aleegis09's picture
Training in progress, step 150, checkpoint
9028144 verified
raw
history blame
27.6 kB
{
"best_metric": 0.7515243291854858,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 1.6997167138810199,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0113314447592068,
"grad_norm": 1.563727617263794,
"learning_rate": 1e-05,
"loss": 1.0261,
"step": 1
},
{
"epoch": 0.0113314447592068,
"eval_loss": 1.1746464967727661,
"eval_runtime": 11.22,
"eval_samples_per_second": 13.28,
"eval_steps_per_second": 3.387,
"step": 1
},
{
"epoch": 0.0226628895184136,
"grad_norm": 1.7917308807373047,
"learning_rate": 2e-05,
"loss": 1.1102,
"step": 2
},
{
"epoch": 0.0339943342776204,
"grad_norm": 1.8879097700119019,
"learning_rate": 3e-05,
"loss": 1.1664,
"step": 3
},
{
"epoch": 0.0453257790368272,
"grad_norm": 1.5070877075195312,
"learning_rate": 4e-05,
"loss": 1.0808,
"step": 4
},
{
"epoch": 0.056657223796033995,
"grad_norm": 0.9339195489883423,
"learning_rate": 5e-05,
"loss": 1.0021,
"step": 5
},
{
"epoch": 0.0679886685552408,
"grad_norm": 0.5353918671607971,
"learning_rate": 6e-05,
"loss": 0.98,
"step": 6
},
{
"epoch": 0.07932011331444759,
"grad_norm": 0.8156968355178833,
"learning_rate": 7e-05,
"loss": 1.0042,
"step": 7
},
{
"epoch": 0.0906515580736544,
"grad_norm": 0.9624820947647095,
"learning_rate": 8e-05,
"loss": 1.0308,
"step": 8
},
{
"epoch": 0.10198300283286119,
"grad_norm": 0.6892203688621521,
"learning_rate": 9e-05,
"loss": 1.0353,
"step": 9
},
{
"epoch": 0.11331444759206799,
"grad_norm": 0.48928651213645935,
"learning_rate": 0.0001,
"loss": 0.9958,
"step": 10
},
{
"epoch": 0.12464589235127478,
"grad_norm": 0.39077329635620117,
"learning_rate": 9.999316524962345e-05,
"loss": 0.9503,
"step": 11
},
{
"epoch": 0.1359773371104816,
"grad_norm": 0.4778994023799896,
"learning_rate": 9.997266286704631e-05,
"loss": 0.9703,
"step": 12
},
{
"epoch": 0.14730878186968838,
"grad_norm": 0.41578197479248047,
"learning_rate": 9.993849845741524e-05,
"loss": 0.9858,
"step": 13
},
{
"epoch": 0.15864022662889518,
"grad_norm": 0.41157615184783936,
"learning_rate": 9.989068136093873e-05,
"loss": 0.9649,
"step": 14
},
{
"epoch": 0.16997167138810199,
"grad_norm": 0.38007310032844543,
"learning_rate": 9.98292246503335e-05,
"loss": 1.0135,
"step": 15
},
{
"epoch": 0.1813031161473088,
"grad_norm": 0.3699261546134949,
"learning_rate": 9.975414512725057e-05,
"loss": 0.9667,
"step": 16
},
{
"epoch": 0.19263456090651557,
"grad_norm": 0.3545251786708832,
"learning_rate": 9.966546331768191e-05,
"loss": 0.9615,
"step": 17
},
{
"epoch": 0.20396600566572237,
"grad_norm": 0.33160850405693054,
"learning_rate": 9.956320346634876e-05,
"loss": 0.9618,
"step": 18
},
{
"epoch": 0.21529745042492918,
"grad_norm": 0.368289053440094,
"learning_rate": 9.944739353007344e-05,
"loss": 0.9773,
"step": 19
},
{
"epoch": 0.22662889518413598,
"grad_norm": 0.4142683744430542,
"learning_rate": 9.931806517013612e-05,
"loss": 1.0223,
"step": 20
},
{
"epoch": 0.23796033994334279,
"grad_norm": 0.47428715229034424,
