prxy5608's picture
Training in progress, step 200, checkpoint
140bbcb verified
{
"best_metric": 0.4362151622772217,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 0.026974172230089688,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00013487086115044844,
"grad_norm": 3.952620267868042,
"learning_rate": 1e-05,
"loss": 1.9551,
"step": 1
},
{
"epoch": 0.00013487086115044844,
"eval_loss": 1.305298089981079,
"eval_runtime": 248.7178,
"eval_samples_per_second": 50.21,
"eval_steps_per_second": 12.552,
"step": 1
},
{
"epoch": 0.0002697417223008969,
"grad_norm": 3.8131320476531982,
"learning_rate": 2e-05,
"loss": 1.9808,
"step": 2
},
{
"epoch": 0.00040461258345134534,
"grad_norm": 3.614694356918335,
"learning_rate": 3e-05,
"loss": 2.0204,
"step": 3
},
{
"epoch": 0.0005394834446017937,
"grad_norm": 3.1372880935668945,
"learning_rate": 4e-05,
"loss": 1.9614,
"step": 4
},
{
"epoch": 0.0006743543057522423,
"grad_norm": 2.398766040802002,
"learning_rate": 5e-05,
"loss": 1.836,
"step": 5
},
{
"epoch": 0.0008092251669026907,
"grad_norm": 2.0184972286224365,
"learning_rate": 6e-05,
"loss": 1.6477,
"step": 6
},
{
"epoch": 0.0009440960280531391,
"grad_norm": 1.7531442642211914,
"learning_rate": 7e-05,
"loss": 1.1582,
"step": 7
},
{
"epoch": 0.0010789668892035875,
"grad_norm": 3.4769623279571533,
"learning_rate": 8e-05,
"loss": 0.4955,
"step": 8
},
{
"epoch": 0.001213837750354036,
"grad_norm": 1.5210298299789429,
"learning_rate": 9e-05,
"loss": 0.509,
"step": 9
},
{
"epoch": 0.0013487086115044845,
"grad_norm": 1.6111201047897339,
"learning_rate": 0.0001,
"loss": 0.4188,
"step": 10
},
{
"epoch": 0.0014835794726549328,
"grad_norm": 1.0375179052352905,
"learning_rate": 9.999316524962345e-05,
"loss": 0.2827,
"step": 11
},
{
"epoch": 0.0016184503338053813,
"grad_norm": 1.1786742210388184,
"learning_rate": 9.997266286704631e-05,
"loss": 0.1066,
"step": 12
},
{
"epoch": 0.0017533211949558299,
"grad_norm": 0.7050691246986389,
"learning_rate": 9.993849845741524e-05,
"loss": 0.1385,
"step": 13
},
{
"epoch": 0.0018881920561062782,
"grad_norm": 0.6430811285972595,
"learning_rate": 9.989068136093873e-05,
"loss": 0.1221,
"step": 14
},
{
"epoch": 0.0020230629172567267,
"grad_norm": 0.7282156348228455,
"learning_rate": 9.98292246503335e-05,
"loss": 0.184,
"step": 15
},
{
"epoch": 0.002157933778407175,
"grad_norm": 2.0262136459350586,
"learning_rate": 9.975414512725057e-05,
"loss": 0.1277,
"step": 16
},
{
"epoch": 0.0022928046395576237,
"grad_norm": 1.4118305444717407,
"learning_rate": 9.966546331768191e-05,
"loss": 0.1338,
"step": 17
},
{
"epoch": 0.002427675500708072,
"grad_norm": 0.29893508553504944,
"learning_rate": 9.956320346634876e-05,
"loss": 0.0457,
"step": 18
},
{
"epoch": 0.0025625463618585203,
"grad_norm": 0.6465992331504822,
"learning_rate": 9.944739353007344e-05,
"loss": 0.0588,
"step": 19
},
{
"epoch": 0.002697417223008969,
"grad_norm": 0.5745024085044861,
"learning_rate": 9.931806517013612e-05,
"loss": 0.0618,
"step": 20
},
{
"epoch": 0.0028322880841594174,
"grad_norm": 0.42711976170539856,
"learning_rate": 9.917525374361912e-05,
"loss": 0.1204,
"step": 21
},
{
"epoch": 0.0029671589453098657,
"grad_norm": 0.35799774527549744,
"learning_rate": 9.901899829374047e-05,
"loss": 0.0552,
"step": 22
},
{
"epoch": 0.0031020298064603144,
"grad_norm": 0.23321257531642914,
"learning_rate": 9.884934153917997e-05,
"loss": 0.0522,
"step": 23
},
{
"epoch": 0.0032369006676107627,
"grad_norm": 0.5112372040748596,
"learning_rate": 9.86663298624003e-05,
"loss": 0.0547,
"step": 24
},
{
"epoch": 0.003371771528761211,
