{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4108885464817668,
  "eval_steps": 10,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001027221366204417,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7522,
      "step": 1
    },
    {
      "epoch": 0.002054442732408834,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7541,
      "step": 2
    },
    {
      "epoch": 0.0030816640986132513,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8031,
      "step": 3
    },
    {
      "epoch": 0.004108885464817668,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8062,
      "step": 4
    },
    {
      "epoch": 0.005136106831022085,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7733,
      "step": 5
    },
    {
      "epoch": 0.0061633281972265025,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7949,
      "step": 6
    },
    {
      "epoch": 0.007190549563430919,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7657,
      "step": 7
    },
    {
      "epoch": 0.008217770929635337,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.803,
      "step": 8
    },
    {
      "epoch": 0.009244992295839754,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7793,
      "step": 9
    },
    {
      "epoch": 0.01027221366204417,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7935,
      "step": 10
    },
    {
      "epoch": 0.01027221366204417,
      "eval_loss": 2.8114004135131836,
      "eval_runtime": 37.8463,
      "eval_samples_per_second": 26.423,
      "eval_steps_per_second": 1.11,
      "step": 10
    },
    {
      "epoch": 0.011299435028248588,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7546,
      "step": 11
    },
    {
      "epoch": 0.012326656394453005,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7423,
      "step": 12
    },
    {
      "epoch": 0.01335387776065742,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8057,
      "step": 13
    },
    {
      "epoch": 0.014381099126861838,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7663,
      "step": 14
    },
    {
      "epoch": 0.015408320493066256,
      "grad_norm": 4.694424152374268,
      "learning_rate": 1.7123287671232876e-08,
      "loss": 2.7715,
      "step": 15
    },
    {
      "epoch": 0.016435541859270673,
      "grad_norm": 4.905329704284668,
      "learning_rate": 3.424657534246575e-08,
      "loss": 2.751,
      "step": 16
    },
    {
      "epoch": 0.01746276322547509,
      "grad_norm": 4.705279350280762,
      "learning_rate": 5.136986301369863e-08,
      "loss": 2.7186,
      "step": 17
    },
    {
      "epoch": 0.01848998459167951,
      "grad_norm": 5.154810905456543,
      "learning_rate": 6.84931506849315e-08,
      "loss": 2.8073,
      "step": 18
    },
    {
      "epoch": 0.019517205957883924,
      "grad_norm": 5.070403099060059,
      "learning_rate": 8.561643835616439e-08,
      "loss": 2.7237,
      "step": 19
    },
    {
      "epoch": 0.02054442732408834,
      "grad_norm": 4.901423454284668,
      "learning_rate": 1.0273972602739726e-07,
      "loss": 2.7882,
      "step": 20
    },
    {
      "epoch": 0.02054442732408834,
      "eval_loss": 2.810307502746582,
      "eval_runtime": 37.65,
      "eval_samples_per_second": 26.56,
      "eval_steps_per_second": 1.116,
      "step": 20
    },
    {
      "epoch": 0.02157164869029276,
      "grad_norm": 4.914156436920166,
      "learning_rate": 1.1986301369863014e-07,
      "loss": 2.8005,
      "step": 21
    },
    {
      "epoch": 0.022598870056497175,
      "grad_norm": 4.937129974365234,
      "learning_rate": 1.36986301369863e-07,
      "loss": 2.7902,
      "step": 22
    },
    {
      "epoch": 0.02362609142270159,
      "grad_norm": 5.0690202713012695,
      "learning_rate": 1.541095890410959e-07,
      "loss": 2.7474,
      "step": 23
    },
    {
      "epoch": 0.02465331278890601,
      "grad_norm": 4.980844974517822,
      "learning_rate": 1.7123287671232878e-07,
      "loss": 2.7695,
      "step": 24
    },
    {
      "epoch": 0.025680534155110426,
      "grad_norm": 4.8092451095581055,
      "learning_rate": 1.8835616438356165e-07,
      "loss": 2.7611,
      "step": 25
    },
    {
      "epoch": 0.02670775552131484,
      "grad_norm": 4.765528202056885,
      "learning_rate": 2.0547945205479452e-07,
      "loss": 2.7823,
      "step": 26
    },
    {
      "epoch": 0.02773497688751926,
      "grad_norm": 3.9759938716888428,
      "learning_rate": 2.226027397260274e-07,
      "loss": 2.7445,
      "step": 27
    },
    {
      "epoch": 0.028762198253723677,
      "grad_norm": 4.023419380187988,
      "learning_rate": 2.397260273972603e-07,
      "loss": 2.7679,
      "step": 28
    },
    {
      "epoch": 0.029789419619928096,
      "grad_norm": 4.161378383636475,
      "learning_rate": 2.568493150684932e-07,
      "loss": 2.7704,
      "step": 29
    },
    {
      "epoch": 0.030816640986132512,
      "grad_norm": 3.8363842964172363,
      "learning_rate": 2.73972602739726e-07,
      "loss": 2.7598,
      "step": 30
    },
    {
      "epoch": 0.030816640986132512,
      "eval_loss": 2.772540330886841,
      "eval_runtime": 37.2624,
      "eval_samples_per_second": 26.837,
      "eval_steps_per_second": 1.127,
      "step": 30
    },
    {
      "epoch": 0.03184386235233693,
      "grad_norm": 3.718747615814209,
      "learning_rate": 2.910958904109589e-07,
      "loss": 2.7241,
      "step": 31
    },
    {
      "epoch": 0.03287108371854135,
      "grad_norm": 3.555985927581787,
      "learning_rate": 3.082191780821918e-07,
      "loss": 2.7751,
      "step": 32
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 3.6041972637176514,
      "learning_rate": 3.2534246575342466e-07,
      "loss": 2.7322,
      "step": 33
    },
    {
      "epoch": 0.03492552645095018,
      "grad_norm": 3.4408438205718994,
      "learning_rate": 3.4246575342465755e-07,
      "loss": 2.727,
      "step": 34
    },
    {
      "epoch": 0.035952747817154594,
      "grad_norm": 3.4169280529022217,
      "learning_rate": 3.595890410958904e-07,
      "loss": 2.7062,
      "step": 35
    },
    {
      "epoch": 0.03697996918335902,
      "grad_norm": 3.3882925510406494,
      "learning_rate": 3.767123287671233e-07,
      "loss": 2.6271,
      "step": 36
    },
    {
      "epoch": 0.03800719054956343,
      "grad_norm": 3.0491855144500732,
      "learning_rate": 3.938356164383562e-07,
      "loss": 2.7309,
      "step": 37
    },
    {
      "epoch": 0.03903441191576785,
      "grad_norm": 2.8444902896881104,
      "learning_rate": 4.1095890410958903e-07,
      "loss": 2.647,
      "step": 38
    },
    {
      "epoch": 0.040061633281972264,
      "grad_norm": 2.7438602447509766,
      "learning_rate": 4.2808219178082193e-07,
      "loss": 2.6478,
      "step": 39
    },
    {
      "epoch": 0.04108885464817668,
      "grad_norm": 2.8886020183563232,
      "learning_rate": 4.452054794520548e-07,
      "loss": 2.7065,
      "step": 40
    },
    {
      "epoch": 0.04108885464817668,
      "eval_loss": 2.7021424770355225,
      "eval_runtime": 37.3227,
      "eval_samples_per_second": 26.793,
      "eval_steps_per_second": 1.125,
      "step": 40
    },
    {
      "epoch": 0.042116076014381096,
      "grad_norm": 2.8825268745422363,
      "learning_rate": 4.6232876712328767e-07,
      "loss": 2.6666,
      "step": 41
    },
    {
      "epoch": 0.04314329738058552,
      "grad_norm": 2.8848748207092285,
      "learning_rate": 4.794520547945206e-07,
      "loss": 2.597,
      "step": 42
    },
    {
      "epoch": 0.044170518746789934,
      "grad_norm": 2.9176979064941406,
      "learning_rate": 4.965753424657534e-07,
      "loss": 2.6638,
      "step": 43
    },
    {
      "epoch": 0.04519774011299435,
      "grad_norm": 2.6903059482574463,
      "learning_rate": 5.136986301369864e-07,
      "loss": 2.6202,
      "step": 44
    },
    {
      "epoch": 0.046224961479198766,
      "grad_norm": 2.5349855422973633,
      "learning_rate": 5.308219178082192e-07,
      "loss": 2.6466,
      "step": 45
    },
    {
      "epoch": 0.04725218284540318,
      "grad_norm": 2.405383825302124,
      "learning_rate": 5.47945205479452e-07,
      "loss": 2.6291,
      "step": 46
    },
    {
      "epoch": 0.048279404211607604,
      "grad_norm": 2.526106595993042,
      "learning_rate": 5.65068493150685e-07,
      "loss": 2.6718,
      "step": 47
    },
    {
      "epoch": 0.04930662557781202,
      "grad_norm": 2.3981597423553467,
      "learning_rate": 5.821917808219178e-07,
      "loss": 2.592,
      "step": 48
    },
    {
      "epoch": 0.050333846944016436,
      "grad_norm": 2.61842679977417,
      "learning_rate": 5.993150684931507e-07,
      "loss": 2.6039,
      "step": 49
    },
    {
      "epoch": 0.05136106831022085,
      "grad_norm": 2.3001420497894287,
      "learning_rate": 6.164383561643836e-07,
      "loss": 2.5481,
      "step": 50
    },
    {
      "epoch": 0.05136106831022085,
      "eval_loss": 2.6244444847106934,
      "eval_runtime": 37.3248,
      "eval_samples_per_second": 26.792,
      "eval_steps_per_second": 1.125,
      "step": 50
    },
    {
      "epoch": 0.05238828967642527,
      "grad_norm": 2.12744140625,
      "learning_rate": 6.335616438356165e-07,
      "loss": 2.5336,
      "step": 51
    },
    {
      "epoch": 0.05341551104262968,
      "grad_norm": 1.974413275718689,
      "learning_rate": 6.506849315068493e-07,
      "loss": 2.5882,
      "step": 52
    },
    {
      "epoch": 0.054442732408834106,
      "grad_norm": 2.098527669906616,
      "learning_rate": 6.678082191780823e-07,
      "loss": 2.5073,
