fats-fme's picture
Training in progress, step 197, checkpoint
354beb9 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9955780164245104,
"eval_steps": 50,
"global_step": 197,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00505369551484523,
"grad_norm": 5.525087356567383,
"learning_rate": 2.0000000000000003e-06,
"loss": 11.0327,
"step": 1
},
{
"epoch": 0.00505369551484523,
"eval_loss": 10.8840913772583,
"eval_runtime": 8.456,
"eval_samples_per_second": 39.499,
"eval_steps_per_second": 9.934,
"step": 1
},
{
"epoch": 0.01010739102969046,
"grad_norm": 5.266482830047607,
"learning_rate": 4.000000000000001e-06,
"loss": 10.9714,
"step": 2
},
{
"epoch": 0.015161086544535692,
"grad_norm": 4.918356895446777,
"learning_rate": 6e-06,
"loss": 10.9057,
"step": 3
},
{
"epoch": 0.02021478205938092,
"grad_norm": 4.777329921722412,
"learning_rate": 8.000000000000001e-06,
"loss": 10.939,
"step": 4
},
{
"epoch": 0.025268477574226154,
"grad_norm": 4.73073148727417,
"learning_rate": 1e-05,
"loss": 11.0369,
"step": 5
},
{
"epoch": 0.030322173089071383,
"grad_norm": 4.6360931396484375,
"learning_rate": 1.2e-05,
"loss": 10.8651,
"step": 6
},
{
"epoch": 0.035375868603916616,
"grad_norm": 4.678157329559326,
"learning_rate": 1.4000000000000001e-05,
"loss": 10.8567,
"step": 7
},
{
"epoch": 0.04042956411876184,
"grad_norm": 4.721307754516602,
"learning_rate": 1.6000000000000003e-05,
"loss": 10.8247,
"step": 8
},
{
"epoch": 0.045483259633607075,
"grad_norm": 4.473278045654297,
"learning_rate": 1.8e-05,
"loss": 10.7567,
"step": 9
},
{
"epoch": 0.05053695514845231,
"grad_norm": 4.979541301727295,
"learning_rate": 2e-05,
"loss": 10.8797,
"step": 10
},
{
"epoch": 0.05559065066329753,
"grad_norm": 4.539080619812012,
"learning_rate": 2.2000000000000003e-05,
"loss": 10.8282,
"step": 11
},
{
"epoch": 0.060644346178142766,
"grad_norm": 4.77044153213501,
"learning_rate": 2.4e-05,
"loss": 10.9363,
"step": 12
},
{
"epoch": 0.065698041692988,
"grad_norm": 4.023128509521484,
"learning_rate": 2.6000000000000002e-05,
"loss": 10.8104,
"step": 13
},
{
"epoch": 0.07075173720783323,
"grad_norm": 4.127583026885986,
"learning_rate": 2.8000000000000003e-05,
"loss": 10.772,
"step": 14
},
{
"epoch": 0.07580543272267846,
"grad_norm": 4.209392070770264,
"learning_rate": 3e-05,
"loss": 10.819,
"step": 15
},
{
"epoch": 0.08085912823752368,
"grad_norm": 4.107909202575684,
"learning_rate": 3.2000000000000005e-05,
"loss": 10.8561,
"step": 16
},
{
"epoch": 0.08591282375236892,
"grad_norm": 3.9726462364196777,
"learning_rate": 3.4000000000000007e-05,
"loss": 10.702,
"step": 17
},
{
"epoch": 0.09096651926721415,
"grad_norm": 3.9486467838287354,
"learning_rate": 3.6e-05,
"loss": 10.86,
"step": 18
},
{
"epoch": 0.09602021478205938,
"grad_norm": 4.086248397827148,
"learning_rate": 3.8e-05,
"loss": 10.6329,
"step": 19
},
{
"epoch": 0.10107391029690461,
"grad_norm": 4.198414325714111,
"learning_rate": 4e-05,
"loss": 10.6256,
"step": 20
},
{
"epoch": 0.10612760581174985,
"grad_norm": 4.264832496643066,
"learning_rate": 4.2e-05,
"loss": 10.668,
"step": 21
},
{
"epoch": 0.11118130132659507,
"grad_norm": 4.420608997344971,
"learning_rate": 4.4000000000000006e-05,
"loss": 10.703,
"step": 22
},
{
"epoch": 0.1162349968414403,
"grad_norm": 4.989047050476074,
"learning_rate": 4.600000000000001e-05,
"loss": 10.7338,
"step": 23
},
{
"epoch": 0.12128869235628553,
"grad_norm": 6.062208652496338,
