prxy5606's picture
Training in progress, step 200, checkpoint
0fd33b5 verified
{
"best_metric": 11.789237976074219,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.07582938388625593,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003791469194312796,
"grad_norm": 0.28769180178642273,
"learning_rate": 1e-05,
"loss": 11.9341,
"step": 1
},
{
"epoch": 0.0003791469194312796,
"eval_loss": 11.931600570678711,
"eval_runtime": 43.8048,
"eval_samples_per_second": 101.404,
"eval_steps_per_second": 25.363,
"step": 1
},
{
"epoch": 0.0007582938388625592,
"grad_norm": 0.26498857140541077,
"learning_rate": 2e-05,
"loss": 11.9335,
"step": 2
},
{
"epoch": 0.001137440758293839,
"grad_norm": 0.2662431299686432,
"learning_rate": 3e-05,
"loss": 11.9364,
"step": 3
},
{
"epoch": 0.0015165876777251184,
"grad_norm": 0.301140695810318,
"learning_rate": 4e-05,
"loss": 11.9313,
"step": 4
},
{
"epoch": 0.0018957345971563982,
"grad_norm": 0.26981547474861145,
"learning_rate": 5e-05,
"loss": 11.9242,
"step": 5
},
{
"epoch": 0.002274881516587678,
"grad_norm": 0.2758404612541199,
"learning_rate": 6e-05,
"loss": 11.9395,
"step": 6
},
{
"epoch": 0.002654028436018957,
"grad_norm": 0.3056615889072418,
"learning_rate": 7e-05,
"loss": 11.9271,
"step": 7
},
{
"epoch": 0.003033175355450237,
"grad_norm": 0.28484514355659485,
"learning_rate": 8e-05,
"loss": 11.9274,
"step": 8
},
{
"epoch": 0.0034123222748815166,
"grad_norm": 0.27682986855506897,
"learning_rate": 9e-05,
"loss": 11.932,
"step": 9
},
{
"epoch": 0.0037914691943127963,
"grad_norm": 0.3237661123275757,
"learning_rate": 0.0001,
"loss": 11.9229,
"step": 10
},
{
"epoch": 0.004170616113744076,
"grad_norm": 0.3356820046901703,
"learning_rate": 9.999316524962345e-05,
"loss": 11.92,
"step": 11
},
{
"epoch": 0.004549763033175356,
"grad_norm": 0.3805263042449951,
"learning_rate": 9.997266286704631e-05,
"loss": 11.9183,
"step": 12
},
{
"epoch": 0.0049289099526066355,
"grad_norm": 0.4529215395450592,
"learning_rate": 9.993849845741524e-05,
"loss": 11.9161,
"step": 13
},
{
"epoch": 0.005308056872037914,
"grad_norm": 0.4107781648635864,
"learning_rate": 9.989068136093873e-05,
"loss": 11.9106,
"step": 14
},
{
"epoch": 0.005687203791469194,
"grad_norm": 0.4610343277454376,
"learning_rate": 9.98292246503335e-05,
"loss": 11.91,
"step": 15
},
{
"epoch": 0.006066350710900474,
"grad_norm": 0.45946910977363586,
"learning_rate": 9.975414512725057e-05,
"loss": 11.9126,
"step": 16
},
{
"epoch": 0.0064454976303317535,
"grad_norm": 0.5091995000839233,
"learning_rate": 9.966546331768191e-05,
"loss": 11.9019,
"step": 17
},
{
"epoch": 0.006824644549763033,
"grad_norm": 0.47413066029548645,
"learning_rate": 9.956320346634876e-05,
"loss": 11.9032,
"step": 18
},
{
"epoch": 0.007203791469194313,
"grad_norm": 0.47228190302848816,
"learning_rate": 9.944739353007344e-05,
"loss": 11.8996,
"step": 19
},
{
"epoch": 0.007582938388625593,
"grad_norm": 0.4501458406448364,
"learning_rate": 9.931806517013612e-05,
"loss": 11.8936,
"step": 20
},
{
"epoch": 0.007962085308056872,
"grad_norm": 0.41325676441192627,
"learning_rate": 9.917525374361912e-05,
"loss": 11.8854,
"step": 21
},
{
"epoch": 0.008341232227488152,
"grad_norm": 0.43374261260032654,
"learning_rate": 9.901899829374047e-05,
"loss": 11.8845,
"step": 22
},
{
"epoch": 0.008720379146919432,
"grad_norm": 0.36916017532348633,
"learning_rate": 9.884934153917997e-05,
"loss": 11.8804,
"step": 23
},
{
"epoch": 0.009099526066350712,
"grad_norm": 0.36391785740852356,
"learning_rate": 9.86663298624003e-05,
"loss": 11.8814,
"step": 24
},
{
"epoch": 0.009478672985781991,
