ancient41's picture
Training in progress, step 150, checkpoint
48fdad7 verified
raw
history blame
28 kB
{
"best_metric": 10.325255393981934,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 0.09752925877763328,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006501950585175553,
"grad_norm": 0.16346317529678345,
"learning_rate": 1e-05,
"loss": 10.3784,
"step": 1
},
{
"epoch": 0.0006501950585175553,
"eval_loss": 10.379300117492676,
"eval_runtime": 5.5894,
"eval_samples_per_second": 463.559,
"eval_steps_per_second": 115.935,
"step": 1
},
{
"epoch": 0.0013003901170351106,
"grad_norm": 0.16755619645118713,
"learning_rate": 2e-05,
"loss": 10.3821,
"step": 2
},
{
"epoch": 0.0019505851755526658,
"grad_norm": 0.13945528864860535,
"learning_rate": 3e-05,
"loss": 10.3833,
"step": 3
},
{
"epoch": 0.002600780234070221,
"grad_norm": 0.143163800239563,
"learning_rate": 4e-05,
"loss": 10.3795,
"step": 4
},
{
"epoch": 0.003250975292587776,
"grad_norm": 0.15274204313755035,
"learning_rate": 5e-05,
"loss": 10.3816,
"step": 5
},
{
"epoch": 0.0039011703511053317,
"grad_norm": 0.15133363008499146,
"learning_rate": 6e-05,
"loss": 10.3774,
"step": 6
},
{
"epoch": 0.004551365409622887,
"grad_norm": 0.1576792299747467,
"learning_rate": 7e-05,
"loss": 10.3812,
"step": 7
},
{
"epoch": 0.005201560468140442,
"grad_norm": 0.16241832077503204,
"learning_rate": 8e-05,
"loss": 10.3794,
"step": 8
},
{
"epoch": 0.005851755526657998,
"grad_norm": 0.158880814909935,
"learning_rate": 9e-05,
"loss": 10.3805,
"step": 9
},
{
"epoch": 0.006501950585175552,
"grad_norm": 0.17472630739212036,
"learning_rate": 0.0001,
"loss": 10.3759,
"step": 10
},
{
"epoch": 0.007152145643693108,
"grad_norm": 0.1583331823348999,
"learning_rate": 9.999316524962345e-05,
"loss": 10.375,
"step": 11
},
{
"epoch": 0.007802340702210663,
"grad_norm": 0.15915250778198242,
"learning_rate": 9.997266286704631e-05,
"loss": 10.374,
"step": 12
},
{
"epoch": 0.008452535760728219,
"grad_norm": 0.16115702688694,
"learning_rate": 9.993849845741524e-05,
"loss": 10.3716,
"step": 13
},
{
"epoch": 0.009102730819245773,
"grad_norm": 0.1993064135313034,
"learning_rate": 9.989068136093873e-05,
"loss": 10.3711,
"step": 14
},
{
"epoch": 0.00975292587776333,
"grad_norm": 0.21445228159427643,
"learning_rate": 9.98292246503335e-05,
"loss": 10.3703,
"step": 15
},
{
"epoch": 0.010403120936280884,
"grad_norm": 0.22083888947963715,
"learning_rate": 9.975414512725057e-05,
"loss": 10.3714,
"step": 16
},
{
"epoch": 0.011053315994798439,
"grad_norm": 0.2086634337902069,
"learning_rate": 9.966546331768191e-05,
"loss": 10.3664,
"step": 17
},
{
"epoch": 0.011703511053315995,
"grad_norm": 0.18963812291622162,
"learning_rate": 9.956320346634876e-05,
"loss": 10.3694,
"step": 18
},
{
"epoch": 0.01235370611183355,
"grad_norm": 0.21092309057712555,
"learning_rate": 9.944739353007344e-05,
"loss": 10.3626,
"step": 19
},
{
"epoch": 0.013003901170351105,
"grad_norm": 0.2150663137435913,
"learning_rate": 9.931806517013612e-05,
"loss": 10.359,
"step": 20
},
{
"epoch": 0.013654096228868661,
"grad_norm": 0.23642702400684357,
