ancient41's picture
Training in progress, step 200, checkpoint
dec129a verified
raw
history blame
37 kB
{
"best_metric": 10.324122428894043,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.13003901170351106,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006501950585175553,
"grad_norm": 0.16127419471740723,
"learning_rate": 1e-05,
"loss": 10.3784,
"step": 1
},
{
"epoch": 0.0006501950585175553,
"eval_loss": 10.379300117492676,
"eval_runtime": 5.6096,
"eval_samples_per_second": 461.885,
"eval_steps_per_second": 115.516,
"step": 1
},
{
"epoch": 0.0013003901170351106,
"grad_norm": 0.16593177616596222,
"learning_rate": 2e-05,
"loss": 10.3821,
"step": 2
},
{
"epoch": 0.0019505851755526658,
"grad_norm": 0.14090585708618164,
"learning_rate": 3e-05,
"loss": 10.3833,
"step": 3
},
{
"epoch": 0.002600780234070221,
"grad_norm": 0.1451084315776825,
"learning_rate": 4e-05,
"loss": 10.3795,
"step": 4
},
{
"epoch": 0.003250975292587776,
"grad_norm": 0.1524554044008255,
"learning_rate": 5e-05,
"loss": 10.3816,
"step": 5
},
{
"epoch": 0.0039011703511053317,
"grad_norm": 0.15180771052837372,
"learning_rate": 6e-05,
"loss": 10.3774,
"step": 6
},
{
"epoch": 0.004551365409622887,
"grad_norm": 0.1551075428724289,
"learning_rate": 7e-05,
"loss": 10.3813,
"step": 7
},
{
"epoch": 0.005201560468140442,
"grad_norm": 0.16006357967853546,
"learning_rate": 8e-05,
"loss": 10.3795,
"step": 8
},
{
"epoch": 0.005851755526657998,
"grad_norm": 0.16124685108661652,
"learning_rate": 9e-05,
"loss": 10.3805,
"step": 9
},
{
"epoch": 0.006501950585175552,
"grad_norm": 0.17426081001758575,
"learning_rate": 0.0001,
"loss": 10.376,
"step": 10
},
{
"epoch": 0.007152145643693108,
"grad_norm": 0.16035602986812592,
"learning_rate": 9.999316524962345e-05,
"loss": 10.375,
"step": 11
},
{
"epoch": 0.007802340702210663,
"grad_norm": 0.1623876988887787,
"learning_rate": 9.997266286704631e-05,
"loss": 10.3741,
"step": 12
},
{
"epoch": 0.008452535760728219,
"grad_norm": 0.16178134083747864,
"learning_rate": 9.993849845741524e-05,
"loss": 10.3718,
"step": 13
},
{
"epoch": 0.009102730819245773,
"grad_norm": 0.19455181062221527,
"learning_rate": 9.989068136093873e-05,
"loss": 10.3716,
"step": 14
},
{
"epoch": 0.00975292587776333,
"grad_norm": 0.2239794284105301,
"learning_rate": 9.98292246503335e-05,
"loss": 10.3702,
"step": 15
},
{
"epoch": 0.010403120936280884,
"grad_norm": 0.22532421350479126,
"learning_rate": 9.975414512725057e-05,
"loss": 10.3715,
"step": 16
},
{
"epoch": 0.011053315994798439,
"grad_norm": 0.2125188708305359,
"learning_rate": 9.966546331768191e-05,
"loss": 10.3667,
"step": 17
},
{
"epoch": 0.011703511053315995,
"grad_norm": 0.20077736675739288,
"learning_rate": 9.956320346634876e-05,
"loss": 10.3692,
"step": 18
},
{
"epoch": 0.01235370611183355,
"grad_norm": 0.2166619896888733,
"learning_rate": 9.944739353007344e-05,
"loss": 10.3627,
"step": 19
},
{
"epoch": 0.013003901170351105,
"grad_norm": 0.22231899201869965,
"learning_rate": 9.931806517013612e-05,
"loss": 10.3592,
"step": 20
},
{
"epoch": 0.013654096228868661,
"grad_norm": 0.2398633509874344,
"learning_rate": 9.917525374361912e-05,
"loss": 10.3597,
"step": 21
},
{
"epoch": 0.014304291287386216,
"grad_norm": 0.21921342611312866,
"learning_rate": 9.901899829374047e-05,
"loss": 10.3618,
"step": 22
},
{
"epoch": 0.01495448634590377,
"grad_norm": 0.24414663016796112,
"learning_rate": 9.884934153917997e-05,
"loss": 10.3571,
"step": 23
},
{
"epoch": 0.015604681404421327,
"grad_norm": 0.24406009912490845,
"learning_rate": 9.86663298624003e-05,
"loss": 10.3548,
"step": 24
},
{