"learning_rate": 9.917525374361912e-05,
"loss": 0.8783,
"step": 21
},
{
"epoch": 0.24929178470254956,
"grad_norm": 1.1350836753845215,
"learning_rate": 9.901899829374047e-05,
"loss": 0.9089,
"step": 22
},
{
"epoch": 0.26062322946175637,
"grad_norm": 0.37484070658683777,
"learning_rate": 9.884934153917997e-05,
"loss": 0.8662,
"step": 23
},
{
"epoch": 0.2719546742209632,
"grad_norm": 0.3438847064971924,
"learning_rate": 9.86663298624003e-05,
"loss": 0.8656,
"step": 24
},
{
"epoch": 0.28328611898017,
"grad_norm": 0.3542642891407013,
"learning_rate": 9.847001329696653e-05,
"loss": 0.9382,
"step": 25
},
{
"epoch": 0.29461756373937675,
"grad_norm": 0.3508148789405823,
"learning_rate": 9.826044551386744e-05,
"loss": 0.9103,
"step": 26
},
{
"epoch": 0.3059490084985836,
"grad_norm": 0.30817940831184387,
"learning_rate": 9.803768380684242e-05,
"loss": 0.8448,
"step": 27
},
{
"epoch": 0.31728045325779036,
"grad_norm": 0.31299149990081787,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9199,
"step": 28
},
{
"epoch": 0.3286118980169972,
"grad_norm": 0.3173774480819702,
"learning_rate": 9.755282581475769e-05,
"loss": 0.8998,
"step": 29
},
{
"epoch": 0.33994334277620397,
"grad_norm": 0.3080953359603882,
"learning_rate": 9.729086208503174e-05,
"loss": 0.8661,
"step": 30
},
{
"epoch": 0.35127478753541075,
"grad_norm": 0.3002243638038635,
"learning_rate": 9.701596950580806e-05,
"loss": 0.9511,
"step": 31
},
{
"epoch": 0.3626062322946176,
"grad_norm": 0.28299739956855774,
"learning_rate": 9.672822322997305e-05,
"loss": 0.8999,
"step": 32
},
{
"epoch": 0.37393767705382436,
"grad_norm": 0.2916186451911926,
"learning_rate": 9.642770192448536e-05,
"loss": 0.9375,
"step": 33
},
{
"epoch": 0.38526912181303113,
"grad_norm": 0.3146689832210541,
"learning_rate": 9.611448774886924e-05,
"loss": 0.9356,
"step": 34
},
{
"epoch": 0.39660056657223797,
"grad_norm": 0.31491371989250183,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9132,
"step": 35
},
{
"epoch": 0.40793201133144474,
"grad_norm": 0.29938894510269165,
"learning_rate": 9.545032675245813e-05,
"loss": 0.893,
"step": 36
},
{
"epoch": 0.4192634560906516,
"grad_norm": 0.302477091550827,
"learning_rate": 9.509956150664796e-05,
"loss": 0.9585,
"step": 37
},
{
"epoch": 0.43059490084985835,
"grad_norm": 0.304225891828537,
"learning_rate": 9.473646649103818e-05,
"loss": 0.9361,
"step": 38
},
{
"epoch": 0.44192634560906513,
"grad_norm": 0.29993778467178345,
"learning_rate": 9.43611409721806e-05,
"loss": 0.8889,
"step": 39
},
{
"epoch": 0.45325779036827196,
"grad_norm": 0.33078035712242126,
"learning_rate": 9.397368756032445e-05,
"loss": 0.8862,
"step": 40
},
{
"epoch": 0.46458923512747874,
"grad_norm": 0.31899866461753845,
"learning_rate": 9.357421218136386e-05,
"loss": 0.881,
"step": 41
},
{
"epoch": 0.47592067988668557,
"grad_norm": 0.3168673813343048,
"learning_rate": 9.316282404787871e-05,
"loss": 0.8917,
"step": 42
},
{
"epoch": 0.48725212464589235,
"grad_norm": 0.3915148079395294,
"learning_rate": 9.273963562927695e-05,
"loss": 0.9215,
"step": 43
