arcwarden46's picture
Training in progress, step 200, checkpoint
0dc137e verified
{
"best_metric": 1.3242443799972534,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.02062334046557191,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00010311670232785956,
"grad_norm": 0.13641047477722168,
"learning_rate": 1e-05,
"loss": 0.8944,
"step": 1
},
{
"epoch": 0.00010311670232785956,
"eval_loss": 1.8116322755813599,
"eval_runtime": 506.7082,
"eval_samples_per_second": 32.236,
"eval_steps_per_second": 8.06,
"step": 1
},
{
"epoch": 0.00020623340465571912,
"grad_norm": 0.16207805275917053,
"learning_rate": 2e-05,
"loss": 1.0525,
"step": 2
},
{
"epoch": 0.0003093501069835787,
"grad_norm": 0.17482194304466248,
"learning_rate": 3e-05,
"loss": 1.0521,
"step": 3
},
{
"epoch": 0.00041246680931143824,
"grad_norm": 0.18694528937339783,
"learning_rate": 4e-05,
"loss": 1.1608,
"step": 4
},
{
"epoch": 0.0005155835116392978,
"grad_norm": 0.23052778840065002,
"learning_rate": 5e-05,
"loss": 1.1293,
"step": 5
},
{
"epoch": 0.0006187002139671574,
"grad_norm": 0.2428814172744751,
"learning_rate": 6e-05,
"loss": 1.1353,
"step": 6
},
{
"epoch": 0.0007218169162950169,
"grad_norm": 0.21254058182239532,
"learning_rate": 7e-05,
"loss": 1.166,
"step": 7
},
{
"epoch": 0.0008249336186228765,
"grad_norm": 0.21390515565872192,
"learning_rate": 8e-05,
"loss": 1.1166,
"step": 8
},
{
"epoch": 0.000928050320950736,
"grad_norm": 0.20631210505962372,
"learning_rate": 9e-05,
"loss": 1.0373,
"step": 9
},
{
"epoch": 0.0010311670232785956,
"grad_norm": 0.2021922767162323,
"learning_rate": 0.0001,
"loss": 1.0805,
"step": 10
},
{
"epoch": 0.0011342837256064552,
"grad_norm": 0.20203207433223724,
"learning_rate": 9.999316524962345e-05,
"loss": 1.0955,
"step": 11
},
{
"epoch": 0.0012374004279343148,
"grad_norm": 0.23040078580379486,
"learning_rate": 9.997266286704631e-05,
"loss": 1.0804,
"step": 12
},
{
"epoch": 0.0013405171302621741,
"grad_norm": 0.25250139832496643,
"learning_rate": 9.993849845741524e-05,
"loss": 1.0029,
"step": 13
},
{
"epoch": 0.0014436338325900337,
"grad_norm": 0.24783891439437866,
"learning_rate": 9.989068136093873e-05,
"loss": 1.1485,
"step": 14
},
{
"epoch": 0.0015467505349178933,
"grad_norm": 0.33059900999069214,
"learning_rate": 9.98292246503335e-05,
"loss": 1.419,
"step": 15
},
{
"epoch": 0.001649867237245753,
"grad_norm": 0.5424182415008545,
"learning_rate": 9.975414512725057e-05,
"loss": 1.724,
"step": 16
},
{
"epoch": 0.0017529839395736123,
"grad_norm": 0.4276541471481323,
"learning_rate": 9.966546331768191e-05,
"loss": 1.597,
"step": 17
},
{
"epoch": 0.001856100641901472,
"grad_norm": 0.40986865758895874,
"learning_rate": 9.956320346634876e-05,
"loss": 1.3401,
"step": 18
},
{
"epoch": 0.0019592173442293317,
"grad_norm": 0.4873920977115631,
"learning_rate": 9.944739353007344e-05,
"loss": 1.523,
"step": 19
},
{
"epoch": 0.002062334046557191,
"grad_norm": 0.49715304374694824,
"learning_rate": 9.931806517013612e-05,
"loss": 1.5551,
"step": 20
},
{
"epoch": 0.0021654507488850505,
"grad_norm": 0.6268296837806702,
"learning_rate": 9.917525374361912e-05,
"loss": 1.6177,
"step": 21
},
{
"epoch": 0.0022685674512129103,
"grad_norm": 0.5099827647209167,
"learning_rate": 9.901899829374047e-05,
"loss": 1.4615,
"step": 22
},
{
"epoch": 0.0023716841535407697,
"grad_norm": 0.521894097328186,
"learning_rate": 9.884934153917997e-05,
"loss": 1.5069,
"step": 23
},
{
"epoch": 0.0024748008558686295,
"grad_norm": 0.4909113943576813,
"learning_rate": 9.86663298624003e-05,
"loss": 1.4625,
"step": 24
},
{
"epoch": 0.002577917558196489,
