outputs / last-checkpoint /trainer_state.json
Ahdoot's picture
Training in progress, step 150, checkpoint
55d4e34 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.23823704586063132,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0015882469724042088,
"grad_norm": 0.9020900726318359,
"learning_rate": 8.000000000000001e-06,
"loss": 1.462,
"step": 1
},
{
"epoch": 0.0031764939448084176,
"grad_norm": 0.8714035749435425,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.7768,
"step": 2
},
{
"epoch": 0.004764740917212627,
"grad_norm": 0.6246618032455444,
"learning_rate": 2.4e-05,
"loss": 1.4764,
"step": 3
},
{
"epoch": 0.006352987889616835,
"grad_norm": 0.6882991194725037,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.3473,
"step": 4
},
{
"epoch": 0.007941234862021045,
"grad_norm": 0.7609978914260864,
"learning_rate": 4e-05,
"loss": 1.4786,
"step": 5
},
{
"epoch": 0.009529481834425254,
"grad_norm": 0.6454429030418396,
"learning_rate": 3.993589743589744e-05,
"loss": 1.5175,
"step": 6
},
{
"epoch": 0.011117728806829461,
"grad_norm": 0.5323919057846069,
"learning_rate": 3.9871794871794875e-05,
"loss": 1.5005,
"step": 7
},
{
"epoch": 0.01270597577923367,
"grad_norm": 0.49380961060523987,
"learning_rate": 3.9807692307692314e-05,
"loss": 1.393,
"step": 8
},
{
"epoch": 0.01429422275163788,
"grad_norm": 0.4742673337459564,
"learning_rate": 3.9743589743589747e-05,
"loss": 1.4615,
"step": 9
},
{
"epoch": 0.01588246972404209,
"grad_norm": 0.47878921031951904,
"learning_rate": 3.9679487179487186e-05,
"loss": 1.4317,
"step": 10
},
{
"epoch": 0.017470716696446297,
"grad_norm": 0.5705658197402954,
"learning_rate": 3.961538461538462e-05,
"loss": 1.4019,
"step": 11
},
{
"epoch": 0.019058963668850508,
"grad_norm": 0.4807969331741333,
"learning_rate": 3.955128205128206e-05,
"loss": 1.3456,
"step": 12
},
{
"epoch": 0.020647210641254715,
"grad_norm": 0.4449750781059265,
"learning_rate": 3.948717948717949e-05,
"loss": 1.2978,
"step": 13
},
{
"epoch": 0.022235457613658922,
"grad_norm": 0.42986753582954407,
"learning_rate": 3.942307692307693e-05,
"loss": 1.3485,
"step": 14
},
{
"epoch": 0.023823704586063133,
"grad_norm": 0.4529072344303131,
"learning_rate": 3.935897435897436e-05,
"loss": 1.1967,
"step": 15
},
{
"epoch": 0.02541195155846734,
"grad_norm": 0.36832889914512634,
"learning_rate": 3.9294871794871794e-05,
"loss": 1.4615,
"step": 16
},
{
"epoch": 0.02700019853087155,
"grad_norm": 0.36332887411117554,
"learning_rate": 3.923076923076923e-05,
"loss": 1.424,
"step": 17
},
{
"epoch": 0.02858844550327576,
"grad_norm": 0.3830856680870056,
"learning_rate": 3.9166666666666665e-05,
"loss": 1.3219,
"step": 18
},
{
"epoch": 0.03017669247567997,
"grad_norm": 0.34034624695777893,
"learning_rate": 3.9102564102564105e-05,
"loss": 1.3907,
"step": 19
},
{
"epoch": 0.03176493944808418,
"grad_norm": 0.5381081104278564,
"learning_rate": 3.9038461538461544e-05,
"loss": 1.166,
"step": 20
},
{
"epoch": 0.03335318642048839,
"grad_norm": 0.3757379651069641,