"learning_rate": 4.8e-05,
"loss": 10.8503,
"step": 24
},
{
"epoch": 0.12634238787113075,
"grad_norm": 7.2560038566589355,
"learning_rate": 5e-05,
"loss": 10.6961,
"step": 25
},
{
"epoch": 0.131396083385976,
"grad_norm": 5.42380428314209,
"learning_rate": 5.2000000000000004e-05,
"loss": 10.654,
"step": 26
},
{
"epoch": 0.13644977890082122,
"grad_norm": 4.605566501617432,
"learning_rate": 5.4000000000000005e-05,
"loss": 10.6335,
"step": 27
},
{
"epoch": 0.14150347441566646,
"grad_norm": 4.439408779144287,
"learning_rate": 5.6000000000000006e-05,
"loss": 10.5825,
"step": 28
},
{
"epoch": 0.14655716993051168,
"grad_norm": 4.211907386779785,
"learning_rate": 5.8e-05,
"loss": 10.5156,
"step": 29
},
{
"epoch": 0.15161086544535693,
"grad_norm": 3.8451991081237793,
"learning_rate": 6e-05,
"loss": 10.3591,
"step": 30
},
{
"epoch": 0.15666456096020215,
"grad_norm": 3.6254827976226807,
"learning_rate": 6.2e-05,
"loss": 10.5195,
"step": 31
},
{
"epoch": 0.16171825647504737,
"grad_norm": 3.743040084838867,
"learning_rate": 6.400000000000001e-05,
"loss": 10.4644,
"step": 32
},
{
"epoch": 0.16677195198989261,
"grad_norm": 3.687465190887451,
"learning_rate": 6.6e-05,
"loss": 10.2991,
"step": 33
},
{
"epoch": 0.17182564750473783,
"grad_norm": 3.4375765323638916,
"learning_rate": 6.800000000000001e-05,
"loss": 10.3176,
"step": 34
},
{
"epoch": 0.17687934301958308,
"grad_norm": 3.485527753829956,
"learning_rate": 7e-05,
"loss": 10.2831,
"step": 35
},
{
"epoch": 0.1819330385344283,
"grad_norm": 3.4168219566345215,
"learning_rate": 7.2e-05,
"loss": 10.1887,
"step": 36
},
{
"epoch": 0.18698673404927352,
"grad_norm": 2.9851391315460205,
"learning_rate": 7.4e-05,
"loss": 10.2611,
"step": 37
},
{
"epoch": 0.19204042956411876,
"grad_norm": 3.173752784729004,
"learning_rate": 7.6e-05,
"loss": 10.0005,
"step": 38
},
{
"epoch": 0.19709412507896398,
"grad_norm": 3.038637161254883,
"learning_rate": 7.800000000000001e-05,
"loss": 10.1846,
"step": 39
},
{
"epoch": 0.20214782059380923,
"grad_norm": 3.0100479125976562,
"learning_rate": 8e-05,
"loss": 10.121,
"step": 40
},
{
"epoch": 0.20720151610865445,
"grad_norm": 3.1173861026763916,
"learning_rate": 8.2e-05,
"loss": 10.055,
"step": 41
},
{
"epoch": 0.2122552116234997,
"grad_norm": 2.935340166091919,
"learning_rate": 8.4e-05,
"loss": 9.9977,
"step": 42
},
{
"epoch": 0.21730890713834491,
"grad_norm": 2.8017685413360596,
"learning_rate": 8.6e-05,
"loss": 9.9614,
"step": 43
},
{
"epoch": 0.22236260265319013,
"grad_norm": 2.6707160472869873,
"learning_rate": 8.800000000000001e-05,
"loss": 10.0095,
"step": 44
},
{
"epoch": 0.22741629816803538,
"grad_norm": 2.65998911857605,
"learning_rate": 9e-05,
"loss": 9.9824,
"step": 45
},
{
"epoch": 0.2324699936828806,
"grad_norm": 2.622680902481079,
"learning_rate": 9.200000000000001e-05,
"loss": 9.8679,
"step": 46
},
{
"epoch": 0.23752368919772585,
"grad_norm": 2.7016119956970215,
"learning_rate": 9.4e-05,
"loss": 9.8601,
"step": 47
},
{
"epoch": 0.24257738471257106,
"grad_norm": 2.5022776126861572,
"learning_rate": 9.6e-05,
"loss": 10.012,
"step": 48
},
{
"epoch": 0.2476310802274163,
"grad_norm": 2.6630473136901855,
"learning_rate": 9.8e-05,
"loss": 9.919,
"step": 49
},
{
"epoch": 0.2526847757422615,
"grad_norm": 3.5715386867523193,
"learning_rate": 0.0001,
"loss": 9.9513,
"step": 50
},
{
"epoch": 0.2526847757422615,
"eval_loss": 9.72451114654541,
"eval_runtime": 8.5338,