},
{
"epoch": 0.4985835694050991,
"grad_norm": 1.4946476221084595,
"learning_rate": 9.230476262104677e-05,
"loss": 0.5584,
"step": 44
},
{
"epoch": 0.509915014164306,
"grad_norm": 0.2577565610408783,
"learning_rate": 9.185832391312644e-05,
"loss": 0.7591,
"step": 45
},
{
"epoch": 0.5212464589235127,
"grad_norm": 0.27161210775375366,
"learning_rate": 9.140044155740101e-05,
"loss": 0.8675,
"step": 46
},
{
"epoch": 0.5325779036827195,
"grad_norm": 0.2780570089817047,
"learning_rate": 9.093124073433463e-05,
"loss": 0.8676,
"step": 47
},
{
"epoch": 0.5439093484419264,
"grad_norm": 0.263107568025589,
"learning_rate": 9.045084971874738e-05,
"loss": 0.8697,
"step": 48
},
{
"epoch": 0.5552407932011332,
"grad_norm": 0.2887552082538605,
"learning_rate": 8.995939984474624e-05,
"loss": 0.891,
"step": 49
},
{
"epoch": 0.56657223796034,
"grad_norm": 0.2745039761066437,
"learning_rate": 8.945702546981969e-05,
"loss": 0.8519,
"step": 50
},
{
"epoch": 0.56657223796034,
"eval_loss": 0.8684490919113159,
"eval_runtime": 11.428,
"eval_samples_per_second": 13.038,
"eval_steps_per_second": 3.325,
"step": 50
},
{
"epoch": 0.5779036827195467,
"grad_norm": 0.2893388867378235,
"learning_rate": 8.894386393810563e-05,
"loss": 0.844,
"step": 51
},
{
"epoch": 0.5892351274787535,
"grad_norm": 0.2875760495662689,
"learning_rate": 8.842005554284296e-05,
"loss": 0.903,
"step": 52
},
{
"epoch": 0.6005665722379604,
"grad_norm": 0.27715393900871277,
"learning_rate": 8.788574348801675e-05,
"loss": 0.9204,
"step": 53
},
{
"epoch": 0.6118980169971672,
"grad_norm": 0.26955386996269226,
"learning_rate": 8.73410738492077e-05,
"loss": 0.8777,
"step": 54
},
{
"epoch": 0.623229461756374,
"grad_norm": 0.2984619736671448,
"learning_rate": 8.678619553365659e-05,
"loss": 0.8642,
"step": 55
},
{
"epoch": 0.6345609065155807,
"grad_norm": 0.2795373797416687,
"learning_rate": 8.622126023955446e-05,
"loss": 0.8738,
"step": 56
},
{
"epoch": 0.6458923512747875,
"grad_norm": 0.28245463967323303,
"learning_rate": 8.564642241456986e-05,
"loss": 0.869,
"step": 57
},
{
"epoch": 0.6572237960339944,
"grad_norm": 0.2853794991970062,
"learning_rate": 8.506183921362443e-05,
"loss": 0.8579,
"step": 58
},
{
"epoch": 0.6685552407932012,
"grad_norm": 0.28548476099967957,
"learning_rate": 8.44676704559283e-05,
"loss": 0.8918,
"step": 59
},
{
"epoch": 0.6798866855524079,
"grad_norm": 0.29240891337394714,
"learning_rate": 8.386407858128706e-05,
"loss": 0.8751,
"step": 60
},
{
"epoch": 0.6912181303116147,
"grad_norm": 0.2984645962715149,
"learning_rate": 8.32512286056924e-05,
"loss": 0.9003,
"step": 61
},
{
"epoch": 0.7025495750708215,
"grad_norm": 0.3319612443447113,
"learning_rate": 8.262928807620843e-05,
"loss": 0.9274,
"step": 62
},
{
"epoch": 0.7138810198300283,
"grad_norm": 0.355567991733551,
"learning_rate": 8.199842702516583e-05,
"loss": 0.8746,
"step": 63
},
{
"epoch": 0.7252124645892352,
"grad_norm": 0.32513099908828735,
"learning_rate": 8.135881792367686e-05,
"loss": 0.8737,
"step": 64
},
{
"epoch": 0.7365439093484419,
