vntl-gemma2-2b-lora / checkpoint-430 /trainer_state.json
lmg-anon's picture
Upload folder using huggingface_hub
cf39eca verified
raw
history blame
75.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.99953509995351,
"eval_steps": 500,
"global_step": 430,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0023245002324500234,
"grad_norm": 24.9628849029541,
"learning_rate": 7.222222222222221e-06,
"loss": 2.9398,
"step": 1
},
{
"epoch": 0.004649000464900047,
"grad_norm": 27.249839782714844,
"learning_rate": 1.4444444444444442e-05,
"loss": 3.0436,
"step": 2
},
{
"epoch": 0.00697350069735007,
"grad_norm": 29.58257293701172,
"learning_rate": 2.1666666666666664e-05,
"loss": 2.5493,
"step": 3
},
{
"epoch": 0.009298000929800094,
"grad_norm": 21.416799545288086,
"learning_rate": 2.8888888888888885e-05,
"loss": 1.5315,
"step": 4
},
{
"epoch": 0.011622501162250116,
"grad_norm": 6.383184909820557,
"learning_rate": 3.611111111111111e-05,
"loss": 1.2681,
"step": 5
},
{
"epoch": 0.01394700139470014,
"grad_norm": 3.6736369132995605,
"learning_rate": 4.333333333333333e-05,
"loss": 1.1031,
"step": 6
},
{
"epoch": 0.016271501627150162,
"grad_norm": 2.394563913345337,
"learning_rate": 5.055555555555555e-05,
"loss": 1.1564,
"step": 7
},
{
"epoch": 0.018596001859600187,
"grad_norm": 2.2405858039855957,
"learning_rate": 5.777777777777777e-05,
"loss": 1.1077,
"step": 8
},
{
"epoch": 0.02092050209205021,
"grad_norm": 2.2083897590637207,
"learning_rate": 6.5e-05,
"loss": 1.0652,
"step": 9
},
{
"epoch": 0.023245002324500233,
"grad_norm": 2.0182244777679443,
"learning_rate": 6.499909512851264e-05,
"loss": 1.0865,
"step": 10
},
{
"epoch": 0.025569502556950254,
"grad_norm": 1.935754418373108,
"learning_rate": 6.499638056443783e-05,
"loss": 1.1143,
"step": 11
},
{
"epoch": 0.02789400278940028,
"grad_norm": 1.7560354471206665,
"learning_rate": 6.499185645893443e-05,
"loss": 1.0293,
"step": 12
},
{
"epoch": 0.030218503021850304,
"grad_norm": 1.882704496383667,
"learning_rate": 6.498552306392452e-05,
"loss": 1.1189,
"step": 13
},
{
"epoch": 0.032543003254300325,
"grad_norm": 1.6570043563842773,
"learning_rate": 6.49773807320794e-05,
"loss": 1.024,
"step": 14
},
{
"epoch": 0.03486750348675035,
"grad_norm": 1.6351194381713867,
"learning_rate": 6.496742991679994e-05,
"loss": 1.1053,
"step": 15
},
{
"epoch": 0.037192003719200374,
"grad_norm": 1.693750023841858,
"learning_rate": 6.495567117219131e-05,
"loss": 1.0443,
"step": 16
},
{
"epoch": 0.03951650395165039,
"grad_norm": 1.6009650230407715,
"learning_rate": 6.494210515303213e-05,
"loss": 0.9832,
"step": 17
},
{
"epoch": 0.04184100418410042,
"grad_norm": 1.6692452430725098,
"learning_rate": 6.492673261473802e-05,
"loss": 0.9498,
"step": 18
},
{
"epoch": 0.04416550441655044,
"grad_norm": 1.6801658868789673,
"learning_rate": 6.490955441331956e-05,
"loss": 0.9983,
"step": 19
},
{
"epoch": 0.046490004649000466,
"grad_norm": 1.5920137166976929,
"learning_rate": 6.489057150533456e-05,
"loss": 1.0731,
"step": 20
},
{
"epoch": 0.04881450488145049,
"grad_norm": 1.5493357181549072,
"learning_rate": 6.486978494783486e-05,
"loss": 0.9685,
"step": 21
},
{
"epoch": 0.05113900511390051,
"grad_norm": 1.4238895177841187,
"learning_rate": 6.484719589830741e-05,
"loss": 0.9721,
"step": 22
},
{
"epoch": 0.05346350534635053,
"grad_norm": 1.572223424911499,
"learning_rate": 6.482280561460986e-05,
"loss": 1.0263,
"step": 23
},
{
"epoch": 0.05578800557880056,
"grad_norm": 1.4538493156433105,
"learning_rate": 6.479661545490052e-05,
"loss": 1.0008,
"step": 24
},
{
"epoch": 0.05811250581125058,
"grad_norm": 1.4649128913879395,
"learning_rate": 6.47686268775627e-05,
"loss": 1.0391,
"step": 25
},
{
"epoch": 0.06043700604370061,
"grad_norm": 1.4427037239074707,
"learning_rate": 6.473884144112351e-05,
"loss": 0.9842,
"step": 26
},
{
"epoch": 0.06276150627615062,
"grad_norm": 1.5365402698516846,
"learning_rate": 6.470726080416707e-05,
"loss": 1.027,
"step": 27
},
{
"epoch": 0.06508600650860065,
"grad_norm": 1.58499014377594,
"learning_rate": 6.467388672524219e-05,
"loss": 1.0134,
"step": 28
},
{
"epoch": 0.06741050674105067,
"grad_norm": 1.4400190114974976,
"learning_rate": 6.463872106276442e-05,
"loss": 0.9216,
"step": 29
},
{
"epoch": 0.0697350069735007,
"grad_norm": 1.5131999254226685,
"learning_rate": 6.46017657749125e-05,
"loss": 0.9949,
"step": 30
},
{
"epoch": 0.07205950720595072,
"grad_norm": 1.4283956289291382,
"learning_rate": 6.456302291951948e-05,
"loss": 0.9467,
"step": 31
},
{
"epoch": 0.07438400743840075,
"grad_norm": 1.48639714717865,
"learning_rate": 6.452249465395796e-05,
"loss": 1.007,
"step": 32
},
{
"epoch": 0.07670850767085077,
"grad_norm": 1.3868178129196167,
"learning_rate": 6.448018323502007e-05,
"loss": 0.9728,
"step": 33
},
{
"epoch": 0.07903300790330078,
"grad_norm": 1.442160725593567,
"learning_rate": 6.443609101879175e-05,
"loss": 0.9678,
"step": 34
},
{
"epoch": 0.08135750813575081,
"grad_norm": 1.334540843963623,
"learning_rate": 6.439022046052158e-05,
"loss": 0.9515,
"step": 35
},
{
"epoch": 0.08368200836820083,
"grad_norm": 1.3423985242843628,
"learning_rate": 6.434257411448404e-05,
"loss": 0.9431,
"step": 36
},
{
"epoch": 0.08600650860065086,
"grad_norm": 1.3876471519470215,
"learning_rate": 6.429315463383725e-05,
"loss": 0.9427,
"step": 37
},
{
"epoch": 0.08833100883310088,
"grad_norm": 1.3787826299667358,
"learning_rate": 6.424196477047534e-05,
"loss": 0.956,
"step": 38
},
{
"epoch": 0.09065550906555091,
"grad_norm": 1.393442153930664,
"learning_rate": 6.418900737487508e-05,
"loss": 0.9742,
"step": 39
},
{
"epoch": 0.09298000929800093,
"grad_norm": 1.3465863466262817,
"learning_rate": 6.413428539593724e-05,
"loss": 0.9512,
"step": 40
},
{
"epoch": 0.09530450953045096,
"grad_norm": 1.3853354454040527,
"learning_rate": 6.407780188082231e-05,
"loss": 0.9802,
"step": 41
},
{
"epoch": 0.09762900976290098,
"grad_norm": 1.506191372871399,
"learning_rate": 6.401955997478094e-05,
"loss": 0.9839,
"step": 42
},
{
"epoch": 0.099953509995351,
"grad_norm": 1.346642255783081,
"learning_rate": 6.395956292097865e-05,
"loss": 0.9612,
"step": 43
},
{
"epoch": 0.10227801022780102,
"grad_norm": 1.4252711534500122,
"learning_rate": 6.389781406031533e-05,
"loss": 0.966,
"step": 44
},
{
"epoch": 0.10460251046025104,
"grad_norm": 1.3196333646774292,
"learning_rate": 6.383431683123921e-05,
"loss": 0.9783,
"step": 45
},
{
"epoch": 0.10692701069270107,
"grad_norm": 1.334774136543274,
"learning_rate": 6.376907476955534e-05,
"loss": 0.9661,
"step": 46
},
{
"epoch": 0.10925151092515109,
"grad_norm": 1.3319814205169678,
"learning_rate": 6.370209150822871e-05,
"loss": 0.9326,
"step": 47
},
{
"epoch": 0.11157601115760112,
"grad_norm": 1.3688098192214966,
"learning_rate": 6.3633370777182e-05,
"loss": 0.9141,
"step": 48
},
{
"epoch": 0.11390051139005114,
"grad_norm": 1.375450849533081,
"learning_rate": 6.356291640308783e-05,
"loss": 0.937,
"step": 49
},
{
"epoch": 0.11622501162250116,
"grad_norm": 1.4250009059906006,
"learning_rate": 6.349073230915569e-05,
"loss": 0.9604,
"step": 50
},
{
"epoch": 0.11854951185495119,
"grad_norm": 1.3212535381317139,
"learning_rate": 6.34168225149135e-05,
"loss": 0.9432,
"step": 51
},
{
"epoch": 0.12087401208740121,
"grad_norm": 1.3916277885437012,
"learning_rate": 6.334119113598371e-05,
"loss": 1.0155,
"step": 52
},
{
"epoch": 0.12319851231985124,