"grad_norm": 0.3365619480609894,
"learning_rate": 9.847001329696653e-05,
"loss": 11.8797,
"step": 25
},
{
"epoch": 0.009857819905213271,
"grad_norm": 0.3295334279537201,
"learning_rate": 9.826044551386744e-05,
"loss": 11.8717,
"step": 26
},
{
"epoch": 0.010236966824644549,
"grad_norm": 0.29351353645324707,
"learning_rate": 9.803768380684242e-05,
"loss": 11.8652,
"step": 27
},
{
"epoch": 0.010616113744075829,
"grad_norm": 0.3394353687763214,
"learning_rate": 9.780178907671789e-05,
"loss": 11.8688,
"step": 28
},
{
"epoch": 0.010995260663507108,
"grad_norm": 0.3891104459762573,
"learning_rate": 9.755282581475769e-05,
"loss": 11.8692,
"step": 29
},
{
"epoch": 0.011374407582938388,
"grad_norm": 0.26279541850090027,
"learning_rate": 9.729086208503174e-05,
"loss": 11.8697,
"step": 30
},
{
"epoch": 0.011753554502369668,
"grad_norm": 0.29191040992736816,
"learning_rate": 9.701596950580806e-05,
"loss": 11.8641,
"step": 31
},
{
"epoch": 0.012132701421800948,
"grad_norm": 0.23644578456878662,
"learning_rate": 9.672822322997305e-05,
"loss": 11.8608,
"step": 32
},
{
"epoch": 0.012511848341232227,
"grad_norm": 0.2428828924894333,
"learning_rate": 9.642770192448536e-05,
"loss": 11.8616,
"step": 33
},
{
"epoch": 0.012890995260663507,
"grad_norm": 0.20023727416992188,
"learning_rate": 9.611448774886924e-05,
"loss": 11.8546,
"step": 34
},
{
"epoch": 0.013270142180094787,
"grad_norm": 0.2178952544927597,
"learning_rate": 9.578866633275288e-05,
"loss": 11.8558,
"step": 35
},
{
"epoch": 0.013649289099526066,
"grad_norm": 0.2382510006427765,
"learning_rate": 9.545032675245813e-05,
"loss": 11.8543,
"step": 36
},
{
"epoch": 0.014028436018957346,
"grad_norm": 0.2123047560453415,
"learning_rate": 9.509956150664796e-05,
"loss": 11.8577,
"step": 37
},
{
"epoch": 0.014407582938388626,
"grad_norm": 0.1820491999387741,
"learning_rate": 9.473646649103818e-05,
"loss": 11.8507,
"step": 38
},
{
"epoch": 0.014786729857819906,
"grad_norm": 0.2487359642982483,
"learning_rate": 9.43611409721806e-05,
"loss": 11.8598,
"step": 39
},
{
"epoch": 0.015165876777251185,
"grad_norm": 0.3035540282726288,
"learning_rate": 9.397368756032445e-05,
"loss": 11.8501,
"step": 40
},
{
"epoch": 0.015545023696682465,
"grad_norm": 0.38344883918762207,
"learning_rate": 9.357421218136386e-05,
"loss": 11.8533,
"step": 41
},
{
"epoch": 0.015924170616113745,
"grad_norm": 0.17882512509822845,
"learning_rate": 9.316282404787871e-05,
"loss": 11.8508,
"step": 42
},
{
"epoch": 0.016303317535545023,
"grad_norm": 0.16976627707481384,
"learning_rate": 9.273963562927695e-05,
"loss": 11.8501,
"step": 43
},
{
"epoch": 0.016682464454976304,
"grad_norm": 0.1657288819551468,
"learning_rate": 9.230476262104677e-05,
"loss": 11.838,
"step": 44
},
{
"epoch": 0.017061611374407582,
"grad_norm": 0.17109397053718567,
"learning_rate": 9.185832391312644e-05,
"loss": 11.8438,
"step": 45
},
{
"epoch": 0.017440758293838864,
"grad_norm": 0.17634600400924683,
"learning_rate": 9.140044155740101e-05,
"loss": 11.8416,
"step": 46
},
{
"epoch": 0.01781990521327014,
"grad_norm": 0.18844150006771088,
"learning_rate": 9.093124073433463e-05,
"loss": 11.8413,
"step": 47
},
{
"epoch": 0.018199052132701423,
"grad_norm": 0.28906017541885376,
"learning_rate": 9.045084971874738e-05,
"loss": 11.85,
"step": 48
},
{
"epoch": 0.0185781990521327,
"grad_norm": 0.20972122251987457,
"learning_rate": 8.995939984474624e-05,
"loss": 11.8434,
"step": 49
},
{
"epoch": 0.018957345971563982,
"grad_norm": 0.24533000588417053,
"learning_rate": 8.945702546981969e-05,
"loss": 11.8367,
"step": 50
},
{
"epoch": 0.018957345971563982,
