0x1202's picture
Training in progress, step 200, checkpoint
681e44f verified
{
"best_metric": 0.20633231103420258,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.657354149548069,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003286770747740345,
"grad_norm": 0.5376676321029663,
"learning_rate": 1e-05,
"loss": 0.9567,
"step": 1
},
{
"epoch": 0.003286770747740345,
"eval_loss": 1.397003173828125,
"eval_runtime": 16.5625,
"eval_samples_per_second": 30.974,
"eval_steps_per_second": 7.789,
"step": 1
},
{
"epoch": 0.00657354149548069,
"grad_norm": 0.6344265341758728,
"learning_rate": 2e-05,
"loss": 0.9993,
"step": 2
},
{
"epoch": 0.009860312243221035,
"grad_norm": 0.6312777996063232,
"learning_rate": 3e-05,
"loss": 1.0271,
"step": 3
},
{
"epoch": 0.01314708299096138,
"grad_norm": 0.2911286950111389,
"learning_rate": 4e-05,
"loss": 1.1796,
"step": 4
},
{
"epoch": 0.016433853738701727,
"grad_norm": 0.3993891775608063,
"learning_rate": 5e-05,
"loss": 1.4233,
"step": 5
},
{
"epoch": 0.01972062448644207,
"grad_norm": 0.3985084295272827,
"learning_rate": 6e-05,
"loss": 1.049,
"step": 6
},
{
"epoch": 0.023007395234182416,
"grad_norm": 0.4213271737098694,
"learning_rate": 7e-05,
"loss": 1.179,
"step": 7
},
{
"epoch": 0.02629416598192276,
"grad_norm": 0.4295935332775116,
"learning_rate": 8e-05,
"loss": 1.0505,
"step": 8
},
{
"epoch": 0.029580936729663106,
"grad_norm": 0.4087089002132416,
"learning_rate": 9e-05,
"loss": 1.0125,
"step": 9
},
{
"epoch": 0.03286770747740345,
"grad_norm": 0.37575092911720276,
"learning_rate": 0.0001,
"loss": 1.0324,
"step": 10
},
{
"epoch": 0.036154478225143796,
"grad_norm": 0.35632026195526123,
"learning_rate": 9.999316524962345e-05,
"loss": 1.0652,
"step": 11
},
{
"epoch": 0.03944124897288414,
"grad_norm": 0.318684846162796,
"learning_rate": 9.997266286704631e-05,
"loss": 0.9594,
"step": 12
},
{
"epoch": 0.04272801972062449,
"grad_norm": 0.3787010610103607,
"learning_rate": 9.993849845741524e-05,
"loss": 0.9284,
"step": 13
},
{
"epoch": 0.04601479046836483,
"grad_norm": 0.4443349540233612,
"learning_rate": 9.989068136093873e-05,
"loss": 0.8033,
"step": 14
},
{
"epoch": 0.049301561216105176,
"grad_norm": 0.4556942582130432,
"learning_rate": 9.98292246503335e-05,
"loss": 0.8241,
"step": 15
},
{
"epoch": 0.05258833196384552,
"grad_norm": 0.4467424154281616,
"learning_rate": 9.975414512725057e-05,
"loss": 0.8875,
"step": 16
},
{
"epoch": 0.05587510271158587,
"grad_norm": 0.4463362991809845,
"learning_rate": 9.966546331768191e-05,
"loss": 0.8988,
"step": 17
},
{
"epoch": 0.05916187345932621,
"grad_norm": 0.4128912389278412,
"learning_rate": 9.956320346634876e-05,
"loss": 0.8455,
"step": 18
},
{
"epoch": 0.062448644207066556,
"grad_norm": 0.3698365092277527,
"learning_rate": 9.944739353007344e-05,
"loss": 0.772,
"step": 19
},
{
"epoch": 0.0657354149548069,
"grad_norm": 0.8387037515640259,
"learning_rate": 9.931806517013612e-05,
"loss": 0.7461,
"step": 20
},
{
"epoch": 0.06902218570254724,
"grad_norm": 0.6368226408958435,
"learning_rate": 9.917525374361912e-05,
"loss": 0.6542,
"step": 21
},
{
"epoch": 0.07230895645028759,
"grad_norm": 0.6496455073356628,
"learning_rate": 9.901899829374047e-05,
"loss": 0.5405,
"step": 22
},
{
"epoch": 0.07559572719802794,
"grad_norm": 0.6005721688270569,
"learning_rate": 9.884934153917997e-05,
"loss": 0.3935,
"step": 23
},
{
"epoch": 0.07888249794576828,
"grad_norm": 0.4601370394229889,
"learning_rate": 9.86663298624003e-05,
"loss": 0.3906,
"step": 24
},
{
"epoch": 0.08216926869350863,