"grad_norm": 1.278640627861023,
"learning_rate": 6.326384238385426e-05,
"loss": 0.9462,
"step": 53
},
{
"epoch": 0.12552301255230125,
"grad_norm": 1.3200207948684692,
"learning_rate": 6.318478056564394e-05,
"loss": 0.9506,
"step": 54
},
{
"epoch": 0.1278475127847513,
"grad_norm": 1.2866770029067993,
"learning_rate": 6.310401008386256e-05,
"loss": 0.9299,
"step": 55
},
{
"epoch": 0.1301720130172013,
"grad_norm": 1.3080073595046997,
"learning_rate": 6.302153543616591e-05,
"loss": 0.9416,
"step": 56
},
{
"epoch": 0.13249651324965134,
"grad_norm": 1.306003451347351,
"learning_rate": 6.293736121510519e-05,
"loss": 0.96,
"step": 57
},
{
"epoch": 0.13482101348210135,
"grad_norm": 1.2852219343185425,
"learning_rate": 6.285149210787132e-05,
"loss": 0.9077,
"step": 58
},
{
"epoch": 0.13714551371455136,
"grad_norm": 1.312796711921692,
"learning_rate": 6.276393289603395e-05,
"loss": 0.96,
"step": 59
},
{
"epoch": 0.1394700139470014,
"grad_norm": 1.3223918676376343,
"learning_rate": 6.267468845527521e-05,
"loss": 0.9349,
"step": 60
},
{
"epoch": 0.1417945141794514,
"grad_norm": 1.2744101285934448,
"learning_rate": 6.258376375511813e-05,
"loss": 0.9634,
"step": 61
},
{
"epoch": 0.14411901441190145,
"grad_norm": 1.2165145874023438,
"learning_rate": 6.249116385865003e-05,
"loss": 0.883,
"step": 62
},
{
"epoch": 0.14644351464435146,
"grad_norm": 1.3080806732177734,
"learning_rate": 6.239689392224053e-05,
"loss": 0.9183,
"step": 63
},
{
"epoch": 0.1487680148768015,
"grad_norm": 1.3560563325881958,
"learning_rate": 6.230095919525438e-05,
"loss": 0.8918,
"step": 64
},
{
"epoch": 0.1510925151092515,
"grad_norm": 1.3362810611724854,
"learning_rate": 6.220336501975922e-05,
"loss": 0.9218,
"step": 65
},
{
"epoch": 0.15341701534170155,
"grad_norm": 1.4007967710494995,
"learning_rate": 6.21041168302281e-05,
"loss": 0.9743,
"step": 66
},
{
"epoch": 0.15574151557415156,
"grad_norm": 1.2750542163848877,
"learning_rate": 6.200322015323678e-05,
"loss": 0.9101,
"step": 67
},
{
"epoch": 0.15806601580660157,
"grad_norm": 1.3171645402908325,
"learning_rate": 6.190068060715615e-05,
"loss": 0.9494,
"step": 68
},
{
"epoch": 0.1603905160390516,
"grad_norm": 1.2462354898452759,
"learning_rate": 6.179650390183923e-05,
"loss": 0.9074,
"step": 69
},
{
"epoch": 0.16271501627150162,
"grad_norm": 1.2816126346588135,
"learning_rate": 6.169069583830324e-05,
"loss": 0.9672,
"step": 70
},
{
"epoch": 0.16503951650395166,
"grad_norm": 1.360295057296753,
"learning_rate": 6.158326230840664e-05,
"loss": 0.9216,
"step": 71
},
{
"epoch": 0.16736401673640167,
"grad_norm": 1.454693078994751,
"learning_rate": 6.1474209294521e-05,
"loss": 0.9648,
"step": 72
},
{
"epoch": 0.1696885169688517,
"grad_norm": 1.2523744106292725,
"learning_rate": 6.136354286919789e-05,
"loss": 0.9098,
"step": 73
},
{
"epoch": 0.17201301720130172,
"grad_norm": 1.265788197517395,
"learning_rate": 6.125126919483069e-05,
"loss": 0.8955,
"step": 74
},
{
"epoch": 0.17433751743375175,
"grad_norm": 1.2782336473464966,
"learning_rate": 6.113739452331156e-05,
"loss": 0.9257,
"step": 75
},
{
"epoch": 0.17666201766620176,
"grad_norm": 1.3308346271514893,
"learning_rate": 6.102192519568312e-05,
"loss": 0.9581,
"step": 76
},
{
"epoch": 0.1789865178986518,
"grad_norm": 1.3193368911743164,
"learning_rate": 6.0904867641785524e-05,
"loss": 0.9376,
"step": 77
},
{
"epoch": 0.18131101813110181,
"grad_norm": 1.2379558086395264,
"learning_rate": 6.078622837989834e-05,
"loss": 0.8897,
"step": 78
},
{
"epoch": 0.18363551836355183,
"grad_norm": 1.314134120941162,
"learning_rate": 6.0666014016377575e-05,
"loss": 0.9065,
"step": 79
},
{
"epoch": 0.18596001859600186,
"grad_norm": 1.3453565835952759,
"learning_rate": 6.0544231245287847e-05,
"loss": 0.9992,
"step": 80
},
{
"epoch": 0.18828451882845187,
"grad_norm": 1.2375950813293457,
"learning_rate": 6.042088684802962e-05,
"loss": 0.8979,
"step": 81
},
{
"epoch": 0.1906090190609019,
"grad_norm": 1.2984182834625244,
"learning_rate": 6.029598769296152e-05,
"loss": 0.9209,
"step": 82
},
{
"epoch": 0.19293351929335192,
"grad_norm": 1.264028787612915,
"learning_rate": 6.0169540735017986e-05,
"loss": 0.9202,
"step": 83
},
{
"epoch": 0.19525801952580196,
"grad_norm": 1.2835426330566406,
"learning_rate": 6.004155301532189e-05,
"loss": 0.9103,
"step": 84
},
{
"epoch": 0.19758251975825197,
"grad_norm": 1.3315404653549194,
"learning_rate": 5.991203166079251e-05,
"loss": 0.9246,
"step": 85
},
{
"epoch": 0.199907019990702,
"grad_norm": 1.2901430130004883,
"learning_rate": 5.978098388374867e-05,
"loss": 0.9187,
"step": 86
},
{
"epoch": 0.20223152022315202,
"grad_norm": 1.2905139923095703,
"learning_rate": 5.964841698150709e-05,
"loss": 0.8755,
"step": 87
},
{
"epoch": 0.20455602045560203,
"grad_norm": 1.284635305404663,
"learning_rate": 5.95143383359761e-05,
"loss": 0.9376,
"step": 88
},
{
"epoch": 0.20688052068805207,
"grad_norm": 1.274927020072937,
"learning_rate": 5.93787554132445e-05,
"loss": 0.8953,
"step": 89
},
{
"epoch": 0.20920502092050208,
"grad_norm": 1.275505542755127,
"learning_rate": 5.92416757631659e-05,
"loss": 0.9458,
"step": 90
},
{
"epoch": 0.21152952115295212,
"grad_norm": 1.249010443687439,
"learning_rate": 5.910310701893825e-05,
"loss": 0.9195,
"step": 91
},
{
"epoch": 0.21385402138540213,
"grad_norm": 1.2102458477020264,
"learning_rate": 5.896305689667885e-05,
"loss": 0.9237,
"step": 92
},
{
"epoch": 0.21617852161785217,
"grad_norm": 1.2785658836364746,
"learning_rate": 5.882153319499459e-05,
"loss": 0.9474,
"step": 93
},
{
"epoch": 0.21850302185030218,
"grad_norm": 1.2559230327606201,
"learning_rate": 5.867854379454777e-05,
"loss": 0.8634,
"step": 94
},
{
"epoch": 0.22082752208275222,
"grad_norm": 1.1916835308074951,
"learning_rate": 5.8534096657617286e-05,
"loss": 0.8826,
"step": 95
},
{
"epoch": 0.22315202231520223,
"grad_norm": 1.2259260416030884,
"learning_rate": 5.838819982765514e-05,
"loss": 0.8864,
"step": 96
},
{
"epoch": 0.22547652254765224,
"grad_norm": 1.2614275217056274,
"learning_rate": 5.824086142883867e-05,
"loss": 0.8649,
"step": 97
},
{
"epoch": 0.22780102278010228,
"grad_norm": 1.3275364637374878,
"learning_rate": 5.8092089665618096e-05,
"loss": 0.9218,
"step": 98
},
{
"epoch": 0.2301255230125523,
"grad_norm": 1.2847840785980225,
"learning_rate": 5.7941892822259686e-05,
"loss": 0.8976,
"step": 99
},
{
"epoch": 0.23245002324500233,
"grad_norm": 1.2817707061767578,
"learning_rate": 5.779027926238441e-05,
"loss": 0.9278,
"step": 100
},
{
"epoch": 0.23477452347745234,
"grad_norm": 1.2560011148452759,
"learning_rate": 5.7637257428502266e-05,
"loss": 0.9113,
"step": 101
},
{
"epoch": 0.23709902370990238,
"grad_norm": 1.222548484802246,
"learning_rate": 5.748283584154215e-05,
"loss": 0.8772,
"step": 102
},
{
"epoch": 0.2394235239423524,
"grad_norm": 1.2913312911987305,
"learning_rate": 5.7327023100377346e-05,
"loss": 0.9342,
"step": 103
},
{
"epoch": 0.24174802417480243,
"grad_norm": 1.1847671270370483,
"learning_rate": 5.716982788134676e-05,
"loss": 0.8713,
"step": 104
},
{
"epoch": 0.24407252440725244,
"grad_norm": 1.2654389142990112,
"learning_rate": 5.70112589377717e-05,
"loss": 0.8818,
"step": 105
},
{
"epoch": 0.24639702463970248,
"grad_norm": 1.2268662452697754,
"learning_rate": 5.6851325099468526e-05,
"loss": 0.8754,
"step": 106
},
{
"epoch": 0.2487215248721525,
"grad_norm": 1.30552339553833,
