{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.935672514619883,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 4.463105201721191,
      "learning_rate": 2e-05,
      "loss": 3.2142,
      "step": 1
    },
    {
      "epoch": 0.00935672514619883,
      "eval_loss": 3.3358547687530518,
      "eval_runtime": 13.9023,
      "eval_samples_per_second": 6.474,
      "eval_steps_per_second": 6.474,
      "step": 1
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 4.7624897956848145,
      "learning_rate": 4e-05,
      "loss": 3.3766,
      "step": 2
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 3.991523265838623,
      "learning_rate": 6e-05,
      "loss": 3.3922,
      "step": 3
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 3.8783044815063477,
      "learning_rate": 8e-05,
      "loss": 3.0767,
      "step": 4
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 4.1902995109558105,
      "learning_rate": 0.0001,
      "loss": 3.2965,
      "step": 5
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 4.054313659667969,
      "learning_rate": 0.00012,
      "loss": 3.0089,
      "step": 6
    },
    {
      "epoch": 0.06549707602339182,
      "grad_norm": 4.280858993530273,
      "learning_rate": 0.00014,
      "loss": 3.0863,
      "step": 7
    },
    {
      "epoch": 0.07485380116959064,
      "grad_norm": 3.999479293823242,
      "learning_rate": 0.00016,
      "loss": 2.9925,
      "step": 8
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 3.4866421222686768,
      "learning_rate": 0.00018,
      "loss": 2.941,
      "step": 9
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 3.900364398956299,
      "learning_rate": 0.0002,
      "loss": 2.7885,
      "step": 10
    },
    {
      "epoch": 0.10292397660818714,
      "grad_norm": 3.4323623180389404,
      "learning_rate": 0.0001999390827019096,
      "loss": 2.8013,
      "step": 11
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": 3.4795432090759277,
      "learning_rate": 0.00019975640502598244,
      "loss": 2.6806,
      "step": 12
    },
    {
      "epoch": 0.1216374269005848,
      "grad_norm": 3.2568836212158203,
      "learning_rate": 0.00019945218953682734,
      "loss": 2.6366,
      "step": 13
    },
    {
      "epoch": 0.13099415204678364,
      "grad_norm": 2.9930436611175537,
      "learning_rate": 0.00019902680687415705,
      "loss": 2.7908,
      "step": 14
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 2.845224380493164,
      "learning_rate": 0.00019848077530122083,
      "loss": 2.5384,
      "step": 15
    },
    {
      "epoch": 0.1497076023391813,
      "grad_norm": 2.690312385559082,
      "learning_rate": 0.00019781476007338058,
      "loss": 2.7595,
      "step": 16
    },
    {
      "epoch": 0.15906432748538013,
      "grad_norm": 3.0404510498046875,
      "learning_rate": 0.00019702957262759965,
      "loss": 2.7844,
      "step": 17
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 2.836411952972412,
      "learning_rate": 0.0001961261695938319,
      "loss": 2.4923,
      "step": 18
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 3.020054578781128,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.6076,
      "step": 19
    },
    {
      "epoch": 0.1871345029239766,
      "grad_norm": 2.719973087310791,
      "learning_rate": 0.00019396926207859084,
      "loss": 2.6418,
      "step": 20
    },
    {
      "epoch": 0.19649122807017544,
      "grad_norm": 3.120027780532837,
      "learning_rate": 0.00019271838545667876,
      "loss": 2.7253,
      "step": 21
    },
    {
      "epoch": 0.20584795321637428,
      "grad_norm": 2.7467753887176514,
      "learning_rate": 0.0001913545457642601,
      "loss": 2.4353,
      "step": 22
    },
    {
      "epoch": 0.2152046783625731,
      "grad_norm": 3.3954317569732666,
      "learning_rate": 0.0001898794046299167,
      "loss": 2.6932,
      "step": 23
    },
    {
      "epoch": 0.22456140350877193,
      "grad_norm": 2.6571295261383057,
      "learning_rate": 0.00018829475928589271,
      "loss": 2.5214,
      "step": 24
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 2.4160666465759277,
      "learning_rate": 0.00018660254037844388,
      "loss": 2.6052,
      "step": 25
    },
    {
      "epoch": 0.23391812865497075,
      "eval_loss": 2.5258662700653076,
      "eval_runtime": 13.9413,
      "eval_samples_per_second": 6.456,
      "eval_steps_per_second": 6.456,