"epoch": 0.016254876462938883,
"grad_norm": 0.24088621139526367,
"learning_rate": 9.847001329696653e-05,
"loss": 10.3498,
"step": 25
},
{
"epoch": 0.016905071521456438,
"grad_norm": 0.2453758418560028,
"learning_rate": 9.826044551386744e-05,
"loss": 10.3553,
"step": 26
},
{
"epoch": 0.017555266579973992,
"grad_norm": 0.2553165853023529,
"learning_rate": 9.803768380684242e-05,
"loss": 10.3504,
"step": 27
},
{
"epoch": 0.018205461638491547,
"grad_norm": 0.26212823390960693,
"learning_rate": 9.780178907671789e-05,
"loss": 10.3451,
"step": 28
},
{
"epoch": 0.0188556566970091,
"grad_norm": 0.2586645185947418,
"learning_rate": 9.755282581475769e-05,
"loss": 10.3534,
"step": 29
},
{
"epoch": 0.01950585175552666,
"grad_norm": 0.2604582905769348,
"learning_rate": 9.729086208503174e-05,
"loss": 10.3466,
"step": 30
},
{
"epoch": 0.020156046814044214,
"grad_norm": 0.21844612061977386,
"learning_rate": 9.701596950580806e-05,
"loss": 10.35,
"step": 31
},
{
"epoch": 0.02080624187256177,
"grad_norm": 0.20937693119049072,
"learning_rate": 9.672822322997305e-05,
"loss": 10.3508,
"step": 32
},
{
"epoch": 0.021456436931079324,
"grad_norm": 0.24164879322052002,
"learning_rate": 9.642770192448536e-05,
"loss": 10.3453,
"step": 33
},
{
"epoch": 0.022106631989596878,
"grad_norm": 0.24934925138950348,
"learning_rate": 9.611448774886924e-05,
"loss": 10.3458,
"step": 34
},
{
"epoch": 0.022756827048114433,
"grad_norm": 0.19900235533714294,
"learning_rate": 9.578866633275288e-05,
"loss": 10.3476,
"step": 35
},
{
"epoch": 0.02340702210663199,
"grad_norm": 0.26383519172668457,
"learning_rate": 9.545032675245813e-05,
"loss": 10.3426,
"step": 36
},
{
"epoch": 0.024057217165149546,
"grad_norm": 0.2527461051940918,
"learning_rate": 9.509956150664796e-05,
"loss": 10.3344,
"step": 37
},
{
"epoch": 0.0247074122236671,
"grad_norm": 0.24075770378112793,
"learning_rate": 9.473646649103818e-05,
"loss": 10.3473,
"step": 38
},
{
"epoch": 0.025357607282184655,
"grad_norm": 0.23403631150722504,
"learning_rate": 9.43611409721806e-05,
"loss": 10.3412,
"step": 39
},
{
"epoch": 0.02600780234070221,
"grad_norm": 0.24316959083080292,
"learning_rate": 9.397368756032445e-05,
"loss": 10.3379,
"step": 40
},
{
"epoch": 0.026657997399219768,
"grad_norm": 0.2774410843849182,
"learning_rate": 9.357421218136386e-05,
"loss": 10.3429,
"step": 41
},
{
"epoch": 0.027308192457737322,
"grad_norm": 0.2878156304359436,
"learning_rate": 9.316282404787871e-05,
"loss": 10.3435,
"step": 42
},
{
"epoch": 0.027958387516254877,
"grad_norm": 0.3024629056453705,
"learning_rate": 9.273963562927695e-05,
"loss": 10.3462,
"step": 43
},
{
"epoch": 0.02860858257477243,
"grad_norm": 0.3248623311519623,
"learning_rate": 9.230476262104677e-05,
"loss": 10.3476,
"step": 44
},
{
"epoch": 0.029258777633289986,
"grad_norm": 0.38004767894744873,
"learning_rate": 9.185832391312644e-05,
"loss": 10.3286,
"step": 45
},
{
"epoch": 0.02990897269180754,
"grad_norm": 0.3565896153450012,
"learning_rate": 9.140044155740101e-05,
"loss": 10.3287,
"step": 46
},
{
"epoch": 0.0305591677503251,
"grad_norm": 0.4507029950618744,
"learning_rate": 9.093124073433463e-05,
"loss": 10.3231,
"step": 47
},
{
"epoch": 0.031209362808842653,
"grad_norm": 0.4504649341106415,
"learning_rate": 9.045084971874738e-05,
"loss": 10.3208,
"step": 48
},
{
"epoch": 0.03185955786736021,
"grad_norm": 0.6150670647621155,
"learning_rate": 8.995939984474624e-05,
"loss": 10.3136,
"step": 49
},
{
"epoch": 0.032509752925877766,
"grad_norm": 0.7125288844108582,
"learning_rate": 8.945702546981969e-05,
"loss": 10.319,
"step": 50
},
{