"learning_rate": 3.8974358974358976e-05,
"loss": 1.3848,
"step": 21
},
{
"epoch": 0.034941433392892594,
"grad_norm": 0.3074859082698822,
"learning_rate": 3.8910256410256416e-05,
"loss": 1.2964,
"step": 22
},
{
"epoch": 0.0365296803652968,
"grad_norm": 0.327610045671463,
"learning_rate": 3.884615384615385e-05,
"loss": 1.1818,
"step": 23
},
{
"epoch": 0.038117927337701016,
"grad_norm": 0.31075817346572876,
"learning_rate": 3.878205128205129e-05,
"loss": 1.1266,
"step": 24
},
{
"epoch": 0.03970617431010522,
"grad_norm": 0.3608109652996063,
"learning_rate": 3.871794871794872e-05,
"loss": 1.3268,
"step": 25
},
{
"epoch": 0.04129442128250943,
"grad_norm": 0.34548354148864746,
"learning_rate": 3.865384615384616e-05,
"loss": 1.4485,
"step": 26
},
{
"epoch": 0.04288266825491364,
"grad_norm": 0.3382280468940735,
"learning_rate": 3.858974358974359e-05,
"loss": 1.4231,
"step": 27
},
{
"epoch": 0.044470915227317845,
"grad_norm": 0.3258324861526489,
"learning_rate": 3.852564102564103e-05,
"loss": 1.2321,
"step": 28
},
{
"epoch": 0.04605916219972206,
"grad_norm": 0.390952467918396,
"learning_rate": 3.846153846153846e-05,
"loss": 1.3014,
"step": 29
},
{
"epoch": 0.047647409172126266,
"grad_norm": 0.34574779868125916,
"learning_rate": 3.83974358974359e-05,
"loss": 1.3385,
"step": 30
},
{
"epoch": 0.049235656144530474,
"grad_norm": 0.32823994755744934,
"learning_rate": 3.833333333333334e-05,
"loss": 1.2178,
"step": 31
},
{
"epoch": 0.05082390311693468,
"grad_norm": 0.4966191053390503,
"learning_rate": 3.8269230769230774e-05,
"loss": 1.3805,
"step": 32
},
{
"epoch": 0.052412150089338895,
"grad_norm": 0.3081677556037903,
"learning_rate": 3.820512820512821e-05,
"loss": 1.2109,
"step": 33
},
{
"epoch": 0.0540003970617431,
"grad_norm": 0.2919631600379944,
"learning_rate": 3.8141025641025645e-05,
"loss": 1.2596,
"step": 34
},
{
"epoch": 0.05558864403414731,
"grad_norm": 0.34928378462791443,
"learning_rate": 3.807692307692308e-05,
"loss": 1.3003,
"step": 35
},
{
"epoch": 0.05717689100655152,
"grad_norm": 0.32200536131858826,
"learning_rate": 3.801282051282052e-05,
"loss": 1.1992,
"step": 36
},
{
"epoch": 0.05876513797895573,
"grad_norm": 0.36465853452682495,
"learning_rate": 3.794871794871795e-05,
"loss": 1.3853,
"step": 37
},
{
"epoch": 0.06035338495135994,
"grad_norm": 0.36780843138694763,
"learning_rate": 3.788461538461539e-05,
"loss": 1.3488,
"step": 38
},
{
"epoch": 0.061941631923764146,
"grad_norm": 0.3747501075267792,
"learning_rate": 3.782051282051282e-05,
"loss": 1.2759,
"step": 39
},
{
"epoch": 0.06352987889616836,
"grad_norm": 0.4664352834224701,
"learning_rate": 3.775641025641026e-05,
"loss": 1.2444,
"step": 40
},
{
"epoch": 0.06511812586857256,
"grad_norm": 0.3714566230773926,
"learning_rate": 3.769230769230769e-05,
"loss": 1.3729,
"step": 41
},
{
"epoch": 0.06670637284097677,
"grad_norm": 0.35391151905059814,
"learning_rate": 3.762820512820513e-05,
"loss": 1.2871,
"step": 42
},
{
"epoch": 0.06829461981338097,
