DuongTrongChi's picture
Training in progress, step 206, checkpoint
7df635a verified
raw
history blame
36.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.30097707971874715,
"eval_steps": 500,
"global_step": 206,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001461053785042462,
"grad_norm": 0.30625924468040466,
"learning_rate": 2.0000000000000002e-07,
"loss": 2.1669,
"step": 1
},
{
"epoch": 0.002922107570084924,
"grad_norm": 0.29808640480041504,
"learning_rate": 4.0000000000000003e-07,
"loss": 2.0395,
"step": 2
},
{
"epoch": 0.004383161355127386,
"grad_norm": 0.24509362876415253,
"learning_rate": 6.000000000000001e-07,
"loss": 1.8973,
"step": 3
},
{
"epoch": 0.005844215140169848,
"grad_norm": 0.27399635314941406,
"learning_rate": 8.000000000000001e-07,
"loss": 2.0403,
"step": 4
},
{
"epoch": 0.00730526892521231,
"grad_norm": 0.30136558413505554,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.0947,
"step": 5
},
{
"epoch": 0.008766322710254772,
"grad_norm": 0.30337047576904297,
"learning_rate": 1.2000000000000002e-06,
"loss": 2.0886,
"step": 6
},
{
"epoch": 0.010227376495297234,
"grad_norm": 0.28456181287765503,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.988,
"step": 7
},
{
"epoch": 0.011688430280339696,
"grad_norm": 0.2553723454475403,
"learning_rate": 1.6000000000000001e-06,
"loss": 2.0434,
"step": 8
},
{
"epoch": 0.013149484065382157,
"grad_norm": 0.2616969645023346,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.9692,
"step": 9
},
{
"epoch": 0.01461053785042462,
"grad_norm": 0.2795903980731964,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.9994,
"step": 10
},
{
"epoch": 0.01607159163546708,
"grad_norm": 0.27633437514305115,
"learning_rate": 2.2e-06,
"loss": 1.9672,
"step": 11
},
{
"epoch": 0.017532645420509543,
"grad_norm": 0.3074289858341217,
"learning_rate": 2.4000000000000003e-06,
"loss": 2.0757,
"step": 12
},
{
"epoch": 0.018993699205552005,
"grad_norm": 0.27444779872894287,
"learning_rate": 2.6e-06,
"loss": 1.9697,
"step": 13
},
{
"epoch": 0.020454752990594467,
"grad_norm": 0.28576454520225525,
"learning_rate": 2.8000000000000003e-06,
"loss": 2.0516,
"step": 14
},
{
"epoch": 0.02191580677563693,
"grad_norm": 0.25402647256851196,
"learning_rate": 3e-06,
"loss": 1.9916,
"step": 15
},
{
"epoch": 0.02337686056067939,
"grad_norm": 0.27070897817611694,
"learning_rate": 3.2000000000000003e-06,
"loss": 2.0079,
"step": 16
},
{
"epoch": 0.024837914345721853,
"grad_norm": 0.26685598492622375,
"learning_rate": 3.4000000000000005e-06,
"loss": 1.997,
"step": 17
},
{
"epoch": 0.026298968130764315,
"grad_norm": 0.2818976044654846,
"learning_rate": 3.6000000000000003e-06,
"loss": 2.0454,
"step": 18
},
{
"epoch": 0.027760021915806777,
"grad_norm": 0.2832131087779999,
"learning_rate": 3.8000000000000005e-06,
"loss": 2.0227,
"step": 19
},
{
"epoch": 0.02922107570084924,
"grad_norm": 0.28652554750442505,
"learning_rate": 4.000000000000001e-06,
"loss": 2.0293,
"step": 20
},
{
"epoch": 0.0306821294858917,
"grad_norm": 0.28600171208381653,
"learning_rate": 4.2000000000000004e-06,
"loss": 2.0214,
"step": 21
},
{
"epoch": 0.03214318327093416,
"grad_norm": 0.2540723383426666,
"learning_rate": 4.4e-06,
"loss": 1.998,
"step": 22
},
{
"epoch": 0.03360423705597662,
"grad_norm": 0.2570485472679138,
"learning_rate": 4.600000000000001e-06,
"loss": 1.9908,
"step": 23
},
{
"epoch": 0.03506529084101909,
"grad_norm": 0.2579878866672516,
"learning_rate": 4.800000000000001e-06,
"loss": 1.9355,
"step": 24
},
{
"epoch": 0.036526344626061545,