"eval_loss": 11.85046672821045,
"eval_runtime": 44.0024,
"eval_samples_per_second": 100.949,
"eval_steps_per_second": 25.249,
"step": 50
},
{
"epoch": 0.01933649289099526,
"grad_norm": 0.21670155227184296,
"learning_rate": 8.894386393810563e-05,
"loss": 11.8483,
"step": 51
},
{
"epoch": 0.019715639810426542,
"grad_norm": 0.1768616884946823,
"learning_rate": 8.842005554284296e-05,
"loss": 11.8614,
"step": 52
},
{
"epoch": 0.02009478672985782,
"grad_norm": 0.14872843027114868,
"learning_rate": 8.788574348801675e-05,
"loss": 11.8544,
"step": 53
},
{
"epoch": 0.020473933649289098,
"grad_norm": 0.26231178641319275,
"learning_rate": 8.73410738492077e-05,
"loss": 11.8611,
"step": 54
},
{
"epoch": 0.02085308056872038,
"grad_norm": 0.1851011961698532,
"learning_rate": 8.678619553365659e-05,
"loss": 11.8575,
"step": 55
},
{
"epoch": 0.021232227488151657,
"grad_norm": 0.16626429557800293,
"learning_rate": 8.622126023955446e-05,
"loss": 11.8542,
"step": 56
},
{
"epoch": 0.02161137440758294,
"grad_norm": 0.1764294058084488,
"learning_rate": 8.564642241456986e-05,
"loss": 11.8449,
"step": 57
},
{
"epoch": 0.021990521327014217,
"grad_norm": 0.19001427292823792,
"learning_rate": 8.506183921362443e-05,
"loss": 11.8618,
"step": 58
},
{
"epoch": 0.022369668246445498,
"grad_norm": 0.20055465400218964,
"learning_rate": 8.44676704559283e-05,
"loss": 11.8561,
"step": 59
},
{
"epoch": 0.022748815165876776,
"grad_norm": 0.1839049756526947,
"learning_rate": 8.386407858128706e-05,
"loss": 11.8538,
"step": 60
},
{
"epoch": 0.023127962085308058,
"grad_norm": 0.16656097769737244,
"learning_rate": 8.32512286056924e-05,
"loss": 11.8499,
"step": 61
},
{
"epoch": 0.023507109004739336,
"grad_norm": 0.15637564659118652,
"learning_rate": 8.262928807620843e-05,
"loss": 11.8478,
"step": 62
},
{
"epoch": 0.023886255924170617,
"grad_norm": 0.1506025791168213,
"learning_rate": 8.199842702516583e-05,
"loss": 11.8496,
"step": 63
},
{
"epoch": 0.024265402843601895,
"grad_norm": 0.18512433767318726,
"learning_rate": 8.135881792367686e-05,
"loss": 11.8521,
"step": 64
},
{
"epoch": 0.024644549763033177,
"grad_norm": 0.19561633467674255,
"learning_rate": 8.07106356344834e-05,
"loss": 11.8488,
"step": 65
},
{
"epoch": 0.025023696682464455,
"grad_norm": 0.15633133053779602,
"learning_rate": 8.005405736415126e-05,
"loss": 11.8452,
"step": 66
},
{
"epoch": 0.025402843601895736,
"grad_norm": 0.15324749052524567,
"learning_rate": 7.938926261462366e-05,
"loss": 11.8427,
"step": 67
},
{
"epoch": 0.025781990521327014,
"grad_norm": 0.16857261955738068,
"learning_rate": 7.871643313414718e-05,
"loss": 11.845,
"step": 68
},
{
"epoch": 0.026161137440758295,
"grad_norm": 0.19223137199878693,
"learning_rate": 7.803575286758364e-05,
"loss": 11.8425,
"step": 69
},
{
"epoch": 0.026540284360189573,
"grad_norm": 0.19688811898231506,
"learning_rate": 7.734740790612136e-05,
"loss": 11.8418,
"step": 70
},
{
"epoch": 0.02691943127962085,
"grad_norm": 0.16625766456127167,
"learning_rate": 7.66515864363997e-05,
"loss": 11.8403,
"step": 71
},
{
"epoch": 0.027298578199052133,
"grad_norm": 0.1805586814880371,
"learning_rate": 7.594847868906076e-05,
"loss": 11.8356,
"step": 72
},
{
"epoch": 0.02767772511848341,
"grad_norm": 0.18211770057678223,
"learning_rate": 7.52382768867422e-05,
"loss": 11.8378,
"step": 73
},
{
"epoch": 0.028056872037914692,
"grad_norm": 0.1834656447172165,
"learning_rate": 7.452117519152542e-05,
"loss": 11.8259,
"step": 74
},
{
"epoch": 0.02843601895734597,
"grad_norm": 0.16003456711769104,
"learning_rate": 7.379736965185368e-05,
"loss": 11.8347,
"step": 75
