prxy5606's picture
Training in progress, step 200, checkpoint
57092a6 verified
{
"best_metric": 0.0016440377803519368,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.014732965009208104,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 7.366482504604051e-05,
"grad_norm": 0.18368157744407654,
"learning_rate": 1e-05,
"loss": 0.0844,
"step": 1
},
{
"epoch": 7.366482504604051e-05,
"eval_loss": 1.087044596672058,
"eval_runtime": 1793.7992,
"eval_samples_per_second": 12.746,
"eval_steps_per_second": 3.187,
"step": 1
},
{
"epoch": 0.00014732965009208102,
"grad_norm": 0.6049424409866333,
"learning_rate": 2e-05,
"loss": 0.2314,
"step": 2
},
{
"epoch": 0.00022099447513812155,
"grad_norm": 0.5489394664764404,
"learning_rate": 3e-05,
"loss": 0.1586,
"step": 3
},
{
"epoch": 0.00029465930018416205,
"grad_norm": 0.6889164447784424,
"learning_rate": 4e-05,
"loss": 0.2033,
"step": 4
},
{
"epoch": 0.00036832412523020257,
"grad_norm": 0.5421706438064575,
"learning_rate": 5e-05,
"loss": 0.1436,
"step": 5
},
{
"epoch": 0.0004419889502762431,
"grad_norm": 0.49941331148147583,
"learning_rate": 6e-05,
"loss": 0.115,
"step": 6
},
{
"epoch": 0.0005156537753222836,
"grad_norm": 0.3723261058330536,
"learning_rate": 7e-05,
"loss": 0.0823,
"step": 7
},
{
"epoch": 0.0005893186003683241,
"grad_norm": 0.40076112747192383,
"learning_rate": 8e-05,
"loss": 0.0853,
"step": 8
},
{
"epoch": 0.0006629834254143647,
"grad_norm": 0.3061796724796295,
"learning_rate": 9e-05,
"loss": 0.0553,
"step": 9
},
{
"epoch": 0.0007366482504604051,
"grad_norm": 0.23587660491466522,
"learning_rate": 0.0001,
"loss": 0.0277,
"step": 10
},
{
"epoch": 0.0008103130755064457,
"grad_norm": 0.2736630439758301,
"learning_rate": 9.999316524962345e-05,
"loss": 0.0126,
"step": 11
},
{
"epoch": 0.0008839779005524862,
"grad_norm": 0.16042162477970123,
"learning_rate": 9.997266286704631e-05,
"loss": 0.011,
"step": 12
},
{
"epoch": 0.0009576427255985267,
"grad_norm": 0.25331348180770874,
"learning_rate": 9.993849845741524e-05,
"loss": 0.0129,
"step": 13
},
{
"epoch": 0.0010313075506445672,
"grad_norm": 0.7531964182853699,
"learning_rate": 9.989068136093873e-05,
"loss": 0.0208,
"step": 14
},
{
"epoch": 0.0011049723756906078,
"grad_norm": 0.2071554809808731,
"learning_rate": 9.98292246503335e-05,
"loss": 0.0039,
"step": 15
},
{
"epoch": 0.0011786372007366482,
"grad_norm": 0.073692187666893,
"learning_rate": 9.975414512725057e-05,
"loss": 0.0016,
"step": 16
},
{
"epoch": 0.0012523020257826888,
"grad_norm": 0.6084344983100891,
"learning_rate": 9.966546331768191e-05,
"loss": 0.0163,
"step": 17
},
{
"epoch": 0.0013259668508287293,
"grad_norm": 0.08913049101829529,
"learning_rate": 9.956320346634876e-05,
"loss": 0.0015,
"step": 18
},
{
"epoch": 0.0013996316758747697,
"grad_norm": 0.04249788075685501,
"learning_rate": 9.944739353007344e-05,
"loss": 0.0014,
"step": 19
},
{
"epoch": 0.0014732965009208103,
"grad_norm": 0.04118398204445839,
"learning_rate": 9.931806517013612e-05,
"loss": 0.0013,
"step": 20
},
{
"epoch": 0.0015469613259668509,
"grad_norm": 0.10122419148683548,
"learning_rate": 9.917525374361912e-05,
"loss": 0.0005,
"step": 21
},
{
"epoch": 0.0016206261510128914,
"grad_norm": 0.17292018234729767,
"learning_rate": 9.901899829374047e-05,
"loss": 0.0056,
"step": 22
},
{
"epoch": 0.0016942909760589318,
"grad_norm": 0.18053512275218964,
"learning_rate": 9.884934153917997e-05,
"loss": 0.0016,
"step": 23
},
{
"epoch": 0.0017679558011049724,
"grad_norm": 0.22602762281894684,
"learning_rate": 9.86663298624003e-05,
"loss": 0.0018,
"step": 24
},
{
"epoch": 0.001841620626151013,