"grad_norm": 0.5351113677024841,
"learning_rate": 9.847001329696653e-05,
"loss": 0.5116,
"step": 25
},
{
"epoch": 0.08545603944124898,
"grad_norm": 0.5325148105621338,
"learning_rate": 9.826044551386744e-05,
"loss": 0.6696,
"step": 26
},
{
"epoch": 0.08874281018898932,
"grad_norm": 0.5001903772354126,
"learning_rate": 9.803768380684242e-05,
"loss": 0.5166,
"step": 27
},
{
"epoch": 0.09202958093672967,
"grad_norm": 0.3596450984477997,
"learning_rate": 9.780178907671789e-05,
"loss": 0.8015,
"step": 28
},
{
"epoch": 0.09531635168447,
"grad_norm": 0.42646610736846924,
"learning_rate": 9.755282581475769e-05,
"loss": 0.7092,
"step": 29
},
{
"epoch": 0.09860312243221035,
"grad_norm": 0.46268323063850403,
"learning_rate": 9.729086208503174e-05,
"loss": 0.8606,
"step": 30
},
{
"epoch": 0.1018898931799507,
"grad_norm": 2.072200298309326,
"learning_rate": 9.701596950580806e-05,
"loss": 0.8873,
"step": 31
},
{
"epoch": 0.10517666392769104,
"grad_norm": 0.4932246506214142,
"learning_rate": 9.672822322997305e-05,
"loss": 1.0041,
"step": 32
},
{
"epoch": 0.10846343467543139,
"grad_norm": 0.6934109926223755,
"learning_rate": 9.642770192448536e-05,
"loss": 1.1726,
"step": 33
},
{
"epoch": 0.11175020542317174,
"grad_norm": 0.8347193598747253,
"learning_rate": 9.611448774886924e-05,
"loss": 1.268,
"step": 34
},
{
"epoch": 0.11503697617091208,
"grad_norm": 0.7671674489974976,
"learning_rate": 9.578866633275288e-05,
"loss": 1.0224,
"step": 35
},
{
"epoch": 0.11832374691865243,
"grad_norm": 0.7764635682106018,
"learning_rate": 9.545032675245813e-05,
"loss": 0.9414,
"step": 36
},
{
"epoch": 0.12161051766639278,
"grad_norm": 0.7140238881111145,
"learning_rate": 9.509956150664796e-05,
"loss": 0.6661,
"step": 37
},
{
"epoch": 0.12489728841413311,
"grad_norm": 0.7519691586494446,
"learning_rate": 9.473646649103818e-05,
"loss": 1.0302,
"step": 38
},
{
"epoch": 0.12818405916187345,
"grad_norm": 0.5438118577003479,
"learning_rate": 9.43611409721806e-05,
"loss": 0.8662,
"step": 39
},
{
"epoch": 0.1314708299096138,
"grad_norm": 0.599733829498291,
"learning_rate": 9.397368756032445e-05,
"loss": 0.6809,
"step": 40
},
{
"epoch": 0.13475760065735415,
"grad_norm": 0.518592894077301,
"learning_rate": 9.357421218136386e-05,
"loss": 0.8405,
"step": 41
},
{
"epoch": 0.13804437140509448,
"grad_norm": 0.463358074426651,
"learning_rate": 9.316282404787871e-05,
"loss": 0.8181,
"step": 42
},
{
"epoch": 0.14133114215283485,
"grad_norm": 0.43573182821273804,
"learning_rate": 9.273963562927695e-05,
"loss": 0.7311,
"step": 43
},
{
"epoch": 0.14461791290057519,
"grad_norm": 0.5833415985107422,
"learning_rate": 9.230476262104677e-05,
"loss": 0.8332,
"step": 44
},
{
"epoch": 0.14790468364831552,
"grad_norm": 0.4384503960609436,
"learning_rate": 9.185832391312644e-05,
"loss": 0.6512,
"step": 45
},
{
"epoch": 0.15119145439605589,
"grad_norm": 0.7110065221786499,
"learning_rate": 9.140044155740101e-05,
"loss": 0.8684,
"step": 46
},
{
"epoch": 0.15447822514379622,
"grad_norm": 0.8291717171669006,
"learning_rate": 9.093124073433463e-05,
"loss": 0.9217,
"step": 47
},
{
"epoch": 0.15776499589153656,
"grad_norm": 0.8114854097366333,
"learning_rate": 9.045084971874738e-05,
"loss": 0.8361,
"step": 48
},
{
"epoch": 0.16105176663927692,
"grad_norm": 0.8501179218292236,
"learning_rate": 8.995939984474624e-05,
"loss": 1.0698,
"step": 49
},
{
"epoch": 0.16433853738701726,
"grad_norm": 1.8633047342300415,
"learning_rate": 8.945702546981969e-05,
"loss": 1.3972,
"step": 50
},
{
"epoch": 0.16433853738701726,
"eval_loss": 0.6269950270652771,
