scaling_exp_refSoM / checkpoint-2400 /trainer_state.json
sujr's picture
Upload folder using huggingface_hub
db13894 verified
raw
history blame
42.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4038364462392731,
"eval_steps": 500,
"global_step": 2400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0016826518593303045,
"grad_norm": 5.367858933563703,
"learning_rate": 4.9999999999999996e-06,
"loss": 0.9537,
"step": 10
},
{
"epoch": 0.003365303718660609,
"grad_norm": 9.386746384686745,
"learning_rate": 9.999999999999999e-06,
"loss": 0.943,
"step": 20
},
{
"epoch": 0.005047955577990914,
"grad_norm": 7.387362447577942,
"learning_rate": 1.5e-05,
"loss": 0.934,
"step": 30
},
{
"epoch": 0.006730607437321218,
"grad_norm": 6.9256319824932655,
"learning_rate": 1.9999999999999998e-05,
"loss": 0.8376,
"step": 40
},
{
"epoch": 0.008413259296651522,
"grad_norm": 9.1148382590838,
"learning_rate": 2.5e-05,
"loss": 0.8484,
"step": 50
},
{
"epoch": 0.010095911155981827,
"grad_norm": 3.9989232759892426,
"learning_rate": 3e-05,
"loss": 0.8097,
"step": 60
},
{
"epoch": 0.011778563015312132,
"grad_norm": 3.892371218590039,
"learning_rate": 2.9999786123888308e-05,
"loss": 0.7811,
"step": 70
},
{
"epoch": 0.013461214874642436,
"grad_norm": 8.096662196282066,
"learning_rate": 2.9999144501652298e-05,
"loss": 0.7446,
"step": 80
},
{
"epoch": 0.01514386673397274,
"grad_norm": 1.5769306611206149,
"learning_rate": 2.9998075151588992e-05,
"loss": 0.7258,
"step": 90
},
{
"epoch": 0.016826518593303044,
"grad_norm": 8.47430485487969,
"learning_rate": 2.999657810419285e-05,
"loss": 0.7052,
"step": 100
},
{
"epoch": 0.01850917045263335,
"grad_norm": 2.363071299913598,
"learning_rate": 2.999465340215489e-05,
"loss": 0.7657,
"step": 110
},
{
"epoch": 0.020191822311963654,
"grad_norm": 1.9252385425154874,
"learning_rate": 2.999230110036149e-05,
"loss": 0.7329,
"step": 120
},
{
"epoch": 0.02187447417129396,
"grad_norm": 8.946028475031488,
"learning_rate": 2.99895212658928e-05,
"loss": 0.7304,
"step": 130
},
{
"epoch": 0.023557126030624265,
"grad_norm": 6.877609312630206,
"learning_rate": 2.9986313978020846e-05,
"loss": 0.7453,
"step": 140
},
{
"epoch": 0.02523977788995457,
"grad_norm": 2.5256324882367993,
"learning_rate": 2.9982679328207262e-05,
"loss": 0.7366,
"step": 150
},
{
"epoch": 0.02692242974928487,
"grad_norm": 2.709550398238738,
"learning_rate": 2.9978617420100692e-05,
"loss": 0.7258,
"step": 160
},
{
"epoch": 0.028605081608615177,
"grad_norm": 1.543550019689774,
"learning_rate": 2.9974128369533805e-05,
"loss": 0.7372,
"step": 170
},
{
"epoch": 0.03028773346794548,
"grad_norm": 3.3453966881155504,
"learning_rate": 2.9969212304520034e-05,
"loss": 0.743,
"step": 180
},
{
"epoch": 0.03197038532727579,
"grad_norm": 1.922001656181265,
"learning_rate": 2.9963869365249895e-05,
"loss": 0.7819,
"step": 190
},
{
"epoch": 0.03365303718660609,
"grad_norm": 2.0611188483400036,
"learning_rate": 2.995809970408699e-05,
"loss": 0.7155,
"step": 200
},
{
"epoch": 0.0353356890459364,
"grad_norm": 1.5313041833127259,
"learning_rate": 2.9951903485563685e-05,
"loss": 0.7322,
"step": 210
},
{
"epoch": 0.0370183409052667,
"grad_norm": 2.0124191694435085,
"learning_rate": 2.99452808863764e-05,
"loss": 0.6759,
"step": 220
},
{
"epoch": 0.03870099276459701,
"grad_norm": 3.182123324389477,
"learning_rate": 2.993823209538056e-05,
"loss": 0.6953,
"step": 230
},
{
"epoch": 0.04038364462392731,
"grad_norm": 1.6122782177661379,
"learning_rate": 2.9930757313585238e-05,
"loss": 0.6953,
"step": 240
},
{
"epoch": 0.04206629648325761,
"grad_norm": 2.2027482596695647,
"learning_rate": 2.9922856754147406e-05,
"loss": 0.7301,
"step": 250
},
{
"epoch": 0.04374894834258792,
"grad_norm": 2.6782477155989213,
"learning_rate": 2.9914530642365852e-05,
"loss": 0.6891,
"step": 260
},
{
"epoch": 0.04543160020191822,
"grad_norm": 1.9740401144541417,
"learning_rate": 2.990577921567476e-05,
"loss": 0.7231,
"step": 270
},
{
"epoch": 0.04711425206124853,
"grad_norm": 1.719874620968932,
"learning_rate": 2.989660272363696e-05,
"loss": 0.7505,
"step": 280
},
{
"epoch": 0.04879690392057883,
"grad_norm": 1.3138364164203409,
"learning_rate": 2.988700142793676e-05,