"grad_norm": 0.016431163996458054,
"learning_rate": 9.847001329696653e-05,
"loss": 0.0004,
"step": 25
},
{
"epoch": 0.0019152854511970533,
"grad_norm": 0.19415265321731567,
"learning_rate": 9.826044551386744e-05,
"loss": 0.0006,
"step": 26
},
{
"epoch": 0.001988950276243094,
"grad_norm": 0.10085350275039673,
"learning_rate": 9.803768380684242e-05,
"loss": 0.0036,
"step": 27
},
{
"epoch": 0.0020626151012891345,
"grad_norm": 0.1329931914806366,
"learning_rate": 9.780178907671789e-05,
"loss": 0.0013,
"step": 28
},
{
"epoch": 0.002136279926335175,
"grad_norm": 0.004965359810739756,
"learning_rate": 9.755282581475769e-05,
"loss": 0.0001,
"step": 29
},
{
"epoch": 0.0022099447513812156,
"grad_norm": 0.09948541969060898,
"learning_rate": 9.729086208503174e-05,
"loss": 0.0017,
"step": 30
},
{
"epoch": 0.002283609576427256,
"grad_norm": 0.2115378975868225,
"learning_rate": 9.701596950580806e-05,
"loss": 0.0011,
"step": 31
},
{
"epoch": 0.0023572744014732964,
"grad_norm": 0.08850453794002533,
"learning_rate": 9.672822322997305e-05,
"loss": 0.0006,
"step": 32
},
{
"epoch": 0.002430939226519337,
"grad_norm": 0.3465259075164795,
"learning_rate": 9.642770192448536e-05,
"loss": 0.0025,
"step": 33
},
{
"epoch": 0.0025046040515653775,
"grad_norm": 0.015224634669721127,
"learning_rate": 9.611448774886924e-05,
"loss": 0.0003,
"step": 34
},
{
"epoch": 0.002578268876611418,
"grad_norm": 0.6286272406578064,
"learning_rate": 9.578866633275288e-05,
"loss": 0.0114,
"step": 35
},
{
"epoch": 0.0026519337016574587,
"grad_norm": 0.9043336510658264,
"learning_rate": 9.545032675245813e-05,
"loss": 0.0109,
"step": 36
},
{
"epoch": 0.002725598526703499,
"grad_norm": 0.012152913957834244,
"learning_rate": 9.509956150664796e-05,
"loss": 0.0001,
"step": 37
},
{
"epoch": 0.0027992633517495394,
"grad_norm": 0.41596049070358276,
"learning_rate": 9.473646649103818e-05,
"loss": 0.0089,
"step": 38
},
{
"epoch": 0.00287292817679558,
"grad_norm": 1.0548653602600098,
"learning_rate": 9.43611409721806e-05,
"loss": 0.0027,
"step": 39
},
{
"epoch": 0.0029465930018416206,
"grad_norm": 0.7401004433631897,
"learning_rate": 9.397368756032445e-05,
"loss": 0.0028,
"step": 40
},
{
"epoch": 0.0030202578268876614,
"grad_norm": 1.7686876058578491,
"learning_rate": 9.357421218136386e-05,
"loss": 0.0153,
"step": 41
},
{
"epoch": 0.0030939226519337017,
"grad_norm": 0.4224011301994324,
"learning_rate": 9.316282404787871e-05,
"loss": 0.0055,
"step": 42
},
{
"epoch": 0.003167587476979742,
"grad_norm": 0.10804013162851334,
"learning_rate": 9.273963562927695e-05,
"loss": 0.0015,
"step": 43
},
{
"epoch": 0.003241252302025783,
"grad_norm": 0.0775923877954483,
"learning_rate": 9.230476262104677e-05,
"loss": 0.0003,
"step": 44
},
{
"epoch": 0.0033149171270718232,
"grad_norm": 0.7671559453010559,
"learning_rate": 9.185832391312644e-05,
"loss": 0.011,
"step": 45
},
{
"epoch": 0.0033885819521178636,
"grad_norm": 0.1762029379606247,
"learning_rate": 9.140044155740101e-05,
"loss": 0.0016,
"step": 46
},
{
"epoch": 0.0034622467771639044,
"grad_norm": 0.015553263016045094,
"learning_rate": 9.093124073433463e-05,
"loss": 0.0004,
"step": 47
},
{
"epoch": 0.0035359116022099448,
"grad_norm": 1.6099673509597778,
"learning_rate": 9.045084971874738e-05,
"loss": 0.0078,
"step": 48
},
{
"epoch": 0.003609576427255985,
"grad_norm": 0.17209604382514954,
"learning_rate": 8.995939984474624e-05,
"loss": 0.0024,
"step": 49
},
{
"epoch": 0.003683241252302026,
"grad_norm": 0.2305936962366104,
"learning_rate": 8.945702546981969e-05,
"loss": 0.0019,
"step": 50
},
{
"epoch": 0.003683241252302026,
"eval_loss": 0.005154376849532127,