"grad_norm": 0.46789324283599854,
"learning_rate": 9.847001329696653e-05,
"loss": 1.5941,
"step": 25
},
{
"epoch": 0.0026810342605243483,
"grad_norm": 0.5269290208816528,
"learning_rate": 9.826044551386744e-05,
"loss": 1.6364,
"step": 26
},
{
"epoch": 0.002784150962852208,
"grad_norm": 0.5379405617713928,
"learning_rate": 9.803768380684242e-05,
"loss": 1.7399,
"step": 27
},
{
"epoch": 0.0028872676651800675,
"grad_norm": 0.43918687105178833,
"learning_rate": 9.780178907671789e-05,
"loss": 1.5555,
"step": 28
},
{
"epoch": 0.0029903843675079273,
"grad_norm": 0.4902992248535156,
"learning_rate": 9.755282581475769e-05,
"loss": 1.5268,
"step": 29
},
{
"epoch": 0.0030935010698357867,
"grad_norm": 0.49381062388420105,
"learning_rate": 9.729086208503174e-05,
"loss": 1.5752,
"step": 30
},
{
"epoch": 0.003196617772163646,
"grad_norm": 0.48866763710975647,
"learning_rate": 9.701596950580806e-05,
"loss": 1.5789,
"step": 31
},
{
"epoch": 0.003299734474491506,
"grad_norm": 0.6181825995445251,
"learning_rate": 9.672822322997305e-05,
"loss": 1.6937,
"step": 32
},
{
"epoch": 0.0034028511768193653,
"grad_norm": 0.4787468910217285,
"learning_rate": 9.642770192448536e-05,
"loss": 1.4854,
"step": 33
},
{
"epoch": 0.0035059678791472247,
"grad_norm": 0.47436949610710144,
"learning_rate": 9.611448774886924e-05,
"loss": 1.3239,
"step": 34
},
{
"epoch": 0.0036090845814750845,
"grad_norm": 0.48589038848876953,
"learning_rate": 9.578866633275288e-05,
"loss": 1.3548,
"step": 35
},
{
"epoch": 0.003712201283802944,
"grad_norm": 0.6065889000892639,
"learning_rate": 9.545032675245813e-05,
"loss": 1.4574,
"step": 36
},
{
"epoch": 0.0038153179861308037,
"grad_norm": 0.6862572431564331,
"learning_rate": 9.509956150664796e-05,
"loss": 1.5534,
"step": 37
},
{
"epoch": 0.0039184346884586635,
"grad_norm": 0.6300075054168701,
"learning_rate": 9.473646649103818e-05,
"loss": 1.3874,
"step": 38
},
{
"epoch": 0.004021551390786523,
"grad_norm": 0.7213515639305115,
"learning_rate": 9.43611409721806e-05,
"loss": 1.4839,
"step": 39
},
{
"epoch": 0.004124668093114382,
"grad_norm": 0.7986886501312256,
"learning_rate": 9.397368756032445e-05,
"loss": 1.4517,
"step": 40
},
{
"epoch": 0.004227784795442242,
"grad_norm": 0.7812718152999878,
"learning_rate": 9.357421218136386e-05,
"loss": 1.3964,
"step": 41
},
{
"epoch": 0.004330901497770101,
"grad_norm": 0.7717916369438171,
"learning_rate": 9.316282404787871e-05,
"loss": 1.4102,
"step": 42
},
{
"epoch": 0.004434018200097961,
"grad_norm": 0.8012552261352539,
"learning_rate": 9.273963562927695e-05,
"loss": 1.6269,
"step": 43
},
{
"epoch": 0.004537134902425821,
"grad_norm": 0.7847433686256409,
"learning_rate": 9.230476262104677e-05,
"loss": 1.4313,
"step": 44
},
{
"epoch": 0.00464025160475368,
"grad_norm": 1.0275577306747437,
"learning_rate": 9.185832391312644e-05,
"loss": 1.5154,
"step": 45
},
{
"epoch": 0.004743368307081539,
"grad_norm": 0.9086756706237793,
"learning_rate": 9.140044155740101e-05,
"loss": 1.4996,
"step": 46
},
{
"epoch": 0.004846485009409399,
"grad_norm": 1.0171937942504883,
"learning_rate": 9.093124073433463e-05,
"loss": 1.5574,
"step": 47
},
{
"epoch": 0.004949601711737259,
"grad_norm": 1.250017523765564,
"learning_rate": 9.045084971874738e-05,
"loss": 1.7319,
"step": 48
},
{
"epoch": 0.0050527184140651184,
"grad_norm": 1.2786903381347656,
"learning_rate": 8.995939984474624e-05,
"loss": 1.6972,
"step": 49
},
{
"epoch": 0.005155835116392978,
"grad_norm": 1.166121244430542,
"learning_rate": 8.945702546981969e-05,
"loss": 1.5357,
"step": 50
},
{
"epoch": 0.005155835116392978,