      "step": 53
    },
    {
      "epoch": 0.05546995377503852,
      "grad_norm": 2.056288719177246,
      "learning_rate": 6.849315068493151e-07,
      "loss": 2.5612,
      "step": 54
    },
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 2.2291629314422607,
      "learning_rate": 7.020547945205481e-07,
      "loss": 2.527,
      "step": 55
    },
    {
      "epoch": 0.05752439650744735,
      "grad_norm": 2.140164375305176,
      "learning_rate": 7.191780821917808e-07,
      "loss": 2.4972,
      "step": 56
    },
    {
      "epoch": 0.05855161787365177,
      "grad_norm": 1.8682485818862915,
      "learning_rate": 7.363013698630137e-07,
      "loss": 2.5231,
      "step": 57
    },
    {
      "epoch": 0.05957883923985619,
      "grad_norm": 1.9373308420181274,
      "learning_rate": 7.534246575342466e-07,
      "loss": 2.4509,
      "step": 58
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.8535712957382202,
      "learning_rate": 7.705479452054795e-07,
      "loss": 2.5164,
      "step": 59
    },
    {
      "epoch": 0.061633281972265024,
      "grad_norm": 1.7497329711914062,
      "learning_rate": 7.876712328767124e-07,
      "loss": 2.5177,
      "step": 60
    },
    {
      "epoch": 0.061633281972265024,
      "eval_loss": 2.5608646869659424,
      "eval_runtime": 37.3426,
      "eval_samples_per_second": 26.779,
      "eval_steps_per_second": 1.125,
      "step": 60
    },
    {
      "epoch": 0.06266050333846944,
      "grad_norm": 1.8476629257202148,
      "learning_rate": 8.047945205479453e-07,
      "loss": 2.4838,
      "step": 61
    },
    {
      "epoch": 0.06368772470467386,
      "grad_norm": 1.7130696773529053,
      "learning_rate": 8.219178082191781e-07,
      "loss": 2.473,
      "step": 62
    },
    {
      "epoch": 0.06471494607087827,
      "grad_norm": 1.751081109046936,
      "learning_rate": 8.39041095890411e-07,
      "loss": 2.5152,
      "step": 63
    },
    {
      "epoch": 0.0657421674370827,
      "grad_norm": 1.7758578062057495,
      "learning_rate": 8.561643835616439e-07,
      "loss": 2.5031,
      "step": 64
    },
    {
      "epoch": 0.0667693888032871,
      "grad_norm": 1.9316363334655762,
      "learning_rate": 8.732876712328768e-07,
      "loss": 2.3695,
      "step": 65
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 1.7765878438949585,
      "learning_rate": 8.904109589041097e-07,
      "loss": 2.4669,
      "step": 66
    },
    {
      "epoch": 0.06882383153569595,
      "grad_norm": 1.7339810132980347,
      "learning_rate": 9.075342465753426e-07,
      "loss": 2.4112,
      "step": 67
    },
    {
      "epoch": 0.06985105290190036,
      "grad_norm": 1.717781662940979,
      "learning_rate": 9.246575342465753e-07,
      "loss": 2.4677,
      "step": 68
    },
    {
      "epoch": 0.07087827426810478,
      "grad_norm": 1.7711046934127808,
      "learning_rate": 9.417808219178083e-07,
      "loss": 2.4131,
      "step": 69
    },
    {
      "epoch": 0.07190549563430919,
      "grad_norm": 1.708680510520935,
      "learning_rate": 9.589041095890411e-07,
      "loss": 2.5191,
      "step": 70
    },
    {
      "epoch": 0.07190549563430919,
      "eval_loss": 2.4920735359191895,
      "eval_runtime": 37.3501,
      "eval_samples_per_second": 26.774,
      "eval_steps_per_second": 1.124,
      "step": 70
    },
    {
      "epoch": 0.07293271700051361,
      "grad_norm": 1.9429680109024048,
      "learning_rate": 9.76027397260274e-07,
      "loss": 2.4099,
      "step": 71
    },
    {
      "epoch": 0.07395993836671803,
      "grad_norm": 1.7411247491836548,
      "learning_rate": 9.931506849315068e-07,
      "loss": 2.3632,
      "step": 72
    },
    {
      "epoch": 0.07498715973292244,
      "grad_norm": 1.7577983140945435,
      "learning_rate": 1.0102739726027399e-06,
      "loss": 2.4214,
      "step": 73
    },
    {
      "epoch": 0.07601438109912687,
      "grad_norm": 2.025926351547241,
      "learning_rate": 1.0273972602739727e-06,
      "loss": 2.394,
      "step": 74
    },
    {
      "epoch": 0.07704160246533127,
      "grad_norm": 2.4366860389709473,
      "learning_rate": 1.0445205479452056e-06,
      "loss": 2.3943,
      "step": 75
    },
    {
      "epoch": 0.0780688238315357,
      "grad_norm": 2.437108278274536,
      "learning_rate": 1.0616438356164384e-06,
      "loss": 2.3844,
      "step": 76
    },
    {
      "epoch": 0.07909604519774012,
      "grad_norm": 2.1352434158325195,
      "learning_rate": 1.0787671232876712e-06,
      "loss": 2.3871,
      "step": 77
    },
    {
      "epoch": 0.08012326656394453,
      "grad_norm": 1.8895397186279297,
      "learning_rate": 1.095890410958904e-06,
      "loss": 2.3927,
      "step": 78
    },
    {
      "epoch": 0.08115048793014895,
      "grad_norm": 2.2960093021392822,
      "learning_rate": 1.1130136986301371e-06,
      "loss": 2.3343,
      "step": 79
    },
    {
      "epoch": 0.08217770929635336,
      "grad_norm": 2.0891849994659424,
      "learning_rate": 1.13013698630137e-06,
      "loss": 2.3732,
      "step": 80
    },
    {
      "epoch": 0.08217770929635336,
      "eval_loss": 2.4189229011535645,
      "eval_runtime": 37.3645,
      "eval_samples_per_second": 26.763,
      "eval_steps_per_second": 1.124,
      "step": 80
    },
    {
      "epoch": 0.08320493066255778,
      "grad_norm": 2.450587034225464,
      "learning_rate": 1.1472602739726028e-06,
      "loss": 2.3163,
      "step": 81
    },
    {
      "epoch": 0.08423215202876219,
      "grad_norm": 2.079949378967285,
      "learning_rate": 1.1643835616438357e-06,
      "loss": 2.3381,
      "step": 82
    },
    {
      "epoch": 0.08525937339496661,
      "grad_norm": 2.160737991333008,
      "learning_rate": 1.1815068493150685e-06,
      "loss": 2.3376,
      "step": 83
    },
    {
      "epoch": 0.08628659476117104,
      "grad_norm": 2.463890552520752,
      "learning_rate": 1.1986301369863014e-06,
      "loss": 2.308,
      "step": 84
    },
    {
      "epoch": 0.08731381612737545,
      "grad_norm": 2.3923065662384033,
      "learning_rate": 1.2157534246575344e-06,
      "loss": 2.2682,
      "step": 85
    },
    {
      "epoch": 0.08834103749357987,
      "grad_norm": 2.2096004486083984,
      "learning_rate": 1.2328767123287673e-06,
      "loss": 2.3256,
      "step": 86
    },
    {
      "epoch": 0.08936825885978428,
      "grad_norm": 2.1402556896209717,
      "learning_rate": 1.25e-06,
      "loss": 2.2767,
      "step": 87
    },
    {
      "epoch": 0.0903954802259887,
      "grad_norm": 2.500629186630249,
      "learning_rate": 1.267123287671233e-06,
      "loss": 2.2576,
      "step": 88
    },
    {
      "epoch": 0.09142270159219312,
      "grad_norm": 2.0257675647735596,
      "learning_rate": 1.284246575342466e-06,
      "loss": 2.2722,
      "step": 89
    },
    {
      "epoch": 0.09244992295839753,
      "grad_norm": 2.148428440093994,
      "learning_rate": 1.3013698630136986e-06,
      "loss": 2.2309,
      "step": 90
    },
    {
      "epoch": 0.09244992295839753,
      "eval_loss": 2.3439993858337402,
      "eval_runtime": 37.3803,
      "eval_samples_per_second": 26.752,
      "eval_steps_per_second": 1.124,
      "step": 90
    },
    {
      "epoch": 0.09347714432460195,
      "grad_norm": 2.3541946411132812,
      "learning_rate": 1.3184931506849317e-06,
      "loss": 2.2347,
      "step": 91
    },
    {
      "epoch": 0.09450436569080636,
      "grad_norm": 2.6239383220672607,
      "learning_rate": 1.3356164383561645e-06,
      "loss": 2.2589,
      "step": 92
    },
    {
      "epoch": 0.09553158705701079,
      "grad_norm": 2.1981804370880127,
      "learning_rate": 1.3527397260273976e-06,
      "loss": 2.2372,
      "step": 93
    },
    {
      "epoch": 0.09655880842321521,
      "grad_norm": 2.3652358055114746,
      "learning_rate": 1.3698630136986302e-06,
      "loss": 2.2169,
      "step": 94
    },
    {
      "epoch": 0.09758602978941962,
      "grad_norm": 2.2078158855438232,
      "learning_rate": 1.386986301369863e-06,
      "loss": 2.2761,
      "step": 95
    },
    {
      "epoch": 0.09861325115562404,
      "grad_norm": 2.494685649871826,
      "learning_rate": 1.4041095890410961e-06,
      "loss": 2.1691,
      "step": 96
    },
    {
      "epoch": 0.09964047252182845,
      "grad_norm": 2.3293051719665527,
      "learning_rate": 1.421232876712329e-06,
      "loss": 2.2246,
      "step": 97
    },
    {
      "epoch": 0.10066769388803287,
      "grad_norm": 2.410687208175659,
      "learning_rate": 1.4383561643835616e-06,
      "loss": 2.1166,
      "step": 98
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 2.5168960094451904,
      "learning_rate": 1.4554794520547946e-06,
      "loss": 2.1417,
      "step": 99
    },
    {
      "epoch": 0.1027221366204417,
      "grad_norm": 2.178412914276123,
      "learning_rate": 1.4726027397260275e-06,
      "loss": 2.1638,
      "step": 100
    },
    {
      "epoch": 0.1027221366204417,
      "eval_loss": 2.273622751235962,
      "eval_runtime": 37.3892,
      "eval_samples_per_second": 26.746,
      "eval_steps_per_second": 1.123,
      "step": 100
    },
    {
      "epoch": 0.10374935798664613,
      "grad_norm": 2.8951706886291504,
      "learning_rate": 1.4897260273972605e-06,
      "loss": 2.1631,
      "step": 101
    },
    {
      "epoch": 0.10477657935285054,
      "grad_norm": 2.103206157684326,
      "learning_rate": 1.5068493150684932e-06,
      "loss": 2.1419,
      "step": 102
    },
    {
      "epoch": 0.10580380071905496,
      "grad_norm": 2.495969772338867,
      "learning_rate": 1.5239726027397262e-06,