"loss": 0.7116,
"step": 290
},
{
"epoch": 0.05047955577990914,
"grad_norm": 5.853627389344256,
"learning_rate": 2.9876975602372536e-05,
"loss": 0.719,
"step": 300
},
{
"epoch": 0.05216220763923944,
"grad_norm": 2.347259437170711,
"learning_rate": 2.9866525532848906e-05,
"loss": 0.6803,
"step": 310
},
{
"epoch": 0.05384485949856974,
"grad_norm": 1.937679220955038,
"learning_rate": 2.9855651517368567e-05,
"loss": 0.7461,
"step": 320
},
{
"epoch": 0.05552751135790005,
"grad_norm": 1.6661300351569575,
"learning_rate": 2.9844353866023802e-05,
"loss": 0.7472,
"step": 330
},
{
"epoch": 0.05721016321723035,
"grad_norm": 2.357915869204484,
"learning_rate": 2.9832632900987642e-05,
"loss": 0.7148,
"step": 340
},
{
"epoch": 0.05889281507656066,
"grad_norm": 4.398815186243292,
"learning_rate": 2.982048895650468e-05,
"loss": 0.6992,
"step": 350
},
{
"epoch": 0.06057546693589096,
"grad_norm": 12.662682224480092,
"learning_rate": 2.9807922378881537e-05,
"loss": 0.7539,
"step": 360
},
{
"epoch": 0.06225811879522127,
"grad_norm": 0.8642696401357872,
"learning_rate": 2.979493352647697e-05,
"loss": 0.7212,
"step": 370
},
{
"epoch": 0.06394077065455157,
"grad_norm": 27.047937858232604,
"learning_rate": 2.9781522769691686e-05,
"loss": 0.722,
"step": 380
},
{
"epoch": 0.06562342251388188,
"grad_norm": 2.598805292448644,
"learning_rate": 2.9767690490957758e-05,
"loss": 0.7065,
"step": 390
},
{
"epoch": 0.06730607437321218,
"grad_norm": 1.2314762895092763,
"learning_rate": 2.9753437084727713e-05,
"loss": 0.7498,
"step": 400
},
{
"epoch": 0.06898872623254249,
"grad_norm": 1.6421909669790502,
"learning_rate": 2.9738762957463292e-05,
"loss": 0.6992,
"step": 410
},
{
"epoch": 0.0706713780918728,
"grad_norm": 2.023552968622588,
"learning_rate": 2.9723668527623877e-05,
"loss": 0.6943,
"step": 420
},
{
"epoch": 0.0723540299512031,
"grad_norm": 1.5172337910969138,
"learning_rate": 2.9708154225654526e-05,
"loss": 0.6987,
"step": 430
},
{
"epoch": 0.0740366818105334,
"grad_norm": 1.197852135730745,
"learning_rate": 2.9692220493973712e-05,
"loss": 0.7302,
"step": 440
},
{
"epoch": 0.0757193336698637,
"grad_norm": 2.4396443837967183,
"learning_rate": 2.9675867786960718e-05,
"loss": 0.7318,
"step": 450
},
{
"epoch": 0.07740198552919401,
"grad_norm": 1.4599851880563282,
"learning_rate": 2.9659096570942654e-05,
"loss": 0.6941,
"step": 460
},
{
"epoch": 0.07908463738852431,
"grad_norm": 1.117755825364562,
"learning_rate": 2.9641907324181194e-05,
"loss": 0.7399,
"step": 470
},
{
"epoch": 0.08076728924785462,
"grad_norm": 2.9235378164576242,
"learning_rate": 2.96243005368589e-05,
"loss": 0.7207,
"step": 480
},
{
"epoch": 0.08244994110718493,
"grad_norm": 7.308883163781362,
"learning_rate": 2.960627671106527e-05,
"loss": 0.682,
"step": 490
},
{
"epoch": 0.08413259296651522,
"grad_norm": 3.4394827932955234,
"learning_rate": 2.9587836360782405e-05,
"loss": 0.708,
"step": 500
},
{
"epoch": 0.08581524482584553,
"grad_norm": 3.2314529856927634,
"learning_rate": 2.9568980011870357e-05,
"loss": 0.7335,
"step": 510
},
{
"epoch": 0.08749789668517584,
"grad_norm": 1.825724533695325,
"learning_rate": 2.954970820205214e-05,
"loss": 0.6951,
"step": 520
},
{
"epoch": 0.08918054854450615,
"grad_norm": 3.3231741746640076,
"learning_rate": 2.9530021480898393e-05,
"loss": 0.7793,
"step": 530
},
{
"epoch": 0.09086320040383644,
"grad_norm": 1.3097651462571123,
"learning_rate": 2.9509920409811696e-05,
"loss": 0.7087,
"step": 540
},
{
"epoch": 0.09254585226316675,
"grad_norm": 6.685911471215255,
"learning_rate": 2.9489405562010565e-05,
"loss": 0.6906,
"step": 550
},
{
"epoch": 0.09422850412249706,
"grad_norm": 2.870746617513948,
"learning_rate": 2.9468477522513132e-05,
"loss": 0.7028,
"step": 560
},
{
"epoch": 0.09591115598182735,
"grad_norm": 1.782555352805469,
"learning_rate": 2.9447136888120408e-05,
"loss": 0.6901,
"step": 570
},
{
"epoch": 0.09759380784115766,
"grad_norm": 2.336519711000487,
"learning_rate": 2.9425384267399327e-05,
"loss": 0.7779,
"step": 580
},
{
"epoch": 0.09927645970048797,
"grad_norm": 8.935574410818228,
"learning_rate": 2.940322028066534e-05,
"loss": 0.7503,
"step": 590
},
{
"epoch": 0.10095911155981828,