"eval_loss": 1.4692386388778687,
"eval_runtime": 506.3027,
"eval_samples_per_second": 32.261,
"eval_steps_per_second": 8.066,
"step": 50
},
{
"epoch": 0.005258951818720837,
"grad_norm": 0.4233190715312958,
"learning_rate": 8.894386393810563e-05,
"loss": 0.9736,
"step": 51
},
{
"epoch": 0.005362068521048697,
"grad_norm": 0.4879826605319977,
"learning_rate": 8.842005554284296e-05,
"loss": 1.0618,
"step": 52
},
{
"epoch": 0.005465185223376557,
"grad_norm": 0.4813477694988251,
"learning_rate": 8.788574348801675e-05,
"loss": 1.1539,
"step": 53
},
{
"epoch": 0.005568301925704416,
"grad_norm": 0.36838722229003906,
"learning_rate": 8.73410738492077e-05,
"loss": 1.0146,
"step": 54
},
{
"epoch": 0.005671418628032276,
"grad_norm": 0.3081735372543335,
"learning_rate": 8.678619553365659e-05,
"loss": 1.0704,
"step": 55
},
{
"epoch": 0.005774535330360135,
"grad_norm": 0.25456702709198,
"learning_rate": 8.622126023955446e-05,
"loss": 1.0831,
"step": 56
},
{
"epoch": 0.005877652032687994,
"grad_norm": 0.25238028168678284,
"learning_rate": 8.564642241456986e-05,
"loss": 1.109,
"step": 57
},
{
"epoch": 0.005980768735015855,
"grad_norm": 0.18831264972686768,
"learning_rate": 8.506183921362443e-05,
"loss": 1.0105,
"step": 58
},
{
"epoch": 0.006083885437343714,
"grad_norm": 0.18811674416065216,
"learning_rate": 8.44676704559283e-05,
"loss": 1.0529,
"step": 59
},
{
"epoch": 0.006187002139671573,
"grad_norm": 0.19896279275417328,
"learning_rate": 8.386407858128706e-05,
"loss": 1.0484,
"step": 60
},
{
"epoch": 0.006290118841999433,
"grad_norm": 0.18097397685050964,
"learning_rate": 8.32512286056924e-05,
"loss": 1.0483,
"step": 61
},
{
"epoch": 0.006393235544327292,
"grad_norm": 0.1842641830444336,
"learning_rate": 8.262928807620843e-05,
"loss": 1.0997,
"step": 62
},
{
"epoch": 0.0064963522466551515,
"grad_norm": 0.21031005680561066,
"learning_rate": 8.199842702516583e-05,
"loss": 1.0689,
"step": 63
},
{
"epoch": 0.006599468948983012,
"grad_norm": 0.24033500254154205,
"learning_rate": 8.135881792367686e-05,
"loss": 1.1279,
"step": 64
},
{
"epoch": 0.006702585651310871,
"grad_norm": 0.26887041330337524,
"learning_rate": 8.07106356344834e-05,
"loss": 1.3336,
"step": 65
},
{
"epoch": 0.0068057023536387306,
"grad_norm": 0.3484480082988739,
"learning_rate": 8.005405736415126e-05,
"loss": 1.3802,
"step": 66
},
{
"epoch": 0.00690881905596659,
"grad_norm": 0.3319461941719055,
"learning_rate": 7.938926261462366e-05,
"loss": 1.4339,
"step": 67
},
{
"epoch": 0.007011935758294449,
"grad_norm": 0.3729444146156311,
"learning_rate": 7.871643313414718e-05,
"loss": 1.5006,
"step": 68
},
{
"epoch": 0.00711505246062231,
"grad_norm": 0.38358449935913086,
"learning_rate": 7.803575286758364e-05,
"loss": 1.5773,
"step": 69
},
{
"epoch": 0.007218169162950169,
"grad_norm": 0.39486539363861084,
"learning_rate": 7.734740790612136e-05,
"loss": 1.6413,
"step": 70
},
{
"epoch": 0.007321285865278028,
"grad_norm": 0.36329948902130127,
"learning_rate": 7.66515864363997e-05,
"loss": 1.3038,
"step": 71
},
{
"epoch": 0.007424402567605888,
"grad_norm": 0.4480375647544861,
"learning_rate": 7.594847868906076e-05,
"loss": 1.5851,
"step": 72
},
{
"epoch": 0.007527519269933747,
"grad_norm": 0.3552588224411011,
"learning_rate": 7.52382768867422e-05,
"loss": 1.4594,
"step": 73
},
{
"epoch": 0.007630635972261607,
"grad_norm": 0.3747362494468689,
"learning_rate": 7.452117519152542e-05,
"loss": 1.4801,
"step": 74
},
{
"epoch": 0.007733752674589467,
"grad_norm": 0.3422439992427826,
"learning_rate": 7.379736965185368e-05,
"loss": 1.3506,
"step": 75
},