"eval_runtime": 1802.9348,
"eval_samples_per_second": 12.682,
"eval_steps_per_second": 3.17,
"step": 50
},
{
"epoch": 0.0037569060773480663,
"grad_norm": 0.14203476905822754,
"learning_rate": 8.894386393810563e-05,
"loss": 0.0496,
"step": 51
},
{
"epoch": 0.0038305709023941066,
"grad_norm": 0.14956742525100708,
"learning_rate": 8.842005554284296e-05,
"loss": 0.0236,
"step": 52
},
{
"epoch": 0.0039042357274401474,
"grad_norm": 0.06372524052858353,
"learning_rate": 8.788574348801675e-05,
"loss": 0.0177,
"step": 53
},
{
"epoch": 0.003977900552486188,
"grad_norm": 0.05046476051211357,
"learning_rate": 8.73410738492077e-05,
"loss": 0.0012,
"step": 54
},
{
"epoch": 0.004051565377532229,
"grad_norm": 0.062402307987213135,
"learning_rate": 8.678619553365659e-05,
"loss": 0.004,
"step": 55
},
{
"epoch": 0.004125230202578269,
"grad_norm": 0.014747344888746738,
"learning_rate": 8.622126023955446e-05,
"loss": 0.0004,
"step": 56
},
{
"epoch": 0.004198895027624309,
"grad_norm": 0.07069471478462219,
"learning_rate": 8.564642241456986e-05,
"loss": 0.0021,
"step": 57
},
{
"epoch": 0.00427255985267035,
"grad_norm": 0.05206258222460747,
"learning_rate": 8.506183921362443e-05,
"loss": 0.0016,
"step": 58
},
{
"epoch": 0.00434622467771639,
"grad_norm": 0.1130603477358818,
"learning_rate": 8.44676704559283e-05,
"loss": 0.0074,
"step": 59
},
{
"epoch": 0.004419889502762431,
"grad_norm": 0.011621471494436264,
"learning_rate": 8.386407858128706e-05,
"loss": 0.0003,
"step": 60
},
{
"epoch": 0.004493554327808472,
"grad_norm": 0.08598984777927399,
"learning_rate": 8.32512286056924e-05,
"loss": 0.0024,
"step": 61
},
{
"epoch": 0.004567219152854512,
"grad_norm": 0.014879305846989155,
"learning_rate": 8.262928807620843e-05,
"loss": 0.0005,
"step": 62
},
{
"epoch": 0.004640883977900552,
"grad_norm": 0.014751851558685303,
"learning_rate": 8.199842702516583e-05,
"loss": 0.0005,
"step": 63
},
{
"epoch": 0.004714548802946593,
"grad_norm": 0.053578369319438934,
"learning_rate": 8.135881792367686e-05,
"loss": 0.0012,
"step": 64
},
{
"epoch": 0.004788213627992633,
"grad_norm": 0.02008475735783577,
"learning_rate": 8.07106356344834e-05,
"loss": 0.0004,
"step": 65
},
{
"epoch": 0.004861878453038674,
"grad_norm": 0.057756297290325165,
"learning_rate": 8.005405736415126e-05,
"loss": 0.0006,
"step": 66
},
{
"epoch": 0.004935543278084715,
"grad_norm": 0.02606124058365822,
"learning_rate": 7.938926261462366e-05,
"loss": 0.0004,
"step": 67
},
{
"epoch": 0.005009208103130755,
"grad_norm": 0.014606554992496967,
"learning_rate": 7.871643313414718e-05,
"loss": 0.0003,
"step": 68
},
{
"epoch": 0.005082872928176795,
"grad_norm": 0.03155618533492088,
"learning_rate": 7.803575286758364e-05,
"loss": 0.0005,
"step": 69
},
{
"epoch": 0.005156537753222836,
"grad_norm": 0.021368781104683876,
"learning_rate": 7.734740790612136e-05,
"loss": 0.0004,
"step": 70
},
{
"epoch": 0.005230202578268877,
"grad_norm": 0.02990240976214409,
"learning_rate": 7.66515864363997e-05,
"loss": 0.0008,
"step": 71
},
{
"epoch": 0.005303867403314917,
"grad_norm": 0.006831527221947908,
"learning_rate": 7.594847868906076e-05,
"loss": 0.0003,
"step": 72
},
{
"epoch": 0.005377532228360958,
"grad_norm": 0.012739215977489948,
"learning_rate": 7.52382768867422e-05,
"loss": 0.0002,
"step": 73
},
{
"epoch": 0.005451197053406998,
"grad_norm": 0.00279725668951869,
"learning_rate": 7.452117519152542e-05,
"loss": 0.0001,
"step": 74
},
{
"epoch": 0.0055248618784530384,
"grad_norm": 0.02894754707813263,
"learning_rate": 7.379736965185368e-05,
"loss": 0.0005,
"step": 75
},
{
"epoch": 0.005598526703499079,
"grad_norm": 0.022462375462055206,
