fengyao1909's picture
Upload folder using huggingface_hub
95c6faa verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9033423667570009,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0018066847335140017,
"grad_norm": 2.6597820350894357,
"learning_rate": 0.0,
"loss": 0.8251,
"step": 1
},
{
"epoch": 0.0036133694670280035,
"grad_norm": 2.7266510344811494,
"learning_rate": 1.0714285714285714e-06,
"loss": 0.8284,
"step": 2
},
{
"epoch": 0.005420054200542005,
"grad_norm": 2.7200407943823968,
"learning_rate": 2.1428571428571427e-06,
"loss": 0.8429,
"step": 3
},
{
"epoch": 0.007226738934056007,
"grad_norm": 2.6398267415203076,
"learning_rate": 3.2142857142857143e-06,
"loss": 0.8381,
"step": 4
},
{
"epoch": 0.009033423667570008,
"grad_norm": 2.450058379558589,
"learning_rate": 4.2857142857142855e-06,
"loss": 0.8245,
"step": 5
},
{
"epoch": 0.01084010840108401,
"grad_norm": 1.9536840033460428,
"learning_rate": 5.357142857142857e-06,
"loss": 0.814,
"step": 6
},
{
"epoch": 0.012646793134598013,
"grad_norm": 1.2180340367347295,
"learning_rate": 6.428571428571429e-06,
"loss": 0.7845,
"step": 7
},
{
"epoch": 0.014453477868112014,
"grad_norm": 1.1514973199014618,
"learning_rate": 7.5e-06,
"loss": 0.7874,
"step": 8
},
{
"epoch": 0.016260162601626018,
"grad_norm": 1.1427251731602237,
"learning_rate": 8.571428571428571e-06,
"loss": 0.7793,
"step": 9
},
{
"epoch": 0.018066847335140017,
"grad_norm": 2.4537001853666673,
"learning_rate": 9.642857142857144e-06,
"loss": 0.7624,
"step": 10
},
{
"epoch": 0.01987353206865402,
"grad_norm": 2.474412722550665,
"learning_rate": 1.0714285714285714e-05,
"loss": 0.7491,
"step": 11
},
{
"epoch": 0.02168021680216802,
"grad_norm": 2.333456673377541,
"learning_rate": 1.1785714285714286e-05,
"loss": 0.762,
"step": 12
},
{
"epoch": 0.023486901535682024,
"grad_norm": 1.6274020508818596,
"learning_rate": 1.2857142857142857e-05,
"loss": 0.7368,
"step": 13
},
{
"epoch": 0.025293586269196026,
"grad_norm": 1.563869927563279,
"learning_rate": 1.3928571428571429e-05,
"loss": 0.7378,
"step": 14
},
{
"epoch": 0.02710027100271003,
"grad_norm": 1.253626680340628,
"learning_rate": 1.5e-05,
"loss": 0.7271,
"step": 15
},
{
"epoch": 0.028906955736224028,
"grad_norm": 0.9176330164857595,
"learning_rate": 1.6071428571428572e-05,
"loss": 0.7131,
"step": 16
},
{
"epoch": 0.03071364046973803,
"grad_norm": 0.7185343991261351,
"learning_rate": 1.7142857142857142e-05,
"loss": 0.7131,
"step": 17
},
{
"epoch": 0.032520325203252036,
"grad_norm": 0.7884609645105337,
"learning_rate": 1.8214285714285712e-05,
"loss": 0.7045,
"step": 18
},
{
"epoch": 0.03432700993676603,
"grad_norm": 0.7399830971167167,
"learning_rate": 1.928571428571429e-05,
"loss": 0.6995,
"step": 19
},
{
"epoch": 0.036133694670280034,
"grad_norm": 0.7376328500886337,
"learning_rate": 2.0357142857142858e-05,
"loss": 0.6779,
"step": 20
},
{
"epoch": 0.037940379403794036,
"grad_norm": 0.6439873145292982,
"learning_rate": 2.1428571428571428e-05,
"loss": 0.6834,
"step": 21
},
{
"epoch": 0.03974706413730804,
"grad_norm": 0.5790542088592184,
"learning_rate": 2.25e-05,
"loss": 0.6721,
"step": 22
},
{
"epoch": 0.04155374887082204,
"grad_norm": 0.5191304250088061,
"learning_rate": 2.357142857142857e-05,
"loss": 0.6707,
"step": 23
},
{
"epoch": 0.04336043360433604,
"grad_norm": 0.4488946670945292,
"learning_rate": 2.464285714285714e-05,
"loss": 0.676,
"step": 24
},
{
"epoch": 0.045167118337850046,
"grad_norm": 0.4798647764154148,
"learning_rate": 2.5714285714285714e-05,
"loss": 0.6585,
"step": 25
},
{
"epoch": 0.04697380307136405,
"grad_norm": 0.4204330566493729,
"learning_rate": 2.6785714285714288e-05,
"loss": 0.673,
"step": 26
},
{
"epoch": 0.04878048780487805,
"grad_norm": 0.47130112684574876,
"learning_rate": 2.7857142857142858e-05,
"loss": 0.6516,
"step": 27
},
{
"epoch": 0.05058717253839205,
"grad_norm": 0.4362815754533529,
"learning_rate": 2.892857142857143e-05,
"loss": 0.6545,
"step": 28
},
{
"epoch": 0.052393857271906055,
"grad_norm": 0.43822648560890193,
"learning_rate": 3e-05,
"loss": 0.6647,
"step": 29
},
{
"epoch": 0.05420054200542006,
"grad_norm": 0.3853311574389301,
"learning_rate": 2.9999731440137413e-05,
"loss": 0.6644,
"step": 30
},
{
"epoch": 0.05600722673893405,
"grad_norm": 0.4221785516753897,
"learning_rate": 2.9998925770166232e-05,
"loss": 0.6534,
"step": 31
},
{
"epoch": 0.057813911472448055,
"grad_norm": 0.3980570059327311,
"learning_rate": 2.9997583018935875e-05,
"loss": 0.6416,
"step": 32
},
{
"epoch": 0.05962059620596206,
"grad_norm": 0.35571676272289743,
"learning_rate": 2.9995703234527553e-05,
"loss": 0.6513,
"step": 33
},
{
"epoch": 0.06142728093947606,
"grad_norm": 0.38024957472516396,
"learning_rate": 2.999328648425255e-05,
"loss": 0.6385,
"step": 34
},
{
"epoch": 0.06323396567299007,
"grad_norm": 0.2924858728569485,
"learning_rate": 2.999033285464982e-05,
"loss": 0.644,
"step": 35
},
{
"epoch": 0.06504065040650407,
"grad_norm": 0.3482798299572746,
"learning_rate": 2.9986842451482876e-05,
"loss": 0.6387,
"step": 36
},
{
"epoch": 0.06684733514001806,
"grad_norm": 0.3705337140725527,
"learning_rate": 2.9982815399736008e-05,
"loss": 0.6432,
"step": 37
},
{
"epoch": 0.06865401987353206,
"grad_norm": 0.3364721163164359,
"learning_rate": 2.9978251843609816e-05,
"loss": 0.6351,
"step": 38
},
{
"epoch": 0.07046070460704607,
"grad_norm": 0.3272631660096153,
"learning_rate": 2.9973151946516027e-05,
"loss": 0.6364,
"step": 39
},
{
"epoch": 0.07226738934056007,
"grad_norm": 0.29708127282462954,
"learning_rate": 2.996751589107167e-05,
"loss": 0.6252,
"step": 40
},
{
"epoch": 0.07407407407407407,
"grad_norm": 0.24921077158970448,
"learning_rate": 2.9961343879092512e-05,
"loss": 0.6308,
"step": 41
},
{
"epoch": 0.07588075880758807,
"grad_norm": 0.3479569257927118,
"learning_rate": 2.9954636131585845e-05,
"loss": 0.6234,
"step": 42
},
{
"epoch": 0.07768744354110207,
"grad_norm": 0.28917511643628596,
"learning_rate": 2.9947392888742566e-05,
"loss": 0.6233,
"step": 43
},
{
"epoch": 0.07949412827461608,
"grad_norm": 0.34737822266968965,
"learning_rate": 2.993961440992859e-05,
"loss": 0.6171,
"step": 44
},
{
"epoch": 0.08130081300813008,
"grad_norm": 0.3247689228102166,
"learning_rate": 2.993130097367553e-05,
"loss": 0.6238,
"step": 45
},
{
"epoch": 0.08310749774164408,
"grad_norm": 0.30719902123424325,
"learning_rate": 2.9922452877670775e-05,
"loss": 0.6252,
"step": 46
},
{
"epoch": 0.08491418247515808,
"grad_norm": 0.3175141153740525,
"learning_rate": 2.991307043874677e-05,
"loss": 0.6281,
"step": 47
},
{
"epoch": 0.08672086720867209,
"grad_norm": 0.31244488771705314,
"learning_rate": 2.9903153992869734e-05,
"loss": 0.6148,
"step": 48
},
{
"epoch": 0.08852755194218609,
"grad_norm": 0.3429131319420423,
"learning_rate": 2.989270389512756e-05,
"loss": 0.6211,
"step": 49
},
{
"epoch": 0.09033423667570009,
"grad_norm": 0.3104062918234721,
"learning_rate": 2.988172051971717e-05,
"loss": 0.6204,
"step": 50
},
{
"epoch": 0.0921409214092141,
"grad_norm": 0.31461103786584654,
"learning_rate": 2.9870204259931062e-05,
"loss": 0.6097,
"step": 51
},
{
"epoch": 0.0939476061427281,
"grad_norm": 0.3151625720082357,
"learning_rate": 2.9858155528143256e-05,
"loss": 0.6268,
"step": 52
},
{
"epoch": 0.0957542908762421,
"grad_norm": 0.2860126481493585,
"learning_rate": 2.9845574755794522e-05,
"loss": 0.6125,
"step": 53
},
{
"epoch": 0.0975609756097561,
"grad_norm": 0.28841121592431124,
"learning_rate": 2.9832462393376926e-05,
"loss": 0.6018,
"step": 54
},
{
"epoch": 0.0993676603432701,
"grad_norm": 0.23534181927847642,
"learning_rate": 2.9818818910417706e-05,
"loss": 0.6169,
"step": 55
},
{
"epoch": 0.1011743450767841,
"grad_norm": 0.28661471046317555,
"learning_rate": 2.9804644795462437e-05,
"loss": 0.6212,
"step": 56
},
{
"epoch": 0.10298102981029811,
"grad_norm": 0.2443857675436309,
"learning_rate": 2.9789940556057574e-05,
"loss": 0.6065,
"step": 57
},
{
"epoch": 0.10478771454381211,
"grad_norm": 0.292418070185767,
"learning_rate": 2.9774706718732255e-05,
"loss": 0.6152,
"step": 58
},
{
"epoch": 0.10659439927732611,
"grad_norm": 0.24742182455944323,
"learning_rate": 2.9758943828979444e-05,
"loss": 0.6009,
"step": 59
},
{
"epoch": 0.10840108401084012,
"grad_norm": 0.25007211477600044,
"learning_rate": 2.9742652451236414e-05,
"loss": 0.6023,
"step": 60
},
{
"epoch": 0.1102077687443541,
"grad_norm": 0.24539117288225054,
"learning_rate": 2.972583316886451e-05,
"loss": 0.6059,
"step": 61
},
{
"epoch": 0.1120144534778681,
"grad_norm": 0.2544907417129908,
"learning_rate": 2.9708486584128303e-05,
"loss": 0.6107,
"step": 62
},
{
"epoch": 0.11382113821138211,