{
"epoch": 0.007836869376917327,
"grad_norm": 0.3330959379673004,
"learning_rate": 7.30670581489344e-05,
"loss": 1.4198,
"step": 76
},
{
"epoch": 0.007939986079245186,
"grad_norm": 0.3605731129646301,
"learning_rate": 7.233044034264034e-05,
"loss": 1.4421,
"step": 77
},
{
"epoch": 0.008043102781573046,
"grad_norm": 0.42000338435173035,
"learning_rate": 7.158771761692464e-05,
"loss": 1.7123,
"step": 78
},
{
"epoch": 0.008146219483900905,
"grad_norm": 0.3885011076927185,
"learning_rate": 7.083909302476453e-05,
"loss": 1.4471,
"step": 79
},
{
"epoch": 0.008249336186228765,
"grad_norm": 0.45452171564102173,
"learning_rate": 7.008477123264848e-05,
"loss": 1.6733,
"step": 80
},
{
"epoch": 0.008352452888556624,
"grad_norm": 0.4291321039199829,
"learning_rate": 6.932495846462261e-05,
"loss": 1.6709,
"step": 81
},
{
"epoch": 0.008455569590884483,
"grad_norm": 0.3677813708782196,
"learning_rate": 6.855986244591104e-05,
"loss": 1.3811,
"step": 82
},
{
"epoch": 0.008558686293212343,
"grad_norm": 0.4475283920764923,
"learning_rate": 6.778969234612584e-05,
"loss": 1.5449,
"step": 83
},
{
"epoch": 0.008661802995540202,
"grad_norm": 0.32593345642089844,
"learning_rate": 6.701465872208216e-05,
"loss": 1.2744,
"step": 84
},
{
"epoch": 0.008764919697868061,
"grad_norm": 0.3548644781112671,
"learning_rate": 6.623497346023418e-05,
"loss": 1.2449,
"step": 85
},
{
"epoch": 0.008868036400195923,
"grad_norm": 0.47024431824684143,
"learning_rate": 6.545084971874738e-05,
"loss": 1.3106,
"step": 86
},
{
"epoch": 0.008971153102523782,
"grad_norm": 0.5437018275260925,
"learning_rate": 6.466250186922325e-05,
"loss": 1.4137,
"step": 87
},
{
"epoch": 0.009074269804851641,
"grad_norm": 0.650269627571106,
"learning_rate": 6.387014543809223e-05,
"loss": 1.4641,
"step": 88
},
{
"epoch": 0.0091773865071795,
"grad_norm": 0.5957223176956177,
"learning_rate": 6.307399704769099e-05,
"loss": 1.3022,
"step": 89
},
{
"epoch": 0.00928050320950736,
"grad_norm": 0.6246781349182129,
"learning_rate": 6.227427435703997e-05,
"loss": 1.5478,
"step": 90
},
{
"epoch": 0.00938361991183522,
"grad_norm": 0.7656978368759155,
"learning_rate": 6.147119600233758e-05,
"loss": 1.5412,
"step": 91
},
{
"epoch": 0.009486736614163079,
"grad_norm": 0.5739739537239075,
"learning_rate": 6.066498153718735e-05,
"loss": 1.414,
"step": 92
},
{
"epoch": 0.009589853316490938,
"grad_norm": 0.5765067934989929,
"learning_rate": 5.985585137257401e-05,
"loss": 1.3631,
"step": 93
},
{
"epoch": 0.009692970018818798,
"grad_norm": 0.6303744316101074,
"learning_rate": 5.90440267166055e-05,
"loss": 1.3773,
"step": 94
},
{
"epoch": 0.009796086721146657,
"grad_norm": 0.7818238139152527,
"learning_rate": 5.8229729514036705e-05,
"loss": 1.442,
"step": 95
},
{
"epoch": 0.009899203423474518,
"grad_norm": 0.7590016722679138,
"learning_rate": 5.74131823855921e-05,
"loss": 1.652,
"step": 96
},
{
"epoch": 0.010002320125802378,
"grad_norm": 0.7199719548225403,
"learning_rate": 5.6594608567103456e-05,
"loss": 1.4092,
"step": 97
},
{
"epoch": 0.010105436828130237,
"grad_norm": 0.8268016576766968,
"learning_rate": 5.577423184847932e-05,
"loss": 1.4708,
"step": 98
},
{
"epoch": 0.010208553530458096,
"grad_norm": 0.892266035079956,
"learning_rate": 5.495227651252315e-05,
"loss": 1.5041,
"step": 99
},
{
"epoch": 0.010311670232785956,
"grad_norm": 1.0809787511825562,
"learning_rate": 5.4128967273616625e-05,
"loss": 1.8147,
"step": 100
},
{
"epoch": 0.010311670232785956,
"eval_loss": 1.363740086555481,
"eval_runtime": 506.8274,
"eval_samples_per_second": 32.228,
"eval_steps_per_second": 8.058,