"eval_runtime": 16.3428,
"eval_samples_per_second": 31.39,
"eval_steps_per_second": 7.893,
"step": 50
},
{
"epoch": 0.1676253081347576,
"grad_norm": 0.4559544026851654,
"learning_rate": 8.894386393810563e-05,
"loss": 0.7437,
"step": 51
},
{
"epoch": 0.17091207888249796,
"grad_norm": 0.4525269865989685,
"learning_rate": 8.842005554284296e-05,
"loss": 0.7677,
"step": 52
},
{
"epoch": 0.1741988496302383,
"grad_norm": 0.4368169605731964,
"learning_rate": 8.788574348801675e-05,
"loss": 0.7699,
"step": 53
},
{
"epoch": 0.17748562037797863,
"grad_norm": 0.3991347849369049,
"learning_rate": 8.73410738492077e-05,
"loss": 0.8881,
"step": 54
},
{
"epoch": 0.18077239112571897,
"grad_norm": 0.5175266861915588,
"learning_rate": 8.678619553365659e-05,
"loss": 0.747,
"step": 55
},
{
"epoch": 0.18405916187345933,
"grad_norm": 0.42107099294662476,
"learning_rate": 8.622126023955446e-05,
"loss": 0.5525,
"step": 56
},
{
"epoch": 0.18734593262119967,
"grad_norm": 0.452173113822937,
"learning_rate": 8.564642241456986e-05,
"loss": 0.6452,
"step": 57
},
{
"epoch": 0.19063270336894,
"grad_norm": 0.41782718896865845,
"learning_rate": 8.506183921362443e-05,
"loss": 0.3968,
"step": 58
},
{
"epoch": 0.19391947411668037,
"grad_norm": 0.4454297721385956,
"learning_rate": 8.44676704559283e-05,
"loss": 0.5575,
"step": 59
},
{
"epoch": 0.1972062448644207,
"grad_norm": 0.32409822940826416,
"learning_rate": 8.386407858128706e-05,
"loss": 0.4473,
"step": 60
},
{
"epoch": 0.20049301561216104,
"grad_norm": 0.3317202627658844,
"learning_rate": 8.32512286056924e-05,
"loss": 0.4111,
"step": 61
},
{
"epoch": 0.2037797863599014,
"grad_norm": 0.22182796895503998,
"learning_rate": 8.262928807620843e-05,
"loss": 0.3707,
"step": 62
},
{
"epoch": 0.20706655710764174,
"grad_norm": 0.250245600938797,
"learning_rate": 8.199842702516583e-05,
"loss": 0.2128,
"step": 63
},
{
"epoch": 0.21035332785538208,
"grad_norm": 0.3182259500026703,
"learning_rate": 8.135881792367686e-05,
"loss": 0.3179,
"step": 64
},
{
"epoch": 0.21364009860312244,
"grad_norm": 0.3628109395503998,
"learning_rate": 8.07106356344834e-05,
"loss": 0.3456,
"step": 65
},
{
"epoch": 0.21692686935086278,
"grad_norm": 0.32747212052345276,
"learning_rate": 8.005405736415126e-05,
"loss": 0.4021,
"step": 66
},
{
"epoch": 0.22021364009860311,
"grad_norm": 0.3861248195171356,
"learning_rate": 7.938926261462366e-05,
"loss": 0.1614,
"step": 67
},
{
"epoch": 0.22350041084634348,
"grad_norm": 0.2884339392185211,
"learning_rate": 7.871643313414718e-05,
"loss": 0.2831,
"step": 68
},
{
"epoch": 0.22678718159408381,
"grad_norm": 0.3135221302509308,
"learning_rate": 7.803575286758364e-05,
"loss": 0.2398,
"step": 69
},
{
"epoch": 0.23007395234182415,
"grad_norm": 0.9935585856437683,
"learning_rate": 7.734740790612136e-05,
"loss": 0.2058,
"step": 70
},
{
"epoch": 0.23336072308956451,
"grad_norm": 0.544156014919281,
"learning_rate": 7.66515864363997e-05,
"loss": 0.2752,
"step": 71
},
{
"epoch": 0.23664749383730485,
"grad_norm": 0.4534812271595001,
"learning_rate": 7.594847868906076e-05,
"loss": 0.1482,
"step": 72
},
{
"epoch": 0.2399342645850452,
"grad_norm": 0.40635770559310913,
"learning_rate": 7.52382768867422e-05,
"loss": 0.1309,
"step": 73
},
{
"epoch": 0.24322103533278555,
"grad_norm": 0.25662505626678467,
"learning_rate": 7.452117519152542e-05,
"loss": 0.0927,
"step": 74
},
{
"epoch": 0.2465078060805259,
"grad_norm": 0.33825063705444336,
"learning_rate": 7.379736965185368e-05,
"loss": 0.1928,
"step": 75
},
{
"epoch": 0.24979457682826622,
