{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1027221366204417,
  "eval_steps": 10,
  "global_step": 100,
  "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
    }
  ],
  "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": 3.11730940936192e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}