"step": 100
},
{
"epoch": 0.010414786935113815,
"grad_norm": 0.14795686304569244,
"learning_rate": 5.330452921628497e-05,
"loss": 0.9004,
"step": 101
},
{
"epoch": 0.010517903637441674,
"grad_norm": 0.17717111110687256,
"learning_rate": 5.247918773366112e-05,
"loss": 1.0257,
"step": 102
},
{
"epoch": 0.010621020339769534,
"grad_norm": 0.18498282134532928,
"learning_rate": 5.165316846586541e-05,
"loss": 1.0396,
"step": 103
},
{
"epoch": 0.010724137042097393,
"grad_norm": 0.19741852581501007,
"learning_rate": 5.0826697238317935e-05,
"loss": 1.1009,
"step": 104
},
{
"epoch": 0.010827253744425253,
"grad_norm": 0.20189106464385986,
"learning_rate": 5e-05,
"loss": 1.0569,
"step": 105
},
{
"epoch": 0.010930370446753114,
"grad_norm": 0.20939910411834717,
"learning_rate": 4.917330276168208e-05,
"loss": 1.0656,
"step": 106
},
{
"epoch": 0.011033487149080973,
"grad_norm": 0.2105722278356552,
"learning_rate": 4.834683153413459e-05,
"loss": 1.0898,
"step": 107
},
{
"epoch": 0.011136603851408832,
"grad_norm": 0.19876085221767426,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.9473,
"step": 108
},
{
"epoch": 0.011239720553736692,
"grad_norm": 0.20182077586650848,
"learning_rate": 4.669547078371504e-05,
"loss": 1.0884,
"step": 109
},
{
"epoch": 0.011342837256064551,
"grad_norm": 0.18769417703151703,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.9572,
"step": 110
},
{
"epoch": 0.01144595395839241,
"grad_norm": 0.18182441592216492,
"learning_rate": 4.504772348747687e-05,
"loss": 1.0277,
"step": 111
},
{
"epoch": 0.01154907066072027,
"grad_norm": 0.1890416145324707,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.9458,
"step": 112
},
{
"epoch": 0.01165218736304813,
"grad_norm": 0.1826457679271698,
"learning_rate": 4.3405391432896555e-05,
"loss": 1.042,
"step": 113
},
{
"epoch": 0.011755304065375989,
"grad_norm": 0.21521930396556854,
"learning_rate": 4.2586817614407895e-05,
"loss": 1.0792,
"step": 114
},
{
"epoch": 0.011858420767703848,
"grad_norm": 0.2592601776123047,
"learning_rate": 4.17702704859633e-05,
"loss": 1.2465,
"step": 115
},
{
"epoch": 0.01196153747003171,
"grad_norm": 0.351700097322464,
"learning_rate": 4.095597328339452e-05,
"loss": 1.4669,
"step": 116
},
{
"epoch": 0.012064654172359569,
"grad_norm": 0.4038744568824768,
"learning_rate": 4.0144148627425993e-05,
"loss": 1.4436,
"step": 117
},
{
"epoch": 0.012167770874687428,
"grad_norm": 0.3753279745578766,
"learning_rate": 3.933501846281267e-05,
"loss": 1.4066,
"step": 118
},
{
"epoch": 0.012270887577015287,
"grad_norm": 0.33974844217300415,
"learning_rate": 3.852880399766243e-05,
"loss": 1.3319,
"step": 119
},
{
"epoch": 0.012374004279343147,
"grad_norm": 0.3477650284767151,
"learning_rate": 3.772572564296005e-05,
"loss": 1.4443,
"step": 120
},
{
"epoch": 0.012477120981671006,
"grad_norm": 0.40520280599594116,
"learning_rate": 3.6926002952309016e-05,
"loss": 1.5132,
"step": 121
},
{
"epoch": 0.012580237683998866,
"grad_norm": 0.3967605233192444,
"learning_rate": 3.612985456190778e-05,
"loss": 1.4972,
"step": 122
},
{
"epoch": 0.012683354386326725,
"grad_norm": 0.4460206627845764,
"learning_rate": 3.533749813077677e-05,
"loss": 1.6543,
"step": 123
},
{
"epoch": 0.012786471088654584,
"grad_norm": 0.4313359558582306,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.7027,
"step": 124
},
{
"epoch": 0.012889587790982444,
"grad_norm": 0.38823527097702026,
"learning_rate": 3.3765026539765834e-05,
"loss": 1.5328,
"step": 125
},
{
"epoch": 0.012992704493310303,
"grad_norm": 0.4104168713092804,
"learning_rate": 3.298534127791785e-05,