"learning_rate": 9.917525374361912e-05,
"loss": 10.3592,
"step": 21
},
{
"epoch": 0.014304291287386216,
"grad_norm": 0.2073623090982437,
"learning_rate": 9.901899829374047e-05,
"loss": 10.362,
"step": 22
},
{
"epoch": 0.01495448634590377,
"grad_norm": 0.23299622535705566,
"learning_rate": 9.884934153917997e-05,
"loss": 10.3571,
"step": 23
},
{
"epoch": 0.015604681404421327,
"grad_norm": 0.22607557475566864,
"learning_rate": 9.86663298624003e-05,
"loss": 10.3554,
"step": 24
},
{
"epoch": 0.016254876462938883,
"grad_norm": 0.2323736995458603,
"learning_rate": 9.847001329696653e-05,
"loss": 10.3501,
"step": 25
},
{
"epoch": 0.016905071521456438,
"grad_norm": 0.23286131024360657,
"learning_rate": 9.826044551386744e-05,
"loss": 10.356,
"step": 26
},
{
"epoch": 0.017555266579973992,
"grad_norm": 0.24602067470550537,
"learning_rate": 9.803768380684242e-05,
"loss": 10.3513,
"step": 27
},
{
"epoch": 0.018205461638491547,
"grad_norm": 0.2561459541320801,
"learning_rate": 9.780178907671789e-05,
"loss": 10.3461,
"step": 28
},
{
"epoch": 0.0188556566970091,
"grad_norm": 0.25998950004577637,
"learning_rate": 9.755282581475769e-05,
"loss": 10.3531,
"step": 29
},
{
"epoch": 0.01950585175552666,
"grad_norm": 0.25198736786842346,
"learning_rate": 9.729086208503174e-05,
"loss": 10.3477,
"step": 30
},
{
"epoch": 0.020156046814044214,
"grad_norm": 0.21755382418632507,
"learning_rate": 9.701596950580806e-05,
"loss": 10.3497,
"step": 31
},
{
"epoch": 0.02080624187256177,
"grad_norm": 0.20511659979820251,
"learning_rate": 9.672822322997305e-05,
"loss": 10.3505,
"step": 32
},
{
"epoch": 0.021456436931079324,
"grad_norm": 0.2415936142206192,
"learning_rate": 9.642770192448536e-05,
"loss": 10.3453,
"step": 33
},
{
"epoch": 0.022106631989596878,
"grad_norm": 0.2516171336174011,
"learning_rate": 9.611448774886924e-05,
"loss": 10.346,
"step": 34
},
{
"epoch": 0.022756827048114433,
"grad_norm": 0.1974753588438034,
"learning_rate": 9.578866633275288e-05,
"loss": 10.3481,
"step": 35
},
{
"epoch": 0.02340702210663199,
"grad_norm": 0.2604691684246063,
"learning_rate": 9.545032675245813e-05,
"loss": 10.3427,
"step": 36
},
{
"epoch": 0.024057217165149546,
"grad_norm": 0.25158172845840454,
"learning_rate": 9.509956150664796e-05,
"loss": 10.3348,
"step": 37
},
{
"epoch": 0.0247074122236671,
"grad_norm": 0.2360960692167282,
"learning_rate": 9.473646649103818e-05,
"loss": 10.3469,
"step": 38
},
{
"epoch": 0.025357607282184655,
"grad_norm": 0.23032498359680176,
"learning_rate": 9.43611409721806e-05,
"loss": 10.34,
"step": 39
},
{
"epoch": 0.02600780234070221,
"grad_norm": 0.2483445554971695,
"learning_rate": 9.397368756032445e-05,
"loss": 10.3397,
"step": 40
},
{
"epoch": 0.026657997399219768,
"grad_norm": 0.2806270718574524,
"learning_rate": 9.357421218136386e-05,
"loss": 10.3426,
"step": 41
},
{
"epoch": 0.027308192457737322,
"grad_norm": 0.2824419438838959,
"learning_rate": 9.316282404787871e-05,
"loss": 10.3438,
"step": 42
},
{
"epoch": 0.027958387516254877,
"grad_norm": 0.2967035472393036,
"learning_rate": 9.273963562927695e-05,
"loss": 10.3453,
"step": 43