"learning_rate": 7.30670581489344e-05,
"loss": 0.0003,
"step": 76
},
{
"epoch": 0.00567219152854512,
"grad_norm": 0.021344490349292755,
"learning_rate": 7.233044034264034e-05,
"loss": 0.0005,
"step": 77
},
{
"epoch": 0.00574585635359116,
"grad_norm": 0.03600762411952019,
"learning_rate": 7.158771761692464e-05,
"loss": 0.0005,
"step": 78
},
{
"epoch": 0.005819521178637201,
"grad_norm": 0.01306220330297947,
"learning_rate": 7.083909302476453e-05,
"loss": 0.0002,
"step": 79
},
{
"epoch": 0.005893186003683241,
"grad_norm": 0.0199806559830904,
"learning_rate": 7.008477123264848e-05,
"loss": 0.0002,
"step": 80
},
{
"epoch": 0.0059668508287292815,
"grad_norm": 0.008712571114301682,
"learning_rate": 6.932495846462261e-05,
"loss": 0.0002,
"step": 81
},
{
"epoch": 0.006040515653775323,
"grad_norm": 0.0022454585414379835,
"learning_rate": 6.855986244591104e-05,
"loss": 0.0001,
"step": 82
},
{
"epoch": 0.006114180478821363,
"grad_norm": 0.0017042462714016438,
"learning_rate": 6.778969234612584e-05,
"loss": 0.0001,
"step": 83
},
{
"epoch": 0.0061878453038674034,
"grad_norm": 0.007450164295732975,
"learning_rate": 6.701465872208216e-05,
"loss": 0.0002,
"step": 84
},
{
"epoch": 0.006261510128913444,
"grad_norm": 0.00840887799859047,
"learning_rate": 6.623497346023418e-05,
"loss": 0.0002,
"step": 85
},
{
"epoch": 0.006335174953959484,
"grad_norm": 0.02648269385099411,
"learning_rate": 6.545084971874738e-05,
"loss": 0.0003,
"step": 86
},
{
"epoch": 0.0064088397790055245,
"grad_norm": 0.002491602674126625,
"learning_rate": 6.466250186922325e-05,
"loss": 0.0001,
"step": 87
},
{
"epoch": 0.006482504604051566,
"grad_norm": 0.006651001516729593,
"learning_rate": 6.387014543809223e-05,
"loss": 0.0002,
"step": 88
},
{
"epoch": 0.006556169429097606,
"grad_norm": 0.006767287850379944,
"learning_rate": 6.307399704769099e-05,
"loss": 0.0002,
"step": 89
},
{
"epoch": 0.0066298342541436465,
"grad_norm": 0.0055321455001831055,
"learning_rate": 6.227427435703997e-05,
"loss": 0.0001,
"step": 90
},
{
"epoch": 0.006703499079189687,
"grad_norm": 0.19037975370883942,
"learning_rate": 6.147119600233758e-05,
"loss": 0.0013,
"step": 91
},
{
"epoch": 0.006777163904235727,
"grad_norm": 0.098416768014431,
"learning_rate": 6.066498153718735e-05,
"loss": 0.0008,
"step": 92
},
{
"epoch": 0.006850828729281768,
"grad_norm": 0.5576754212379456,
"learning_rate": 5.985585137257401e-05,
"loss": 0.0123,
"step": 93
},
{
"epoch": 0.006924493554327809,
"grad_norm": 0.21522895991802216,
"learning_rate": 5.90440267166055e-05,
"loss": 0.0022,
"step": 94
},
{
"epoch": 0.006998158379373849,
"grad_norm": 0.09357759356498718,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.0006,
"step": 95
},
{
"epoch": 0.0070718232044198895,
"grad_norm": 0.004402390215545893,
"learning_rate": 5.74131823855921e-05,
"loss": 0.0001,
"step": 96
},
{
"epoch": 0.00714548802946593,
"grad_norm": 0.04337269440293312,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.0007,
"step": 97
},
{
"epoch": 0.00721915285451197,
"grad_norm": 0.0028723084833472967,
"learning_rate": 5.577423184847932e-05,
"loss": 0.0001,
"step": 98
},
{
"epoch": 0.0072928176795580115,
"grad_norm": 0.009090679697692394,
"learning_rate": 5.495227651252315e-05,
"loss": 0.0002,
"step": 99
},
{
"epoch": 0.007366482504604052,
"grad_norm": 0.008667516522109509,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.0002,
"step": 100
},
{
"epoch": 0.007366482504604052,
"eval_loss": 0.0033941082656383514,
"eval_runtime": 1802.122,
"eval_samples_per_second": 12.687,
"eval_steps_per_second": 3.172,
"step": 100
},
{
"epoch": 0.007440147329650092,
