dada22231's picture
Training in progress, step 95, checkpoint
b525ffc verified
{
"best_metric": 2.399653673171997,
"best_model_checkpoint": "miner_id_24/checkpoint-75",
"epoch": 2.931533269045323,
"eval_steps": 25,
"global_step": 95,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03085824493731919,
"grad_norm": 3.483962297439575,
"learning_rate": 3.3333333333333335e-05,
"loss": 3.0123,
"step": 1
},
{
"epoch": 0.03085824493731919,
"eval_loss": 3.7543375492095947,
"eval_runtime": 1.0337,
"eval_samples_per_second": 48.37,
"eval_steps_per_second": 12.576,
"step": 1
},
{
"epoch": 0.06171648987463838,
"grad_norm": 5.019814491271973,
"learning_rate": 6.666666666666667e-05,
"loss": 3.1782,
"step": 2
},
{
"epoch": 0.09257473481195758,
"grad_norm": 1.596342921257019,
"learning_rate": 0.0001,
"loss": 3.2528,
"step": 3
},
{
"epoch": 0.12343297974927676,
"grad_norm": 1.8322774171829224,
"learning_rate": 9.997376600647783e-05,
"loss": 3.4564,
"step": 4
},
{
"epoch": 0.15429122468659595,
"grad_norm": 1.8009212017059326,
"learning_rate": 9.989509461357426e-05,
"loss": 3.5413,
"step": 5
},
{
"epoch": 0.18514946962391515,
"grad_norm": 2.0400755405426025,
"learning_rate": 9.976407754861426e-05,
"loss": 3.5354,
"step": 6
},
{
"epoch": 0.21600771456123433,
"grad_norm": 2.3967275619506836,
"learning_rate": 9.958086757163489e-05,
"loss": 3.8566,
"step": 7
},
{
"epoch": 0.24686595949855353,
"grad_norm": 3.859480857849121,
"learning_rate": 9.934567829727386e-05,
"loss": 4.6317,
"step": 8
},
{
"epoch": 0.2777242044358727,
"grad_norm": 1.6781890392303467,
"learning_rate": 9.905878394570453e-05,
"loss": 2.8004,
"step": 9
},
{
"epoch": 0.3085824493731919,
"grad_norm": 1.3796833753585815,
"learning_rate": 9.872051902290737e-05,
"loss": 2.965,
"step": 10
},
{
"epoch": 0.3394406943105111,
"grad_norm": 0.9881917834281921,
"learning_rate": 9.833127793065098e-05,
"loss": 2.9565,
"step": 11
},
{
"epoch": 0.3702989392478303,
"grad_norm": 0.948172926902771,
"learning_rate": 9.789151450663723e-05,
"loss": 2.8742,
"step": 12
},
{
"epoch": 0.40115718418514945,
"grad_norm": 1.1040772199630737,
"learning_rate": 9.740174149534693e-05,
"loss": 2.965,
"step": 13
},
{
"epoch": 0.43201542912246865,
"grad_norm": 1.1895042657852173,
"learning_rate": 9.686252995020249e-05,
"loss": 3.1018,
"step": 14
},
{
"epoch": 0.46287367405978785,
"grad_norm": 2.180389642715454,
"learning_rate": 9.627450856774539e-05,
"loss": 3.3855,
"step": 15
},
{
"epoch": 0.49373191899710706,
"grad_norm": 5.135152816772461,
"learning_rate": 9.563836295460398e-05,
"loss": 3.8834,
"step": 16
},
{
"epoch": 0.5245901639344263,
"grad_norm": 0.8842887878417969,
"learning_rate": 9.495483482810688e-05,
"loss": 2.6782,
"step": 17
},
{
"epoch": 0.5554484088717454,
"grad_norm": 0.8219107389450073,
"learning_rate": 9.422472115147382e-05,
"loss": 2.6542,
"step": 18
},
{
"epoch": 0.5863066538090647,
"grad_norm": 0.9832227230072021,
"learning_rate": 9.3448873204592e-05,
"loss": 2.7092,
"step": 19
},
{
"epoch": 0.6171648987463838,
"grad_norm": 1.3776500225067139,
"learning_rate": 9.2628195591462e-05,
"loss": 2.7271,
"step": 20
},
{
"epoch": 0.648023143683703,
"grad_norm": 1.578552007675171,
"learning_rate": 9.176364518546989e-05,
"loss": 2.7814,
"step": 21
},
{
"epoch": 0.6788813886210222,
"grad_norm": 1.2780201435089111,
"learning_rate": 9.08562300137157e-05,
"loss": 2.8189,
"step": 22
},
{
"epoch": 0.7097396335583414,
"grad_norm": 1.4978731870651245,