"grad_norm": 0.25269030392560393,
"learning_rate": 2.9690613318173966e-05,
"loss": 0.611,
"step": 63
},
{
"epoch": 0.11562782294489611,
"grad_norm": 0.20651691272156247,
"learning_rate": 2.9672214011007087e-05,
"loss": 0.6091,
"step": 64
},
{
"epoch": 0.11743450767841011,
"grad_norm": 0.25759031036445135,
"learning_rate": 2.9653289321469715e-05,
"loss": 0.6031,
"step": 65
},
{
"epoch": 0.11924119241192412,
"grad_norm": 0.27004948462624506,
"learning_rate": 2.9633839927216793e-05,
"loss": 0.6061,
"step": 66
},
{
"epoch": 0.12104787714543812,
"grad_norm": 0.23899477664304233,
"learning_rate": 2.9613866524691867e-05,
"loss": 0.5958,
"step": 67
},
{
"epoch": 0.12285456187895212,
"grad_norm": 0.3109356502387666,
"learning_rate": 2.9593369829102173e-05,
"loss": 0.6119,
"step": 68
},
{
"epoch": 0.12466124661246612,
"grad_norm": 0.23973937288759506,
"learning_rate": 2.957235057439301e-05,
"loss": 0.6135,
"step": 69
},
{
"epoch": 0.12646793134598014,
"grad_norm": 0.29402451520285133,
"learning_rate": 2.955080951322147e-05,
"loss": 0.6178,
"step": 70
},
{
"epoch": 0.12827461607949414,
"grad_norm": 0.29085498534508775,
"learning_rate": 2.9528747416929467e-05,
"loss": 0.5907,
"step": 71
},
{
"epoch": 0.13008130081300814,
"grad_norm": 0.25477514255751904,
"learning_rate": 2.9506165075516148e-05,
"loss": 0.6073,
"step": 72
},
{
"epoch": 0.13188798554652212,
"grad_norm": 0.28366229733780235,
"learning_rate": 2.9483063297609577e-05,
"loss": 0.6063,
"step": 73
},
{
"epoch": 0.13369467028003612,
"grad_norm": 0.26317649422081363,
"learning_rate": 2.9459442910437798e-05,
"loss": 0.598,
"step": 74
},
{
"epoch": 0.13550135501355012,
"grad_norm": 0.28039599919104496,
"learning_rate": 2.94353047597992e-05,
"loss": 0.5971,
"step": 75
},
{
"epoch": 0.13730803974706413,
"grad_norm": 0.271745198157929,
"learning_rate": 2.941064971003224e-05,
"loss": 0.593,
"step": 76
},
{
"epoch": 0.13911472448057813,
"grad_norm": 0.24998502389958926,
"learning_rate": 2.9385478643984484e-05,
"loss": 0.5878,
"step": 77
},
{
"epoch": 0.14092140921409213,
"grad_norm": 0.30322559816019845,
"learning_rate": 2.9359792462981007e-05,
"loss": 0.599,
"step": 78
},
{
"epoch": 0.14272809394760613,
"grad_norm": 0.29351194680487536,
"learning_rate": 2.9333592086792113e-05,
"loss": 0.6075,
"step": 79
},
{
"epoch": 0.14453477868112014,
"grad_norm": 0.2670107767188747,
"learning_rate": 2.9306878453600382e-05,
"loss": 0.6161,
"step": 80
},
{
"epoch": 0.14634146341463414,
"grad_norm": 0.2927366904918854,
"learning_rate": 2.9279652519967105e-05,
"loss": 0.6004,
"step": 81
},
{
"epoch": 0.14814814814814814,
"grad_norm": 0.28777141201555767,
"learning_rate": 2.9251915260798024e-05,
"loss": 0.593,
"step": 82
},
{
"epoch": 0.14995483288166214,
"grad_norm": 0.282262421377073,
"learning_rate": 2.9223667669308395e-05,
"loss": 0.6038,
"step": 83
},
{
"epoch": 0.15176151761517614,
"grad_norm": 0.24811154699761442,
"learning_rate": 2.9194910756987464e-05,
"loss": 0.5976,
"step": 84
},
{
"epoch": 0.15356820234869015,
"grad_norm": 0.27670190484589513,
"learning_rate": 2.9165645553562215e-05,
"loss": 0.5997,
"step": 85
},
{
"epoch": 0.15537488708220415,
"grad_norm": 0.24338487756299684,
"learning_rate": 2.9135873106960525e-05,
"loss": 0.5994,
"step": 86
},
{
"epoch": 0.15718157181571815,
"grad_norm": 0.3040191021283788,
"learning_rate": 2.9105594483273603e-05,
"loss": 0.6012,
"step": 87
},
{
"epoch": 0.15898825654923215,
"grad_norm": 0.26703924304748566,
"learning_rate": 2.9074810766717865e-05,
"loss": 0.6058,
"step": 88
},
{
"epoch": 0.16079494128274616,
"grad_norm": 0.2694312104706441,
"learning_rate": 2.904352305959606e-05,
"loss": 0.602,
"step": 89
},
{
"epoch": 0.16260162601626016,
"grad_norm": 0.29517928394037635,
"learning_rate": 2.9011732482257835e-05,
"loss": 0.5944,
"step": 90
},
{
"epoch": 0.16440831074977416,
"grad_norm": 0.25118801401605734,
"learning_rate": 2.89794401730596e-05,
"loss": 0.5923,
"step": 91
},
{
"epoch": 0.16621499548328816,
"grad_norm": 0.3348680034328015,
"learning_rate": 2.894664728832377e-05,
"loss": 0.5958,
"step": 92
},
{
"epoch": 0.16802168021680217,
"grad_norm": 0.25945936645525364,
"learning_rate": 2.8913355002297367e-05,
"loss": 0.6025,
"step": 93
},
{
"epoch": 0.16982836495031617,
"grad_norm": 0.31672412557275315,
"learning_rate": 2.887956450710995e-05,
"loss": 0.602,
"step": 94
},
{
"epoch": 0.17163504968383017,
"grad_norm": 0.2631935513788724,
"learning_rate": 2.8845277012730963e-05,
"loss": 0.5939,
"step": 95
},
{
"epoch": 0.17344173441734417,
"grad_norm": 0.28309967073656406,
"learning_rate": 2.8810493746926364e-05,
"loss": 0.5932,
"step": 96
},
{
"epoch": 0.17524841915085818,
"grad_norm": 0.28939178950900774,
"learning_rate": 2.87752159552147e-05,
"loss": 0.5993,
"step": 97
},
{
"epoch": 0.17705510388437218,
"grad_norm": 0.3021445789644071,
"learning_rate": 2.87394449008225e-05,
"loss": 0.5924,
"step": 98
},
{
"epoch": 0.17886178861788618,
"grad_norm": 0.2648161341085879,
"learning_rate": 2.8703181864639013e-05,
"loss": 0.6058,
"step": 99
},
{
"epoch": 0.18066847335140018,
"grad_norm": 0.28484263640616314,
"learning_rate": 2.8666428145170385e-05,
"loss": 0.5789,
"step": 100
},
{
"epoch": 0.18247515808491419,
"grad_norm": 0.2611846886724786,
"learning_rate": 2.8629185058493116e-05,
"loss": 0.5949,
"step": 101
},
{
"epoch": 0.1842818428184282,
"grad_norm": 0.33149916071305763,
"learning_rate": 2.8591453938206985e-05,
"loss": 0.6134,
"step": 102
},
{
"epoch": 0.1860885275519422,
"grad_norm": 0.28402400837841096,
"learning_rate": 2.8553236135387247e-05,
"loss": 0.5914,
"step": 103
},
{
"epoch": 0.1878952122854562,
"grad_norm": 0.28825320782588004,
"learning_rate": 2.8514533018536286e-05,
"loss": 0.5897,
"step": 104
},
{
"epoch": 0.1897018970189702,
"grad_norm": 0.2901395812522203,
"learning_rate": 2.8475345973534605e-05,
"loss": 0.5822,
"step": 105
},
{
"epoch": 0.1915085817524842,
"grad_norm": 0.25034051990006584,
"learning_rate": 2.8435676403591193e-05,
"loss": 0.5846,
"step": 106
},
{
"epoch": 0.1933152664859982,
"grad_norm": 0.27868357694305945,
"learning_rate": 2.8395525729193284e-05,
"loss": 0.5907,
"step": 107
},
{
"epoch": 0.1951219512195122,
"grad_norm": 0.257742952703987,
"learning_rate": 2.835489538805548e-05,
"loss": 0.5888,
"step": 108
},
{
"epoch": 0.1969286359530262,
"grad_norm": 0.26397326166674545,
"learning_rate": 2.8313786835068314e-05,
"loss": 0.5976,
"step": 109
},
{
"epoch": 0.1987353206865402,
"grad_norm": 0.2721484510112116,
"learning_rate": 2.8272201542246077e-05,
"loss": 0.5792,
"step": 110
},
{
"epoch": 0.2005420054200542,
"grad_norm": 0.2374425057236497,
"learning_rate": 2.8230140998674185e-05,
"loss": 0.599,
"step": 111
},
{
"epoch": 0.2023486901535682,
"grad_norm": 0.24242218904343407,
"learning_rate": 2.8187606710455807e-05,
"loss": 0.5921,
"step": 112
},
{
"epoch": 0.2041553748870822,
"grad_norm": 0.2742052397132371,
"learning_rate": 2.8144600200657953e-05,
"loss": 0.5965,
"step": 113
},
{
"epoch": 0.20596205962059622,
"grad_norm": 0.2240931438132582,
"learning_rate": 2.8101123009256946e-05,
"loss": 0.5792,
"step": 114
},
{
"epoch": 0.20776874435411022,
"grad_norm": 0.2763456467888191,
"learning_rate": 2.8057176693083253e-05,
"loss": 0.5958,
"step": 115
},
{
"epoch": 0.20957542908762422,
"grad_norm": 0.2435434093260049,
"learning_rate": 2.8012762825765763e-05,
"loss": 0.5891,
"step": 116
},
{
"epoch": 0.21138211382113822,
"grad_norm": 0.2769370185736096,
"learning_rate": 2.7967882997675424e-05,
"loss": 0.6012,
"step": 117
},
{
"epoch": 0.21318879855465223,
"grad_norm": 0.2556991024086139,
"learning_rate": 2.7922538815868287e-05,
"loss": 0.5879,
"step": 118
},
{
"epoch": 0.21499548328816623,
"grad_norm": 0.2913165244476914,
"learning_rate": 2.7876731904027994e-05,
"loss": 0.5784,
"step": 119
},
{
"epoch": 0.21680216802168023,
"grad_norm": 0.29037318268167045,
"learning_rate": 2.78304639024076e-05,
"loss": 0.5968,
"step": 120
},
{
"epoch": 0.2186088527551942,
"grad_norm": 0.24340049924612678,
"learning_rate": 2.7783736467770863e-05,
"loss": 0.5927,
"step": 121
},
{
"epoch": 0.2204155374887082,
"grad_norm": 0.29825692316659325,
"learning_rate": 2.7736551273332908e-05,
"loss": 0.5972,
"step": 122
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.2593832259683122,
"learning_rate": 2.7688910008700305e-05,
"loss": 0.5876,
"step": 123
},
{
"epoch": 0.2240289069557362,
"grad_norm": 0.27547771011759425,
"learning_rate": 2.764081437981059e-05,
"loss": 0.5742,
"step": 124
},
{
"epoch": 0.22583559168925021,
"grad_norm": 0.27158658907185634,
"learning_rate": 2.7592266108871158e-05,
