{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.978165938864628,
  "eval_steps": 500,
  "global_step": 570,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008733624454148471,
      "grad_norm": 648.0,
      "learning_rate": 3.5087719298245615e-06,
      "loss": 56.9969,
      "step": 1
    },
    {
      "epoch": 0.043668122270742356,
      "grad_norm": 584.0,
      "learning_rate": 1.7543859649122806e-05,
      "loss": 59.6974,
      "step": 5
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 356.0,
      "learning_rate": 3.508771929824561e-05,
      "loss": 42.0524,
      "step": 10
    },
    {
      "epoch": 0.13100436681222707,
      "grad_norm": 39.75,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 23.223,
      "step": 15
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 26.625,
      "learning_rate": 7.017543859649122e-05,
      "loss": 20.5089,
      "step": 20
    },
    {
      "epoch": 0.2183406113537118,
      "grad_norm": 7.15625,
      "learning_rate": 8.771929824561403e-05,
      "loss": 17.4609,
      "step": 25
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 10.25,
      "learning_rate": 0.00010526315789473685,
      "loss": 16.9699,
      "step": 30
    },
    {
      "epoch": 0.3056768558951965,
      "grad_norm": 36.0,
      "learning_rate": 0.00012280701754385965,
      "loss": 14.7118,
      "step": 35
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 54.75,
      "learning_rate": 0.00014035087719298245,
      "loss": 9.0151,
      "step": 40
    },
    {
      "epoch": 0.3930131004366812,
      "grad_norm": 4.09375,
      "learning_rate": 0.00015789473684210527,
      "loss": 2.2763,
      "step": 45
    },
    {
      "epoch": 0.4366812227074236,
      "grad_norm": 2.5,
      "learning_rate": 0.00017543859649122806,
      "loss": 1.6984,
      "step": 50
    },
    {
      "epoch": 0.48034934497816595,
      "grad_norm": 2.5,
      "learning_rate": 0.00019298245614035088,
      "loss": 1.4194,
      "step": 55
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 1.9765625,
      "learning_rate": 0.00019998312416333227,
      "loss": 1.2842,
      "step": 60
    },
    {
      "epoch": 0.5676855895196506,
      "grad_norm": 13.0625,
      "learning_rate": 0.0001998800146766861,
      "loss": 1.2936,
      "step": 65
    },
    {
      "epoch": 0.611353711790393,
      "grad_norm": 3.15625,
      "learning_rate": 0.00019968326771610797,
      "loss": 1.1866,
      "step": 70
    },
    {
      "epoch": 0.6550218340611353,
      "grad_norm": 3.765625,
      "learning_rate": 0.00019939306773179497,
      "loss": 1.0911,
      "step": 75
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 5.34375,
      "learning_rate": 0.00019900968678611666,
      "loss": 1.0412,
      "step": 80
    },
    {
      "epoch": 0.74235807860262,
      "grad_norm": 2.625,
      "learning_rate": 0.00019853348429855672,
      "loss": 0.9954,
      "step": 85
    },
    {
      "epoch": 0.7860262008733624,
      "grad_norm": 2.6875,
      "learning_rate": 0.0001979649067087574,
      "loss": 0.9395,
      "step": 90
    },
    {
      "epoch": 0.8296943231441049,
      "grad_norm": 4.375,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.9498,
      "step": 95
    },
    {
      "epoch": 0.8733624454148472,
      "grad_norm": 4.875,
      "learning_rate": 0.00019655284448939094,
      "loss": 0.8991,
      "step": 100
    },
    {
      "epoch": 0.9170305676855895,
      "grad_norm": 1.75,
      "learning_rate": 0.00019571068366759143,
      "loss": 0.8827,
      "step": 105
    },
    {
      "epoch": 0.9606986899563319,
      "grad_norm": 3.1875,
      "learning_rate": 0.00019477879411801844,
      "loss": 0.8665,
      "step": 110
    },
    {
      "epoch": 0.9956331877729258,
      "eval_loss": 2.268367052078247,
      "eval_runtime": 1.0131,
      "eval_samples_per_second": 4.935,
      "eval_steps_per_second": 1.974,
      "step": 114
    },
    {
      "epoch": 1.0043668122270741,
      "grad_norm": 1.6015625,
