checkpoint_2b_rag / trainer_state.json
Ankush
add model
7955524
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9984871406959153,
"eval_steps": 42,
"global_step": 165,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006051437216338881,
"grad_norm": 322108055.4732022,
"learning_rate": 4.000000000000001e-06,
"loss": 1.5249,
"step": 1
},
{
"epoch": 0.012102874432677761,
"grad_norm": 355567958.2983011,
"learning_rate": 8.000000000000001e-06,
"loss": 1.5229,
"step": 2
},
{
"epoch": 0.018154311649016642,
"grad_norm": 423.8526182225412,
"learning_rate": 1.2e-05,
"loss": 1.5354,
"step": 3
},
{
"epoch": 0.024205748865355523,
"grad_norm": 277.5486933849194,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.4714,
"step": 4
},
{
"epoch": 0.030257186081694403,
"grad_norm": 273.8460168069521,
"learning_rate": 2e-05,
"loss": 1.3484,
"step": 5
},
{
"epoch": 0.036308623298033284,
"grad_norm": 112.32279225722033,
"learning_rate": 1.9998072404820648e-05,
"loss": 1.1769,
"step": 6
},
{
"epoch": 0.04236006051437216,
"grad_norm": 218.62284085206207,
"learning_rate": 1.9992290362407232e-05,
"loss": 1.1161,
"step": 7
},
{
"epoch": 0.048411497730711045,
"grad_norm": 19.085494659650685,
"learning_rate": 1.998265610184716e-05,
"loss": 1.0773,
"step": 8
},
{
"epoch": 0.05446293494704992,
"grad_norm": 4.403325468378393,
"learning_rate": 1.9969173337331283e-05,
"loss": 1.0162,
"step": 9
},
{
"epoch": 0.060514372163388806,
"grad_norm": 5.142034077751713,
"learning_rate": 1.995184726672197e-05,
"loss": 1.0376,
"step": 10
},
{
"epoch": 0.06656580937972768,
"grad_norm": 4.287306300328979,
"learning_rate": 1.9930684569549265e-05,
"loss": 1.0029,
"step": 11
},
{
"epoch": 0.07261724659606657,
"grad_norm": 3.9972486646227705,
"learning_rate": 1.990569340443577e-05,
"loss": 1.0038,
"step": 12
},
{
"epoch": 0.07866868381240545,
"grad_norm": 3.590191395959283,
"learning_rate": 1.9876883405951378e-05,
"loss": 0.9865,
"step": 13
},
{
"epoch": 0.08472012102874432,
"grad_norm": 2.7816117361481307,
"learning_rate": 1.9844265680898917e-05,
"loss": 0.9811,
"step": 14
},
{
"epoch": 0.0907715582450832,
"grad_norm": 3.579650046953478,
"learning_rate": 1.9807852804032306e-05,
"loss": 0.9568,
"step": 15
},
{
"epoch": 0.09682299546142209,
"grad_norm": 2.8686935445684334,
"learning_rate": 1.9767658813208725e-05,
"loss": 0.9674,
"step": 16
},
{
"epoch": 0.10287443267776097,
"grad_norm": 3.6458707387233273,
"learning_rate": 1.9723699203976768e-05,
"loss": 0.9359,
"step": 17
},
{
"epoch": 0.10892586989409984,
"grad_norm": 2.883416632767117,
"learning_rate": 1.96759909236026e-05,
"loss": 0.9651,
"step": 18
},
{
"epoch": 0.11497730711043873,
"grad_norm": 2.8600382067348784,
"learning_rate": 1.9624552364536472e-05,
"loss": 0.9438,
"step": 19
},
{
"epoch": 0.12102874432677761,
"grad_norm": 2.884830361179161,
"learning_rate": 1.956940335732209e-05,
"loss": 0.9554,
"step": 20
},
{
"epoch": 0.12708018154311648,