"loss": 1.4856,
"step": 126
},
{
"epoch": 0.013095821195638164,
"grad_norm": 0.44358229637145996,
"learning_rate": 3.221030765387417e-05,
"loss": 1.5431,
"step": 127
},
{
"epoch": 0.013198937897966024,
"grad_norm": 0.419261634349823,
"learning_rate": 3.144013755408895e-05,
"loss": 1.5564,
"step": 128
},
{
"epoch": 0.013302054600293883,
"grad_norm": 0.468816876411438,
"learning_rate": 3.0675041535377405e-05,
"loss": 1.5998,
"step": 129
},
{
"epoch": 0.013405171302621742,
"grad_norm": 0.40720266103744507,
"learning_rate": 2.991522876735154e-05,
"loss": 1.6278,
"step": 130
},
{
"epoch": 0.013508288004949602,
"grad_norm": 0.37988948822021484,
"learning_rate": 2.916090697523549e-05,
"loss": 1.4482,
"step": 131
},
{
"epoch": 0.013611404707277461,
"grad_norm": 0.41549137234687805,
"learning_rate": 2.8412282383075363e-05,
"loss": 1.4159,
"step": 132
},
{
"epoch": 0.01371452140960532,
"grad_norm": 0.4578942656517029,
"learning_rate": 2.766955965735968e-05,
"loss": 1.7196,
"step": 133
},
{
"epoch": 0.01381763811193318,
"grad_norm": 0.37664926052093506,
"learning_rate": 2.693294185106562e-05,
"loss": 1.4267,
"step": 134
},
{
"epoch": 0.01392075481426104,
"grad_norm": 0.4693012833595276,
"learning_rate": 2.6202630348146324e-05,
"loss": 1.5935,
"step": 135
},
{
"epoch": 0.014023871516588899,
"grad_norm": 0.38475286960601807,
"learning_rate": 2.547882480847461e-05,
"loss": 1.3708,
"step": 136
},
{
"epoch": 0.01412698821891676,
"grad_norm": 0.45392167568206787,
"learning_rate": 2.476172311325783e-05,
"loss": 1.1787,
"step": 137
},
{
"epoch": 0.01423010492124462,
"grad_norm": 0.49088478088378906,
"learning_rate": 2.405152131093926e-05,
"loss": 1.3393,
"step": 138
},
{
"epoch": 0.014333221623572479,
"grad_norm": 0.5570761561393738,
"learning_rate": 2.3348413563600325e-05,
"loss": 1.4169,
"step": 139
},
{
"epoch": 0.014436338325900338,
"grad_norm": 0.5477977991104126,
"learning_rate": 2.2652592093878666e-05,
"loss": 1.3538,
"step": 140
},
{
"epoch": 0.014539455028228197,
"grad_norm": 0.5661804676055908,
"learning_rate": 2.196424713241637e-05,
"loss": 1.2375,
"step": 141
},
{
"epoch": 0.014642571730556057,
"grad_norm": 0.5767088532447815,
"learning_rate": 2.128356686585282e-05,
"loss": 1.2619,
"step": 142
},
{
"epoch": 0.014745688432883916,
"grad_norm": 0.6942093968391418,
"learning_rate": 2.061073738537635e-05,
"loss": 1.4754,
"step": 143
},
{
"epoch": 0.014848805135211775,
"grad_norm": 0.6901765465736389,
"learning_rate": 1.9945942635848748e-05,
"loss": 1.485,
"step": 144
},
{
"epoch": 0.014951921837539635,
"grad_norm": 0.7722551822662354,
"learning_rate": 1.928936436551661e-05,
"loss": 1.4824,
"step": 145
},
{
"epoch": 0.015055038539867494,
"grad_norm": 0.7323166131973267,
"learning_rate": 1.8641182076323148e-05,
"loss": 1.3823,
"step": 146
},
{
"epoch": 0.015158155242195355,
"grad_norm": 0.7713239192962646,
"learning_rate": 1.800157297483417e-05,
"loss": 1.421,
"step": 147
},
{
"epoch": 0.015261271944523215,
"grad_norm": 0.9180830121040344,
"learning_rate": 1.7370711923791567e-05,
"loss": 1.4636,
"step": 148
},
{
"epoch": 0.015364388646851074,
"grad_norm": 0.8078856468200684,
"learning_rate": 1.6748771394307585e-05,
"loss": 1.4319,
"step": 149
},
{
"epoch": 0.015467505349178933,
"grad_norm": 1.2015869617462158,
"learning_rate": 1.6135921418712956e-05,
"loss": 1.7577,
"step": 150
},
{
"epoch": 0.015467505349178933,
"eval_loss": 1.3284672498703003,
"eval_runtime": 506.7409,
"eval_samples_per_second": 32.233,
"eval_steps_per_second": 8.059,
"step": 150
},
{
"epoch": 0.015570622051506793,