"grad_norm": 0.4961523413658142,
"learning_rate": 9.847001329696653e-05,
"loss": 0.0648,
"step": 25
},
{
"epoch": 0.0035066423899116597,
"grad_norm": 0.25381654500961304,
"learning_rate": 9.826044551386744e-05,
"loss": 0.0463,
"step": 26
},
{
"epoch": 0.003641513251062108,
"grad_norm": 0.3249934911727905,
"learning_rate": 9.803768380684242e-05,
"loss": 0.0477,
"step": 27
},
{
"epoch": 0.0037763841122125563,
"grad_norm": 0.5097329020500183,
"learning_rate": 9.780178907671789e-05,
"loss": 0.0637,
"step": 28
},
{
"epoch": 0.003911254973363005,
"grad_norm": 0.5418552756309509,
"learning_rate": 9.755282581475769e-05,
"loss": 0.0715,
"step": 29
},
{
"epoch": 0.004046125834513453,
"grad_norm": 0.27045565843582153,
"learning_rate": 9.729086208503174e-05,
"loss": 0.046,
"step": 30
},
{
"epoch": 0.004180996695663902,
"grad_norm": 0.28286728262901306,
"learning_rate": 9.701596950580806e-05,
"loss": 0.0478,
"step": 31
},
{
"epoch": 0.00431586755681435,
"grad_norm": 0.3227049708366394,
"learning_rate": 9.672822322997305e-05,
"loss": 0.0465,
"step": 32
},
{
"epoch": 0.004450738417964798,
"grad_norm": 0.15957967936992645,
"learning_rate": 9.642770192448536e-05,
"loss": 0.0495,
"step": 33
},
{
"epoch": 0.0045856092791152474,
"grad_norm": 0.15069830417633057,
"learning_rate": 9.611448774886924e-05,
"loss": 0.0447,
"step": 34
},
{
"epoch": 0.004720480140265696,
"grad_norm": 0.11230260878801346,
"learning_rate": 9.578866633275288e-05,
"loss": 0.0422,
"step": 35
},
{
"epoch": 0.004855351001416144,
"grad_norm": 0.23992353677749634,
"learning_rate": 9.545032675245813e-05,
"loss": 0.0536,
"step": 36
},
{
"epoch": 0.004990221862566592,
"grad_norm": 3.2765743732452393,
"learning_rate": 9.509956150664796e-05,
"loss": 0.6955,
"step": 37
},
{
"epoch": 0.005125092723717041,
"grad_norm": 6.307303428649902,
"learning_rate": 9.473646649103818e-05,
"loss": 1.4932,
"step": 38
},
{
"epoch": 0.005259963584867489,
"grad_norm": 4.192469120025635,
"learning_rate": 9.43611409721806e-05,
"loss": 1.2673,
"step": 39
},
{
"epoch": 0.005394834446017938,
"grad_norm": 1.417549967765808,
"learning_rate": 9.397368756032445e-05,
"loss": 1.2006,
"step": 40
},
{
"epoch": 0.005529705307168386,
"grad_norm": 1.5354728698730469,
"learning_rate": 9.357421218136386e-05,
"loss": 1.2097,
"step": 41
},
{
"epoch": 0.005664576168318835,
"grad_norm": 0.8183015584945679,
"learning_rate": 9.316282404787871e-05,
"loss": 1.1678,
"step": 42
},
{
"epoch": 0.005799447029469283,
"grad_norm": 0.8261300921440125,
"learning_rate": 9.273963562927695e-05,
"loss": 1.1522,
"step": 43
},
{
"epoch": 0.005934317890619731,
"grad_norm": 0.8683955669403076,
"learning_rate": 9.230476262104677e-05,
"loss": 1.1262,
"step": 44
},
{
"epoch": 0.00606918875177018,
"grad_norm": 0.7765291929244995,
"learning_rate": 9.185832391312644e-05,
"loss": 1.0977,
"step": 45
},
{
"epoch": 0.006204059612920629,
"grad_norm": 0.9712295532226562,
"learning_rate": 9.140044155740101e-05,
"loss": 1.1303,
"step": 46
},
{
"epoch": 0.006338930474071077,
"grad_norm": 1.1252740621566772,
"learning_rate": 9.093124073433463e-05,
"loss": 1.1203,
"step": 47
},
{
"epoch": 0.006473801335221525,
"grad_norm": 0.9857378602027893,
"learning_rate": 9.045084971874738e-05,
"loss": 1.0839,
"step": 48
},
{
"epoch": 0.006608672196371974,
"grad_norm": 0.9927234649658203,
"learning_rate": 8.995939984474624e-05,
"loss": 1.0828,
"step": 49
},
{
"epoch": 0.006743543057522422,
"grad_norm": 1.4275062084197998,
"learning_rate": 8.945702546981969e-05,
"loss": 1.0701,
"step": 50
},
{
"epoch": 0.006743543057522422,
"eval_loss": 0.5367962121963501,