"grad_norm": 0.3406578600406647,
"learning_rate": 7.30670581489344e-05,
"loss": 0.3491,
"step": 76
},
{
"epoch": 0.2530813475760066,
"grad_norm": 0.39477869868278503,
"learning_rate": 7.233044034264034e-05,
"loss": 0.3476,
"step": 77
},
{
"epoch": 0.2563681183237469,
"grad_norm": 0.4040183126926422,
"learning_rate": 7.158771761692464e-05,
"loss": 0.489,
"step": 78
},
{
"epoch": 0.25965488907148726,
"grad_norm": 0.40438491106033325,
"learning_rate": 7.083909302476453e-05,
"loss": 0.5799,
"step": 79
},
{
"epoch": 0.2629416598192276,
"grad_norm": 0.7980288863182068,
"learning_rate": 7.008477123264848e-05,
"loss": 0.5116,
"step": 80
},
{
"epoch": 0.26622843056696793,
"grad_norm": 0.8446006774902344,
"learning_rate": 6.932495846462261e-05,
"loss": 0.5693,
"step": 81
},
{
"epoch": 0.2695152013147083,
"grad_norm": 0.5259266495704651,
"learning_rate": 6.855986244591104e-05,
"loss": 0.5988,
"step": 82
},
{
"epoch": 0.27280197206244866,
"grad_norm": 0.6898009181022644,
"learning_rate": 6.778969234612584e-05,
"loss": 0.4705,
"step": 83
},
{
"epoch": 0.27608874281018897,
"grad_norm": 0.4572669267654419,
"learning_rate": 6.701465872208216e-05,
"loss": 0.3367,
"step": 84
},
{
"epoch": 0.27937551355792933,
"grad_norm": 0.419035941362381,
"learning_rate": 6.623497346023418e-05,
"loss": 0.4817,
"step": 85
},
{
"epoch": 0.2826622843056697,
"grad_norm": 0.33516401052474976,
"learning_rate": 6.545084971874738e-05,
"loss": 0.2506,
"step": 86
},
{
"epoch": 0.28594905505341,
"grad_norm": 0.3988212049007416,
"learning_rate": 6.466250186922325e-05,
"loss": 0.362,
"step": 87
},
{
"epoch": 0.28923582580115037,
"grad_norm": 0.47392523288726807,
"learning_rate": 6.387014543809223e-05,
"loss": 0.4859,
"step": 88
},
{
"epoch": 0.29252259654889073,
"grad_norm": 0.3696557581424713,
"learning_rate": 6.307399704769099e-05,
"loss": 0.3675,
"step": 89
},
{
"epoch": 0.29580936729663104,
"grad_norm": 0.40943896770477295,
"learning_rate": 6.227427435703997e-05,
"loss": 0.4461,
"step": 90
},
{
"epoch": 0.2990961380443714,
"grad_norm": 0.43168923258781433,
"learning_rate": 6.147119600233758e-05,
"loss": 0.3183,
"step": 91
},
{
"epoch": 0.30238290879211177,
"grad_norm": 0.38362520933151245,
"learning_rate": 6.066498153718735e-05,
"loss": 0.4047,
"step": 92
},
{
"epoch": 0.3056696795398521,
"grad_norm": 0.3913039267063141,
"learning_rate": 5.985585137257401e-05,
"loss": 0.4147,
"step": 93
},
{
"epoch": 0.30895645028759244,
"grad_norm": 0.3679688572883606,
"learning_rate": 5.90440267166055e-05,
"loss": 0.3136,
"step": 94
},
{
"epoch": 0.3122432210353328,
"grad_norm": 0.5510644912719727,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.5742,
"step": 95
},
{
"epoch": 0.3155299917830731,
"grad_norm": 0.6156324148178101,
"learning_rate": 5.74131823855921e-05,
"loss": 0.4884,
"step": 96
},
{
"epoch": 0.3188167625308135,
"grad_norm": 0.556567907333374,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.4131,
"step": 97
},
{
"epoch": 0.32210353327855384,
"grad_norm": 0.603244960308075,
"learning_rate": 5.577423184847932e-05,
"loss": 0.5538,
"step": 98
},
{
"epoch": 0.32539030402629415,
"grad_norm": 0.5927567481994629,
"learning_rate": 5.495227651252315e-05,
"loss": 0.4704,
"step": 99
},
{
"epoch": 0.3286770747740345,
"grad_norm": 1.7233991622924805,
"learning_rate": 5.4128967273616625e-05,
"loss": 1.2242,
"step": 100
},
{
"epoch": 0.3286770747740345,
"eval_loss": 0.3188861608505249,
"eval_runtime": 16.4523,
"eval_samples_per_second": 31.181,
"eval_steps_per_second": 7.841,
"step": 100
},
{
"epoch": 0.3319638455217749,