"grad_norm": 0.3675692677497864,
"learning_rate": 8.07106356344834e-05,
"loss": 0.88,
"step": 65
},
{
"epoch": 0.7478753541076487,
"grad_norm": 0.7361142635345459,
"learning_rate": 8.005405736415126e-05,
"loss": 0.9353,
"step": 66
},
{
"epoch": 0.7592067988668555,
"grad_norm": 0.3202268183231354,
"learning_rate": 7.938926261462366e-05,
"loss": 0.8416,
"step": 67
},
{
"epoch": 0.7705382436260623,
"grad_norm": 0.3057731091976166,
"learning_rate": 7.871643313414718e-05,
"loss": 0.8207,
"step": 68
},
{
"epoch": 0.7818696883852692,
"grad_norm": 0.29968634247779846,
"learning_rate": 7.803575286758364e-05,
"loss": 0.8556,
"step": 69
},
{
"epoch": 0.7932011331444759,
"grad_norm": 0.2880346477031708,
"learning_rate": 7.734740790612136e-05,
"loss": 0.8181,
"step": 70
},
{
"epoch": 0.8045325779036827,
"grad_norm": 0.29776275157928467,
"learning_rate": 7.66515864363997e-05,
"loss": 0.8898,
"step": 71
},
{
"epoch": 0.8158640226628895,
"grad_norm": 0.2974025011062622,
"learning_rate": 7.594847868906076e-05,
"loss": 0.8094,
"step": 72
},
{
"epoch": 0.8271954674220963,
"grad_norm": 0.2973535358905792,
"learning_rate": 7.52382768867422e-05,
"loss": 0.8292,
"step": 73
},
{
"epoch": 0.8385269121813032,
"grad_norm": 0.2857825756072998,
"learning_rate": 7.452117519152542e-05,
"loss": 0.8457,
"step": 74
},
{
"epoch": 0.8498583569405099,
"grad_norm": 0.2873602509498596,
"learning_rate": 7.379736965185368e-05,
"loss": 0.8835,
"step": 75
},
{
"epoch": 0.8611898016997167,
"grad_norm": 0.2918296456336975,
"learning_rate": 7.30670581489344e-05,
"loss": 0.8375,
"step": 76
},
{
"epoch": 0.8725212464589235,
"grad_norm": 0.2822003662586212,
"learning_rate": 7.233044034264034e-05,
"loss": 0.8625,
"step": 77
},
{
"epoch": 0.8838526912181303,
"grad_norm": 0.2973242998123169,
"learning_rate": 7.158771761692464e-05,
"loss": 0.8737,
"step": 78
},
{
"epoch": 0.8951841359773371,
"grad_norm": 0.29444533586502075,
"learning_rate": 7.083909302476453e-05,
"loss": 0.8341,
"step": 79
},
{
"epoch": 0.9065155807365439,
"grad_norm": 0.29816219210624695,
"learning_rate": 7.008477123264848e-05,
"loss": 0.8417,
"step": 80
},
{
"epoch": 0.9178470254957507,
"grad_norm": 0.29705649614334106,
"learning_rate": 6.932495846462261e-05,
"loss": 0.8601,
"step": 81
},
{
"epoch": 0.9291784702549575,
"grad_norm": 0.3126617968082428,
"learning_rate": 6.855986244591104e-05,
"loss": 0.8669,
"step": 82
},
{
"epoch": 0.9405099150141643,
"grad_norm": 0.32415011525154114,
"learning_rate": 6.778969234612584e-05,
"loss": 0.8647,
"step": 83
},
{
"epoch": 0.9518413597733711,
"grad_norm": 0.317557692527771,
"learning_rate": 6.701465872208216e-05,
"loss": 0.8415,
"step": 84
},
{
"epoch": 0.9631728045325779,
"grad_norm": 0.36104077100753784,
"learning_rate": 6.623497346023418e-05,
"loss": 0.7996,
"step": 85
},
{
"epoch": 0.9745042492917847,
"grad_norm": 0.3510071635246277,
"learning_rate": 6.545084971874738e-05,
"loss": 0.8511,
"step": 86
},
{
"epoch": 0.9858356940509915,
"grad_norm": 0.3717744052410126,
"learning_rate": 6.466250186922325e-05,
"loss": 0.7375,