"epoch": 0.032509752925877766,
"eval_loss": 10.332371711730957,
"eval_runtime": 5.5939,
"eval_samples_per_second": 463.181,
"eval_steps_per_second": 115.84,
"step": 50
},
{
"epoch": 0.03315994798439532,
"grad_norm": 0.1598876267671585,
"learning_rate": 8.894386393810563e-05,
"loss": 10.3379,
"step": 51
},
{
"epoch": 0.033810143042912875,
"grad_norm": 0.1482846438884735,
"learning_rate": 8.842005554284296e-05,
"loss": 10.3383,
"step": 52
},
{
"epoch": 0.03446033810143043,
"grad_norm": 0.16184358298778534,
"learning_rate": 8.788574348801675e-05,
"loss": 10.3355,
"step": 53
},
{
"epoch": 0.035110533159947985,
"grad_norm": 0.16479916870594025,
"learning_rate": 8.73410738492077e-05,
"loss": 10.3343,
"step": 54
},
{
"epoch": 0.03576072821846554,
"grad_norm": 0.15844371914863586,
"learning_rate": 8.678619553365659e-05,
"loss": 10.3351,
"step": 55
},
{
"epoch": 0.036410923276983094,
"grad_norm": 0.14632071554660797,
"learning_rate": 8.622126023955446e-05,
"loss": 10.3378,
"step": 56
},
{
"epoch": 0.03706111833550065,
"grad_norm": 0.15669602155685425,
"learning_rate": 8.564642241456986e-05,
"loss": 10.3373,
"step": 57
},
{
"epoch": 0.0377113133940182,
"grad_norm": 0.15801014006137848,
"learning_rate": 8.506183921362443e-05,
"loss": 10.337,
"step": 58
},
{
"epoch": 0.03836150845253576,
"grad_norm": 0.15716378390789032,
"learning_rate": 8.44676704559283e-05,
"loss": 10.3339,
"step": 59
},
{
"epoch": 0.03901170351105332,
"grad_norm": 0.1375216543674469,
"learning_rate": 8.386407858128706e-05,
"loss": 10.3385,
"step": 60
},
{
"epoch": 0.03966189856957087,
"grad_norm": 0.13198484480381012,
"learning_rate": 8.32512286056924e-05,
"loss": 10.3323,
"step": 61
},
{
"epoch": 0.04031209362808843,
"grad_norm": 0.13879011571407318,
"learning_rate": 8.262928807620843e-05,
"loss": 10.3352,
"step": 62
},
{
"epoch": 0.04096228868660598,
"grad_norm": 0.13692507147789001,
"learning_rate": 8.199842702516583e-05,
"loss": 10.3305,
"step": 63
},
{
"epoch": 0.04161248374512354,
"grad_norm": 0.15211237967014313,
"learning_rate": 8.135881792367686e-05,
"loss": 10.3301,
"step": 64
},
{
"epoch": 0.04226267880364109,
"grad_norm": 0.11579670757055283,
"learning_rate": 8.07106356344834e-05,
"loss": 10.3357,
"step": 65
},
{
"epoch": 0.04291287386215865,
"grad_norm": 0.15383192896842957,
"learning_rate": 8.005405736415126e-05,
"loss": 10.331,
"step": 66
},
{
"epoch": 0.043563068920676205,
"grad_norm": 0.11632498353719711,
"learning_rate": 7.938926261462366e-05,
"loss": 10.3275,
"step": 67
},
{
"epoch": 0.044213263979193757,
"grad_norm": 0.11216708272695541,
"learning_rate": 7.871643313414718e-05,
"loss": 10.3344,
"step": 68
},
{
"epoch": 0.044863459037711315,
"grad_norm": 0.10444188863039017,
"learning_rate": 7.803575286758364e-05,
"loss": 10.3361,
"step": 69
},
{
"epoch": 0.045513654096228866,
"grad_norm": 0.11757842451334,
"learning_rate": 7.734740790612136e-05,
"loss": 10.3346,
"step": 70
},
{
"epoch": 0.046163849154746424,
"grad_norm": 0.07830046862363815,
"learning_rate": 7.66515864363997e-05,
"loss": 10.336,
"step": 71
},
{
"epoch": 0.04681404421326398,
"grad_norm": 0.09273282438516617,
"learning_rate": 7.594847868906076e-05,
"loss": 10.3341,
"step": 72
},
{
"epoch": 0.04746423927178153,
"grad_norm": 0.09832680970430374,
"learning_rate": 7.52382768867422e-05,
"loss": 10.3297,
"step": 73
},
{
"epoch": 0.04811443433029909,
"grad_norm": 0.09351181238889694,
"learning_rate": 7.452117519152542e-05,
"loss": 10.3353,
"step": 74
},
{
"epoch": 0.04876462938881664,
"grad_norm": 0.1021319255232811,
"learning_rate": 7.379736965185368e-05,
"loss": 10.3316,