      "step": 25
    },
    {
      "epoch": 0.2432748538011696,
      "grad_norm": 2.6495888233184814,
      "learning_rate": 0.0001848048096156426,
      "loss": 2.5469,
      "step": 26
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 2.838324785232544,
      "learning_rate": 0.00018290375725550417,
      "loss": 2.5969,
      "step": 27
    },
    {
      "epoch": 0.26198830409356727,
      "grad_norm": 2.747297525405884,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.4122,
      "step": 28
    },
    {
      "epoch": 0.27134502923976606,
      "grad_norm": 2.5374674797058105,
      "learning_rate": 0.00017880107536067218,
      "loss": 2.2964,
      "step": 29
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 2.8469207286834717,
      "learning_rate": 0.0001766044443118978,
      "loss": 2.6656,
      "step": 30
    },
    {
      "epoch": 0.29005847953216374,
      "grad_norm": 2.8864634037017822,
      "learning_rate": 0.00017431448254773944,
      "loss": 2.2717,
      "step": 31
    },
    {
      "epoch": 0.2994152046783626,
      "grad_norm": 2.550114393234253,
      "learning_rate": 0.0001719339800338651,
      "loss": 2.3912,
      "step": 32
    },
    {
      "epoch": 0.3087719298245614,
      "grad_norm": 2.7608063220977783,
      "learning_rate": 0.00016946583704589973,
      "loss": 2.3453,
      "step": 33
    },
    {
      "epoch": 0.31812865497076026,
      "grad_norm": 2.7784292697906494,
      "learning_rate": 0.00016691306063588583,
      "loss": 2.495,
      "step": 34
    },
    {
      "epoch": 0.32748538011695905,
      "grad_norm": 2.7670254707336426,
      "learning_rate": 0.00016427876096865394,
      "loss": 2.3523,
      "step": 35
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 2.92022442817688,
      "learning_rate": 0.0001615661475325658,
      "loss": 2.5027,
      "step": 36
    },
    {
      "epoch": 0.34619883040935673,
      "grad_norm": 2.6825602054595947,
      "learning_rate": 0.00015877852522924732,
      "loss": 2.5576,
      "step": 37
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.5809407234191895,
      "learning_rate": 0.0001559192903470747,
      "loss": 2.4248,
      "step": 38
    },
    {
      "epoch": 0.3649122807017544,
      "grad_norm": 2.5570051670074463,
      "learning_rate": 0.0001529919264233205,
      "loss": 2.3693,
      "step": 39
    },
    {
      "epoch": 0.3742690058479532,
      "grad_norm": 2.4310109615325928,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.4687,
      "step": 40
    },
    {
      "epoch": 0.38362573099415204,
      "grad_norm": 2.647545099258423,
      "learning_rate": 0.00014694715627858908,
      "loss": 2.5393,
      "step": 41
    },
    {
      "epoch": 0.3929824561403509,
      "grad_norm": 2.5504465103149414,
      "learning_rate": 0.00014383711467890774,
      "loss": 2.3839,
      "step": 42
    },
    {
      "epoch": 0.4023391812865497,
      "grad_norm": 2.3321890830993652,
      "learning_rate": 0.00014067366430758004,
      "loss": 2.5113,
      "step": 43
    },
    {
      "epoch": 0.41169590643274856,
      "grad_norm": 2.408841371536255,
      "learning_rate": 0.00013746065934159123,
      "loss": 2.3157,
      "step": 44
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 2.5375423431396484,
      "learning_rate": 0.00013420201433256689,
      "loss": 2.676,
      "step": 45
    },
    {
      "epoch": 0.4304093567251462,
      "grad_norm": 2.8962650299072266,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.8322,
      "step": 46
    },
    {
      "epoch": 0.439766081871345,
      "grad_norm": 2.144554615020752,
      "learning_rate": 0.0001275637355816999,
      "loss": 2.2713,
      "step": 47
    },
    {
      "epoch": 0.44912280701754387,
      "grad_norm": 2.3191635608673096,
      "learning_rate": 0.00012419218955996676,
      "loss": 2.3502,
      "step": 48
    },
    {
      "epoch": 0.4584795321637427,
      "grad_norm": 2.344190835952759,
      "learning_rate": 0.00012079116908177593,
      "loss": 2.5839,
      "step": 49
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 2.446531295776367,
      "learning_rate": 0.00011736481776669306,
      "loss": 2.5168,
      "step": 50
    },
    {
      "epoch": 0.4678362573099415,
      "eval_loss": 2.3896028995513916,
      "eval_runtime": 13.9611,
      "eval_samples_per_second": 6.446,
      "eval_steps_per_second": 6.446,