"grad_norm": 0.29550811648368835,
"learning_rate": 5e-06,
"loss": 2.0992,
"step": 25
},
{
"epoch": 0.03798739841110401,
"grad_norm": 0.2850530445575714,
"learning_rate": 5.2e-06,
"loss": 2.042,
"step": 26
},
{
"epoch": 0.03944845219614647,
"grad_norm": 0.2779623568058014,
"learning_rate": 5.400000000000001e-06,
"loss": 1.9592,
"step": 27
},
{
"epoch": 0.040909505981188934,
"grad_norm": 0.2843893766403198,
"learning_rate": 5.600000000000001e-06,
"loss": 2.0435,
"step": 28
},
{
"epoch": 0.04237055976623139,
"grad_norm": 0.26713600754737854,
"learning_rate": 5.8e-06,
"loss": 2.0014,
"step": 29
},
{
"epoch": 0.04383161355127386,
"grad_norm": 0.2971515357494354,
"learning_rate": 6e-06,
"loss": 2.0246,
"step": 30
},
{
"epoch": 0.04529266733631632,
"grad_norm": 0.2626894414424896,
"learning_rate": 6.200000000000001e-06,
"loss": 2.0402,
"step": 31
},
{
"epoch": 0.04675372112135878,
"grad_norm": 0.27606457471847534,
"learning_rate": 6.4000000000000006e-06,
"loss": 2.0549,
"step": 32
},
{
"epoch": 0.04821477490640124,
"grad_norm": 0.27802756428718567,
"learning_rate": 6.600000000000001e-06,
"loss": 1.9889,
"step": 33
},
{
"epoch": 0.049675828691443706,
"grad_norm": 0.2772068977355957,
"learning_rate": 6.800000000000001e-06,
"loss": 1.9913,
"step": 34
},
{
"epoch": 0.051136882476486165,
"grad_norm": 0.2816425561904907,
"learning_rate": 7e-06,
"loss": 1.9677,
"step": 35
},
{
"epoch": 0.05259793626152863,
"grad_norm": 0.2521456182003021,
"learning_rate": 7.2000000000000005e-06,
"loss": 1.9705,
"step": 36
},
{
"epoch": 0.05405899004657109,
"grad_norm": 0.24795399606227875,
"learning_rate": 7.4e-06,
"loss": 2.0483,
"step": 37
},
{
"epoch": 0.055520043831613554,
"grad_norm": 0.2924613654613495,
"learning_rate": 7.600000000000001e-06,
"loss": 2.0585,
"step": 38
},
{
"epoch": 0.05698109761665601,
"grad_norm": 0.2479739636182785,
"learning_rate": 7.800000000000002e-06,
"loss": 1.9588,
"step": 39
},
{
"epoch": 0.05844215140169848,
"grad_norm": 0.27038994431495667,
"learning_rate": 8.000000000000001e-06,
"loss": 1.9146,
"step": 40
},
{
"epoch": 0.059903205186740936,
"grad_norm": 0.263032466173172,
"learning_rate": 8.2e-06,
"loss": 1.925,
"step": 41
},
{
"epoch": 0.0613642589717834,
"grad_norm": 0.25826576352119446,
"learning_rate": 8.400000000000001e-06,
"loss": 1.9664,
"step": 42
},
{
"epoch": 0.06282531275682586,
"grad_norm": 0.3021976351737976,
"learning_rate": 8.6e-06,
"loss": 2.0211,
"step": 43
},
{
"epoch": 0.06428636654186833,
"grad_norm": 0.2642092704772949,
"learning_rate": 8.8e-06,
"loss": 1.8985,
"step": 44
},
{
"epoch": 0.06574742032691079,
"grad_norm": 0.2693665623664856,
"learning_rate": 9e-06,
"loss": 2.0221,
"step": 45
},
{
"epoch": 0.06720847411195324,
"grad_norm": 0.24328897893428802,
"learning_rate": 9.200000000000002e-06,
"loss": 1.9289,
"step": 46
},
{
"epoch": 0.06866952789699571,
"grad_norm": 0.24804741144180298,
"learning_rate": 9.4e-06,
"loss": 1.9128,
"step": 47
},
{
"epoch": 0.07013058168203817,
"grad_norm": 0.2629912197589874,
"learning_rate": 9.600000000000001e-06,
"loss": 1.8998,
"step": 48
},
{
"epoch": 0.07159163546708064,
"grad_norm": 0.22671160101890564,
"learning_rate": 9.800000000000001e-06,
"loss": 1.8634,
"step": 49
},
{
"epoch": 0.07305268925212309,
"grad_norm": 0.22378858923912048,
"learning_rate": 1e-05,
"loss": 1.9038,
"step": 50
},
{
"epoch": 0.07451374303716556,
"grad_norm": 0.25769534707069397,
"learning_rate": 1.02e-05,
"loss": 1.8324,
"step": 51
},
{
"epoch": 0.07597479682220802,