"learning_rate": 5.669003527225696e-05,
"loss": 0.946,
"step": 107
},
{
"epoch": 0.2510460251046025,
"grad_norm": 1.239740252494812,
"learning_rate": 5.65273984374641e-05,
"loss": 0.9061,
"step": 108
},
{
"epoch": 0.2533705253370525,
"grad_norm": 1.2037532329559326,
"learning_rate": 5.6363423651424416e-05,
"loss": 0.9221,
"step": 109
},
{
"epoch": 0.2556950255695026,
"grad_norm": 1.3354305028915405,
"learning_rate": 5.6198120044975337e-05,
"loss": 0.9359,
"step": 110
},
{
"epoch": 0.2580195258019526,
"grad_norm": 1.3739912509918213,
"learning_rate": 5.603149682294886e-05,
"loss": 0.9305,
"step": 111
},
{
"epoch": 0.2603440260344026,
"grad_norm": 1.2662415504455566,
"learning_rate": 5.586356326365904e-05,
"loss": 0.8996,
"step": 112
},
{
"epoch": 0.2626685262668526,
"grad_norm": 1.3930978775024414,
"learning_rate": 5.5694328718385214e-05,
"loss": 0.9477,
"step": 113
},
{
"epoch": 0.2649930264993027,
"grad_norm": 1.276788592338562,
"learning_rate": 5.552380261085135e-05,
"loss": 0.886,
"step": 114
},
{
"epoch": 0.2673175267317527,
"grad_norm": 1.2634483575820923,
"learning_rate": 5.5351994436701326e-05,
"loss": 0.9207,
"step": 115
},
{
"epoch": 0.2696420269642027,
"grad_norm": 1.3280141353607178,
"learning_rate": 5.5178913762970074e-05,
"loss": 0.916,
"step": 116
},
{
"epoch": 0.2719665271966527,
"grad_norm": 1.2456930875778198,
"learning_rate": 5.500457022755095e-05,
"loss": 0.8524,
"step": 117
},
{
"epoch": 0.2742910274291027,
"grad_norm": 1.2636594772338867,
"learning_rate": 5.4828973538658974e-05,
"loss": 0.9525,
"step": 118
},
{
"epoch": 0.2766155276615528,
"grad_norm": 1.223232626914978,
"learning_rate": 5.465213347429026e-05,
"loss": 0.8556,
"step": 119
},
{
"epoch": 0.2789400278940028,
"grad_norm": 1.414523720741272,
"learning_rate": 5.4474059881677566e-05,
"loss": 0.9719,
"step": 120
},
{
"epoch": 0.2812645281264528,
"grad_norm": 1.2748632431030273,
"learning_rate": 5.42947626767419e-05,
"loss": 0.9076,
"step": 121
},
{
"epoch": 0.2835890283589028,
"grad_norm": 1.1875295639038086,
"learning_rate": 5.411425184354042e-05,
"loss": 0.8475,
"step": 122
},
{
"epoch": 0.2859135285913529,
"grad_norm": 1.168205976486206,
"learning_rate": 5.393253743371041e-05,
"loss": 0.8827,
"step": 123
},
{
"epoch": 0.2882380288238029,
"grad_norm": 1.2521716356277466,
"learning_rate": 5.3749629565909614e-05,
"loss": 0.9238,
"step": 124
},
{
"epoch": 0.2905625290562529,
"grad_norm": 1.3135292530059814,
"learning_rate": 5.356553842525278e-05,
"loss": 0.9562,
"step": 125
},
{
"epoch": 0.2928870292887029,
"grad_norm": 1.1815370321273804,
"learning_rate": 5.3380274262744447e-05,
"loss": 0.8571,
"step": 126
},
{
"epoch": 0.2952115295211529,
"grad_norm": 1.2776923179626465,
"learning_rate": 5.319384739470821e-05,
"loss": 0.9234,
"step": 127
},
{
"epoch": 0.297536029753603,
"grad_norm": 1.3336985111236572,
"learning_rate": 5.300626820221224e-05,
"loss": 0.9257,
"step": 128
},
{
"epoch": 0.299860529986053,
"grad_norm": 1.2534116506576538,
"learning_rate": 5.2817547130491154e-05,
"loss": 0.8918,
"step": 129
},
{
"epoch": 0.302185030218503,
"grad_norm": 1.2334403991699219,
"learning_rate": 5.262769468836446e-05,
"loss": 0.8407,
"step": 130
},
{
"epoch": 0.304509530450953,
"grad_norm": 1.2081224918365479,
"learning_rate": 5.2436721447651325e-05,
"loss": 0.8976,
"step": 131
},
{
"epoch": 0.3068340306834031,
"grad_norm": 1.3717191219329834,
"learning_rate": 5.224463804258194e-05,
"loss": 0.9156,
"step": 132
},
{
"epoch": 0.3091585309158531,
"grad_norm": 1.2610055208206177,
"learning_rate": 5.205145516920531e-05,
"loss": 0.925,
"step": 133
},
{
"epoch": 0.3114830311483031,
"grad_norm": 1.2727302312850952,
"learning_rate": 5.185718358479369e-05,
"loss": 0.9217,
"step": 134
},
{
"epoch": 0.3138075313807531,
"grad_norm": 1.2891085147857666,
"learning_rate": 5.166183410724353e-05,
"loss": 0.9583,
"step": 135
},
{
"epoch": 0.31613203161320313,
"grad_norm": 1.1891586780548096,
"learning_rate": 5.146541761447313e-05,
"loss": 0.8329,
"step": 136
},
{
"epoch": 0.3184565318456532,
"grad_norm": 1.203373670578003,
"learning_rate": 5.1267945043816886e-05,
"loss": 0.8716,
"step": 137
},
{
"epoch": 0.3207810320781032,
"grad_norm": 1.2259798049926758,
"learning_rate": 5.106942739141625e-05,
"loss": 0.9246,
"step": 138
},
{
"epoch": 0.3231055323105532,
"grad_norm": 1.237679123878479,
"learning_rate": 5.086987571160746e-05,
"loss": 0.8769,
"step": 139
},
{
"epoch": 0.32543003254300323,
"grad_norm": 1.2703795433044434,
"learning_rate": 5.0669301116305886e-05,
"loss": 0.8838,
"step": 140
},
{
"epoch": 0.3277545327754533,
"grad_norm": 1.2701797485351562,
"learning_rate": 5.0467714774387386e-05,
"loss": 0.8438,
"step": 141
},
{
"epoch": 0.3300790330079033,
"grad_norm": 1.2709927558898926,
"learning_rate": 5.0265127911066295e-05,
"loss": 0.9252,
"step": 142
},
{
"epoch": 0.3324035332403533,
"grad_norm": 1.291172981262207,
"learning_rate": 5.0061551807270376e-05,
"loss": 0.93,
"step": 143
},
{
"epoch": 0.33472803347280333,
"grad_norm": 1.2257442474365234,
"learning_rate": 4.9856997799012677e-05,
"loss": 0.8957,
"step": 144
},
{
"epoch": 0.33705253370525334,
"grad_norm": 1.2257241010665894,
"learning_rate": 4.965147727676027e-05,
"loss": 0.9213,
"step": 145
},
{
"epoch": 0.3393770339377034,
"grad_norm": 1.16828191280365,
"learning_rate": 4.944500168479995e-05,
"loss": 0.8625,
"step": 146
},
{
"epoch": 0.3417015341701534,
"grad_norm": 1.2331054210662842,
"learning_rate": 4.9237582520600986e-05,
"loss": 0.9318,
"step": 147
},
{
"epoch": 0.34402603440260343,
"grad_norm": 1.2196905612945557,
"learning_rate": 4.902923133417496e-05,
"loss": 0.8709,
"step": 148
},
{
"epoch": 0.34635053463505344,
"grad_norm": 1.2139414548873901,
"learning_rate": 4.8819959727432496e-05,
"loss": 0.9081,
"step": 149
},
{
"epoch": 0.3486750348675035,
"grad_norm": 1.204951524734497,
"learning_rate": 4.86097793535373e-05,
"loss": 0.8331,
"step": 150
},
{
"epoch": 0.3509995350999535,
"grad_norm": 1.1808617115020752,
"learning_rate": 4.839870191625722e-05,
"loss": 0.865,
"step": 151
},
{
"epoch": 0.35332403533240353,
"grad_norm": 1.1742596626281738,
"learning_rate": 4.818673916931252e-05,
"loss": 0.8266,
"step": 152
},
{
"epoch": 0.35564853556485354,
"grad_norm": 1.2377365827560425,
"learning_rate": 4.797390291572145e-05,
"loss": 0.841,
"step": 153
},
{
"epoch": 0.3579730357973036,
"grad_norm": 1.2187622785568237,
"learning_rate": 4.7760205007142904e-05,
"loss": 0.875,
"step": 154
},
{
"epoch": 0.3602975360297536,
"grad_norm": 1.182664394378662,
"learning_rate": 4.754565734321654e-05,
"loss": 0.8742,
"step": 155
},
{
"epoch": 0.36262203626220363,
"grad_norm": 1.2196147441864014,
"learning_rate": 4.733027187090013e-05,
"loss": 0.8849,
"step": 156
},
{
"epoch": 0.36494653649465364,
"grad_norm": 1.2542427778244019,
"learning_rate": 4.711406058380429e-05,
"loss": 0.847,
"step": 157
},
{
"epoch": 0.36727103672710365,
"grad_norm": 1.2659164667129517,
"learning_rate": 4.689703552152467e-05,
"loss": 0.8557,
"step": 158
},
{
"epoch": 0.3695955369595537,
"grad_norm": 1.1970021724700928,
"learning_rate": 4.667920876897147e-05,
"loss": 0.8474,
"step": 159
},
{
"epoch": 0.3719200371920037,
"grad_norm": 1.2822171449661255,
"learning_rate": 4.646059245569654e-05,
"loss": 0.9273,
"step": 160
},
{
"epoch": 0.37424453742445374,
"grad_norm": 1.233355164527893,
"learning_rate": 4.6241198755217925e-05,