"grad_norm": 2.754713786882031,
"learning_rate": 2.938064555996476e-05,
"loss": 0.7208,
"step": 600
},
{
"epoch": 0.10264176341914857,
"grad_norm": 1.5082503557652136,
"learning_rate": 2.9357660749056713e-05,
"loss": 0.7169,
"step": 610
},
{
"epoch": 0.10432441527847888,
"grad_norm": 9.04522194526273,
"learning_rate": 2.9334266503394803e-05,
"loss": 0.6927,
"step": 620
},
{
"epoch": 0.10600706713780919,
"grad_norm": 55.28278686388287,
"learning_rate": 2.9310463490108397e-05,
"loss": 0.7107,
"step": 630
},
{
"epoch": 0.10768971899713949,
"grad_norm": 3.721916069105249,
"learning_rate": 2.928625238798362e-05,
"loss": 0.6951,
"step": 640
},
{
"epoch": 0.1093723708564698,
"grad_norm": 2.5040797323750112,
"learning_rate": 2.9261633887443993e-05,
"loss": 0.6916,
"step": 650
},
{
"epoch": 0.1110550227158001,
"grad_norm": 3.5468924769840617,
"learning_rate": 2.9236608690530738e-05,
"loss": 0.7077,
"step": 660
},
{
"epoch": 0.11273767457513041,
"grad_norm": 3.0266819778200746,
"learning_rate": 2.921117751088276e-05,
"loss": 0.6952,
"step": 670
},
{
"epoch": 0.1144203264344607,
"grad_norm": 1.634743894298146,
"learning_rate": 2.91853410737163e-05,
"loss": 0.6936,
"step": 680
},
{
"epoch": 0.11610297829379101,
"grad_norm": 1.0925365801520501,
"learning_rate": 2.915910011580426e-05,
"loss": 0.7317,
"step": 690
},
{
"epoch": 0.11778563015312132,
"grad_norm": 1.6959112138540386,
"learning_rate": 2.9132455385455176e-05,
"loss": 0.6917,
"step": 700
},
{
"epoch": 0.11946828201245162,
"grad_norm": 1.9723433746891168,
"learning_rate": 2.9105407642491895e-05,
"loss": 0.7209,
"step": 710
},
{
"epoch": 0.12115093387178193,
"grad_norm": 2.1537215293733833,
"learning_rate": 2.907795765822989e-05,
"loss": 0.7488,
"step": 720
},
{
"epoch": 0.12283358573111224,
"grad_norm": 3.227101869737169,
"learning_rate": 2.9050106215455283e-05,
"loss": 0.7152,
"step": 730
},
{
"epoch": 0.12451623759044254,
"grad_norm": 2.7222358893572554,
"learning_rate": 2.9021854108402516e-05,
"loss": 0.708,
"step": 740
},
{
"epoch": 0.12619888944977284,
"grad_norm": 2.1054843767538136,
"learning_rate": 2.8993202142731693e-05,
"loss": 0.7251,
"step": 750
},
{
"epoch": 0.12788154130910315,
"grad_norm": 2.11845883419618,
"learning_rate": 2.8964151135505616e-05,
"loss": 0.7405,
"step": 760
},
{
"epoch": 0.12956419316843346,
"grad_norm": 13.171512404187755,
"learning_rate": 2.8934701915166477e-05,
"loss": 0.6844,
"step": 770
},
{
"epoch": 0.13124684502776376,
"grad_norm": 2.7633375632879127,
"learning_rate": 2.890485532151225e-05,
"loss": 0.6766,
"step": 780
},
{
"epoch": 0.13292949688709407,
"grad_norm": 1.8420785342693768,
"learning_rate": 2.887461220567271e-05,
"loss": 0.7037,
"step": 790
},
{
"epoch": 0.13461214874642435,
"grad_norm": 1.5557447509529954,
"learning_rate": 2.8843973430085204e-05,
"loss": 0.6991,
"step": 800
},
{
"epoch": 0.13629480060575466,
"grad_norm": 1.9295826624758823,
"learning_rate": 2.8812939868470016e-05,
"loss": 0.6956,
"step": 810
},
{
"epoch": 0.13797745246508497,
"grad_norm": 3.3211216557707126,
"learning_rate": 2.878151240580548e-05,
"loss": 0.6774,
"step": 820
},
{
"epoch": 0.13966010432441528,
"grad_norm": 4.196064403930616,
"learning_rate": 2.874969193830274e-05,
"loss": 0.6752,
"step": 830
},
{
"epoch": 0.1413427561837456,
"grad_norm": 5.574976270137628,
"learning_rate": 2.871747937338016e-05,
"loss": 0.6553,
"step": 840
},
{
"epoch": 0.1430254080430759,
"grad_norm": 1.6494038718740478,
"learning_rate": 2.8684875629637505e-05,
"loss": 0.7152,
"step": 850
},
{
"epoch": 0.1447080599024062,
"grad_norm": 1.3061892609414858,
"learning_rate": 2.8651881636829698e-05,
"loss": 0.7462,
"step": 860
},
{
"epoch": 0.1463907117617365,
"grad_norm": 4.321044418392694,
"learning_rate": 2.861849833584032e-05,
"loss": 0.6902,
"step": 870
},
{
"epoch": 0.1480733636210668,
"grad_norm": 2.9444722968009764,
"learning_rate": 2.8584726678654787e-05,
"loss": 0.6813,
"step": 880
},
{
"epoch": 0.1497560154803971,
"grad_norm": 1.4940245340163587,
"learning_rate": 2.85505676283332e-05,
"loss": 0.689,
"step": 890
},
{
"epoch": 0.1514386673397274,
"grad_norm": 3.3704010040589565,
"learning_rate": 2.851602215898287e-05,