"grad_norm": 0.22694693505764008,
"learning_rate": 1.04e-05,
"loss": 1.8374,
"step": 52
},
{
"epoch": 0.07743585060725047,
"grad_norm": 0.23865583539009094,
"learning_rate": 1.0600000000000002e-05,
"loss": 1.9129,
"step": 53
},
{
"epoch": 0.07889690439229294,
"grad_norm": 0.23314256966114044,
"learning_rate": 1.0800000000000002e-05,
"loss": 1.8512,
"step": 54
},
{
"epoch": 0.0803579581773354,
"grad_norm": 0.2111833393573761,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.8608,
"step": 55
},
{
"epoch": 0.08181901196237787,
"grad_norm": 0.24742205440998077,
"learning_rate": 1.1200000000000001e-05,
"loss": 1.9129,
"step": 56
},
{
"epoch": 0.08328006574742032,
"grad_norm": 0.2268109768629074,
"learning_rate": 1.14e-05,
"loss": 1.7996,
"step": 57
},
{
"epoch": 0.08474111953246279,
"grad_norm": 0.24065515398979187,
"learning_rate": 1.16e-05,
"loss": 1.9203,
"step": 58
},
{
"epoch": 0.08620217331750525,
"grad_norm": 0.23937389254570007,
"learning_rate": 1.18e-05,
"loss": 1.8845,
"step": 59
},
{
"epoch": 0.08766322710254772,
"grad_norm": 0.22344107925891876,
"learning_rate": 1.2e-05,
"loss": 1.94,
"step": 60
},
{
"epoch": 0.08912428088759017,
"grad_norm": 0.24668040871620178,
"learning_rate": 1.22e-05,
"loss": 1.9473,
"step": 61
},
{
"epoch": 0.09058533467263263,
"grad_norm": 0.21312135457992554,
"learning_rate": 1.2400000000000002e-05,
"loss": 1.8225,
"step": 62
},
{
"epoch": 0.0920463884576751,
"grad_norm": 0.2296803593635559,
"learning_rate": 1.2600000000000001e-05,
"loss": 1.7675,
"step": 63
},
{
"epoch": 0.09350744224271756,
"grad_norm": 0.20073962211608887,
"learning_rate": 1.2800000000000001e-05,
"loss": 1.7844,
"step": 64
},
{
"epoch": 0.09496849602776002,
"grad_norm": 0.23866504430770874,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.7766,
"step": 65
},
{
"epoch": 0.09642954981280248,
"grad_norm": 0.24550433456897736,
"learning_rate": 1.3200000000000002e-05,
"loss": 1.9283,
"step": 66
},
{
"epoch": 0.09789060359784495,
"grad_norm": 0.24073684215545654,
"learning_rate": 1.3400000000000002e-05,
"loss": 1.841,
"step": 67
},
{
"epoch": 0.09935165738288741,
"grad_norm": 0.21318458020687103,
"learning_rate": 1.3600000000000002e-05,
"loss": 1.7465,
"step": 68
},
{
"epoch": 0.10081271116792986,
"grad_norm": 0.2440112829208374,
"learning_rate": 1.38e-05,
"loss": 1.8503,
"step": 69
},
{
"epoch": 0.10227376495297233,
"grad_norm": 0.21730957925319672,
"learning_rate": 1.4e-05,
"loss": 1.7624,
"step": 70
},
{
"epoch": 0.1037348187380148,
"grad_norm": 0.22476676106452942,
"learning_rate": 1.4200000000000001e-05,
"loss": 1.8127,
"step": 71
},
{
"epoch": 0.10519587252305726,
"grad_norm": 0.2405499368906021,
"learning_rate": 1.4400000000000001e-05,
"loss": 1.7755,
"step": 72
},
{
"epoch": 0.10665692630809971,
"grad_norm": 0.24996110796928406,
"learning_rate": 1.46e-05,
"loss": 1.841,
"step": 73
},
{
"epoch": 0.10811798009314218,
"grad_norm": 0.26147621870040894,
"learning_rate": 1.48e-05,
"loss": 1.7769,
"step": 74
},
{
"epoch": 0.10957903387818464,
"grad_norm": 0.23422400653362274,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.7561,
"step": 75
},
{
"epoch": 0.11104008766322711,
"grad_norm": 0.24707835912704468,
"learning_rate": 1.5200000000000002e-05,
"loss": 1.7038,
"step": 76
},
{
"epoch": 0.11250114144826956,
"grad_norm": 0.25473567843437195,
"learning_rate": 1.54e-05,
"loss": 1.7496,
"step": 77
},
{
"epoch": 0.11396219523331202,
"grad_norm": 0.3016836941242218,
"learning_rate": 1.5600000000000003e-05,
"loss": 1.7323,
"step": 78
},