"loss": 0.8528,
"step": 161
},
{
"epoch": 0.37656903765690375,
"grad_norm": 1.2058496475219727,
"learning_rate": 4.602103988434206e-05,
"loss": 0.86,
"step": 162
},
{
"epoch": 0.3788935378893538,
"grad_norm": 1.3541826009750366,
"learning_rate": 4.5800128102483376e-05,
"loss": 0.9412,
"step": 163
},
{
"epoch": 0.3812180381218038,
"grad_norm": 1.1209250688552856,
"learning_rate": 4.5578475710981745e-05,
"loss": 0.8332,
"step": 164
},
{
"epoch": 0.38354253835425384,
"grad_norm": 1.2058111429214478,
"learning_rate": 4.535609505241742e-05,
"loss": 0.857,
"step": 165
},
{
"epoch": 0.38586703858670385,
"grad_norm": 1.2212828397750854,
"learning_rate": 4.513299850992376e-05,
"loss": 0.8301,
"step": 166
},
{
"epoch": 0.38819153881915386,
"grad_norm": 1.2507742643356323,
"learning_rate": 4.4909198506497725e-05,
"loss": 0.88,
"step": 167
},
{
"epoch": 0.3905160390516039,
"grad_norm": 1.1851963996887207,
"learning_rate": 4.4684707504308036e-05,
"loss": 0.8504,
"step": 168
},
{
"epoch": 0.39284053928405394,
"grad_norm": 1.1980507373809814,
"learning_rate": 4.4459538004001276e-05,
"loss": 0.8413,
"step": 169
},
{
"epoch": 0.39516503951650395,
"grad_norm": 1.210808515548706,
"learning_rate": 4.42337025440058e-05,
"loss": 0.8669,
"step": 170
},
{
"epoch": 0.39748953974895396,
"grad_norm": 1.1731034517288208,
"learning_rate": 4.400721369983352e-05,
"loss": 0.9147,
"step": 171
},
{
"epoch": 0.399814039981404,
"grad_norm": 1.2603881359100342,
"learning_rate": 4.3780084083379654e-05,
"loss": 0.8829,
"step": 172
},
{
"epoch": 0.40213854021385403,
"grad_norm": 1.2504175901412964,
"learning_rate": 4.3552326342220444e-05,
"loss": 0.8924,
"step": 173
},
{
"epoch": 0.40446304044630405,
"grad_norm": 1.1380208730697632,
"learning_rate": 4.332395315890887e-05,
"loss": 0.7826,
"step": 174
},
{
"epoch": 0.40678754067875406,
"grad_norm": 1.2040411233901978,
"learning_rate": 4.309497725026844e-05,
"loss": 0.8476,
"step": 175
},
{
"epoch": 0.40911204091120407,
"grad_norm": 1.2187401056289673,
"learning_rate": 4.2865411366685064e-05,
"loss": 0.8605,
"step": 176
},
{
"epoch": 0.41143654114365413,
"grad_norm": 1.2218343019485474,
"learning_rate": 4.2635268291397054e-05,
"loss": 0.8408,
"step": 177
},
{
"epoch": 0.41376104137610414,
"grad_norm": 1.3197338581085205,
"learning_rate": 4.240456083978329e-05,
"loss": 0.8658,
"step": 178
},
{
"epoch": 0.41608554160855415,
"grad_norm": 1.3240693807601929,
"learning_rate": 4.2173301858649605e-05,
"loss": 0.9434,
"step": 179
},
{
"epoch": 0.41841004184100417,
"grad_norm": 1.2702267169952393,
"learning_rate": 4.1941504225513445e-05,
"loss": 0.8643,
"step": 180
},
{
"epoch": 0.42073454207345423,
"grad_norm": 1.2468559741973877,
"learning_rate": 4.1709180847886745e-05,
"loss": 0.8797,
"step": 181
},
{
"epoch": 0.42305904230590424,
"grad_norm": 1.2787050008773804,
"learning_rate": 4.147634466255721e-05,
"loss": 0.8794,
"step": 182
},
{
"epoch": 0.42538354253835425,
"grad_norm": 1.222352147102356,
"learning_rate": 4.124300863486793e-05,
"loss": 0.8459,
"step": 183
},
{
"epoch": 0.42770804277080426,
"grad_norm": 1.203860878944397,
"learning_rate": 4.100918575799543e-05,
"loss": 0.9002,
"step": 184
},
{
"epoch": 0.4300325430032543,
"grad_norm": 1.1671602725982666,
"learning_rate": 4.077488905222613e-05,
"loss": 0.8686,
"step": 185
},
{
"epoch": 0.43235704323570434,
"grad_norm": 1.172710657119751,
"learning_rate": 4.0540131564231346e-05,
"loss": 0.8665,
"step": 186
},
{
"epoch": 0.43468154346815435,
"grad_norm": 1.196799635887146,
"learning_rate": 4.0304926366340746e-05,
"loss": 0.874,
"step": 187
},
{
"epoch": 0.43700604370060436,
"grad_norm": 1.3162767887115479,
"learning_rate": 4.006928655581446e-05,
"loss": 0.9128,
"step": 188
},
{
"epoch": 0.4393305439330544,
"grad_norm": 1.1845192909240723,
"learning_rate": 3.983322525411379e-05,
"loss": 0.8354,
"step": 189
},
{
"epoch": 0.44165504416550444,
"grad_norm": 1.2140437364578247,
"learning_rate": 3.959675560617049e-05,
"loss": 0.8716,
"step": 190
},
{
"epoch": 0.44397954439795445,
"grad_norm": 1.1984777450561523,
"learning_rate": 3.9359890779654846e-05,
"loss": 0.8063,
"step": 191
},
{
"epoch": 0.44630404463040446,
"grad_norm": 1.1856093406677246,
"learning_rate": 3.91226439642424e-05,
"loss": 0.7776,
"step": 192
},
{
"epoch": 0.4486285448628545,
"grad_norm": 1.2061065435409546,
"learning_rate": 3.8885028370879544e-05,
"loss": 0.8475,
"step": 193
},
{
"epoch": 0.4509530450953045,
"grad_norm": 1.2898370027542114,
"learning_rate": 3.864705723104786e-05,
"loss": 0.8788,
"step": 194
},
{
"epoch": 0.45327754532775455,
"grad_norm": 1.2373768091201782,
"learning_rate": 3.840874379602728e-05,
"loss": 0.8424,
"step": 195
},
{
"epoch": 0.45560204556020456,
"grad_norm": 1.2365310192108154,
"learning_rate": 3.817010133615827e-05,
"loss": 0.8429,
"step": 196
},
{
"epoch": 0.45792654579265457,
"grad_norm": 1.2247048616409302,
"learning_rate": 3.793114314010282e-05,
"loss": 0.8806,
"step": 197
},
{
"epoch": 0.4602510460251046,
"grad_norm": 1.2044016122817993,
"learning_rate": 3.769188251410454e-05,
"loss": 0.8633,
"step": 198
},
{
"epoch": 0.46257554625755465,
"grad_norm": 1.1678348779678345,
"learning_rate": 3.7452332781247633e-05,
"loss": 0.8325,
"step": 199
},
{
"epoch": 0.46490004649000466,
"grad_norm": 1.2637572288513184,
"learning_rate": 3.7212507280715056e-05,
"loss": 0.8471,
"step": 200
},
{
"epoch": 0.46722454672245467,
"grad_norm": 1.1990036964416504,
"learning_rate": 3.6972419367045726e-05,
"loss": 0.8821,
"step": 201
},
{
"epoch": 0.4695490469549047,
"grad_norm": 1.1562861204147339,
"learning_rate": 3.673208240939088e-05,
"loss": 0.8486,
"step": 202
},
{
"epoch": 0.4718735471873547,
"grad_norm": 1.2566421031951904,
"learning_rate": 3.6491509790769616e-05,
"loss": 0.9117,
"step": 203
},
{
"epoch": 0.47419804741980476,
"grad_norm": 1.2128387689590454,
"learning_rate": 3.625071490732366e-05,
"loss": 0.8905,
"step": 204
},
{
"epoch": 0.47652254765225477,
"grad_norm": 1.2243783473968506,
"learning_rate": 3.6009711167571434e-05,
"loss": 0.8362,
"step": 205
},
{
"epoch": 0.4788470478847048,
"grad_norm": 1.2012783288955688,
"learning_rate": 3.57685119916614e-05,
"loss": 0.841,
"step": 206
},
{
"epoch": 0.4811715481171548,
"grad_norm": 1.1792044639587402,
"learning_rate": 3.552713081062478e-05,
"loss": 0.8673,
"step": 207
},
{
"epoch": 0.48349604834960486,
"grad_norm": 1.2149136066436768,
"learning_rate": 3.528558106562759e-05,
"loss": 0.8776,
"step": 208
},
{
"epoch": 0.48582054858205487,
"grad_norm": 1.2262108325958252,
"learning_rate": 3.50438762072223e-05,
"loss": 0.8598,
"step": 209
},
{
"epoch": 0.4881450488145049,
"grad_norm": 1.1815216541290283,
"learning_rate": 3.4802029694598705e-05,
"loss": 0.7776,
"step": 210
},
{
"epoch": 0.4904695490469549,
"grad_norm": 1.1577028036117554,
"learning_rate": 3.456005499483456e-05,
"loss": 0.8072,
"step": 211
},
{
"epoch": 0.49279404927940496,
"grad_norm": 1.1453114748001099,
"learning_rate": 3.4317965582145684e-05,
"loss": 0.8518,
"step": 212
},
{
"epoch": 0.49511854951185497,
"grad_norm": 1.2426217794418335,
"learning_rate": 3.4075774937135554e-05,
"loss": 0.88,
"step": 213
},
{
"epoch": 0.497443049744305,
"grad_norm": 1.2424201965332031,
"learning_rate": 3.3833496546044746e-05,
"loss": 0.8669,
"step": 214
},
{
"epoch": 0.499767549976755,
"grad_norm": 1.2596735954284668,