"step": 75
},
{
"epoch": 0.0494148244473342,
"grad_norm": 0.10671185702085495,
"learning_rate": 7.30670581489344e-05,
"loss": 10.3285,
"step": 76
},
{
"epoch": 0.05006501950585176,
"grad_norm": 0.09196629375219345,
"learning_rate": 7.233044034264034e-05,
"loss": 10.3347,
"step": 77
},
{
"epoch": 0.05071521456436931,
"grad_norm": 0.09259489923715591,
"learning_rate": 7.158771761692464e-05,
"loss": 10.3315,
"step": 78
},
{
"epoch": 0.05136540962288687,
"grad_norm": 0.08821659535169601,
"learning_rate": 7.083909302476453e-05,
"loss": 10.3313,
"step": 79
},
{
"epoch": 0.05201560468140442,
"grad_norm": 0.15504157543182373,
"learning_rate": 7.008477123264848e-05,
"loss": 10.3241,
"step": 80
},
{
"epoch": 0.05266579973992198,
"grad_norm": 0.1313365399837494,
"learning_rate": 6.932495846462261e-05,
"loss": 10.3254,
"step": 81
},
{
"epoch": 0.053315994798439535,
"grad_norm": 0.14146195352077484,
"learning_rate": 6.855986244591104e-05,
"loss": 10.3244,
"step": 82
},
{
"epoch": 0.053966189856957086,
"grad_norm": 0.09124355763196945,
"learning_rate": 6.778969234612584e-05,
"loss": 10.3274,
"step": 83
},
{
"epoch": 0.054616384915474644,
"grad_norm": 0.11179622262716293,
"learning_rate": 6.701465872208216e-05,
"loss": 10.3381,
"step": 84
},
{
"epoch": 0.055266579973992196,
"grad_norm": 0.1515960395336151,
"learning_rate": 6.623497346023418e-05,
"loss": 10.3356,
"step": 85
},
{
"epoch": 0.055916775032509754,
"grad_norm": 0.0902651995420456,
"learning_rate": 6.545084971874738e-05,
"loss": 10.3257,
"step": 86
},
{
"epoch": 0.056566970091027305,
"grad_norm": 0.13399207592010498,
"learning_rate": 6.466250186922325e-05,
"loss": 10.334,
"step": 87
},
{
"epoch": 0.05721716514954486,
"grad_norm": 0.1068468987941742,
"learning_rate": 6.387014543809223e-05,
"loss": 10.3262,
"step": 88
},
{
"epoch": 0.05786736020806242,
"grad_norm": 0.132808655500412,
"learning_rate": 6.307399704769099e-05,
"loss": 10.3341,
"step": 89
},
{
"epoch": 0.05851755526657997,
"grad_norm": 0.13788598775863647,
"learning_rate": 6.227427435703997e-05,
"loss": 10.3326,
"step": 90
},
{
"epoch": 0.05916775032509753,
"grad_norm": 0.1425122618675232,
"learning_rate": 6.147119600233758e-05,
"loss": 10.3221,
"step": 91
},
{
"epoch": 0.05981794538361508,
"grad_norm": 0.1713189333677292,
"learning_rate": 6.066498153718735e-05,
"loss": 10.3292,
"step": 92
},
{
"epoch": 0.06046814044213264,
"grad_norm": 0.2495804876089096,
"learning_rate": 5.985585137257401e-05,
"loss": 10.3214,
"step": 93
},
{
"epoch": 0.0611183355006502,
"grad_norm": 0.2658974230289459,
"learning_rate": 5.90440267166055e-05,
"loss": 10.3255,
"step": 94
},
{
"epoch": 0.06176853055916775,
"grad_norm": 0.23585231602191925,
"learning_rate": 5.8229729514036705e-05,
"loss": 10.3244,
"step": 95
},
{
"epoch": 0.06241872561768531,
"grad_norm": 0.35915854573249817,
"learning_rate": 5.74131823855921e-05,
"loss": 10.3122,
"step": 96
},
{
"epoch": 0.06306892067620286,
"grad_norm": 0.31185299158096313,
"learning_rate": 5.6594608567103456e-05,
"loss": 10.3114,
"step": 97
},
{
"epoch": 0.06371911573472042,
"grad_norm": 0.33438408374786377,
"learning_rate": 5.577423184847932e-05,
"loss": 10.3181,
"step": 98
},
{
"epoch": 0.06436931079323797,
"grad_norm": 0.41990014910697937,
"learning_rate": 5.495227651252315e-05,
"loss": 10.3179,
"step": 99
},
{
"epoch": 0.06501950585175553,
"grad_norm": 0.5420405864715576,
"learning_rate": 5.4128967273616625e-05,
"loss": 10.3005,
"step": 100
},
{
"epoch": 0.06501950585175553,
"eval_loss": 10.327727317810059,
"eval_runtime": 5.5862,
"eval_samples_per_second": 463.82,