{
"epoch": 0.11542324901835449,
"grad_norm": 0.26107528805732727,
"learning_rate": 1.58e-05,
"loss": 1.7511,
"step": 79
},
{
"epoch": 0.11688430280339696,
"grad_norm": 0.3029772639274597,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.691,
"step": 80
},
{
"epoch": 0.11834535658843941,
"grad_norm": 0.30675315856933594,
"learning_rate": 1.62e-05,
"loss": 1.6696,
"step": 81
},
{
"epoch": 0.11980641037348187,
"grad_norm": 0.3136438727378845,
"learning_rate": 1.64e-05,
"loss": 1.6624,
"step": 82
},
{
"epoch": 0.12126746415852434,
"grad_norm": 0.32071617245674133,
"learning_rate": 1.66e-05,
"loss": 1.6458,
"step": 83
},
{
"epoch": 0.1227285179435668,
"grad_norm": 0.3253510594367981,
"learning_rate": 1.6800000000000002e-05,
"loss": 1.6169,
"step": 84
},
{
"epoch": 0.12418957172860925,
"grad_norm": 0.3446858525276184,
"learning_rate": 1.7e-05,
"loss": 1.6721,
"step": 85
},
{
"epoch": 0.12565062551365172,
"grad_norm": 0.33179470896720886,
"learning_rate": 1.72e-05,
"loss": 1.578,
"step": 86
},
{
"epoch": 0.12711167929869419,
"grad_norm": 0.3791605830192566,
"learning_rate": 1.7400000000000003e-05,
"loss": 1.6055,
"step": 87
},
{
"epoch": 0.12857273308373665,
"grad_norm": 0.5245212912559509,
"learning_rate": 1.76e-05,
"loss": 1.626,
"step": 88
},
{
"epoch": 0.13003378686877912,
"grad_norm": 0.43215855956077576,
"learning_rate": 1.7800000000000002e-05,
"loss": 1.6177,
"step": 89
},
{
"epoch": 0.13149484065382158,
"grad_norm": 0.4050828516483307,
"learning_rate": 1.8e-05,
"loss": 1.4903,
"step": 90
},
{
"epoch": 0.13295589443886402,
"grad_norm": 0.399501234292984,
"learning_rate": 1.8200000000000002e-05,
"loss": 1.6079,
"step": 91
},
{
"epoch": 0.13441694822390649,
"grad_norm": 0.439622700214386,
"learning_rate": 1.8400000000000003e-05,
"loss": 1.5405,
"step": 92
},
{
"epoch": 0.13587800200894895,
"grad_norm": 0.4368193447589874,
"learning_rate": 1.86e-05,
"loss": 1.415,
"step": 93
},
{
"epoch": 0.13733905579399142,
"grad_norm": 0.3644118010997772,
"learning_rate": 1.88e-05,
"loss": 1.525,
"step": 94
},
{
"epoch": 0.13880010957903388,
"grad_norm": 0.3868708312511444,
"learning_rate": 1.9e-05,
"loss": 1.4903,
"step": 95
},
{
"epoch": 0.14026116336407635,
"grad_norm": 0.43034952878952026,
"learning_rate": 1.9200000000000003e-05,
"loss": 1.4605,
"step": 96
},
{
"epoch": 0.1417222171491188,
"grad_norm": 0.4087560772895813,
"learning_rate": 1.94e-05,
"loss": 1.3544,
"step": 97
},
{
"epoch": 0.14318327093416128,
"grad_norm": 0.29801666736602783,
"learning_rate": 1.9600000000000002e-05,
"loss": 1.4098,
"step": 98
},
{
"epoch": 0.14464432471920372,
"grad_norm": 0.275905966758728,
"learning_rate": 1.98e-05,
"loss": 1.4732,
"step": 99
},
{
"epoch": 0.14610537850424618,
"grad_norm": 0.32271912693977356,
"learning_rate": 2e-05,
"loss": 1.4156,
"step": 100
},
{
"epoch": 0.14756643228928865,
"grad_norm": 0.3191397190093994,
"learning_rate": 1.9965753424657538e-05,
"loss": 1.3254,
"step": 101
},
{
"epoch": 0.1490274860743311,
"grad_norm": 0.26260653138160706,
"learning_rate": 1.993150684931507e-05,
"loss": 1.3877,
"step": 102
},
{
"epoch": 0.15048853985937358,
"grad_norm": 0.2782766819000244,
"learning_rate": 1.9897260273972604e-05,
"loss": 1.3683,
"step": 103
},
{
"epoch": 0.15194959364441604,
"grad_norm": 0.2510565221309662,
"learning_rate": 1.9863013698630137e-05,
"loss": 1.3996,
"step": 104
},
{
"epoch": 0.1534106474294585,
"grad_norm": 0.2523151934146881,
"learning_rate": 1.9828767123287674e-05,
"loss": 1.3192,
"step": 105
},
{
"epoch": 0.15487170121450095,