"eval_samples_per_second": 39.139,
"eval_steps_per_second": 9.843,
"step": 50
},
{
"epoch": 0.25773847125710675,
"grad_norm": 2.438196897506714,
"learning_rate": 9.99885820390154e-05,
"loss": 9.9308,
"step": 51
},
{
"epoch": 0.262792166771952,
"grad_norm": 2.2800676822662354,
"learning_rate": 9.995433337085491e-05,
"loss": 9.7762,
"step": 52
},
{
"epoch": 0.26784586228679724,
"grad_norm": 2.2999722957611084,
"learning_rate": 9.989726963751682e-05,
"loss": 9.6314,
"step": 53
},
{
"epoch": 0.27289955780164243,
"grad_norm": 2.0864381790161133,
"learning_rate": 9.981741690106034e-05,
"loss": 9.5644,
"step": 54
},
{
"epoch": 0.2779532533164877,
"grad_norm": 1.9628472328186035,
"learning_rate": 9.971481163170268e-05,
"loss": 9.6852,
"step": 55
},
{
"epoch": 0.2830069488313329,
"grad_norm": 2.0100128650665283,
"learning_rate": 9.95895006911623e-05,
"loss": 9.532,
"step": 56
},
{
"epoch": 0.2880606443461781,
"grad_norm": 1.903132438659668,
"learning_rate": 9.944154131125642e-05,
"loss": 9.5968,
"step": 57
},
{
"epoch": 0.29311433986102337,
"grad_norm": 1.8894416093826294,
"learning_rate": 9.927100106776212e-05,
"loss": 9.45,
"step": 58
},
{
"epoch": 0.2981680353758686,
"grad_norm": 1.8624144792556763,
"learning_rate": 9.907795784955327e-05,
"loss": 9.462,
"step": 59
},
{
"epoch": 0.30322173089071386,
"grad_norm": 1.88225519657135,
"learning_rate": 9.88624998230272e-05,
"loss": 9.3977,
"step": 60
},
{
"epoch": 0.30827542640555905,
"grad_norm": 1.9469467401504517,
"learning_rate": 9.862472539183756e-05,
"loss": 9.2517,
"step": 61
},
{
"epoch": 0.3133291219204043,
"grad_norm": 1.6683619022369385,
"learning_rate": 9.836474315195147e-05,
"loss": 9.4305,
"step": 62
},
{
"epoch": 0.31838281743524954,
"grad_norm": 1.663127064704895,
"learning_rate": 9.808267184205183e-05,
"loss": 9.2934,
"step": 63
},
{
"epoch": 0.32343651295009473,
"grad_norm": 1.6440531015396118,
"learning_rate": 9.777864028930705e-05,
"loss": 9.3013,
"step": 64
},
{
"epoch": 0.32849020846494,
"grad_norm": 1.6826865673065186,
"learning_rate": 9.745278735053343e-05,
"loss": 9.2594,
"step": 65
},
{
"epoch": 0.33354390397978523,
"grad_norm": 1.596401572227478,
"learning_rate": 9.710526184877667e-05,
"loss": 9.2143,
"step": 66
},
{
"epoch": 0.3385975994946305,
"grad_norm": 1.764570951461792,
"learning_rate": 9.673622250534156e-05,
"loss": 9.0152,
"step": 67
},
{
"epoch": 0.34365129500947567,
"grad_norm": 1.5638481378555298,
"learning_rate": 9.63458378673011e-05,
"loss": 9.1172,
"step": 68
},
{
"epoch": 0.3487049905243209,
"grad_norm": 1.5338134765625,
"learning_rate": 9.593428623051792e-05,
"loss": 9.0363,
"step": 69
},
{
"epoch": 0.35375868603916616,
"grad_norm": 1.6992957592010498,
"learning_rate": 9.550175555821333e-05,
"loss": 9.0962,
"step": 70
},
{
"epoch": 0.35881238155401135,
"grad_norm": 1.6055617332458496,
"learning_rate": 9.504844339512095e-05,
"loss": 9.1217,
"step": 71
},
{
"epoch": 0.3638660770688566,
"grad_norm": 1.7240350246429443,
"learning_rate": 9.457455677726448e-05,
"loss": 9.2245,
"step": 72
},
{
"epoch": 0.36891977258370184,
"grad_norm": 1.9936858415603638,
"learning_rate": 9.408031213740045e-05,
"loss": 9.3585,
"step": 73
},
{
"epoch": 0.37397346809854703,
"grad_norm": 2.1292333602905273,
"learning_rate": 9.356593520616948e-05,
"loss": 9.4107,
"step": 74
},
{
"epoch": 0.3790271636133923,
"grad_norm": 3.4360055923461914,
"learning_rate": 9.303166090900082e-05,