      "learning_rate": 0.00019375804948675306,
      "loss": 0.8773,
      "step": 115
    },
    {
      "epoch": 1.0480349344978166,
      "grad_norm": 9.1875,
      "learning_rate": 0.00019264940672148018,
      "loss": 0.8211,
      "step": 120
    },
    {
      "epoch": 1.091703056768559,
      "grad_norm": 1.25,
      "learning_rate": 0.00019145390517435012,
      "loss": 0.8465,
      "step": 125
    },
    {
      "epoch": 1.1353711790393013,
      "grad_norm": 3.09375,
      "learning_rate": 0.00019017266562758659,
      "loss": 0.8369,
      "step": 130
    },
    {
      "epoch": 1.1790393013100438,
      "grad_norm": 1.015625,
      "learning_rate": 0.00018880688924275378,
      "loss": 0.7924,
      "step": 135
    },
    {
      "epoch": 1.222707423580786,
      "grad_norm": 1.9140625,
      "learning_rate": 0.00018735785643466784,
      "loss": 0.778,
      "step": 140
    },
    {
      "epoch": 1.2663755458515285,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00018582692567100867,
      "loss": 0.7681,
      "step": 145
    },
    {
      "epoch": 1.3100436681222707,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00018421553219875658,
      "loss": 0.8007,
      "step": 150
    },
    {
      "epoch": 1.3537117903930131,
      "grad_norm": 80.5,
      "learning_rate": 0.00018252518669864936,
      "loss": 0.7683,
      "step": 155
    },
    {
      "epoch": 1.3973799126637554,
      "grad_norm": 0.73828125,
      "learning_rate": 0.0001807574738689193,
      "loss": 0.7713,
      "step": 160
    },
    {
      "epoch": 1.4410480349344978,
      "grad_norm": 2.875,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.7784,
      "step": 165
    },
    {
      "epoch": 1.48471615720524,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00017699664611907072,
      "loss": 0.7742,
      "step": 170
    },
    {
      "epoch": 1.5283842794759825,
      "grad_norm": 2.046875,
      "learning_rate": 0.0001750070569734681,
      "loss": 0.7356,
      "step": 175
    },
    {
      "epoch": 1.572052401746725,
      "grad_norm": 1.375,
      "learning_rate": 0.0001729471487418621,
      "loss": 0.7613,
      "step": 180
    },
    {
      "epoch": 1.6157205240174672,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00017081885258739846,
      "loss": 0.7373,
      "step": 185
    },
    {
      "epoch": 1.6593886462882095,
      "grad_norm": 1.109375,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.7395,
      "step": 190
    },
    {
      "epoch": 1.703056768558952,
      "grad_norm": 0.77734375,
      "learning_rate": 0.00016636513986016213,
      "loss": 0.7456,
      "step": 195
    },
    {
      "epoch": 1.7467248908296944,
      "grad_norm": 1.5,
      "learning_rate": 0.00016404389864129533,
      "loss": 0.7535,
      "step": 200
    },
    {
      "epoch": 1.7903930131004366,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00016166261629298995,
      "loss": 0.7334,
      "step": 205
    },
    {
      "epoch": 1.8340611353711789,
      "grad_norm": 0.99609375,
      "learning_rate": 0.00015922352526649803,
      "loss": 0.7087,
      "step": 210
    },
    {
      "epoch": 1.8777292576419216,
      "grad_norm": 5.03125,
      "learning_rate": 0.00015672891220868432,
      "loss": 0.7264,
      "step": 215
    },
    {
      "epoch": 1.9213973799126638,
      "grad_norm": 0.60546875,
      "learning_rate": 0.00015418111581829574,
      "loss": 0.7336,
      "step": 220
    },
    {
      "epoch": 1.965065502183406,
      "grad_norm": 0.79296875,
      "learning_rate": 0.00015158252465343242,
      "loss": 0.7577,
      "step": 225
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.1721692085266113,
      "eval_runtime": 1.0003,
      "eval_samples_per_second": 4.999,
      "eval_steps_per_second": 1.999,
      "step": 229
    },
    {
      "epoch": 2.0087336244541483,
      "grad_norm": 0.5078125,
      "learning_rate": 0.00014893557489227517,
      "loss": 0.7045,
      "step": 230
    },
    {