      "step": 50
    },
    {
      "epoch": 0.47719298245614034,
      "grad_norm": 2.4833006858825684,
      "learning_rate": 0.00011391731009600654,
      "loss": 2.6256,
      "step": 51
    },
    {
      "epoch": 0.4865497076023392,
      "grad_norm": 2.2681424617767334,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.3367,
      "step": 52
    },
    {
      "epoch": 0.495906432748538,
      "grad_norm": 2.4194841384887695,
      "learning_rate": 0.00010697564737441252,
      "loss": 2.3812,
      "step": 53
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 2.4216341972351074,
      "learning_rate": 0.00010348994967025012,
      "loss": 2.6421,
      "step": 54
    },
    {
      "epoch": 0.5146198830409356,
      "grad_norm": 2.5757429599761963,
      "learning_rate": 0.0001,
      "loss": 2.7692,
      "step": 55
    },
    {
      "epoch": 0.5239766081871345,
      "grad_norm": 2.352524757385254,
      "learning_rate": 9.651005032974994e-05,
      "loss": 2.1221,
      "step": 56
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.435523271560669,
      "learning_rate": 9.302435262558747e-05,
      "loss": 2.5788,
      "step": 57
    },
    {
      "epoch": 0.5426900584795321,
      "grad_norm": 2.124344825744629,
      "learning_rate": 8.954715367323468e-05,
      "loss": 2.2217,
      "step": 58
    },
    {
      "epoch": 0.552046783625731,
      "grad_norm": 2.3110225200653076,
      "learning_rate": 8.608268990399349e-05,
      "loss": 2.4934,
      "step": 59
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 2.773723840713501,
      "learning_rate": 8.263518223330697e-05,
      "loss": 2.8535,
      "step": 60
    },
    {
      "epoch": 0.5707602339181287,
      "grad_norm": 2.4425599575042725,
      "learning_rate": 7.920883091822408e-05,
      "loss": 2.6014,
      "step": 61
    },
    {
      "epoch": 0.5801169590643275,
      "grad_norm": 2.4114837646484375,
      "learning_rate": 7.580781044003324e-05,
      "loss": 2.2151,
      "step": 62
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 2.333024024963379,
      "learning_rate": 7.243626441830009e-05,
      "loss": 2.3344,
      "step": 63
    },
    {
      "epoch": 0.5988304093567252,
      "grad_norm": 2.4764840602874756,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.5599,
      "step": 64
    },
    {
      "epoch": 0.6081871345029239,
      "grad_norm": 2.4353721141815186,
      "learning_rate": 6.579798566743314e-05,
      "loss": 2.0338,
      "step": 65
    },
    {
      "epoch": 0.6175438596491228,
      "grad_norm": 2.4556148052215576,
      "learning_rate": 6.25393406584088e-05,
      "loss": 2.0903,
      "step": 66
    },
    {
      "epoch": 0.6269005847953216,
      "grad_norm": 2.566187858581543,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 2.4776,
      "step": 67
    },
    {
      "epoch": 0.6362573099415205,
      "grad_norm": 3.249467611312866,
      "learning_rate": 5.616288532109225e-05,
      "loss": 2.4283,
      "step": 68
    },
    {
      "epoch": 0.6456140350877193,
      "grad_norm": 2.354640483856201,
      "learning_rate": 5.305284372141095e-05,
      "loss": 2.2281,
      "step": 69
    },
    {
      "epoch": 0.6549707602339181,
      "grad_norm": 2.517160177230835,
      "learning_rate": 5.000000000000002e-05,
      "loss": 2.2233,
      "step": 70
    },
    {
      "epoch": 0.664327485380117,
      "grad_norm": 2.740892171859741,
      "learning_rate": 4.700807357667952e-05,
      "loss": 2.4251,
      "step": 71
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 2.4594883918762207,
      "learning_rate": 4.4080709652925336e-05,
      "loss": 2.5892,
      "step": 72
    },
    {
      "epoch": 0.6830409356725147,
      "grad_norm": 2.5558207035064697,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.5979,
      "step": 73
    },
    {
      "epoch": 0.6923976608187135,
      "grad_norm": 2.260289192199707,
      "learning_rate": 3.843385246743417e-05,
      "loss": 2.3547,
      "step": 74
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 2.2581794261932373,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 2.3779,
      "step": 75
    },
    {
      "epoch": 0.7017543859649122,
      "eval_loss": 2.32470965385437,
      "eval_runtime": 14.0307,
      "eval_samples_per_second": 6.414,
      "eval_steps_per_second": 6.414,
      "step": 75
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.6566221714019775,