"loss": 9.1299,
"step": 75
},
{
"epoch": 0.38408085912823753,
"grad_norm": 1.3017970323562622,
"learning_rate": 9.24777332588177e-05,
"loss": 9.224,
"step": 76
},
{
"epoch": 0.3891345546430828,
"grad_norm": 1.1683531999588013,
"learning_rate": 9.190440524459203e-05,
"loss": 9.2729,
"step": 77
},
{
"epoch": 0.39418825015792797,
"grad_norm": 1.235701084136963,
"learning_rate": 9.131193871579975e-05,
"loss": 9.0347,
"step": 78
},
{
"epoch": 0.3992419456727732,
"grad_norm": 1.1109133958816528,
"learning_rate": 9.070060426282925e-05,
"loss": 9.0375,
"step": 79
},
{
"epoch": 0.40429564118761846,
"grad_norm": 1.2668910026550293,
"learning_rate": 9.007068109339784e-05,
"loss": 8.9948,
"step": 80
},
{
"epoch": 0.40934933670246365,
"grad_norm": 1.3104698657989502,
"learning_rate": 8.942245690503239e-05,
"loss": 8.9623,
"step": 81
},
{
"epoch": 0.4144030322173089,
"grad_norm": 1.198638916015625,
"learning_rate": 8.87562277536726e-05,
"loss": 9.0571,
"step": 82
},
{
"epoch": 0.41945672773215414,
"grad_norm": 1.2889971733093262,
"learning_rate": 8.807229791845673e-05,
"loss": 8.9898,
"step": 83
},
{
"epoch": 0.4245104232469994,
"grad_norm": 1.2756685018539429,
"learning_rate": 8.737097976275178e-05,
"loss": 8.896,
"step": 84
},
{
"epoch": 0.4295641187618446,
"grad_norm": 1.1489578485488892,
"learning_rate": 8.665259359149132e-05,
"loss": 9.067,
"step": 85
},
{
"epoch": 0.43461781427668983,
"grad_norm": 1.1491981744766235,
"learning_rate": 8.591746750488639e-05,
"loss": 8.8872,
"step": 86
},
{
"epoch": 0.4396715097915351,
"grad_norm": 1.072772741317749,
"learning_rate": 8.516593724857598e-05,
"loss": 8.887,
"step": 87
},
{
"epoch": 0.44472520530638027,
"grad_norm": 1.0014466047286987,
"learning_rate": 8.439834606028594e-05,
"loss": 8.8939,
"step": 88
},
{
"epoch": 0.4497789008212255,
"grad_norm": 1.1188455820083618,
"learning_rate": 8.361504451306585e-05,
"loss": 8.7898,
"step": 89
},
{
"epoch": 0.45483259633607076,
"grad_norm": 1.039220929145813,
"learning_rate": 8.28163903551759e-05,
"loss": 8.8616,
"step": 90
},
{
"epoch": 0.459886291850916,
"grad_norm": 1.1389069557189941,
"learning_rate": 8.200274834669675e-05,
"loss": 8.7895,
"step": 91
},
{
"epoch": 0.4649399873657612,
"grad_norm": 1.1462750434875488,
"learning_rate": 8.117449009293668e-05,
"loss": 8.8468,
"step": 92
},
{
"epoch": 0.46999368288060644,
"grad_norm": 1.1461669206619263,
"learning_rate": 8.033199387471277e-05,
"loss": 8.7652,
"step": 93
},
{
"epoch": 0.4750473783954517,
"grad_norm": 1.254766583442688,
"learning_rate": 7.9475644475583e-05,
"loss": 8.612,
"step": 94
},
{
"epoch": 0.4801010739102969,
"grad_norm": 1.3156293630599976,
"learning_rate": 7.860583300610849e-05,
"loss": 8.7556,
"step": 95
},
{
"epoch": 0.48515476942514213,
"grad_norm": 1.2289044857025146,
"learning_rate": 7.772295672522615e-05,
"loss": 8.8208,
"step": 96
},
{
"epoch": 0.4902084649399874,
"grad_norm": 1.7439113855361938,
"learning_rate": 7.682741885881315e-05,
"loss": 9.0702,
"step": 97
},
{
"epoch": 0.4952621604548326,
"grad_norm": 1.3451626300811768,
"learning_rate": 7.591962841552627e-05,
"loss": 8.8565,
"step": 98
},
{
"epoch": 0.5003158559696779,
"grad_norm": 1.7298027276992798,
"learning_rate": 7.500000000000001e-05,
"loss": 9.0691,
"step": 99
},
{
"epoch": 0.505369551484523,
"grad_norm": 2.368654727935791,
"learning_rate": 7.406895362348916e-05,
"loss": 8.8959,
"step": 100
},
{