"eval_steps_per_second": 116.0,
"step": 100
},
{
"epoch": 0.06566970091027308,
"grad_norm": 0.143467977643013,
"learning_rate": 5.330452921628497e-05,
"loss": 10.3332,
"step": 101
},
{
"epoch": 0.06631989596879063,
"grad_norm": 0.12299665808677673,
"learning_rate": 5.247918773366112e-05,
"loss": 10.3333,
"step": 102
},
{
"epoch": 0.06697009102730819,
"grad_norm": 0.11833786219358444,
"learning_rate": 5.165316846586541e-05,
"loss": 10.331,
"step": 103
},
{
"epoch": 0.06762028608582575,
"grad_norm": 0.1268458515405655,
"learning_rate": 5.0826697238317935e-05,
"loss": 10.3301,
"step": 104
},
{
"epoch": 0.06827048114434331,
"grad_norm": 0.11286137998104095,
"learning_rate": 5e-05,
"loss": 10.3307,
"step": 105
},
{
"epoch": 0.06892067620286085,
"grad_norm": 0.11881788074970245,
"learning_rate": 4.917330276168208e-05,
"loss": 10.3321,
"step": 106
},
{
"epoch": 0.06957087126137841,
"grad_norm": 0.13090336322784424,
"learning_rate": 4.834683153413459e-05,
"loss": 10.328,
"step": 107
},
{
"epoch": 0.07022106631989597,
"grad_norm": 0.1043592095375061,
"learning_rate": 4.7520812266338885e-05,
"loss": 10.3317,
"step": 108
},
{
"epoch": 0.07087126137841353,
"grad_norm": 0.1152200773358345,
"learning_rate": 4.669547078371504e-05,
"loss": 10.3305,
"step": 109
},
{
"epoch": 0.07152145643693109,
"grad_norm": 0.11908014863729477,
"learning_rate": 4.5871032726383386e-05,
"loss": 10.3275,
"step": 110
},
{
"epoch": 0.07217165149544863,
"grad_norm": 0.15754158794879913,
"learning_rate": 4.504772348747687e-05,
"loss": 10.3317,
"step": 111
},
{
"epoch": 0.07282184655396619,
"grad_norm": 0.11912248283624649,
"learning_rate": 4.4225768151520694e-05,
"loss": 10.3282,
"step": 112
},
{
"epoch": 0.07347204161248375,
"grad_norm": 0.12206631153821945,
"learning_rate": 4.3405391432896555e-05,
"loss": 10.3257,
"step": 113
},
{
"epoch": 0.0741222366710013,
"grad_norm": 0.09090618789196014,
"learning_rate": 4.2586817614407895e-05,
"loss": 10.3288,
"step": 114
},
{
"epoch": 0.07477243172951886,
"grad_norm": 0.10142911970615387,
"learning_rate": 4.17702704859633e-05,
"loss": 10.3317,
"step": 115
},
{
"epoch": 0.0754226267880364,
"grad_norm": 0.10292045772075653,
"learning_rate": 4.095597328339452e-05,
"loss": 10.3256,
"step": 116
},
{
"epoch": 0.07607282184655396,
"grad_norm": 0.11896487325429916,
"learning_rate": 4.0144148627425993e-05,
"loss": 10.3252,
"step": 117
},
{
"epoch": 0.07672301690507152,
"grad_norm": 0.10349823534488678,
"learning_rate": 3.933501846281267e-05,
"loss": 10.3321,
"step": 118
},
{
"epoch": 0.07737321196358908,
"grad_norm": 0.08643659949302673,
"learning_rate": 3.852880399766243e-05,
"loss": 10.3302,
"step": 119
},
{
"epoch": 0.07802340702210664,
"grad_norm": 0.08573546260595322,
"learning_rate": 3.772572564296005e-05,
"loss": 10.3279,
"step": 120
},
{
"epoch": 0.07867360208062418,
"grad_norm": 0.09166166186332703,
"learning_rate": 3.6926002952309016e-05,
"loss": 10.3354,
"step": 121
},
{
"epoch": 0.07932379713914174,
"grad_norm": 0.10453158617019653,
"learning_rate": 3.612985456190778e-05,
"loss": 10.3262,
"step": 122
},
{
"epoch": 0.0799739921976593,
"grad_norm": 0.09580694884061813,
"learning_rate": 3.533749813077677e-05,
"loss": 10.3278,
"step": 123
},
{
"epoch": 0.08062418725617686,
"grad_norm": 0.0793313980102539,
"learning_rate": 3.4549150281252636e-05,
"loss": 10.3301,
"step": 124
},
{
"epoch": 0.0812743823146944,
"grad_norm": 0.06261216849088669,
"learning_rate": 3.3765026539765834e-05,
"loss": 10.3273,
"step": 125
},
{
"epoch": 0.08192457737321196,
"grad_norm": 0.0954262837767601,
"learning_rate": 3.298534127791785e-05,