"loss": 0.5812,
"step": 125
},
{
"epoch": 0.22764227642276422,
"grad_norm": 0.2715497634460973,
"learning_rate": 2.754326693429761e-05,
"loss": 0.5931,
"step": 126
},
{
"epoch": 0.22944896115627822,
"grad_norm": 0.24142985625388147,
"learning_rate": 2.7493818610651493e-05,
"loss": 0.5859,
"step": 127
},
{
"epoch": 0.23125564588979222,
"grad_norm": 0.2530474955317245,
"learning_rate": 2.744392290857747e-05,
"loss": 0.5857,
"step": 128
},
{
"epoch": 0.23306233062330622,
"grad_norm": 0.2567731311347638,
"learning_rate": 2.7393581614739924e-05,
"loss": 0.5803,
"step": 129
},
{
"epoch": 0.23486901535682023,
"grad_norm": 0.2628073110459229,
"learning_rate": 2.7342796531758984e-05,
"loss": 0.5987,
"step": 130
},
{
"epoch": 0.23667570009033423,
"grad_norm": 0.23510376935644756,
"learning_rate": 2.729156947814598e-05,
"loss": 0.5926,
"step": 131
},
{
"epoch": 0.23848238482384823,
"grad_norm": 0.23576954058784624,
"learning_rate": 2.7239902288238297e-05,
"loss": 0.5721,
"step": 132
},
{
"epoch": 0.24028906955736223,
"grad_norm": 0.24964231366212492,
"learning_rate": 2.7187796812133733e-05,
"loss": 0.5873,
"step": 133
},
{
"epoch": 0.24209575429087624,
"grad_norm": 0.23911643013915115,
"learning_rate": 2.7135254915624213e-05,
"loss": 0.5878,
"step": 134
},
{
"epoch": 0.24390243902439024,
"grad_norm": 0.23601189225311667,
"learning_rate": 2.708227848012901e-05,
"loss": 0.585,
"step": 135
},
{
"epoch": 0.24570912375790424,
"grad_norm": 0.28061149806949875,
"learning_rate": 2.7028869402627357e-05,
"loss": 0.5889,
"step": 136
},
{
"epoch": 0.24751580849141824,
"grad_norm": 0.2537605160128264,
"learning_rate": 2.6975029595590523e-05,
"loss": 0.5726,
"step": 137
},
{
"epoch": 0.24932249322493225,
"grad_norm": 0.2631279788827005,
"learning_rate": 2.6920760986913332e-05,
"loss": 0.5901,
"step": 138
},
{
"epoch": 0.25112917795844625,
"grad_norm": 0.24684546421512338,
"learning_rate": 2.6866065519845124e-05,
"loss": 0.5932,
"step": 139
},
{
"epoch": 0.2529358626919603,
"grad_norm": 0.25108587954115535,
"learning_rate": 2.681094515292018e-05,
"loss": 0.5927,
"step": 140
},
{
"epoch": 0.25474254742547425,
"grad_norm": 0.2759732073497199,
"learning_rate": 2.6755401859887598e-05,
"loss": 0.573,
"step": 141
},
{
"epoch": 0.2565492321589883,
"grad_norm": 0.2927986426856055,
"learning_rate": 2.6699437629640595e-05,
"loss": 0.5934,
"step": 142
},
{
"epoch": 0.25835591689250226,
"grad_norm": 0.2915811926744858,
"learning_rate": 2.6643054466145297e-05,
"loss": 0.5846,
"step": 143
},
{
"epoch": 0.2601626016260163,
"grad_norm": 0.25639674407942853,
"learning_rate": 2.6586254388368995e-05,
"loss": 0.5733,
"step": 144
},
{
"epoch": 0.26196928635953026,
"grad_norm": 0.25466281147535325,
"learning_rate": 2.652903943020783e-05,
"loss": 0.5862,
"step": 145
},
{
"epoch": 0.26377597109304424,
"grad_norm": 0.24151461009286013,
"learning_rate": 2.647141164041398e-05,
"loss": 0.5904,
"step": 146
},
{
"epoch": 0.26558265582655827,
"grad_norm": 0.259822033974557,
"learning_rate": 2.641337308252228e-05,
"loss": 0.581,
"step": 147
},
{
"epoch": 0.26738934056007224,
"grad_norm": 0.24532475377494284,
"learning_rate": 2.6354925834776346e-05,
"loss": 0.5817,
"step": 148
},
{
"epoch": 0.26919602529358627,
"grad_norm": 0.2555788655192275,
"learning_rate": 2.6296071990054167e-05,
"loss": 0.579,
"step": 149
},
{
"epoch": 0.27100271002710025,
"grad_norm": 0.2534339164884998,
"learning_rate": 2.6236813655793123e-05,
"loss": 0.5886,
"step": 150
},
{
"epoch": 0.2728093947606143,
"grad_norm": 0.25366511050468843,
"learning_rate": 2.617715295391457e-05,
"loss": 0.5707,
"step": 151
},
{
"epoch": 0.27461607949412825,
"grad_norm": 0.26118391438335414,
"learning_rate": 2.6117092020747824e-05,
"loss": 0.5779,
"step": 152
},
{
"epoch": 0.2764227642276423,
"grad_norm": 0.31049055796662123,
"learning_rate": 2.6056633006953677e-05,
"loss": 0.5783,
"step": 153
},
{
"epoch": 0.27822944896115626,
"grad_norm": 0.2611788471953917,
"learning_rate": 2.5995778077447393e-05,
"loss": 0.5823,
"step": 154
},
{
"epoch": 0.2800361336946703,
"grad_norm": 0.3259190805002546,
"learning_rate": 2.5934529411321174e-05,
"loss": 0.5743,
"step": 155
},
{
"epoch": 0.28184281842818426,
"grad_norm": 0.2222204544644696,
"learning_rate": 2.587288920176613e-05,
"loss": 0.575,
"step": 156
},
{
"epoch": 0.2836495031616983,
"grad_norm": 0.29042132848143276,
"learning_rate": 2.581085965599375e-05,
"loss": 0.5877,
"step": 157
},
{
"epoch": 0.28545618789521227,
"grad_norm": 0.2577824036794116,
"learning_rate": 2.5748442995156882e-05,
"loss": 0.5854,
"step": 158
},
{
"epoch": 0.2872628726287263,
"grad_norm": 0.24041412490024394,
"learning_rate": 2.5685641454270172e-05,
"loss": 0.566,
"step": 159
},
{
"epoch": 0.28906955736224027,
"grad_norm": 0.33137613211077116,
"learning_rate": 2.5622457282130046e-05,
"loss": 0.5753,
"step": 160
},
{
"epoch": 0.2908762420957543,
"grad_norm": 0.2252657452973701,
"learning_rate": 2.5558892741234173e-05,
"loss": 0.5827,
"step": 161
},
{
"epoch": 0.2926829268292683,
"grad_norm": 0.353225035311219,
"learning_rate": 2.5494950107700482e-05,
"loss": 0.5692,
"step": 162
},
{
"epoch": 0.2944896115627823,
"grad_norm": 0.2549710140850951,
"learning_rate": 2.5430631671185616e-05,
"loss": 0.5775,
"step": 163
},
{
"epoch": 0.2962962962962963,
"grad_norm": 0.320108207545845,
"learning_rate": 2.5365939734802973e-05,
"loss": 0.5871,
"step": 164
},
{
"epoch": 0.2981029810298103,
"grad_norm": 0.27118178617195304,
"learning_rate": 2.5300876615040223e-05,
"loss": 0.5777,
"step": 165
},
{
"epoch": 0.2999096657633243,
"grad_norm": 0.2732065296628375,
"learning_rate": 2.523544464167637e-05,
"loss": 0.5842,
"step": 166
},
{
"epoch": 0.3017163504968383,
"grad_norm": 0.2440418264084237,
"learning_rate": 2.5169646157698313e-05,
"loss": 0.583,
"step": 167
},
{
"epoch": 0.3035230352303523,
"grad_norm": 0.2400624724182379,
"learning_rate": 2.5103483519216964e-05,
"loss": 0.5813,
"step": 168
},
{
"epoch": 0.3053297199638663,
"grad_norm": 0.25905283588713374,
"learning_rate": 2.5036959095382875e-05,
"loss": 0.574,
"step": 169
},
{
"epoch": 0.3071364046973803,
"grad_norm": 0.2591290671871167,
"learning_rate": 2.4970075268301388e-05,
"loss": 0.5877,
"step": 170
},
{
"epoch": 0.3089430894308943,
"grad_norm": 0.2235510897395504,
"learning_rate": 2.4902834432947353e-05,
"loss": 0.5706,
"step": 171
},
{
"epoch": 0.3107497741644083,
"grad_norm": 0.23760061910249497,
"learning_rate": 2.4835238997079382e-05,
"loss": 0.5771,
"step": 172
},
{
"epoch": 0.31255645889792233,
"grad_norm": 0.2617951363502666,
"learning_rate": 2.4767291381153603e-05,
"loss": 0.5807,
"step": 173
},
{
"epoch": 0.3143631436314363,
"grad_norm": 0.23091611449448254,
"learning_rate": 2.4698994018236994e-05,
"loss": 0.5721,
"step": 174
},
{
"epoch": 0.31616982836495033,
"grad_norm": 0.25262572503013164,
"learning_rate": 2.4630349353920284e-05,
"loss": 0.5767,
"step": 175
},
{
"epoch": 0.3179765130984643,
"grad_norm": 0.23055115622552902,
"learning_rate": 2.4561359846230346e-05,
"loss": 0.5906,
"step": 176
},
{
"epoch": 0.31978319783197834,
"grad_norm": 0.21968694104114944,
"learning_rate": 2.4492027965542217e-05,
"loss": 0.5657,
"step": 177
},
{
"epoch": 0.3215898825654923,
"grad_norm": 0.2525014182918365,
"learning_rate": 2.44223561944906e-05,
"loss": 0.5724,
"step": 178
},
{
"epoch": 0.32339656729900634,
"grad_norm": 0.2407328065060556,
"learning_rate": 2.4352347027881003e-05,
"loss": 0.5825,
"step": 179
},
{
"epoch": 0.3252032520325203,
"grad_norm": 0.2547387307288275,
"learning_rate": 2.4282002972600382e-05,
"loss": 0.5908,
"step": 180
},
{
"epoch": 0.32700993676603435,
"grad_norm": 0.2263495601766316,
"learning_rate": 2.4211326547527377e-05,
"loss": 0.5688,
"step": 181
},
{
"epoch": 0.3288166214995483,
"grad_norm": 0.2789402543570071,
"learning_rate": 2.4140320283442125e-05,
"loss": 0.579,
"step": 182
},
{
"epoch": 0.33062330623306235,
"grad_norm": 0.2567309540458022,
"learning_rate": 2.4068986722935625e-05,
"loss": 0.5893,
"step": 183
},
{
"epoch": 0.3324299909665763,
"grad_norm": 0.24182513399667138,
"learning_rate": 2.3997328420318705e-05,
"loss": 0.5858,
"step": 184
},
{
"epoch": 0.33423667570009036,
"grad_norm": 0.2675738732389291,
"learning_rate": 2.3925347941530556e-05,
"loss": 0.5822,
"step": 185
},
{
"epoch": 0.33604336043360433,
"grad_norm": 0.23428952659343405,
"learning_rate": 2.3853047864046843e-05,
"loss": 0.5779,
"step": 186
},
{
"epoch": 0.33785004516711836,
"grad_norm": 0.26339154899807604,
"learning_rate": 2.3780430776787413e-05,
"loss": 0.5747,
"step": 187
},
{
"epoch": 0.33965672990063234,