"loss": 0.6953,
"step": 900
},
{
"epoch": 0.15312131919905772,
"grad_norm": 1.6597144402924948,
"learning_rate": 2.8481091255730552e-05,
"loss": 0.7277,
"step": 910
},
{
"epoch": 0.15480397105838803,
"grad_norm": 10.969872224353953,
"learning_rate": 2.844577591469435e-05,
"loss": 0.7142,
"step": 920
},
{
"epoch": 0.15648662291771834,
"grad_norm": 8.45616831264245,
"learning_rate": 2.8410077142955304e-05,
"loss": 0.7197,
"step": 930
},
{
"epoch": 0.15816927477704862,
"grad_norm": 2.9594258901214427,
"learning_rate": 2.8373995958528683e-05,
"loss": 0.7351,
"step": 940
},
{
"epoch": 0.15985192663637893,
"grad_norm": 2.168676312428759,
"learning_rate": 2.8337533390334942e-05,
"loss": 0.7544,
"step": 950
},
{
"epoch": 0.16153457849570924,
"grad_norm": 7.898767360662744,
"learning_rate": 2.8300690478170388e-05,
"loss": 0.7015,
"step": 960
},
{
"epoch": 0.16321723035503954,
"grad_norm": 16.83650212945308,
"learning_rate": 2.826346827267753e-05,
"loss": 0.7139,
"step": 970
},
{
"epoch": 0.16489988221436985,
"grad_norm": 2.3791337429068977,
"learning_rate": 2.8225867835315114e-05,
"loss": 0.7053,
"step": 980
},
{
"epoch": 0.16658253407370016,
"grad_norm": 1.9679363325295285,
"learning_rate": 2.8187890238327842e-05,
"loss": 0.7313,
"step": 990
},
{
"epoch": 0.16826518593303044,
"grad_norm": 1.4822625638777076,
"learning_rate": 2.814953656471583e-05,
"loss": 0.7085,
"step": 1000
},
{
"epoch": 0.16994783779236075,
"grad_norm": 2.647291447509443,
"learning_rate": 2.8110807908203682e-05,
"loss": 0.6638,
"step": 1010
},
{
"epoch": 0.17163048965169106,
"grad_norm": 2.969379719654364,
"learning_rate": 2.8071705373209328e-05,
"loss": 0.6884,
"step": 1020
},
{
"epoch": 0.17331314151102137,
"grad_norm": 1.1163745403124403,
"learning_rate": 2.803223007481252e-05,
"loss": 0.6885,
"step": 1030
},
{
"epoch": 0.17499579337035168,
"grad_norm": 1.2686557979094786,
"learning_rate": 2.7992383138723034e-05,
"loss": 0.7037,
"step": 1040
},
{
"epoch": 0.17667844522968199,
"grad_norm": 4.648945448875594,
"learning_rate": 2.7952165701248573e-05,
"loss": 0.6933,
"step": 1050
},
{
"epoch": 0.1783610970890123,
"grad_norm": 4.723564874595428,
"learning_rate": 2.7911578909262353e-05,
"loss": 0.7144,
"step": 1060
},
{
"epoch": 0.18004374894834257,
"grad_norm": 5.211806926801946,
"learning_rate": 2.787062392017041e-05,
"loss": 0.7266,
"step": 1070
},
{
"epoch": 0.18172640080767288,
"grad_norm": 1.3725560316172503,
"learning_rate": 2.7829301901878592e-05,
"loss": 0.7445,
"step": 1080
},
{
"epoch": 0.1834090526670032,
"grad_norm": 0.9012241436004484,
"learning_rate": 2.7787614032759243e-05,
"loss": 0.6986,
"step": 1090
},
{
"epoch": 0.1850917045263335,
"grad_norm": 2.912544243603394,
"learning_rate": 2.7745561501617605e-05,
"loss": 0.7173,
"step": 1100
},
{
"epoch": 0.1867743563856638,
"grad_norm": 1.4248442614931247,
"learning_rate": 2.7703145507657923e-05,
"loss": 0.7035,
"step": 1110
},
{
"epoch": 0.18845700824499412,
"grad_norm": 2.186609904533333,
"learning_rate": 2.766036726044926e-05,
"loss": 0.7371,
"step": 1120
},
{
"epoch": 0.19013966010432443,
"grad_norm": 2.0524595532166603,
"learning_rate": 2.7617227979890957e-05,
"loss": 0.6986,
"step": 1130
},
{
"epoch": 0.1918223119636547,
"grad_norm": 1.8227045280907195,
"learning_rate": 2.7573728896177897e-05,
"loss": 0.7075,
"step": 1140
},
{
"epoch": 0.19350496382298502,
"grad_norm": 1.8425998009576734,
"learning_rate": 2.7529871249765397e-05,
"loss": 0.6897,
"step": 1150
},
{
"epoch": 0.19518761568231532,
"grad_norm": 5.3035191638420836,
"learning_rate": 2.7485656291333845e-05,
"loss": 0.7027,
"step": 1160
},
{
"epoch": 0.19687026754164563,
"grad_norm": 3.3228474353685504,
"learning_rate": 2.7441085281753028e-05,
"loss": 0.7091,
"step": 1170
},
{
"epoch": 0.19855291940097594,
"grad_norm": 3.5016968564731283,
"learning_rate": 2.739615949204617e-05,
"loss": 0.7241,
"step": 1180
},
{
"epoch": 0.20023557126030625,
"grad_norm": 1.7190048028902127,
"learning_rate": 2.7350880203353703e-05,
"loss": 0.7192,
"step": 1190
},
{
"epoch": 0.20191822311963656,
"grad_norm": 3.7186824247487515,
"learning_rate": 2.7305248706896722e-05,
"loss": 0.7063,
"step": 1200
},
{