      "loss": 2.1029,
      "step": 103
    },
    {
      "epoch": 0.10683102208525937,
      "grad_norm": 2.5686826705932617,
      "learning_rate": 1.541095890410959e-06,
      "loss": 2.1235,
      "step": 104
    },
    {
      "epoch": 0.10785824345146379,
      "grad_norm": 3.4710471630096436,
      "learning_rate": 1.5582191780821921e-06,
      "loss": 2.1832,
      "step": 105
    },
    {
      "epoch": 0.10888546481766821,
      "grad_norm": 2.2563316822052,
      "learning_rate": 1.5753424657534248e-06,
      "loss": 2.1441,
      "step": 106
    },
    {
      "epoch": 0.10991268618387262,
      "grad_norm": 3.860506534576416,
      "learning_rate": 1.5924657534246576e-06,
      "loss": 2.1764,
      "step": 107
    },
    {
      "epoch": 0.11093990755007704,
      "grad_norm": 2.550135850906372,
      "learning_rate": 1.6095890410958907e-06,
      "loss": 2.1455,
      "step": 108
    },
    {
      "epoch": 0.11196712891628145,
      "grad_norm": 3.168283700942993,
      "learning_rate": 1.6267123287671235e-06,
      "loss": 2.0246,
      "step": 109
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 2.577069044113159,
      "learning_rate": 1.6438356164383561e-06,
      "loss": 2.0921,
      "step": 110
    },
    {
      "epoch": 0.11299435028248588,
      "eval_loss": 2.2218997478485107,
      "eval_runtime": 37.246,
      "eval_samples_per_second": 26.849,
      "eval_steps_per_second": 1.128,
      "step": 110
    },
    {
      "epoch": 0.1140215716486903,
      "grad_norm": 2.3515374660491943,
      "learning_rate": 1.6609589041095892e-06,
      "loss": 2.0209,
      "step": 111
    },
    {
      "epoch": 0.1150487930148947,
      "grad_norm": 2.7660279273986816,
      "learning_rate": 1.678082191780822e-06,
      "loss": 2.1165,
      "step": 112
    },
    {
      "epoch": 0.11607601438109913,
      "grad_norm": 2.567336082458496,
      "learning_rate": 1.695205479452055e-06,
      "loss": 2.0529,
      "step": 113
    },
    {
      "epoch": 0.11710323574730354,
      "grad_norm": 2.4126152992248535,
      "learning_rate": 1.7123287671232877e-06,
      "loss": 2.1028,
      "step": 114
    },
    {
      "epoch": 0.11813045711350796,
      "grad_norm": 3.577528476715088,
      "learning_rate": 1.7294520547945206e-06,
      "loss": 2.0317,
      "step": 115
    },
    {
      "epoch": 0.11915767847971238,
      "grad_norm": 2.9624195098876953,
      "learning_rate": 1.7465753424657536e-06,
      "loss": 2.1318,
      "step": 116
    },
    {
      "epoch": 0.12018489984591679,
      "grad_norm": 2.789854049682617,
      "learning_rate": 1.7636986301369865e-06,
      "loss": 2.0822,
      "step": 117
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.8168365955352783,
      "learning_rate": 1.7808219178082193e-06,
      "loss": 2.08,
      "step": 118
    },
    {
      "epoch": 0.12223934257832562,
      "grad_norm": 2.7616257667541504,
      "learning_rate": 1.7979452054794521e-06,
      "loss": 2.0668,
      "step": 119
    },
    {
      "epoch": 0.12326656394453005,
      "grad_norm": 2.5610315799713135,
      "learning_rate": 1.8150684931506852e-06,
      "loss": 2.1518,
      "step": 120
    },
    {
      "epoch": 0.12326656394453005,
      "eval_loss": 2.184033155441284,
      "eval_runtime": 37.3784,
      "eval_samples_per_second": 26.753,
      "eval_steps_per_second": 1.124,
      "step": 120
    },
    {
      "epoch": 0.12429378531073447,
      "grad_norm": 2.817063093185425,
      "learning_rate": 1.832191780821918e-06,
      "loss": 2.0813,
      "step": 121
    },
    {
      "epoch": 0.12532100667693888,
      "grad_norm": 2.987205982208252,
      "learning_rate": 1.8493150684931507e-06,
      "loss": 2.0421,
      "step": 122
    },
    {
      "epoch": 0.1263482280431433,
      "grad_norm": 2.8480496406555176,
      "learning_rate": 1.8664383561643837e-06,
      "loss": 2.0018,
      "step": 123
    },
    {
      "epoch": 0.12737544940934772,
      "grad_norm": 2.994274616241455,
      "learning_rate": 1.8835616438356166e-06,
      "loss": 2.0266,
      "step": 124
    },
    {
      "epoch": 0.12840267077555212,
      "grad_norm": 2.64136004447937,
      "learning_rate": 1.9006849315068496e-06,
      "loss": 1.9873,
      "step": 125
    },
    {
      "epoch": 0.12942989214175654,
      "grad_norm": 2.9426915645599365,
      "learning_rate": 1.9178082191780823e-06,
      "loss": 2.0566,
      "step": 126
    },
    {
      "epoch": 0.13045711350796096,
      "grad_norm": 2.9018619060516357,
      "learning_rate": 1.9349315068493153e-06,
      "loss": 1.9674,
      "step": 127
    },
    {
      "epoch": 0.1314843348741654,
      "grad_norm": 3.6921045780181885,
      "learning_rate": 1.952054794520548e-06,
      "loss": 2.0295,
      "step": 128
    },
    {
      "epoch": 0.1325115562403698,
      "grad_norm": 2.4194657802581787,
      "learning_rate": 1.969178082191781e-06,
      "loss": 2.0639,
      "step": 129
    },
    {
      "epoch": 0.1335387776065742,
      "grad_norm": 3.252349615097046,
      "learning_rate": 1.9863013698630136e-06,
      "loss": 2.0613,
      "step": 130
    },
    {
      "epoch": 0.1335387776065742,
      "eval_loss": 2.153157949447632,
      "eval_runtime": 37.394,
      "eval_samples_per_second": 26.742,
      "eval_steps_per_second": 1.123,
      "step": 130
    },
    {
      "epoch": 0.13456599897277863,
      "grad_norm": 2.9361023902893066,
      "learning_rate": 2.0034246575342467e-06,
      "loss": 1.9817,
      "step": 131
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 2.834803581237793,
      "learning_rate": 2.0205479452054797e-06,
      "loss": 2.0539,
      "step": 132
    },
    {
      "epoch": 0.13662044170518747,
      "grad_norm": 2.8814785480499268,
      "learning_rate": 2.037671232876713e-06,
      "loss": 2.0296,
      "step": 133
    },
    {
      "epoch": 0.1376476630713919,
      "grad_norm": 2.647125482559204,
      "learning_rate": 2.0547945205479454e-06,
      "loss": 1.9739,
      "step": 134
    },
    {
      "epoch": 0.1386748844375963,
      "grad_norm": 2.9608750343322754,
      "learning_rate": 2.071917808219178e-06,
      "loss": 2.0083,
      "step": 135
    },
    {
      "epoch": 0.1397021058038007,
      "grad_norm": 2.8570032119750977,
      "learning_rate": 2.089041095890411e-06,
      "loss": 2.0216,
      "step": 136
    },
    {
      "epoch": 0.14072932717000514,
      "grad_norm": 2.806358575820923,
      "learning_rate": 2.106164383561644e-06,
      "loss": 1.9457,
      "step": 137
    },
    {
      "epoch": 0.14175654853620956,
      "grad_norm": 3.1003353595733643,
      "learning_rate": 2.123287671232877e-06,
      "loss": 2.0324,
      "step": 138
    },
    {
      "epoch": 0.14278376990241398,
      "grad_norm": 2.679588556289673,
      "learning_rate": 2.14041095890411e-06,
      "loss": 1.9699,
      "step": 139
    },
    {
      "epoch": 0.14381099126861838,
      "grad_norm": 2.9436194896698,
      "learning_rate": 2.1575342465753425e-06,
      "loss": 1.9824,
      "step": 140
    },
    {
      "epoch": 0.14381099126861838,
      "eval_loss": 2.123953104019165,
      "eval_runtime": 37.4214,
      "eval_samples_per_second": 26.723,
      "eval_steps_per_second": 1.122,
      "step": 140
    },
    {
      "epoch": 0.1448382126348228,
      "grad_norm": 3.088301420211792,
      "learning_rate": 2.1746575342465755e-06,
      "loss": 1.9861,
      "step": 141
    },
    {
      "epoch": 0.14586543400102722,
      "grad_norm": 3.011859178543091,
      "learning_rate": 2.191780821917808e-06,
      "loss": 1.9383,
      "step": 142
    },
    {
      "epoch": 0.14689265536723164,
      "grad_norm": 2.930264472961426,
      "learning_rate": 2.2089041095890412e-06,
      "loss": 2.0674,
      "step": 143
    },
    {
      "epoch": 0.14791987673343607,
      "grad_norm": 3.361328601837158,
      "learning_rate": 2.2260273972602743e-06,
      "loss": 1.9495,
      "step": 144
    },
    {
      "epoch": 0.14894709809964046,
      "grad_norm": 2.7825112342834473,
      "learning_rate": 2.243150684931507e-06,
      "loss": 1.9335,
      "step": 145
    },
    {
      "epoch": 0.14997431946584489,
      "grad_norm": 3.7215847969055176,
      "learning_rate": 2.26027397260274e-06,
      "loss": 1.9403,
      "step": 146
    },
    {
      "epoch": 0.1510015408320493,
      "grad_norm": 2.5125460624694824,
      "learning_rate": 2.2773972602739726e-06,
      "loss": 1.9437,
      "step": 147
    },
    {
      "epoch": 0.15202876219825373,
      "grad_norm": 3.0963492393493652,
      "learning_rate": 2.2945205479452057e-06,
      "loss": 1.9651,
      "step": 148
    },
    {
      "epoch": 0.15305598356445815,
      "grad_norm": 2.9147121906280518,
      "learning_rate": 2.3116438356164387e-06,
      "loss": 2.0567,
      "step": 149
    },
    {
      "epoch": 0.15408320493066255,
      "grad_norm": 3.5275802612304688,
      "learning_rate": 2.3287671232876713e-06,
      "loss": 1.9773,
      "step": 150
    },
    {
      "epoch": 0.15408320493066255,
      "eval_loss": 2.112344264984131,
      "eval_runtime": 37.4142,
      "eval_samples_per_second": 26.728,
      "eval_steps_per_second": 1.123,
      "step": 150
    },
    {
      "epoch": 0.15511042629686697,
      "grad_norm": 3.013786554336548,
      "learning_rate": 2.3458904109589044e-06,
      "loss": 1.8753,
      "step": 151
    },
    {
      "epoch": 0.1561376476630714,
      "grad_norm": 3.433615207672119,
      "learning_rate": 2.363013698630137e-06,
      "loss": 1.9256,
      "step": 152
    },
    {
      "epoch": 0.15716486902927582,