"grad_norm": 0.21349849308750005,
"learning_rate": 2.3707499280023604e-05,
"loss": 0.5747,
"step": 188
},
{
"epoch": 0.34146341463414637,
"grad_norm": 0.26554041110868815,
"learning_rate": 2.3634255985285104e-05,
"loss": 0.5825,
"step": 189
},
{
"epoch": 0.34327009936766034,
"grad_norm": 0.23538164196617103,
"learning_rate": 2.356070351526648e-05,
"loss": 0.5708,
"step": 190
},
{
"epoch": 0.34507678410117437,
"grad_norm": 0.24516795740455555,
"learning_rate": 2.348684450373322e-05,
"loss": 0.5691,
"step": 191
},
{
"epoch": 0.34688346883468835,
"grad_norm": 0.2320939063694949,
"learning_rate": 2.3412681595427467e-05,
"loss": 0.5761,
"step": 192
},
{
"epoch": 0.3486901535682023,
"grad_norm": 0.24367157013907606,
"learning_rate": 2.3338217445973268e-05,
"loss": 0.5776,
"step": 193
},
{
"epoch": 0.35049683830171635,
"grad_norm": 0.2383952654545809,
"learning_rate": 2.3263454721781537e-05,
"loss": 0.5793,
"step": 194
},
{
"epoch": 0.3523035230352303,
"grad_norm": 0.21970860044862534,
"learning_rate": 2.318839609995453e-05,
"loss": 0.5625,
"step": 195
},
{
"epoch": 0.35411020776874436,
"grad_norm": 0.22393266445368756,
"learning_rate": 2.3113044268189995e-05,
"loss": 0.5758,
"step": 196
},
{
"epoch": 0.35591689250225833,
"grad_norm": 0.20965253283535495,
"learning_rate": 2.303740192468495e-05,
"loss": 0.5754,
"step": 197
},
{
"epoch": 0.35772357723577236,
"grad_norm": 0.2134213495454822,
"learning_rate": 2.2961471778039045e-05,
"loss": 0.5521,
"step": 198
},
{
"epoch": 0.35953026196928634,
"grad_norm": 0.2077804399624621,
"learning_rate": 2.288525654715757e-05,
"loss": 0.5758,
"step": 199
},
{
"epoch": 0.36133694670280037,
"grad_norm": 0.21089298206975676,
"learning_rate": 2.280875896115413e-05,
"loss": 0.5645,
"step": 200
},
{
"epoch": 0.36314363143631434,
"grad_norm": 0.22751400705060473,
"learning_rate": 2.2731981759252876e-05,
"loss": 0.5595,
"step": 201
},
{
"epoch": 0.36495031616982837,
"grad_norm": 0.22071355320317226,
"learning_rate": 2.2654927690690445e-05,
"loss": 0.5858,
"step": 202
},
{
"epoch": 0.36675700090334235,
"grad_norm": 0.2269131246517602,
"learning_rate": 2.257759951461752e-05,
"loss": 0.5733,
"step": 203
},
{
"epoch": 0.3685636856368564,
"grad_norm": 0.27195813360203375,
"learning_rate": 2.25e-05,
"loss": 0.5855,
"step": 204
},
{
"epoch": 0.37037037037037035,
"grad_norm": 0.24074584104894936,
"learning_rate": 2.24221319255199e-05,
"loss": 0.5761,
"step": 205
},
{
"epoch": 0.3721770551038844,
"grad_norm": 0.2643169067368919,
"learning_rate": 2.234399807947579e-05,
"loss": 0.5632,
"step": 206
},
{
"epoch": 0.37398373983739835,
"grad_norm": 0.2602452192335381,
"learning_rate": 2.2265601259683e-05,
"loss": 0.5713,
"step": 207
},
{
"epoch": 0.3757904245709124,
"grad_norm": 0.22491768260975722,
"learning_rate": 2.2186944273373426e-05,
"loss": 0.5589,
"step": 208
},
{
"epoch": 0.37759710930442636,
"grad_norm": 0.23899265916988002,
"learning_rate": 2.210802993709498e-05,
"loss": 0.5799,
"step": 209
},
{
"epoch": 0.3794037940379404,
"grad_norm": 0.28185732149789655,
"learning_rate": 2.202886107661078e-05,
"loss": 0.576,
"step": 210
},
{
"epoch": 0.38121047877145436,
"grad_norm": 0.20671343969870537,
"learning_rate": 2.1949440526797928e-05,
"loss": 0.5761,
"step": 211
},
{
"epoch": 0.3830171635049684,
"grad_norm": 0.245945113158813,
"learning_rate": 2.1869771131546015e-05,
"loss": 0.5834,
"step": 212
},
{
"epoch": 0.38482384823848237,
"grad_norm": 0.2051130167210825,
"learning_rate": 2.178985574365529e-05,
"loss": 0.5837,
"step": 213
},
{
"epoch": 0.3866305329719964,
"grad_norm": 0.25952305018947347,
"learning_rate": 2.170969722473449e-05,
"loss": 0.57,
"step": 214
},
{
"epoch": 0.3884372177055104,
"grad_norm": 0.24249808093673167,
"learning_rate": 2.1629298445098403e-05,
"loss": 0.5966,
"step": 215
},
{
"epoch": 0.3902439024390244,
"grad_norm": 0.237872387820411,
"learning_rate": 2.154866228366505e-05,
"loss": 0.5856,
"step": 216
},
{
"epoch": 0.3920505871725384,
"grad_norm": 0.20572539636470738,
"learning_rate": 2.146779162785263e-05,
"loss": 0.5857,
"step": 217
},
{
"epoch": 0.3938572719060524,
"grad_norm": 0.22849509908427684,
"learning_rate": 2.138668937347609e-05,
"loss": 0.5775,
"step": 218
},
{
"epoch": 0.3956639566395664,
"grad_norm": 0.21171703597428448,
"learning_rate": 2.1305358424643484e-05,
"loss": 0.572,
"step": 219
},
{
"epoch": 0.3974706413730804,
"grad_norm": 0.2333174990121186,
"learning_rate": 2.1223801693651927e-05,
"loss": 0.5746,
"step": 220
},
{
"epoch": 0.3992773261065944,
"grad_norm": 0.21728105831361583,
"learning_rate": 2.114202210088336e-05,
"loss": 0.5633,
"step": 221
},
{
"epoch": 0.4010840108401084,
"grad_norm": 0.2232469073657137,
"learning_rate": 2.106002257469993e-05,
"loss": 0.5805,
"step": 222
},
{
"epoch": 0.4028906955736224,
"grad_norm": 0.23039919622981786,
"learning_rate": 2.0977806051339172e-05,
"loss": 0.5631,
"step": 223
},
{
"epoch": 0.4046973803071364,
"grad_norm": 0.24767592985180426,
"learning_rate": 2.0895375474808857e-05,
"loss": 0.5681,
"step": 224
},
{
"epoch": 0.4065040650406504,
"grad_norm": 0.22933111893390376,
"learning_rate": 2.0812733796781544e-05,
"loss": 0.5728,
"step": 225
},
{
"epoch": 0.4083107497741644,
"grad_norm": 0.24263450877516124,
"learning_rate": 2.0729883976488936e-05,
"loss": 0.5792,
"step": 226
},
{
"epoch": 0.4101174345076784,
"grad_norm": 0.24644389391459087,
"learning_rate": 2.064682898061588e-05,
"loss": 0.5836,
"step": 227
},
{
"epoch": 0.41192411924119243,
"grad_norm": 0.23999077805752708,
"learning_rate": 2.0563571783194146e-05,
"loss": 0.5697,
"step": 228
},
{
"epoch": 0.4137308039747064,
"grad_norm": 0.20338232613186608,
"learning_rate": 2.0480115365495928e-05,
"loss": 0.5723,
"step": 229
},
{
"epoch": 0.41553748870822044,
"grad_norm": 0.21451640836421845,
"learning_rate": 2.0396462715927107e-05,
"loss": 0.5748,
"step": 230
},
{
"epoch": 0.4173441734417344,
"grad_norm": 0.23674092702209837,
"learning_rate": 2.0312616829920222e-05,
"loss": 0.5737,
"step": 231
},
{
"epoch": 0.41915085817524844,
"grad_norm": 0.2040271869891673,
"learning_rate": 2.022858070982723e-05,
"loss": 0.5768,
"step": 232
},
{
"epoch": 0.4209575429087624,
"grad_norm": 0.23013110791835603,
"learning_rate": 2.0144357364811973e-05,
"loss": 0.5586,
"step": 233
},
{
"epoch": 0.42276422764227645,
"grad_norm": 0.23251714747465213,
"learning_rate": 2.0059949810742452e-05,
"loss": 0.5744,
"step": 234
},
{
"epoch": 0.4245709123757904,
"grad_norm": 0.24113338282908972,
"learning_rate": 1.997536107008281e-05,
"loss": 0.5696,
"step": 235
},
{
"epoch": 0.42637759710930445,
"grad_norm": 0.217275693069977,
"learning_rate": 1.9890594171785128e-05,
"loss": 0.5807,
"step": 236
},
{
"epoch": 0.4281842818428184,
"grad_norm": 0.20589216064741256,
"learning_rate": 1.9805652151180945e-05,
"loss": 0.5804,
"step": 237
},
{
"epoch": 0.42999096657633246,
"grad_norm": 0.22359306351640823,
"learning_rate": 1.972053804987258e-05,
"loss": 0.5889,
"step": 238
},
{
"epoch": 0.43179765130984643,
"grad_norm": 0.20375725610745427,
"learning_rate": 1.963525491562421e-05,
"loss": 0.5701,
"step": 239
},
{
"epoch": 0.43360433604336046,
"grad_norm": 0.20454609097134233,
"learning_rate": 1.954980580225275e-05,
"loss": 0.5702,
"step": 240
},
{
"epoch": 0.43541102077687444,
"grad_norm": 0.19497163244699564,
"learning_rate": 1.946419376951848e-05,
"loss": 0.5693,
"step": 241
},
{
"epoch": 0.4372177055103884,
"grad_norm": 0.21551459772294188,
"learning_rate": 1.9378421883015505e-05,
"loss": 0.57,
"step": 242
},
{
"epoch": 0.43902439024390244,
"grad_norm": 0.23200634978654613,
"learning_rate": 1.9292493214061953e-05,
"loss": 0.5741,
"step": 243
},
{
"epoch": 0.4408310749774164,
"grad_norm": 0.1884963011054949,
"learning_rate": 1.9206410839590042e-05,
"loss": 0.5804,
"step": 244
},
{
"epoch": 0.44263775971093045,
"grad_norm": 0.25404075829436523,
"learning_rate": 1.9120177842035853e-05,
"loss": 0.5726,
"step": 245
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.22097319274710464,
"learning_rate": 1.9033797309228984e-05,
"loss": 0.5794,
"step": 246
},
{
"epoch": 0.44625112917795845,
"grad_norm": 0.19246576672187318,
"learning_rate": 1.8947272334281977e-05,
"loss": 0.5616,
"step": 247
},
{
"epoch": 0.4480578139114724,
"grad_norm": 0.22700593999033858,
"learning_rate": 1.8860606015479537e-05,
"loss": 0.5801,
"step": 248
},
{
"epoch": 0.44986449864498645,
"grad_norm": 0.1934681513313933,
"learning_rate": 1.877380145616763e-05,
"loss": 0.5632,
"step": 249
},
{
"epoch": 0.45167118337850043,
"grad_norm": 0.21167453440737605,
"learning_rate": 1.868686176464232e-05,
"loss": 0.5781,
"step": 250