"grad_norm": 0.33896926045417786,
"learning_rate": 5.330452921628497e-05,
"loss": 0.4904,
"step": 101
},
{
"epoch": 0.3352506162695152,
"grad_norm": 0.34122586250305176,
"learning_rate": 5.247918773366112e-05,
"loss": 0.522,
"step": 102
},
{
"epoch": 0.33853738701725555,
"grad_norm": 0.30066755414009094,
"learning_rate": 5.165316846586541e-05,
"loss": 0.575,
"step": 103
},
{
"epoch": 0.3418241577649959,
"grad_norm": 0.34648483991622925,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.5829,
"step": 104
},
{
"epoch": 0.3451109285127362,
"grad_norm": 0.3443598449230194,
"learning_rate": 5e-05,
"loss": 0.4209,
"step": 105
},
{
"epoch": 0.3483976992604766,
"grad_norm": 0.2928950786590576,
"learning_rate": 4.917330276168208e-05,
"loss": 0.2759,
"step": 106
},
{
"epoch": 0.35168447000821695,
"grad_norm": 0.23965677618980408,
"learning_rate": 4.834683153413459e-05,
"loss": 0.3019,
"step": 107
},
{
"epoch": 0.35497124075595726,
"grad_norm": 0.23738184571266174,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.2139,
"step": 108
},
{
"epoch": 0.3582580115036976,
"grad_norm": 0.30263885855674744,
"learning_rate": 4.669547078371504e-05,
"loss": 0.2152,
"step": 109
},
{
"epoch": 0.36154478225143794,
"grad_norm": 0.25680890679359436,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.2478,
"step": 110
},
{
"epoch": 0.3648315529991783,
"grad_norm": 0.22688838839530945,
"learning_rate": 4.504772348747687e-05,
"loss": 0.2176,
"step": 111
},
{
"epoch": 0.36811832374691866,
"grad_norm": 0.2743438184261322,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.2407,
"step": 112
},
{
"epoch": 0.37140509449465897,
"grad_norm": 0.20848655700683594,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.1105,
"step": 113
},
{
"epoch": 0.37469186524239934,
"grad_norm": 0.21718445420265198,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.1817,
"step": 114
},
{
"epoch": 0.3779786359901397,
"grad_norm": 0.21895334124565125,
"learning_rate": 4.17702704859633e-05,
"loss": 0.1831,
"step": 115
},
{
"epoch": 0.38126540673788,
"grad_norm": 0.23855812847614288,
"learning_rate": 4.095597328339452e-05,
"loss": 0.2006,
"step": 116
},
{
"epoch": 0.3845521774856204,
"grad_norm": 0.1995995193719864,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.1829,
"step": 117
},
{
"epoch": 0.38783894823336074,
"grad_norm": 0.2324177473783493,
"learning_rate": 3.933501846281267e-05,
"loss": 0.2264,
"step": 118
},
{
"epoch": 0.39112571898110104,
"grad_norm": 0.23554456233978271,
"learning_rate": 3.852880399766243e-05,
"loss": 0.22,
"step": 119
},
{
"epoch": 0.3944124897288414,
"grad_norm": 0.4167206883430481,
"learning_rate": 3.772572564296005e-05,
"loss": 0.192,
"step": 120
},
{
"epoch": 0.3976992604765818,
"grad_norm": 0.8786826729774475,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.144,
"step": 121
},
{
"epoch": 0.4009860312243221,
"grad_norm": 0.2801782488822937,
"learning_rate": 3.612985456190778e-05,
"loss": 0.1437,
"step": 122
},
{
"epoch": 0.40427280197206245,
"grad_norm": 0.31139618158340454,
"learning_rate": 3.533749813077677e-05,
"loss": 0.1134,
"step": 123
},
{
"epoch": 0.4075595727198028,
"grad_norm": 0.2824283838272095,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.1319,
"step": 124
},
{
"epoch": 0.4108463434675431,
"grad_norm": 0.2261425405740738,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.2231,
"step": 125
},
{
"epoch": 0.4141331142152835,
"grad_norm": 0.28707796335220337,
"learning_rate": 3.298534127791785e-05,
"loss": 0.2281,
"step": 126