"grad_norm": 0.11829923838376999,
"learning_rate": 5.330452921628497e-05,
"loss": 0.0247,
"step": 101
},
{
"epoch": 0.0075138121546961326,
"grad_norm": 0.2091480791568756,
"learning_rate": 5.247918773366112e-05,
"loss": 0.0088,
"step": 102
},
{
"epoch": 0.007587476979742173,
"grad_norm": 0.1110382229089737,
"learning_rate": 5.165316846586541e-05,
"loss": 0.0021,
"step": 103
},
{
"epoch": 0.007661141804788213,
"grad_norm": 0.012496083974838257,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.0001,
"step": 104
},
{
"epoch": 0.0077348066298342545,
"grad_norm": 0.0018954469123855233,
"learning_rate": 5e-05,
"loss": 0.0001,
"step": 105
},
{
"epoch": 0.007808471454880295,
"grad_norm": 0.09856453537940979,
"learning_rate": 4.917330276168208e-05,
"loss": 0.0011,
"step": 106
},
{
"epoch": 0.007882136279926335,
"grad_norm": 0.05144748464226723,
"learning_rate": 4.834683153413459e-05,
"loss": 0.0006,
"step": 107
},
{
"epoch": 0.007955801104972376,
"grad_norm": 0.023395325988531113,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.0002,
"step": 108
},
{
"epoch": 0.008029465930018416,
"grad_norm": 0.007794566918164492,
"learning_rate": 4.669547078371504e-05,
"loss": 0.0002,
"step": 109
},
{
"epoch": 0.008103130755064457,
"grad_norm": 0.19280481338500977,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.002,
"step": 110
},
{
"epoch": 0.008176795580110497,
"grad_norm": 0.10028093308210373,
"learning_rate": 4.504772348747687e-05,
"loss": 0.0016,
"step": 111
},
{
"epoch": 0.008250460405156538,
"grad_norm": 0.00195652456022799,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.0001,
"step": 112
},
{
"epoch": 0.008324125230202577,
"grad_norm": 0.03706127777695656,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.0005,
"step": 113
},
{
"epoch": 0.008397790055248619,
"grad_norm": 0.05740731209516525,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.0006,
"step": 114
},
{
"epoch": 0.00847145488029466,
"grad_norm": 0.014088164083659649,
"learning_rate": 4.17702704859633e-05,
"loss": 0.0002,
"step": 115
},
{
"epoch": 0.0085451197053407,
"grad_norm": 0.012177246622741222,
"learning_rate": 4.095597328339452e-05,
"loss": 0.0002,
"step": 116
},
{
"epoch": 0.00861878453038674,
"grad_norm": 0.02699141949415207,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.0004,
"step": 117
},
{
"epoch": 0.00869244935543278,
"grad_norm": 0.111921526491642,
"learning_rate": 3.933501846281267e-05,
"loss": 0.0016,
"step": 118
},
{
"epoch": 0.008766114180478821,
"grad_norm": 0.003571714274585247,
"learning_rate": 3.852880399766243e-05,
"loss": 0.0001,
"step": 119
},
{
"epoch": 0.008839779005524863,
"grad_norm": 0.002393726957961917,
"learning_rate": 3.772572564296005e-05,
"loss": 0.0001,
"step": 120
},
{
"epoch": 0.008913443830570902,
"grad_norm": 0.04804624989628792,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.0004,
"step": 121
},
{
"epoch": 0.008987108655616943,
"grad_norm": 0.010899403132498264,
"learning_rate": 3.612985456190778e-05,
"loss": 0.0002,
"step": 122
},
{
"epoch": 0.009060773480662983,
"grad_norm": 0.1602235734462738,
"learning_rate": 3.533749813077677e-05,
"loss": 0.003,
"step": 123
},
{
"epoch": 0.009134438305709024,
"grad_norm": 0.017247473821043968,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.0003,
"step": 124
},
{
"epoch": 0.009208103130755065,
"grad_norm": 0.05777062848210335,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.0003,
"step": 125
},
{
"epoch": 0.009281767955801105,
"grad_norm": 0.0014383806847035885,
"learning_rate": 3.298534127791785e-05,
"loss": 0.0001,
"step": 126
},
{