"step": 87
},
{
"epoch": 0.9971671388101983,
"grad_norm": 0.735817551612854,
"learning_rate": 6.387014543809223e-05,
"loss": 0.6304,
"step": 88
},
{
"epoch": 1.0084985835694051,
"grad_norm": 0.6571866273880005,
"learning_rate": 6.307399704769099e-05,
"loss": 1.3475,
"step": 89
},
{
"epoch": 1.019830028328612,
"grad_norm": 0.2599029242992401,
"learning_rate": 6.227427435703997e-05,
"loss": 0.7176,
"step": 90
},
{
"epoch": 1.0311614730878187,
"grad_norm": 0.2709405720233917,
"learning_rate": 6.147119600233758e-05,
"loss": 0.7737,
"step": 91
},
{
"epoch": 1.0424929178470255,
"grad_norm": 0.2753128409385681,
"learning_rate": 6.066498153718735e-05,
"loss": 0.7402,
"step": 92
},
{
"epoch": 1.0538243626062322,
"grad_norm": 0.2703261375427246,
"learning_rate": 5.985585137257401e-05,
"loss": 0.7564,
"step": 93
},
{
"epoch": 1.065155807365439,
"grad_norm": 0.29065266251564026,
"learning_rate": 5.90440267166055e-05,
"loss": 0.7662,
"step": 94
},
{
"epoch": 1.0764872521246458,
"grad_norm": 0.3075530230998993,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.7171,
"step": 95
},
{
"epoch": 1.0878186968838528,
"grad_norm": 0.28683334589004517,
"learning_rate": 5.74131823855921e-05,
"loss": 0.7185,
"step": 96
},
{
"epoch": 1.0991501416430596,
"grad_norm": 0.2910711467266083,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.7349,
"step": 97
},
{
"epoch": 1.1104815864022664,
"grad_norm": 0.2993939220905304,
"learning_rate": 5.577423184847932e-05,
"loss": 0.6895,
"step": 98
},
{
"epoch": 1.1218130311614731,
"grad_norm": 0.31023624539375305,
"learning_rate": 5.495227651252315e-05,
"loss": 0.7225,
"step": 99
},
{
"epoch": 1.13314447592068,
"grad_norm": 0.32338133454322815,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.7458,
"step": 100
},
{
"epoch": 1.13314447592068,
"eval_loss": 0.8006256818771362,
"eval_runtime": 11.4274,
"eval_samples_per_second": 13.039,
"eval_steps_per_second": 3.325,
"step": 100
},
{
"epoch": 1.1444759206798867,
"grad_norm": 0.31149691343307495,
"learning_rate": 5.330452921628497e-05,
"loss": 0.6993,
"step": 101
},
{
"epoch": 1.1558073654390935,
"grad_norm": 0.31584376096725464,
"learning_rate": 5.247918773366112e-05,
"loss": 0.7272,
"step": 102
},
{
"epoch": 1.1671388101983002,
"grad_norm": 0.33238154649734497,
"learning_rate": 5.165316846586541e-05,
"loss": 0.7262,
"step": 103
},
{
"epoch": 1.178470254957507,
"grad_norm": 0.34204113483428955,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.7337,
"step": 104
},
{
"epoch": 1.1898016997167138,
"grad_norm": 0.3630761504173279,
"learning_rate": 5e-05,
"loss": 0.748,
"step": 105
},
{
"epoch": 1.2011331444759206,
"grad_norm": 0.3507816791534424,
"learning_rate": 4.917330276168208e-05,
"loss": 0.6793,
"step": 106
},
{
"epoch": 1.2124645892351276,
"grad_norm": 0.40318283438682556,
"learning_rate": 4.834683153413459e-05,
"loss": 0.7535,
"step": 107
},
{
"epoch": 1.2237960339943343,
"grad_norm": 0.4211021065711975,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.7193,
"step": 108
},
{
"epoch": 1.2351274787535411,