"grad_norm": 0.20559488236904144,
"learning_rate": 1.9794520547945207e-05,
"loss": 1.2096,
"step": 106
},
{
"epoch": 0.1563327549995434,
"grad_norm": 0.17568816244602203,
"learning_rate": 1.9760273972602743e-05,
"loss": 1.3795,
"step": 107
},
{
"epoch": 0.15779380878458588,
"grad_norm": 0.1778278350830078,
"learning_rate": 1.9726027397260276e-05,
"loss": 1.3146,
"step": 108
},
{
"epoch": 0.15925486256962834,
"grad_norm": 0.18488670885562897,
"learning_rate": 1.969178082191781e-05,
"loss": 1.4105,
"step": 109
},
{
"epoch": 0.1607159163546708,
"grad_norm": 0.1593291312456131,
"learning_rate": 1.9657534246575346e-05,
"loss": 1.3054,
"step": 110
},
{
"epoch": 0.16217697013971327,
"grad_norm": 0.14311783015727997,
"learning_rate": 1.962328767123288e-05,
"loss": 1.3985,
"step": 111
},
{
"epoch": 0.16363802392475574,
"grad_norm": 0.14948627352714539,
"learning_rate": 1.9589041095890412e-05,
"loss": 1.3395,
"step": 112
},
{
"epoch": 0.1650990777097982,
"grad_norm": 0.14075608551502228,
"learning_rate": 1.9554794520547945e-05,
"loss": 1.3868,
"step": 113
},
{
"epoch": 0.16656013149484064,
"grad_norm": 0.14439420402050018,
"learning_rate": 1.952054794520548e-05,
"loss": 1.2985,
"step": 114
},
{
"epoch": 0.1680211852798831,
"grad_norm": 0.13425147533416748,
"learning_rate": 1.9486301369863014e-05,
"loss": 1.3855,
"step": 115
},
{
"epoch": 0.16948223906492557,
"grad_norm": 0.1291724145412445,
"learning_rate": 1.945205479452055e-05,
"loss": 1.2942,
"step": 116
},
{
"epoch": 0.17094329284996804,
"grad_norm": 0.1350926160812378,
"learning_rate": 1.9417808219178084e-05,
"loss": 1.3649,
"step": 117
},
{
"epoch": 0.1724043466350105,
"grad_norm": 0.1309756338596344,
"learning_rate": 1.9383561643835617e-05,
"loss": 1.3241,
"step": 118
},
{
"epoch": 0.17386540042005297,
"grad_norm": 0.12676255404949188,
"learning_rate": 1.9349315068493153e-05,
"loss": 1.3773,
"step": 119
},
{
"epoch": 0.17532645420509543,
"grad_norm": 0.1361505538225174,
"learning_rate": 1.9315068493150686e-05,
"loss": 1.3259,
"step": 120
},
{
"epoch": 0.1767875079901379,
"grad_norm": 0.1225372925400734,
"learning_rate": 1.9280821917808223e-05,
"loss": 1.2854,
"step": 121
},
{
"epoch": 0.17824856177518034,
"grad_norm": 0.12647689878940582,
"learning_rate": 1.9246575342465756e-05,
"loss": 1.2741,
"step": 122
},
{
"epoch": 0.1797096155602228,
"grad_norm": 0.12492359429597855,
"learning_rate": 1.921232876712329e-05,
"loss": 1.2728,
"step": 123
},
{
"epoch": 0.18117066934526527,
"grad_norm": 0.1245495080947876,
"learning_rate": 1.9178082191780822e-05,
"loss": 1.2829,
"step": 124
},
{
"epoch": 0.18263172313030773,
"grad_norm": 0.12087871879339218,
"learning_rate": 1.9143835616438358e-05,
"loss": 1.3673,
"step": 125
},
{
"epoch": 0.1840927769153502,
"grad_norm": 0.13881978392601013,
"learning_rate": 1.910958904109589e-05,
"loss": 1.2749,
"step": 126
},
{
"epoch": 0.18555383070039266,
"grad_norm": 0.12226665765047073,
"learning_rate": 1.9075342465753424e-05,
"loss": 1.3216,
"step": 127
},
{
"epoch": 0.18701488448543513,
"grad_norm": 0.12877057492733002,
"learning_rate": 1.904109589041096e-05,
"loss": 1.3632,
"step": 128
},
{
"epoch": 0.1884759382704776,
"grad_norm": 0.13042791187763214,
"learning_rate": 1.9006849315068494e-05,
"loss": 1.3087,
"step": 129
},
{
"epoch": 0.18993699205552003,
"grad_norm": 0.1289220005273819,
"learning_rate": 1.897260273972603e-05,
"loss": 1.3569,
"step": 130
},
{
"epoch": 0.1913980458405625,
"grad_norm": 0.12027924507856369,
"learning_rate": 1.8938356164383563e-05,