"grad_norm": 0.10401152819395065,
"learning_rate": 1.553232954407171e-05,
"loss": 0.8956,
"step": 151
},
{
"epoch": 0.015673738753834654,
"grad_norm": 0.1082741841673851,
"learning_rate": 1.4938160786375572e-05,
"loss": 1.0063,
"step": 152
},
{
"epoch": 0.015776855456162513,
"grad_norm": 0.1250486522912979,
"learning_rate": 1.435357758543015e-05,
"loss": 0.9764,
"step": 153
},
{
"epoch": 0.015879972158490373,
"grad_norm": 0.13116863369941711,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.9793,
"step": 154
},
{
"epoch": 0.015983088860818232,
"grad_norm": 0.13560180366039276,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.978,
"step": 155
},
{
"epoch": 0.01608620556314609,
"grad_norm": 0.17932438850402832,
"learning_rate": 1.2658926150792322e-05,
"loss": 1.058,
"step": 156
},
{
"epoch": 0.01618932226547395,
"grad_norm": 0.17844700813293457,
"learning_rate": 1.2114256511983274e-05,
"loss": 1.1249,
"step": 157
},
{
"epoch": 0.01629243896780181,
"grad_norm": 0.17633530497550964,
"learning_rate": 1.157994445715706e-05,
"loss": 1.0437,
"step": 158
},
{
"epoch": 0.01639555567012967,
"grad_norm": 0.16599993407726288,
"learning_rate": 1.1056136061894384e-05,
"loss": 1.052,
"step": 159
},
{
"epoch": 0.01649867237245753,
"grad_norm": 0.16478130221366882,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.9945,
"step": 160
},
{
"epoch": 0.01660178907478539,
"grad_norm": 0.15815843641757965,
"learning_rate": 1.0040600155253765e-05,
"loss": 1.0654,
"step": 161
},
{
"epoch": 0.016704905777113248,
"grad_norm": 0.18982729315757751,
"learning_rate": 9.549150281252633e-06,
"loss": 1.1457,
"step": 162
},
{
"epoch": 0.016808022479441107,
"grad_norm": 0.1751786768436432,
"learning_rate": 9.068759265665384e-06,
"loss": 1.0106,
"step": 163
},
{
"epoch": 0.016911139181768967,
"grad_norm": 0.19624489545822144,
"learning_rate": 8.599558442598998e-06,
"loss": 1.0653,
"step": 164
},
{
"epoch": 0.017014255884096826,
"grad_norm": 0.2050933986902237,
"learning_rate": 8.141676086873572e-06,
"loss": 1.1671,
"step": 165
},
{
"epoch": 0.017117372586424685,
"grad_norm": 0.2514212727546692,
"learning_rate": 7.695237378953223e-06,
"loss": 1.2161,
"step": 166
},
{
"epoch": 0.017220489288752545,
"grad_norm": 0.37303903698921204,
"learning_rate": 7.260364370723044e-06,
"loss": 1.3017,
"step": 167
},
{
"epoch": 0.017323605991080404,
"grad_norm": 0.413673996925354,
"learning_rate": 6.837175952121306e-06,
"loss": 1.423,
"step": 168
},
{
"epoch": 0.017426722693408263,
"grad_norm": 0.46047505736351013,
"learning_rate": 6.425787818636131e-06,
"loss": 1.4109,
"step": 169
},
{
"epoch": 0.017529839395736123,
"grad_norm": 0.4138045012950897,
"learning_rate": 6.026312439675552e-06,
"loss": 1.4099,
"step": 170
},
{
"epoch": 0.017632956098063982,
"grad_norm": 0.4037923812866211,
"learning_rate": 5.6388590278194096e-06,
"loss": 1.4191,
"step": 171
},
{
"epoch": 0.017736072800391845,
"grad_norm": 0.5340560674667358,
"learning_rate": 5.263533508961827e-06,
"loss": 1.7325,
"step": 172
},
{
"epoch": 0.017839189502719704,
"grad_norm": 0.3980885148048401,
"learning_rate": 4.900438493352055e-06,
"loss": 1.4803,
"step": 173
},
{
"epoch": 0.017942306205047564,
"grad_norm": 0.4497031271457672,
"learning_rate": 4.549673247541875e-06,
"loss": 1.5099,
"step": 174
},
{
"epoch": 0.018045422907375423,
"grad_norm": 0.4226648509502411,
"learning_rate": 4.2113336672471245e-06,
"loss": 1.492,
"step": 175
},
{
"epoch": 0.018148539609703283,
"grad_norm": 0.44598400592803955,
"learning_rate": 3.885512251130763e-06,
"loss": 1.5066,
"step": 176
},
{