      "epoch": 2.052401746724891,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00014624274804916958,
      "loss": 0.6618,
      "step": 235
    },
    {
      "epoch": 2.096069868995633,
      "grad_norm": 0.62109375,
      "learning_rate": 0.00014350656864820733,
      "loss": 0.6572,
      "step": 240
    },
    {
      "epoch": 2.1397379912663754,
      "grad_norm": 0.515625,
      "learning_rate": 0.00014072960185648577,
      "loss": 0.6606,
      "step": 245
    },
    {
      "epoch": 2.183406113537118,
      "grad_norm": 0.75,
      "learning_rate": 0.00013791445107926478,
      "loss": 0.6832,
      "step": 250
    },
    {
      "epoch": 2.2270742358078603,
      "grad_norm": 0.86328125,
      "learning_rate": 0.00013506375551927547,
      "loss": 0.6344,
      "step": 255
    },
    {
      "epoch": 2.2707423580786026,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00013218018770246858,
      "loss": 0.6513,
      "step": 260
    },
    {
      "epoch": 2.314410480349345,
      "grad_norm": 0.83203125,
      "learning_rate": 0.0001292664509725226,
      "loss": 0.6569,
      "step": 265
    },
    {
      "epoch": 2.3580786026200875,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00012632527695645993,
      "loss": 0.6706,
      "step": 270
    },
    {
      "epoch": 2.4017467248908297,
      "grad_norm": 1.265625,
      "learning_rate": 0.00012335942300374788,
      "loss": 0.6641,
      "step": 275
    },
    {
      "epoch": 2.445414847161572,
      "grad_norm": 1.59375,
      "learning_rate": 0.00012037166960128443,
      "loss": 0.6636,
      "step": 280
    },
    {
      "epoch": 2.489082969432314,
      "grad_norm": 0.765625,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.6687,
      "step": 285
    },
    {
      "epoch": 2.532751091703057,
      "grad_norm": 0.73046875,
      "learning_rate": 0.00011434168642236964,
      "loss": 0.6601,
      "step": 290
    },
    {
      "epoch": 2.576419213973799,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00011130510975274409,
      "loss": 0.6467,
      "step": 295
    },
    {
      "epoch": 2.6200873362445414,
      "grad_norm": 0.53125,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.6567,
      "step": 300
    },
    {
      "epoch": 2.6637554585152836,
      "grad_norm": 0.875,
      "learning_rate": 0.00010520301753137724,
      "loss": 0.6625,
      "step": 305
    },
    {
      "epoch": 2.7074235807860263,
      "grad_norm": 0.59375,
      "learning_rate": 0.00010214322268866032,
      "loss": 0.6614,
      "step": 310
    },
    {
      "epoch": 2.7510917030567685,
      "grad_norm": 0.5703125,
      "learning_rate": 9.908141857552737e-05,
      "loss": 0.6382,
      "step": 315
    },
    {
      "epoch": 2.7947598253275108,
      "grad_norm": 0.470703125,
      "learning_rate": 9.602047563211359e-05,
      "loss": 0.6527,
      "step": 320
    },
    {
      "epoch": 2.8384279475982535,
      "grad_norm": 0.89453125,
      "learning_rate": 9.296326349120785e-05,
      "loss": 0.682,
      "step": 325
    },
    {
      "epoch": 2.8820960698689957,
      "grad_norm": 0.49609375,
      "learning_rate": 8.991264828797319e-05,
      "loss": 0.651,
      "step": 330
    },
    {
      "epoch": 2.925764192139738,
      "grad_norm": 0.51953125,
      "learning_rate": 8.687148997294621e-05,
      "loss": 0.667,
      "step": 335
    },
    {
      "epoch": 2.96943231441048,
      "grad_norm": 0.427734375,
      "learning_rate": 8.384263963083453e-05,
      "loss": 0.6255,
      "step": 340
    },
    {
      "epoch": 2.995633187772926,
      "eval_loss": 2.174067974090576,
      "eval_runtime": 1.051,
      "eval_samples_per_second": 4.757,
      "eval_steps_per_second": 1.903,
      "step": 343
    },
    {
      "epoch": 3.013100436681223,
      "grad_norm": 0.62890625,
      "learning_rate": 8.082893680762619e-05,
      "loss": 0.6202,
      "step": 345
    },
    {
      "epoch": 3.056768558951965,
      "grad_norm": 0.53125,
      "learning_rate": 7.783320684851614e-05,