"grad_norm": 0.37723308801651,
"learning_rate": 3.7564102564102564e-05,
"loss": 1.3243,
"step": 43
},
{
"epoch": 0.06988286678578519,
"grad_norm": 0.3361778259277344,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.1932,
"step": 44
},
{
"epoch": 0.0714711137581894,
"grad_norm": 0.31701332330703735,
"learning_rate": 3.7435897435897436e-05,
"loss": 1.3294,
"step": 45
},
{
"epoch": 0.0730593607305936,
"grad_norm": 0.3698272705078125,
"learning_rate": 3.7371794871794875e-05,
"loss": 1.2617,
"step": 46
},
{
"epoch": 0.07464760770299782,
"grad_norm": 0.34270384907722473,
"learning_rate": 3.7307692307692314e-05,
"loss": 1.3205,
"step": 47
},
{
"epoch": 0.07623585467540203,
"grad_norm": 0.31238165497779846,
"learning_rate": 3.724358974358975e-05,
"loss": 1.297,
"step": 48
},
{
"epoch": 0.07782410164780623,
"grad_norm": 0.3665103614330292,
"learning_rate": 3.7179487179487186e-05,
"loss": 1.3757,
"step": 49
},
{
"epoch": 0.07941234862021045,
"grad_norm": 0.36817964911460876,
"learning_rate": 3.711538461538462e-05,
"loss": 1.3225,
"step": 50
},
{
"epoch": 0.08100059559261465,
"grad_norm": 0.32568806409835815,
"learning_rate": 3.705128205128206e-05,
"loss": 1.1309,
"step": 51
},
{
"epoch": 0.08258884256501886,
"grad_norm": 0.2992149293422699,
"learning_rate": 3.698717948717949e-05,
"loss": 1.2399,
"step": 52
},
{
"epoch": 0.08417708953742307,
"grad_norm": 0.3493598401546478,
"learning_rate": 3.692307692307693e-05,
"loss": 1.2718,
"step": 53
},
{
"epoch": 0.08576533650982728,
"grad_norm": 0.38273313641548157,
"learning_rate": 3.685897435897436e-05,
"loss": 1.2875,
"step": 54
},
{
"epoch": 0.08735358348223149,
"grad_norm": 0.3631385266780853,
"learning_rate": 3.6794871794871794e-05,
"loss": 1.176,
"step": 55
},
{
"epoch": 0.08894183045463569,
"grad_norm": 0.33916208148002625,
"learning_rate": 3.673076923076923e-05,
"loss": 1.3624,
"step": 56
},
{
"epoch": 0.0905300774270399,
"grad_norm": 0.3310489058494568,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.1639,
"step": 57
},
{
"epoch": 0.09211832439944412,
"grad_norm": 0.3602941930294037,
"learning_rate": 3.6602564102564105e-05,
"loss": 1.288,
"step": 58
},
{
"epoch": 0.09370657137184832,
"grad_norm": 0.39397984743118286,
"learning_rate": 3.653846153846154e-05,
"loss": 1.285,
"step": 59
},
{
"epoch": 0.09529481834425253,
"grad_norm": 0.3368014991283417,
"learning_rate": 3.6474358974358977e-05,
"loss": 1.2523,
"step": 60
},
{
"epoch": 0.09688306531665675,
"grad_norm": 0.32057568430900574,
"learning_rate": 3.6410256410256416e-05,
"loss": 1.0862,
"step": 61
},
{
"epoch": 0.09847131228906095,
"grad_norm": 0.409466028213501,
"learning_rate": 3.634615384615385e-05,
"loss": 1.4059,
"step": 62
},
{
"epoch": 0.10005955926146516,
"grad_norm": 0.3347267210483551,
"learning_rate": 3.628205128205129e-05,
"loss": 1.0021,
"step": 63
},
{
"epoch": 0.10164780623386936,
"grad_norm": 0.31896549463272095,
"learning_rate": 3.621794871794872e-05,
"loss": 1.1485,
"step": 64
},
{
"epoch": 0.10323605320627358,