"loss": 10.3324,
"step": 126
},
{
"epoch": 0.08257477243172952,
"grad_norm": 0.09346198290586472,
"learning_rate": 3.221030765387417e-05,
"loss": 10.3301,
"step": 127
},
{
"epoch": 0.08322496749024708,
"grad_norm": 0.07352735847234726,
"learning_rate": 3.144013755408895e-05,
"loss": 10.3335,
"step": 128
},
{
"epoch": 0.08387516254876463,
"grad_norm": 0.1031741201877594,
"learning_rate": 3.0675041535377405e-05,
"loss": 10.3312,
"step": 129
},
{
"epoch": 0.08452535760728218,
"grad_norm": 0.14191220700740814,
"learning_rate": 2.991522876735154e-05,
"loss": 10.324,
"step": 130
},
{
"epoch": 0.08517555266579974,
"grad_norm": 0.10067912191152573,
"learning_rate": 2.916090697523549e-05,
"loss": 10.3249,
"step": 131
},
{
"epoch": 0.0858257477243173,
"grad_norm": 0.10549023002386093,
"learning_rate": 2.8412282383075363e-05,
"loss": 10.3188,
"step": 132
},
{
"epoch": 0.08647594278283485,
"grad_norm": 0.1337430775165558,
"learning_rate": 2.766955965735968e-05,
"loss": 10.332,
"step": 133
},
{
"epoch": 0.08712613784135241,
"grad_norm": 0.1169704720377922,
"learning_rate": 2.693294185106562e-05,
"loss": 10.3353,
"step": 134
},
{
"epoch": 0.08777633289986995,
"grad_norm": 0.13879139721393585,
"learning_rate": 2.6202630348146324e-05,
"loss": 10.3178,
"step": 135
},
{
"epoch": 0.08842652795838751,
"grad_norm": 0.12521077692508698,
"learning_rate": 2.547882480847461e-05,
"loss": 10.3244,
"step": 136
},
{
"epoch": 0.08907672301690507,
"grad_norm": 0.10924085229635239,
"learning_rate": 2.476172311325783e-05,
"loss": 10.3201,
"step": 137
},
{
"epoch": 0.08972691807542263,
"grad_norm": 0.11174332350492477,
"learning_rate": 2.405152131093926e-05,
"loss": 10.3249,
"step": 138
},
{
"epoch": 0.09037711313394019,
"grad_norm": 0.17982299625873566,
"learning_rate": 2.3348413563600325e-05,
"loss": 10.3266,
"step": 139
},
{
"epoch": 0.09102730819245773,
"grad_norm": 0.14450889825820923,
"learning_rate": 2.2652592093878666e-05,
"loss": 10.3288,
"step": 140
},
{
"epoch": 0.09167750325097529,
"grad_norm": 0.16409315168857574,
"learning_rate": 2.196424713241637e-05,
"loss": 10.3298,
"step": 141
},
{
"epoch": 0.09232769830949285,
"grad_norm": 0.20656029880046844,
"learning_rate": 2.128356686585282e-05,
"loss": 10.3221,
"step": 142
},
{
"epoch": 0.0929778933680104,
"grad_norm": 0.22564861178398132,
"learning_rate": 2.061073738537635e-05,
"loss": 10.3117,
"step": 143
},
{
"epoch": 0.09362808842652796,
"grad_norm": 0.2071637362241745,
"learning_rate": 1.9945942635848748e-05,
"loss": 10.3108,
"step": 144
},
{
"epoch": 0.09427828348504551,
"grad_norm": 0.2876690924167633,
"learning_rate": 1.928936436551661e-05,
"loss": 10.3201,
"step": 145
},
{
"epoch": 0.09492847854356307,
"grad_norm": 0.2864055335521698,
"learning_rate": 1.8641182076323148e-05,
"loss": 10.3257,
"step": 146
},
{
"epoch": 0.09557867360208062,
"grad_norm": 0.3475603461265564,
"learning_rate": 1.800157297483417e-05,
"loss": 10.3133,
"step": 147
},
{
"epoch": 0.09622886866059818,
"grad_norm": 0.36229249835014343,
"learning_rate": 1.7370711923791567e-05,
"loss": 10.3001,
"step": 148
},
{
"epoch": 0.09687906371911574,
"grad_norm": 0.3875623941421509,
"learning_rate": 1.6748771394307585e-05,
"loss": 10.2974,
"step": 149
},
{
"epoch": 0.09752925877763328,
"grad_norm": 0.6343831419944763,
"learning_rate": 1.6135921418712956e-05,
"loss": 10.2951,
"step": 150
},
{
"epoch": 0.09752925877763328,
"eval_loss": 10.324746131896973,
"eval_runtime": 5.5938,
"eval_samples_per_second": 463.195,
"eval_steps_per_second": 115.843,
"step": 150
},
{
"epoch": 0.09817945383615084,