},
{
"epoch": 0.02860858257477243,
"grad_norm": 0.32099294662475586,
"learning_rate": 9.230476262104677e-05,
"loss": 10.3459,
"step": 44
},
{
"epoch": 0.029258777633289986,
"grad_norm": 0.3763386011123657,
"learning_rate": 9.185832391312644e-05,
"loss": 10.3269,
"step": 45
},
{
"epoch": 0.02990897269180754,
"grad_norm": 0.35344579815864563,
"learning_rate": 9.140044155740101e-05,
"loss": 10.3263,
"step": 46
},
{
"epoch": 0.0305591677503251,
"grad_norm": 0.4409536123275757,
"learning_rate": 9.093124073433463e-05,
"loss": 10.3216,
"step": 47
},
{
"epoch": 0.031209362808842653,
"grad_norm": 0.4443815350532532,
"learning_rate": 9.045084971874738e-05,
"loss": 10.3193,
"step": 48
},
{
"epoch": 0.03185955786736021,
"grad_norm": 0.6149159073829651,
"learning_rate": 8.995939984474624e-05,
"loss": 10.31,
"step": 49
},
{
"epoch": 0.032509752925877766,
"grad_norm": 0.7020171284675598,
"learning_rate": 8.945702546981969e-05,
"loss": 10.3139,
"step": 50
},
{
"epoch": 0.032509752925877766,
"eval_loss": 10.332472801208496,
"eval_runtime": 5.5797,
"eval_samples_per_second": 464.364,
"eval_steps_per_second": 116.136,
"step": 50
},
{
"epoch": 0.03315994798439532,
"grad_norm": 0.1617739200592041,
"learning_rate": 8.894386393810563e-05,
"loss": 10.3382,
"step": 51
},
{
"epoch": 0.033810143042912875,
"grad_norm": 0.15137234330177307,
"learning_rate": 8.842005554284296e-05,
"loss": 10.3388,
"step": 52
},
{
"epoch": 0.03446033810143043,
"grad_norm": 0.16740497946739197,
"learning_rate": 8.788574348801675e-05,
"loss": 10.3361,
"step": 53
},
{
"epoch": 0.035110533159947985,
"grad_norm": 0.16936829686164856,
"learning_rate": 8.73410738492077e-05,
"loss": 10.3349,
"step": 54
},
{
"epoch": 0.03576072821846554,
"grad_norm": 0.163704976439476,
"learning_rate": 8.678619553365659e-05,
"loss": 10.3357,
"step": 55
},
{
"epoch": 0.036410923276983094,
"grad_norm": 0.15288466215133667,
"learning_rate": 8.622126023955446e-05,
"loss": 10.3383,
"step": 56
},
{
"epoch": 0.03706111833550065,
"grad_norm": 0.16119521856307983,
"learning_rate": 8.564642241456986e-05,
"loss": 10.3378,
"step": 57
},
{
"epoch": 0.0377113133940182,
"grad_norm": 0.16358798742294312,
"learning_rate": 8.506183921362443e-05,
"loss": 10.3376,
"step": 58
},
{
"epoch": 0.03836150845253576,
"grad_norm": 0.1631506383419037,
"learning_rate": 8.44676704559283e-05,
"loss": 10.3348,
"step": 59
},
{
"epoch": 0.03901170351105332,
"grad_norm": 0.14433640241622925,
"learning_rate": 8.386407858128706e-05,
"loss": 10.3391,
"step": 60
},
{
"epoch": 0.03966189856957087,
"grad_norm": 0.1398957520723343,
"learning_rate": 8.32512286056924e-05,
"loss": 10.3326,
"step": 61
},
{
"epoch": 0.04031209362808843,
"grad_norm": 0.14255324006080627,
"learning_rate": 8.262928807620843e-05,
"loss": 10.3356,
"step": 62
},
{
"epoch": 0.04096228868660598,
"grad_norm": 0.14317190647125244,
"learning_rate": 8.199842702516583e-05,
"loss": 10.3308,
"step": 63
},
{
"epoch": 0.04161248374512354,
"grad_norm": 0.1559898555278778,
"learning_rate": 8.135881792367686e-05,
"loss": 10.3306,
"step": 64
},
{
"epoch": 0.04226267880364109,