"epoch": 0.505369551484523,
"eval_loss": 8.748159408569336,
"eval_runtime": 8.2562,
"eval_samples_per_second": 40.455,
"eval_steps_per_second": 10.174,
"step": 100
},
{
"epoch": 0.5104232469993683,
"grad_norm": 1.6569247245788574,
"learning_rate": 7.312691451204178e-05,
"loss": 8.9028,
"step": 101
},
{
"epoch": 0.5154769425142135,
"grad_norm": 1.122266173362732,
"learning_rate": 7.217431291229067e-05,
"loss": 8.8732,
"step": 102
},
{
"epoch": 0.5205306380290587,
"grad_norm": 0.9974745512008667,
"learning_rate": 7.121158389495186e-05,
"loss": 8.9486,
"step": 103
},
{
"epoch": 0.525584333543904,
"grad_norm": 1.1596142053604126,
"learning_rate": 7.023916715611969e-05,
"loss": 8.7343,
"step": 104
},
{
"epoch": 0.5306380290587492,
"grad_norm": 1.1720257997512817,
"learning_rate": 6.925750681644953e-05,
"loss": 8.7557,
"step": 105
},
{
"epoch": 0.5356917245735945,
"grad_norm": 1.1216539144515991,
"learning_rate": 6.826705121831976e-05,
"loss": 8.7399,
"step": 106
},
{
"epoch": 0.5407454200884396,
"grad_norm": 1.0456095933914185,
"learning_rate": 6.726825272106538e-05,
"loss": 8.8259,
"step": 107
},
{
"epoch": 0.5457991156032849,
"grad_norm": 1.1412315368652344,
"learning_rate": 6.626156749437736e-05,
"loss": 8.7779,
"step": 108
},
{
"epoch": 0.5508528111181301,
"grad_norm": 1.144679069519043,
"learning_rate": 6.524745530996137e-05,
"loss": 8.7377,
"step": 109
},
{
"epoch": 0.5559065066329754,
"grad_norm": 1.1518090963363647,
"learning_rate": 6.422637933155162e-05,
"loss": 8.5458,
"step": 110
},
{
"epoch": 0.5609602021478206,
"grad_norm": 1.0327682495117188,
"learning_rate": 6.319880590337549e-05,
"loss": 8.7034,
"step": 111
},
{
"epoch": 0.5660138976626659,
"grad_norm": 0.9186742901802063,
"learning_rate": 6.216520433716545e-05,
"loss": 8.7843,
"step": 112
},
{
"epoch": 0.5710675931775111,
"grad_norm": 0.9329281449317932,
"learning_rate": 6.112604669781572e-05,
"loss": 8.7471,
"step": 113
},
{
"epoch": 0.5761212886923562,
"grad_norm": 1.0598094463348389,
"learning_rate": 6.008180758778167e-05,
"loss": 8.6698,
"step": 114
},
{
"epoch": 0.5811749842072015,
"grad_norm": 1.1156866550445557,
"learning_rate": 5.903296393031995e-05,
"loss": 8.6572,
"step": 115
},
{
"epoch": 0.5862286797220467,
"grad_norm": 1.0410085916519165,
"learning_rate": 5.7979994751668964e-05,
"loss": 8.505,
"step": 116
},
{
"epoch": 0.591282375236892,
"grad_norm": 1.126705288887024,
"learning_rate": 5.69233809622687e-05,
"loss": 8.7812,
"step": 117
},
{
"epoch": 0.5963360707517372,
"grad_norm": 1.1464685201644897,
"learning_rate": 5.58636051371201e-05,
"loss": 8.5813,
"step": 118
},
{
"epoch": 0.6013897662665825,
"grad_norm": 1.146330714225769,
"learning_rate": 5.480115129538409e-05,
"loss": 8.4167,
"step": 119
},
{
"epoch": 0.6064434617814277,
"grad_norm": 1.079012393951416,
"learning_rate": 5.373650467932122e-05,
"loss": 8.5148,
"step": 120
},
{
"epoch": 0.6114971572962729,
"grad_norm": 1.281872272491455,
"learning_rate": 5.267015153267245e-05,
"loss": 8.4182,
"step": 121
},
{
"epoch": 0.6165508528111181,
"grad_norm": 1.1823097467422485,
"learning_rate": 5.1602578878582776e-05,
"loss": 8.6779,
"step": 122
},
{
"epoch": 0.6216045483259633,
"grad_norm": 1.620906114578247,
"learning_rate": 5.053427429716867e-05,
"loss": 8.8053,
"step": 123
},
{
"epoch": 0.6266582438408086,
"grad_norm": 1.704972505569458,
"learning_rate": 4.9465725702831346e-05,
"loss": 8.9209,
"step": 124
},
{