"grad_norm": 2.476836373159168,
"learning_rate": 1.9510565162951538e-05,
"loss": 0.947,
"step": 21
},
{
"epoch": 0.13313161875945537,
"grad_norm": 2.944165972805459,
"learning_rate": 1.944806046466878e-05,
"loss": 0.9527,
"step": 22
},
{
"epoch": 0.13918305597579425,
"grad_norm": 2.3742259285155614,
"learning_rate": 1.9381913359224844e-05,
"loss": 0.902,
"step": 23
},
{
"epoch": 0.14523449319213314,
"grad_norm": 3.0336829637888365,
"learning_rate": 1.9312149347588035e-05,
"loss": 0.915,
"step": 24
},
{
"epoch": 0.15128593040847202,
"grad_norm": 2.6677796541697467,
"learning_rate": 1.9238795325112867e-05,
"loss": 0.953,
"step": 25
},
{
"epoch": 0.1573373676248109,
"grad_norm": 2.309703771715573,
"learning_rate": 1.916187957117136e-05,
"loss": 0.8936,
"step": 26
},
{
"epoch": 0.16338880484114976,
"grad_norm": 2.629974494687599,
"learning_rate": 1.9081431738250815e-05,
"loss": 0.9079,
"step": 27
},
{
"epoch": 0.16944024205748864,
"grad_norm": 2.5585105826631103,
"learning_rate": 1.8997482840522218e-05,
"loss": 0.889,
"step": 28
},
{
"epoch": 0.17549167927382753,
"grad_norm": 2.47972204943994,
"learning_rate": 1.891006524188368e-05,
"loss": 0.9031,
"step": 29
},
{
"epoch": 0.1815431164901664,
"grad_norm": 2.321681224058349,
"learning_rate": 1.881921264348355e-05,
"loss": 0.8974,
"step": 30
},
{
"epoch": 0.1875945537065053,
"grad_norm": 2.332021782915067,
"learning_rate": 1.8724960070727974e-05,
"loss": 0.8621,
"step": 31
},
{
"epoch": 0.19364599092284418,
"grad_norm": 2.2862950649440172,
"learning_rate": 1.862734385977792e-05,
"loss": 0.8973,
"step": 32
},
{
"epoch": 0.19969742813918306,
"grad_norm": 2.29932921318996,
"learning_rate": 1.8526401643540924e-05,
"loss": 0.8894,
"step": 33
},
{
"epoch": 0.20574886535552195,
"grad_norm": 2.3159798136981187,
"learning_rate": 1.8422172337162865e-05,
"loss": 0.9114,
"step": 34
},
{
"epoch": 0.2118003025718608,
"grad_norm": 2.3198744636701965,
"learning_rate": 1.8314696123025456e-05,
"loss": 0.8793,
"step": 35
},
{
"epoch": 0.2178517397881997,
"grad_norm": 2.434268725037439,
"learning_rate": 1.8204014435255136e-05,
"loss": 0.8814,
"step": 36
},
{
"epoch": 0.22390317700453857,
"grad_norm": 2.405117668347263,
"learning_rate": 1.8090169943749477e-05,
"loss": 0.8571,
"step": 37
},
{
"epoch": 0.22995461422087746,
"grad_norm": 2.342704896759622,
"learning_rate": 1.797320653772707e-05,
"loss": 0.8755,
"step": 38
},
{
"epoch": 0.23600605143721634,
"grad_norm": 2.417838836739983,
"learning_rate": 1.785316930880745e-05,
"loss": 0.9081,
"step": 39
},
{
"epoch": 0.24205748865355523,
"grad_norm": 2.2078057388117562,
"learning_rate": 1.773010453362737e-05,
"loss": 0.8563,
"step": 40
},
{
"epoch": 0.2481089258698941,
"grad_norm": 98.18997315518052,
"learning_rate": 1.7604059656000313e-05,
"loss": 0.8809,
"step": 41
},
{
"epoch": 0.25416036308623297,
"grad_norm": 5.131232569983683,
"learning_rate": 1.747508326862597e-05,
"loss": 0.8612,