},
{
"epoch": 0.41741988496302385,
"grad_norm": 0.2526625096797943,
"learning_rate": 3.221030765387417e-05,
"loss": 0.348,
"step": 127
},
{
"epoch": 0.42070665571076415,
"grad_norm": 0.3449920415878296,
"learning_rate": 3.144013755408895e-05,
"loss": 0.3178,
"step": 128
},
{
"epoch": 0.4239934264585045,
"grad_norm": 0.25349077582359314,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.2697,
"step": 129
},
{
"epoch": 0.4272801972062449,
"grad_norm": 0.39583712816238403,
"learning_rate": 2.991522876735154e-05,
"loss": 0.3819,
"step": 130
},
{
"epoch": 0.4305669679539852,
"grad_norm": 0.7952384948730469,
"learning_rate": 2.916090697523549e-05,
"loss": 0.2385,
"step": 131
},
{
"epoch": 0.43385373870172556,
"grad_norm": 0.5077905654907227,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.662,
"step": 132
},
{
"epoch": 0.4371405094494659,
"grad_norm": 0.6528022289276123,
"learning_rate": 2.766955965735968e-05,
"loss": 0.5801,
"step": 133
},
{
"epoch": 0.44042728019720623,
"grad_norm": 0.8854542374610901,
"learning_rate": 2.693294185106562e-05,
"loss": 0.4741,
"step": 134
},
{
"epoch": 0.4437140509449466,
"grad_norm": 0.6882192492485046,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.3931,
"step": 135
},
{
"epoch": 0.44700082169268696,
"grad_norm": 0.5874613523483276,
"learning_rate": 2.547882480847461e-05,
"loss": 0.3331,
"step": 136
},
{
"epoch": 0.45028759244042726,
"grad_norm": 0.38002461194992065,
"learning_rate": 2.476172311325783e-05,
"loss": 0.1443,
"step": 137
},
{
"epoch": 0.45357436318816763,
"grad_norm": 0.49303731322288513,
"learning_rate": 2.405152131093926e-05,
"loss": 0.2977,
"step": 138
},
{
"epoch": 0.456861133935908,
"grad_norm": 0.38906121253967285,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.2047,
"step": 139
},
{
"epoch": 0.4601479046836483,
"grad_norm": 0.3448793888092041,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.2172,
"step": 140
},
{
"epoch": 0.46343467543138867,
"grad_norm": 0.5098046660423279,
"learning_rate": 2.196424713241637e-05,
"loss": 0.2515,
"step": 141
},
{
"epoch": 0.46672144617912903,
"grad_norm": 0.6721360087394714,
"learning_rate": 2.128356686585282e-05,
"loss": 0.2549,
"step": 142
},
{
"epoch": 0.47000821692686934,
"grad_norm": 0.6480476260185242,
"learning_rate": 2.061073738537635e-05,
"loss": 0.2612,
"step": 143
},
{
"epoch": 0.4732949876746097,
"grad_norm": 0.3877548575401306,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.1928,
"step": 144
},
{
"epoch": 0.47658175842235007,
"grad_norm": 0.3219442665576935,
"learning_rate": 1.928936436551661e-05,
"loss": 0.2134,
"step": 145
},
{
"epoch": 0.4798685291700904,
"grad_norm": 0.3933016061782837,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.2965,
"step": 146
},
{
"epoch": 0.48315529991783074,
"grad_norm": 0.39766329526901245,
"learning_rate": 1.800157297483417e-05,
"loss": 0.2177,
"step": 147
},
{
"epoch": 0.4864420706655711,
"grad_norm": 0.43686503171920776,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.3232,
"step": 148
},
{
"epoch": 0.4897288414133114,
"grad_norm": 0.38429713249206543,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.2532,
"step": 149
},
{
"epoch": 0.4930156121610518,
"grad_norm": 1.483277440071106,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.6403,
"step": 150
},
{
"epoch": 0.4930156121610518,
"eval_loss": 0.22606314718723297,
"eval_runtime": 16.4597,
"eval_samples_per_second": 31.167,
"eval_steps_per_second": 7.837,
"step": 150
},
{
"epoch": 0.49630238290879214,
"grad_norm": 0.3249725103378296,