"eval_runtime": 249.3026,
"eval_samples_per_second": 50.092,
"eval_steps_per_second": 12.523,
"step": 50
},
{
"epoch": 0.00687841391867287,
"grad_norm": 4.181732177734375,
"learning_rate": 8.894386393810563e-05,
"loss": 1.4594,
"step": 51
},
{
"epoch": 0.0070132847798233195,
"grad_norm": 3.3127622604370117,
"learning_rate": 8.842005554284296e-05,
"loss": 1.4116,
"step": 52
},
{
"epoch": 0.007148155640973768,
"grad_norm": 2.0005574226379395,
"learning_rate": 8.788574348801675e-05,
"loss": 1.2912,
"step": 53
},
{
"epoch": 0.007283026502124216,
"grad_norm": 1.5402761697769165,
"learning_rate": 8.73410738492077e-05,
"loss": 1.2334,
"step": 54
},
{
"epoch": 0.007417897363274664,
"grad_norm": 0.7755981683731079,
"learning_rate": 8.678619553365659e-05,
"loss": 1.0904,
"step": 55
},
{
"epoch": 0.007552768224425113,
"grad_norm": 0.6753297448158264,
"learning_rate": 8.622126023955446e-05,
"loss": 0.9433,
"step": 56
},
{
"epoch": 0.007687639085575561,
"grad_norm": 0.529584527015686,
"learning_rate": 8.564642241456986e-05,
"loss": 0.2841,
"step": 57
},
{
"epoch": 0.00782250994672601,
"grad_norm": 0.33971166610717773,
"learning_rate": 8.506183921362443e-05,
"loss": 0.214,
"step": 58
},
{
"epoch": 0.007957380807876458,
"grad_norm": 0.3845877945423126,
"learning_rate": 8.44676704559283e-05,
"loss": 0.219,
"step": 59
},
{
"epoch": 0.008092251669026907,
"grad_norm": 0.22050003707408905,
"learning_rate": 8.386407858128706e-05,
"loss": 0.1005,
"step": 60
},
{
"epoch": 0.008227122530177355,
"grad_norm": 0.2131161093711853,
"learning_rate": 8.32512286056924e-05,
"loss": 0.0995,
"step": 61
},
{
"epoch": 0.008361993391327803,
"grad_norm": 0.1473701298236847,
"learning_rate": 8.262928807620843e-05,
"loss": 0.0435,
"step": 62
},
{
"epoch": 0.008496864252478252,
"grad_norm": 0.2677707076072693,
"learning_rate": 8.199842702516583e-05,
"loss": 0.054,
"step": 63
},
{
"epoch": 0.0086317351136287,
"grad_norm": 0.22308439016342163,
"learning_rate": 8.135881792367686e-05,
"loss": 0.1021,
"step": 64
},
{
"epoch": 0.008766605974779148,
"grad_norm": 0.33880776166915894,
"learning_rate": 8.07106356344834e-05,
"loss": 0.1548,
"step": 65
},
{
"epoch": 0.008901476835929597,
"grad_norm": 0.18450771272182465,
"learning_rate": 8.005405736415126e-05,
"loss": 0.0448,
"step": 66
},
{
"epoch": 0.009036347697080047,
"grad_norm": 0.20539778470993042,
"learning_rate": 7.938926261462366e-05,
"loss": 0.0963,
"step": 67
},
{
"epoch": 0.009171218558230495,
"grad_norm": 0.23271337151527405,
"learning_rate": 7.871643313414718e-05,
"loss": 0.1025,
"step": 68
},
{
"epoch": 0.009306089419380943,
"grad_norm": 0.23447385430335999,
"learning_rate": 7.803575286758364e-05,
"loss": 0.1049,
"step": 69
},
{
"epoch": 0.009440960280531391,
"grad_norm": 0.14262907207012177,
"learning_rate": 7.734740790612136e-05,
"loss": 0.0497,
"step": 70
},
{
"epoch": 0.00957583114168184,
"grad_norm": 0.10921374708414078,
"learning_rate": 7.66515864363997e-05,
"loss": 0.0474,
"step": 71
},
{
"epoch": 0.009710702002832288,
"grad_norm": 0.14240165054798126,
"learning_rate": 7.594847868906076e-05,
"loss": 0.0456,
"step": 72
},
{
"epoch": 0.009845572863982736,
"grad_norm": 0.23817573487758636,
"learning_rate": 7.52382768867422e-05,
"loss": 0.0465,
"step": 73
},
{
"epoch": 0.009980443725133185,
"grad_norm": 0.13582269847393036,
"learning_rate": 7.452117519152542e-05,
"loss": 0.0438,
"step": 74
},
{
"epoch": 0.010115314586283633,
"grad_norm": 0.12343823164701462,
"learning_rate": 7.379736965185368e-05,
"loss": 0.0427,
"step": 75
},
{
"epoch": 0.010250185447434081,