"step": 42
},
{
"epoch": 0.25416036308623297,
"eval_loss": 0.8720352053642273,
"eval_runtime": 18.6299,
"eval_samples_per_second": 227.054,
"eval_steps_per_second": 3.596,
"step": 42
},
{
"epoch": 0.26021180030257185,
"grad_norm": 2.64020419160499,
"learning_rate": 1.7343225094356857e-05,
"loss": 0.8713,
"step": 43
},
{
"epoch": 0.26626323751891073,
"grad_norm": 2.055772213227932,
"learning_rate": 1.720853596702919e-05,
"loss": 0.8599,
"step": 44
},
{
"epoch": 0.2723146747352496,
"grad_norm": 2.391193584495332,
"learning_rate": 1.7071067811865477e-05,
"loss": 0.8716,
"step": 45
},
{
"epoch": 0.2783661119515885,
"grad_norm": 2.3262868956430935,
"learning_rate": 1.6930873625456362e-05,
"loss": 0.8696,
"step": 46
},
{
"epoch": 0.2844175491679274,
"grad_norm": 2.4150484400617063,
"learning_rate": 1.678800745532942e-05,
"loss": 0.8601,
"step": 47
},
{
"epoch": 0.29046898638426627,
"grad_norm": 2.1160799680175355,
"learning_rate": 1.664252437911282e-05,
"loss": 0.8683,
"step": 48
},
{
"epoch": 0.29652042360060515,
"grad_norm": 2.141034341547075,
"learning_rate": 1.6494480483301836e-05,
"loss": 0.8488,
"step": 49
},
{
"epoch": 0.30257186081694404,
"grad_norm": 2.2446379091355326,
"learning_rate": 1.6343932841636455e-05,
"loss": 0.8498,
"step": 50
},
{
"epoch": 0.3086232980332829,
"grad_norm": 1.8953751487603734,
"learning_rate": 1.6190939493098344e-05,
"loss": 0.8436,
"step": 51
},
{
"epoch": 0.3146747352496218,
"grad_norm": 2.3495639918564706,
"learning_rate": 1.6035559419535714e-05,
"loss": 0.8514,
"step": 52
},
{
"epoch": 0.3207261724659607,
"grad_norm": 2.089228593794166,
"learning_rate": 1.5877852522924733e-05,
"loss": 0.8186,
"step": 53
},
{
"epoch": 0.3267776096822995,
"grad_norm": 1.9846619076339054,
"learning_rate": 1.5717879602276123e-05,
"loss": 0.8099,
"step": 54
},
{
"epoch": 0.3328290468986384,
"grad_norm": 2.1032076715725228,
"learning_rate": 1.5555702330196024e-05,
"loss": 0.8257,
"step": 55
},
{
"epoch": 0.3388804841149773,
"grad_norm": 1.9288875770005138,
"learning_rate": 1.5391383229110005e-05,
"loss": 0.8272,
"step": 56
},
{
"epoch": 0.34493192133131617,
"grad_norm": 2.0377322835567218,
"learning_rate": 1.5224985647159489e-05,
"loss": 0.842,
"step": 57
},
{
"epoch": 0.35098335854765506,
"grad_norm": 1.9170865504462093,
"learning_rate": 1.5056573733779848e-05,
"loss": 0.8247,
"step": 58
},
{
"epoch": 0.35703479576399394,
"grad_norm": 1.9956821044576363,
"learning_rate": 1.4886212414969551e-05,
"loss": 0.819,
"step": 59
},
{
"epoch": 0.3630862329803328,
"grad_norm": 18.62969206014239,
"learning_rate": 1.4713967368259981e-05,
"loss": 0.8437,
"step": 60
},
{
"epoch": 0.3691376701966717,
"grad_norm": 3.367255140934318,
"learning_rate": 1.4539904997395468e-05,
"loss": 0.8367,
"step": 61
},
{
"epoch": 0.3751891074130106,
"grad_norm": 2.5151226639465265,
"learning_rate": 1.436409240673342e-05,
"loss": 0.8425,
"step": 62
},
{
"epoch": 0.3812405446293495,