"learning_rate": 3.3591143899999905e-05,
"loss": 0.8546,
"step": 215
},
{
"epoch": 0.502092050209205,
"grad_norm": 1.2579164505004883,
"learning_rate": 3.334873049426253e-05,
"loss": 0.8954,
"step": 216
},
{
"epoch": 0.504416550441655,
"grad_norm": 1.1875728368759155,
"learning_rate": 3.3106269827477484e-05,
"loss": 0.8319,
"step": 217
},
{
"epoch": 0.506741050674105,
"grad_norm": 1.241857647895813,
"learning_rate": 3.286377540092133e-05,
"loss": 0.9209,
"step": 218
},
{
"epoch": 0.5090655509065551,
"grad_norm": 1.1753859519958496,
"learning_rate": 3.2621260717750515e-05,
"loss": 0.8092,
"step": 219
},
{
"epoch": 0.5113900511390052,
"grad_norm": 1.1673084497451782,
"learning_rate": 3.237873928224948e-05,
"loss": 0.831,
"step": 220
},
{
"epoch": 0.5137145513714552,
"grad_norm": 1.2066866159439087,
"learning_rate": 3.213622459907867e-05,
"loss": 0.8413,
"step": 221
},
{
"epoch": 0.5160390516039052,
"grad_norm": 1.1958924531936646,
"learning_rate": 3.189373017252252e-05,
"loss": 0.8648,
"step": 222
},
{
"epoch": 0.5183635518363552,
"grad_norm": 1.1267814636230469,
"learning_rate": 3.165126950573747e-05,
"loss": 0.8551,
"step": 223
},
{
"epoch": 0.5206880520688052,
"grad_norm": 1.1723332405090332,
"learning_rate": 3.140885610000009e-05,
"loss": 0.8732,
"step": 224
},
{
"epoch": 0.5230125523012552,
"grad_norm": 1.2160817384719849,
"learning_rate": 3.116650345395524e-05,
"loss": 0.874,
"step": 225
},
{
"epoch": 0.5253370525337052,
"grad_norm": 1.1341142654418945,
"learning_rate": 3.0924225062864434e-05,
"loss": 0.8044,
"step": 226
},
{
"epoch": 0.5276615527661552,
"grad_norm": 1.1896854639053345,
"learning_rate": 3.0682034417854324e-05,
"loss": 0.8364,
"step": 227
},
{
"epoch": 0.5299860529986054,
"grad_norm": 1.229346513748169,
"learning_rate": 3.0439945005165433e-05,
"loss": 0.8821,
"step": 228
},
{
"epoch": 0.5323105532310554,
"grad_norm": 1.1989872455596924,
"learning_rate": 3.0197970305401306e-05,
"loss": 0.8566,
"step": 229
},
{
"epoch": 0.5346350534635054,
"grad_norm": 1.248273491859436,
"learning_rate": 2.9956123792777708e-05,
"loss": 0.7907,
"step": 230
},
{
"epoch": 0.5369595536959554,
"grad_norm": 1.235098958015442,
"learning_rate": 2.9714418934372402e-05,
"loss": 0.8838,
"step": 231
},
{
"epoch": 0.5392840539284054,
"grad_norm": 1.2413426637649536,
"learning_rate": 2.9472869189375224e-05,
"loss": 0.8614,
"step": 232
},
{
"epoch": 0.5416085541608554,
"grad_norm": 1.2023251056671143,
"learning_rate": 2.9231488008338592e-05,
"loss": 0.8328,
"step": 233
},
{
"epoch": 0.5439330543933054,
"grad_norm": 1.2137963771820068,
"learning_rate": 2.899028883242856e-05,
"loss": 0.8174,
"step": 234
},
{
"epoch": 0.5462575546257554,
"grad_norm": 1.1812171936035156,
"learning_rate": 2.8749285092676343e-05,
"loss": 0.8636,
"step": 235
},
{
"epoch": 0.5485820548582054,
"grad_norm": 1.2329221963882446,
"learning_rate": 2.8508490209230388e-05,
"loss": 0.8419,
"step": 236
},
{
"epoch": 0.5509065550906556,
"grad_norm": 1.176352620124817,
"learning_rate": 2.8267917590609115e-05,
"loss": 0.8174,
"step": 237
},
{
"epoch": 0.5532310553231056,
"grad_norm": 1.2109792232513428,
"learning_rate": 2.802758063295427e-05,
"loss": 0.8718,
"step": 238
},
{
"epoch": 0.5555555555555556,
"grad_norm": 1.155416488647461,
"learning_rate": 2.7787492719284935e-05,
"loss": 0.8365,
"step": 239
},
{
"epoch": 0.5578800557880056,
"grad_norm": 1.2347787618637085,
"learning_rate": 2.7547667218752358e-05,
"loss": 0.9275,
"step": 240
},
{
"epoch": 0.5602045560204556,
"grad_norm": 1.2063627243041992,
"learning_rate": 2.7308117485895463e-05,
"loss": 0.8702,
"step": 241
},
{
"epoch": 0.5625290562529056,
"grad_norm": 1.1815749406814575,
"learning_rate": 2.7068856859897173e-05,
"loss": 0.8222,
"step": 242
},
{
"epoch": 0.5648535564853556,
"grad_norm": 1.1446418762207031,
"learning_rate": 2.6829898663841733e-05,
"loss": 0.7562,
"step": 243
},
{
"epoch": 0.5671780567178056,
"grad_norm": 1.117566466331482,
"learning_rate": 2.659125620397272e-05,
"loss": 0.7828,
"step": 244
},
{
"epoch": 0.5695025569502556,
"grad_norm": 1.1796785593032837,
"learning_rate": 2.6352942768952144e-05,
"loss": 0.8555,
"step": 245
},
{
"epoch": 0.5718270571827058,
"grad_norm": 1.1962978839874268,
"learning_rate": 2.6114971629120454e-05,
"loss": 0.8359,
"step": 246
},
{
"epoch": 0.5741515574151558,
"grad_norm": 1.2345088720321655,
"learning_rate": 2.5877356035757598e-05,
"loss": 0.857,
"step": 247
},
{
"epoch": 0.5764760576476058,
"grad_norm": 1.1942895650863647,
"learning_rate": 2.564010922034516e-05,
"loss": 0.8233,
"step": 248
},
{
"epoch": 0.5788005578800558,
"grad_norm": 1.2165658473968506,
"learning_rate": 2.5403244393829505e-05,
"loss": 0.8141,
"step": 249
},
{
"epoch": 0.5811250581125058,
"grad_norm": 1.2151166200637817,
"learning_rate": 2.5166774745886202e-05,
"loss": 0.8538,
"step": 250
},
{
"epoch": 0.5834495583449558,
"grad_norm": 1.203872799873352,
"learning_rate": 2.493071344418553e-05,
"loss": 0.8177,
"step": 251
},
{
"epoch": 0.5857740585774058,
"grad_norm": 1.2117934226989746,
"learning_rate": 2.4695073633659245e-05,
"loss": 0.8277,
"step": 252
},
{
"epoch": 0.5880985588098558,
"grad_norm": 1.1932367086410522,
"learning_rate": 2.4459868435768644e-05,
"loss": 0.8342,
"step": 253
},
{
"epoch": 0.5904230590423059,
"grad_norm": 1.1477673053741455,
"learning_rate": 2.4225110947773856e-05,
"loss": 0.751,
"step": 254
},
{
"epoch": 0.592747559274756,
"grad_norm": 1.243074655532837,
"learning_rate": 2.3990814242004573e-05,
"loss": 0.8784,
"step": 255
},
{
"epoch": 0.595072059507206,
"grad_norm": 1.1835278272628784,
"learning_rate": 2.375699136513207e-05,
"loss": 0.8597,
"step": 256
},
{
"epoch": 0.597396559739656,
"grad_norm": 1.2624067068099976,
"learning_rate": 2.3523655337442798e-05,
"loss": 0.8519,
"step": 257
},
{
"epoch": 0.599721059972106,
"grad_norm": 1.1431169509887695,
"learning_rate": 2.3290819152113256e-05,
"loss": 0.8444,
"step": 258
},
{
"epoch": 0.602045560204556,
"grad_norm": 1.1751455068588257,
"learning_rate": 2.3058495774486553e-05,
"loss": 0.8608,
"step": 259
},
{
"epoch": 0.604370060437006,
"grad_norm": 1.1753759384155273,
"learning_rate": 2.2826698141350392e-05,
"loss": 0.8567,
"step": 260
},
{
"epoch": 0.606694560669456,
"grad_norm": 1.22267746925354,
"learning_rate": 2.2595439160216713e-05,
"loss": 0.8707,
"step": 261
},
{
"epoch": 0.609019060901906,
"grad_norm": 1.1453746557235718,
"learning_rate": 2.2364731708602947e-05,
"loss": 0.831,
"step": 262
},
{
"epoch": 0.6113435611343561,
"grad_norm": 1.1886532306671143,
"learning_rate": 2.2134588633314937e-05,
"loss": 0.763,
"step": 263
},
{
"epoch": 0.6136680613668062,
"grad_norm": 1.3295722007751465,
"learning_rate": 2.1905022749731563e-05,
"loss": 0.8818,
"step": 264
},
{
"epoch": 0.6159925615992562,
"grad_norm": 1.124739408493042,
"learning_rate": 2.1676046841091133e-05,
"loss": 0.7534,
"step": 265
},
{
"epoch": 0.6183170618317062,
"grad_norm": 1.2315418720245361,
"learning_rate": 2.144767365777955e-05,
"loss": 0.8528,
"step": 266
},
{
"epoch": 0.6206415620641562,
"grad_norm": 1.248775601387024,
"learning_rate": 2.121991591662034e-05,
"loss": 0.8536,
"step": 267
},
{
"epoch": 0.6229660622966062,
"grad_norm": 1.2271955013275146,
"learning_rate": 2.0992786300166472e-05,
"loss": 0.8731,
"step": 268
},
{
"epoch": 0.6252905625290562,
"grad_norm": 1.1660230159759521,