"grad_norm": 0.13671594858169556,
"learning_rate": 7.30670581489344e-05,
"loss": 0.0418,
"step": 76
},
{
"epoch": 0.01038505630858453,
"grad_norm": 0.21372199058532715,
"learning_rate": 7.233044034264034e-05,
"loss": 0.0531,
"step": 77
},
{
"epoch": 0.010519927169734978,
"grad_norm": 0.213307723402977,
"learning_rate": 7.158771761692464e-05,
"loss": 0.0516,
"step": 78
},
{
"epoch": 0.010654798030885428,
"grad_norm": 0.1346154659986496,
"learning_rate": 7.083909302476453e-05,
"loss": 0.0394,
"step": 79
},
{
"epoch": 0.010789668892035876,
"grad_norm": 0.1617816984653473,
"learning_rate": 7.008477123264848e-05,
"loss": 0.0433,
"step": 80
},
{
"epoch": 0.010924539753186325,
"grad_norm": 0.1087741106748581,
"learning_rate": 6.932495846462261e-05,
"loss": 0.0414,
"step": 81
},
{
"epoch": 0.011059410614336773,
"grad_norm": 0.21984659135341644,
"learning_rate": 6.855986244591104e-05,
"loss": 0.0522,
"step": 82
},
{
"epoch": 0.011194281475487221,
"grad_norm": 0.19846725463867188,
"learning_rate": 6.778969234612584e-05,
"loss": 0.0434,
"step": 83
},
{
"epoch": 0.01132915233663767,
"grad_norm": 0.14853249490261078,
"learning_rate": 6.701465872208216e-05,
"loss": 0.0408,
"step": 84
},
{
"epoch": 0.011464023197788118,
"grad_norm": 0.148597851395607,
"learning_rate": 6.623497346023418e-05,
"loss": 0.0414,
"step": 85
},
{
"epoch": 0.011598894058938566,
"grad_norm": 0.25445815920829773,
"learning_rate": 6.545084971874738e-05,
"loss": 0.0424,
"step": 86
},
{
"epoch": 0.011733764920089014,
"grad_norm": 4.882418155670166,
"learning_rate": 6.466250186922325e-05,
"loss": 1.1463,
"step": 87
},
{
"epoch": 0.011868635781239463,
"grad_norm": 4.033985137939453,
"learning_rate": 6.387014543809223e-05,
"loss": 1.2096,
"step": 88
},
{
"epoch": 0.012003506642389911,
"grad_norm": 1.3840826749801636,
"learning_rate": 6.307399704769099e-05,
"loss": 1.0783,
"step": 89
},
{
"epoch": 0.01213837750354036,
"grad_norm": 1.433290719985962,
"learning_rate": 6.227427435703997e-05,
"loss": 1.123,
"step": 90
},
{
"epoch": 0.01227324836469081,
"grad_norm": 1.2154169082641602,
"learning_rate": 6.147119600233758e-05,
"loss": 1.1174,
"step": 91
},
{
"epoch": 0.012408119225841258,
"grad_norm": 0.9925626516342163,
"learning_rate": 6.066498153718735e-05,
"loss": 1.0694,
"step": 92
},
{
"epoch": 0.012542990086991706,
"grad_norm": 0.8280858993530273,
"learning_rate": 5.985585137257401e-05,
"loss": 1.0655,
"step": 93
},
{
"epoch": 0.012677860948142154,
"grad_norm": 0.7677132487297058,
"learning_rate": 5.90440267166055e-05,
"loss": 1.0975,
"step": 94
},
{
"epoch": 0.012812731809292602,
"grad_norm": 0.8708370327949524,
"learning_rate": 5.8229729514036705e-05,
"loss": 1.0705,
"step": 95
},
{
"epoch": 0.01294760267044305,
"grad_norm": 0.5792795419692993,
"learning_rate": 5.74131823855921e-05,
"loss": 1.0495,
"step": 96
},
{
"epoch": 0.013082473531593499,
"grad_norm": 0.6706490516662598,
"learning_rate": 5.6594608567103456e-05,
"loss": 1.0352,
"step": 97
},
{
"epoch": 0.013217344392743947,
"grad_norm": 0.7173192501068115,
"learning_rate": 5.577423184847932e-05,
"loss": 1.0646,
"step": 98
},
{
"epoch": 0.013352215253894396,
"grad_norm": 0.9378214478492737,
"learning_rate": 5.495227651252315e-05,
"loss": 1.0641,
"step": 99
},
{
"epoch": 0.013487086115044844,
"grad_norm": 1.4355167150497437,
"learning_rate": 5.4128967273616625e-05,
"loss": 1.0136,
"step": 100
},
{
"epoch": 0.013487086115044844,
"eval_loss": 0.45874062180519104,
"eval_runtime": 249.2933,
"eval_samples_per_second": 50.094,
"eval_steps_per_second": 12.523,
"step": 100
},
{
"epoch": 0.013621956976195292,