"epoch": 0.20360087497896684,
"grad_norm": 4.1717869895766935,
"learning_rate": 2.7259266303940164e-05,
"loss": 0.7088,
"step": 1210
},
{
"epoch": 0.20528352683829715,
"grad_norm": 2.5124857963805804,
"learning_rate": 2.7212934305755697e-05,
"loss": 0.7198,
"step": 1220
},
{
"epoch": 0.20696617869762746,
"grad_norm": 2.095136268936366,
"learning_rate": 2.7166254033584343e-05,
"loss": 0.753,
"step": 1230
},
{
"epoch": 0.20864883055695777,
"grad_norm": 3.2661098868577256,
"learning_rate": 2.7119226818598784e-05,
"loss": 0.6779,
"step": 1240
},
{
"epoch": 0.21033148241628807,
"grad_norm": 3.055506603735091,
"learning_rate": 2.7071854001865402e-05,
"loss": 0.7013,
"step": 1250
},
{
"epoch": 0.21201413427561838,
"grad_norm": 12.522953778477769,
"learning_rate": 2.702413693430604e-05,
"loss": 0.7088,
"step": 1260
},
{
"epoch": 0.2136967861349487,
"grad_norm": 3.476240301739368,
"learning_rate": 2.697607697665948e-05,
"loss": 0.689,
"step": 1270
},
{
"epoch": 0.21537943799427897,
"grad_norm": 1.1862686197570156,
"learning_rate": 2.6927675499442648e-05,
"loss": 0.7243,
"step": 1280
},
{
"epoch": 0.21706208985360928,
"grad_norm": 1.6505042403801382,
"learning_rate": 2.68789338829115e-05,
"loss": 0.7083,
"step": 1290
},
{
"epoch": 0.2187447417129396,
"grad_norm": 4.74071740077375,
"learning_rate": 2.6829853517021698e-05,
"loss": 0.7016,
"step": 1300
},
{
"epoch": 0.2204273935722699,
"grad_norm": 4.124079283639458,
"learning_rate": 2.6780435801388945e-05,
"loss": 0.7077,
"step": 1310
},
{
"epoch": 0.2221100454316002,
"grad_norm": 1.9487864410536297,
"learning_rate": 2.6730682145249093e-05,
"loss": 0.7355,
"step": 1320
},
{
"epoch": 0.22379269729093051,
"grad_norm": 2.4839241050514733,
"learning_rate": 2.668059396741795e-05,
"loss": 0.7092,
"step": 1330
},
{
"epoch": 0.22547534915026082,
"grad_norm": 2.841913657394254,
"learning_rate": 2.6630172696250804e-05,
"loss": 0.7303,
"step": 1340
},
{
"epoch": 0.2271580010095911,
"grad_norm": 2.7442870185873347,
"learning_rate": 2.6579419769601715e-05,
"loss": 0.6739,
"step": 1350
},
{
"epoch": 0.2288406528689214,
"grad_norm": 1.3854365909071105,
"learning_rate": 2.6528336634782493e-05,
"loss": 0.7073,
"step": 1360
},
{
"epoch": 0.23052330472825172,
"grad_norm": 3.115941001607779,
"learning_rate": 2.6476924748521443e-05,
"loss": 0.7267,
"step": 1370
},
{
"epoch": 0.23220595658758203,
"grad_norm": 6.9185951332741,
"learning_rate": 2.6425185576921812e-05,
"loss": 0.7456,
"step": 1380
},
{
"epoch": 0.23388860844691234,
"grad_norm": 2.378601355345996,
"learning_rate": 2.637312059541997e-05,
"loss": 0.6912,
"step": 1390
},
{
"epoch": 0.23557126030624265,
"grad_norm": 2.7929947858543906,
"learning_rate": 2.632073128874336e-05,
"loss": 0.7184,
"step": 1400
},
{
"epoch": 0.23725391216557296,
"grad_norm": 1.5382855773213957,
"learning_rate": 2.6268019150868144e-05,
"loss": 0.7099,
"step": 1410
},
{
"epoch": 0.23893656402490324,
"grad_norm": 6.1010563795570025,
"learning_rate": 2.62149856849766e-05,
"loss": 0.6895,
"step": 1420
},
{
"epoch": 0.24061921588423354,
"grad_norm": 5.999491987974443,
"learning_rate": 2.616163240341426e-05,
"loss": 0.7493,
"step": 1430
},
{
"epoch": 0.24230186774356385,
"grad_norm": 2.837037600849311,
"learning_rate": 2.6107960827646774e-05,
"loss": 0.7176,
"step": 1440
},
{
"epoch": 0.24398451960289416,
"grad_norm": 1.7029089834427125,
"learning_rate": 2.6053972488216538e-05,
"loss": 0.6852,
"step": 1450
},
{
"epoch": 0.24566717146222447,
"grad_norm": 1.382189249222589,
"learning_rate": 2.5999668924699035e-05,
"loss": 0.685,
"step": 1460
},
{
"epoch": 0.24734982332155478,
"grad_norm": 1.9496045543050813,
"learning_rate": 2.5945051685658923e-05,
"loss": 0.6591,
"step": 1470
},
{
"epoch": 0.2490324751808851,
"grad_norm": 5.479390805764353,
"learning_rate": 2.5890122328605908e-05,
"loss": 0.7085,
"step": 1480
},
{
"epoch": 0.25071512704021537,
"grad_norm": 1.7567995670915637,
"learning_rate": 2.5834882419950295e-05,
"loss": 0.7091,
"step": 1490
},
{
"epoch": 0.2523977788995457,
"grad_norm": 1.9685911084195309,
"learning_rate": 2.577933353495833e-05,
"loss": 0.7218,
"step": 1500
},
{
"epoch": 0.254080430758876,
"grad_norm": 3.400633915540874,