"learning_rate": 8.990700808169889e-05,
"loss": 2.9776,
"step": 23
},
{
"epoch": 0.7405978784956606,
"grad_norm": 4.018599033355713,
"learning_rate": 8.891708613973126e-05,
"loss": 3.2692,
"step": 24
},
{
"epoch": 0.7714561234329798,
"grad_norm": 0.643608570098877,
"learning_rate": 8.788761839251559e-05,
"loss": 2.5616,
"step": 25
},
{
"epoch": 0.7714561234329798,
"eval_loss": 2.653991460800171,
"eval_runtime": 1.0209,
"eval_samples_per_second": 48.978,
"eval_steps_per_second": 12.734,
"step": 25
},
{
"epoch": 0.8023143683702989,
"grad_norm": 0.6692939400672913,
"learning_rate": 8.681980515339464e-05,
"loss": 2.6014,
"step": 26
},
{
"epoch": 0.8331726133076182,
"grad_norm": 0.6837179660797119,
"learning_rate": 8.571489144483944e-05,
"loss": 2.614,
"step": 27
},
{
"epoch": 0.8640308582449373,
"grad_norm": 0.7611942291259766,
"learning_rate": 8.457416554680877e-05,
"loss": 2.6286,
"step": 28
},
{
"epoch": 0.8948891031822566,
"grad_norm": 0.8610087633132935,
"learning_rate": 8.339895749467238e-05,
"loss": 2.7091,
"step": 29
},
{
"epoch": 0.9257473481195757,
"grad_norm": 0.9536398649215698,
"learning_rate": 8.219063752844926e-05,
"loss": 2.6736,
"step": 30
},
{
"epoch": 0.9566055930568949,
"grad_norm": 1.5485323667526245,
"learning_rate": 8.095061449516903e-05,
"loss": 2.7427,
"step": 31
},
{
"epoch": 0.9874638379942141,
"grad_norm": 2.791057586669922,
"learning_rate": 7.968033420621935e-05,
"loss": 2.9027,
"step": 32
},
{
"epoch": 1.0183220829315334,
"grad_norm": 1.133805274963379,
"learning_rate": 7.838127775159452e-05,
"loss": 4.2342,
"step": 33
},
{
"epoch": 1.0491803278688525,
"grad_norm": 0.5696182250976562,
"learning_rate": 7.705495977301078e-05,
"loss": 2.4703,
"step": 34
},
{
"epoch": 1.0800385728061717,
"grad_norm": 0.7950026988983154,
"learning_rate": 7.570292669790186e-05,
"loss": 2.5597,
"step": 35
},
{
"epoch": 1.1108968177434908,
"grad_norm": 0.8173376321792603,
"learning_rate": 7.43267549363537e-05,
"loss": 2.6145,
"step": 36
},
{
"epoch": 1.14175506268081,
"grad_norm": 0.7578170895576477,
"learning_rate": 7.292804904308087e-05,
"loss": 2.4873,
"step": 37
},
{
"epoch": 1.1726133076181293,
"grad_norm": 0.9220737814903259,
"learning_rate": 7.150843984658754e-05,
"loss": 2.6142,
"step": 38
},
{
"epoch": 1.2034715525554485,
"grad_norm": 1.000977635383606,
"learning_rate": 7.006958254769438e-05,
"loss": 2.7668,
"step": 39
},
{
"epoch": 1.2343297974927676,
"grad_norm": 1.9137243032455444,
"learning_rate": 6.861315478964841e-05,
"loss": 2.6618,
"step": 40
},
{
"epoch": 1.2651880424300868,
"grad_norm": 1.144348382949829,
"learning_rate": 6.714085470206609e-05,
"loss": 2.2853,
"step": 41
},
{
"epoch": 1.296046287367406,
"grad_norm": 0.494349867105484,
"learning_rate": 6.56543989209901e-05,
"loss": 2.4441,
"step": 42
},
{
"epoch": 1.326904532304725,
"grad_norm": 0.6220836639404297,
"learning_rate": 6.415552058736854e-05,
"loss": 2.4758,
"step": 43
},
{
"epoch": 1.3577627772420444,
"grad_norm": 0.6606362462043762,
"learning_rate": 6.264596732629e-05,
"loss": 2.5194,
"step": 44
},
{
"epoch": 1.3886210221793636,
"grad_norm": 0.7131364345550537,
"learning_rate": 6.112749920933111e-05,
"loss": 2.4692,
"step": 45
},
{
"epoch": 1.4194792671166827,
"grad_norm": 0.7623465061187744,
"learning_rate": 5.960188670239154e-05,
"loss": 2.4903,
"step": 46
},
{
"epoch": 1.4503375120540019,
"grad_norm": 0.8568875193595886,
"learning_rate": 5.80709086014102e-05,
"loss": 2.6904,
"step": 47
},
{
"epoch": 1.4811957569913212,