},
{
"epoch": 0.45347786811201446,
"grad_norm": 0.23469761452053498,
"learning_rate": 1.8599790054038487e-05,
"loss": 0.5653,
"step": 251
},
{
"epoch": 0.45528455284552843,
"grad_norm": 0.20579485783023402,
"learning_rate": 1.8512589442218358e-05,
"loss": 0.5472,
"step": 252
},
{
"epoch": 0.45709123757904246,
"grad_norm": 0.20450811714095307,
"learning_rate": 1.8425263051659838e-05,
"loss": 0.5701,
"step": 253
},
{
"epoch": 0.45889792231255644,
"grad_norm": 0.2795902989622695,
"learning_rate": 1.8337814009344716e-05,
"loss": 0.5692,
"step": 254
},
{
"epoch": 0.46070460704607047,
"grad_norm": 0.26043149982302555,
"learning_rate": 1.8250245446646707e-05,
"loss": 0.5627,
"step": 255
},
{
"epoch": 0.46251129177958444,
"grad_norm": 0.2115149201329313,
"learning_rate": 1.8162560499219286e-05,
"loss": 0.563,
"step": 256
},
{
"epoch": 0.4643179765130985,
"grad_norm": 0.2863165296718786,
"learning_rate": 1.807476230688346e-05,
"loss": 0.5726,
"step": 257
},
{
"epoch": 0.46612466124661245,
"grad_norm": 0.22723135404479125,
"learning_rate": 1.7986854013515274e-05,
"loss": 0.5682,
"step": 258
},
{
"epoch": 0.4679313459801265,
"grad_norm": 0.21269365868540174,
"learning_rate": 1.78988387669333e-05,
"loss": 0.5718,
"step": 259
},
{
"epoch": 0.46973803071364045,
"grad_norm": 0.27706961689827647,
"learning_rate": 1.781071971878587e-05,
"loss": 0.5852,
"step": 260
},
{
"epoch": 0.4715447154471545,
"grad_norm": 0.21919053031721478,
"learning_rate": 1.7722500024438244e-05,
"loss": 0.5766,
"step": 261
},
{
"epoch": 0.47335140018066846,
"grad_norm": 0.2458759125768864,
"learning_rate": 1.7634182842859628e-05,
"loss": 0.565,
"step": 262
},
{
"epoch": 0.4751580849141825,
"grad_norm": 0.2489757112909537,
"learning_rate": 1.7545771336510033e-05,
"loss": 0.5695,
"step": 263
},
{
"epoch": 0.47696476964769646,
"grad_norm": 0.2101979687684982,
"learning_rate": 1.7457268671227067e-05,
"loss": 0.5759,
"step": 264
},
{
"epoch": 0.4787714543812105,
"grad_norm": 0.2500578266252668,
"learning_rate": 1.736867801611254e-05,
"loss": 0.5569,
"step": 265
},
{
"epoch": 0.48057813911472447,
"grad_norm": 0.19262415552045406,
"learning_rate": 1.728000254341901e-05,
"loss": 0.5813,
"step": 266
},
{
"epoch": 0.4823848238482385,
"grad_norm": 0.19478984136741012,
"learning_rate": 1.7191245428436175e-05,
"loss": 0.5653,
"step": 267
},
{
"epoch": 0.48419150858175247,
"grad_norm": 0.23871243123226799,
"learning_rate": 1.7102409849377188e-05,
"loss": 0.5661,
"step": 268
},
{
"epoch": 0.4859981933152665,
"grad_norm": 0.17665577180387385,
"learning_rate": 1.7013498987264832e-05,
"loss": 0.5727,
"step": 269
},
{
"epoch": 0.4878048780487805,
"grad_norm": 0.21091637968705407,
"learning_rate": 1.6924516025817636e-05,
"loss": 0.5544,
"step": 270
},
{
"epoch": 0.4896115627822945,
"grad_norm": 0.25253202754252524,
"learning_rate": 1.683546415133584e-05,
"loss": 0.5761,
"step": 271
},
{
"epoch": 0.4914182475158085,
"grad_norm": 0.2150474071339765,
"learning_rate": 1.6746346552587342e-05,
"loss": 0.5704,
"step": 272
},
{
"epoch": 0.4932249322493225,
"grad_norm": 0.24422291161795256,
"learning_rate": 1.665716642069349e-05,
"loss": 0.5785,
"step": 273
},
{
"epoch": 0.4950316169828365,
"grad_norm": 0.19465875800542706,
"learning_rate": 1.6567926949014805e-05,
"loss": 0.5658,
"step": 274
},
{
"epoch": 0.4968383017163505,
"grad_norm": 0.20059784342394038,
"learning_rate": 1.6478631333036655e-05,
"loss": 0.5607,
"step": 275
},
{
"epoch": 0.4986449864498645,
"grad_norm": 0.19428493006954836,
"learning_rate": 1.638928277025482e-05,
"loss": 0.5523,
"step": 276
},
{
"epoch": 0.5004516711833785,
"grad_norm": 0.190112158192132,
"learning_rate": 1.6299884460061005e-05,
"loss": 0.5643,
"step": 277
},
{
"epoch": 0.5022583559168925,
"grad_norm": 0.18317648770164868,
"learning_rate": 1.621043960362826e-05,
"loss": 0.5509,
"step": 278
},
{
"epoch": 0.5040650406504065,
"grad_norm": 0.20777757920037251,
"learning_rate": 1.6120951403796367e-05,
"loss": 0.5659,
"step": 279
},
{
"epoch": 0.5058717253839206,
"grad_norm": 0.24714269404949812,
"learning_rate": 1.603142306495714e-05,
"loss": 0.5625,
"step": 280
},
{
"epoch": 0.5076784101174345,
"grad_norm": 0.1771707758636966,
"learning_rate": 1.5941857792939702e-05,
"loss": 0.5629,
"step": 281
},
{
"epoch": 0.5094850948509485,
"grad_norm": 0.19209684745372535,
"learning_rate": 1.585225879489567e-05,
"loss": 0.5577,
"step": 282
},
{
"epoch": 0.5112917795844625,
"grad_norm": 0.22597515112664288,
"learning_rate": 1.5762629279184326e-05,
"loss": 0.5728,
"step": 283
},
{
"epoch": 0.5130984643179766,
"grad_norm": 0.17250544743705307,
"learning_rate": 1.5672972455257726e-05,
"loss": 0.5611,
"step": 284
},
{
"epoch": 0.5149051490514905,
"grad_norm": 0.20410988336988065,
"learning_rate": 1.5583291533545775e-05,
"loss": 0.5557,
"step": 285
},
{
"epoch": 0.5167118337850045,
"grad_norm": 0.20391700905101098,
"learning_rate": 1.549358972534128e-05,
"loss": 0.5538,
"step": 286
},
{
"epoch": 0.5185185185185185,
"grad_norm": 0.18259503875294242,
"learning_rate": 1.5403870242684942e-05,
"loss": 0.5754,
"step": 287
},
{
"epoch": 0.5203252032520326,
"grad_norm": 0.18696008552172258,
"learning_rate": 1.5314136298250355e-05,
"loss": 0.5723,
"step": 288
},
{
"epoch": 0.5221318879855466,
"grad_norm": 0.19653948540679103,
"learning_rate": 1.5224391105228956e-05,
"loss": 0.5565,
"step": 289
},
{
"epoch": 0.5239385727190605,
"grad_norm": 0.17253613754365116,
"learning_rate": 1.5134637877214968e-05,
"loss": 0.5682,
"step": 290
},
{
"epoch": 0.5257452574525745,
"grad_norm": 0.2056061343083173,
"learning_rate": 1.5044879828090346e-05,
"loss": 0.5727,
"step": 291
},
{
"epoch": 0.5275519421860885,
"grad_norm": 0.19894424925026757,
"learning_rate": 1.4955120171909658e-05,
"loss": 0.5763,
"step": 292
},
{
"epoch": 0.5293586269196026,
"grad_norm": 0.1659275906965013,
"learning_rate": 1.4865362122785031e-05,
"loss": 0.5689,
"step": 293
},
{
"epoch": 0.5311653116531165,
"grad_norm": 0.17986609793129524,
"learning_rate": 1.4775608894771048e-05,
"loss": 0.5612,
"step": 294
},
{
"epoch": 0.5329719963866305,
"grad_norm": 0.232250278692599,
"learning_rate": 1.4685863701749648e-05,
"loss": 0.5589,
"step": 295
},
{
"epoch": 0.5347786811201445,
"grad_norm": 0.22464497097731725,
"learning_rate": 1.4596129757315062e-05,
"loss": 0.5628,
"step": 296
},
{
"epoch": 0.5365853658536586,
"grad_norm": 0.1952420747386217,
"learning_rate": 1.4506410274658718e-05,
"loss": 0.5682,
"step": 297
},
{
"epoch": 0.5383920505871725,
"grad_norm": 0.2106666884744506,
"learning_rate": 1.441670846645423e-05,
"loss": 0.5627,
"step": 298
},
{
"epoch": 0.5401987353206865,
"grad_norm": 0.21061181918065086,
"learning_rate": 1.4327027544742281e-05,
"loss": 0.5783,
"step": 299
},
{
"epoch": 0.5420054200542005,
"grad_norm": 0.1861290798519661,
"learning_rate": 1.4237370720815675e-05,
"loss": 0.5664,
"step": 300
},
{
"epoch": 0.5438121047877146,
"grad_norm": 0.18862693026886343,
"learning_rate": 1.4147741205104336e-05,
"loss": 0.5683,
"step": 301
},
{
"epoch": 0.5456187895212286,
"grad_norm": 0.18676460565472633,
"learning_rate": 1.40581422070603e-05,
"loss": 0.5796,
"step": 302
},
{
"epoch": 0.5474254742547425,
"grad_norm": 0.1752400383590249,
"learning_rate": 1.3968576935042864e-05,
"loss": 0.5608,
"step": 303
},
{
"epoch": 0.5492321589882565,
"grad_norm": 0.18836688433228918,
"learning_rate": 1.3879048596203637e-05,
"loss": 0.5561,
"step": 304
},
{
"epoch": 0.5510388437217706,
"grad_norm": 0.19530506408089982,
"learning_rate": 1.3789560396371742e-05,
"loss": 0.5622,
"step": 305
},
{
"epoch": 0.5528455284552846,
"grad_norm": 0.17965863699921675,
"learning_rate": 1.3700115539938995e-05,
"loss": 0.5605,
"step": 306
},
{
"epoch": 0.5546522131887985,
"grad_norm": 0.21750349150527712,
"learning_rate": 1.3610717229745183e-05,
"loss": 0.578,
"step": 307
},
{
"epoch": 0.5564588979223125,
"grad_norm": 0.19147158863524186,
"learning_rate": 1.3521368666963348e-05,
"loss": 0.5572,
"step": 308
},
{
"epoch": 0.5582655826558266,
"grad_norm": 0.18608236035974007,
"learning_rate": 1.3432073050985201e-05,
"loss": 0.5669,
"step": 309
},
{
"epoch": 0.5600722673893406,
"grad_norm": 0.18440593641158914,
"learning_rate": 1.3342833579306511e-05,
"loss": 0.5492,
"step": 310
},
{
"epoch": 0.5618789521228545,
"grad_norm": 0.1843799787511743,
"learning_rate": 1.3253653447412658e-05,
"loss": 0.5685,
"step": 311
},
{
"epoch": 0.5636856368563685,
"grad_norm": 0.20261725696919525,
"learning_rate": 1.3164535848664167e-05,
"loss": 0.5674,
"step": 312
},
{
"epoch": 0.5654923215898826,
"grad_norm": 0.17558184672847507,