"learning_rate": 2.5723477257707293e-05,
"loss": 0.7148,
"step": 1510
},
{
"epoch": 0.2557630826182063,
"grad_norm": 1.2116738326443663,
"learning_rate": 2.566731518104029e-05,
"loss": 0.7321,
"step": 1520
},
{
"epoch": 0.2574457344775366,
"grad_norm": 1.3376343864594256,
"learning_rate": 2.5610848906520878e-05,
"loss": 0.748,
"step": 1530
},
{
"epoch": 0.2591283863368669,
"grad_norm": 2.6089861003232055,
"learning_rate": 2.5554080044387344e-05,
"loss": 0.7127,
"step": 1540
},
{
"epoch": 0.2608110381961972,
"grad_norm": 3.2047926120640526,
"learning_rate": 2.5497010213506825e-05,
"loss": 0.7262,
"step": 1550
},
{
"epoch": 0.26249369005552753,
"grad_norm": 1.4899957348295265,
"learning_rate": 2.5439641041329128e-05,
"loss": 0.7122,
"step": 1560
},
{
"epoch": 0.26417634191485784,
"grad_norm": 3.595968473922136,
"learning_rate": 2.5381974163840313e-05,
"loss": 0.7092,
"step": 1570
},
{
"epoch": 0.26585899377418815,
"grad_norm": 3.5232117574234003,
"learning_rate": 2.532401122551605e-05,
"loss": 0.6924,
"step": 1580
},
{
"epoch": 0.2675416456335184,
"grad_norm": 2.618947453668302,
"learning_rate": 2.526575387927473e-05,
"loss": 0.7067,
"step": 1590
},
{
"epoch": 0.2692242974928487,
"grad_norm": 3.6282673284589566,
"learning_rate": 2.52072037864303e-05,
"loss": 0.6945,
"step": 1600
},
{
"epoch": 0.270906949352179,
"grad_norm": 2.2274379147013,
"learning_rate": 2.5148362616644926e-05,
"loss": 0.6727,
"step": 1610
},
{
"epoch": 0.2725896012115093,
"grad_norm": 2.823867881580523,
"learning_rate": 2.508923204788135e-05,
"loss": 0.7158,
"step": 1620
},
{
"epoch": 0.27427225307083963,
"grad_norm": 2.0118901151982245,
"learning_rate": 2.5029813766355062e-05,
"loss": 0.7422,
"step": 1630
},
{
"epoch": 0.27595490493016994,
"grad_norm": 1.2843584175617246,
"learning_rate": 2.4970109466486202e-05,
"loss": 0.7099,
"step": 1640
},
{
"epoch": 0.27763755678950025,
"grad_norm": 3.5059277881120914,
"learning_rate": 2.491012085085122e-05,
"loss": 0.7164,
"step": 1650
},
{
"epoch": 0.27932020864883056,
"grad_norm": 1.7458993688338285,
"learning_rate": 2.4849849630134384e-05,
"loss": 0.6901,
"step": 1660
},
{
"epoch": 0.28100286050816087,
"grad_norm": 5.813346226937464,
"learning_rate": 2.4789297523078924e-05,
"loss": 0.7181,
"step": 1670
},
{
"epoch": 0.2826855123674912,
"grad_norm": 2.0515286491489237,
"learning_rate": 2.4728466256438072e-05,
"loss": 0.7431,
"step": 1680
},
{
"epoch": 0.2843681642268215,
"grad_norm": 2.6702746679350375,
"learning_rate": 2.4667357564925798e-05,
"loss": 0.701,
"step": 1690
},
{
"epoch": 0.2860508160861518,
"grad_norm": 2.707565805299449,
"learning_rate": 2.460597319116735e-05,
"loss": 0.6725,
"step": 1700
},
{
"epoch": 0.2877334679454821,
"grad_norm": 1.7994267796032153,
"learning_rate": 2.4544314885649552e-05,
"loss": 0.7043,
"step": 1710
},
{
"epoch": 0.2894161198048124,
"grad_norm": 2.240627477157692,
"learning_rate": 2.4482384406670883e-05,
"loss": 0.7337,
"step": 1720
},
{
"epoch": 0.29109877166414266,
"grad_norm": 1.4093208691675285,
"learning_rate": 2.4420183520291354e-05,
"loss": 0.706,
"step": 1730
},
{
"epoch": 0.292781423523473,
"grad_norm": 1.5799653304195502,
"learning_rate": 2.4357714000282127e-05,
"loss": 0.7254,
"step": 1740
},
{
"epoch": 0.2944640753828033,
"grad_norm": 1.8282839714116759,
"learning_rate": 2.4294977628074938e-05,
"loss": 0.68,
"step": 1750
},
{
"epoch": 0.2961467272421336,
"grad_norm": 13.490769798309381,
"learning_rate": 2.42319761927113e-05,
"loss": 0.6984,
"step": 1760
},
{
"epoch": 0.2978293791014639,
"grad_norm": 1.1660842236351188,
"learning_rate": 2.4168711490791484e-05,
"loss": 0.6893,
"step": 1770
},
{
"epoch": 0.2995120309607942,
"grad_norm": 1.4880113732457052,
"learning_rate": 2.4105185326423286e-05,
"loss": 0.7371,
"step": 1780
},
{
"epoch": 0.3011946828201245,
"grad_norm": 1.9796491202207207,
"learning_rate": 2.4041399511170574e-05,
"loss": 0.7372,
"step": 1790
},
{
"epoch": 0.3028773346794548,
"grad_norm": 3.2861914347482846,
"learning_rate": 2.3977355864001635e-05,
"loss": 0.7145,
"step": 1800
},
{
"epoch": 0.30455998653878513,
"grad_norm": 3.8536888582450595,
"learning_rate": 2.3913056211237304e-05,
"loss": 0.7244,