"grad_norm": 0.3799891471862793,
"learning_rate": 3.615384615384616e-05,
"loss": 1.2916,
"step": 65
},
{
"epoch": 0.10482430017867779,
"grad_norm": 0.3329267203807831,
"learning_rate": 3.608974358974359e-05,
"loss": 1.3268,
"step": 66
},
{
"epoch": 0.10641254715108199,
"grad_norm": 0.4332905411720276,
"learning_rate": 3.602564102564103e-05,
"loss": 1.3233,
"step": 67
},
{
"epoch": 0.1080007941234862,
"grad_norm": 0.4160114824771881,
"learning_rate": 3.596153846153846e-05,
"loss": 1.154,
"step": 68
},
{
"epoch": 0.1095890410958904,
"grad_norm": 0.32984739542007446,
"learning_rate": 3.58974358974359e-05,
"loss": 1.1314,
"step": 69
},
{
"epoch": 0.11117728806829462,
"grad_norm": 0.3880075216293335,
"learning_rate": 3.5833333333333335e-05,
"loss": 1.3362,
"step": 70
},
{
"epoch": 0.11276553504069883,
"grad_norm": 0.33941248059272766,
"learning_rate": 3.5769230769230774e-05,
"loss": 1.2692,
"step": 71
},
{
"epoch": 0.11435378201310303,
"grad_norm": 0.3812304139137268,
"learning_rate": 3.570512820512821e-05,
"loss": 1.0389,
"step": 72
},
{
"epoch": 0.11594202898550725,
"grad_norm": 0.3491113483905792,
"learning_rate": 3.5641025641025646e-05,
"loss": 1.0725,
"step": 73
},
{
"epoch": 0.11753027595791146,
"grad_norm": 0.371980220079422,
"learning_rate": 3.557692307692308e-05,
"loss": 1.2572,
"step": 74
},
{
"epoch": 0.11911852293031566,
"grad_norm": 0.4158433675765991,
"learning_rate": 3.551282051282052e-05,
"loss": 1.3052,
"step": 75
},
{
"epoch": 0.12070676990271988,
"grad_norm": 0.340273380279541,
"learning_rate": 3.544871794871795e-05,
"loss": 1.0866,
"step": 76
},
{
"epoch": 0.12229501687512408,
"grad_norm": 0.42024505138397217,
"learning_rate": 3.538461538461539e-05,
"loss": 1.3908,
"step": 77
},
{
"epoch": 0.12388326384752829,
"grad_norm": 0.3871309757232666,
"learning_rate": 3.532051282051282e-05,
"loss": 1.1443,
"step": 78
},
{
"epoch": 0.1254715108199325,
"grad_norm": 0.4081447124481201,
"learning_rate": 3.525641025641026e-05,
"loss": 1.256,
"step": 79
},
{
"epoch": 0.12705975779233672,
"grad_norm": 0.398825079202652,
"learning_rate": 3.519230769230769e-05,
"loss": 1.0935,
"step": 80
},
{
"epoch": 0.12864800476474092,
"grad_norm": 0.41756635904312134,
"learning_rate": 3.512820512820513e-05,
"loss": 1.3101,
"step": 81
},
{
"epoch": 0.13023625173714512,
"grad_norm": 0.3089386522769928,
"learning_rate": 3.5064102564102565e-05,
"loss": 1.0133,
"step": 82
},
{
"epoch": 0.13182449870954935,
"grad_norm": 0.319243848323822,
"learning_rate": 3.5000000000000004e-05,
"loss": 0.8617,
"step": 83
},
{
"epoch": 0.13341274568195355,
"grad_norm": 0.4051594138145447,
"learning_rate": 3.4935897435897436e-05,
"loss": 1.2443,
"step": 84
},
{
"epoch": 0.13500099265435775,
"grad_norm": 0.43612000346183777,
"learning_rate": 3.4871794871794875e-05,
"loss": 1.269,
"step": 85
},
{
"epoch": 0.13658923962676195,
"grad_norm": 0.43578770756721497,
"learning_rate": 3.4807692307692315e-05,
"loss": 1.2405,
"step": 86
},
{
"epoch": 0.13817748659916618,