"grad_norm": 1.9600047451684992,
"learning_rate": 1.4186597375374283e-05,
"loss": 0.8658,
"step": 63
},
{
"epoch": 0.38729198184568836,
"grad_norm": 2.4222060882815892,
"learning_rate": 1.4007488331031409e-05,
"loss": 0.8161,
"step": 64
},
{
"epoch": 0.39334341906202724,
"grad_norm": 2.2477181276420173,
"learning_rate": 1.3826834323650899e-05,
"loss": 0.8656,
"step": 65
},
{
"epoch": 0.39939485627836613,
"grad_norm": 1.8742784721591048,
"learning_rate": 1.3644704998791501e-05,
"loss": 0.809,
"step": 66
},
{
"epoch": 0.405446293494705,
"grad_norm": 2.1877492110983243,
"learning_rate": 1.346117057077493e-05,
"loss": 0.8128,
"step": 67
},
{
"epoch": 0.4114977307110439,
"grad_norm": 2.5045082263088756,
"learning_rate": 1.3276301795616937e-05,
"loss": 0.8306,
"step": 68
},
{
"epoch": 0.4175491679273828,
"grad_norm": 9.178317432612376,
"learning_rate": 1.3090169943749475e-05,
"loss": 0.8362,
"step": 69
},
{
"epoch": 0.4236006051437216,
"grad_norm": 1.9516499520055601,
"learning_rate": 1.2902846772544625e-05,
"loss": 0.8416,
"step": 70
},
{
"epoch": 0.4296520423600605,
"grad_norm": 2.056957203256862,
"learning_rate": 1.2714404498650743e-05,
"loss": 0.8175,
"step": 71
},
{
"epoch": 0.4357034795763994,
"grad_norm": 1.7996994310274146,
"learning_rate": 1.252491577015158e-05,
"loss": 0.8221,
"step": 72
},
{
"epoch": 0.44175491679273826,
"grad_norm": 2.0147397373742324,
"learning_rate": 1.2334453638559057e-05,
"loss": 0.8303,
"step": 73
},
{
"epoch": 0.44780635400907715,
"grad_norm": 1.927010852316909,
"learning_rate": 1.2143091530650508e-05,
"loss": 0.8164,
"step": 74
},
{
"epoch": 0.45385779122541603,
"grad_norm": 1.8247659306832096,
"learning_rate": 1.1950903220161286e-05,
"loss": 0.8155,
"step": 75
},
{
"epoch": 0.4599092284417549,
"grad_norm": 1.8869494426432945,
"learning_rate": 1.1757962799343548e-05,
"loss": 0.7975,
"step": 76
},
{
"epoch": 0.4659606656580938,
"grad_norm": 1.803043385328956,
"learning_rate": 1.156434465040231e-05,
"loss": 0.7827,
"step": 77
},
{
"epoch": 0.4720121028744327,
"grad_norm": 2.217030000986005,
"learning_rate": 1.1370123416819683e-05,
"loss": 0.8282,
"step": 78
},
{
"epoch": 0.47806354009077157,
"grad_norm": 1.901237420277299,
"learning_rate": 1.1175373974578378e-05,
"loss": 0.8325,
"step": 79
},
{
"epoch": 0.48411497730711045,
"grad_norm": 1.7707085530448825,
"learning_rate": 1.098017140329561e-05,
"loss": 0.8161,
"step": 80
},
{
"epoch": 0.49016641452344933,
"grad_norm": 1.8472271061761294,
"learning_rate": 1.0784590957278452e-05,
"loss": 0.8233,
"step": 81
},
{
"epoch": 0.4962178517397882,
"grad_norm": 1.7924659284438058,
"learning_rate": 1.058870803651189e-05,
"loss": 0.8014,
"step": 82
},
{
"epoch": 0.5022692889561271,
"grad_norm": 1.8913059036929798,
"learning_rate": 1.0392598157590687e-05,
"loss": 0.8398,
"step": 83
},
{
"epoch": 0.5083207261724659,
"grad_norm": 2.0067650663505376,
"learning_rate": 1.0196336924606282e-05,
"loss": 0.8251,