"grad_norm": 0.12277127802371979,
"learning_rate": 8.07106356344834e-05,
"loss": 10.3363,
"step": 65
},
{
"epoch": 0.04291287386215865,
"grad_norm": 0.15871265530586243,
"learning_rate": 8.005405736415126e-05,
"loss": 10.3315,
"step": 66
},
{
"epoch": 0.043563068920676205,
"grad_norm": 0.12418786436319351,
"learning_rate": 7.938926261462366e-05,
"loss": 10.3282,
"step": 67
},
{
"epoch": 0.044213263979193757,
"grad_norm": 0.11996562778949738,
"learning_rate": 7.871643313414718e-05,
"loss": 10.3349,
"step": 68
},
{
"epoch": 0.044863459037711315,
"grad_norm": 0.11101393401622772,
"learning_rate": 7.803575286758364e-05,
"loss": 10.3365,
"step": 69
},
{
"epoch": 0.045513654096228866,
"grad_norm": 0.12501025199890137,
"learning_rate": 7.734740790612136e-05,
"loss": 10.335,
"step": 70
},
{
"epoch": 0.046163849154746424,
"grad_norm": 0.08429504930973053,
"learning_rate": 7.66515864363997e-05,
"loss": 10.3364,
"step": 71
},
{
"epoch": 0.04681404421326398,
"grad_norm": 0.10076665133237839,
"learning_rate": 7.594847868906076e-05,
"loss": 10.3345,
"step": 72
},
{
"epoch": 0.04746423927178153,
"grad_norm": 0.10460986942052841,
"learning_rate": 7.52382768867422e-05,
"loss": 10.3301,
"step": 73
},
{
"epoch": 0.04811443433029909,
"grad_norm": 0.09893473237752914,
"learning_rate": 7.452117519152542e-05,
"loss": 10.3357,
"step": 74
},
{
"epoch": 0.04876462938881664,
"grad_norm": 0.10728178173303604,
"learning_rate": 7.379736965185368e-05,
"loss": 10.332,
"step": 75
},
{
"epoch": 0.0494148244473342,
"grad_norm": 0.11523190885782242,
"learning_rate": 7.30670581489344e-05,
"loss": 10.3292,
"step": 76
},
{
"epoch": 0.05006501950585176,
"grad_norm": 0.0974254235625267,
"learning_rate": 7.233044034264034e-05,
"loss": 10.3351,
"step": 77
},
{
"epoch": 0.05071521456436931,
"grad_norm": 0.09802504628896713,
"learning_rate": 7.158771761692464e-05,
"loss": 10.3317,
"step": 78
},
{
"epoch": 0.05136540962288687,
"grad_norm": 0.092984639108181,
"learning_rate": 7.083909302476453e-05,
"loss": 10.3316,
"step": 79
},
{
"epoch": 0.05201560468140442,
"grad_norm": 0.16028176248073578,
"learning_rate": 7.008477123264848e-05,
"loss": 10.3247,
"step": 80
},
{
"epoch": 0.05266579973992198,
"grad_norm": 0.1374354213476181,
"learning_rate": 6.932495846462261e-05,
"loss": 10.3259,
"step": 81
},
{
"epoch": 0.053315994798439535,
"grad_norm": 0.14670050144195557,
"learning_rate": 6.855986244591104e-05,
"loss": 10.3247,
"step": 82
},
{
"epoch": 0.053966189856957086,
"grad_norm": 0.0978398248553276,
"learning_rate": 6.778969234612584e-05,
"loss": 10.3281,
"step": 83
},
{
"epoch": 0.054616384915474644,
"grad_norm": 0.09942269325256348,
"learning_rate": 6.701465872208216e-05,
"loss": 10.3378,
"step": 84
},
{
"epoch": 0.055266579973992196,
"grad_norm": 0.167091965675354,
"learning_rate": 6.623497346023418e-05,
"loss": 10.3373,
"step": 85
},
{
"epoch": 0.055916775032509754,
"grad_norm": 0.09370499104261398,
"learning_rate": 6.545084971874738e-05,
"loss": 10.3259,
"step": 86
},
{
"epoch": 0.056566970091027305,
"grad_norm": 0.1366993486881256,
"learning_rate": 6.466250186922325e-05,