"grad_norm": 0.4056044816970825,
"learning_rate": 3.474358974358975e-05,
"loss": 1.0946,
"step": 87
},
{
"epoch": 0.13976573357157038,
"grad_norm": 0.3657781779766083,
"learning_rate": 3.4679487179487186e-05,
"loss": 1.0036,
"step": 88
},
{
"epoch": 0.14135398054397458,
"grad_norm": 0.38766562938690186,
"learning_rate": 3.461538461538462e-05,
"loss": 1.2921,
"step": 89
},
{
"epoch": 0.1429422275163788,
"grad_norm": 0.3952920436859131,
"learning_rate": 3.455128205128206e-05,
"loss": 1.0871,
"step": 90
},
{
"epoch": 0.144530474488783,
"grad_norm": 0.37682345509529114,
"learning_rate": 3.448717948717949e-05,
"loss": 1.3176,
"step": 91
},
{
"epoch": 0.1461187214611872,
"grad_norm": 0.41130203008651733,
"learning_rate": 3.442307692307693e-05,
"loss": 1.4224,
"step": 92
},
{
"epoch": 0.14770696843359143,
"grad_norm": 0.446526437997818,
"learning_rate": 3.435897435897436e-05,
"loss": 1.1269,
"step": 93
},
{
"epoch": 0.14929521540599563,
"grad_norm": 0.3832029104232788,
"learning_rate": 3.4294871794871794e-05,
"loss": 1.2257,
"step": 94
},
{
"epoch": 0.15088346237839984,
"grad_norm": 0.3874358534812927,
"learning_rate": 3.4230769230769234e-05,
"loss": 1.2198,
"step": 95
},
{
"epoch": 0.15247170935080406,
"grad_norm": 0.44150203466415405,
"learning_rate": 3.4166666666666666e-05,
"loss": 1.4579,
"step": 96
},
{
"epoch": 0.15405995632320826,
"grad_norm": 0.49795201420783997,
"learning_rate": 3.4102564102564105e-05,
"loss": 1.1809,
"step": 97
},
{
"epoch": 0.15564820329561246,
"grad_norm": 0.38568922877311707,
"learning_rate": 3.403846153846154e-05,
"loss": 1.2511,
"step": 98
},
{
"epoch": 0.15723645026801666,
"grad_norm": 0.3719356060028076,
"learning_rate": 3.397435897435898e-05,
"loss": 1.1881,
"step": 99
},
{
"epoch": 0.1588246972404209,
"grad_norm": 0.4000978469848633,
"learning_rate": 3.391025641025641e-05,
"loss": 1.0767,
"step": 100
},
{
"epoch": 0.1604129442128251,
"grad_norm": 0.46317172050476074,
"learning_rate": 3.384615384615385e-05,
"loss": 1.1606,
"step": 101
},
{
"epoch": 0.1620011911852293,
"grad_norm": 0.42941561341285706,
"learning_rate": 3.378205128205129e-05,
"loss": 1.1359,
"step": 102
},
{
"epoch": 0.16358943815763352,
"grad_norm": 0.3518621325492859,
"learning_rate": 3.371794871794872e-05,
"loss": 1.1586,
"step": 103
},
{
"epoch": 0.16517768513003772,
"grad_norm": 0.45329567790031433,
"learning_rate": 3.365384615384616e-05,
"loss": 1.3658,
"step": 104
},
{
"epoch": 0.16676593210244192,
"grad_norm": 0.39535844326019287,
"learning_rate": 3.358974358974359e-05,
"loss": 1.1398,
"step": 105
},
{
"epoch": 0.16835417907484615,
"grad_norm": 0.3700944781303406,
"learning_rate": 3.352564102564103e-05,
"loss": 1.0872,
"step": 106
},
{
"epoch": 0.16994242604725035,
"grad_norm": 0.3956209719181061,
"learning_rate": 3.346153846153846e-05,
"loss": 1.3071,
"step": 107
},
{
"epoch": 0.17153067301965455,
"grad_norm": 0.3819758892059326,
"learning_rate": 3.33974358974359e-05,
"loss": 1.1822,
"step": 108
},
{