"grad_norm": 0.4252460300922394,
"learning_rate": 4.669547078371504e-05,
"loss": 0.7051,
"step": 109
},
{
"epoch": 1.246458923512748,
"grad_norm": 0.6195134520530701,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.6238,
"step": 110
},
{
"epoch": 1.2577903682719547,
"grad_norm": 0.3660491704940796,
"learning_rate": 4.504772348747687e-05,
"loss": 0.5634,
"step": 111
},
{
"epoch": 1.2691218130311614,
"grad_norm": 0.46309658885002136,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.7133,
"step": 112
},
{
"epoch": 1.2804532577903682,
"grad_norm": 0.39401277899742126,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.716,
"step": 113
},
{
"epoch": 1.291784702549575,
"grad_norm": 0.37151670455932617,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.7727,
"step": 114
},
{
"epoch": 1.3031161473087818,
"grad_norm": 0.3559165596961975,
"learning_rate": 4.17702704859633e-05,
"loss": 0.7659,
"step": 115
},
{
"epoch": 1.3144475920679888,
"grad_norm": 0.3626144230365753,
"learning_rate": 4.095597328339452e-05,
"loss": 0.7037,
"step": 116
},
{
"epoch": 1.3257790368271953,
"grad_norm": 0.3644079566001892,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.6993,
"step": 117
},
{
"epoch": 1.3371104815864023,
"grad_norm": 0.37085551023483276,
"learning_rate": 3.933501846281267e-05,
"loss": 0.7115,
"step": 118
},
{
"epoch": 1.348441926345609,
"grad_norm": 0.3566945195198059,
"learning_rate": 3.852880399766243e-05,
"loss": 0.7249,
"step": 119
},
{
"epoch": 1.3597733711048159,
"grad_norm": 0.3588652014732361,
"learning_rate": 3.772572564296005e-05,
"loss": 0.7622,
"step": 120
},
{
"epoch": 1.3711048158640227,
"grad_norm": 0.34322044253349304,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.677,
"step": 121
},
{
"epoch": 1.3824362606232294,
"grad_norm": 0.35693424940109253,
"learning_rate": 3.612985456190778e-05,
"loss": 0.7196,
"step": 122
},
{
"epoch": 1.3937677053824362,
"grad_norm": 0.3655772805213928,
"learning_rate": 3.533749813077677e-05,
"loss": 0.7097,
"step": 123
},
{
"epoch": 1.405099150141643,
"grad_norm": 0.3697783052921295,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.7266,
"step": 124
},
{
"epoch": 1.41643059490085,
"grad_norm": 0.355410635471344,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.676,
"step": 125
},
{
"epoch": 1.4277620396600565,
"grad_norm": 0.3988121449947357,
"learning_rate": 3.298534127791785e-05,
"loss": 0.7216,
"step": 126
},
{
"epoch": 1.4390934844192635,
"grad_norm": 0.4042431116104126,
"learning_rate": 3.221030765387417e-05,
"loss": 0.6971,
"step": 127
},
{
"epoch": 1.4504249291784703,
"grad_norm": 0.3926319181919098,
"learning_rate": 3.144013755408895e-05,
"loss": 0.6643,
"step": 128
},
{
"epoch": 1.461756373937677,
"grad_norm": 0.4321343004703522,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.6273,
"step": 129
},
{
"epoch": 1.4730878186968839,
"grad_norm": 0.48049649596214294,
"learning_rate": 2.991522876735154e-05,
"loss": 0.5886,
"step": 130
},
{
"epoch": 1.4844192634560907,
"grad_norm": 0.4928465783596039,