"step": 84
},
{
"epoch": 0.5083207261724659,
"eval_loss": 0.8105137348175049,
"eval_runtime": 15.8887,
"eval_samples_per_second": 266.227,
"eval_steps_per_second": 4.217,
"step": 84
},
{
"epoch": 0.5143721633888049,
"grad_norm": 1.8193592150156823,
"learning_rate": 1e-05,
"loss": 0.8059,
"step": 85
},
{
"epoch": 0.5204236006051437,
"grad_norm": 1.7674018898267811,
"learning_rate": 9.80366307539372e-06,
"loss": 0.7919,
"step": 86
},
{
"epoch": 0.5264750378214826,
"grad_norm": 1.821253850079311,
"learning_rate": 9.607401842409318e-06,
"loss": 0.8175,
"step": 87
},
{
"epoch": 0.5325264750378215,
"grad_norm": 1.7701691651746592,
"learning_rate": 9.41129196348811e-06,
"loss": 0.8067,
"step": 88
},
{
"epoch": 0.5385779122541604,
"grad_norm": 1.8706627989987974,
"learning_rate": 9.215409042721553e-06,
"loss": 0.8277,
"step": 89
},
{
"epoch": 0.5446293494704992,
"grad_norm": 1.7301034510569795,
"learning_rate": 9.019828596704394e-06,
"loss": 0.7623,
"step": 90
},
{
"epoch": 0.5506807866868382,
"grad_norm": 1.8109305813892944,
"learning_rate": 8.824626025421625e-06,
"loss": 0.7968,
"step": 91
},
{
"epoch": 0.556732223903177,
"grad_norm": 1.7916083013522495,
"learning_rate": 8.629876583180322e-06,
"loss": 0.7906,
"step": 92
},
{
"epoch": 0.5627836611195158,
"grad_norm": 1.723041951018134,
"learning_rate": 8.43565534959769e-06,
"loss": 0.7923,
"step": 93
},
{
"epoch": 0.5688350983358548,
"grad_norm": 1.906015357724372,
"learning_rate": 8.242037200656455e-06,
"loss": 0.8064,
"step": 94
},
{
"epoch": 0.5748865355521936,
"grad_norm": 1.7522630769630916,
"learning_rate": 8.04909677983872e-06,
"loss": 0.7945,
"step": 95
},
{
"epoch": 0.5809379727685325,
"grad_norm": 1.7968696551333927,
"learning_rate": 7.856908469349495e-06,
"loss": 0.7894,
"step": 96
},
{
"epoch": 0.5869894099848714,
"grad_norm": 1.8942858022507922,
"learning_rate": 7.66554636144095e-06,
"loss": 0.8282,
"step": 97
},
{
"epoch": 0.5930408472012103,
"grad_norm": 1.8099448490609888,
"learning_rate": 7.4750842298484205e-06,
"loss": 0.8045,
"step": 98
},
{
"epoch": 0.5990922844175491,
"grad_norm": 1.777972803175514,
"learning_rate": 7.285595501349259e-06,
"loss": 0.8025,
"step": 99
},
{
"epoch": 0.6051437216338881,
"grad_norm": 1.783144416540341,
"learning_rate": 7.097153227455379e-06,
"loss": 0.8243,
"step": 100
},
{
"epoch": 0.6111951588502269,
"grad_norm": 1.7896936879748115,
"learning_rate": 6.909830056250527e-06,
"loss": 0.8098,
"step": 101
},
{
"epoch": 0.6172465960665658,
"grad_norm": 1.7287133254606566,
"learning_rate": 6.723698204383067e-06,
"loss": 0.7946,
"step": 102
},
{
"epoch": 0.6232980332829047,
"grad_norm": 1.8036680843631874,
"learning_rate": 6.538829429225068e-06,
"loss": 0.7762,
"step": 103
},
{
"epoch": 0.6293494704992436,
"grad_norm": 1.8545633375284538,
"learning_rate": 6.355295001208504e-06,
"loss": 0.8059,
"step": 104
},
{
"epoch": 0.6354009077155824,
"grad_norm": 1.865666266019574,