"epoch": 0.6317119393556538,
"grad_norm": 2.0735604763031006,
"learning_rate": 4.839742112141724e-05,
"loss": 8.7427,
"step": 125
},
{
"epoch": 0.6367656348704991,
"grad_norm": 1.3401007652282715,
"learning_rate": 4.732984846732755e-05,
"loss": 8.7623,
"step": 126
},
{
"epoch": 0.6418193303853443,
"grad_norm": 1.1091989278793335,
"learning_rate": 4.626349532067879e-05,
"loss": 8.7094,
"step": 127
},
{
"epoch": 0.6468730259001895,
"grad_norm": 1.1784418821334839,
"learning_rate": 4.5198848704615914e-05,
"loss": 8.5668,
"step": 128
},
{
"epoch": 0.6519267214150347,
"grad_norm": 1.323731541633606,
"learning_rate": 4.4136394862879914e-05,
"loss": 8.4429,
"step": 129
},
{
"epoch": 0.65698041692988,
"grad_norm": 0.8502984642982483,
"learning_rate": 4.307661903773129e-05,
"loss": 8.7092,
"step": 130
},
{
"epoch": 0.6620341124447252,
"grad_norm": 1.1920008659362793,
"learning_rate": 4.2020005248331054e-05,
"loss": 8.4987,
"step": 131
},
{
"epoch": 0.6670878079595705,
"grad_norm": 1.0251978635787964,
"learning_rate": 4.096703606968006e-05,
"loss": 8.6157,
"step": 132
},
{
"epoch": 0.6721415034744157,
"grad_norm": 1.0642647743225098,
"learning_rate": 3.991819241221835e-05,
"loss": 8.4535,
"step": 133
},
{
"epoch": 0.677195198989261,
"grad_norm": 1.3170267343521118,
"learning_rate": 3.887395330218429e-05,
"loss": 8.4171,
"step": 134
},
{
"epoch": 0.6822488945041061,
"grad_norm": 1.0994036197662354,
"learning_rate": 3.783479566283457e-05,
"loss": 8.6795,
"step": 135
},
{
"epoch": 0.6873025900189513,
"grad_norm": 1.2040021419525146,
"learning_rate": 3.680119409662452e-05,
"loss": 8.5518,
"step": 136
},
{
"epoch": 0.6923562855337966,
"grad_norm": 1.1834477186203003,
"learning_rate": 3.5773620668448384e-05,
"loss": 8.6813,
"step": 137
},
{
"epoch": 0.6974099810486418,
"grad_norm": 0.9281287789344788,
"learning_rate": 3.4752544690038647e-05,
"loss": 8.535,
"step": 138
},
{
"epoch": 0.7024636765634871,
"grad_norm": 1.0375516414642334,
"learning_rate": 3.373843250562265e-05,
"loss": 8.5263,
"step": 139
},
{
"epoch": 0.7075173720783323,
"grad_norm": 0.9735792279243469,
"learning_rate": 3.273174727893463e-05,
"loss": 8.4796,
"step": 140
},
{
"epoch": 0.7125710675931776,
"grad_norm": 1.0425305366516113,
"learning_rate": 3.173294878168025e-05,
"loss": 8.4304,
"step": 141
},
{
"epoch": 0.7176247631080227,
"grad_norm": 1.076398491859436,
"learning_rate": 3.074249318355046e-05,
"loss": 8.4417,
"step": 142
},
{
"epoch": 0.722678458622868,
"grad_norm": 1.0114437341690063,
"learning_rate": 2.976083284388031e-05,
"loss": 8.3947,
"step": 143
},
{
"epoch": 0.7277321541377132,
"grad_norm": 1.0746240615844727,
"learning_rate": 2.8788416105048122e-05,
"loss": 8.3048,
"step": 144
},
{
"epoch": 0.7327858496525584,
"grad_norm": 1.0370659828186035,
"learning_rate": 2.7825687087709328e-05,
"loss": 8.3032,
"step": 145
},
{
"epoch": 0.7378395451674037,
"grad_norm": 1.1819736957550049,
"learning_rate": 2.687308548795825e-05,
"loss": 8.3238,
"step": 146
},
{
"epoch": 0.7428932406822489,
"grad_norm": 1.3127453327178955,
"learning_rate": 2.5931046376510877e-05,
"loss": 8.5473,
"step": 147
},
{
"epoch": 0.7479469361970941,
"grad_norm": 1.3957887887954712,
"learning_rate": 2.500000000000001e-05,
"loss": 8.4965,
"step": 148
},
{
"epoch": 0.7530006317119393,
"grad_norm": 1.6841113567352295,
"learning_rate": 2.4080371584473748e-05,
"loss": 8.5345,
"step": 149
},
{