"grad_norm": 0.1216152161359787,
"learning_rate": 1.553232954407171e-05,
"loss": 10.3272,
"step": 151
},
{
"epoch": 0.0988296488946684,
"grad_norm": 0.10398002713918686,
"learning_rate": 1.4938160786375572e-05,
"loss": 10.3268,
"step": 152
},
{
"epoch": 0.09947984395318596,
"grad_norm": 0.11506969481706619,
"learning_rate": 1.435357758543015e-05,
"loss": 10.3285,
"step": 153
},
{
"epoch": 0.10013003901170352,
"grad_norm": 0.10437972098588943,
"learning_rate": 1.3778739760445552e-05,
"loss": 10.3281,
"step": 154
},
{
"epoch": 0.10078023407022106,
"grad_norm": 0.10129734128713608,
"learning_rate": 1.3213804466343421e-05,
"loss": 10.328,
"step": 155
},
{
"epoch": 0.10143042912873862,
"grad_norm": 0.11362939327955246,
"learning_rate": 1.2658926150792322e-05,
"loss": 10.3251,
"step": 156
},
{
"epoch": 0.10208062418725618,
"grad_norm": 0.10383567959070206,
"learning_rate": 1.2114256511983274e-05,
"loss": 10.3251,
"step": 157
},
{
"epoch": 0.10273081924577374,
"grad_norm": 0.10725058615207672,
"learning_rate": 1.157994445715706e-05,
"loss": 10.3275,
"step": 158
},
{
"epoch": 0.1033810143042913,
"grad_norm": 0.11777881532907486,
"learning_rate": 1.1056136061894384e-05,
"loss": 10.3254,
"step": 159
},
{
"epoch": 0.10403120936280884,
"grad_norm": 0.10041073709726334,
"learning_rate": 1.0542974530180327e-05,
"loss": 10.3268,
"step": 160
},
{
"epoch": 0.1046814044213264,
"grad_norm": 0.09719385951757431,
"learning_rate": 1.0040600155253765e-05,
"loss": 10.3279,
"step": 161
},
{
"epoch": 0.10533159947984395,
"grad_norm": 0.09627390652894974,
"learning_rate": 9.549150281252633e-06,
"loss": 10.3275,
"step": 162
},
{
"epoch": 0.10598179453836151,
"grad_norm": 0.11505679041147232,
"learning_rate": 9.068759265665384e-06,
"loss": 10.3267,
"step": 163
},
{
"epoch": 0.10663198959687907,
"grad_norm": 0.0919860377907753,
"learning_rate": 8.599558442598998e-06,
"loss": 10.3235,
"step": 164
},
{
"epoch": 0.10728218465539661,
"grad_norm": 0.10943809896707535,
"learning_rate": 8.141676086873572e-06,
"loss": 10.3274,
"step": 165
},
{
"epoch": 0.10793237971391417,
"grad_norm": 0.09337712824344635,
"learning_rate": 7.695237378953223e-06,
"loss": 10.3284,
"step": 166
},
{
"epoch": 0.10858257477243173,
"grad_norm": 0.08571542054414749,
"learning_rate": 7.260364370723044e-06,
"loss": 10.3259,
"step": 167
},
{
"epoch": 0.10923276983094929,
"grad_norm": 0.10791494697332382,
"learning_rate": 6.837175952121306e-06,
"loss": 10.3239,
"step": 168
},
{
"epoch": 0.10988296488946683,
"grad_norm": 0.09137783199548721,
"learning_rate": 6.425787818636131e-06,
"loss": 10.3338,
"step": 169
},
{
"epoch": 0.11053315994798439,
"grad_norm": 0.09270033240318298,
"learning_rate": 6.026312439675552e-06,
"loss": 10.324,
"step": 170
},
{
"epoch": 0.11118335500650195,
"grad_norm": 0.09181763976812363,
"learning_rate": 5.6388590278194096e-06,
"loss": 10.3258,
"step": 171
},
{
"epoch": 0.11183355006501951,
"grad_norm": 0.10405848920345306,
"learning_rate": 5.263533508961827e-06,
"loss": 10.3318,
"step": 172
},
{
"epoch": 0.11248374512353707,
"grad_norm": 0.09887488186359406,
"learning_rate": 4.900438493352055e-06,
"loss": 10.3328,
"step": 173
},
{
"epoch": 0.11313394018205461,
"grad_norm": 0.09410857409238815,
"learning_rate": 4.549673247541875e-06,
"loss": 10.3251,
"step": 174
},
{
"epoch": 0.11378413524057217,
"grad_norm": 0.09131878614425659,
"learning_rate": 4.2113336672471245e-06,
"loss": 10.3203,
"step": 175
},
{
"epoch": 0.11443433029908973,
"grad_norm": 0.11112850904464722,
"learning_rate": 3.885512251130763e-06,
"loss": 10.326,
"step": 176
},
{