"loss": 1.3487,
"step": 131
},
{
"epoch": 0.19285909962560496,
"grad_norm": 0.13009122014045715,
"learning_rate": 1.8904109589041096e-05,
"loss": 1.2639,
"step": 132
},
{
"epoch": 0.19432015341064743,
"grad_norm": 0.13321325182914734,
"learning_rate": 1.8869863013698633e-05,
"loss": 1.2982,
"step": 133
},
{
"epoch": 0.1957812071956899,
"grad_norm": 0.1279006004333496,
"learning_rate": 1.8835616438356166e-05,
"loss": 1.3291,
"step": 134
},
{
"epoch": 0.19724226098073236,
"grad_norm": 0.13129518926143646,
"learning_rate": 1.8801369863013702e-05,
"loss": 1.2805,
"step": 135
},
{
"epoch": 0.19870331476577482,
"grad_norm": 0.1193300113081932,
"learning_rate": 1.8767123287671235e-05,
"loss": 1.3173,
"step": 136
},
{
"epoch": 0.2001643685508173,
"grad_norm": 0.12838037312030792,
"learning_rate": 1.8732876712328768e-05,
"loss": 1.3416,
"step": 137
},
{
"epoch": 0.20162542233585973,
"grad_norm": 0.1269877851009369,
"learning_rate": 1.86986301369863e-05,
"loss": 1.295,
"step": 138
},
{
"epoch": 0.2030864761209022,
"grad_norm": 0.13122180104255676,
"learning_rate": 1.8664383561643838e-05,
"loss": 1.293,
"step": 139
},
{
"epoch": 0.20454752990594466,
"grad_norm": 0.1385333091020584,
"learning_rate": 1.863013698630137e-05,
"loss": 1.2237,
"step": 140
},
{
"epoch": 0.20600858369098712,
"grad_norm": 0.1442401111125946,
"learning_rate": 1.8595890410958907e-05,
"loss": 1.2833,
"step": 141
},
{
"epoch": 0.2074696374760296,
"grad_norm": 0.1236981600522995,
"learning_rate": 1.856164383561644e-05,
"loss": 1.3252,
"step": 142
},
{
"epoch": 0.20893069126107205,
"grad_norm": 0.13414394855499268,
"learning_rate": 1.8527397260273973e-05,
"loss": 1.4099,
"step": 143
},
{
"epoch": 0.21039174504611452,
"grad_norm": 0.1376720666885376,
"learning_rate": 1.849315068493151e-05,
"loss": 1.3735,
"step": 144
},
{
"epoch": 0.21185279883115699,
"grad_norm": 0.13452522456645966,
"learning_rate": 1.8458904109589043e-05,
"loss": 1.2442,
"step": 145
},
{
"epoch": 0.21331385261619942,
"grad_norm": 0.12783923745155334,
"learning_rate": 1.8424657534246576e-05,
"loss": 1.3028,
"step": 146
},
{
"epoch": 0.2147749064012419,
"grad_norm": 0.1320268213748932,
"learning_rate": 1.839041095890411e-05,
"loss": 1.2906,
"step": 147
},
{
"epoch": 0.21623596018628435,
"grad_norm": 0.14116773009300232,
"learning_rate": 1.8356164383561645e-05,
"loss": 1.3724,
"step": 148
},
{
"epoch": 0.21769701397132682,
"grad_norm": 0.13176654279232025,
"learning_rate": 1.8321917808219182e-05,
"loss": 1.2719,
"step": 149
},
{
"epoch": 0.21915806775636928,
"grad_norm": 0.13379769027233124,
"learning_rate": 1.8287671232876715e-05,
"loss": 1.3286,
"step": 150
},
{
"epoch": 0.22061912154141175,
"grad_norm": 0.13172045350074768,
"learning_rate": 1.8253424657534248e-05,
"loss": 1.3104,
"step": 151
},
{
"epoch": 0.22208017532645422,
"grad_norm": 0.14471982419490814,
"learning_rate": 1.821917808219178e-05,
"loss": 1.3111,
"step": 152
},
{
"epoch": 0.22354122911149665,
"grad_norm": 0.14093175530433655,
"learning_rate": 1.8184931506849317e-05,
"loss": 1.2696,
"step": 153
},
{
"epoch": 0.22500228289653912,
"grad_norm": 0.14340919256210327,
"learning_rate": 1.815068493150685e-05,
"loss": 1.3105,
"step": 154
},
{
"epoch": 0.22646333668158158,
"grad_norm": 0.15136584639549255,
"learning_rate": 1.8116438356164387e-05,
"loss": 1.1514,
"step": 155
},
{
"epoch": 0.22792439046662405,
"grad_norm": 0.16463331878185272,
"learning_rate": 1.808219178082192e-05,
"loss": 1.2292,
"step": 156
},
{
"epoch": 0.22938544425166651,