"loss": 10.3342,
"step": 87
},
{
"epoch": 0.05721716514954486,
"grad_norm": 0.10995159298181534,
"learning_rate": 6.387014543809223e-05,
"loss": 10.3262,
"step": 88
},
{
"epoch": 0.05786736020806242,
"grad_norm": 0.15136249363422394,
"learning_rate": 6.307399704769099e-05,
"loss": 10.3345,
"step": 89
},
{
"epoch": 0.05851755526657997,
"grad_norm": 0.1419341266155243,
"learning_rate": 6.227427435703997e-05,
"loss": 10.3333,
"step": 90
},
{
"epoch": 0.05916775032509753,
"grad_norm": 0.1429876685142517,
"learning_rate": 6.147119600233758e-05,
"loss": 10.3223,
"step": 91
},
{
"epoch": 0.05981794538361508,
"grad_norm": 0.17432060837745667,
"learning_rate": 6.066498153718735e-05,
"loss": 10.3292,
"step": 92
},
{
"epoch": 0.06046814044213264,
"grad_norm": 0.25426992774009705,
"learning_rate": 5.985585137257401e-05,
"loss": 10.3214,
"step": 93
},
{
"epoch": 0.0611183355006502,
"grad_norm": 0.2577574551105499,
"learning_rate": 5.90440267166055e-05,
"loss": 10.3246,
"step": 94
},
{
"epoch": 0.06176853055916775,
"grad_norm": 0.2434469610452652,
"learning_rate": 5.8229729514036705e-05,
"loss": 10.324,
"step": 95
},
{
"epoch": 0.06241872561768531,
"grad_norm": 0.39230114221572876,
"learning_rate": 5.74131823855921e-05,
"loss": 10.314,
"step": 96
},
{
"epoch": 0.06306892067620286,
"grad_norm": 0.3213576376438141,
"learning_rate": 5.6594608567103456e-05,
"loss": 10.3102,
"step": 97
},
{
"epoch": 0.06371911573472042,
"grad_norm": 0.3435070812702179,
"learning_rate": 5.577423184847932e-05,
"loss": 10.3174,
"step": 98
},
{
"epoch": 0.06436931079323797,
"grad_norm": 0.43636587262153625,
"learning_rate": 5.495227651252315e-05,
"loss": 10.3166,
"step": 99
},
{
"epoch": 0.06501950585175553,
"grad_norm": 0.5642738938331604,
"learning_rate": 5.4128967273616625e-05,
"loss": 10.2996,
"step": 100
},
{
"epoch": 0.06501950585175553,
"eval_loss": 10.327905654907227,
"eval_runtime": 5.584,
"eval_samples_per_second": 464.007,
"eval_steps_per_second": 116.046,
"step": 100
},
{
"epoch": 0.06566970091027308,
"grad_norm": 0.14702510833740234,
"learning_rate": 5.330452921628497e-05,
"loss": 10.3337,
"step": 101
},
{
"epoch": 0.06631989596879063,
"grad_norm": 0.12457651644945145,
"learning_rate": 5.247918773366112e-05,
"loss": 10.3339,
"step": 102
},
{
"epoch": 0.06697009102730819,
"grad_norm": 0.1211831346154213,
"learning_rate": 5.165316846586541e-05,
"loss": 10.3315,
"step": 103
},
{
"epoch": 0.06762028608582575,
"grad_norm": 0.12895992398262024,
"learning_rate": 5.0826697238317935e-05,
"loss": 10.3308,
"step": 104
},
{
"epoch": 0.06827048114434331,
"grad_norm": 0.1148681566119194,
"learning_rate": 5e-05,
"loss": 10.3314,
"step": 105
},
{
"epoch": 0.06892067620286085,
"grad_norm": 0.12179314345121384,
"learning_rate": 4.917330276168208e-05,
"loss": 10.3326,
"step": 106
},
{
"epoch": 0.06957087126137841,
"grad_norm": 0.13260143995285034,
"learning_rate": 4.834683153413459e-05,
"loss": 10.3289,
"step": 107
},
{
"epoch": 0.07022106631989597,
"grad_norm": 0.107021763920784,
"learning_rate": 4.7520812266338885e-05,
"loss": 10.3325,
"step": 108