"epoch": 0.009355432780847146,
"grad_norm": 0.10282876342535019,
"learning_rate": 3.221030765387417e-05,
"loss": 0.0017,
"step": 127
},
{
"epoch": 0.009429097605893185,
"grad_norm": 0.002600087784230709,
"learning_rate": 3.144013755408895e-05,
"loss": 0.0,
"step": 128
},
{
"epoch": 0.009502762430939227,
"grad_norm": 0.1263400763273239,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.0038,
"step": 129
},
{
"epoch": 0.009576427255985266,
"grad_norm": 0.10259674489498138,
"learning_rate": 2.991522876735154e-05,
"loss": 0.0012,
"step": 130
},
{
"epoch": 0.009650092081031307,
"grad_norm": 0.0640677884221077,
"learning_rate": 2.916090697523549e-05,
"loss": 0.0022,
"step": 131
},
{
"epoch": 0.009723756906077349,
"grad_norm": 0.0023545536678284407,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.0001,
"step": 132
},
{
"epoch": 0.009797421731123388,
"grad_norm": 0.0071535371243953705,
"learning_rate": 2.766955965735968e-05,
"loss": 0.0002,
"step": 133
},
{
"epoch": 0.00987108655616943,
"grad_norm": 0.03181946277618408,
"learning_rate": 2.693294185106562e-05,
"loss": 0.0003,
"step": 134
},
{
"epoch": 0.009944751381215469,
"grad_norm": 0.010810406878590584,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.0002,
"step": 135
},
{
"epoch": 0.01001841620626151,
"grad_norm": 0.12009802460670471,
"learning_rate": 2.547882480847461e-05,
"loss": 0.0042,
"step": 136
},
{
"epoch": 0.010092081031307551,
"grad_norm": 0.14293478429317474,
"learning_rate": 2.476172311325783e-05,
"loss": 0.0107,
"step": 137
},
{
"epoch": 0.01016574585635359,
"grad_norm": 0.035140279680490494,
"learning_rate": 2.405152131093926e-05,
"loss": 0.0004,
"step": 138
},
{
"epoch": 0.010239410681399632,
"grad_norm": 0.0029654952231794596,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.0001,
"step": 139
},
{
"epoch": 0.010313075506445672,
"grad_norm": 0.0072612278163433075,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.0002,
"step": 140
},
{
"epoch": 0.010386740331491713,
"grad_norm": 0.0034849776420742273,
"learning_rate": 2.196424713241637e-05,
"loss": 0.0001,
"step": 141
},
{
"epoch": 0.010460405156537754,
"grad_norm": 0.007106333505362272,
"learning_rate": 2.128356686585282e-05,
"loss": 0.0001,
"step": 142
},
{
"epoch": 0.010534069981583793,
"grad_norm": 0.014908818528056145,
"learning_rate": 2.061073738537635e-05,
"loss": 0.0003,
"step": 143
},
{
"epoch": 0.010607734806629835,
"grad_norm": 0.3296809792518616,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.0043,
"step": 144
},
{
"epoch": 0.010681399631675874,
"grad_norm": 0.01654644124209881,
"learning_rate": 1.928936436551661e-05,
"loss": 0.0004,
"step": 145
},
{
"epoch": 0.010755064456721915,
"grad_norm": 0.8910931348800659,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.0156,
"step": 146
},
{
"epoch": 0.010828729281767955,
"grad_norm": 0.0547972172498703,
"learning_rate": 1.800157297483417e-05,
"loss": 0.001,
"step": 147
},
{
"epoch": 0.010902394106813996,
"grad_norm": 0.00392822315916419,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.0001,
"step": 148
},
{
"epoch": 0.010976058931860037,
"grad_norm": 0.0017114396905526519,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.0001,
"step": 149
},
{
"epoch": 0.011049723756906077,
"grad_norm": 0.19709661602973938,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.0023,
"step": 150
},
{
"epoch": 0.011049723756906077,
"eval_loss": 0.0017171857180073857,
"eval_runtime": 1804.6367,
"eval_samples_per_second": 12.67,
"eval_steps_per_second": 3.167,
"step": 150
},
{
"epoch": 0.011123388581952118,
"grad_norm": 0.13535618782043457,