      "loss": 0.6176,
      "step": 350
    },
    {
      "epoch": 3.1004366812227073,
      "grad_norm": 0.51171875,
      "learning_rate": 7.485825824914659e-05,
      "loss": 0.5783,
      "step": 355
    },
    {
      "epoch": 3.14410480349345,
      "grad_norm": 0.50390625,
      "learning_rate": 7.190688002264308e-05,
      "loss": 0.5812,
      "step": 360
    },
    {
      "epoch": 3.1877729257641922,
      "grad_norm": 0.5546875,
      "learning_rate": 6.898183908491617e-05,
      "loss": 0.5981,
      "step": 365
    },
    {
      "epoch": 3.2314410480349345,
      "grad_norm": 0.53125,
      "learning_rate": 6.608587766067852e-05,
      "loss": 0.5853,
      "step": 370
    },
    {
      "epoch": 3.2751091703056767,
      "grad_norm": 0.609375,
      "learning_rate": 6.322171071261071e-05,
      "loss": 0.5908,
      "step": 375
    },
    {
      "epoch": 3.3187772925764194,
      "grad_norm": 1.125,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.5644,
      "step": 380
    },
    {
      "epoch": 3.3624454148471616,
      "grad_norm": 0.63671875,
      "learning_rate": 5.7599468541830356e-05,
      "loss": 0.5746,
      "step": 385
    },
    {
      "epoch": 3.406113537117904,
      "grad_norm": 0.8828125,
      "learning_rate": 5.484666416891109e-05,
      "loss": 0.5929,
      "step": 390
    },
    {
      "epoch": 3.449781659388646,
      "grad_norm": 0.5859375,
      "learning_rate": 5.2136191030328455e-05,
      "loss": 0.5704,
      "step": 395
    },
    {
      "epoch": 3.493449781659389,
      "grad_norm": 0.671875,
      "learning_rate": 4.9470590193569044e-05,
      "loss": 0.5971,
      "step": 400
    },
    {
      "epoch": 3.537117903930131,
      "grad_norm": 0.51953125,
      "learning_rate": 4.685236065835443e-05,
      "loss": 0.6042,
      "step": 405
    },
    {
      "epoch": 3.5807860262008733,
      "grad_norm": 0.61328125,
      "learning_rate": 4.4283957013829846e-05,
      "loss": 0.5822,
      "step": 410
    },
    {
      "epoch": 3.6244541484716155,
      "grad_norm": 0.64453125,
      "learning_rate": 4.176778713738787e-05,
      "loss": 0.5709,
      "step": 415
    },
    {
      "epoch": 3.668122270742358,
      "grad_norm": 0.49609375,
      "learning_rate": 3.9306209937284346e-05,
      "loss": 0.5907,
      "step": 420
    },
    {
      "epoch": 3.7117903930131004,
      "grad_norm": 0.5625,
      "learning_rate": 3.69015331411628e-05,
      "loss": 0.589,
      "step": 425
    },
    {
      "epoch": 3.7554585152838427,
      "grad_norm": 0.65234375,
      "learning_rate": 3.455601113256073e-05,
      "loss": 0.6115,
      "step": 430
    },
    {
      "epoch": 3.7991266375545854,
      "grad_norm": 0.50390625,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.5629,
      "step": 435
    },
    {
      "epoch": 3.8427947598253276,
      "grad_norm": 0.458984375,
      "learning_rate": 3.0051169662624225e-05,
      "loss": 0.5943,
      "step": 440
    },
    {
      "epoch": 3.88646288209607,
      "grad_norm": 0.4765625,
      "learning_rate": 2.789607348837153e-05,
      "loss": 0.5944,
      "step": 445
    },
    {
      "epoch": 3.930131004366812,
      "grad_norm": 0.4765625,
      "learning_rate": 2.5808574716471856e-05,
      "loss": 0.6155,
      "step": 450
    },
    {
      "epoch": 3.9737991266375547,
      "grad_norm": 0.48828125,
      "learning_rate": 2.379063037619146e-05,
      "loss": 0.5966,
      "step": 455
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.214209794998169,
      "eval_runtime": 1.0004,
      "eval_samples_per_second": 4.998,
      "eval_steps_per_second": 1.999,
      "step": 458
    },
    {
      "epoch": 4.0174672489082965,
      "grad_norm": 0.458984375,
      "learning_rate": 2.184413228954468e-05,
      "loss": 0.5676,
      "step": 460
    },
    {
      "epoch": 4.06113537117904,
      "grad_norm": 0.48828125,
      "learning_rate": 1.9970905297711606e-05,
      "loss": 0.5632,
      "step": 465
    },
    {
      "epoch": 4.104803493449782,