"grad_norm": 1.154103398323059,
"learning_rate": 5.330452921628497e-05,
"loss": 1.0931,
"step": 101
},
{
"epoch": 0.01375682783734574,
"grad_norm": 1.06230628490448,
"learning_rate": 5.247918773366112e-05,
"loss": 1.1436,
"step": 102
},
{
"epoch": 0.01389169869849619,
"grad_norm": 0.7162177562713623,
"learning_rate": 5.165316846586541e-05,
"loss": 1.1061,
"step": 103
},
{
"epoch": 0.014026569559646639,
"grad_norm": 0.5899637341499329,
"learning_rate": 5.0826697238317935e-05,
"loss": 1.1117,
"step": 104
},
{
"epoch": 0.014161440420797087,
"grad_norm": 0.6702312231063843,
"learning_rate": 5e-05,
"loss": 1.05,
"step": 105
},
{
"epoch": 0.014296311281947536,
"grad_norm": 0.5332008004188538,
"learning_rate": 4.917330276168208e-05,
"loss": 0.7966,
"step": 106
},
{
"epoch": 0.014431182143097984,
"grad_norm": 0.49046453833580017,
"learning_rate": 4.834683153413459e-05,
"loss": 0.3945,
"step": 107
},
{
"epoch": 0.014566053004248432,
"grad_norm": 0.3994702994823456,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.2001,
"step": 108
},
{
"epoch": 0.01470092386539888,
"grad_norm": 0.2636468708515167,
"learning_rate": 4.669547078371504e-05,
"loss": 0.2455,
"step": 109
},
{
"epoch": 0.014835794726549329,
"grad_norm": 0.20182305574417114,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.094,
"step": 110
},
{
"epoch": 0.014970665587699777,
"grad_norm": 0.19701479375362396,
"learning_rate": 4.504772348747687e-05,
"loss": 0.0477,
"step": 111
},
{
"epoch": 0.015105536448850225,
"grad_norm": 0.35208454728126526,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.1586,
"step": 112
},
{
"epoch": 0.015240407310000674,
"grad_norm": 0.2762204706668854,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.1482,
"step": 113
},
{
"epoch": 0.015375278171151122,
"grad_norm": 0.17137527465820312,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.04,
"step": 114
},
{
"epoch": 0.015510149032301572,
"grad_norm": 0.12093689292669296,
"learning_rate": 4.17702704859633e-05,
"loss": 0.036,
"step": 115
},
{
"epoch": 0.01564501989345202,
"grad_norm": 0.2148885577917099,
"learning_rate": 4.095597328339452e-05,
"loss": 0.0409,
"step": 116
},
{
"epoch": 0.01577989075460247,
"grad_norm": 0.14908663928508759,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.0433,
"step": 117
},
{
"epoch": 0.015914761615752917,
"grad_norm": 0.20705260336399078,
"learning_rate": 3.933501846281267e-05,
"loss": 0.0401,
"step": 118
},
{
"epoch": 0.016049632476903365,
"grad_norm": 0.163040891289711,
"learning_rate": 3.852880399766243e-05,
"loss": 0.0458,
"step": 119
},
{
"epoch": 0.016184503338053813,
"grad_norm": 0.15930142998695374,
"learning_rate": 3.772572564296005e-05,
"loss": 0.0466,
"step": 120
},
{
"epoch": 0.016319374199204262,
"grad_norm": 0.11527015268802643,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.0396,
"step": 121
},
{
"epoch": 0.01645424506035471,
"grad_norm": 0.13680198788642883,
"learning_rate": 3.612985456190778e-05,
"loss": 0.0441,
"step": 122
},
{
"epoch": 0.01658911592150516,
"grad_norm": 0.19573064148426056,
"learning_rate": 3.533749813077677e-05,
"loss": 0.0956,
"step": 123
},
{
"epoch": 0.016723986782655607,
"grad_norm": 0.14308318495750427,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.0391,
"step": 124
},
{
"epoch": 0.016858857643806055,
"grad_norm": 0.15585479140281677,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.0393,
"step": 125
},
{
"epoch": 0.016993728504956503,
"grad_norm": 0.09065719693899155,
"learning_rate": 3.298534127791785e-05,
"loss": 0.0399,
"step": 126
},
{
"epoch": 0.01712859936610695,