"learning_rate": 1.553232954407171e-05,
"loss": 0.3533,
"step": 151
},
{
"epoch": 0.49958915365653245,
"grad_norm": 0.32189080119132996,
"learning_rate": 1.4938160786375572e-05,
"loss": 0.3736,
"step": 152
},
{
"epoch": 0.5028759244042728,
"grad_norm": 0.32421982288360596,
"learning_rate": 1.435357758543015e-05,
"loss": 0.3918,
"step": 153
},
{
"epoch": 0.5061626951520132,
"grad_norm": 0.2580222487449646,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.4741,
"step": 154
},
{
"epoch": 0.5094494658997535,
"grad_norm": 0.33704525232315063,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.4128,
"step": 155
},
{
"epoch": 0.5127362366474938,
"grad_norm": 0.361449658870697,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.3237,
"step": 156
},
{
"epoch": 0.5160230073952342,
"grad_norm": 0.26285064220428467,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.1615,
"step": 157
},
{
"epoch": 0.5193097781429745,
"grad_norm": 0.2225951850414276,
"learning_rate": 1.157994445715706e-05,
"loss": 0.1396,
"step": 158
},
{
"epoch": 0.5225965488907148,
"grad_norm": 0.20313875377178192,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.2012,
"step": 159
},
{
"epoch": 0.5258833196384552,
"grad_norm": 0.22657664120197296,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.2195,
"step": 160
},
{
"epoch": 0.5291700903861956,
"grad_norm": 0.22878260910511017,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.1294,
"step": 161
},
{
"epoch": 0.5324568611339359,
"grad_norm": 0.23764368891716003,
"learning_rate": 9.549150281252633e-06,
"loss": 0.1884,
"step": 162
},
{
"epoch": 0.5357436318816763,
"grad_norm": 0.19356532394886017,
"learning_rate": 9.068759265665384e-06,
"loss": 0.0751,
"step": 163
},
{
"epoch": 0.5390304026294166,
"grad_norm": 0.19187261164188385,
"learning_rate": 8.599558442598998e-06,
"loss": 0.0729,
"step": 164
},
{
"epoch": 0.5423171733771569,
"grad_norm": 0.27540451288223267,
"learning_rate": 8.141676086873572e-06,
"loss": 0.153,
"step": 165
},
{
"epoch": 0.5456039441248973,
"grad_norm": 0.2189805954694748,
"learning_rate": 7.695237378953223e-06,
"loss": 0.0986,
"step": 166
},
{
"epoch": 0.5488907148726376,
"grad_norm": 0.2369193434715271,
"learning_rate": 7.260364370723044e-06,
"loss": 0.095,
"step": 167
},
{
"epoch": 0.5521774856203779,
"grad_norm": 0.23423631489276886,
"learning_rate": 6.837175952121306e-06,
"loss": 0.1879,
"step": 168
},
{
"epoch": 0.5554642563681184,
"grad_norm": 0.24483321607112885,
"learning_rate": 6.425787818636131e-06,
"loss": 0.1789,
"step": 169
},
{
"epoch": 0.5587510271158587,
"grad_norm": 0.42989063262939453,
"learning_rate": 6.026312439675552e-06,
"loss": 0.0937,
"step": 170
},
{
"epoch": 0.562037797863599,
"grad_norm": 0.34984058141708374,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.174,
"step": 171
},
{
"epoch": 0.5653245686113394,
"grad_norm": 0.4214020073413849,
"learning_rate": 5.263533508961827e-06,
"loss": 0.1106,
"step": 172
},
{
"epoch": 0.5686113393590797,
"grad_norm": 0.3998816907405853,
"learning_rate": 4.900438493352055e-06,
"loss": 0.0893,
"step": 173
},
{
"epoch": 0.57189811010682,
"grad_norm": 0.30972716212272644,
"learning_rate": 4.549673247541875e-06,
"loss": 0.1009,
"step": 174
},
{
"epoch": 0.5751848808545604,
"grad_norm": 0.2425047755241394,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.1632,
"step": 175
},
{
"epoch": 0.5784716516023007,
"grad_norm": 0.20142392814159393,
"learning_rate": 3.885512251130763e-06,
"loss": 0.1551,
"step": 176
},
{
"epoch": 0.581758422350041,