"learning_rate": 1.3075483974182368e-05,
"loss": 0.5684,
"step": 313
},
{
"epoch": 0.5672990063233966,
"grad_norm": 0.17907331587608558,
"learning_rate": 1.2986501012735174e-05,
"loss": 0.5609,
"step": 314
},
{
"epoch": 0.5691056910569106,
"grad_norm": 0.1934736256775333,
"learning_rate": 1.2897590150622812e-05,
"loss": 0.5613,
"step": 315
},
{
"epoch": 0.5709123757904245,
"grad_norm": 0.17567517580021857,
"learning_rate": 1.2808754571563827e-05,
"loss": 0.5573,
"step": 316
},
{
"epoch": 0.5727190605239386,
"grad_norm": 0.19690748080324788,
"learning_rate": 1.2719997456580993e-05,
"loss": 0.5525,
"step": 317
},
{
"epoch": 0.5745257452574526,
"grad_norm": 0.20212907631156332,
"learning_rate": 1.2631321983887464e-05,
"loss": 0.5654,
"step": 318
},
{
"epoch": 0.5763324299909666,
"grad_norm": 0.19608541723414,
"learning_rate": 1.2542731328772936e-05,
"loss": 0.5744,
"step": 319
},
{
"epoch": 0.5781391147244805,
"grad_norm": 0.20857428025225674,
"learning_rate": 1.2454228663489967e-05,
"loss": 0.5569,
"step": 320
},
{
"epoch": 0.5799457994579946,
"grad_norm": 0.17609191697173338,
"learning_rate": 1.2365817157140373e-05,
"loss": 0.5541,
"step": 321
},
{
"epoch": 0.5817524841915086,
"grad_norm": 0.18308421719879198,
"learning_rate": 1.2277499975561755e-05,
"loss": 0.5753,
"step": 322
},
{
"epoch": 0.5835591689250226,
"grad_norm": 0.17484046660309832,
"learning_rate": 1.2189280281214128e-05,
"loss": 0.5609,
"step": 323
},
{
"epoch": 0.5853658536585366,
"grad_norm": 0.17252551757672757,
"learning_rate": 1.2101161233066704e-05,
"loss": 0.5419,
"step": 324
},
{
"epoch": 0.5871725383920506,
"grad_norm": 0.17553463607522976,
"learning_rate": 1.201314598648473e-05,
"loss": 0.5591,
"step": 325
},
{
"epoch": 0.5889792231255646,
"grad_norm": 0.17326333720847636,
"learning_rate": 1.1925237693116546e-05,
"loss": 0.5689,
"step": 326
},
{
"epoch": 0.5907859078590786,
"grad_norm": 0.18687445963344007,
"learning_rate": 1.1837439500780718e-05,
"loss": 0.5553,
"step": 327
},
{
"epoch": 0.5925925925925926,
"grad_norm": 0.19428514170213504,
"learning_rate": 1.1749754553353297e-05,
"loss": 0.562,
"step": 328
},
{
"epoch": 0.5943992773261066,
"grad_norm": 0.17110021647920834,
"learning_rate": 1.1662185990655285e-05,
"loss": 0.5518,
"step": 329
},
{
"epoch": 0.5962059620596206,
"grad_norm": 0.18984185404031334,
"learning_rate": 1.1574736948340163e-05,
"loss": 0.559,
"step": 330
},
{
"epoch": 0.5980126467931346,
"grad_norm": 0.16874712774452827,
"learning_rate": 1.1487410557781642e-05,
"loss": 0.5632,
"step": 331
},
{
"epoch": 0.5998193315266486,
"grad_norm": 0.1806801244410073,
"learning_rate": 1.140020994596151e-05,
"loss": 0.5467,
"step": 332
},
{
"epoch": 0.6016260162601627,
"grad_norm": 0.17626693416571312,
"learning_rate": 1.1313138235357683e-05,
"loss": 0.5674,
"step": 333
},
{
"epoch": 0.6034327009936766,
"grad_norm": 0.1770136401046488,
"learning_rate": 1.1226198543832373e-05,
"loss": 0.5798,
"step": 334
},
{
"epoch": 0.6052393857271906,
"grad_norm": 0.1910726991764081,
"learning_rate": 1.1139393984520467e-05,
"loss": 0.563,
"step": 335
},
{
"epoch": 0.6070460704607046,
"grad_norm": 0.1718176664612323,
"learning_rate": 1.1052727665718027e-05,
"loss": 0.5596,
"step": 336
},
{
"epoch": 0.6088527551942186,
"grad_norm": 0.17250346288280585,
"learning_rate": 1.0966202690771015e-05,
"loss": 0.5611,
"step": 337
},
{
"epoch": 0.6106594399277326,
"grad_norm": 0.19111207535840807,
"learning_rate": 1.087982215796415e-05,
"loss": 0.5572,
"step": 338
},
{
"epoch": 0.6124661246612466,
"grad_norm": 0.1686795998299278,
"learning_rate": 1.079358916040996e-05,
"loss": 0.5657,
"step": 339
},
{
"epoch": 0.6142728093947606,
"grad_norm": 0.16862020455628596,
"learning_rate": 1.0707506785938052e-05,
"loss": 0.5611,
"step": 340
},
{
"epoch": 0.6160794941282746,
"grad_norm": 0.1637656583385122,
"learning_rate": 1.0621578116984501e-05,
"loss": 0.5593,
"step": 341
},
{
"epoch": 0.6178861788617886,
"grad_norm": 0.16170288648566758,
"learning_rate": 1.0535806230481525e-05,
"loss": 0.5628,
"step": 342
},
{
"epoch": 0.6196928635953026,
"grad_norm": 0.1717924247456263,
"learning_rate": 1.0450194197747252e-05,
"loss": 0.5567,
"step": 343
},
{
"epoch": 0.6214995483288166,
"grad_norm": 0.16174500558159677,
"learning_rate": 1.036474508437579e-05,
"loss": 0.5464,
"step": 344
},
{
"epoch": 0.6233062330623306,
"grad_norm": 0.16381172759058904,
"learning_rate": 1.0279461950127422e-05,
"loss": 0.5608,
"step": 345
},
{
"epoch": 0.6251129177958447,
"grad_norm": 0.17001972937010654,
"learning_rate": 1.0194347848819055e-05,
"loss": 0.5623,
"step": 346
},
{
"epoch": 0.6269196025293586,
"grad_norm": 0.17303311757989492,
"learning_rate": 1.0109405828214872e-05,
"loss": 0.5482,
"step": 347
},
{
"epoch": 0.6287262872628726,
"grad_norm": 0.1882537905657933,
"learning_rate": 1.0024638929917192e-05,
"loss": 0.5492,
"step": 348
},
{
"epoch": 0.6305329719963866,
"grad_norm": 0.15457360070696674,
"learning_rate": 9.940050189257552e-06,
"loss": 0.5521,
"step": 349
},
{
"epoch": 0.6323396567299007,
"grad_norm": 0.15615688544922562,
"learning_rate": 9.85564263518803e-06,
"loss": 0.5643,
"step": 350
},
{
"epoch": 0.6341463414634146,
"grad_norm": 0.16319062879774318,
"learning_rate": 9.771419290172776e-06,
"loss": 0.554,
"step": 351
},
{
"epoch": 0.6359530261969286,
"grad_norm": 0.15770060432248675,
"learning_rate": 9.68738317007978e-06,
"loss": 0.5682,
"step": 352
},
{
"epoch": 0.6377597109304426,
"grad_norm": 0.16898427412267347,
"learning_rate": 9.6035372840729e-06,
"loss": 0.568,
"step": 353
},
{
"epoch": 0.6395663956639567,
"grad_norm": 0.15918955141776597,
"learning_rate": 9.519884634504074e-06,
"loss": 0.5631,
"step": 354
},
{
"epoch": 0.6413730803974707,
"grad_norm": 0.1635896927311437,
"learning_rate": 9.436428216805862e-06,
"loss": 0.5524,
"step": 355
},
{
"epoch": 0.6431797651309846,
"grad_norm": 0.15329421947992738,
"learning_rate": 9.35317101938412e-06,
"loss": 0.566,
"step": 356
},
{
"epoch": 0.6449864498644986,
"grad_norm": 0.18290183186305234,
"learning_rate": 9.270116023511063e-06,
"loss": 0.5676,
"step": 357
},
{
"epoch": 0.6467931345980127,
"grad_norm": 0.18253658487556157,
"learning_rate": 9.187266203218457e-06,
"loss": 0.5729,
"step": 358
},
{
"epoch": 0.6485998193315267,
"grad_norm": 0.1791341463101353,
"learning_rate": 9.104624525191147e-06,
"loss": 0.546,
"step": 359
},
{
"epoch": 0.6504065040650406,
"grad_norm": 0.14674620232896526,
"learning_rate": 9.022193948660825e-06,
"loss": 0.5548,
"step": 360
},
{
"epoch": 0.6522131887985546,
"grad_norm": 0.19660949623094373,
"learning_rate": 8.939977425300072e-06,
"loss": 0.56,
"step": 361
},
{
"epoch": 0.6540198735320687,
"grad_norm": 0.1876501178479123,
"learning_rate": 8.857977899116645e-06,
"loss": 0.5717,
"step": 362
},
{
"epoch": 0.6558265582655827,
"grad_norm": 0.21507796351172995,
"learning_rate": 8.776198306348072e-06,
"loss": 0.5618,
"step": 363
},
{
"epoch": 0.6576332429990966,
"grad_norm": 0.18228320215554383,
"learning_rate": 8.69464157535652e-06,
"loss": 0.5612,
"step": 364
},
{
"epoch": 0.6594399277326106,
"grad_norm": 0.1757206345144353,
"learning_rate": 8.61331062652391e-06,
"loss": 0.5534,
"step": 365
},
{
"epoch": 0.6612466124661247,
"grad_norm": 0.19026770352731234,
"learning_rate": 8.532208372147376e-06,
"loss": 0.5746,
"step": 366
},
{
"epoch": 0.6630532971996387,
"grad_norm": 0.1865886995183675,
"learning_rate": 8.451337716334953e-06,
"loss": 0.5556,
"step": 367
},
{
"epoch": 0.6648599819331527,
"grad_norm": 0.1797695927669861,
"learning_rate": 8.370701554901603e-06,
"loss": 0.5675,
"step": 368
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.17670482413719021,
"learning_rate": 8.290302775265509e-06,
"loss": 0.5686,
"step": 369
},
{
"epoch": 0.6684733514001807,
"grad_norm": 0.1701577263486839,
"learning_rate": 8.210144256344714e-06,
"loss": 0.5668,
"step": 370
},
{
"epoch": 0.6702800361336947,
"grad_norm": 0.2061129978805257,
"learning_rate": 8.130228868453989e-06,
"loss": 0.555,
"step": 371
},
{
"epoch": 0.6720867208672087,
"grad_norm": 0.1969046824239301,
"learning_rate": 8.050559473202078e-06,
"loss": 0.5727,
"step": 372
},
{
"epoch": 0.6738934056007226,
"grad_norm": 0.15311615793545202,
"learning_rate": 7.971138923389221e-06,
"loss": 0.5583,
"step": 373
},
{
"epoch": 0.6757000903342367,
"grad_norm": 0.18976350186526125,
"learning_rate": 7.89197006290502e-06,
"loss": 0.5473,
"step": 374
},
{
"epoch": 0.6775067750677507,
"grad_norm": 0.1879352111528028,
"learning_rate": 7.813055726626579e-06,
"loss": 0.5619,
"step": 375
},
{
"epoch": 0.6793134598012647,
"grad_norm": 0.20499323771840253,