"grad_norm": 0.15405875444412231,
"learning_rate": 3.221030765387417e-05,
"loss": 0.0457,
"step": 127
},
{
"epoch": 0.0172634702272574,
"grad_norm": 0.10315316915512085,
"learning_rate": 3.144013755408895e-05,
"loss": 0.0411,
"step": 128
},
{
"epoch": 0.017398341088407848,
"grad_norm": 0.21783660352230072,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.041,
"step": 129
},
{
"epoch": 0.017533211949558297,
"grad_norm": 0.11783421039581299,
"learning_rate": 2.991522876735154e-05,
"loss": 0.035,
"step": 130
},
{
"epoch": 0.017668082810708745,
"grad_norm": 0.17072497308254242,
"learning_rate": 2.916090697523549e-05,
"loss": 0.0369,
"step": 131
},
{
"epoch": 0.017802953671859193,
"grad_norm": 0.14656904339790344,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.0436,
"step": 132
},
{
"epoch": 0.017937824533009645,
"grad_norm": 0.13313239812850952,
"learning_rate": 2.766955965735968e-05,
"loss": 0.0379,
"step": 133
},
{
"epoch": 0.018072695394160093,
"grad_norm": 0.09710622578859329,
"learning_rate": 2.693294185106562e-05,
"loss": 0.0362,
"step": 134
},
{
"epoch": 0.01820756625531054,
"grad_norm": 0.17009422183036804,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.0354,
"step": 135
},
{
"epoch": 0.01834243711646099,
"grad_norm": 0.15286409854888916,
"learning_rate": 2.547882480847461e-05,
"loss": 0.0472,
"step": 136
},
{
"epoch": 0.018477307977611438,
"grad_norm": 1.024570107460022,
"learning_rate": 2.476172311325783e-05,
"loss": 0.4006,
"step": 137
},
{
"epoch": 0.018612178838761886,
"grad_norm": 1.9380091428756714,
"learning_rate": 2.405152131093926e-05,
"loss": 1.0402,
"step": 138
},
{
"epoch": 0.018747049699912335,
"grad_norm": 1.3342516422271729,
"learning_rate": 2.3348413563600325e-05,
"loss": 1.0091,
"step": 139
},
{
"epoch": 0.018881920561062783,
"grad_norm": 1.0465189218521118,
"learning_rate": 2.2652592093878666e-05,
"loss": 1.0345,
"step": 140
},
{
"epoch": 0.01901679142221323,
"grad_norm": 0.7378867864608765,
"learning_rate": 2.196424713241637e-05,
"loss": 1.014,
"step": 141
},
{
"epoch": 0.01915166228336368,
"grad_norm": 0.8982412219047546,
"learning_rate": 2.128356686585282e-05,
"loss": 1.0255,
"step": 142
},
{
"epoch": 0.019286533144514128,
"grad_norm": 0.7232892513275146,
"learning_rate": 2.061073738537635e-05,
"loss": 0.9907,
"step": 143
},
{
"epoch": 0.019421404005664576,
"grad_norm": 0.6869871020317078,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.9829,
"step": 144
},
{
"epoch": 0.019556274866815024,
"grad_norm": 0.6115788817405701,
"learning_rate": 1.928936436551661e-05,
"loss": 1.0492,
"step": 145
},
{
"epoch": 0.019691145727965473,
"grad_norm": 0.5646613836288452,
"learning_rate": 1.8641182076323148e-05,
"loss": 1.0136,
"step": 146
},
{
"epoch": 0.01982601658911592,
"grad_norm": 0.7063979506492615,
"learning_rate": 1.800157297483417e-05,
"loss": 0.9944,
"step": 147
},
{
"epoch": 0.01996088745026637,
"grad_norm": 0.6069715619087219,
"learning_rate": 1.7370711923791567e-05,
"loss": 1.0393,
"step": 148
},
{
"epoch": 0.020095758311416818,
"grad_norm": 0.7639333605766296,
"learning_rate": 1.6748771394307585e-05,
"loss": 1.0475,
"step": 149
},
{
"epoch": 0.020230629172567266,
"grad_norm": 0.734391987323761,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.9679,
"step": 150
},
{
"epoch": 0.020230629172567266,
"eval_loss": 0.4362151622772217,
"eval_runtime": 249.2132,
"eval_samples_per_second": 50.11,
"eval_steps_per_second": 12.527,
"step": 150
},
{
"epoch": 0.020365500033717714,
"grad_norm": 0.4770492911338806,
"learning_rate": 1.553232954407171e-05,