},
{
"epoch": 0.02881516587677725,
"grad_norm": 0.1905023753643036,
"learning_rate": 7.30670581489344e-05,
"loss": 11.8263,
"step": 76
},
{
"epoch": 0.02919431279620853,
"grad_norm": 0.14761149883270264,
"learning_rate": 7.233044034264034e-05,
"loss": 11.8357,
"step": 77
},
{
"epoch": 0.02957345971563981,
"grad_norm": 0.1856553852558136,
"learning_rate": 7.158771761692464e-05,
"loss": 11.8237,
"step": 78
},
{
"epoch": 0.02995260663507109,
"grad_norm": 0.14715948700904846,
"learning_rate": 7.083909302476453e-05,
"loss": 11.8252,
"step": 79
},
{
"epoch": 0.03033175355450237,
"grad_norm": 0.1759246587753296,
"learning_rate": 7.008477123264848e-05,
"loss": 11.8251,
"step": 80
},
{
"epoch": 0.03071090047393365,
"grad_norm": 0.13867217302322388,
"learning_rate": 6.932495846462261e-05,
"loss": 11.8188,
"step": 81
},
{
"epoch": 0.03109004739336493,
"grad_norm": 0.12833894789218903,
"learning_rate": 6.855986244591104e-05,
"loss": 11.8229,
"step": 82
},
{
"epoch": 0.03146919431279621,
"grad_norm": 0.12929992377758026,
"learning_rate": 6.778969234612584e-05,
"loss": 11.8198,
"step": 83
},
{
"epoch": 0.03184834123222749,
"grad_norm": 0.1879982054233551,
"learning_rate": 6.701465872208216e-05,
"loss": 11.8211,
"step": 84
},
{
"epoch": 0.03222748815165877,
"grad_norm": 0.13484127819538116,
"learning_rate": 6.623497346023418e-05,
"loss": 11.8133,
"step": 85
},
{
"epoch": 0.032606635071090045,
"grad_norm": 0.16426604986190796,
"learning_rate": 6.545084971874738e-05,
"loss": 11.8192,
"step": 86
},
{
"epoch": 0.03298578199052133,
"grad_norm": 0.15773631632328033,
"learning_rate": 6.466250186922325e-05,
"loss": 11.8171,
"step": 87
},
{
"epoch": 0.03336492890995261,
"grad_norm": 0.1757354736328125,
"learning_rate": 6.387014543809223e-05,
"loss": 11.8124,
"step": 88
},
{
"epoch": 0.033744075829383886,
"grad_norm": 0.1542123258113861,
"learning_rate": 6.307399704769099e-05,
"loss": 11.8166,
"step": 89
},
{
"epoch": 0.034123222748815164,
"grad_norm": 0.16527996957302094,
"learning_rate": 6.227427435703997e-05,
"loss": 11.8206,
"step": 90
},
{
"epoch": 0.03450236966824644,
"grad_norm": 0.16867831349372864,
"learning_rate": 6.147119600233758e-05,
"loss": 11.8075,
"step": 91
},
{
"epoch": 0.03488151658767773,
"grad_norm": 0.15023113787174225,
"learning_rate": 6.066498153718735e-05,
"loss": 11.8108,
"step": 92
},
{
"epoch": 0.035260663507109005,
"grad_norm": 0.14039337635040283,
"learning_rate": 5.985585137257401e-05,
"loss": 11.7986,
"step": 93
},
{
"epoch": 0.03563981042654028,
"grad_norm": 0.18728798627853394,
"learning_rate": 5.90440267166055e-05,
"loss": 11.8061,
"step": 94
},
{
"epoch": 0.03601895734597156,
"grad_norm": 0.21996043622493744,
"learning_rate": 5.8229729514036705e-05,
"loss": 11.8135,
"step": 95
},
{
"epoch": 0.036398104265402846,
"grad_norm": 0.20277753472328186,
"learning_rate": 5.74131823855921e-05,
"loss": 11.8046,
"step": 96
},
{
"epoch": 0.036777251184834124,
"grad_norm": 0.18947215378284454,
"learning_rate": 5.6594608567103456e-05,
"loss": 11.8009,
"step": 97
},
{
"epoch": 0.0371563981042654,
"grad_norm": 0.19484518468379974,
"learning_rate": 5.577423184847932e-05,
"loss": 11.8014,
"step": 98
},
{
"epoch": 0.03753554502369668,
"grad_norm": 0.2266094982624054,
"learning_rate": 5.495227651252315e-05,
"loss": 11.7963,
"step": 99
},
{
"epoch": 0.037914691943127965,
"grad_norm": 0.23149214684963226,
"learning_rate": 5.4128967273616625e-05,
"loss": 11.7938,
"step": 100
},
{
"epoch": 0.037914691943127965,
"eval_loss": 11.812297821044922,
"eval_runtime": 43.9061,
"eval_samples_per_second": 101.17,