"grad_norm": 0.217716246843338,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.1367,
"step": 177
},
{
"epoch": 0.5850451930977815,
"grad_norm": 0.23498113453388214,
"learning_rate": 3.271776770026963e-06,
"loss": 0.2072,
"step": 178
},
{
"epoch": 0.5883319638455218,
"grad_norm": 0.2317870855331421,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.1968,
"step": 179
},
{
"epoch": 0.5916187345932621,
"grad_norm": 0.3005838990211487,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.2572,
"step": 180
},
{
"epoch": 0.5949055053410025,
"grad_norm": 0.39571020007133484,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.2892,
"step": 181
},
{
"epoch": 0.5981922760887428,
"grad_norm": 0.4269047975540161,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.5649,
"step": 182
},
{
"epoch": 0.6014790468364831,
"grad_norm": 0.4670911431312561,
"learning_rate": 1.962316193157593e-06,
"loss": 0.5174,
"step": 183
},
{
"epoch": 0.6047658175842235,
"grad_norm": 0.46366462111473083,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.4158,
"step": 184
},
{
"epoch": 0.6080525883319639,
"grad_norm": 0.6012901663780212,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.1436,
"step": 185
},
{
"epoch": 0.6113393590797042,
"grad_norm": 0.6685888171195984,
"learning_rate": 1.333670137599713e-06,
"loss": 0.3459,
"step": 186
},
{
"epoch": 0.6146261298274446,
"grad_norm": 0.5841985940933228,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.2571,
"step": 187
},
{
"epoch": 0.6179129005751849,
"grad_norm": 0.4382514953613281,
"learning_rate": 9.810017062595322e-07,
"loss": 0.1154,
"step": 188
},
{
"epoch": 0.6211996713229252,
"grad_norm": 0.46723124384880066,
"learning_rate": 8.247462563808817e-07,
"loss": 0.207,
"step": 189
},
{
"epoch": 0.6244864420706656,
"grad_norm": 0.5373465418815613,
"learning_rate": 6.819348298638839e-07,
"loss": 0.2619,
"step": 190
},
{
"epoch": 0.6277732128184059,
"grad_norm": 0.4011353552341461,
"learning_rate": 5.526064699265753e-07,
"loss": 0.2443,
"step": 191
},
{
"epoch": 0.6310599835661462,
"grad_norm": 0.4876985549926758,
"learning_rate": 4.367965336512403e-07,
"loss": 0.1971,
"step": 192
},
{
"epoch": 0.6343467543138867,
"grad_norm": 0.35112836956977844,
"learning_rate": 3.3453668231809286e-07,
"loss": 0.213,
"step": 193
},
{
"epoch": 0.637633525061627,
"grad_norm": 0.4315146505832672,
"learning_rate": 2.458548727494292e-07,
"loss": 0.2362,
"step": 194
},
{
"epoch": 0.6409202958093673,
"grad_norm": 0.5324535369873047,
"learning_rate": 1.7077534966650766e-07,
"loss": 0.3856,
"step": 195
},
{
"epoch": 0.6442070665571077,
"grad_norm": 0.3898642957210541,
"learning_rate": 1.0931863906127327e-07,
"loss": 0.393,
"step": 196
},
{
"epoch": 0.647493837304848,
"grad_norm": 0.2846044600009918,
"learning_rate": 6.150154258476315e-08,
"loss": 0.1404,
"step": 197
},
{
"epoch": 0.6507806080525883,
"grad_norm": 0.37767189741134644,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.2469,
"step": 198
},
{
"epoch": 0.6540673788003287,
"grad_norm": 0.5033150315284729,
"learning_rate": 6.834750376549792e-09,
"loss": 0.4336,
"step": 199
},
{
"epoch": 0.657354149548069,
"grad_norm": 0.689267098903656,
"learning_rate": 0.0,
"loss": 0.4148,
"step": 200
},
{
"epoch": 0.657354149548069,
"eval_loss": 0.20633231103420258,
"eval_runtime": 16.348,
"eval_samples_per_second": 31.38,
"eval_steps_per_second": 7.891,
"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": 7.056528023696179e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}