"epoch": 0.17311891999205878,
"grad_norm": 0.44656893610954285,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.3185,
"step": 109
},
{
"epoch": 0.17470716696446298,
"grad_norm": 0.35640376806259155,
"learning_rate": 3.3269230769230774e-05,
"loss": 1.0616,
"step": 110
},
{
"epoch": 0.17629541393686718,
"grad_norm": 0.3747159242630005,
"learning_rate": 3.3205128205128207e-05,
"loss": 1.1727,
"step": 111
},
{
"epoch": 0.17788366090927138,
"grad_norm": 0.4224643409252167,
"learning_rate": 3.3141025641025646e-05,
"loss": 1.155,
"step": 112
},
{
"epoch": 0.1794719078816756,
"grad_norm": 0.45572227239608765,
"learning_rate": 3.307692307692308e-05,
"loss": 1.1105,
"step": 113
},
{
"epoch": 0.1810601548540798,
"grad_norm": 0.4539688527584076,
"learning_rate": 3.301282051282051e-05,
"loss": 1.1952,
"step": 114
},
{
"epoch": 0.182648401826484,
"grad_norm": 0.45282796025276184,
"learning_rate": 3.294871794871795e-05,
"loss": 1.2254,
"step": 115
},
{
"epoch": 0.18423664879888824,
"grad_norm": 0.37122872471809387,
"learning_rate": 3.288461538461539e-05,
"loss": 1.0683,
"step": 116
},
{
"epoch": 0.18582489577129244,
"grad_norm": 0.5063671469688416,
"learning_rate": 3.282051282051282e-05,
"loss": 1.2554,
"step": 117
},
{
"epoch": 0.18741314274369664,
"grad_norm": 0.4486718475818634,
"learning_rate": 3.275641025641026e-05,
"loss": 1.3148,
"step": 118
},
{
"epoch": 0.18900138971610086,
"grad_norm": 0.43316200375556946,
"learning_rate": 3.269230769230769e-05,
"loss": 1.3,
"step": 119
},
{
"epoch": 0.19058963668850507,
"grad_norm": 0.4560703635215759,
"learning_rate": 3.262820512820513e-05,
"loss": 1.0387,
"step": 120
},
{
"epoch": 0.19217788366090927,
"grad_norm": 0.41410017013549805,
"learning_rate": 3.2564102564102565e-05,
"loss": 1.2125,
"step": 121
},
{
"epoch": 0.1937661306333135,
"grad_norm": 0.43740931153297424,
"learning_rate": 3.2500000000000004e-05,
"loss": 1.1765,
"step": 122
},
{
"epoch": 0.1953543776057177,
"grad_norm": 0.4682227671146393,
"learning_rate": 3.2435897435897436e-05,
"loss": 1.3742,
"step": 123
},
{
"epoch": 0.1969426245781219,
"grad_norm": 0.47108888626098633,
"learning_rate": 3.2371794871794876e-05,
"loss": 1.3794,
"step": 124
},
{
"epoch": 0.1985308715505261,
"grad_norm": 0.4044567048549652,
"learning_rate": 3.230769230769231e-05,
"loss": 1.2427,
"step": 125
},
{
"epoch": 0.20011911852293032,
"grad_norm": 0.44156500697135925,
"learning_rate": 3.224358974358975e-05,
"loss": 1.1546,
"step": 126
},
{
"epoch": 0.20170736549533452,
"grad_norm": 0.4503639340400696,
"learning_rate": 3.2179487179487186e-05,
"loss": 1.1677,
"step": 127
},
{
"epoch": 0.20329561246773872,
"grad_norm": 0.40942591428756714,
"learning_rate": 3.211538461538462e-05,
"loss": 1.0108,
"step": 128
},
{
"epoch": 0.20488385944014295,
"grad_norm": 0.5105980038642883,
"learning_rate": 3.205128205128206e-05,
"loss": 1.313,
"step": 129
},
{
"epoch": 0.20647210641254715,
"grad_norm": 0.46841809153556824,
"learning_rate": 3.198717948717949e-05,