"eval_steps_per_second": 25.304,
"step": 100
},
{
"epoch": 0.03829383886255924,
"grad_norm": 0.16850636899471283,
"learning_rate": 5.330452921628497e-05,
"loss": 11.8059,
"step": 101
},
{
"epoch": 0.03867298578199052,
"grad_norm": 0.1942441463470459,
"learning_rate": 5.247918773366112e-05,
"loss": 11.815,
"step": 102
},
{
"epoch": 0.0390521327014218,
"grad_norm": 0.19246946275234222,
"learning_rate": 5.165316846586541e-05,
"loss": 11.8159,
"step": 103
},
{
"epoch": 0.039431279620853084,
"grad_norm": 0.18047946691513062,
"learning_rate": 5.0826697238317935e-05,
"loss": 11.8168,
"step": 104
},
{
"epoch": 0.03981042654028436,
"grad_norm": 0.16079886257648468,
"learning_rate": 5e-05,
"loss": 11.813,
"step": 105
},
{
"epoch": 0.04018957345971564,
"grad_norm": 0.17524497210979462,
"learning_rate": 4.917330276168208e-05,
"loss": 11.8219,
"step": 106
},
{
"epoch": 0.04056872037914692,
"grad_norm": 0.14713990688323975,
"learning_rate": 4.834683153413459e-05,
"loss": 11.8148,
"step": 107
},
{
"epoch": 0.040947867298578196,
"grad_norm": 0.127065971493721,
"learning_rate": 4.7520812266338885e-05,
"loss": 11.821,
"step": 108
},
{
"epoch": 0.04132701421800948,
"grad_norm": 0.10191242396831512,
"learning_rate": 4.669547078371504e-05,
"loss": 11.8177,
"step": 109
},
{
"epoch": 0.04170616113744076,
"grad_norm": 0.12673281133174896,
"learning_rate": 4.5871032726383386e-05,
"loss": 11.8152,
"step": 110
},
{
"epoch": 0.04208530805687204,
"grad_norm": 0.14365102350711823,
"learning_rate": 4.504772348747687e-05,
"loss": 11.8153,
"step": 111
},
{
"epoch": 0.042464454976303315,
"grad_norm": 0.13751044869422913,
"learning_rate": 4.4225768151520694e-05,
"loss": 11.8114,
"step": 112
},
{
"epoch": 0.0428436018957346,
"grad_norm": 0.14924171566963196,
"learning_rate": 4.3405391432896555e-05,
"loss": 11.8159,
"step": 113
},
{
"epoch": 0.04322274881516588,
"grad_norm": 0.10858994722366333,
"learning_rate": 4.2586817614407895e-05,
"loss": 11.8082,
"step": 114
},
{
"epoch": 0.043601895734597156,
"grad_norm": 0.1294364482164383,
"learning_rate": 4.17702704859633e-05,
"loss": 11.8152,
"step": 115
},
{
"epoch": 0.043981042654028434,
"grad_norm": 0.1143607646226883,
"learning_rate": 4.095597328339452e-05,
"loss": 11.8159,
"step": 116
},
{
"epoch": 0.04436018957345972,
"grad_norm": 0.10796434432268143,
"learning_rate": 4.0144148627425993e-05,
"loss": 11.8102,
"step": 117
},
{
"epoch": 0.044739336492890996,
"grad_norm": 0.16013963520526886,
"learning_rate": 3.933501846281267e-05,
"loss": 11.8237,
"step": 118
},
{
"epoch": 0.045118483412322274,
"grad_norm": 0.10867973417043686,
"learning_rate": 3.852880399766243e-05,
"loss": 11.807,
"step": 119
},
{
"epoch": 0.04549763033175355,
"grad_norm": 0.14788459241390228,
"learning_rate": 3.772572564296005e-05,
"loss": 11.8125,
"step": 120
},
{
"epoch": 0.04587677725118484,
"grad_norm": 0.14955635368824005,
"learning_rate": 3.6926002952309016e-05,
"loss": 11.8122,
"step": 121
},
{
"epoch": 0.046255924170616115,
"grad_norm": 0.1232515349984169,
"learning_rate": 3.612985456190778e-05,
"loss": 11.81,
"step": 122
},
{
"epoch": 0.04663507109004739,
"grad_norm": 0.12674307823181152,
"learning_rate": 3.533749813077677e-05,
"loss": 11.8097,
"step": 123
},
{
"epoch": 0.04701421800947867,
"grad_norm": 0.10738085210323334,
"learning_rate": 3.4549150281252636e-05,
"loss": 11.8108,
"step": 124
},
{
"epoch": 0.04739336492890995,
"grad_norm": 0.11420100927352905,
"learning_rate": 3.3765026539765834e-05,
"loss": 11.7998,
"step": 125
},
{
"epoch": 0.047772511848341234,
"grad_norm": 0.1361931413412094,
"learning_rate": 3.298534127791785e-05,