      "learning_rate": 3.308693936411421e-05,
      "loss": 2.3354,
      "step": 76
    },
    {
      "epoch": 0.7204678362573099,
      "grad_norm": 2.7329909801483154,
      "learning_rate": 3.053416295410026e-05,
      "loss": 2.3228,
      "step": 77
    },
    {
      "epoch": 0.7298245614035088,
      "grad_norm": 2.649616241455078,
      "learning_rate": 2.8066019966134904e-05,
      "loss": 2.2475,
      "step": 78
    },
    {
      "epoch": 0.7391812865497076,
      "grad_norm": 2.667179584503174,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 2.6119,
      "step": 79
    },
    {
      "epoch": 0.7485380116959064,
      "grad_norm": 2.4291374683380127,
      "learning_rate": 2.339555568810221e-05,
      "loss": 2.3532,
      "step": 80
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 2.347785472869873,
      "learning_rate": 2.119892463932781e-05,
      "loss": 2.5149,
      "step": 81
    },
    {
      "epoch": 0.7672514619883041,
      "grad_norm": 2.5152335166931152,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.4291,
      "step": 82
    },
    {
      "epoch": 0.776608187134503,
      "grad_norm": 2.509918212890625,
      "learning_rate": 1.7096242744495837e-05,
      "loss": 2.2923,
      "step": 83
    },
    {
      "epoch": 0.7859649122807018,
      "grad_norm": 2.535485029220581,
      "learning_rate": 1.5195190384357404e-05,
      "loss": 2.2462,
      "step": 84
    },
    {
      "epoch": 0.7953216374269005,
      "grad_norm": 2.524515151977539,
      "learning_rate": 1.339745962155613e-05,
      "loss": 2.3981,
      "step": 85
    },
    {
      "epoch": 0.8046783625730994,
      "grad_norm": 2.53387713432312,
      "learning_rate": 1.1705240714107302e-05,
      "loss": 2.3842,
      "step": 86
    },
    {
      "epoch": 0.8140350877192982,
      "grad_norm": 2.3665547370910645,
      "learning_rate": 1.0120595370083318e-05,
      "loss": 2.0239,
      "step": 87
    },
    {
      "epoch": 0.8233918128654971,
      "grad_norm": 2.359243631362915,
      "learning_rate": 8.645454235739903e-06,
      "loss": 2.3947,
      "step": 88
    },
    {
      "epoch": 0.8327485380116959,
      "grad_norm": 2.518428325653076,
      "learning_rate": 7.281614543321269e-06,
      "loss": 2.1668,
      "step": 89
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 2.3977906703948975,
      "learning_rate": 6.030737921409169e-06,
      "loss": 2.2668,
      "step": 90
    },
    {
      "epoch": 0.8514619883040936,
      "grad_norm": 2.6835556030273438,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 2.255,
      "step": 91
    },
    {
      "epoch": 0.8608187134502924,
      "grad_norm": 2.503506898880005,
      "learning_rate": 3.873830406168111e-06,
      "loss": 2.2606,
      "step": 92
    },
    {
      "epoch": 0.8701754385964913,
      "grad_norm": 2.585240125656128,
      "learning_rate": 2.970427372400353e-06,
      "loss": 2.1736,
      "step": 93
    },
    {
      "epoch": 0.87953216374269,
      "grad_norm": 2.5094244480133057,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 2.3768,
      "step": 94
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.3380393981933594,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 2.4361,
      "step": 95
    },
    {
      "epoch": 0.8982456140350877,
      "grad_norm": 2.5652716159820557,
      "learning_rate": 9.731931258429638e-07,
      "loss": 2.1897,
      "step": 96
    },
    {
      "epoch": 0.9076023391812865,
      "grad_norm": 2.379408836364746,
      "learning_rate": 5.478104631726711e-07,
      "loss": 2.397,
      "step": 97
    },
    {
      "epoch": 0.9169590643274854,
      "grad_norm": 2.5933423042297363,
      "learning_rate": 2.4359497401758024e-07,
      "loss": 2.5667,
      "step": 98
    },
    {
      "epoch": 0.9263157894736842,
      "grad_norm": 2.5865583419799805,
      "learning_rate": 6.09172980904238e-08,
      "loss": 2.4204,
      "step": 99
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 2.6614973545074463,
      "learning_rate": 0.0,
      "loss": 2.624,
      "step": 100
    },
    {
      "epoch": 0.935672514619883,
      "eval_loss": 2.30788254737854,
      "eval_runtime": 13.8631,
      "eval_samples_per_second": 6.492,
      "eval_steps_per_second": 6.492,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.738765926137856e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}