"learning_rate": 1.553232954407171e-05,
"loss": 0.0359,
"step": 151
},
{
"epoch": 0.011197053406998158,
"grad_norm": 0.07493212074041367,
"learning_rate": 1.4938160786375572e-05,
"loss": 0.0031,
"step": 152
},
{
"epoch": 0.011270718232044199,
"grad_norm": 0.014278370887041092,
"learning_rate": 1.435357758543015e-05,
"loss": 0.0002,
"step": 153
},
{
"epoch": 0.01134438305709024,
"grad_norm": 0.007056003902107477,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.0002,
"step": 154
},
{
"epoch": 0.01141804788213628,
"grad_norm": 0.02154668979346752,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.0005,
"step": 155
},
{
"epoch": 0.01149171270718232,
"grad_norm": 0.0009774231584742665,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.0,
"step": 156
},
{
"epoch": 0.01156537753222836,
"grad_norm": 0.012745398096740246,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.0002,
"step": 157
},
{
"epoch": 0.011639042357274402,
"grad_norm": 0.1661229431629181,
"learning_rate": 1.157994445715706e-05,
"loss": 0.007,
"step": 158
},
{
"epoch": 0.011712707182320443,
"grad_norm": 0.02389194257557392,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.0001,
"step": 159
},
{
"epoch": 0.011786372007366482,
"grad_norm": 0.04091808199882507,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.0002,
"step": 160
},
{
"epoch": 0.011860036832412523,
"grad_norm": 0.006261663045734167,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.0001,
"step": 161
},
{
"epoch": 0.011933701657458563,
"grad_norm": 0.05155990645289421,
"learning_rate": 9.549150281252633e-06,
"loss": 0.0006,
"step": 162
},
{
"epoch": 0.012007366482504604,
"grad_norm": 0.01671556383371353,
"learning_rate": 9.068759265665384e-06,
"loss": 0.0003,
"step": 163
},
{
"epoch": 0.012081031307550645,
"grad_norm": 0.006735862698405981,
"learning_rate": 8.599558442598998e-06,
"loss": 0.0001,
"step": 164
},
{
"epoch": 0.012154696132596685,
"grad_norm": 0.01708943583071232,
"learning_rate": 8.141676086873572e-06,
"loss": 0.0003,
"step": 165
},
{
"epoch": 0.012228360957642726,
"grad_norm": 0.055670272558927536,
"learning_rate": 7.695237378953223e-06,
"loss": 0.0005,
"step": 166
},
{
"epoch": 0.012302025782688766,
"grad_norm": 0.06127498671412468,
"learning_rate": 7.260364370723044e-06,
"loss": 0.0018,
"step": 167
},
{
"epoch": 0.012375690607734807,
"grad_norm": 0.00878976471722126,
"learning_rate": 6.837175952121306e-06,
"loss": 0.0001,
"step": 168
},
{
"epoch": 0.012449355432780846,
"grad_norm": 0.02192527800798416,
"learning_rate": 6.425787818636131e-06,
"loss": 0.0004,
"step": 169
},
{
"epoch": 0.012523020257826888,
"grad_norm": 0.013975542970001698,
"learning_rate": 6.026312439675552e-06,
"loss": 0.0001,
"step": 170
},
{
"epoch": 0.012596685082872929,
"grad_norm": 0.011623718775808811,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.0002,
"step": 171
},
{
"epoch": 0.012670349907918968,
"grad_norm": 0.0031957433093339205,
"learning_rate": 5.263533508961827e-06,
"loss": 0.0001,
"step": 172
},
{
"epoch": 0.01274401473296501,
"grad_norm": 0.00475406413897872,
"learning_rate": 4.900438493352055e-06,
"loss": 0.0001,
"step": 173
},
{
"epoch": 0.012817679558011049,
"grad_norm": 0.004182871431112289,
"learning_rate": 4.549673247541875e-06,
"loss": 0.0001,
"step": 174
},
{
"epoch": 0.01289134438305709,
"grad_norm": 0.14371535181999207,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.0012,
"step": 175
},
{
"epoch": 0.012965009208103132,
"grad_norm": 0.009259273298084736,
"learning_rate": 3.885512251130763e-06,
"loss": 0.0002,
"step": 176
},
{
"epoch": 0.013038674033149171,