"epoch": 0.7580543272267846,
"grad_norm": 2.3189311027526855,
"learning_rate": 2.317258114118686e-05,
"loss": 8.6134,
"step": 150
},
{
"epoch": 0.7580543272267846,
"eval_loss": 8.470457077026367,
"eval_runtime": 8.309,
"eval_samples_per_second": 40.198,
"eval_steps_per_second": 10.11,
"step": 150
},
{
"epoch": 0.7631080227416298,
"grad_norm": 1.57240629196167,
"learning_rate": 2.2277043274773857e-05,
"loss": 8.6231,
"step": 151
},
{
"epoch": 0.7681617182564751,
"grad_norm": 1.579606294631958,
"learning_rate": 2.139416699389153e-05,
"loss": 8.7382,
"step": 152
},
{
"epoch": 0.7732154137713203,
"grad_norm": 1.3761146068572998,
"learning_rate": 2.0524355524417017e-05,
"loss": 8.6744,
"step": 153
},
{
"epoch": 0.7782691092861656,
"grad_norm": 1.1861869096755981,
"learning_rate": 1.966800612528723e-05,
"loss": 8.5027,
"step": 154
},
{
"epoch": 0.7833228048010107,
"grad_norm": 1.0866706371307373,
"learning_rate": 1.8825509907063327e-05,
"loss": 8.4262,
"step": 155
},
{
"epoch": 0.7883765003158559,
"grad_norm": 1.204898476600647,
"learning_rate": 1.7997251653303248e-05,
"loss": 8.3984,
"step": 156
},
{
"epoch": 0.7934301958307012,
"grad_norm": 1.0119705200195312,
"learning_rate": 1.7183609644824096e-05,
"loss": 8.56,
"step": 157
},
{
"epoch": 0.7984838913455464,
"grad_norm": 0.953957200050354,
"learning_rate": 1.6384955486934156e-05,
"loss": 8.5253,
"step": 158
},
{
"epoch": 0.8035375868603917,
"grad_norm": 1.0408637523651123,
"learning_rate": 1.5601653939714074e-05,
"loss": 8.3057,
"step": 159
},
{
"epoch": 0.8085912823752369,
"grad_norm": 0.88932204246521,
"learning_rate": 1.4834062751424015e-05,
"loss": 8.4848,
"step": 160
},
{
"epoch": 0.8136449778900822,
"grad_norm": 0.8721324801445007,
"learning_rate": 1.4082532495113626e-05,
"loss": 8.5545,
"step": 161
},
{
"epoch": 0.8186986734049273,
"grad_norm": 0.8064855933189392,
"learning_rate": 1.3347406408508695e-05,
"loss": 8.4817,
"step": 162
},
{
"epoch": 0.8237523689197725,
"grad_norm": 0.9848885536193848,
"learning_rate": 1.262902023724824e-05,
"loss": 8.5021,
"step": 163
},
{
"epoch": 0.8288060644346178,
"grad_norm": 1.0922009944915771,
"learning_rate": 1.1927702081543279e-05,
"loss": 8.1272,
"step": 164
},
{
"epoch": 0.833859759949463,
"grad_norm": 0.9150477051734924,
"learning_rate": 1.1243772246327416e-05,
"loss": 8.3211,
"step": 165
},
{
"epoch": 0.8389134554643083,
"grad_norm": 1.0169014930725098,
"learning_rate": 1.0577543094967612e-05,
"loss": 8.3955,
"step": 166
},
{
"epoch": 0.8439671509791535,
"grad_norm": 1.039054036140442,
"learning_rate": 9.929318906602175e-06,
"loss": 8.3066,
"step": 167
},
{
"epoch": 0.8490208464939988,
"grad_norm": 1.2704006433486938,
"learning_rate": 9.299395737170757e-06,
"loss": 8.1375,
"step": 168
},
{
"epoch": 0.8540745420088439,
"grad_norm": 1.1755458116531372,
"learning_rate": 8.688061284200266e-06,
"loss": 8.1842,
"step": 169
},
{
"epoch": 0.8591282375236892,
"grad_norm": 1.1061482429504395,
"learning_rate": 8.09559475540797e-06,
"loss": 8.4689,
"step": 170
},
{
"epoch": 0.8641819330385344,
"grad_norm": 1.089499831199646,
"learning_rate": 7.522266741182305e-06,
"loss": 8.2855,
"step": 171
},
{
"epoch": 0.8692356285533797,
"grad_norm": 1.1633696556091309,
"learning_rate": 6.968339090999187e-06,
"loss": 8.4485,
"step": 172
},
{
"epoch": 0.8742893240682249,
"grad_norm": 1.172793984413147,
"learning_rate": 6.43406479383053e-06,
"loss": 8.4008,
"step": 173