"learning_rate": 2.0766297455994204e-05,
"loss": 0.8301,
"step": 269
},
{
"epoch": 0.6276150627615062,
"grad_norm": 1.2100571393966675,
"learning_rate": 2.054046199599873e-05,
"loss": 0.867,
"step": 270
},
{
"epoch": 0.6299395629939563,
"grad_norm": 1.1913954019546509,
"learning_rate": 2.031529249569197e-05,
"loss": 0.8322,
"step": 271
},
{
"epoch": 0.6322640632264063,
"grad_norm": 1.1850714683532715,
"learning_rate": 2.0090801493502276e-05,
"loss": 0.8616,
"step": 272
},
{
"epoch": 0.6345885634588564,
"grad_norm": 1.152343511581421,
"learning_rate": 1.986700149007624e-05,
"loss": 0.8155,
"step": 273
},
{
"epoch": 0.6369130636913064,
"grad_norm": 1.195383906364441,
"learning_rate": 1.964390494758258e-05,
"loss": 0.8021,
"step": 274
},
{
"epoch": 0.6392375639237564,
"grad_norm": 1.4834905862808228,
"learning_rate": 1.9421524289018253e-05,
"loss": 0.8191,
"step": 275
},
{
"epoch": 0.6415620641562064,
"grad_norm": 1.250483751296997,
"learning_rate": 1.919987189751662e-05,
"loss": 0.8497,
"step": 276
},
{
"epoch": 0.6438865643886564,
"grad_norm": 1.1749329566955566,
"learning_rate": 1.8978960115657944e-05,
"loss": 0.837,
"step": 277
},
{
"epoch": 0.6462110646211064,
"grad_norm": 1.1642099618911743,
"learning_rate": 1.875880124478207e-05,
"loss": 0.8454,
"step": 278
},
{
"epoch": 0.6485355648535565,
"grad_norm": 1.2152022123336792,
"learning_rate": 1.853940754430346e-05,
"loss": 0.8492,
"step": 279
},
{
"epoch": 0.6508600650860065,
"grad_norm": 1.1679767370224,
"learning_rate": 1.8320791231028526e-05,
"loss": 0.8454,
"step": 280
},
{
"epoch": 0.6531845653184565,
"grad_norm": 1.2204087972640991,
"learning_rate": 1.8102964478475316e-05,
"loss": 0.9385,
"step": 281
},
{
"epoch": 0.6555090655509066,
"grad_norm": 1.1549757719039917,
"learning_rate": 1.7885939416195687e-05,
"loss": 0.7963,
"step": 282
},
{
"epoch": 0.6578335657833566,
"grad_norm": 1.1434992551803589,
"learning_rate": 1.766972812909988e-05,
"loss": 0.7884,
"step": 283
},
{
"epoch": 0.6601580660158066,
"grad_norm": 1.151331901550293,
"learning_rate": 1.7454342656783464e-05,
"loss": 0.767,
"step": 284
},
{
"epoch": 0.6624825662482566,
"grad_norm": 1.1396957635879517,
"learning_rate": 1.7239794992857097e-05,
"loss": 0.8191,
"step": 285
},
{
"epoch": 0.6648070664807066,
"grad_norm": 1.1968632936477661,
"learning_rate": 1.7026097084278556e-05,
"loss": 0.8241,
"step": 286
},
{
"epoch": 0.6671315667131567,
"grad_norm": 1.1648362874984741,
"learning_rate": 1.6813260830687472e-05,
"loss": 0.7965,
"step": 287
},
{
"epoch": 0.6694560669456067,
"grad_norm": 1.226285457611084,
"learning_rate": 1.660129808374279e-05,
"loss": 0.9029,
"step": 288
},
{
"epoch": 0.6717805671780567,
"grad_norm": 1.178755760192871,
"learning_rate": 1.6390220646462693e-05,
"loss": 0.7986,
"step": 289
},
{
"epoch": 0.6741050674105067,
"grad_norm": 1.1674259901046753,
"learning_rate": 1.618004027256749e-05,
"loss": 0.7532,
"step": 290
},
{
"epoch": 0.6764295676429568,
"grad_norm": 1.196860671043396,
"learning_rate": 1.5970768665825036e-05,
"loss": 0.8043,
"step": 291
},
{
"epoch": 0.6787540678754068,
"grad_norm": 1.2226951122283936,
"learning_rate": 1.5762417479399005e-05,
"loss": 0.847,
"step": 292
},
{
"epoch": 0.6810785681078568,
"grad_norm": 1.1900945901870728,
"learning_rate": 1.555499831520006e-05,
"loss": 0.847,
"step": 293
},
{
"epoch": 0.6834030683403068,
"grad_norm": 1.176953911781311,
"learning_rate": 1.5348522723239726e-05,
"loss": 0.8145,
"step": 294
},
{
"epoch": 0.6857275685727569,
"grad_norm": 1.1760255098342896,
"learning_rate": 1.5143002200987304e-05,
"loss": 0.792,
"step": 295
},
{
"epoch": 0.6880520688052069,
"grad_norm": 1.1875512599945068,
"learning_rate": 1.4938448192729617e-05,
"loss": 0.8698,
"step": 296
},
{
"epoch": 0.6903765690376569,
"grad_norm": 1.142947793006897,
"learning_rate": 1.4734872088933713e-05,
"loss": 0.8222,
"step": 297
},
{
"epoch": 0.6927010692701069,
"grad_norm": 1.2026643753051758,
"learning_rate": 1.4532285225612613e-05,
"loss": 0.8494,
"step": 298
},
{
"epoch": 0.695025569502557,
"grad_norm": 1.1509863138198853,
"learning_rate": 1.4330698883694115e-05,
"loss": 0.8091,
"step": 299
},
{
"epoch": 0.697350069735007,
"grad_norm": 1.237417459487915,
"learning_rate": 1.413012428839254e-05,
"loss": 0.8465,
"step": 300
},
{
"epoch": 0.699674569967457,
"grad_norm": 1.1145235300064087,
"learning_rate": 1.3930572608583745e-05,
"loss": 0.7913,
"step": 301
},
{
"epoch": 0.701999070199907,
"grad_norm": 1.1738826036453247,
"learning_rate": 1.3732054956183111e-05,
"loss": 0.8164,
"step": 302
},
{
"epoch": 0.704323570432357,
"grad_norm": 1.1653589010238647,
"learning_rate": 1.3534582385526876e-05,
"loss": 0.7946,
"step": 303
},
{
"epoch": 0.7066480706648071,
"grad_norm": 1.1790781021118164,
"learning_rate": 1.3338165892756468e-05,
"loss": 0.8287,
"step": 304
},
{
"epoch": 0.7089725708972571,
"grad_norm": 1.1557509899139404,
"learning_rate": 1.3142816415206304e-05,
"loss": 0.7584,
"step": 305
},
{
"epoch": 0.7112970711297071,
"grad_norm": 1.2092468738555908,
"learning_rate": 1.2948544830794682e-05,
"loss": 0.8641,
"step": 306
},
{
"epoch": 0.7136215713621571,
"grad_norm": 1.1953829526901245,
"learning_rate": 1.275536195741805e-05,
"loss": 0.8669,
"step": 307
},
{
"epoch": 0.7159460715946072,
"grad_norm": 1.1542140245437622,
"learning_rate": 1.2563278552348676e-05,
"loss": 0.8841,
"step": 308
},
{
"epoch": 0.7182705718270572,
"grad_norm": 1.2032291889190674,
"learning_rate": 1.2372305311635541e-05,
"loss": 0.8485,
"step": 309
},
{
"epoch": 0.7205950720595072,
"grad_norm": 1.1283597946166992,
"learning_rate": 1.2182452869508834e-05,
"loss": 0.7937,
"step": 310
},
{
"epoch": 0.7229195722919572,
"grad_norm": 1.133653163909912,
"learning_rate": 1.1993731797787766e-05,
"loss": 0.81,
"step": 311
},
{
"epoch": 0.7252440725244073,
"grad_norm": 1.1899718046188354,
"learning_rate": 1.1806152605291783e-05,
"loss": 0.8785,
"step": 312
},
{
"epoch": 0.7275685727568573,
"grad_norm": 1.182756781578064,
"learning_rate": 1.1619725737255553e-05,
"loss": 0.8157,
"step": 313
},
{
"epoch": 0.7298930729893073,
"grad_norm": 1.1462957859039307,
"learning_rate": 1.143446157474723e-05,
"loss": 0.8032,
"step": 314
},
{
"epoch": 0.7322175732217573,
"grad_norm": 1.1228857040405273,
"learning_rate": 1.1250370434090382e-05,
"loss": 0.7521,
"step": 315
},
{
"epoch": 0.7345420734542073,
"grad_norm": 1.1679176092147827,
"learning_rate": 1.1067462566289592e-05,
"loss": 0.8729,
"step": 316
},
{
"epoch": 0.7368665736866574,
"grad_norm": 1.1772230863571167,
"learning_rate": 1.0885748156459578e-05,
"loss": 0.8305,
"step": 317
},
{
"epoch": 0.7391910739191074,
"grad_norm": 1.1800023317337036,
"learning_rate": 1.0705237323258088e-05,
"loss": 0.8285,
"step": 318
},
{
"epoch": 0.7415155741515574,
"grad_norm": 1.1623144149780273,
"learning_rate": 1.0525940118322434e-05,
"loss": 0.8343,
"step": 319
},
{
"epoch": 0.7438400743840075,
"grad_norm": 1.2074713706970215,
"learning_rate": 1.0347866525709737e-05,
"loss": 0.8442,
"step": 320
},
{
"epoch": 0.7461645746164575,
"grad_norm": 1.1325371265411377,
"learning_rate": 1.017102646134103e-05,
"loss": 0.8072,
"step": 321
},
{
"epoch": 0.7484890748489075,
"grad_norm": 1.176443099975586,
"learning_rate": 9.995429772449044e-06,
"loss": 0.8585,
"step": 322
},
{
"epoch": 0.7508135750813575,
"grad_norm": 1.159180760383606,
"learning_rate": 9.82108623702991e-06,