"grad_norm": 1.716271162033081,
"learning_rate": 5.653634995836856e-05,
"loss": 2.6191,
"step": 48
},
{
"epoch": 1.5120540019286404,
"grad_norm": 1.0471079349517822,
"learning_rate": 5.500000000000001e-05,
"loss": 2.2445,
"step": 49
},
{
"epoch": 1.5429122468659595,
"grad_norm": 0.5166476368904114,
"learning_rate": 5.346365004163145e-05,
"loss": 2.3682,
"step": 50
},
{
"epoch": 1.5429122468659595,
"eval_loss": 2.457026958465576,
"eval_runtime": 1.0293,
"eval_samples_per_second": 48.575,
"eval_steps_per_second": 12.63,
"step": 50
},
{
"epoch": 1.5737704918032787,
"grad_norm": 0.5249651670455933,
"learning_rate": 5.192909139858981e-05,
"loss": 2.4008,
"step": 51
},
{
"epoch": 1.6046287367405978,
"grad_norm": 0.6013681888580322,
"learning_rate": 5.0398113297608465e-05,
"loss": 2.4913,
"step": 52
},
{
"epoch": 1.635486981677917,
"grad_norm": 0.6412144303321838,
"learning_rate": 4.887250079066892e-05,
"loss": 2.4426,
"step": 53
},
{
"epoch": 1.666345226615236,
"grad_norm": 0.6970781683921814,
"learning_rate": 4.7354032673710005e-05,
"loss": 2.4047,
"step": 54
},
{
"epoch": 1.6972034715525555,
"grad_norm": 0.9001191258430481,
"learning_rate": 4.584447941263149e-05,
"loss": 2.6642,
"step": 55
},
{
"epoch": 1.7280617164898746,
"grad_norm": 1.341004729270935,
"learning_rate": 4.43456010790099e-05,
"loss": 2.6088,
"step": 56
},
{
"epoch": 1.758919961427194,
"grad_norm": 0.9179188013076782,
"learning_rate": 4.285914529793391e-05,
"loss": 2.221,
"step": 57
},
{
"epoch": 1.7897782063645131,
"grad_norm": 0.4809790551662445,
"learning_rate": 4.13868452103516e-05,
"loss": 2.3116,
"step": 58
},
{
"epoch": 1.8206364513018323,
"grad_norm": 0.5321066975593567,
"learning_rate": 3.9930417452305626e-05,
"loss": 2.4158,
"step": 59
},
{
"epoch": 1.8514946962391514,
"grad_norm": 0.5725705623626709,
"learning_rate": 3.8491560153412466e-05,
"loss": 2.4831,
"step": 60
},
{
"epoch": 1.8823529411764706,
"grad_norm": 0.6086663007736206,
"learning_rate": 3.707195095691913e-05,
"loss": 2.3898,
"step": 61
},
{
"epoch": 1.9132111861137897,
"grad_norm": 0.706947386264801,
"learning_rate": 3.567324506364632e-05,
"loss": 2.4053,
"step": 62
},
{
"epoch": 1.9440694310511089,
"grad_norm": 0.8199314475059509,
"learning_rate": 3.4297073302098156e-05,
"loss": 2.5932,
"step": 63
},
{
"epoch": 1.974927675988428,
"grad_norm": 1.3784408569335938,
"learning_rate": 3.2945040226989244e-05,
"loss": 2.388,
"step": 64
},
{
"epoch": 2.005785920925747,
"grad_norm": 1.1446154117584229,
"learning_rate": 3.16187222484055e-05,
"loss": 3.6818,
"step": 65
},
{
"epoch": 2.0366441658630667,
"grad_norm": 0.4999466836452484,
"learning_rate": 3.0319665793780648e-05,
"loss": 2.3201,
"step": 66
},
{
"epoch": 2.067502410800386,
"grad_norm": 0.5073311924934387,
"learning_rate": 2.9049385504830985e-05,
"loss": 2.3395,
"step": 67
},
{
"epoch": 2.098360655737705,
"grad_norm": 0.5418161749839783,
"learning_rate": 2.7809362471550748e-05,
"loss": 2.4537,
"step": 68
},
{
"epoch": 2.129218900675024,
"grad_norm": 0.5538686513900757,
"learning_rate": 2.660104250532764e-05,
"loss": 2.3635,
"step": 69
},
{
"epoch": 2.1600771456123433,
"grad_norm": 0.6167834401130676,
"learning_rate": 2.5425834453191232e-05,
"loss": 2.3901,
"step": 70
},
{
"epoch": 2.1909353905496625,
"grad_norm": 0.7404617071151733,
"learning_rate": 2.4285108555160577e-05,
"loss": 2.4675,
"step": 71
},
{
"epoch": 2.2217936354869816,
"grad_norm": 1.0577208995819092,
"learning_rate": 2.3180194846605367e-05,