"epoch": 0.11508452535760728,
"grad_norm": 0.11711225658655167,
"learning_rate": 3.5722980755146517e-06,
"loss": 10.3197,
"step": 177
},
{
"epoch": 0.11573472041612484,
"grad_norm": 0.07148018479347229,
"learning_rate": 3.271776770026963e-06,
"loss": 10.3266,
"step": 178
},
{
"epoch": 0.11638491547464239,
"grad_norm": 0.10184058547019958,
"learning_rate": 2.9840304941919415e-06,
"loss": 10.3288,
"step": 179
},
{
"epoch": 0.11703511053315994,
"grad_norm": 0.14172475039958954,
"learning_rate": 2.7091379149682685e-06,
"loss": 10.3263,
"step": 180
},
{
"epoch": 0.1176853055916775,
"grad_norm": 0.0866977646946907,
"learning_rate": 2.4471741852423237e-06,
"loss": 10.3236,
"step": 181
},
{
"epoch": 0.11833550065019506,
"grad_norm": 0.09405398368835449,
"learning_rate": 2.1982109232821178e-06,
"loss": 10.3329,
"step": 182
},
{
"epoch": 0.11898569570871262,
"grad_norm": 0.09134174883365631,
"learning_rate": 1.962316193157593e-06,
"loss": 10.3321,
"step": 183
},
{
"epoch": 0.11963589076723016,
"grad_norm": 0.10691911727190018,
"learning_rate": 1.7395544861325718e-06,
"loss": 10.3323,
"step": 184
},
{
"epoch": 0.12028608582574772,
"grad_norm": 0.10940374433994293,
"learning_rate": 1.5299867030334814e-06,
"loss": 10.3277,
"step": 185
},
{
"epoch": 0.12093628088426528,
"grad_norm": 0.10505640506744385,
"learning_rate": 1.333670137599713e-06,
"loss": 10.3221,
"step": 186
},
{
"epoch": 0.12158647594278284,
"grad_norm": 0.12675940990447998,
"learning_rate": 1.1506584608200367e-06,
"loss": 10.3208,
"step": 187
},
{
"epoch": 0.1222366710013004,
"grad_norm": 0.15413792431354523,
"learning_rate": 9.810017062595322e-07,
"loss": 10.3214,
"step": 188
},
{
"epoch": 0.12288686605981794,
"grad_norm": 0.1255342662334442,
"learning_rate": 8.247462563808817e-07,
"loss": 10.3313,
"step": 189
},
{
"epoch": 0.1235370611183355,
"grad_norm": 0.179266557097435,
"learning_rate": 6.819348298638839e-07,
"loss": 10.3249,
"step": 190
},
{
"epoch": 0.12418725617685306,
"grad_norm": 0.17855946719646454,
"learning_rate": 5.526064699265753e-07,
"loss": 10.3213,
"step": 191
},
{
"epoch": 0.12483745123537061,
"grad_norm": 0.1523905098438263,
"learning_rate": 4.367965336512403e-07,
"loss": 10.3158,
"step": 192
},
{
"epoch": 0.12548764629388817,
"grad_norm": 0.17341147363185883,
"learning_rate": 3.3453668231809286e-07,
"loss": 10.3153,
"step": 193
},
{
"epoch": 0.12613784135240572,
"grad_norm": 0.17141734063625336,
"learning_rate": 2.458548727494292e-07,
"loss": 10.3119,
"step": 194
},
{
"epoch": 0.1267880364109233,
"grad_norm": 0.22108782827854156,
"learning_rate": 1.7077534966650766e-07,
"loss": 10.3104,
"step": 195
},
{
"epoch": 0.12743823146944083,
"grad_norm": 0.25344622135162354,
"learning_rate": 1.0931863906127327e-07,
"loss": 10.32,
"step": 196
},
{
"epoch": 0.12808842652795838,
"grad_norm": 0.292223185300827,
"learning_rate": 6.150154258476315e-08,
"loss": 10.3095,
"step": 197
},
{
"epoch": 0.12873862158647595,
"grad_norm": 0.3518892228603363,
"learning_rate": 2.7337132953697554e-08,
"loss": 10.2972,
"step": 198
},
{
"epoch": 0.1293888166449935,
"grad_norm": 0.35086145997047424,
"learning_rate": 6.834750376549792e-09,
"loss": 10.3082,
"step": 199
},
{
"epoch": 0.13003901170351106,
"grad_norm": 0.45979052782058716,
"learning_rate": 0.0,
"loss": 10.3006,
"step": 200
},
{
"epoch": 0.13003901170351106,
"eval_loss": 10.324122428894043,
"eval_runtime": 5.6129,
"eval_samples_per_second": 461.613,
"eval_steps_per_second": 115.448,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 43412304691200.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}