025706004760932e-07,
      "loss": 2.2131,
      "step": 78
    },
    {
      "epoch": 0.03342854120385063,
      "grad_norm": 1.3560621738433838,
      "learning_rate": 1.0069334586854107e-07,
      "loss": 2.2186,
      "step": 79
    },
    {
      "epoch": 0.03385168729503861,
      "grad_norm": 1.1883161067962646,
      "learning_rate": 0.0,
      "loss": 2.2633,
      "step": 80
    },
    {
      "epoch": 0.03385168729503861,
      "eval_loss": 2.1620700359344482,
      "eval_runtime": 24.9252,
      "eval_samples_per_second": 79.839,
      "eval_steps_per_second": 19.98,
      "step": 80
    }
  ],
  "logging_steps": 1,
  "max_steps": 80,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1476504563220480.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}