"loss": 2.4195,
"step": 72
},
{
"epoch": 2.2526518804243008,
"grad_norm": 1.4013382196426392,
"learning_rate": 2.2112381607484417e-05,
"loss": 2.3431,
"step": 73
},
{
"epoch": 2.28351012536162,
"grad_norm": 0.39989662170410156,
"learning_rate": 2.1082913860268765e-05,
"loss": 2.2114,
"step": 74
},
{
"epoch": 2.314368370298939,
"grad_norm": 0.498582124710083,
"learning_rate": 2.0092991918301108e-05,
"loss": 2.4161,
"step": 75
},
{
"epoch": 2.314368370298939,
"eval_loss": 2.399653673171997,
"eval_runtime": 1.0327,
"eval_samples_per_second": 48.418,
"eval_steps_per_second": 12.589,
"step": 75
},
{
"epoch": 2.3452266152362586,
"grad_norm": 0.5155852437019348,
"learning_rate": 1.91437699862843e-05,
"loss": 2.3823,
"step": 76
},
{
"epoch": 2.376084860173578,
"grad_norm": 0.5314053297042847,
"learning_rate": 1.8236354814530112e-05,
"loss": 2.3937,
"step": 77
},
{
"epoch": 2.406943105110897,
"grad_norm": 0.6399489045143127,
"learning_rate": 1.7371804408538024e-05,
"loss": 2.4228,
"step": 78
},
{
"epoch": 2.437801350048216,
"grad_norm": 0.6850634217262268,
"learning_rate": 1.6551126795408016e-05,
"loss": 2.4441,
"step": 79
},
{
"epoch": 2.468659594985535,
"grad_norm": 1.0091044902801514,
"learning_rate": 1.577527884852619e-05,
"loss": 2.3599,
"step": 80
},
{
"epoch": 2.4995178399228544,
"grad_norm": 1.378424882888794,
"learning_rate": 1.5045165171893116e-05,
"loss": 2.1828,
"step": 81
},
{
"epoch": 2.5303760848601735,
"grad_norm": 0.4469667673110962,
"learning_rate": 1.4361637045396029e-05,
"loss": 2.2746,
"step": 82
},
{
"epoch": 2.5612343297974927,
"grad_norm": 0.48588716983795166,
"learning_rate": 1.3725491432254624e-05,
"loss": 2.3452,
"step": 83
},
{
"epoch": 2.592092574734812,
"grad_norm": 0.5537601709365845,
"learning_rate": 1.313747004979751e-05,
"loss": 2.4595,
"step": 84
},
{
"epoch": 2.6229508196721314,
"grad_norm": 0.5473658442497253,
"learning_rate": 1.2598258504653081e-05,
"loss": 2.3284,
"step": 85
},
{
"epoch": 2.65380906460945,
"grad_norm": 0.6774117946624756,
"learning_rate": 1.2108485493362765e-05,
"loss": 2.3467,
"step": 86
},
{
"epoch": 2.6846673095467697,
"grad_norm": 0.7467882633209229,
"learning_rate": 1.1668722069349041e-05,
"loss": 2.4901,
"step": 87
},
{
"epoch": 2.715525554484089,
"grad_norm": 1.0815759897232056,
"learning_rate": 1.1279480977092635e-05,
"loss": 2.3596,
"step": 88
},
{
"epoch": 2.746383799421408,
"grad_norm": 1.4572314023971558,
"learning_rate": 1.094121605429547e-05,
"loss": 2.1992,
"step": 89
},
{
"epoch": 2.777242044358727,
"grad_norm": 0.4223305284976959,
"learning_rate": 1.0654321702726141e-05,
"loss": 2.2878,
"step": 90
},
{
"epoch": 2.8081002892960463,
"grad_norm": 0.48473823070526123,
"learning_rate": 1.0419132428365116e-05,
"loss": 2.3765,
"step": 91
},
{
"epoch": 2.8389585342333654,
"grad_norm": 0.5096808075904846,
"learning_rate": 1.0235922451385733e-05,
"loss": 2.4602,
"step": 92
},
{
"epoch": 2.8698167791706846,
"grad_norm": 0.5460689663887024,
"learning_rate": 1.0104905386425733e-05,
"loss": 2.3527,
"step": 93
},
{
"epoch": 2.9006750241080037,
"grad_norm": 0.6414793133735657,
"learning_rate": 1.002623399352217e-05,
"loss": 2.3315,
"step": 94
},
{
"epoch": 2.931533269045323,
"grad_norm": 0.7416414022445679,
"learning_rate": 1e-05,
"loss": 2.4737,
"step": 95
}
],
"logging_steps": 1,
"max_steps": 95,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": 1.584532913431511e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}