      "grad_norm": 3.1526033878326416,
      "learning_rate": 2.38013698630137e-06,
      "loss": 1.9815,
      "step": 153
    },
    {
      "epoch": 0.15819209039548024,
      "grad_norm": 3.2099974155426025,
      "learning_rate": 2.3972602739726027e-06,
      "loss": 1.9628,
      "step": 154
    },
    {
      "epoch": 0.15921931176168463,
      "grad_norm": 3.2713584899902344,
      "learning_rate": 2.4143835616438358e-06,
      "loss": 1.9128,
      "step": 155
    },
    {
      "epoch": 0.16024653312788906,
      "grad_norm": 3.287649393081665,
      "learning_rate": 2.431506849315069e-06,
      "loss": 1.8764,
      "step": 156
    },
    {
      "epoch": 0.16127375449409348,
      "grad_norm": 3.1439101696014404,
      "learning_rate": 2.4486301369863015e-06,
      "loss": 1.9428,
      "step": 157
    },
    {
      "epoch": 0.1623009758602979,
      "grad_norm": 3.006457805633545,
      "learning_rate": 2.4657534246575345e-06,
      "loss": 1.9516,
      "step": 158
    },
    {
      "epoch": 0.1633281972265023,
      "grad_norm": 2.9567787647247314,
      "learning_rate": 2.482876712328767e-06,
      "loss": 1.915,
      "step": 159
    },
    {
      "epoch": 0.16435541859270672,
      "grad_norm": 3.2475216388702393,
      "learning_rate": 2.5e-06,
      "loss": 1.9451,
      "step": 160
    },
    {
      "epoch": 0.16435541859270672,
      "eval_loss": 2.086299419403076,
      "eval_runtime": 37.3939,
      "eval_samples_per_second": 26.742,
      "eval_steps_per_second": 1.123,
      "step": 160
    },
    {
      "epoch": 0.16538263995891114,
      "grad_norm": 2.9586498737335205,
      "learning_rate": 2.5171232876712333e-06,
      "loss": 1.9298,
      "step": 161
    },
    {
      "epoch": 0.16640986132511557,
      "grad_norm": 3.066910982131958,
      "learning_rate": 2.534246575342466e-06,
      "loss": 1.9103,
      "step": 162
    },
    {
      "epoch": 0.16743708269132,
      "grad_norm": 2.814741611480713,
      "learning_rate": 2.551369863013699e-06,
      "loss": 1.8678,
      "step": 163
    },
    {
      "epoch": 0.16846430405752438,
      "grad_norm": 3.7239339351654053,
      "learning_rate": 2.568493150684932e-06,
      "loss": 1.9321,
      "step": 164
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 2.829899787902832,
      "learning_rate": 2.585616438356164e-06,
      "loss": 1.9587,
      "step": 165
    },
    {
      "epoch": 0.17051874678993323,
      "grad_norm": 3.826289176940918,
      "learning_rate": 2.6027397260273973e-06,
      "loss": 1.9288,
      "step": 166
    },
    {
      "epoch": 0.17154596815613765,
      "grad_norm": 3.1028499603271484,
      "learning_rate": 2.6198630136986303e-06,
      "loss": 1.8685,
      "step": 167
    },
    {
      "epoch": 0.17257318952234207,
      "grad_norm": 3.6923508644104004,
      "learning_rate": 2.6369863013698634e-06,
      "loss": 1.9276,
      "step": 168
    },
    {
      "epoch": 0.17360041088854647,
      "grad_norm": 3.0577642917633057,
      "learning_rate": 2.654109589041096e-06,
      "loss": 1.9653,
      "step": 169
    },
    {
      "epoch": 0.1746276322547509,
      "grad_norm": 3.363762617111206,
      "learning_rate": 2.671232876712329e-06,
      "loss": 1.9465,
      "step": 170
    },
    {
      "epoch": 0.1746276322547509,
      "eval_loss": 2.0753531455993652,
      "eval_runtime": 37.3955,
      "eval_samples_per_second": 26.741,
      "eval_steps_per_second": 1.123,
      "step": 170
    },
    {
      "epoch": 0.17565485362095531,
      "grad_norm": 2.9063165187835693,
      "learning_rate": 2.688356164383562e-06,
      "loss": 1.8827,
      "step": 171
    },
    {
      "epoch": 0.17668207498715974,
      "grad_norm": 3.4709181785583496,
      "learning_rate": 2.705479452054795e-06,
      "loss": 1.882,
      "step": 172
    },
    {
      "epoch": 0.17770929635336416,
      "grad_norm": 3.395397663116455,
      "learning_rate": 2.7226027397260274e-06,
      "loss": 1.8711,
      "step": 173
    },
    {
      "epoch": 0.17873651771956856,
      "grad_norm": 3.9973363876342773,
      "learning_rate": 2.7397260273972604e-06,
      "loss": 1.8223,
      "step": 174
    },
    {
      "epoch": 0.17976373908577298,
      "grad_norm": 3.1841156482696533,
      "learning_rate": 2.7568493150684935e-06,
      "loss": 1.947,
      "step": 175
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 3.1841156482696533,
      "learning_rate": 2.7568493150684935e-06,
      "loss": 1.9192,
      "step": 176
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.84712290763855,
      "learning_rate": 2.773972602739726e-06,
      "loss": 1.8344,
      "step": 177
    },
    {
      "epoch": 0.18284540318438625,
      "grad_norm": 3.487525463104248,
      "learning_rate": 2.791095890410959e-06,
      "loss": 1.9242,
      "step": 178
    },
    {
      "epoch": 0.18387262455059064,
      "grad_norm": 3.1980319023132324,
      "learning_rate": 2.8082191780821922e-06,
      "loss": 1.7959,
      "step": 179
    },
    {
      "epoch": 0.18489984591679506,
      "grad_norm": 3.56462025642395,
      "learning_rate": 2.8253424657534253e-06,
      "loss": 1.9668,
      "step": 180
    },
    {
      "epoch": 0.18489984591679506,
      "eval_loss": 2.0606908798217773,
      "eval_runtime": 37.3994,
      "eval_samples_per_second": 26.738,
      "eval_steps_per_second": 1.123,
      "step": 180
    },
    {
      "epoch": 0.1859270672829995,
      "grad_norm": 3.613842248916626,
      "learning_rate": 2.842465753424658e-06,
      "loss": 1.925,
      "step": 181
    },
    {
      "epoch": 0.1869542886492039,
      "grad_norm": 2.9755642414093018,
      "learning_rate": 2.8595890410958905e-06,
      "loss": 1.9251,
      "step": 182
    },
    {
      "epoch": 0.18798151001540833,
      "grad_norm": 2.9678146839141846,
      "learning_rate": 2.876712328767123e-06,
      "loss": 1.9406,
      "step": 183
    },
    {
      "epoch": 0.18900873138161273,
      "grad_norm": 3.3536393642425537,
      "learning_rate": 2.8938356164383562e-06,
      "loss": 1.8041,
      "step": 184
    },
    {
      "epoch": 0.19003595274781715,
      "grad_norm": 2.714902877807617,
      "learning_rate": 2.9109589041095893e-06,
      "loss": 1.8213,
      "step": 185
    },
    {
      "epoch": 0.19106317411402157,
      "grad_norm": 3.0686237812042236,
      "learning_rate": 2.9280821917808223e-06,
      "loss": 1.817,
      "step": 186
    },
    {
      "epoch": 0.192090395480226,
      "grad_norm": 3.510448932647705,
      "learning_rate": 2.945205479452055e-06,
      "loss": 1.8317,
      "step": 187
    },
    {
      "epoch": 0.19311761684643042,
      "grad_norm": 3.2060787677764893,
      "learning_rate": 2.962328767123288e-06,
      "loss": 1.894,
      "step": 188
    },
    {
      "epoch": 0.1941448382126348,
      "grad_norm": 3.1756906509399414,
      "learning_rate": 2.979452054794521e-06,
      "loss": 1.8788,
      "step": 189
    },
    {
      "epoch": 0.19517205957883924,
      "grad_norm": 3.059863805770874,
      "learning_rate": 2.9965753424657533e-06,
      "loss": 1.8198,
      "step": 190
    },
    {
      "epoch": 0.19517205957883924,
      "eval_loss": 2.0506513118743896,
      "eval_runtime": 37.4014,
      "eval_samples_per_second": 26.737,
      "eval_steps_per_second": 1.123,
      "step": 190
    },
    {
      "epoch": 0.19619928094504366,
      "grad_norm": 3.193685531616211,
      "learning_rate": 3.0136986301369864e-06,
      "loss": 1.8818,
      "step": 191
    },
    {
      "epoch": 0.19722650231124808,
      "grad_norm": 2.905402183532715,
      "learning_rate": 3.0308219178082194e-06,
      "loss": 1.8546,
      "step": 192
    },
    {
      "epoch": 0.1982537236774525,
      "grad_norm": 3.423109531402588,
      "learning_rate": 3.0479452054794525e-06,
      "loss": 1.8142,
      "step": 193
    },
    {
      "epoch": 0.1992809450436569,
      "grad_norm": 3.136094331741333,
      "learning_rate": 3.065068493150685e-06,
      "loss": 1.8553,
      "step": 194
    },
    {
      "epoch": 0.20030816640986132,
      "grad_norm": 3.0746538639068604,
      "learning_rate": 3.082191780821918e-06,
      "loss": 1.8153,
      "step": 195
    },
    {
      "epoch": 0.20133538777606574,
      "grad_norm": 2.9354681968688965,
      "learning_rate": 3.099315068493151e-06,
      "loss": 1.8301,
      "step": 196
    },
    {
      "epoch": 0.20236260914227017,
      "grad_norm": 3.00426983833313,
      "learning_rate": 3.1164383561643843e-06,
      "loss": 1.8233,
      "step": 197
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 3.2754054069519043,
      "learning_rate": 3.1335616438356165e-06,
      "loss": 1.787,
      "step": 198
    },
    {
      "epoch": 0.20441705187467898,
      "grad_norm": 2.9854509830474854,
      "learning_rate": 3.1506849315068495e-06,
      "loss": 1.9341,
      "step": 199
    },
    {
      "epoch": 0.2054442732408834,
      "grad_norm": 3.5655088424682617,
      "learning_rate": 3.167808219178082e-06,
      "loss": 1.7964,
      "step": 200
    },
    {
      "epoch": 0.2054442732408834,
      "eval_loss": 2.0440263748168945,
      "eval_runtime": 37.4054,
      "eval_samples_per_second": 26.734,
      "eval_steps_per_second": 1.123,
      "step": 200
    },
    {
      "epoch": 0.20647149460708783,
      "grad_norm": 3.132373571395874,
      "learning_rate": 3.184931506849315e-06,
      "loss": 1.8019,
      "step": 201
    },
    {
      "epoch": 0.20749871597329225,
      "grad_norm": 3.3017780780792236,
      "learning_rate": 3.2020547945205483e-06,
      "loss": 1.7786,
      "step": 202