"grad_norm": 0.14684943854808807,
"learning_rate": 1.8047945205479453e-05,
"loss": 1.1744,
"step": 157
},
{
"epoch": 0.23084649803670898,
"grad_norm": 0.17171254754066467,
"learning_rate": 1.801369863013699e-05,
"loss": 1.2522,
"step": 158
},
{
"epoch": 0.23230755182175145,
"grad_norm": 0.1535484492778778,
"learning_rate": 1.7979452054794522e-05,
"loss": 1.3086,
"step": 159
},
{
"epoch": 0.2337686056067939,
"grad_norm": 0.15115784108638763,
"learning_rate": 1.7945205479452055e-05,
"loss": 1.3126,
"step": 160
},
{
"epoch": 0.23522965939183635,
"grad_norm": 0.15851254761219025,
"learning_rate": 1.791095890410959e-05,
"loss": 1.3022,
"step": 161
},
{
"epoch": 0.23669071317687881,
"grad_norm": 0.16716252267360687,
"learning_rate": 1.7876712328767125e-05,
"loss": 1.2339,
"step": 162
},
{
"epoch": 0.23815176696192128,
"grad_norm": 0.1609048694372177,
"learning_rate": 1.7842465753424658e-05,
"loss": 1.3374,
"step": 163
},
{
"epoch": 0.23961282074696375,
"grad_norm": 0.17205393314361572,
"learning_rate": 1.7808219178082194e-05,
"loss": 1.2043,
"step": 164
},
{
"epoch": 0.2410738745320062,
"grad_norm": 0.17497386038303375,
"learning_rate": 1.7773972602739727e-05,
"loss": 1.2267,
"step": 165
},
{
"epoch": 0.24253492831704868,
"grad_norm": 0.17982399463653564,
"learning_rate": 1.773972602739726e-05,
"loss": 1.2363,
"step": 166
},
{
"epoch": 0.24399598210209114,
"grad_norm": 0.17415454983711243,
"learning_rate": 1.7705479452054797e-05,
"loss": 1.2339,
"step": 167
},
{
"epoch": 0.2454570358871336,
"grad_norm": 0.17761662602424622,
"learning_rate": 1.767123287671233e-05,
"loss": 1.2549,
"step": 168
},
{
"epoch": 0.24691808967217604,
"grad_norm": 0.17029732465744019,
"learning_rate": 1.7636986301369866e-05,
"loss": 1.2175,
"step": 169
},
{
"epoch": 0.2483791434572185,
"grad_norm": 0.1831396073102951,
"learning_rate": 1.76027397260274e-05,
"loss": 1.2975,
"step": 170
},
{
"epoch": 0.24984019724226098,
"grad_norm": 0.1648183912038803,
"learning_rate": 1.7568493150684932e-05,
"loss": 1.317,
"step": 171
},
{
"epoch": 0.25130125102730344,
"grad_norm": 0.19559577107429504,
"learning_rate": 1.7534246575342465e-05,
"loss": 1.2482,
"step": 172
},
{
"epoch": 0.2527623048123459,
"grad_norm": 0.17486748099327087,
"learning_rate": 1.7500000000000002e-05,
"loss": 1.2638,
"step": 173
},
{
"epoch": 0.25422335859738837,
"grad_norm": 0.18816767632961273,
"learning_rate": 1.7465753424657538e-05,
"loss": 1.2739,
"step": 174
},
{
"epoch": 0.25568441238243084,
"grad_norm": 0.1921810507774353,
"learning_rate": 1.743150684931507e-05,
"loss": 1.2028,
"step": 175
},
{
"epoch": 0.2571454661674733,
"grad_norm": 0.20229558646678925,
"learning_rate": 1.7397260273972604e-05,
"loss": 1.2518,
"step": 176
},
{
"epoch": 0.25860651995251577,
"grad_norm": 0.21454092860221863,
"learning_rate": 1.7363013698630137e-05,
"loss": 1.2257,
"step": 177
},
{
"epoch": 0.26006757373755823,
"grad_norm": 0.20349366962909698,
"learning_rate": 1.7328767123287674e-05,
"loss": 1.229,
"step": 178
},
{
"epoch": 0.2615286275226007,
"grad_norm": 0.22348977625370026,
"learning_rate": 1.7294520547945207e-05,
"loss": 1.3047,
"step": 179
},
{
"epoch": 0.26298968130764316,
"grad_norm": 0.18413174152374268,
"learning_rate": 1.726027397260274e-05,
"loss": 1.2372,
"step": 180
},
{
"epoch": 0.2644507350926856,
"grad_norm": 0.22073839604854584,
"learning_rate": 1.7226027397260273e-05,
"loss": 1.2719,
"step": 181
},
{
"epoch": 0.26591178887772804,
"grad_norm": 0.25906509160995483,
"learning_rate": 1.719178082191781e-05,