"learning_rate": 2.916090697523549e-05,
"loss": 0.5801,
"step": 131
},
{
"epoch": 1.4957507082152974,
"grad_norm": 0.7852864265441895,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.4474,
"step": 132
},
{
"epoch": 1.5070821529745042,
"grad_norm": 0.3517076075077057,
"learning_rate": 2.766955965735968e-05,
"loss": 0.5221,
"step": 133
},
{
"epoch": 1.5184135977337112,
"grad_norm": 0.43520981073379517,
"learning_rate": 2.693294185106562e-05,
"loss": 0.6602,
"step": 134
},
{
"epoch": 1.5297450424929178,
"grad_norm": 0.5653157234191895,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.7331,
"step": 135
},
{
"epoch": 1.5410764872521248,
"grad_norm": 0.45808669924736023,
"learning_rate": 2.547882480847461e-05,
"loss": 0.692,
"step": 136
},
{
"epoch": 1.5524079320113313,
"grad_norm": 0.3955627977848053,
"learning_rate": 2.476172311325783e-05,
"loss": 0.6531,
"step": 137
},
{
"epoch": 1.5637393767705383,
"grad_norm": 0.40485164523124695,
"learning_rate": 2.405152131093926e-05,
"loss": 0.6694,
"step": 138
},
{
"epoch": 1.575070821529745,
"grad_norm": 0.40561431646347046,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.7055,
"step": 139
},
{
"epoch": 1.5864022662889519,
"grad_norm": 0.3729764223098755,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.6782,
"step": 140
},
{
"epoch": 1.5977337110481586,
"grad_norm": 0.38850530982017517,
"learning_rate": 2.196424713241637e-05,
"loss": 0.7543,
"step": 141
},
{
"epoch": 1.6090651558073654,
"grad_norm": 0.37639227509498596,
"learning_rate": 2.128356686585282e-05,
"loss": 0.6859,
"step": 142
},
{
"epoch": 1.6203966005665722,
"grad_norm": 0.3915426731109619,
"learning_rate": 2.061073738537635e-05,
"loss": 0.6985,
"step": 143
},
{
"epoch": 1.631728045325779,
"grad_norm": 0.3907557725906372,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.6392,
"step": 144
},
{
"epoch": 1.643059490084986,
"grad_norm": 0.37761691212654114,
"learning_rate": 1.928936436551661e-05,
"loss": 0.6814,
"step": 145
},
{
"epoch": 1.6543909348441925,
"grad_norm": 0.38431620597839355,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.6704,
"step": 146
},
{
"epoch": 1.6657223796033995,
"grad_norm": 0.38361120223999023,
"learning_rate": 1.800157297483417e-05,
"loss": 0.6842,
"step": 147
},
{
"epoch": 1.677053824362606,
"grad_norm": 0.39874064922332764,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.6795,
"step": 148
},
{
"epoch": 1.688385269121813,
"grad_norm": 0.40643274784088135,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.6898,
"step": 149
},
{
"epoch": 1.6997167138810199,
"grad_norm": 0.4098912179470062,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.6418,
"step": 150
},
{
"epoch": 1.6997167138810199,
"eval_loss": 0.7515243291854858,
"eval_runtime": 11.4029,
"eval_samples_per_second": 13.067,
"eval_steps_per_second": 3.332,
"step": 150
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": false
},
"attributes": {}
}
},
"total_flos": 2.27361280946602e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}