"learning_rate": 6.173165676349103e-06,
"loss": 0.7859,
"step": 105
},
{
"epoch": 0.6414523449319214,
"grad_norm": 1.6652988720333,
"learning_rate": 5.9925116689685925e-06,
"loss": 0.767,
"step": 106
},
{
"epoch": 0.6475037821482602,
"grad_norm": 1.761164487737613,
"learning_rate": 5.813402624625722e-06,
"loss": 0.7818,
"step": 107
},
{
"epoch": 0.653555219364599,
"grad_norm": 1.8325436940760458,
"learning_rate": 5.635907593266578e-06,
"loss": 0.7797,
"step": 108
},
{
"epoch": 0.659606656580938,
"grad_norm": 1.7458851309984722,
"learning_rate": 5.460095002604533e-06,
"loss": 0.7929,
"step": 109
},
{
"epoch": 0.6656580937972768,
"grad_norm": 1.7511730155909075,
"learning_rate": 5.286032631740023e-06,
"loss": 0.8146,
"step": 110
},
{
"epoch": 0.6717095310136157,
"grad_norm": 1.6942068341047123,
"learning_rate": 5.1137875850304545e-06,
"loss": 0.7714,
"step": 111
},
{
"epoch": 0.6777609682299546,
"grad_norm": 1.7566917917926772,
"learning_rate": 4.943426266220156e-06,
"loss": 0.7956,
"step": 112
},
{
"epoch": 0.6838124054462935,
"grad_norm": 1.713757862020219,
"learning_rate": 4.775014352840512e-06,
"loss": 0.7862,
"step": 113
},
{
"epoch": 0.6898638426626323,
"grad_norm": 1.7331168505190726,
"learning_rate": 4.608616770889998e-06,
"loss": 0.7804,
"step": 114
},
{
"epoch": 0.6959152798789713,
"grad_norm": 1.8104874747906492,
"learning_rate": 4.444297669803981e-06,
"loss": 0.8187,
"step": 115
},
{
"epoch": 0.7019667170953101,
"grad_norm": 1.6744618936972424,
"learning_rate": 4.282120397723879e-06,
"loss": 0.7704,
"step": 116
},
{
"epoch": 0.708018154311649,
"grad_norm": 1.7261151885353918,
"learning_rate": 4.12214747707527e-06,
"loss": 0.7902,
"step": 117
},
{
"epoch": 0.7140695915279879,
"grad_norm": 1.7369036940485543,
"learning_rate": 3.964440580464286e-06,
"loss": 0.8147,
"step": 118
},
{
"epoch": 0.7201210287443268,
"grad_norm": 1.7029028180642818,
"learning_rate": 3.8090605069016596e-06,
"loss": 0.8068,
"step": 119
},
{
"epoch": 0.7261724659606656,
"grad_norm": 1.7441391740410612,
"learning_rate": 3.6560671583635467e-06,
"loss": 0.8065,
"step": 120
},
{
"epoch": 0.7322239031770046,
"grad_norm": 1.7387201084449406,
"learning_rate": 3.505519516698165e-06,
"loss": 0.8015,
"step": 121
},
{
"epoch": 0.7382753403933434,
"grad_norm": 1.697622312997327,
"learning_rate": 3.3574756208871862e-06,
"loss": 0.7832,
"step": 122
},
{
"epoch": 0.7443267776096822,
"grad_norm": 1.731136127294693,
"learning_rate": 3.2119925446705824e-06,
"loss": 0.79,
"step": 123
},
{
"epoch": 0.7503782148260212,
"grad_norm": 1.6365994311291872,
"learning_rate": 3.069126374543643e-06,
"loss": 0.7865,
"step": 124
},
{
"epoch": 0.75642965204236,
"grad_norm": 1.6359863467519138,
"learning_rate": 2.9289321881345257e-06,
"loss": 0.7668,
"step": 125
},
{
"epoch": 0.762481089258699,
"grad_norm": 1.709421331560918,
"learning_rate": 2.791464032970812e-06,
"loss": 0.7812,
"step": 126
},
{
"epoch": 0.762481089258699,