    },
    {
      "epoch": 0.20852593733949668,
      "grad_norm": 3.009382486343384,
      "learning_rate": 3.2191780821917813e-06,
      "loss": 1.7639,
      "step": 203
    },
    {
      "epoch": 0.20955315870570107,
      "grad_norm": 3.5784854888916016,
      "learning_rate": 3.236301369863014e-06,
      "loss": 1.76,
      "step": 204
    },
    {
      "epoch": 0.2105803800719055,
      "grad_norm": 3.236858367919922,
      "learning_rate": 3.253424657534247e-06,
      "loss": 1.7295,
      "step": 205
    },
    {
      "epoch": 0.21160760143810992,
      "grad_norm": 3.6157479286193848,
      "learning_rate": 3.2705479452054796e-06,
      "loss": 1.8287,
      "step": 206
    },
    {
      "epoch": 0.21263482280431434,
      "grad_norm": 3.51790452003479,
      "learning_rate": 3.2876712328767123e-06,
      "loss": 1.8004,
      "step": 207
    },
    {
      "epoch": 0.21366204417051873,
      "grad_norm": 3.0700764656066895,
      "learning_rate": 3.3047945205479453e-06,
      "loss": 1.7581,
      "step": 208
    },
    {
      "epoch": 0.21468926553672316,
      "grad_norm": 3.2651591300964355,
      "learning_rate": 3.3219178082191784e-06,
      "loss": 1.7724,
      "step": 209
    },
    {
      "epoch": 0.21571648690292758,
      "grad_norm": 2.9267404079437256,
      "learning_rate": 3.3390410958904114e-06,
      "loss": 1.8154,
      "step": 210
    },
    {
      "epoch": 0.21571648690292758,
      "eval_loss": 2.0323731899261475,
      "eval_runtime": 37.2156,
      "eval_samples_per_second": 26.87,
      "eval_steps_per_second": 1.129,
      "step": 210
    },
    {
      "epoch": 0.216743708269132,
      "grad_norm": 3.463411808013916,
      "learning_rate": 3.356164383561644e-06,
      "loss": 1.8309,
      "step": 211
    },
    {
      "epoch": 0.21777092963533642,
      "grad_norm": 3.123573064804077,
      "learning_rate": 3.373287671232877e-06,
      "loss": 1.8793,
      "step": 212
    },
    {
      "epoch": 0.21879815100154082,
      "grad_norm": 3.427051305770874,
      "learning_rate": 3.39041095890411e-06,
      "loss": 1.8259,
      "step": 213
    },
    {
      "epoch": 0.21982537236774524,
      "grad_norm": 3.306366443634033,
      "learning_rate": 3.4075342465753424e-06,
      "loss": 1.8565,
      "step": 214
    },
    {
      "epoch": 0.22085259373394966,
      "grad_norm": 3.557340383529663,
      "learning_rate": 3.4246575342465754e-06,
      "loss": 1.7531,
      "step": 215
    },
    {
      "epoch": 0.2218798151001541,
      "grad_norm": 3.20525860786438,
      "learning_rate": 3.4417808219178085e-06,
      "loss": 1.8032,
      "step": 216
    },
    {
      "epoch": 0.2229070364663585,
      "grad_norm": 3.2657511234283447,
      "learning_rate": 3.458904109589041e-06,
      "loss": 1.8026,
      "step": 217
    },
    {
      "epoch": 0.2239342578325629,
      "grad_norm": 3.1869699954986572,
      "learning_rate": 3.476027397260274e-06,
      "loss": 1.814,
      "step": 218
    },
    {
      "epoch": 0.22496147919876733,
      "grad_norm": 2.661536931991577,
      "learning_rate": 3.4931506849315072e-06,
      "loss": 1.8005,
      "step": 219
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 3.1108739376068115,
      "learning_rate": 3.5102739726027403e-06,
      "loss": 1.8095,
      "step": 220
    },
    {
      "epoch": 0.22598870056497175,
      "eval_loss": 2.015268325805664,
      "eval_runtime": 37.2867,
      "eval_samples_per_second": 26.819,
      "eval_steps_per_second": 1.126,
      "step": 220
    },
    {
      "epoch": 0.22701592193117617,
      "grad_norm": 2.8078837394714355,
      "learning_rate": 3.527397260273973e-06,
      "loss": 1.8016,
      "step": 221
    },
    {
      "epoch": 0.2280431432973806,
      "grad_norm": 3.131399631500244,
      "learning_rate": 3.5445205479452056e-06,
      "loss": 1.7787,
      "step": 222
    },
    {
      "epoch": 0.229070364663585,
      "grad_norm": 3.114422559738159,
      "learning_rate": 3.5616438356164386e-06,
      "loss": 1.7899,
      "step": 223
    },
    {
      "epoch": 0.2300975860297894,
      "grad_norm": 3.040816068649292,
      "learning_rate": 3.5787671232876712e-06,
      "loss": 1.8601,
      "step": 224
    },
    {
      "epoch": 0.23112480739599384,
      "grad_norm": 3.043100357055664,
      "learning_rate": 3.5958904109589043e-06,
      "loss": 1.8244,
      "step": 225
    },
    {
      "epoch": 0.23215202876219826,
      "grad_norm": 3.4232981204986572,
      "learning_rate": 3.6130136986301373e-06,
      "loss": 1.7634,
      "step": 226
    },
    {
      "epoch": 0.23317925012840268,
      "grad_norm": 2.8170571327209473,
      "learning_rate": 3.6301369863013704e-06,
      "loss": 1.7793,
      "step": 227
    },
    {
      "epoch": 0.23420647149460708,
      "grad_norm": 3.9133572578430176,
      "learning_rate": 3.647260273972603e-06,
      "loss": 1.8239,
      "step": 228
    },
    {
      "epoch": 0.2352336928608115,
      "grad_norm": 2.7053382396698,
      "learning_rate": 3.664383561643836e-06,
      "loss": 1.8209,
      "step": 229
    },
    {
      "epoch": 0.23626091422701592,
      "grad_norm": 3.4366891384124756,
      "learning_rate": 3.6815068493150687e-06,
      "loss": 1.7539,
      "step": 230
    },
    {
      "epoch": 0.23626091422701592,
      "eval_loss": 2.0176751613616943,
      "eval_runtime": 37.3064,
      "eval_samples_per_second": 26.805,
      "eval_steps_per_second": 1.126,
      "step": 230
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 2.592280149459839,
      "learning_rate": 3.6986301369863014e-06,
      "loss": 1.7858,
      "step": 231
    },
    {
      "epoch": 0.23831535695942477,
      "grad_norm": 2.8370869159698486,
      "learning_rate": 3.7157534246575344e-06,
      "loss": 1.7414,
      "step": 232
    },
    {
      "epoch": 0.23934257832562916,
      "grad_norm": 3.2120535373687744,
      "learning_rate": 3.7328767123287675e-06,
      "loss": 1.8467,
      "step": 233
    },
    {
      "epoch": 0.24036979969183359,
      "grad_norm": 2.9314255714416504,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.7602,
      "step": 234
    },
    {
      "epoch": 0.241397021058038,
      "grad_norm": 3.056293249130249,
      "learning_rate": 3.767123287671233e-06,
      "loss": 1.7972,
      "step": 235
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 2.5918917655944824,
      "learning_rate": 3.784246575342466e-06,
      "loss": 1.8274,
      "step": 236
    },
    {
      "epoch": 0.24345146379044685,
      "grad_norm": 2.7911906242370605,
      "learning_rate": 3.8013698630136993e-06,
      "loss": 1.753,
      "step": 237
    },
    {
      "epoch": 0.24447868515665125,
      "grad_norm": 2.810612916946411,
      "learning_rate": 3.818493150684932e-06,
      "loss": 1.7822,
      "step": 238
    },
    {
      "epoch": 0.24550590652285567,
      "grad_norm": 2.8863744735717773,
      "learning_rate": 3.8356164383561645e-06,
      "loss": 1.7258,
      "step": 239
    },
    {
      "epoch": 0.2465331278890601,
      "grad_norm": 3.002087116241455,
      "learning_rate": 3.852739726027397e-06,
      "loss": 1.8423,
      "step": 240
    },
    {
      "epoch": 0.2465331278890601,
      "eval_loss": 2.020223617553711,
      "eval_runtime": 37.3197,
      "eval_samples_per_second": 26.796,
      "eval_steps_per_second": 1.125,
      "step": 240
    },
    {
      "epoch": 0.24756034925526452,
      "grad_norm": 2.892317056655884,
      "learning_rate": 3.869863013698631e-06,
      "loss": 1.8181,
      "step": 241
    },
    {
      "epoch": 0.24858757062146894,
      "grad_norm": 2.895620584487915,
      "learning_rate": 3.886986301369863e-06,
      "loss": 1.7538,
      "step": 242
    },
    {
      "epoch": 0.24961479198767333,
      "grad_norm": 3.015660524368286,
      "learning_rate": 3.904109589041096e-06,
      "loss": 1.766,
      "step": 243
    },
    {
      "epoch": 0.25064201335387776,
      "grad_norm": 2.7516112327575684,
      "learning_rate": 3.921232876712329e-06,
      "loss": 1.7324,
      "step": 244
    },
    {
      "epoch": 0.2516692347200822,
      "grad_norm": 2.937777519226074,
      "learning_rate": 3.938356164383562e-06,
      "loss": 1.7468,
      "step": 245
    },
    {
      "epoch": 0.2526964560862866,
      "grad_norm": 3.1706550121307373,
      "learning_rate": 3.9554794520547955e-06,
      "loss": 1.7035,
      "step": 246
    },
    {
      "epoch": 0.253723677452491,
      "grad_norm": 2.7795372009277344,
      "learning_rate": 3.972602739726027e-06,
      "loss": 1.7912,
      "step": 247
    },
    {
      "epoch": 0.25475089881869545,
      "grad_norm": 3.0375940799713135,
      "learning_rate": 3.989726027397261e-06,
      "loss": 1.7208,
      "step": 248
    },
    {
      "epoch": 0.25577812018489987,
      "grad_norm": 2.863913059234619,
      "learning_rate": 4.006849315068493e-06,
      "loss": 1.7891,
      "step": 249
    },
    {
      "epoch": 0.25680534155110424,
      "grad_norm": 3.02720046043396,
      "learning_rate": 4.023972602739726e-06,
      "loss": 1.7864,
      "step": 250
    },
    {
      "epoch": 0.25680534155110424,
      "eval_loss": 1.9981943368911743,
      "eval_runtime": 37.3019,
      "eval_samples_per_second": 26.808,
      "eval_steps_per_second": 1.126,
      "step": 250
    },
    {
      "epoch": 0.25783256291730866,
      "grad_norm": 2.90144681930542,
      "learning_rate": 4.0410958904109595e-06,
      "loss": 1.7508,
      "step": 251
    },
    {
      "epoch": 0.2588597842835131,
      "grad_norm": 2.7670342922210693,
      "learning_rate": 4.058219178082192e-06,