"loss": 11.8028,
"step": 126
},
{
"epoch": 0.04815165876777251,
"grad_norm": 0.12988242506980896,
"learning_rate": 3.221030765387417e-05,
"loss": 11.7993,
"step": 127
},
{
"epoch": 0.04853080568720379,
"grad_norm": 0.18020643293857574,
"learning_rate": 3.144013755408895e-05,
"loss": 11.8009,
"step": 128
},
{
"epoch": 0.04890995260663507,
"grad_norm": 0.1143268421292305,
"learning_rate": 3.0675041535377405e-05,
"loss": 11.8097,
"step": 129
},
{
"epoch": 0.04928909952606635,
"grad_norm": 0.13046760857105255,
"learning_rate": 2.991522876735154e-05,
"loss": 11.8051,
"step": 130
},
{
"epoch": 0.04966824644549763,
"grad_norm": 0.12067389488220215,
"learning_rate": 2.916090697523549e-05,
"loss": 11.8046,
"step": 131
},
{
"epoch": 0.05004739336492891,
"grad_norm": 0.13390123844146729,
"learning_rate": 2.8412282383075363e-05,
"loss": 11.8001,
"step": 132
},
{
"epoch": 0.05042654028436019,
"grad_norm": 0.1690846085548401,
"learning_rate": 2.766955965735968e-05,
"loss": 11.7989,
"step": 133
},
{
"epoch": 0.05080568720379147,
"grad_norm": 0.1262759566307068,
"learning_rate": 2.693294185106562e-05,
"loss": 11.7955,
"step": 134
},
{
"epoch": 0.05118483412322275,
"grad_norm": 0.1195095032453537,
"learning_rate": 2.6202630348146324e-05,
"loss": 11.7831,
"step": 135
},
{
"epoch": 0.05156398104265403,
"grad_norm": 0.1531498283147812,
"learning_rate": 2.547882480847461e-05,
"loss": 11.7925,
"step": 136
},
{
"epoch": 0.051943127962085306,
"grad_norm": 0.1306382119655609,
"learning_rate": 2.476172311325783e-05,
"loss": 11.7897,
"step": 137
},
{
"epoch": 0.05232227488151659,
"grad_norm": 0.17050689458847046,
"learning_rate": 2.405152131093926e-05,
"loss": 11.7833,
"step": 138
},
{
"epoch": 0.05270142180094787,
"grad_norm": 0.1543818861246109,
"learning_rate": 2.3348413563600325e-05,
"loss": 11.7778,
"step": 139
},
{
"epoch": 0.05308056872037915,
"grad_norm": 0.1629064679145813,
"learning_rate": 2.2652592093878666e-05,
"loss": 11.7884,
"step": 140
},
{
"epoch": 0.053459715639810425,
"grad_norm": 0.15135161578655243,
"learning_rate": 2.196424713241637e-05,
"loss": 11.7921,
"step": 141
},
{
"epoch": 0.0538388625592417,
"grad_norm": 0.13913819193840027,
"learning_rate": 2.128356686585282e-05,
"loss": 11.7866,
"step": 142
},
{
"epoch": 0.05421800947867299,
"grad_norm": 0.14062654972076416,
"learning_rate": 2.061073738537635e-05,
"loss": 11.7869,
"step": 143
},
{
"epoch": 0.054597156398104266,
"grad_norm": 0.18874435126781464,
"learning_rate": 1.9945942635848748e-05,
"loss": 11.7835,
"step": 144
},
{
"epoch": 0.054976303317535544,
"grad_norm": 0.15453287959098816,
"learning_rate": 1.928936436551661e-05,
"loss": 11.7864,
"step": 145
},
{
"epoch": 0.05535545023696682,
"grad_norm": 0.1882849633693695,
"learning_rate": 1.8641182076323148e-05,
"loss": 11.7744,
"step": 146
},
{
"epoch": 0.05573459715639811,
"grad_norm": 0.19366946816444397,
"learning_rate": 1.800157297483417e-05,
"loss": 11.7785,
"step": 147
},
{
"epoch": 0.056113744075829385,
"grad_norm": 0.20455895364284515,
"learning_rate": 1.7370711923791567e-05,
"loss": 11.7727,
"step": 148
},
{
"epoch": 0.05649289099526066,
"grad_norm": 0.23381587862968445,
"learning_rate": 1.6748771394307585e-05,
"loss": 11.7837,
"step": 149
},
{
"epoch": 0.05687203791469194,
"grad_norm": 0.21379578113555908,
"learning_rate": 1.6135921418712956e-05,
"loss": 11.7728,
"step": 150
},
{
"epoch": 0.05687203791469194,
"eval_loss": 11.7927827835083,
"eval_runtime": 43.8842,
"eval_samples_per_second": 101.221,
"eval_steps_per_second": 25.317,
"step": 150
},
{
"epoch": 0.057251184834123225,