"eval_loss": 0.7835145592689514,
"eval_runtime": 15.87,
"eval_samples_per_second": 266.541,
"eval_steps_per_second": 4.222,
"step": 126
},
{
"epoch": 0.7685325264750378,
"grad_norm": 1.7259657772685697,
"learning_rate": 2.656774905643147e-06,
"loss": 0.7763,
"step": 127
},
{
"epoch": 0.7745839636913767,
"grad_norm": 1.663157745899699,
"learning_rate": 2.5249167313740307e-06,
"loss": 0.7886,
"step": 128
},
{
"epoch": 0.7806354009077155,
"grad_norm": 1.7071181408125617,
"learning_rate": 2.395940343999691e-06,
"loss": 0.7974,
"step": 129
},
{
"epoch": 0.7866868381240545,
"grad_norm": 1.7398875364830548,
"learning_rate": 2.26989546637263e-06,
"loss": 0.7922,
"step": 130
},
{
"epoch": 0.7927382753403933,
"grad_norm": 1.7262145967298637,
"learning_rate": 2.146830691192553e-06,
"loss": 0.7857,
"step": 131
},
{
"epoch": 0.7987897125567323,
"grad_norm": 1.7599571064642554,
"learning_rate": 2.02679346227293e-06,
"loss": 0.8111,
"step": 132
},
{
"epoch": 0.8048411497730711,
"grad_norm": 1.764758571264166,
"learning_rate": 1.9098300562505266e-06,
"loss": 0.7884,
"step": 133
},
{
"epoch": 0.81089258698941,
"grad_norm": 1.666273478784506,
"learning_rate": 1.7959855647448642e-06,
"loss": 0.7669,
"step": 134
},
{
"epoch": 0.8169440242057489,
"grad_norm": 1.644818476714854,
"learning_rate": 1.6853038769745466e-06,
"loss": 0.7879,
"step": 135
},
{
"epoch": 0.8229954614220878,
"grad_norm": 1.6371021662929024,
"learning_rate": 1.577827662837136e-06,
"loss": 0.7672,
"step": 136
},
{
"epoch": 0.8290468986384266,
"grad_norm": 1.7096483505883402,
"learning_rate": 1.4735983564590784e-06,
"loss": 0.7785,
"step": 137
},
{
"epoch": 0.8350983358547656,
"grad_norm": 1.637601012545836,
"learning_rate": 1.3726561402220818e-06,
"loss": 0.7837,
"step": 138
},
{
"epoch": 0.8411497730711044,
"grad_norm": 1.6793180233293152,
"learning_rate": 1.2750399292720284e-06,
"loss": 0.7769,
"step": 139
},
{
"epoch": 0.8472012102874432,
"grad_norm": 1.6978760771073718,
"learning_rate": 1.1807873565164507e-06,
"loss": 0.7658,
"step": 140
},
{
"epoch": 0.8532526475037822,
"grad_norm": 1.6749246259946589,
"learning_rate": 1.0899347581163222e-06,
"loss": 0.7711,
"step": 141
},
{
"epoch": 0.859304084720121,
"grad_norm": 1.6758050707650343,
"learning_rate": 1.0025171594777872e-06,
"loss": 0.7686,
"step": 142
},
{
"epoch": 0.8653555219364599,
"grad_norm": 1.7468688446067502,
"learning_rate": 9.185682617491865e-07,
"loss": 0.8124,
"step": 143
},
{
"epoch": 0.8714069591527988,
"grad_norm": 1.6696901769364607,
"learning_rate": 8.381204288286415e-07,
"loss": 0.7753,
"step": 144
},
{
"epoch": 0.8774583963691377,
"grad_norm": 1.7545342313458392,
"learning_rate": 7.612046748871327e-07,
"loss": 0.7826,
"step": 145
},
{
"epoch": 0.8835098335854765,
"grad_norm": 1.720087490611314,
"learning_rate": 6.878506524119644e-07,
"loss": 0.7841,
"step": 146
},
{
"epoch": 0.8895612708018155,
"grad_norm": 1.7154929931979837,