      "loss": 1.7668,
      "step": 252
    },
    {
      "epoch": 0.2598870056497175,
      "grad_norm": 3.0309600830078125,
      "learning_rate": 4.075342465753426e-06,
      "loss": 1.7853,
      "step": 253
    },
    {
      "epoch": 0.26091422701592193,
      "grad_norm": 2.995190143585205,
      "learning_rate": 4.092465753424658e-06,
      "loss": 1.7409,
      "step": 254
    },
    {
      "epoch": 0.26194144838212635,
      "grad_norm": 3.127767324447632,
      "learning_rate": 4.109589041095891e-06,
      "loss": 1.743,
      "step": 255
    },
    {
      "epoch": 0.2629686697483308,
      "grad_norm": 3.7104549407958984,
      "learning_rate": 4.1267123287671235e-06,
      "loss": 1.8149,
      "step": 256
    },
    {
      "epoch": 0.2639958911145352,
      "grad_norm": 3.042569160461426,
      "learning_rate": 4.143835616438356e-06,
      "loss": 1.7544,
      "step": 257
    },
    {
      "epoch": 0.2650231124807396,
      "grad_norm": 2.9337198734283447,
      "learning_rate": 4.16095890410959e-06,
      "loss": 1.823,
      "step": 258
    },
    {
      "epoch": 0.26605033384694404,
      "grad_norm": 3.1853089332580566,
      "learning_rate": 4.178082191780822e-06,
      "loss": 1.8002,
      "step": 259
    },
    {
      "epoch": 0.2670775552131484,
      "grad_norm": 2.9620680809020996,
      "learning_rate": 4.195205479452055e-06,
      "loss": 1.7401,
      "step": 260
    },
    {
      "epoch": 0.2670775552131484,
      "eval_loss": 1.9844669103622437,
      "eval_runtime": 37.3162,
      "eval_samples_per_second": 26.798,
      "eval_steps_per_second": 1.126,
      "step": 260
    },
    {
      "epoch": 0.26810477657935283,
      "grad_norm": 3.477985382080078,
      "learning_rate": 4.212328767123288e-06,
      "loss": 1.7456,
      "step": 261
    },
    {
      "epoch": 0.26913199794555726,
      "grad_norm": 2.881277084350586,
      "learning_rate": 4.229452054794521e-06,
      "loss": 1.7427,
      "step": 262
    },
    {
      "epoch": 0.2701592193117617,
      "grad_norm": 3.3313355445861816,
      "learning_rate": 4.246575342465754e-06,
      "loss": 1.7537,
      "step": 263
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 2.947119951248169,
      "learning_rate": 4.263698630136986e-06,
      "loss": 1.7349,
      "step": 264
    },
    {
      "epoch": 0.2722136620441705,
      "grad_norm": 3.0780889987945557,
      "learning_rate": 4.28082191780822e-06,
      "loss": 1.694,
      "step": 265
    },
    {
      "epoch": 0.27324088341037495,
      "grad_norm": 3.3371143341064453,
      "learning_rate": 4.297945205479452e-06,
      "loss": 1.8489,
      "step": 266
    },
    {
      "epoch": 0.27426810477657937,
      "grad_norm": 3.01694917678833,
      "learning_rate": 4.315068493150685e-06,
      "loss": 1.7478,
      "step": 267
    },
    {
      "epoch": 0.2752953261427838,
      "grad_norm": 3.001850128173828,
      "learning_rate": 4.3321917808219185e-06,
      "loss": 1.7298,
      "step": 268
    },
    {
      "epoch": 0.2763225475089882,
      "grad_norm": 2.9096696376800537,
      "learning_rate": 4.349315068493151e-06,
      "loss": 1.7542,
      "step": 269
    },
    {
      "epoch": 0.2773497688751926,
      "grad_norm": 3.209601402282715,
      "learning_rate": 4.3664383561643846e-06,
      "loss": 1.7248,
      "step": 270
    },
    {
      "epoch": 0.2773497688751926,
      "eval_loss": 1.9732507467269897,
      "eval_runtime": 37.3151,
      "eval_samples_per_second": 26.799,
      "eval_steps_per_second": 1.126,
      "step": 270
    },
    {
      "epoch": 0.278376990241397,
      "grad_norm": 2.9635558128356934,
      "learning_rate": 4.383561643835616e-06,
      "loss": 1.727,
      "step": 271
    },
    {
      "epoch": 0.2794042116076014,
      "grad_norm": 3.143821954727173,
      "learning_rate": 4.40068493150685e-06,
      "loss": 1.8045,
      "step": 272
    },
    {
      "epoch": 0.28043143297380585,
      "grad_norm": 3.4248714447021484,
      "learning_rate": 4.4178082191780825e-06,
      "loss": 1.7649,
      "step": 273
    },
    {
      "epoch": 0.2814586543400103,
      "grad_norm": 2.902162790298462,
      "learning_rate": 4.434931506849315e-06,
      "loss": 1.7324,
      "step": 274
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 2.8899712562561035,
      "learning_rate": 4.4520547945205486e-06,
      "loss": 1.6886,
      "step": 275
    },
    {
      "epoch": 0.2835130970724191,
      "grad_norm": 3.2267258167266846,
      "learning_rate": 4.469178082191781e-06,
      "loss": 1.7442,
      "step": 276
    },
    {
      "epoch": 0.28454031843862354,
      "grad_norm": 3.275735378265381,
      "learning_rate": 4.486301369863014e-06,
      "loss": 1.7334,
      "step": 277
    },
    {
      "epoch": 0.28556753980482796,
      "grad_norm": 2.991509199142456,
      "learning_rate": 4.503424657534247e-06,
      "loss": 1.7853,
      "step": 278
    },
    {
      "epoch": 0.28659476117103233,
      "grad_norm": 2.8380391597747803,
      "learning_rate": 4.52054794520548e-06,
      "loss": 1.6885,
      "step": 279
    },
    {
      "epoch": 0.28762198253723675,
      "grad_norm": 2.909980297088623,
      "learning_rate": 4.537671232876713e-06,
      "loss": 1.7146,
      "step": 280
    },
    {
      "epoch": 0.28762198253723675,
      "eval_loss": 1.9755980968475342,
      "eval_runtime": 37.3524,
      "eval_samples_per_second": 26.772,
      "eval_steps_per_second": 1.124,
      "step": 280
    },
    {
      "epoch": 0.2886492039034412,
      "grad_norm": 3.2689175605773926,
      "learning_rate": 4.554794520547945e-06,
      "loss": 1.7747,
      "step": 281
    },
    {
      "epoch": 0.2896764252696456,
      "grad_norm": 2.8242290019989014,
      "learning_rate": 4.571917808219179e-06,
      "loss": 1.7657,
      "step": 282
    },
    {
      "epoch": 0.29070364663585,
      "grad_norm": 3.03828501701355,
      "learning_rate": 4.589041095890411e-06,
      "loss": 1.7555,
      "step": 283
    },
    {
      "epoch": 0.29173086800205444,
      "grad_norm": 2.714351177215576,
      "learning_rate": 4.606164383561644e-06,
      "loss": 1.7055,
      "step": 284
    },
    {
      "epoch": 0.29275808936825887,
      "grad_norm": 2.9540348052978516,
      "learning_rate": 4.6232876712328774e-06,
      "loss": 1.7258,
      "step": 285
    },
    {
      "epoch": 0.2937853107344633,
      "grad_norm": 3.107060670852661,
      "learning_rate": 4.64041095890411e-06,
      "loss": 1.7376,
      "step": 286
    },
    {
      "epoch": 0.2948125321006677,
      "grad_norm": 3.3266639709472656,
      "learning_rate": 4.657534246575343e-06,
      "loss": 1.7063,
      "step": 287
    },
    {
      "epoch": 0.29583975346687214,
      "grad_norm": 3.3113174438476562,
      "learning_rate": 4.674657534246575e-06,
      "loss": 1.7514,
      "step": 288
    },
    {
      "epoch": 0.2968669748330765,
      "grad_norm": 3.313321352005005,
      "learning_rate": 4.691780821917809e-06,
      "loss": 1.73,
      "step": 289
    },
    {
      "epoch": 0.2978941961992809,
      "grad_norm": 2.901522159576416,
      "learning_rate": 4.7089041095890414e-06,
      "loss": 1.7709,
      "step": 290
    },
    {
      "epoch": 0.2978941961992809,
      "eval_loss": 1.9608837366104126,
      "eval_runtime": 37.3687,
      "eval_samples_per_second": 26.76,
      "eval_steps_per_second": 1.124,
      "step": 290
    },
    {
      "epoch": 0.29892141756548535,
      "grad_norm": 3.4208264350891113,
      "learning_rate": 4.726027397260274e-06,
      "loss": 1.73,
      "step": 291
    },
    {
      "epoch": 0.29994863893168977,
      "grad_norm": 2.8982441425323486,
      "learning_rate": 4.7431506849315075e-06,
      "loss": 1.7416,
      "step": 292
    },
    {
      "epoch": 0.3009758602978942,
      "grad_norm": 3.2743732929229736,
      "learning_rate": 4.76027397260274e-06,
      "loss": 1.7443,
      "step": 293
    },
    {
      "epoch": 0.3020030816640986,
      "grad_norm": 3.028764486312866,
      "learning_rate": 4.777397260273973e-06,
      "loss": 1.6879,
      "step": 294
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 3.3531785011291504,
      "learning_rate": 4.7945205479452054e-06,
      "loss": 1.7096,
      "step": 295
    },
    {
      "epoch": 0.30405752439650746,
      "grad_norm": 2.5602540969848633,
      "learning_rate": 4.811643835616439e-06,
      "loss": 1.7125,
      "step": 296
    },
    {
      "epoch": 0.3050847457627119,
      "grad_norm": 3.1823129653930664,
      "learning_rate": 4.8287671232876716e-06,
      "loss": 1.6531,
      "step": 297
    },
    {
      "epoch": 0.3061119671289163,
      "grad_norm": 2.6700282096862793,
      "learning_rate": 4.845890410958904e-06,
      "loss": 1.6983,
      "step": 298
    },
    {
      "epoch": 0.3071391884951207,
      "grad_norm": 2.7118732929229736,
      "learning_rate": 4.863013698630138e-06,
      "loss": 1.7056,
      "step": 299
    },
    {
      "epoch": 0.3081664098613251,
      "grad_norm": 3.3493311405181885,
      "learning_rate": 4.88013698630137e-06,
      "loss": 1.6944,
      "step": 300
    },
    {
      "epoch": 0.3081664098613251,
      "eval_loss": 1.9489911794662476,
      "eval_runtime": 37.35,
      "eval_samples_per_second": 26.774,
      "eval_steps_per_second": 1.124,
      "step": 300
    },
    {
      "epoch": 0.3091936312275295,
      "grad_norm": 2.9436538219451904,
      "learning_rate": 4.897260273972603e-06,
      "loss": 1.6717,
      "step": 301
    },
    {
      "epoch": 0.31022085259373394,
      "grad_norm": 2.894737482070923,