"step": 1810
},
{
"epoch": 0.30624263839811544,
"grad_norm": 2.250827213388724,
"learning_rate": 2.3848502386498866e-05,
"loss": 0.7444,
"step": 1820
},
{
"epoch": 0.30792529025744575,
"grad_norm": 1.6760548188250846,
"learning_rate": 2.3783696230655802e-05,
"loss": 0.7415,
"step": 1830
},
{
"epoch": 0.30960794211677606,
"grad_norm": 2.83690011157284,
"learning_rate": 2.371863959177326e-05,
"loss": 0.6769,
"step": 1840
},
{
"epoch": 0.31129059397610637,
"grad_norm": 3.6586666108883037,
"learning_rate": 2.365333432505937e-05,
"loss": 0.6981,
"step": 1850
},
{
"epoch": 0.3129732458354367,
"grad_norm": 2.967916913846329,
"learning_rate": 2.3587782292812323e-05,
"loss": 0.7235,
"step": 1860
},
{
"epoch": 0.31465589769476693,
"grad_norm": 2.7607388194454607,
"learning_rate": 2.35219853643673e-05,
"loss": 0.7202,
"step": 1870
},
{
"epoch": 0.31633854955409724,
"grad_norm": 2.5793375573884925,
"learning_rate": 2.3455945416043132e-05,
"loss": 0.7437,
"step": 1880
},
{
"epoch": 0.31802120141342755,
"grad_norm": 1.6474727320404343,
"learning_rate": 2.338966433108879e-05,
"loss": 0.6664,
"step": 1890
},
{
"epoch": 0.31970385327275785,
"grad_norm": 2.8252072958720102,
"learning_rate": 2.3323143999629712e-05,
"loss": 0.6641,
"step": 1900
},
{
"epoch": 0.32138650513208816,
"grad_norm": 1.8240997471681801,
"learning_rate": 2.3256386318613877e-05,
"loss": 0.7029,
"step": 1910
},
{
"epoch": 0.32306915699141847,
"grad_norm": 1.7867386563705459,
"learning_rate": 2.318939319175771e-05,
"loss": 0.6806,
"step": 1920
},
{
"epoch": 0.3247518088507488,
"grad_norm": 2.519605910503542,
"learning_rate": 2.3122166529491822e-05,
"loss": 0.6837,
"step": 1930
},
{
"epoch": 0.3264344607100791,
"grad_norm": 1.5090617010699425,
"learning_rate": 2.3054708248906483e-05,
"loss": 0.7201,
"step": 1940
},
{
"epoch": 0.3281171125694094,
"grad_norm": 1.85373627743108,
"learning_rate": 2.2987020273696996e-05,
"loss": 0.7007,
"step": 1950
},
{
"epoch": 0.3297997644287397,
"grad_norm": 3.1668783585579714,
"learning_rate": 2.2919104534108825e-05,
"loss": 0.6827,
"step": 1960
},
{
"epoch": 0.33148241628807,
"grad_norm": 2.802801151344103,
"learning_rate": 2.2850962966882547e-05,
"loss": 0.733,
"step": 1970
},
{
"epoch": 0.3331650681474003,
"grad_norm": 4.351080547606847,
"learning_rate": 2.278259751519861e-05,
"loss": 0.7125,
"step": 1980
},
{
"epoch": 0.33484772000673063,
"grad_norm": 1.4284076903376268,
"learning_rate": 2.2714010128621957e-05,
"loss": 0.7166,
"step": 1990
},
{
"epoch": 0.3365303718660609,
"grad_norm": 1.4047557097137526,
"learning_rate": 2.2645202763046385e-05,
"loss": 0.7306,
"step": 2000
},
{
"epoch": 0.3382130237253912,
"grad_norm": 1.7792478988054032,
"learning_rate": 2.2576177380638808e-05,
"loss": 0.6819,
"step": 2010
},
{
"epoch": 0.3398956755847215,
"grad_norm": 1.541280861427235,
"learning_rate": 2.2506935949783277e-05,
"loss": 0.7188,
"step": 2020
},
{
"epoch": 0.3415783274440518,
"grad_norm": 3.1010621866032717,
"learning_rate": 2.243748044502485e-05,
"loss": 0.7262,
"step": 2030
},
{
"epoch": 0.3432609793033821,
"grad_norm": 2.3564311476470245,
"learning_rate": 2.236781284701332e-05,
"loss": 0.6862,
"step": 2040
},
{
"epoch": 0.3449436311627124,
"grad_norm": 2.277474191898381,
"learning_rate": 2.229793514244666e-05,
"loss": 0.7086,
"step": 2050
},
{
"epoch": 0.34662628302204274,
"grad_norm": 1.9189792309740905,
"learning_rate": 2.222784932401445e-05,
"loss": 0.6785,
"step": 2060
},
{
"epoch": 0.34830893488137304,
"grad_norm": 8.557409847942546,
"learning_rate": 2.2157557390341e-05,
"loss": 0.7162,
"step": 2070
},
{
"epoch": 0.34999158674070335,
"grad_norm": 2.0580462138378324,
"learning_rate": 2.2087061345928375e-05,
"loss": 0.663,
"step": 2080
},
{
"epoch": 0.35167423860003366,
"grad_norm": 11.262172640870563,
"learning_rate": 2.2016363201099205e-05,
"loss": 0.7363,
"step": 2090
},
{
"epoch": 0.35335689045936397,
"grad_norm": 12.967220942427355,
"learning_rate": 2.1945464971939424e-05,
"loss": 0.7169,
"step": 2100
},
{
"epoch": 0.3550395423186943,
"grad_norm": 31.131995950709616,
"learning_rate": 2.1874368680240692e-05,
"loss": 0.7109,
"step": 2110
},
{
"epoch": 0.3567221941780246,