"learning_rate": 7.734398740316999e-06,
"loss": 0.5467,
"step": 376
},
{
"epoch": 0.6811201445347786,
"grad_norm": 0.17137028091933101,
"learning_rate": 7.65600192052422e-06,
"loss": 0.563,
"step": 377
},
{
"epoch": 0.6829268292682927,
"grad_norm": 0.18099761803792097,
"learning_rate": 7.577868074480107e-06,
"loss": 0.5634,
"step": 378
},
{
"epoch": 0.6847335140018067,
"grad_norm": 0.19896866364484633,
"learning_rate": 7.500000000000004e-06,
"loss": 0.5664,
"step": 379
},
{
"epoch": 0.6865401987353207,
"grad_norm": 0.1884102435991128,
"learning_rate": 7.422400485382484e-06,
"loss": 0.5473,
"step": 380
},
{
"epoch": 0.6883468834688347,
"grad_norm": 0.17513345385135934,
"learning_rate": 7.345072309309557e-06,
"loss": 0.5638,
"step": 381
},
{
"epoch": 0.6901535682023487,
"grad_norm": 0.1733806383727063,
"learning_rate": 7.268018240747129e-06,
"loss": 0.5515,
"step": 382
},
{
"epoch": 0.6919602529358627,
"grad_norm": 0.18213237487884423,
"learning_rate": 7.191241038845876e-06,
"loss": 0.5704,
"step": 383
},
{
"epoch": 0.6937669376693767,
"grad_norm": 0.20160376104741037,
"learning_rate": 7.114743452842428e-06,
"loss": 0.5681,
"step": 384
},
{
"epoch": 0.6955736224028907,
"grad_norm": 0.14133588164420194,
"learning_rate": 7.038528221960959e-06,
"loss": 0.5504,
"step": 385
},
{
"epoch": 0.6973803071364046,
"grad_norm": 0.1554959410199801,
"learning_rate": 6.962598075315047e-06,
"loss": 0.5622,
"step": 386
},
{
"epoch": 0.6991869918699187,
"grad_norm": 0.17804707625227728,
"learning_rate": 6.886955731810009e-06,
"loss": 0.5622,
"step": 387
},
{
"epoch": 0.7009936766034327,
"grad_norm": 0.1770700659186734,
"learning_rate": 6.811603900045477e-06,
"loss": 0.5612,
"step": 388
},
{
"epoch": 0.7028003613369467,
"grad_norm": 0.15981371678518486,
"learning_rate": 6.736545278218464e-06,
"loss": 0.5642,
"step": 389
},
{
"epoch": 0.7046070460704607,
"grad_norm": 0.1530064162827602,
"learning_rate": 6.661782554026735e-06,
"loss": 0.5584,
"step": 390
},
{
"epoch": 0.7064137308039747,
"grad_norm": 0.16596305105845469,
"learning_rate": 6.587318404572537e-06,
"loss": 0.5583,
"step": 391
},
{
"epoch": 0.7082204155374887,
"grad_norm": 0.16327470933567317,
"learning_rate": 6.513155496266783e-06,
"loss": 0.5641,
"step": 392
},
{
"epoch": 0.7100271002710027,
"grad_norm": 0.1574337263337296,
"learning_rate": 6.439296484733526e-06,
"loss": 0.5689,
"step": 393
},
{
"epoch": 0.7118337850045167,
"grad_norm": 0.16018951967211098,
"learning_rate": 6.3657440147149e-06,
"loss": 0.5716,
"step": 394
},
{
"epoch": 0.7136404697380307,
"grad_norm": 0.14974112027258443,
"learning_rate": 6.292500719976397e-06,
"loss": 0.5659,
"step": 395
},
{
"epoch": 0.7154471544715447,
"grad_norm": 0.16158709365351387,
"learning_rate": 6.219569223212585e-06,
"loss": 0.56,
"step": 396
},
{
"epoch": 0.7172538392050587,
"grad_norm": 0.15600729659089102,
"learning_rate": 6.146952135953158e-06,
"loss": 0.5598,
"step": 397
},
{
"epoch": 0.7190605239385727,
"grad_norm": 0.15620491253414515,
"learning_rate": 6.074652058469447e-06,
"loss": 0.5616,
"step": 398
},
{
"epoch": 0.7208672086720868,
"grad_norm": 0.16380045583881614,
"learning_rate": 6.0026715796812945e-06,
"loss": 0.5644,
"step": 399
},
{
"epoch": 0.7226738934056007,
"grad_norm": 0.14967907113452944,
"learning_rate": 5.931013277064377e-06,
"loss": 0.5609,
"step": 400
},
{
"epoch": 0.7244805781391147,
"grad_norm": 0.15280123889646421,
"learning_rate": 5.859679716557879e-06,
"loss": 0.5626,
"step": 401
},
{
"epoch": 0.7262872628726287,
"grad_norm": 0.16341975790372415,
"learning_rate": 5.788673452472622e-06,
"loss": 0.5696,
"step": 402
},
{
"epoch": 0.7280939476061428,
"grad_norm": 0.1562147019531761,
"learning_rate": 5.717997027399624e-06,
"loss": 0.5516,
"step": 403
},
{
"epoch": 0.7299006323396567,
"grad_norm": 0.15660229823809,
"learning_rate": 5.647652972118998e-06,
"loss": 0.5569,
"step": 404
},
{
"epoch": 0.7317073170731707,
"grad_norm": 0.16555666302974795,
"learning_rate": 5.577643805509404e-06,
"loss": 0.5549,
"step": 405
},
{
"epoch": 0.7335140018066847,
"grad_norm": 0.1507767089868411,
"learning_rate": 5.507972034457786e-06,
"loss": 0.5615,
"step": 406
},
{
"epoch": 0.7353206865401988,
"grad_norm": 0.1557734692497816,
"learning_rate": 5.438640153769654e-06,
"loss": 0.5534,
"step": 407
},
{
"epoch": 0.7371273712737128,
"grad_norm": 0.14782949914277185,
"learning_rate": 5.369650646079719e-06,
"loss": 0.547,
"step": 408
},
{
"epoch": 0.7389340560072267,
"grad_norm": 0.17200870547934033,
"learning_rate": 5.301005981763007e-06,
"loss": 0.5669,
"step": 409
},
{
"epoch": 0.7407407407407407,
"grad_norm": 0.16956590081345058,
"learning_rate": 5.2327086188463964e-06,
"loss": 0.5672,
"step": 410
},
{
"epoch": 0.7425474254742548,
"grad_norm": 0.17288972695084148,
"learning_rate": 5.164761002920615e-06,
"loss": 0.5695,
"step": 411
},
{
"epoch": 0.7443541102077688,
"grad_norm": 0.15302551358387134,
"learning_rate": 5.097165567052646e-06,
"loss": 0.543,
"step": 412
},
{
"epoch": 0.7461607949412827,
"grad_norm": 0.1659332169274283,
"learning_rate": 5.029924731698619e-06,
"loss": 0.5586,
"step": 413
},
{
"epoch": 0.7479674796747967,
"grad_norm": 0.14771275975107256,
"learning_rate": 4.963040904617131e-06,
"loss": 0.5466,
"step": 414
},
{
"epoch": 0.7497741644083108,
"grad_norm": 0.14811614613987537,
"learning_rate": 4.8965164807830355e-06,
"loss": 0.568,
"step": 415
},
{
"epoch": 0.7515808491418248,
"grad_norm": 0.1448610651899535,
"learning_rate": 4.83035384230169e-06,
"loss": 0.5537,
"step": 416
},
{
"epoch": 0.7533875338753387,
"grad_norm": 0.1705391112022685,
"learning_rate": 4.764555358323632e-06,
"loss": 0.5756,
"step": 417
},
{
"epoch": 0.7551942186088527,
"grad_norm": 0.17264531117869172,
"learning_rate": 4.699123384959783e-06,
"loss": 0.5576,
"step": 418
},
{
"epoch": 0.7570009033423668,
"grad_norm": 0.15278513072031447,
"learning_rate": 4.6340602651970304e-06,
"loss": 0.559,
"step": 419
},
{
"epoch": 0.7588075880758808,
"grad_norm": 0.15921165848077162,
"learning_rate": 4.5693683288143884e-06,
"loss": 0.5727,
"step": 420
},
{
"epoch": 0.7606142728093948,
"grad_norm": 0.14827263328330628,
"learning_rate": 4.505049892299517e-06,
"loss": 0.5544,
"step": 421
},
{
"epoch": 0.7624209575429087,
"grad_norm": 0.13887513696660272,
"learning_rate": 4.441107258765827e-06,
"loss": 0.5578,
"step": 422
},
{
"epoch": 0.7642276422764228,
"grad_norm": 0.15863025954427973,
"learning_rate": 4.377542717869959e-06,
"loss": 0.5669,
"step": 423
},
{
"epoch": 0.7660343270099368,
"grad_norm": 0.16888324911277486,
"learning_rate": 4.31435854572983e-06,
"loss": 0.5701,
"step": 424
},
{
"epoch": 0.7678410117434508,
"grad_norm": 0.1543410763323266,
"learning_rate": 4.251557004843116e-06,
"loss": 0.5489,
"step": 425
},
{
"epoch": 0.7696476964769647,
"grad_norm": 0.1535360923186684,
"learning_rate": 4.1891403440062495e-06,
"loss": 0.5696,
"step": 426
},
{
"epoch": 0.7714543812104788,
"grad_norm": 0.1436847387652519,
"learning_rate": 4.1271107982338745e-06,
"loss": 0.541,
"step": 427
},
{
"epoch": 0.7732610659439928,
"grad_norm": 0.14133645853071267,
"learning_rate": 4.06547058867883e-06,
"loss": 0.5616,
"step": 428
},
{
"epoch": 0.7750677506775068,
"grad_norm": 0.14833855735489168,
"learning_rate": 4.004221922552608e-06,
"loss": 0.5567,
"step": 429
},
{
"epoch": 0.7768744354110207,
"grad_norm": 0.13504301863448828,
"learning_rate": 3.943366993046323e-06,
"loss": 0.5573,
"step": 430
},
{
"epoch": 0.7786811201445348,
"grad_norm": 0.15479562167447294,
"learning_rate": 3.88290797925218e-06,
"loss": 0.5665,
"step": 431
},
{
"epoch": 0.7804878048780488,
"grad_norm": 0.14971545791291554,
"learning_rate": 3.82284704608543e-06,
"loss": 0.5618,
"step": 432
},
{
"epoch": 0.7822944896115628,
"grad_norm": 0.15163059932702447,
"learning_rate": 3.763186344206877e-06,
"loss": 0.5694,
"step": 433
},
{
"epoch": 0.7841011743450768,
"grad_norm": 0.14913417270860077,
"learning_rate": 3.7039280099458373e-06,
"loss": 0.5678,
"step": 434
},
{
"epoch": 0.7859078590785907,
"grad_norm": 0.13874898886438794,
"learning_rate": 3.645074165223656e-06,
"loss": 0.5457,
"step": 435
},
{
"epoch": 0.7877145438121048,
"grad_norm": 0.15341138739380675,
"learning_rate": 3.586626917477724e-06,
"loss": 0.5599,
"step": 436
},
{
"epoch": 0.7895212285456188,
"grad_norm": 0.1396125925965087,
"learning_rate": 3.528588359586024e-06,
"loss": 0.5586,
"step": 437
},
{
"epoch": 0.7913279132791328,
"grad_norm": 0.1724528227666086,
"learning_rate": 3.4709605697921735e-06,
"loss": 0.5499,
"step": 438
},
{
"epoch": 0.7931345980126467,
"grad_norm": 0.15954102946516008,