"loss": 1.0373,
"step": 151
},
{
"epoch": 0.020500370894868163,
"grad_norm": 0.4720907509326935,
"learning_rate": 1.4938160786375572e-05,
"loss": 1.0514,
"step": 152
},
{
"epoch": 0.02063524175601861,
"grad_norm": 0.40358442068099976,
"learning_rate": 1.435357758543015e-05,
"loss": 1.0898,
"step": 153
},
{
"epoch": 0.02077011261716906,
"grad_norm": 0.4329061210155487,
"learning_rate": 1.3778739760445552e-05,
"loss": 1.0842,
"step": 154
},
{
"epoch": 0.020904983478319508,
"grad_norm": 0.43310973048210144,
"learning_rate": 1.3213804466343421e-05,
"loss": 1.0313,
"step": 155
},
{
"epoch": 0.021039854339469956,
"grad_norm": 0.41418910026550293,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.6619,
"step": 156
},
{
"epoch": 0.021174725200620408,
"grad_norm": 0.41492196917533875,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.2823,
"step": 157
},
{
"epoch": 0.021309596061770856,
"grad_norm": 0.40460270643234253,
"learning_rate": 1.157994445715706e-05,
"loss": 0.2479,
"step": 158
},
{
"epoch": 0.021444466922921304,
"grad_norm": 0.29948437213897705,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.1944,
"step": 159
},
{
"epoch": 0.021579337784071752,
"grad_norm": 0.2803797721862793,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.1948,
"step": 160
},
{
"epoch": 0.0217142086452222,
"grad_norm": 0.26013702154159546,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.0366,
"step": 161
},
{
"epoch": 0.02184907950637265,
"grad_norm": 0.15579740703105927,
"learning_rate": 9.549150281252633e-06,
"loss": 0.0882,
"step": 162
},
{
"epoch": 0.021983950367523097,
"grad_norm": 0.20640526711940765,
"learning_rate": 9.068759265665384e-06,
"loss": 0.0393,
"step": 163
},
{
"epoch": 0.022118821228673546,
"grad_norm": 0.21217302978038788,
"learning_rate": 8.599558442598998e-06,
"loss": 0.0866,
"step": 164
},
{
"epoch": 0.022253692089823994,
"grad_norm": 0.26351720094680786,
"learning_rate": 8.141676086873572e-06,
"loss": 0.1363,
"step": 165
},
{
"epoch": 0.022388562950974442,
"grad_norm": 0.14430148899555206,
"learning_rate": 7.695237378953223e-06,
"loss": 0.0436,
"step": 166
},
{
"epoch": 0.02252343381212489,
"grad_norm": 0.1613907814025879,
"learning_rate": 7.260364370723044e-06,
"loss": 0.0391,
"step": 167
},
{
"epoch": 0.02265830467327534,
"grad_norm": 0.18218548595905304,
"learning_rate": 6.837175952121306e-06,
"loss": 0.0443,
"step": 168
},
{
"epoch": 0.022793175534425787,
"grad_norm": 0.26546183228492737,
"learning_rate": 6.425787818636131e-06,
"loss": 0.0427,
"step": 169
},
{
"epoch": 0.022928046395576235,
"grad_norm": 0.22911402583122253,
"learning_rate": 6.026312439675552e-06,
"loss": 0.0417,
"step": 170
},
{
"epoch": 0.023062917256726684,
"grad_norm": 0.23015467822551727,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.0384,
"step": 171
},
{
"epoch": 0.023197788117877132,
"grad_norm": 0.15810216963291168,
"learning_rate": 5.263533508961827e-06,
"loss": 0.0303,
"step": 172
},
{
"epoch": 0.02333265897902758,
"grad_norm": 0.21922291815280914,
"learning_rate": 4.900438493352055e-06,
"loss": 0.0397,
"step": 173
},
{
"epoch": 0.02346752984017803,
"grad_norm": 0.12656520307064056,
"learning_rate": 4.549673247541875e-06,
"loss": 0.0334,
"step": 174
},
{
"epoch": 0.023602400701328477,
"grad_norm": 0.1482604295015335,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.0304,
"step": 175
},
{
"epoch": 0.023737271562478925,
"grad_norm": 0.18631023168563843,
"learning_rate": 3.885512251130763e-06,
"loss": 0.04,
"step": 176
},
{
"epoch": 0.023872142423629374,