"grad_norm": 0.16750890016555786,
"learning_rate": 1.553232954407171e-05,
"loss": 11.7841,
"step": 151
},
{
"epoch": 0.0576303317535545,
"grad_norm": 0.15428869426250458,
"learning_rate": 1.4938160786375572e-05,
"loss": 11.7955,
"step": 152
},
{
"epoch": 0.05800947867298578,
"grad_norm": 0.11902543902397156,
"learning_rate": 1.435357758543015e-05,
"loss": 11.7913,
"step": 153
},
{
"epoch": 0.05838862559241706,
"grad_norm": 0.13620445132255554,
"learning_rate": 1.3778739760445552e-05,
"loss": 11.8091,
"step": 154
},
{
"epoch": 0.058767772511848344,
"grad_norm": 0.14771781861782074,
"learning_rate": 1.3213804466343421e-05,
"loss": 11.7953,
"step": 155
},
{
"epoch": 0.05914691943127962,
"grad_norm": 0.12858200073242188,
"learning_rate": 1.2658926150792322e-05,
"loss": 11.8072,
"step": 156
},
{
"epoch": 0.0595260663507109,
"grad_norm": 0.12467218935489655,
"learning_rate": 1.2114256511983274e-05,
"loss": 11.8091,
"step": 157
},
{
"epoch": 0.05990521327014218,
"grad_norm": 0.11657291650772095,
"learning_rate": 1.157994445715706e-05,
"loss": 11.7938,
"step": 158
},
{
"epoch": 0.060284360189573456,
"grad_norm": 0.13835157454013824,
"learning_rate": 1.1056136061894384e-05,
"loss": 11.808,
"step": 159
},
{
"epoch": 0.06066350710900474,
"grad_norm": 0.1299125999212265,
"learning_rate": 1.0542974530180327e-05,
"loss": 11.8075,
"step": 160
},
{
"epoch": 0.06104265402843602,
"grad_norm": 0.12044967710971832,
"learning_rate": 1.0040600155253765e-05,
"loss": 11.8016,
"step": 161
},
{
"epoch": 0.0614218009478673,
"grad_norm": 0.1253618597984314,
"learning_rate": 9.549150281252633e-06,
"loss": 11.7931,
"step": 162
},
{
"epoch": 0.061800947867298575,
"grad_norm": 0.1312033236026764,
"learning_rate": 9.068759265665384e-06,
"loss": 11.798,
"step": 163
},
{
"epoch": 0.06218009478672986,
"grad_norm": 0.14857697486877441,
"learning_rate": 8.599558442598998e-06,
"loss": 11.7953,
"step": 164
},
{
"epoch": 0.06255924170616113,
"grad_norm": 0.15264755487442017,
"learning_rate": 8.141676086873572e-06,
"loss": 11.7924,
"step": 165
},
{
"epoch": 0.06293838862559242,
"grad_norm": 0.11737260222434998,
"learning_rate": 7.695237378953223e-06,
"loss": 11.8009,
"step": 166
},
{
"epoch": 0.0633175355450237,
"grad_norm": 0.11783807724714279,
"learning_rate": 7.260364370723044e-06,
"loss": 11.7974,
"step": 167
},
{
"epoch": 0.06369668246445498,
"grad_norm": 0.10636231303215027,
"learning_rate": 6.837175952121306e-06,
"loss": 11.7982,
"step": 168
},
{
"epoch": 0.06407582938388626,
"grad_norm": 0.12794683873653412,
"learning_rate": 6.425787818636131e-06,
"loss": 11.8013,
"step": 169
},
{
"epoch": 0.06445497630331753,
"grad_norm": 0.1254904866218567,
"learning_rate": 6.026312439675552e-06,
"loss": 11.7946,
"step": 170
},
{
"epoch": 0.06483412322274881,
"grad_norm": 0.1281624734401703,
"learning_rate": 5.6388590278194096e-06,
"loss": 11.8008,
"step": 171
},
{
"epoch": 0.06521327014218009,
"grad_norm": 0.10411489754915237,
"learning_rate": 5.263533508961827e-06,
"loss": 11.7897,
"step": 172
},
{
"epoch": 0.06559241706161137,
"grad_norm": 0.11528629809617996,
"learning_rate": 4.900438493352055e-06,
"loss": 11.7978,
"step": 173
},
{
"epoch": 0.06597156398104266,
"grad_norm": 0.130488783121109,
"learning_rate": 4.549673247541875e-06,
"loss": 11.7993,
"step": 174
},
{
"epoch": 0.06635071090047394,
"grad_norm": 0.10437383502721786,
"learning_rate": 4.2113336672471245e-06,
"loss": 11.7945,
"step": 175
},
{
"epoch": 0.06672985781990522,
"grad_norm": 0.1090942770242691,
"learning_rate": 3.885512251130763e-06,
"loss": 11.7843,
"step": 176
},
{