"loss": 0.8226,
"step": 323
},
{
"epoch": 0.7531380753138075,
"grad_norm": 1.180493950843811,
"learning_rate": 9.648005563298672e-06,
"loss": 0.8364,
"step": 324
},
{
"epoch": 0.7554625755462575,
"grad_norm": 1.2017948627471924,
"learning_rate": 9.476197389148645e-06,
"loss": 0.8531,
"step": 325
},
{
"epoch": 0.7577870757787076,
"grad_norm": 1.156783103942871,
"learning_rate": 9.305671281614786e-06,
"loss": 0.8105,
"step": 326
},
{
"epoch": 0.7601115760111576,
"grad_norm": 1.145729660987854,
"learning_rate": 9.136436736340962e-06,
"loss": 0.8248,
"step": 327
},
{
"epoch": 0.7624360762436077,
"grad_norm": 1.2108309268951416,
"learning_rate": 8.968503177051128e-06,
"loss": 0.8042,
"step": 328
},
{
"epoch": 0.7647605764760577,
"grad_norm": 1.193647861480713,
"learning_rate": 8.801879955024671e-06,
"loss": 0.8598,
"step": 329
},
{
"epoch": 0.7670850767085077,
"grad_norm": 1.2257269620895386,
"learning_rate": 8.636576348575587e-06,
"loss": 0.8747,
"step": 330
},
{
"epoch": 0.7694095769409577,
"grad_norm": 1.2016220092773438,
"learning_rate": 8.472601562535888e-06,
"loss": 0.799,
"step": 331
},
{
"epoch": 0.7717340771734077,
"grad_norm": 1.243636131286621,
"learning_rate": 8.309964727743042e-06,
"loss": 0.8876,
"step": 332
},
{
"epoch": 0.7740585774058577,
"grad_norm": 1.2658741474151611,
"learning_rate": 8.148674900531466e-06,
"loss": 0.8943,
"step": 333
},
{
"epoch": 0.7763830776383077,
"grad_norm": 1.1937084197998047,
"learning_rate": 7.988741062228303e-06,
"loss": 0.8072,
"step": 334
},
{
"epoch": 0.7787075778707578,
"grad_norm": 1.188068151473999,
"learning_rate": 7.830172118653236e-06,
"loss": 0.8405,
"step": 335
},
{
"epoch": 0.7810320781032078,
"grad_norm": 1.1817395687103271,
"learning_rate": 7.672976899622636e-06,
"loss": 0.8474,
"step": 336
},
{
"epoch": 0.7833565783356579,
"grad_norm": 1.2230587005615234,
"learning_rate": 7.517164158457843e-06,
"loss": 0.8168,
"step": 337
},
{
"epoch": 0.7856810785681079,
"grad_norm": 1.1503418684005737,
"learning_rate": 7.362742571497723e-06,
"loss": 0.7769,
"step": 338
},
{
"epoch": 0.7880055788005579,
"grad_norm": 1.1554263830184937,
"learning_rate": 7.209720737615588e-06,
"loss": 0.7941,
"step": 339
},
{
"epoch": 0.7903300790330079,
"grad_norm": 1.167829155921936,
"learning_rate": 7.058107177740316e-06,
"loss": 0.861,
"step": 340
},
{
"epoch": 0.7926545792654579,
"grad_norm": 1.1501438617706299,
"learning_rate": 6.907910334381895e-06,
"loss": 0.7728,
"step": 341
},
{
"epoch": 0.7949790794979079,
"grad_norm": 1.2136327028274536,
"learning_rate": 6.759138571161328e-06,
"loss": 0.8745,
"step": 342
},
{
"epoch": 0.7973035797303579,
"grad_norm": 1.15041184425354,
"learning_rate": 6.611800172344858e-06,
"loss": 0.8245,
"step": 343
},
{
"epoch": 0.799628079962808,
"grad_norm": 1.2242484092712402,
"learning_rate": 6.4659033423827105e-06,
"loss": 0.8703,
"step": 344
},
{
"epoch": 0.8019525801952581,
"grad_norm": 1.2068572044372559,
"learning_rate": 6.321456205452219e-06,
"loss": 0.8453,
"step": 345
},
{
"epoch": 0.8042770804277081,
"grad_norm": 1.138300895690918,
"learning_rate": 6.17846680500541e-06,
"loss": 0.8205,
"step": 346
},
{
"epoch": 0.8066015806601581,
"grad_norm": 1.2071059942245483,
"learning_rate": 6.0369431033211525e-06,
"loss": 0.873,
"step": 347
},
{
"epoch": 0.8089260808926081,
"grad_norm": 1.2351478338241577,
"learning_rate": 5.896892981061738e-06,
"loss": 0.8453,
"step": 348
},
{
"epoch": 0.8112505811250581,
"grad_norm": 1.1644549369812012,
"learning_rate": 5.758324236834091e-06,
"loss": 0.8112,
"step": 349
},
{
"epoch": 0.8135750813575081,
"grad_norm": 1.2177077531814575,
"learning_rate": 5.621244586755496e-06,
"loss": 0.8216,
"step": 350
},
{
"epoch": 0.8158995815899581,
"grad_norm": 1.202233076095581,
"learning_rate": 5.485661664023893e-06,
"loss": 0.8821,
"step": 351
},
{
"epoch": 0.8182240818224081,
"grad_norm": 1.173756718635559,
"learning_rate": 5.351583018492902e-06,
"loss": 0.8337,
"step": 352
},
{
"epoch": 0.8205485820548583,
"grad_norm": 1.1963239908218384,
"learning_rate": 5.219016116251332e-06,
"loss": 0.8751,
"step": 353
},
{
"epoch": 0.8228730822873083,
"grad_norm": 1.1608357429504395,
"learning_rate": 5.087968339207486e-06,
"loss": 0.8938,
"step": 354
},
{
"epoch": 0.8251975825197583,
"grad_norm": 1.1277998685836792,
"learning_rate": 4.958446984678114e-06,
"loss": 0.7774,
"step": 355
},
{
"epoch": 0.8275220827522083,
"grad_norm": 1.2397881746292114,
"learning_rate": 4.830459264982011e-06,
"loss": 0.8269,
"step": 356
},
{
"epoch": 0.8298465829846583,
"grad_norm": 1.2230621576309204,
"learning_rate": 4.704012307038478e-06,
"loss": 0.8511,
"step": 357
},
{
"epoch": 0.8321710832171083,
"grad_norm": 1.1905261278152466,
"learning_rate": 4.579113151970381e-06,
"loss": 0.8424,
"step": 358
},
{
"epoch": 0.8344955834495583,
"grad_norm": 1.2389678955078125,
"learning_rate": 4.455768754712141e-06,
"loss": 0.8978,
"step": 359
},
{
"epoch": 0.8368200836820083,
"grad_norm": 1.2028136253356934,
"learning_rate": 4.3339859836224235e-06,
"loss": 0.8501,
"step": 360
},
{
"epoch": 0.8391445839144583,
"grad_norm": 1.1460210084915161,
"learning_rate": 4.213771620101661e-06,
"loss": 0.7621,
"step": 361
},
{
"epoch": 0.8414690841469085,
"grad_norm": 1.1692181825637817,
"learning_rate": 4.095132358214476e-06,
"loss": 0.8351,
"step": 362
},
{
"epoch": 0.8437935843793585,
"grad_norm": 1.1694318056106567,
"learning_rate": 3.97807480431688e-06,
"loss": 0.7781,
"step": 363
},
{
"epoch": 0.8461180846118085,
"grad_norm": 1.1537806987762451,
"learning_rate": 3.862605476688435e-06,
"loss": 0.7383,
"step": 364
},
{
"epoch": 0.8484425848442585,
"grad_norm": 1.1844308376312256,
"learning_rate": 3.748730805169292e-06,
"loss": 0.8434,
"step": 365
},
{
"epoch": 0.8507670850767085,
"grad_norm": 1.2213958501815796,
"learning_rate": 3.6364571308021075e-06,
"loss": 0.9058,
"step": 366
},
{
"epoch": 0.8530915853091585,
"grad_norm": 1.2063052654266357,
"learning_rate": 3.5257907054789965e-06,
"loss": 0.864,
"step": 367
},
{
"epoch": 0.8554160855416085,
"grad_norm": 1.2098087072372437,
"learning_rate": 3.416737691593364e-06,
"loss": 0.8397,
"step": 368
},
{
"epoch": 0.8577405857740585,
"grad_norm": 1.197662591934204,
"learning_rate": 3.309304161696762e-06,
"loss": 0.8456,
"step": 369
},
{
"epoch": 0.8600650860065086,
"grad_norm": 1.167975902557373,
"learning_rate": 3.203496098160773e-06,
"loss": 0.8325,
"step": 370
},
{
"epoch": 0.8623895862389587,
"grad_norm": 1.1775121688842773,
"learning_rate": 3.0993193928438364e-06,
"loss": 0.8519,
"step": 371
},
{
"epoch": 0.8647140864714087,
"grad_norm": 1.1968019008636475,
"learning_rate": 2.996779846763207e-06,
"loss": 0.8299,
"step": 372
},
{
"epoch": 0.8670385867038587,
"grad_norm": 1.1625730991363525,
"learning_rate": 2.8958831697719116e-06,
"loss": 0.7785,
"step": 373
},
{
"epoch": 0.8693630869363087,
"grad_norm": 1.2199307680130005,
"learning_rate": 2.796634980240773e-06,
"loss": 0.8107,
"step": 374
},
{
"epoch": 0.8716875871687587,
"grad_norm": 1.2188974618911743,
"learning_rate": 2.6990408047456208e-06,
"loss": 0.8457,
"step": 375
},
{
"epoch": 0.8740120874012087,
"grad_norm": 1.194596767425537,
"learning_rate": 2.603106077759467e-06,
"loss": 0.8295,
"step": 376
},
{
"epoch": 0.8763365876336587,
"grad_norm": 1.0834101438522339,
"learning_rate": 2.508836141349955e-06,
"loss": 0.7247,
"step": 377