"loss": 1.3129,
"step": 130
},
{
"epoch": 0.20806035338495135,
"grad_norm": 0.4008212387561798,
"learning_rate": 3.192307692307693e-05,
"loss": 1.2303,
"step": 131
},
{
"epoch": 0.20964860035735558,
"grad_norm": 0.42567890882492065,
"learning_rate": 3.185897435897436e-05,
"loss": 1.2456,
"step": 132
},
{
"epoch": 0.21123684732975978,
"grad_norm": 0.44130662083625793,
"learning_rate": 3.1794871794871795e-05,
"loss": 1.38,
"step": 133
},
{
"epoch": 0.21282509430216398,
"grad_norm": 0.5576122999191284,
"learning_rate": 3.1730769230769234e-05,
"loss": 1.3357,
"step": 134
},
{
"epoch": 0.2144133412745682,
"grad_norm": 0.4331263601779938,
"learning_rate": 3.1666666666666666e-05,
"loss": 1.0914,
"step": 135
},
{
"epoch": 0.2160015882469724,
"grad_norm": 0.5117509961128235,
"learning_rate": 3.1602564102564105e-05,
"loss": 1.2846,
"step": 136
},
{
"epoch": 0.2175898352193766,
"grad_norm": 0.5039793848991394,
"learning_rate": 3.153846153846154e-05,
"loss": 1.4331,
"step": 137
},
{
"epoch": 0.2191780821917808,
"grad_norm": 0.4223591387271881,
"learning_rate": 3.147435897435898e-05,
"loss": 1.1687,
"step": 138
},
{
"epoch": 0.22076632916418504,
"grad_norm": 0.40778806805610657,
"learning_rate": 3.141025641025641e-05,
"loss": 1.173,
"step": 139
},
{
"epoch": 0.22235457613658924,
"grad_norm": 0.4686231017112732,
"learning_rate": 3.134615384615385e-05,
"loss": 1.3669,
"step": 140
},
{
"epoch": 0.22394282310899344,
"grad_norm": 0.43122047185897827,
"learning_rate": 3.128205128205129e-05,
"loss": 1.2708,
"step": 141
},
{
"epoch": 0.22553107008139767,
"grad_norm": 0.3762079179286957,
"learning_rate": 3.121794871794872e-05,
"loss": 1.1584,
"step": 142
},
{
"epoch": 0.22711931705380187,
"grad_norm": 0.417106568813324,
"learning_rate": 3.115384615384616e-05,
"loss": 1.1314,
"step": 143
},
{
"epoch": 0.22870756402620607,
"grad_norm": 0.4525890052318573,
"learning_rate": 3.108974358974359e-05,
"loss": 1.124,
"step": 144
},
{
"epoch": 0.2302958109986103,
"grad_norm": 0.41886812448501587,
"learning_rate": 3.102564102564103e-05,
"loss": 1.1735,
"step": 145
},
{
"epoch": 0.2318840579710145,
"grad_norm": 0.39290478825569153,
"learning_rate": 3.0961538461538464e-05,
"loss": 1.2455,
"step": 146
},
{
"epoch": 0.2334723049434187,
"grad_norm": 0.42833879590034485,
"learning_rate": 3.08974358974359e-05,
"loss": 1.2274,
"step": 147
},
{
"epoch": 0.23506055191582292,
"grad_norm": 0.37532350420951843,
"learning_rate": 3.0833333333333335e-05,
"loss": 1.0969,
"step": 148
},
{
"epoch": 0.23664879888822712,
"grad_norm": 0.36185258626937866,
"learning_rate": 3.0769230769230774e-05,
"loss": 1.1227,
"step": 149
},
{
"epoch": 0.23823704586063132,
"grad_norm": 0.4009798765182495,
"learning_rate": 3.070512820512821e-05,
"loss": 1.0955,
"step": 150
}
],
"logging_steps": 1,
"max_steps": 629,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 75,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.0710275291755315e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}