},
{
"epoch": 0.07087126137841353,
"grad_norm": 0.11854235827922821,
"learning_rate": 4.669547078371504e-05,
"loss": 10.3314,
"step": 109
},
{
"epoch": 0.07152145643693109,
"grad_norm": 0.12161704897880554,
"learning_rate": 4.5871032726383386e-05,
"loss": 10.3282,
"step": 110
},
{
"epoch": 0.07217165149544863,
"grad_norm": 0.15688025951385498,
"learning_rate": 4.504772348747687e-05,
"loss": 10.3325,
"step": 111
},
{
"epoch": 0.07282184655396619,
"grad_norm": 0.11931723356246948,
"learning_rate": 4.4225768151520694e-05,
"loss": 10.3291,
"step": 112
},
{
"epoch": 0.07347204161248375,
"grad_norm": 0.12152872234582901,
"learning_rate": 4.3405391432896555e-05,
"loss": 10.3266,
"step": 113
},
{
"epoch": 0.0741222366710013,
"grad_norm": 0.09103374928236008,
"learning_rate": 4.2586817614407895e-05,
"loss": 10.3297,
"step": 114
},
{
"epoch": 0.07477243172951886,
"grad_norm": 0.10488580912351608,
"learning_rate": 4.17702704859633e-05,
"loss": 10.3322,
"step": 115
},
{
"epoch": 0.0754226267880364,
"grad_norm": 0.10290385782718658,
"learning_rate": 4.095597328339452e-05,
"loss": 10.3267,
"step": 116
},
{
"epoch": 0.07607282184655396,
"grad_norm": 0.12015118449926376,
"learning_rate": 4.0144148627425993e-05,
"loss": 10.3262,
"step": 117
},
{
"epoch": 0.07672301690507152,
"grad_norm": 0.10647259652614594,
"learning_rate": 3.933501846281267e-05,
"loss": 10.333,
"step": 118
},
{
"epoch": 0.07737321196358908,
"grad_norm": 0.08933848142623901,
"learning_rate": 3.852880399766243e-05,
"loss": 10.3309,
"step": 119
},
{
"epoch": 0.07802340702210664,
"grad_norm": 0.08935253322124481,
"learning_rate": 3.772572564296005e-05,
"loss": 10.3286,
"step": 120
},
{
"epoch": 0.07867360208062418,
"grad_norm": 0.09451843053102493,
"learning_rate": 3.6926002952309016e-05,
"loss": 10.3358,
"step": 121
},
{
"epoch": 0.07932379713914174,
"grad_norm": 0.1087484136223793,
"learning_rate": 3.612985456190778e-05,
"loss": 10.3267,
"step": 122
},
{
"epoch": 0.0799739921976593,
"grad_norm": 0.09872005134820938,
"learning_rate": 3.533749813077677e-05,
"loss": 10.3285,
"step": 123
},
{
"epoch": 0.08062418725617686,
"grad_norm": 0.0816490575671196,
"learning_rate": 3.4549150281252636e-05,
"loss": 10.3305,
"step": 124
},
{
"epoch": 0.0812743823146944,
"grad_norm": 0.06516312807798386,
"learning_rate": 3.3765026539765834e-05,
"loss": 10.3277,
"step": 125
},
{
"epoch": 0.08192457737321196,
"grad_norm": 0.0979132354259491,
"learning_rate": 3.298534127791785e-05,
"loss": 10.3333,
"step": 126
},
{
"epoch": 0.08257477243172952,
"grad_norm": 0.09683828055858612,
"learning_rate": 3.221030765387417e-05,
"loss": 10.3303,
"step": 127
},
{
"epoch": 0.08322496749024708,
"grad_norm": 0.07626654207706451,
"learning_rate": 3.144013755408895e-05,
"loss": 10.3337,
"step": 128
},
{
"epoch": 0.08387516254876463,
"grad_norm": 0.10697361826896667,
"learning_rate": 3.0675041535377405e-05,
"loss": 10.3315,
"step": 129
},
{
"epoch": 0.08452535760728218,
"grad_norm": 0.14729544520378113,
"learning_rate": 2.991522876735154e-05,
"loss": 10.3242,
"step": 130
},
{
"epoch": 0.08517555266579974,