},
{
"epoch": 0.8786610878661087,
"grad_norm": 1.1972309350967407,
"learning_rate": 2.4162362448818634e-06,
"loss": 0.9107,
"step": 378
},
{
"epoch": 0.8809855880985588,
"grad_norm": 1.1724853515625,
"learning_rate": 2.3253115447247866e-06,
"loss": 0.8098,
"step": 379
},
{
"epoch": 0.8833100883310089,
"grad_norm": 1.1860358715057373,
"learning_rate": 2.2360671039660346e-06,
"loss": 0.8301,
"step": 380
},
{
"epoch": 0.8856345885634589,
"grad_norm": 1.2200249433517456,
"learning_rate": 2.148507892128674e-06,
"loss": 0.8012,
"step": 381
},
{
"epoch": 0.8879590887959089,
"grad_norm": 1.118643045425415,
"learning_rate": 2.062638784894803e-06,
"loss": 0.7925,
"step": 382
},
{
"epoch": 0.8902835890283589,
"grad_norm": 1.1284154653549194,
"learning_rate": 1.9784645638340827e-06,
"loss": 0.825,
"step": 383
},
{
"epoch": 0.8926080892608089,
"grad_norm": 1.2449028491973877,
"learning_rate": 1.8959899161374317e-06,
"loss": 0.8187,
"step": 384
},
{
"epoch": 0.8949325894932589,
"grad_norm": 1.1662657260894775,
"learning_rate": 1.8152194343560626e-06,
"loss": 0.8131,
"step": 385
},
{
"epoch": 0.897257089725709,
"grad_norm": 1.2282719612121582,
"learning_rate": 1.736157616145729e-06,
"loss": 0.8428,
"step": 386
},
{
"epoch": 0.899581589958159,
"grad_norm": 1.112457275390625,
"learning_rate": 1.6588088640162775e-06,
"loss": 0.767,
"step": 387
},
{
"epoch": 0.901906090190609,
"grad_norm": 1.1861826181411743,
"learning_rate": 1.5831774850865059e-06,
"loss": 0.8122,
"step": 388
},
{
"epoch": 0.9042305904230591,
"grad_norm": 1.1628504991531372,
"learning_rate": 1.5092676908443047e-06,
"loss": 0.7754,
"step": 389
},
{
"epoch": 0.9065550906555091,
"grad_norm": 1.1673952341079712,
"learning_rate": 1.4370835969121649e-06,
"loss": 0.8309,
"step": 390
},
{
"epoch": 0.9088795908879591,
"grad_norm": 1.203006386756897,
"learning_rate": 1.366629222817995e-06,
"loss": 0.7955,
"step": 391
},
{
"epoch": 0.9112040911204091,
"grad_norm": 1.1598377227783203,
"learning_rate": 1.2979084917712842e-06,
"loss": 0.8337,
"step": 392
},
{
"epoch": 0.9135285913528591,
"grad_norm": 1.1832410097122192,
"learning_rate": 1.2309252304446607e-06,
"loss": 0.8024,
"step": 393
},
{
"epoch": 0.9158530915853091,
"grad_norm": 1.1913425922393799,
"learning_rate": 1.1656831687607826e-06,
"loss": 0.8127,
"step": 394
},
{
"epoch": 0.9181775918177592,
"grad_norm": 1.1691555976867676,
"learning_rate": 1.1021859396846632e-06,
"loss": 0.7681,
"step": 395
},
{
"epoch": 0.9205020920502092,
"grad_norm": 1.2271596193313599,
"learning_rate": 1.0404370790213507e-06,
"loss": 0.8653,
"step": 396
},
{
"epoch": 0.9228265922826592,
"grad_norm": 1.1940650939941406,
"learning_rate": 9.804400252190588e-07,
"loss": 0.8275,
"step": 397
},
{
"epoch": 0.9251510925151093,
"grad_norm": 1.322935938835144,
"learning_rate": 9.221981191776801e-07,
"loss": 0.9482,
"step": 398
},
{
"epoch": 0.9274755927475593,
"grad_norm": 1.226189374923706,
"learning_rate": 8.657146040627655e-07,
"loss": 0.8803,
"step": 399
},
{
"epoch": 0.9298000929800093,
"grad_norm": 1.2069227695465088,
"learning_rate": 8.109926251249163e-07,
"loss": 0.8547,
"step": 400
},
{
"epoch": 0.9321245932124593,
"grad_norm": 1.2206929922103882,
"learning_rate": 7.58035229524658e-07,
"loss": 0.8214,
"step": 401
},
{
"epoch": 0.9344490934449093,
"grad_norm": 1.2493535280227661,
"learning_rate": 7.068453661627424e-07,
"loss": 0.8802,
"step": 402
},
{
"epoch": 0.9367735936773594,
"grad_norm": 1.1659430265426636,
"learning_rate": 6.574258855159656e-07,
"loss": 0.803,
"step": 403
},
{
"epoch": 0.9390980939098094,
"grad_norm": 1.2101560831069946,
"learning_rate": 6.097795394784138e-07,
"loss": 0.8255,
"step": 404
},
{
"epoch": 0.9414225941422594,
"grad_norm": 1.1926182508468628,
"learning_rate": 5.639089812082365e-07,
"loss": 0.7878,
"step": 405
},
{
"epoch": 0.9437470943747094,
"grad_norm": 1.1893055438995361,
"learning_rate": 5.198167649799214e-07,
"loss": 0.8213,
"step": 406
},
{
"epoch": 0.9460715946071595,
"grad_norm": 1.2222219705581665,
"learning_rate": 4.775053460420305e-07,
"loss": 0.8765,
"step": 407
},
{
"epoch": 0.9483960948396095,
"grad_norm": 1.1839882135391235,
"learning_rate": 4.369770804805123e-07,
"loss": 0.7754,
"step": 408
},
{
"epoch": 0.9507205950720595,
"grad_norm": 1.1785272359848022,
"learning_rate": 3.98234225087489e-07,
"loss": 0.8291,
"step": 409
},
{
"epoch": 0.9530450953045095,
"grad_norm": 1.1746994256973267,
"learning_rate": 3.6127893723558233e-07,
"loss": 0.8198,
"step": 410
},
{
"epoch": 0.9553695955369595,
"grad_norm": 1.218136191368103,
"learning_rate": 3.2611327475779545e-07,
"loss": 0.8316,
"step": 411
},
{
"epoch": 0.9576940957694096,
"grad_norm": 1.2541922330856323,
"learning_rate": 2.927391958329195e-07,
"loss": 0.8747,
"step": 412
},
{
"epoch": 0.9600185960018596,
"grad_norm": 1.1385949850082397,
"learning_rate": 2.6115855887648195e-07,
"loss": 0.7893,
"step": 413
},
{
"epoch": 0.9623430962343096,
"grad_norm": 1.142892837524414,
"learning_rate": 2.3137312243728834e-07,
"loss": 0.7838,
"step": 414
},
{
"epoch": 0.9646675964667596,
"grad_norm": 1.2635773420333862,
"learning_rate": 2.033845450994659e-07,
"loss": 0.8358,
"step": 415
},
{
"epoch": 0.9669920966992097,
"grad_norm": 1.141421914100647,
"learning_rate": 1.771943853901292e-07,
"loss": 0.8355,
"step": 416
},
{
"epoch": 0.9693165969316597,
"grad_norm": 1.1934841871261597,
"learning_rate": 1.5280410169258794e-07,
"loss": 0.8171,
"step": 417
},
{
"epoch": 0.9716410971641097,
"grad_norm": 1.1529548168182373,
"learning_rate": 1.3021505216514017e-07,
"loss": 0.7629,
"step": 418
},
{
"epoch": 0.9739655973965597,
"grad_norm": 1.207676649093628,
"learning_rate": 1.0942849466543308e-07,
"loss": 0.8672,
"step": 419
},
{
"epoch": 0.9762900976290098,
"grad_norm": 1.264219045639038,
"learning_rate": 9.044558668043461e-08,
"loss": 0.9103,
"step": 420
},
{
"epoch": 0.9786145978614598,
"grad_norm": 1.2143738269805908,
"learning_rate": 7.32673852619689e-08,
"loss": 0.8604,
"step": 421
},
{
"epoch": 0.9809390980939098,
"grad_norm": 1.172698974609375,
"learning_rate": 5.7894846967866115e-08,
"loss": 0.823,
"step": 422
},
{
"epoch": 0.9832635983263598,
"grad_norm": 1.194075584411621,
"learning_rate": 4.432882780868341e-08,
"loss": 0.8139,
"step": 423
},
{
"epoch": 0.9855880985588099,
"grad_norm": 1.191976547241211,
"learning_rate": 3.257008320005111e-08,
"loss": 0.8117,
"step": 424
},
{
"epoch": 0.9879125987912599,
"grad_norm": 1.202752709388733,
"learning_rate": 2.261926792058999e-08,
"loss": 0.8479,
"step": 425
},
{
"epoch": 0.9902370990237099,
"grad_norm": 1.2659246921539307,
"learning_rate": 1.4476936075475397e-08,
"loss": 0.8472,
"step": 426
},
{
"epoch": 0.9925615992561599,
"grad_norm": 1.1615605354309082,
"learning_rate": 8.143541065568914e-09,
"loss": 0.778,
"step": 427
},
{
"epoch": 0.99488609948861,
"grad_norm": 1.23662531375885,
"learning_rate": 3.619435562157158e-09,
"loss": 0.8868,
"step": 428
},
{
"epoch": 0.99721059972106,
"grad_norm": 1.181993007659912,
"learning_rate": 9.048714873446938e-10,
"loss": 0.8409,
"step": 429
},
{
"epoch": 0.99953509995351,
"grad_norm": 1.1682720184326172,
"learning_rate": 0.0,
"loss": 0.8589,
"step": 430
}
],
"logging_steps": 1,
"max_steps": 430,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.6061243889342874e+17,
"train_batch_size": 6,
"trial_name": null,
"trial_params": null
}