"grad_norm": 0.17001986503601074,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.0357,
"step": 177
},
{
"epoch": 0.024007013284779822,
"grad_norm": 0.12342365831136703,
"learning_rate": 3.271776770026963e-06,
"loss": 0.0319,
"step": 178
},
{
"epoch": 0.02414188414593027,
"grad_norm": 0.23690053820610046,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.0341,
"step": 179
},
{
"epoch": 0.02427675500708072,
"grad_norm": 0.22250895202159882,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.0377,
"step": 180
},
{
"epoch": 0.02441162586823117,
"grad_norm": 0.18933339416980743,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.0383,
"step": 181
},
{
"epoch": 0.02454649672938162,
"grad_norm": 0.1443464159965515,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.0384,
"step": 182
},
{
"epoch": 0.024681367590532067,
"grad_norm": 0.20531915128231049,
"learning_rate": 1.962316193157593e-06,
"loss": 0.0353,
"step": 183
},
{
"epoch": 0.024816238451682515,
"grad_norm": 0.14282475411891937,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.0331,
"step": 184
},
{
"epoch": 0.024951109312832963,
"grad_norm": 0.19556961953639984,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.038,
"step": 185
},
{
"epoch": 0.025085980173983412,
"grad_norm": 0.7125883102416992,
"learning_rate": 1.333670137599713e-06,
"loss": 0.41,
"step": 186
},
{
"epoch": 0.02522085103513386,
"grad_norm": 1.3167765140533447,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.985,
"step": 187
},
{
"epoch": 0.02535572189628431,
"grad_norm": 1.1046371459960938,
"learning_rate": 9.810017062595322e-07,
"loss": 0.9784,
"step": 188
},
{
"epoch": 0.025490592757434757,
"grad_norm": 1.3128546476364136,
"learning_rate": 8.247462563808817e-07,
"loss": 1.0151,
"step": 189
},
{
"epoch": 0.025625463618585205,
"grad_norm": 1.1267266273498535,
"learning_rate": 6.819348298638839e-07,
"loss": 1.0485,
"step": 190
},
{
"epoch": 0.025760334479735653,
"grad_norm": 1.157323956489563,
"learning_rate": 5.526064699265753e-07,
"loss": 1.0234,
"step": 191
},
{
"epoch": 0.0258952053408861,
"grad_norm": 1.1781102418899536,
"learning_rate": 4.367965336512403e-07,
"loss": 1.0485,
"step": 192
},
{
"epoch": 0.02603007620203655,
"grad_norm": 1.4020339250564575,
"learning_rate": 3.3453668231809286e-07,
"loss": 1.0351,
"step": 193
},
{
"epoch": 0.026164947063186998,
"grad_norm": 1.2867029905319214,
"learning_rate": 2.458548727494292e-07,
"loss": 1.0347,
"step": 194
},
{
"epoch": 0.026299817924337447,
"grad_norm": 1.3159316778182983,
"learning_rate": 1.7077534966650766e-07,
"loss": 1.072,
"step": 195
},
{
"epoch": 0.026434688785487895,
"grad_norm": 1.4533225297927856,
"learning_rate": 1.0931863906127327e-07,
"loss": 1.0355,
"step": 196
},
{
"epoch": 0.026569559646638343,
"grad_norm": 1.4070099592208862,
"learning_rate": 6.150154258476315e-08,
"loss": 1.042,
"step": 197
},
{
"epoch": 0.02670443050778879,
"grad_norm": 1.6895979642868042,
"learning_rate": 2.7337132953697554e-08,
"loss": 1.0694,
"step": 198
},
{
"epoch": 0.02683930136893924,
"grad_norm": 1.4647972583770752,
"learning_rate": 6.834750376549792e-09,
"loss": 1.0512,
"step": 199
},
{
"epoch": 0.026974172230089688,
"grad_norm": 1.777890682220459,
"learning_rate": 0.0,
"loss": 1.0001,
"step": 200
},
{
"epoch": 0.026974172230089688,
"eval_loss": 0.4377606511116028,
"eval_runtime": 249.0577,
"eval_samples_per_second": 50.141,
"eval_steps_per_second": 12.535,
"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": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.26629570494464e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}