"epoch": 0.018251656312031142,
"grad_norm": 0.42252328991889954,
"learning_rate": 3.5722980755146517e-06,
"loss": 1.5739,
"step": 177
},
{
"epoch": 0.018354773014359,
"grad_norm": 0.46086522936820984,
"learning_rate": 3.271776770026963e-06,
"loss": 1.4554,
"step": 178
},
{
"epoch": 0.01845788971668686,
"grad_norm": 0.40245306491851807,
"learning_rate": 2.9840304941919415e-06,
"loss": 1.3787,
"step": 179
},
{
"epoch": 0.01856100641901472,
"grad_norm": 0.42477142810821533,
"learning_rate": 2.7091379149682685e-06,
"loss": 1.4888,
"step": 180
},
{
"epoch": 0.01866412312134258,
"grad_norm": 0.4308255612850189,
"learning_rate": 2.4471741852423237e-06,
"loss": 1.5525,
"step": 181
},
{
"epoch": 0.01876723982367044,
"grad_norm": 0.40677839517593384,
"learning_rate": 2.1982109232821178e-06,
"loss": 1.4496,
"step": 182
},
{
"epoch": 0.0188703565259983,
"grad_norm": 0.4230005443096161,
"learning_rate": 1.962316193157593e-06,
"loss": 1.4637,
"step": 183
},
{
"epoch": 0.018973473228326158,
"grad_norm": 0.39707356691360474,
"learning_rate": 1.7395544861325718e-06,
"loss": 1.299,
"step": 184
},
{
"epoch": 0.019076589930654017,
"grad_norm": 0.3630697727203369,
"learning_rate": 1.5299867030334814e-06,
"loss": 1.2778,
"step": 185
},
{
"epoch": 0.019179706632981876,
"grad_norm": 0.3885824978351593,
"learning_rate": 1.333670137599713e-06,
"loss": 1.253,
"step": 186
},
{
"epoch": 0.019282823335309736,
"grad_norm": 0.5005578994750977,
"learning_rate": 1.1506584608200367e-06,
"loss": 1.3638,
"step": 187
},
{
"epoch": 0.019385940037637595,
"grad_norm": 0.5407949090003967,
"learning_rate": 9.810017062595322e-07,
"loss": 1.2982,
"step": 188
},
{
"epoch": 0.019489056739965455,
"grad_norm": 0.5471893548965454,
"learning_rate": 8.247462563808817e-07,
"loss": 1.2282,
"step": 189
},
{
"epoch": 0.019592173442293314,
"grad_norm": 0.5935094952583313,
"learning_rate": 6.819348298638839e-07,
"loss": 1.3384,
"step": 190
},
{
"epoch": 0.019695290144621173,
"grad_norm": 0.6995060443878174,
"learning_rate": 5.526064699265753e-07,
"loss": 1.4361,
"step": 191
},
{
"epoch": 0.019798406846949036,
"grad_norm": 0.6163309812545776,
"learning_rate": 4.367965336512403e-07,
"loss": 1.3297,
"step": 192
},
{
"epoch": 0.019901523549276896,
"grad_norm": 0.6966249942779541,
"learning_rate": 3.3453668231809286e-07,
"loss": 1.4012,
"step": 193
},
{
"epoch": 0.020004640251604755,
"grad_norm": 0.8141657710075378,
"learning_rate": 2.458548727494292e-07,
"loss": 1.4142,
"step": 194
},
{
"epoch": 0.020107756953932614,
"grad_norm": 0.7082520723342896,
"learning_rate": 1.7077534966650766e-07,
"loss": 1.4988,
"step": 195
},
{
"epoch": 0.020210873656260474,
"grad_norm": 0.7098881006240845,
"learning_rate": 1.0931863906127327e-07,
"loss": 1.4731,
"step": 196
},
{
"epoch": 0.020313990358588333,
"grad_norm": 0.8272214531898499,
"learning_rate": 6.150154258476315e-08,
"loss": 1.4376,
"step": 197
},
{
"epoch": 0.020417107060916193,
"grad_norm": 0.7066119313240051,
"learning_rate": 2.7337132953697554e-08,
"loss": 1.3871,
"step": 198
},
{
"epoch": 0.020520223763244052,
"grad_norm": 1.0534216165542603,
"learning_rate": 6.834750376549792e-09,
"loss": 1.5164,
"step": 199
},
{
"epoch": 0.02062334046557191,
"grad_norm": 1.0066883563995361,
"learning_rate": 0.0,
"loss": 1.4387,
"step": 200
},
{
"epoch": 0.02062334046557191,
"eval_loss": 1.3242443799972534,
"eval_runtime": 507.7738,
"eval_samples_per_second": 32.168,
"eval_steps_per_second": 8.043,
"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": 6.874530817926758e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}