"grad_norm": 0.0022057625465095043,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.0001,
"step": 177
},
{
"epoch": 0.013112338858195212,
"grad_norm": 0.0032077066134661436,
"learning_rate": 3.271776770026963e-06,
"loss": 0.0001,
"step": 178
},
{
"epoch": 0.013186003683241252,
"grad_norm": 0.0103165153414011,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.0001,
"step": 179
},
{
"epoch": 0.013259668508287293,
"grad_norm": 0.03156290948390961,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.0004,
"step": 180
},
{
"epoch": 0.013333333333333334,
"grad_norm": 0.00353939994238317,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.0001,
"step": 181
},
{
"epoch": 0.013406998158379374,
"grad_norm": 0.10992857068777084,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.0065,
"step": 182
},
{
"epoch": 0.013480662983425415,
"grad_norm": 0.02945050224661827,
"learning_rate": 1.962316193157593e-06,
"loss": 0.0003,
"step": 183
},
{
"epoch": 0.013554327808471454,
"grad_norm": 0.019432615488767624,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.0005,
"step": 184
},
{
"epoch": 0.013627992633517496,
"grad_norm": 0.2162013202905655,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.0017,
"step": 185
},
{
"epoch": 0.013701657458563535,
"grad_norm": 0.010258818045258522,
"learning_rate": 1.333670137599713e-06,
"loss": 0.0001,
"step": 186
},
{
"epoch": 0.013775322283609576,
"grad_norm": 0.0015229276614263654,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.0001,
"step": 187
},
{
"epoch": 0.013848987108655618,
"grad_norm": 0.008272695355117321,
"learning_rate": 9.810017062595322e-07,
"loss": 0.0001,
"step": 188
},
{
"epoch": 0.013922651933701657,
"grad_norm": 0.008334990590810776,
"learning_rate": 8.247462563808817e-07,
"loss": 0.0002,
"step": 189
},
{
"epoch": 0.013996316758747698,
"grad_norm": 0.04099377989768982,
"learning_rate": 6.819348298638839e-07,
"loss": 0.0004,
"step": 190
},
{
"epoch": 0.014069981583793738,
"grad_norm": 0.01831510290503502,
"learning_rate": 5.526064699265753e-07,
"loss": 0.0001,
"step": 191
},
{
"epoch": 0.014143646408839779,
"grad_norm": 0.28331729769706726,
"learning_rate": 4.367965336512403e-07,
"loss": 0.0048,
"step": 192
},
{
"epoch": 0.01421731123388582,
"grad_norm": 0.001715951133519411,
"learning_rate": 3.3453668231809286e-07,
"loss": 0.0001,
"step": 193
},
{
"epoch": 0.01429097605893186,
"grad_norm": 0.14312292635440826,
"learning_rate": 2.458548727494292e-07,
"loss": 0.0014,
"step": 194
},
{
"epoch": 0.014364640883977901,
"grad_norm": 0.0035134998615831137,
"learning_rate": 1.7077534966650766e-07,
"loss": 0.0001,
"step": 195
},
{
"epoch": 0.01443830570902394,
"grad_norm": 0.02167433314025402,
"learning_rate": 1.0931863906127327e-07,
"loss": 0.0001,
"step": 196
},
{
"epoch": 0.014511970534069982,
"grad_norm": 0.2886894643306732,
"learning_rate": 6.150154258476315e-08,
"loss": 0.0169,
"step": 197
},
{
"epoch": 0.014585635359116023,
"grad_norm": 0.025198718532919884,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.0004,
"step": 198
},
{
"epoch": 0.014659300184162062,
"grad_norm": 0.027238836511969566,
"learning_rate": 6.834750376549792e-09,
"loss": 0.0005,
"step": 199
},
{
"epoch": 0.014732965009208104,
"grad_norm": 1.0381667613983154,
"learning_rate": 0.0,
"loss": 0.0336,
"step": 200
},
{
"epoch": 0.014732965009208104,
"eval_loss": 0.0016440377803519368,
"eval_runtime": 1802.4102,
"eval_samples_per_second": 12.685,
"eval_steps_per_second": 3.171,
"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": 3.141479527738245e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}