"grad_norm": 3.759967527046392,
"learning_rate": 2.1803076353442806e-05,
"loss": 0.72,
"step": 2120
},
{
"epoch": 0.3584048460373549,
"grad_norm": 2.0854209231683494,
"learning_rate": 2.1731590024575848e-05,
"loss": 0.7443,
"step": 2130
},
{
"epoch": 0.36008749789668515,
"grad_norm": 1.550491190575623,
"learning_rate": 2.165991173220223e-05,
"loss": 0.7272,
"step": 2140
},
{
"epoch": 0.36177014975601546,
"grad_norm": 3.184378797474582,
"learning_rate": 2.158804352035855e-05,
"loss": 0.6796,
"step": 2150
},
{
"epoch": 0.36345280161534577,
"grad_norm": 2.2017388277936623,
"learning_rate": 2.1515987438497295e-05,
"loss": 0.7079,
"step": 2160
},
{
"epoch": 0.3651354534746761,
"grad_norm": 1.8785352439752243,
"learning_rate": 2.1443745541428416e-05,
"loss": 0.7157,
"step": 2170
},
{
"epoch": 0.3668181053340064,
"grad_norm": 5.799376408169486,
"learning_rate": 2.137131988926072e-05,
"loss": 0.7147,
"step": 2180
},
{
"epoch": 0.3685007571933367,
"grad_norm": 1.463705775425984,
"learning_rate": 2.129871254734312e-05,
"loss": 0.6965,
"step": 2190
},
{
"epoch": 0.370183409052667,
"grad_norm": 2.8778655656985435,
"learning_rate": 2.122592558620575e-05,
"loss": 0.6853,
"step": 2200
},
{
"epoch": 0.3718660609119973,
"grad_norm": 2.830232793716089,
"learning_rate": 2.1152961081500906e-05,
"loss": 0.6682,
"step": 2210
},
{
"epoch": 0.3735487127713276,
"grad_norm": 7.790226305121679,
"learning_rate": 2.1079821113943863e-05,
"loss": 0.6855,
"step": 2220
},
{
"epoch": 0.3752313646306579,
"grad_norm": 1.635629077245975,
"learning_rate": 2.100650776925353e-05,
"loss": 0.7156,
"step": 2230
},
{
"epoch": 0.37691401648998824,
"grad_norm": 1.6353332190474046,
"learning_rate": 2.0933023138092995e-05,
"loss": 0.7083,
"step": 2240
},
{
"epoch": 0.37859666834931854,
"grad_norm": 2.4020219788955237,
"learning_rate": 2.0859369316009877e-05,
"loss": 0.6873,
"step": 2250
},
{
"epoch": 0.38027932020864885,
"grad_norm": 1.5183766349594623,
"learning_rate": 2.0785548403376592e-05,
"loss": 0.6882,
"step": 2260
},
{
"epoch": 0.38196197206797916,
"grad_norm": 3.9509980884297313,
"learning_rate": 2.0711562505330437e-05,
"loss": 0.7037,
"step": 2270
},
{
"epoch": 0.3836446239273094,
"grad_norm": 1.080804508141519,
"learning_rate": 2.063741373171357e-05,
"loss": 0.7124,
"step": 2280
},
{
"epoch": 0.3853272757866397,
"grad_norm": 2.4771901968792975,
"learning_rate": 2.0563104197012847e-05,
"loss": 0.7348,
"step": 2290
},
{
"epoch": 0.38700992764597003,
"grad_norm": 1.4012276716265397,
"learning_rate": 2.048863602029951e-05,
"loss": 0.7157,
"step": 2300
},
{
"epoch": 0.38869257950530034,
"grad_norm": 1.8764316814985353,
"learning_rate": 2.0414011325168777e-05,
"loss": 0.6932,
"step": 2310
},
{
"epoch": 0.39037523136463065,
"grad_norm": 3.2158348437646183,
"learning_rate": 2.0339232239679252e-05,
"loss": 0.6789,
"step": 2320
},
{
"epoch": 0.39205788322396096,
"grad_norm": 2.468508068736803,
"learning_rate": 2.026430089629229e-05,
"loss": 0.7163,
"step": 2330
},
{
"epoch": 0.39374053508329127,
"grad_norm": 2.0179845911955656,
"learning_rate": 2.0189219431811123e-05,
"loss": 0.6566,
"step": 2340
},
{
"epoch": 0.3954231869426216,
"grad_norm": 0.9653345936734927,
"learning_rate": 2.0113989987319988e-05,
"loss": 0.6939,
"step": 2350
},
{
"epoch": 0.3971058388019519,
"grad_norm": 1.568403155522187,
"learning_rate": 2.0038614708123023e-05,
"loss": 0.7288,
"step": 2360
},
{
"epoch": 0.3987884906612822,
"grad_norm": 5.098482519541986,
"learning_rate": 1.996309574368311e-05,
"loss": 0.7217,
"step": 2370
},
{
"epoch": 0.4004711425206125,
"grad_norm": 1.656770228609968,
"learning_rate": 1.9887435247560586e-05,
"loss": 0.743,
"step": 2380
},
{
"epoch": 0.4021537943799428,
"grad_norm": 1.679661595344395,
"learning_rate": 1.981163537735181e-05,
"loss": 0.724,
"step": 2390
},
{
"epoch": 0.4038364462392731,
"grad_norm": 2.057009585071239,
"learning_rate": 1.9735698294627644e-05,
"loss": 0.7228,
"step": 2400
}
],
"logging_steps": 10,
"max_steps": 5943,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 400,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.0934282360979456e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}