      "learning_rate": 4.914383561643836e-06,
      "loss": 1.7895,
      "step": 302
    },
    {
      "epoch": 0.31124807395993837,
      "grad_norm": 2.8645665645599365,
      "learning_rate": 4.931506849315069e-06,
      "loss": 1.721,
      "step": 303
    },
    {
      "epoch": 0.3122752953261428,
      "grad_norm": 3.050203323364258,
      "learning_rate": 4.948630136986302e-06,
      "loss": 1.7564,
      "step": 304
    },
    {
      "epoch": 0.3133025166923472,
      "grad_norm": 3.146395206451416,
      "learning_rate": 4.965753424657534e-06,
      "loss": 1.7938,
      "step": 305
    },
    {
      "epoch": 0.31432973805855163,
      "grad_norm": 3.1021251678466797,
      "learning_rate": 4.982876712328768e-06,
      "loss": 1.6682,
      "step": 306
    },
    {
      "epoch": 0.31535695942475606,
      "grad_norm": 2.7301125526428223,
      "learning_rate": 5e-06,
      "loss": 1.6974,
      "step": 307
    },
    {
      "epoch": 0.3163841807909605,
      "grad_norm": 2.7602250576019287,
      "learning_rate": 4.998096688237534e-06,
      "loss": 1.6523,
      "step": 308
    },
    {
      "epoch": 0.31741140215716485,
      "grad_norm": 2.8149876594543457,
      "learning_rate": 4.996193376475067e-06,
      "loss": 1.7535,
      "step": 309
    },
    {
      "epoch": 0.31843862352336927,
      "grad_norm": 2.54823637008667,
      "learning_rate": 4.9942900647126005e-06,
      "loss": 1.63,
      "step": 310
    },
    {
      "epoch": 0.31843862352336927,
      "eval_loss": 1.928893804550171,
      "eval_runtime": 37.2236,
      "eval_samples_per_second": 26.865,
      "eval_steps_per_second": 1.128,
      "step": 310
    },
    {
      "epoch": 0.3194658448895737,
      "grad_norm": 2.7819766998291016,
      "learning_rate": 4.992386752950134e-06,
      "loss": 1.6461,
      "step": 311
    },
    {
      "epoch": 0.3204930662557781,
      "grad_norm": 2.999209403991699,
      "learning_rate": 4.990483441187667e-06,
      "loss": 1.6861,
      "step": 312
    },
    {
      "epoch": 0.32152028762198254,
      "grad_norm": 2.7288851737976074,
      "learning_rate": 4.9885801294252e-06,
      "loss": 1.7076,
      "step": 313
    },
    {
      "epoch": 0.32254750898818696,
      "grad_norm": 2.8722457885742188,
      "learning_rate": 4.986676817662733e-06,
      "loss": 1.7079,
      "step": 314
    },
    {
      "epoch": 0.3235747303543914,
      "grad_norm": 2.853344678878784,
      "learning_rate": 4.9847735059002665e-06,
      "loss": 1.6699,
      "step": 315
    },
    {
      "epoch": 0.3246019517205958,
      "grad_norm": 2.7404720783233643,
      "learning_rate": 4.9828701941378e-06,
      "loss": 1.7423,
      "step": 316
    },
    {
      "epoch": 0.3256291730868002,
      "grad_norm": 2.6062633991241455,
      "learning_rate": 4.980966882375333e-06,
      "loss": 1.6811,
      "step": 317
    },
    {
      "epoch": 0.3266563944530046,
      "grad_norm": 2.834162712097168,
      "learning_rate": 4.979063570612867e-06,
      "loss": 1.6575,
      "step": 318
    },
    {
      "epoch": 0.327683615819209,
      "grad_norm": 2.7741048336029053,
      "learning_rate": 4.9771602588504e-06,
      "loss": 1.6158,
      "step": 319
    },
    {
      "epoch": 0.32871083718541344,
      "grad_norm": 2.6216888427734375,
      "learning_rate": 4.975256947087933e-06,
      "loss": 1.7295,
      "step": 320
    },
    {
      "epoch": 0.32871083718541344,
      "eval_loss": 1.9309543371200562,
      "eval_runtime": 37.3489,
      "eval_samples_per_second": 26.775,
      "eval_steps_per_second": 1.125,
      "step": 320
    },
    {
      "epoch": 0.32973805855161786,
      "grad_norm": 2.6282548904418945,
      "learning_rate": 4.973353635325467e-06,
      "loss": 1.6266,
      "step": 321
    },
    {
      "epoch": 0.3307652799178223,
      "grad_norm": 2.632124662399292,
      "learning_rate": 4.971450323563e-06,
      "loss": 1.6887,
      "step": 322
    },
    {
      "epoch": 0.3317925012840267,
      "grad_norm": 2.5844857692718506,
      "learning_rate": 4.969547011800533e-06,
      "loss": 1.6287,
      "step": 323
    },
    {
      "epoch": 0.33281972265023113,
      "grad_norm": 2.597620964050293,
      "learning_rate": 4.967643700038067e-06,
      "loss": 1.6876,
      "step": 324
    },
    {
      "epoch": 0.33384694401643555,
      "grad_norm": 2.6529343128204346,
      "learning_rate": 4.9657403882756e-06,
      "loss": 1.6883,
      "step": 325
    },
    {
      "epoch": 0.33487416538264,
      "grad_norm": 2.592874526977539,
      "learning_rate": 4.9638370765131335e-06,
      "loss": 1.653,
      "step": 326
    },
    {
      "epoch": 0.3359013867488444,
      "grad_norm": 2.523489236831665,
      "learning_rate": 4.961933764750667e-06,
      "loss": 1.6501,
      "step": 327
    },
    {
      "epoch": 0.33692860811504877,
      "grad_norm": 2.6721699237823486,
      "learning_rate": 4.9600304529882e-06,
      "loss": 1.7126,
      "step": 328
    },
    {
      "epoch": 0.3379558294812532,
      "grad_norm": 2.513122797012329,
      "learning_rate": 4.9581271412257335e-06,
      "loss": 1.7268,
      "step": 329
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 2.571118116378784,
      "learning_rate": 4.956223829463266e-06,
      "loss": 1.6862,
      "step": 330
    },
    {
      "epoch": 0.3389830508474576,
      "eval_loss": 1.9501315355300903,
      "eval_runtime": 37.3287,
      "eval_samples_per_second": 26.789,
      "eval_steps_per_second": 1.125,
      "step": 330
    },
    {
      "epoch": 0.34001027221366203,
      "grad_norm": 2.5783371925354004,
      "learning_rate": 4.954320517700799e-06,
      "loss": 1.6041,
      "step": 331
    },
    {
      "epoch": 0.34103749357986646,
      "grad_norm": 2.6829233169555664,
      "learning_rate": 4.952417205938333e-06,
      "loss": 1.7111,
      "step": 332
    },
    {
      "epoch": 0.3420647149460709,
      "grad_norm": 2.6643247604370117,
      "learning_rate": 4.950513894175866e-06,
      "loss": 1.6797,
      "step": 333
    },
    {
      "epoch": 0.3430919363122753,
      "grad_norm": 2.776308298110962,
      "learning_rate": 4.9486105824133995e-06,
      "loss": 1.6766,
      "step": 334
    },
    {
      "epoch": 0.3441191576784797,
      "grad_norm": 2.722667932510376,
      "learning_rate": 4.946707270650933e-06,
      "loss": 1.6865,
      "step": 335
    },
    {
      "epoch": 0.34514637904468415,
      "grad_norm": 2.7050845623016357,
      "learning_rate": 4.944803958888466e-06,
      "loss": 1.6967,
      "step": 336
    },
    {
      "epoch": 0.34617360041088857,
      "grad_norm": 3.0009098052978516,
      "learning_rate": 4.942900647126e-06,
      "loss": 1.714,
      "step": 337
    },
    {
      "epoch": 0.34720082177709294,
      "grad_norm": 2.793621301651001,
      "learning_rate": 4.940997335363533e-06,
      "loss": 1.6591,
      "step": 338
    },
    {
      "epoch": 0.34822804314329736,
      "grad_norm": 2.844383478164673,
      "learning_rate": 4.939094023601066e-06,
      "loss": 1.611,
      "step": 339
    },
    {
      "epoch": 0.3492552645095018,
      "grad_norm": 2.829378366470337,
      "learning_rate": 4.9371907118386e-06,
      "loss": 1.666,
      "step": 340
    },
    {
      "epoch": 0.3492552645095018,
      "eval_loss": 1.96309494972229,
      "eval_runtime": 37.3346,
      "eval_samples_per_second": 26.785,
      "eval_steps_per_second": 1.125,
      "step": 340
    },
    {
      "epoch": 0.3502824858757062,
      "grad_norm": 2.9702041149139404,
      "learning_rate": 4.935287400076133e-06,
      "loss": 1.6703,
      "step": 341
    },
    {
      "epoch": 0.35130970724191063,
      "grad_norm": 2.7555935382843018,
      "learning_rate": 4.933384088313666e-06,
      "loss": 1.6879,
      "step": 342
    },
    {
      "epoch": 0.35233692860811505,
      "grad_norm": 2.8968169689178467,
      "learning_rate": 4.9314807765512e-06,
      "loss": 1.6342,
      "step": 343
    },
    {
      "epoch": 0.3533641499743195,
      "grad_norm": 3.010115385055542,
      "learning_rate": 4.929577464788733e-06,
      "loss": 1.5883,
      "step": 344
    },
    {
      "epoch": 0.3543913713405239,
      "grad_norm": 2.6449785232543945,
      "learning_rate": 4.9276741530262665e-06,
      "loss": 1.654,
      "step": 345
    },
    {
      "epoch": 0.3554185927067283,
      "grad_norm": 2.976109266281128,
      "learning_rate": 4.9257708412638e-06,
      "loss": 1.6483,
      "step": 346
    },
    {
      "epoch": 0.35644581407293274,
      "grad_norm": 2.856144666671753,
      "learning_rate": 4.923867529501332e-06,
      "loss": 1.6536,
      "step": 347
    },
    {
      "epoch": 0.3574730354391371,
      "grad_norm": 2.8142166137695312,
      "learning_rate": 4.921964217738866e-06,
      "loss": 1.6415,
      "step": 348
    },
    {
      "epoch": 0.35850025680534153,
      "grad_norm": 2.70807147026062,
      "learning_rate": 4.920060905976399e-06,
      "loss": 1.7099,
      "step": 349
    },
    {
      "epoch": 0.35952747817154596,
      "grad_norm": 2.7715506553649902,
      "learning_rate": 4.9181575942139325e-06,
      "loss": 1.6947,
      "step": 350
    },
    {
      "epoch": 0.35952747817154596,
      "eval_loss": 1.9507063627243042,
      "eval_runtime": 37.3094,
      "eval_samples_per_second": 26.803,
      "eval_steps_per_second": 1.126,
      "step": 350
    },
    {
      "epoch": 0.3605546995377504,
      "grad_norm": 2.8816769123077393,
      "learning_rate": 4.916254282451466e-06,
      "loss": 1.6906,
      "step": 351
    },
    {
      "epoch": 0.3615819209039548,