"grad_norm": 0.10379993170499802,
"learning_rate": 2.916090697523549e-05,
"loss": 10.325,
"step": 131
},
{
"epoch": 0.0858257477243173,
"grad_norm": 0.10697386413812637,
"learning_rate": 2.8412282383075363e-05,
"loss": 10.3193,
"step": 132
},
{
"epoch": 0.08647594278283485,
"grad_norm": 0.1377425342798233,
"learning_rate": 2.766955965735968e-05,
"loss": 10.3321,
"step": 133
},
{
"epoch": 0.08712613784135241,
"grad_norm": 0.11706317961215973,
"learning_rate": 2.693294185106562e-05,
"loss": 10.336,
"step": 134
},
{
"epoch": 0.08777633289986995,
"grad_norm": 0.14264702796936035,
"learning_rate": 2.6202630348146324e-05,
"loss": 10.3188,
"step": 135
},
{
"epoch": 0.08842652795838751,
"grad_norm": 0.12680768966674805,
"learning_rate": 2.547882480847461e-05,
"loss": 10.3245,
"step": 136
},
{
"epoch": 0.08907672301690507,
"grad_norm": 0.11113236844539642,
"learning_rate": 2.476172311325783e-05,
"loss": 10.3203,
"step": 137
},
{
"epoch": 0.08972691807542263,
"grad_norm": 0.11357241868972778,
"learning_rate": 2.405152131093926e-05,
"loss": 10.3253,
"step": 138
},
{
"epoch": 0.09037711313394019,
"grad_norm": 0.18896634876728058,
"learning_rate": 2.3348413563600325e-05,
"loss": 10.3266,
"step": 139
},
{
"epoch": 0.09102730819245773,
"grad_norm": 0.14701613783836365,
"learning_rate": 2.2652592093878666e-05,
"loss": 10.3287,
"step": 140
},
{
"epoch": 0.09167750325097529,
"grad_norm": 0.1726110726594925,
"learning_rate": 2.196424713241637e-05,
"loss": 10.3284,
"step": 141
},
{
"epoch": 0.09232769830949285,
"grad_norm": 0.21298569440841675,
"learning_rate": 2.128356686585282e-05,
"loss": 10.3223,
"step": 142
},
{
"epoch": 0.0929778933680104,
"grad_norm": 0.230911985039711,
"learning_rate": 2.061073738537635e-05,
"loss": 10.312,
"step": 143
},
{
"epoch": 0.09362808842652796,
"grad_norm": 0.21737301349639893,
"learning_rate": 1.9945942635848748e-05,
"loss": 10.3104,
"step": 144
},
{
"epoch": 0.09427828348504551,
"grad_norm": 0.29789188504219055,
"learning_rate": 1.928936436551661e-05,
"loss": 10.3194,
"step": 145
},
{
"epoch": 0.09492847854356307,
"grad_norm": 0.29933807253837585,
"learning_rate": 1.8641182076323148e-05,
"loss": 10.3249,
"step": 146
},
{
"epoch": 0.09557867360208062,
"grad_norm": 0.3598063290119171,
"learning_rate": 1.800157297483417e-05,
"loss": 10.3118,
"step": 147
},
{
"epoch": 0.09622886866059818,
"grad_norm": 0.3791145980358124,
"learning_rate": 1.7370711923791567e-05,
"loss": 10.2997,
"step": 148
},
{
"epoch": 0.09687906371911574,
"grad_norm": 0.40345707535743713,
"learning_rate": 1.6748771394307585e-05,
"loss": 10.2971,
"step": 149
},
{
"epoch": 0.09752925877763328,
"grad_norm": 0.6572499871253967,
"learning_rate": 1.6135921418712956e-05,
"loss": 10.2936,
"step": 150
},
{
"epoch": 0.09752925877763328,
"eval_loss": 10.325255393981934,
"eval_runtime": 5.5941,
"eval_samples_per_second": 463.164,
"eval_steps_per_second": 115.836,
"step": 150
}
],
"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": false
},
"attributes": {}
}
},
"total_flos": 32559228518400.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}