"epoch": 0.0671090047393365,
"grad_norm": 0.12790200114250183,
"learning_rate": 3.5722980755146517e-06,
"loss": 11.785,
"step": 177
},
{
"epoch": 0.06748815165876777,
"grad_norm": 0.14767682552337646,
"learning_rate": 3.271776770026963e-06,
"loss": 11.7857,
"step": 178
},
{
"epoch": 0.06786729857819905,
"grad_norm": 0.15827041864395142,
"learning_rate": 2.9840304941919415e-06,
"loss": 11.8018,
"step": 179
},
{
"epoch": 0.06824644549763033,
"grad_norm": 0.13997766375541687,
"learning_rate": 2.7091379149682685e-06,
"loss": 11.7856,
"step": 180
},
{
"epoch": 0.0686255924170616,
"grad_norm": 0.1263304501771927,
"learning_rate": 2.4471741852423237e-06,
"loss": 11.7963,
"step": 181
},
{
"epoch": 0.06900473933649288,
"grad_norm": 0.14048518240451813,
"learning_rate": 2.1982109232821178e-06,
"loss": 11.7878,
"step": 182
},
{
"epoch": 0.06938388625592418,
"grad_norm": 0.1328687071800232,
"learning_rate": 1.962316193157593e-06,
"loss": 11.7846,
"step": 183
},
{
"epoch": 0.06976303317535545,
"grad_norm": 0.1481953263282776,
"learning_rate": 1.7395544861325718e-06,
"loss": 11.7851,
"step": 184
},
{
"epoch": 0.07014218009478673,
"grad_norm": 0.14546702802181244,
"learning_rate": 1.5299867030334814e-06,
"loss": 11.788,
"step": 185
},
{
"epoch": 0.07052132701421801,
"grad_norm": 0.12582269310951233,
"learning_rate": 1.333670137599713e-06,
"loss": 11.7925,
"step": 186
},
{
"epoch": 0.07090047393364929,
"grad_norm": 0.14950110018253326,
"learning_rate": 1.1506584608200367e-06,
"loss": 11.7883,
"step": 187
},
{
"epoch": 0.07127962085308057,
"grad_norm": 0.12403721362352371,
"learning_rate": 9.810017062595322e-07,
"loss": 11.7848,
"step": 188
},
{
"epoch": 0.07165876777251184,
"grad_norm": 0.1594034880399704,
"learning_rate": 8.247462563808817e-07,
"loss": 11.774,
"step": 189
},
{
"epoch": 0.07203791469194312,
"grad_norm": 0.15566158294677734,
"learning_rate": 6.819348298638839e-07,
"loss": 11.7819,
"step": 190
},
{
"epoch": 0.07241706161137441,
"grad_norm": 0.14381428062915802,
"learning_rate": 5.526064699265753e-07,
"loss": 11.7861,
"step": 191
},
{
"epoch": 0.07279620853080569,
"grad_norm": 0.1404116153717041,
"learning_rate": 4.367965336512403e-07,
"loss": 11.778,
"step": 192
},
{
"epoch": 0.07317535545023697,
"grad_norm": 0.14419354498386383,
"learning_rate": 3.3453668231809286e-07,
"loss": 11.7789,
"step": 193
},
{
"epoch": 0.07355450236966825,
"grad_norm": 0.18890376389026642,
"learning_rate": 2.458548727494292e-07,
"loss": 11.774,
"step": 194
},
{
"epoch": 0.07393364928909953,
"grad_norm": 0.1897961050271988,
"learning_rate": 1.7077534966650766e-07,
"loss": 11.774,
"step": 195
},
{
"epoch": 0.0743127962085308,
"grad_norm": 0.16154845058918,
"learning_rate": 1.0931863906127327e-07,
"loss": 11.7702,
"step": 196
},
{
"epoch": 0.07469194312796208,
"grad_norm": 0.15937910974025726,
"learning_rate": 6.150154258476315e-08,
"loss": 11.7803,
"step": 197
},
{
"epoch": 0.07507109004739336,
"grad_norm": 0.212022602558136,
"learning_rate": 2.7337132953697554e-08,
"loss": 11.7682,
"step": 198
},
{
"epoch": 0.07545023696682464,
"grad_norm": 0.21921372413635254,
"learning_rate": 6.834750376549792e-09,
"loss": 11.7774,
"step": 199
},
{
"epoch": 0.07582938388625593,
"grad_norm": 0.2652130424976349,
"learning_rate": 0.0,
"loss": 11.7693,
"step": 200
},
{
"epoch": 0.07582938388625593,
"eval_loss": 11.789237976074219,
"eval_runtime": 43.9011,
"eval_samples_per_second": 101.182,
"eval_steps_per_second": 25.307,
"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": 226142650368000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}