      "grad_norm": 3.08797025680542,
      "learning_rate": 4.914350970688999e-06,
      "loss": 1.7387,
      "step": 352
    },
    {
      "epoch": 0.3626091422701592,
      "grad_norm": 2.6018118858337402,
      "learning_rate": 4.9124476589265325e-06,
      "loss": 1.6319,
      "step": 353
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.7790255546569824,
      "learning_rate": 4.910544347164066e-06,
      "loss": 1.6357,
      "step": 354
    },
    {
      "epoch": 0.36466358500256807,
      "grad_norm": 2.7360289096832275,
      "learning_rate": 4.908641035401599e-06,
      "loss": 1.7127,
      "step": 355
    },
    {
      "epoch": 0.3656908063687725,
      "grad_norm": 2.6693854331970215,
      "learning_rate": 4.906737723639133e-06,
      "loss": 1.7747,
      "step": 356
    },
    {
      "epoch": 0.3667180277349769,
      "grad_norm": 2.642868995666504,
      "learning_rate": 4.904834411876665e-06,
      "loss": 1.6401,
      "step": 357
    },
    {
      "epoch": 0.3677452491011813,
      "grad_norm": 2.7230374813079834,
      "learning_rate": 4.902931100114199e-06,
      "loss": 1.6833,
      "step": 358
    },
    {
      "epoch": 0.3687724704673857,
      "grad_norm": 2.499457359313965,
      "learning_rate": 4.901027788351733e-06,
      "loss": 1.6007,
      "step": 359
    },
    {
      "epoch": 0.3697996918335901,
      "grad_norm": 2.7695276737213135,
      "learning_rate": 4.899124476589266e-06,
      "loss": 1.6486,
      "step": 360
    },
    {
      "epoch": 0.3697996918335901,
      "eval_loss": 1.9434194564819336,
      "eval_runtime": 37.3126,
      "eval_samples_per_second": 26.801,
      "eval_steps_per_second": 1.126,
      "step": 360
    },
    {
      "epoch": 0.37082691319979455,
      "grad_norm": 2.5715794563293457,
      "learning_rate": 4.8972211648267994e-06,
      "loss": 1.6183,
      "step": 361
    },
    {
      "epoch": 0.371854134565999,
      "grad_norm": 2.637859582901001,
      "learning_rate": 4.895317853064333e-06,
      "loss": 1.6648,
      "step": 362
    },
    {
      "epoch": 0.3728813559322034,
      "grad_norm": 2.5601117610931396,
      "learning_rate": 4.893414541301866e-06,
      "loss": 1.6475,
      "step": 363
    },
    {
      "epoch": 0.3739085772984078,
      "grad_norm": 2.429337739944458,
      "learning_rate": 4.891511229539399e-06,
      "loss": 1.6435,
      "step": 364
    },
    {
      "epoch": 0.37493579866461224,
      "grad_norm": 2.6890885829925537,
      "learning_rate": 4.889607917776932e-06,
      "loss": 1.6577,
      "step": 365
    },
    {
      "epoch": 0.37596302003081666,
      "grad_norm": 2.55492901802063,
      "learning_rate": 4.887704606014465e-06,
      "loss": 1.6523,
      "step": 366
    },
    {
      "epoch": 0.37699024139702103,
      "grad_norm": 2.841362476348877,
      "learning_rate": 4.885801294251999e-06,
      "loss": 1.6742,
      "step": 367
    },
    {
      "epoch": 0.37801746276322545,
      "grad_norm": 2.8041367530822754,
      "learning_rate": 4.883897982489532e-06,
      "loss": 1.5946,
      "step": 368
    },
    {
      "epoch": 0.3790446841294299,
      "grad_norm": 2.7135822772979736,
      "learning_rate": 4.8819946707270655e-06,
      "loss": 1.6909,
      "step": 369
    },
    {
      "epoch": 0.3800719054956343,
      "grad_norm": 2.9020211696624756,
      "learning_rate": 4.880091358964599e-06,
      "loss": 1.6804,
      "step": 370
    },
    {
      "epoch": 0.3800719054956343,
      "eval_loss": 1.9353317022323608,
      "eval_runtime": 37.3188,
      "eval_samples_per_second": 26.796,
      "eval_steps_per_second": 1.125,
      "step": 370
    },
    {
      "epoch": 0.3810991268618387,
      "grad_norm": 2.567310333251953,
      "learning_rate": 4.878188047202132e-06,
      "loss": 1.5885,
      "step": 371
    },
    {
      "epoch": 0.38212634822804314,
      "grad_norm": 2.910834789276123,
      "learning_rate": 4.876284735439666e-06,
      "loss": 1.7681,
      "step": 372
    },
    {
      "epoch": 0.38315356959424757,
      "grad_norm": 2.7507543563842773,
      "learning_rate": 4.874381423677199e-06,
      "loss": 1.7228,
      "step": 373
    },
    {
      "epoch": 0.384180790960452,
      "grad_norm": 2.9230854511260986,
      "learning_rate": 4.8724781119147315e-06,
      "loss": 1.6491,
      "step": 374
    },
    {
      "epoch": 0.3852080123266564,
      "grad_norm": 2.608980178833008,
      "learning_rate": 4.870574800152265e-06,
      "loss": 1.6757,
      "step": 375
    },
    {
      "epoch": 0.38623523369286084,
      "grad_norm": 2.9557063579559326,
      "learning_rate": 4.868671488389798e-06,
      "loss": 1.607,
      "step": 376
    },
    {
      "epoch": 0.3872624550590652,
      "grad_norm": 2.982243537902832,
      "learning_rate": 4.8667681766273316e-06,
      "loss": 1.6169,
      "step": 377
    },
    {
      "epoch": 0.3882896764252696,
      "grad_norm": 2.775012254714966,
      "learning_rate": 4.864864864864866e-06,
      "loss": 1.5835,
      "step": 378
    },
    {
      "epoch": 0.38931689779147405,
      "grad_norm": 2.9500741958618164,
      "learning_rate": 4.862961553102399e-06,
      "loss": 1.6504,
      "step": 379
    },
    {
      "epoch": 0.39034411915767847,
      "grad_norm": 2.889702796936035,
      "learning_rate": 4.8610582413399325e-06,
      "loss": 1.6814,
      "step": 380
    },
    {
      "epoch": 0.39034411915767847,
      "eval_loss": 1.9426418542861938,
      "eval_runtime": 37.3276,
      "eval_samples_per_second": 26.79,
      "eval_steps_per_second": 1.125,
      "step": 380
    },
    {
      "epoch": 0.3913713405238829,
      "grad_norm": 2.5075154304504395,
      "learning_rate": 4.859154929577465e-06,
      "loss": 1.6368,
      "step": 381
    },
    {
      "epoch": 0.3923985618900873,
      "grad_norm": 2.6461148262023926,
      "learning_rate": 4.857251617814998e-06,
      "loss": 1.6526,
      "step": 382
    },
    {
      "epoch": 0.39342578325629174,
      "grad_norm": 2.681501626968384,
      "learning_rate": 4.855348306052532e-06,
      "loss": 1.6846,
      "step": 383
    },
    {
      "epoch": 0.39445300462249616,
      "grad_norm": 2.557311773300171,
      "learning_rate": 4.853444994290065e-06,
      "loss": 1.6645,
      "step": 384
    },
    {
      "epoch": 0.3954802259887006,
      "grad_norm": 2.6819186210632324,
      "learning_rate": 4.8515416825275985e-06,
      "loss": 1.6323,
      "step": 385
    },
    {
      "epoch": 0.396507447354905,
      "grad_norm": 2.8803794384002686,
      "learning_rate": 4.849638370765132e-06,
      "loss": 1.6991,
      "step": 386
    },
    {
      "epoch": 0.3975346687211094,
      "grad_norm": 2.7181358337402344,
      "learning_rate": 4.847735059002665e-06,
      "loss": 1.6256,
      "step": 387
    },
    {
      "epoch": 0.3985618900873138,
      "grad_norm": 2.5668489933013916,
      "learning_rate": 4.8458317472401985e-06,
      "loss": 1.58,
      "step": 388
    },
    {
      "epoch": 0.3995891114535182,
      "grad_norm": 2.708804130554199,
      "learning_rate": 4.843928435477732e-06,
      "loss": 1.67,
      "step": 389
    },
    {
      "epoch": 0.40061633281972264,
      "grad_norm": 2.6565728187561035,
      "learning_rate": 4.842025123715265e-06,
      "loss": 1.622,
      "step": 390
    },
    {
      "epoch": 0.40061633281972264,
      "eval_loss": 1.9529728889465332,
      "eval_runtime": 37.3489,
      "eval_samples_per_second": 26.775,
      "eval_steps_per_second": 1.125,
      "step": 390
    },
    {
      "epoch": 0.40164355418592707,
      "grad_norm": 2.8743324279785156,
      "learning_rate": 4.840121811952798e-06,
      "loss": 1.6618,
      "step": 391
    },
    {
      "epoch": 0.4026707755521315,
      "grad_norm": 2.86134672164917,
      "learning_rate": 4.838218500190331e-06,
      "loss": 1.6544,
      "step": 392
    },
    {
      "epoch": 0.4036979969183359,
      "grad_norm": 3.3492071628570557,
      "learning_rate": 4.8363151884278645e-06,
      "loss": 1.6683,
      "step": 393
    },
    {
      "epoch": 0.40472521828454033,
      "grad_norm": 2.6630825996398926,
      "learning_rate": 4.834411876665398e-06,
      "loss": 1.6447,
      "step": 394
    },
    {
      "epoch": 0.40575243965074476,
      "grad_norm": 2.820096492767334,
      "learning_rate": 4.832508564902931e-06,
      "loss": 1.6579,
      "step": 395
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 3.076234817504883,
      "learning_rate": 4.830605253140465e-06,
      "loss": 1.6039,
      "step": 396
    },
    {
      "epoch": 0.40780688238315355,
      "grad_norm": 2.667719841003418,
      "learning_rate": 4.828701941377998e-06,
      "loss": 1.6364,
      "step": 397
    },
    {
      "epoch": 0.40883410374935797,
      "grad_norm": 3.2132771015167236,
      "learning_rate": 4.826798629615531e-06,
      "loss": 1.5906,
      "step": 398
    },
    {
      "epoch": 0.4098613251155624,
      "grad_norm": 2.661484479904175,
      "learning_rate": 4.824895317853065e-06,
      "loss": 1.613,
      "step": 399
    },
    {
      "epoch": 0.4108885464817668,
      "grad_norm": 3.002636671066284,
      "learning_rate": 4.822992006090598e-06,
      "loss": 1.6305,
      "step": 400
    },
    {
      "epoch": 0.4108885464817668,
      "eval_loss": 1.9345510005950928,
      "eval_runtime": 37.3369,
      "eval_samples_per_second": 26.783,
      "eval_steps_per_second": 1.125,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 2919,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.246923763744768e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}