"learning_rate": 3.413745611631009e-06,
"loss": 0.5672,
"step": 439
},
{
"epoch": 0.7949412827461608,
"grad_norm": 0.13471275186125906,
"learning_rate": 3.356945533854708e-06,
"loss": 0.5582,
"step": 440
},
{
"epoch": 0.7967479674796748,
"grad_norm": 0.1277139415264683,
"learning_rate": 3.3005623703594082e-06,
"loss": 0.544,
"step": 441
},
{
"epoch": 0.7985546522131888,
"grad_norm": 0.13269007698962448,
"learning_rate": 3.244598140112404e-06,
"loss": 0.5531,
"step": 442
},
{
"epoch": 0.8003613369467028,
"grad_norm": 0.16876313389901235,
"learning_rate": 3.1890548470798196e-06,
"loss": 0.5603,
"step": 443
},
{
"epoch": 0.8021680216802168,
"grad_norm": 0.14703779234405664,
"learning_rate": 3.1339344801548854e-06,
"loss": 0.5662,
"step": 444
},
{
"epoch": 0.8039747064137308,
"grad_norm": 0.16211778059337975,
"learning_rate": 3.079239013086673e-06,
"loss": 0.5541,
"step": 445
},
{
"epoch": 0.8057813911472448,
"grad_norm": 0.13960967725757564,
"learning_rate": 3.02497040440948e-06,
"loss": 0.5521,
"step": 446
},
{
"epoch": 0.8075880758807588,
"grad_norm": 0.14347409440257566,
"learning_rate": 2.9711305973726404e-06,
"loss": 0.5568,
"step": 447
},
{
"epoch": 0.8093947606142728,
"grad_norm": 0.13685149510690353,
"learning_rate": 2.91772151987099e-06,
"loss": 0.5595,
"step": 448
},
{
"epoch": 0.8112014453477868,
"grad_norm": 0.14371214973855934,
"learning_rate": 2.86474508437579e-06,
"loss": 0.5541,
"step": 449
},
{
"epoch": 0.8130081300813008,
"grad_norm": 0.13902608999443639,
"learning_rate": 2.812203187866272e-06,
"loss": 0.5651,
"step": 450
},
{
"epoch": 0.8148148148148148,
"grad_norm": 0.18456478885896846,
"learning_rate": 2.7600977117617027e-06,
"loss": 0.566,
"step": 451
},
{
"epoch": 0.8166214995483289,
"grad_norm": 0.13874263584368351,
"learning_rate": 2.7084305218540217e-06,
"loss": 0.5626,
"step": 452
},
{
"epoch": 0.8184281842818428,
"grad_norm": 0.13915434189224746,
"learning_rate": 2.6572034682410144e-06,
"loss": 0.5547,
"step": 453
},
{
"epoch": 0.8202348690153568,
"grad_norm": 0.14072111536288506,
"learning_rate": 2.60641838526008e-06,
"loss": 0.5396,
"step": 454
},
{
"epoch": 0.8220415537488708,
"grad_norm": 0.13282415327633357,
"learning_rate": 2.5560770914225356e-06,
"loss": 0.5625,
"step": 455
},
{
"epoch": 0.8238482384823849,
"grad_norm": 0.1472812938618023,
"learning_rate": 2.5061813893485087e-06,
"loss": 0.5549,
"step": 456
},
{
"epoch": 0.8256549232158988,
"grad_norm": 0.14223186780386796,
"learning_rate": 2.45673306570239e-06,
"loss": 0.5692,
"step": 457
},
{
"epoch": 0.8274616079494128,
"grad_norm": 0.13382708637823343,
"learning_rate": 2.407733891128841e-06,
"loss": 0.5612,
"step": 458
},
{
"epoch": 0.8292682926829268,
"grad_norm": 0.13648137063446,
"learning_rate": 2.3591856201894124e-06,
"loss": 0.5511,
"step": 459
},
{
"epoch": 0.8310749774164409,
"grad_norm": 0.1547065089258408,
"learning_rate": 2.3110899912996993e-06,
"loss": 0.5602,
"step": 460
},
{
"epoch": 0.8328816621499548,
"grad_norm": 0.14643671146676157,
"learning_rate": 2.263448726667098e-06,
"loss": 0.548,
"step": 461
},
{
"epoch": 0.8346883468834688,
"grad_norm": 0.13651107636976717,
"learning_rate": 2.2162635322291365e-06,
"loss": 0.556,
"step": 462
},
{
"epoch": 0.8364950316169828,
"grad_norm": 0.1368276434381763,
"learning_rate": 2.169536097592401e-06,
"loss": 0.5603,
"step": 463
},
{
"epoch": 0.8383017163504969,
"grad_norm": 0.1445464211298085,
"learning_rate": 2.1232680959720085e-06,
"loss": 0.5628,
"step": 464
},
{
"epoch": 0.8401084010840109,
"grad_norm": 0.1581727260316551,
"learning_rate": 2.0774611841317164e-06,
"loss": 0.5728,
"step": 465
},
{
"epoch": 0.8419150858175248,
"grad_norm": 0.13832300858835891,
"learning_rate": 2.0321170023245835e-06,
"loss": 0.5554,
"step": 466
},
{
"epoch": 0.8437217705510388,
"grad_norm": 0.1326854914012355,
"learning_rate": 1.9872371742342366e-06,
"loss": 0.5525,
"step": 467
},
{
"epoch": 0.8455284552845529,
"grad_norm": 0.1324315694543524,
"learning_rate": 1.942823306916746e-06,
"loss": 0.5629,
"step": 468
},
{
"epoch": 0.8473351400180669,
"grad_norm": 0.14327810150506223,
"learning_rate": 1.8988769907430553e-06,
"loss": 0.5522,
"step": 469
},
{
"epoch": 0.8491418247515808,
"grad_norm": 0.1440779207735543,
"learning_rate": 1.8553997993420495e-06,
"loss": 0.5485,
"step": 470
},
{
"epoch": 0.8509485094850948,
"grad_norm": 0.1582379305959562,
"learning_rate": 1.8123932895441953e-06,
"loss": 0.5777,
"step": 471
},
{
"epoch": 0.8527551942186089,
"grad_norm": 0.13834720570877437,
"learning_rate": 1.7698590013258187e-06,
"loss": 0.5486,
"step": 472
},
{
"epoch": 0.8545618789521229,
"grad_norm": 0.13843120298455933,
"learning_rate": 1.7277984577539224e-06,
"loss": 0.5676,
"step": 473
},
{
"epoch": 0.8563685636856369,
"grad_norm": 0.1279953110251041,
"learning_rate": 1.6862131649316885e-06,
"loss": 0.5629,
"step": 474
},
{
"epoch": 0.8581752484191508,
"grad_norm": 0.1585683209243492,
"learning_rate": 1.6451046119445174e-06,
"loss": 0.553,
"step": 475
},
{
"epoch": 0.8599819331526649,
"grad_norm": 0.1466497632190738,
"learning_rate": 1.6044742708067206e-06,
"loss": 0.5592,
"step": 476
},
{
"epoch": 0.8617886178861789,
"grad_norm": 0.1387550564906503,
"learning_rate": 1.5643235964088065e-06,
"loss": 0.5564,
"step": 477
},
{
"epoch": 0.8635953026196929,
"grad_norm": 0.14950588928435643,
"learning_rate": 1.524654026465394e-06,
"loss": 0.5671,
"step": 478
},
{
"epoch": 0.8654019873532068,
"grad_norm": 0.14015867212642105,
"learning_rate": 1.4854669814637145e-06,
"loss": 0.5532,
"step": 479
},
{
"epoch": 0.8672086720867209,
"grad_norm": 0.1262404297566839,
"learning_rate": 1.4467638646127551e-06,
"loss": 0.5513,
"step": 480
},
{
"epoch": 0.8690153568202349,
"grad_norm": 0.12824154810533317,
"learning_rate": 1.4085460617930196e-06,
"loss": 0.5622,
"step": 481
},
{
"epoch": 0.8708220415537489,
"grad_norm": 0.1345600337122948,
"learning_rate": 1.3708149415068827e-06,
"loss": 0.5661,
"step": 482
},
{
"epoch": 0.8726287262872628,
"grad_norm": 0.13838894371767235,
"learning_rate": 1.3335718548296194e-06,
"loss": 0.5504,
"step": 483
},
{
"epoch": 0.8744354110207768,
"grad_norm": 0.13576491587772027,
"learning_rate": 1.2968181353609854e-06,
"loss": 0.5472,
"step": 484
},
{
"epoch": 0.8762420957542909,
"grad_norm": 0.14339241553346477,
"learning_rate": 1.2605550991775033e-06,
"loss": 0.5576,
"step": 485
},
{
"epoch": 0.8780487804878049,
"grad_norm": 0.131210165981635,
"learning_rate": 1.2247840447852993e-06,
"loss": 0.5633,
"step": 486
},
{
"epoch": 0.8798554652213189,
"grad_norm": 0.12636963673731474,
"learning_rate": 1.1895062530736412e-06,
"loss": 0.5515,
"step": 487
},
{
"epoch": 0.8816621499548328,
"grad_norm": 0.12776691333292706,
"learning_rate": 1.1547229872690407e-06,
"loss": 0.5505,
"step": 488
},
{
"epoch": 0.8834688346883469,
"grad_norm": 0.12702102055757536,
"learning_rate": 1.1204354928900496e-06,
"loss": 0.5602,
"step": 489
},
{
"epoch": 0.8852755194218609,
"grad_norm": 0.13494740824410642,
"learning_rate": 1.086644997702635e-06,
"loss": 0.5571,
"step": 490
},
{
"epoch": 0.8870822041553749,
"grad_norm": 0.12513086965807382,
"learning_rate": 1.0533527116762298e-06,
"loss": 0.5483,
"step": 491
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.1320750230179298,
"learning_rate": 1.0205598269404026e-06,
"loss": 0.55,
"step": 492
},
{
"epoch": 0.8906955736224029,
"grad_norm": 0.12753125629115394,
"learning_rate": 9.882675177421662e-07,
"loss": 0.5444,
"step": 493
},
{
"epoch": 0.8925022583559169,
"grad_norm": 0.12278292224063106,
"learning_rate": 9.56476940403942e-07,
"loss": 0.5617,
"step": 494
},
{
"epoch": 0.8943089430894309,
"grad_norm": 0.13711394488670506,
"learning_rate": 9.251892332821388e-07,
"loss": 0.5584,
"step": 495
},
{
"epoch": 0.8961156278229448,
"grad_norm": 0.13665462597200176,
"learning_rate": 8.944055167263982e-07,
"loss": 0.5706,
"step": 496
},
{
"epoch": 0.8979223125564589,
"grad_norm": 0.14101341052067656,
"learning_rate": 8.641268930394791e-07,
"loss": 0.5578,
"step": 497
},
{
"epoch": 0.8997289972899729,
"grad_norm": 0.1371088435731868,
"learning_rate": 8.34354446437785e-07,
"loss": 0.5571,
"step": 498
},
{
"epoch": 0.9015356820234869,
"grad_norm": 0.15044968278360257,
"learning_rate": 8.050892430125362e-07,
"loss": 0.5662,
"step": 499
},
{
"epoch": 0.9033423667570009,
"grad_norm": 0.13190920385566557,
"learning_rate": 7.763323306916037e-07,
"loss": 0.565,
"step": 500
}
],
"logging_steps": 1,
"max_steps": 553,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 579500543967232.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}