"loss": 1.2132,
"step": 182
},
{
"epoch": 0.2673728426627705,
"grad_norm": 0.22006724774837494,
"learning_rate": 1.7157534246575346e-05,
"loss": 1.2595,
"step": 183
},
{
"epoch": 0.26883389644781297,
"grad_norm": 0.2628309428691864,
"learning_rate": 1.712328767123288e-05,
"loss": 1.1812,
"step": 184
},
{
"epoch": 0.27029495023285544,
"grad_norm": 0.21583111584186554,
"learning_rate": 1.7089041095890412e-05,
"loss": 1.2631,
"step": 185
},
{
"epoch": 0.2717560040178979,
"grad_norm": 0.19774451851844788,
"learning_rate": 1.7054794520547945e-05,
"loss": 1.2511,
"step": 186
},
{
"epoch": 0.27321705780294037,
"grad_norm": 0.199305459856987,
"learning_rate": 1.702054794520548e-05,
"loss": 1.2836,
"step": 187
},
{
"epoch": 0.27467811158798283,
"grad_norm": 0.17964106798171997,
"learning_rate": 1.6986301369863014e-05,
"loss": 1.2784,
"step": 188
},
{
"epoch": 0.2761391653730253,
"grad_norm": 0.15635524690151215,
"learning_rate": 1.695205479452055e-05,
"loss": 1.2959,
"step": 189
},
{
"epoch": 0.27760021915806776,
"grad_norm": 0.14683344960212708,
"learning_rate": 1.6917808219178084e-05,
"loss": 1.2453,
"step": 190
},
{
"epoch": 0.27906127294311023,
"grad_norm": 0.1619580239057541,
"learning_rate": 1.6883561643835617e-05,
"loss": 1.2602,
"step": 191
},
{
"epoch": 0.2805223267281527,
"grad_norm": 0.19470493495464325,
"learning_rate": 1.6849315068493153e-05,
"loss": 1.1052,
"step": 192
},
{
"epoch": 0.28198338051319516,
"grad_norm": 0.17526264488697052,
"learning_rate": 1.6815068493150686e-05,
"loss": 1.2553,
"step": 193
},
{
"epoch": 0.2834444342982376,
"grad_norm": 0.1810723841190338,
"learning_rate": 1.678082191780822e-05,
"loss": 1.2121,
"step": 194
},
{
"epoch": 0.2849054880832801,
"grad_norm": 0.16387374699115753,
"learning_rate": 1.6746575342465753e-05,
"loss": 1.1702,
"step": 195
},
{
"epoch": 0.28636654186832255,
"grad_norm": 0.1537161022424698,
"learning_rate": 1.671232876712329e-05,
"loss": 1.1865,
"step": 196
},
{
"epoch": 0.28782759565336496,
"grad_norm": 0.13615332543849945,
"learning_rate": 1.6678082191780822e-05,
"loss": 1.2578,
"step": 197
},
{
"epoch": 0.28928864943840743,
"grad_norm": 0.13642196357250214,
"learning_rate": 1.664383561643836e-05,
"loss": 1.1813,
"step": 198
},
{
"epoch": 0.2907497032234499,
"grad_norm": 0.1444728523492813,
"learning_rate": 1.660958904109589e-05,
"loss": 1.2815,
"step": 199
},
{
"epoch": 0.29221075700849236,
"grad_norm": 0.13030050694942474,
"learning_rate": 1.6575342465753425e-05,
"loss": 1.2848,
"step": 200
},
{
"epoch": 0.2936718107935348,
"grad_norm": 0.13471786677837372,
"learning_rate": 1.654109589041096e-05,
"loss": 1.1634,
"step": 201
},
{
"epoch": 0.2951328645785773,
"grad_norm": 0.11596754193305969,
"learning_rate": 1.6506849315068494e-05,
"loss": 1.2522,
"step": 202
},
{
"epoch": 0.29659391836361976,
"grad_norm": 0.11978977173566818,
"learning_rate": 1.647260273972603e-05,
"loss": 1.2585,
"step": 203
},
{
"epoch": 0.2980549721486622,
"grad_norm": 0.11857204139232635,
"learning_rate": 1.6438356164383563e-05,
"loss": 1.1372,
"step": 204
},
{
"epoch": 0.2995160259337047,
"grad_norm": 0.12098690867424011,
"learning_rate": 1.6404109589041096e-05,
"loss": 1.1391,
"step": 205
},
{
"epoch": 0.30097707971874715,
"grad_norm": 0.12197306752204895,
"learning_rate": 1.6369863013698633e-05,
"loss": 1.2073,
"step": 206
}
],
"logging_steps": 1,
"max_steps": 684,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.3075689748657357e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}