      "grad_norm": 0.5078125,
      "learning_rate": 1.8172705550250092e-05,
      "loss": 0.5515,
      "step": 470
    },
    {
      "epoch": 4.148471615720524,
      "grad_norm": 0.47265625,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.5725,
      "step": 475
    },
    {
      "epoch": 4.192139737991266,
      "grad_norm": 0.50390625,
      "learning_rate": 1.4808059116167305e-05,
      "loss": 0.5362,
      "step": 480
    },
    {
      "epoch": 4.235807860262009,
      "grad_norm": 0.478515625,
      "learning_rate": 1.3244766784236307e-05,
      "loss": 0.5569,
      "step": 485
    },
    {
      "epoch": 4.279475982532751,
      "grad_norm": 0.46484375,
      "learning_rate": 1.176280744885121e-05,
      "loss": 0.573,
      "step": 490
    },
    {
      "epoch": 4.323144104803493,
      "grad_norm": 0.478515625,
      "learning_rate": 1.0363570446297999e-05,
      "loss": 0.5559,
      "step": 495
    },
    {
      "epoch": 4.366812227074236,
      "grad_norm": 0.53125,
      "learning_rate": 9.048367560708604e-06,
      "loss": 0.548,
      "step": 500
    },
    {
      "epoch": 4.4104803493449785,
      "grad_norm": 0.515625,
      "learning_rate": 7.818431794263836e-06,
      "loss": 0.5755,
      "step": 505
    },
    {
      "epoch": 4.454148471615721,
      "grad_norm": 0.470703125,
      "learning_rate": 6.674916211254289e-06,
      "loss": 0.5559,
      "step": 510
    },
    {
      "epoch": 4.497816593886463,
      "grad_norm": 0.50390625,
      "learning_rate": 5.618892857083069e-06,
      "loss": 0.5491,
      "step": 515
    },
    {
      "epoch": 4.541484716157205,
      "grad_norm": 0.4765625,
      "learning_rate": 4.65135175322361e-06,
      "loss": 0.5586,
      "step": 520
    },
    {
      "epoch": 4.585152838427947,
      "grad_norm": 0.458984375,
      "learning_rate": 3.7731999690749585e-06,
      "loss": 0.5569,
      "step": 525
    },
    {
      "epoch": 4.62882096069869,
      "grad_norm": 0.47265625,
      "learning_rate": 2.9852607715846193e-06,
      "loss": 0.5458,
      "step": 530
    },
    {
      "epoch": 4.672489082969433,
      "grad_norm": 0.470703125,
      "learning_rate": 2.288272853436013e-06,
      "loss": 0.5253,
      "step": 535
    },
    {
      "epoch": 4.716157205240175,
      "grad_norm": 0.47265625,
      "learning_rate": 1.6828896405244988e-06,
      "loss": 0.5595,
      "step": 540
    },
    {
      "epoch": 4.759825327510917,
      "grad_norm": 0.486328125,
      "learning_rate": 1.1696786793707781e-06,
      "loss": 0.5626,
      "step": 545
    },
    {
      "epoch": 4.8034934497816595,
      "grad_norm": 0.5,
      "learning_rate": 7.491211050462798e-07,
      "loss": 0.5407,
      "step": 550
    },
    {
      "epoch": 4.847161572052402,
      "grad_norm": 0.47265625,
      "learning_rate": 4.216111901092501e-07,
      "loss": 0.5542,
      "step": 555
    },
    {
      "epoch": 4.890829694323144,
      "grad_norm": 0.5234375,
      "learning_rate": 1.8745597497433765e-07,
      "loss": 0.5542,
      "step": 560
    },
    {
      "epoch": 4.934497816593886,
      "grad_norm": 0.458984375,
      "learning_rate": 4.687498006236135e-08,
      "loss": 0.5682,
      "step": 565
    },
    {
      "epoch": 4.978165938864628,
      "grad_norm": 0.49609375,
      "learning_rate": 0.0,
      "loss": 0.5399,
      "step": 570
    },
    {
      "epoch": 4.978165938864628,
      "eval_loss": 2.236276865005493,
      "eval_runtime": 0.9998,
      "eval_samples_per_second": 5.001,
      "eval_steps_per_second": 2.0,
      "step": 570
    },
    {
      "epoch": 4.978165938864628,
      "step": 570,
      "total_flos": 8.714577082329334e+17,
      "train_loss": 2.449154797771521,
      "train_runtime": 4532.0541,
      "train_samples_per_second": 2.02,
      "train_steps_per_second": 0.126
    }
  ],
  "logging_steps": 5,
  "max_steps": 570,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.714577082329334e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}