"learning_rate": 6.180866407751595e-07,
"loss": 0.8065,
"step": 147
},
{
"epoch": 0.8956127080181543,
"grad_norm": 1.6938285717094959,
"learning_rate": 5.519395353312195e-07,
"loss": 0.7599,
"step": 148
},
{
"epoch": 0.9016641452344932,
"grad_norm": 1.7221938520673765,
"learning_rate": 4.894348370484648e-07,
"loss": 0.7921,
"step": 149
},
{
"epoch": 0.9077155824508321,
"grad_norm": 1.7085140075465948,
"learning_rate": 4.305966426779118e-07,
"loss": 0.7883,
"step": 150
},
{
"epoch": 0.913767019667171,
"grad_norm": 1.6823778148451014,
"learning_rate": 3.7544763546352834e-07,
"loss": 0.762,
"step": 151
},
{
"epoch": 0.9198184568835098,
"grad_norm": 1.6556587985252844,
"learning_rate": 3.2400907639740243e-07,
"loss": 0.7801,
"step": 152
},
{
"epoch": 0.9258698940998488,
"grad_norm": 1.682814477644372,
"learning_rate": 2.7630079602323447e-07,
"loss": 0.7711,
"step": 153
},
{
"epoch": 0.9319213313161876,
"grad_norm": 1.6477141580840275,
"learning_rate": 2.3234118679127615e-07,
"loss": 0.7615,
"step": 154
},
{
"epoch": 0.9379727685325264,
"grad_norm": 1.7152855010369743,
"learning_rate": 1.921471959676957e-07,
"loss": 0.8066,
"step": 155
},
{
"epoch": 0.9440242057488654,
"grad_norm": 1.7156519942956723,
"learning_rate": 1.5573431910108404e-07,
"loss": 0.7754,
"step": 156
},
{
"epoch": 0.9500756429652042,
"grad_norm": 1.6843373848088317,
"learning_rate": 1.231165940486234e-07,
"loss": 0.7766,
"step": 157
},
{
"epoch": 0.9561270801815431,
"grad_norm": 1.6626529442380376,
"learning_rate": 9.43065955642275e-08,
"loss": 0.7709,
"step": 158
},
{
"epoch": 0.962178517397882,
"grad_norm": 1.648515446524827,
"learning_rate": 6.931543045073708e-08,
"loss": 0.7766,
"step": 159
},
{
"epoch": 0.9682299546142209,
"grad_norm": 1.666828705980742,
"learning_rate": 4.815273327803183e-08,
"loss": 0.7756,
"step": 160
},
{
"epoch": 0.9742813918305597,
"grad_norm": 1.6783538075057698,
"learning_rate": 3.082666266872036e-08,
"loss": 0.7934,
"step": 161
},
{
"epoch": 0.9803328290468987,
"grad_norm": 1.6237786363290807,
"learning_rate": 1.7343898152841765e-08,
"loss": 0.7769,
"step": 162
},
{
"epoch": 0.9863842662632375,
"grad_norm": 1.619244118831079,
"learning_rate": 7.70963759277099e-09,
"loss": 0.7587,
"step": 163
},
{
"epoch": 0.9924357034795764,
"grad_norm": 1.7166293751335602,
"learning_rate": 1.9275951793518154e-09,
"loss": 0.7877,
"step": 164
},
{
"epoch": 0.9984871406959153,
"grad_norm": 1.7273091506087734,
"learning_rate": 0.0,
"loss": 0.7917,
"step": 165
},
{
"epoch": 0.9984871406959153,
"step": 165,
"total_flos": 104016591716352.0,
"train_loss": 0.8553301778706637,
"train_runtime": 654.3507,
"train_samples_per_second": 64.649,
"train_steps_per_second": 0.252
}
],
"logging_steps": 1.0,
"max_steps": 165,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 42,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 104016591716352.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}