},
{
"epoch": 0.8793430195830702,
"grad_norm": 1.4023175239562988,
"learning_rate": 5.919687862599549e-06,
"loss": 8.603,
"step": 174
},
{
"epoch": 0.8843967150979154,
"grad_norm": 2.343562602996826,
"learning_rate": 5.425443222735527e-06,
"loss": 8.4168,
"step": 175
},
{
"epoch": 0.8894504106127605,
"grad_norm": 1.2631791830062866,
"learning_rate": 4.951556604879048e-06,
"loss": 8.6435,
"step": 176
},
{
"epoch": 0.8945041061276058,
"grad_norm": 1.2387241125106812,
"learning_rate": 4.498244441786675e-06,
"loss": 8.5938,
"step": 177
},
{
"epoch": 0.899557801642451,
"grad_norm": 0.9759954214096069,
"learning_rate": 4.065713769482082e-06,
"loss": 8.7213,
"step": 178
},
{
"epoch": 0.9046114971572963,
"grad_norm": 0.8986900448799133,
"learning_rate": 3.654162132698918e-06,
"loss": 8.5998,
"step": 179
},
{
"epoch": 0.9096651926721415,
"grad_norm": 0.8717695474624634,
"learning_rate": 3.2637774946584486e-06,
"loss": 8.6061,
"step": 180
},
{
"epoch": 0.9147188881869868,
"grad_norm": 0.9505631327629089,
"learning_rate": 2.894738151223331e-06,
"loss": 8.5173,
"step": 181
},
{
"epoch": 0.919772583701832,
"grad_norm": 0.8661491870880127,
"learning_rate": 2.547212649466568e-06,
"loss": 8.5595,
"step": 182
},
{
"epoch": 0.9248262792166771,
"grad_norm": 0.8975613117218018,
"learning_rate": 2.221359710692961e-06,
"loss": 8.483,
"step": 183
},
{
"epoch": 0.9298799747315224,
"grad_norm": 0.8268275856971741,
"learning_rate": 1.9173281579481892e-06,
"loss": 8.4253,
"step": 184
},
{
"epoch": 0.9349336702463676,
"grad_norm": 0.9205915927886963,
"learning_rate": 1.6352568480485276e-06,
"loss": 8.5825,
"step": 185
},
{
"epoch": 0.9399873657612129,
"grad_norm": 0.8719313740730286,
"learning_rate": 1.3752746081624467e-06,
"loss": 8.3617,
"step": 186
},
{
"epoch": 0.9450410612760581,
"grad_norm": 0.9109625816345215,
"learning_rate": 1.1375001769727999e-06,
"loss": 8.3006,
"step": 187
},
{
"epoch": 0.9500947567909034,
"grad_norm": 0.8622517585754395,
"learning_rate": 9.220421504467281e-07,
"loss": 8.4956,
"step": 188
},
{
"epoch": 0.9551484523057486,
"grad_norm": 0.9728400707244873,
"learning_rate": 7.289989322378732e-07,
"loss": 8.4565,
"step": 189
},
{
"epoch": 0.9602021478205938,
"grad_norm": 0.9318665862083435,
"learning_rate": 5.584586887435739e-07,
"loss": 8.3316,
"step": 190
},
{
"epoch": 0.965255843335439,
"grad_norm": 0.9625034332275391,
"learning_rate": 4.104993088376974e-07,
"loss": 8.3455,
"step": 191
},
{
"epoch": 0.9703095388502843,
"grad_norm": 1.1241123676300049,
"learning_rate": 2.851883682973233e-07,
"loss": 8.0974,
"step": 192
},
{
"epoch": 0.9753632343651295,
"grad_norm": 1.197749137878418,
"learning_rate": 1.8258309893965375e-07,
"loss": 8.19,
"step": 193
},
{
"epoch": 0.9804169298799748,
"grad_norm": 0.9713776111602783,
"learning_rate": 1.0273036248318324e-07,
"loss": 8.4274,
"step": 194
},
{
"epoch": 0.98547062539482,
"grad_norm": 1.0657098293304443,
"learning_rate": 4.566662914508579e-08,
"loss": 8.2398,
"step": 195
},
{
"epoch": 0.9905243209096652,
"grad_norm": 1.2770274877548218,
"learning_rate": 1.1417960984605458e-08,
"loss": 8.5457,
"step": 196
},
{
"epoch": 0.9955780164245104,
"grad_norm": 1.4860167503356934,
"learning_rate": 0.0,
"loss": 8.5989,
"step": 197
}
],
"logging_steps": 1,
"max_steps": 197,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 223101181231104.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}