hadxs's picture
Upload folder using huggingface_hub
6632122 verified
Raw
History Blame Contribute Delete
45.9 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.031431319423926775,
"eval_steps": 500,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00012572527769570712,
"grad_norm": 0.5962838530540466,
"learning_rate": 4.75e-07,
"loss": 3.0013919830322267,
"step": 20
},
{
"epoch": 0.00025145055539141424,
"grad_norm": 0.6844280958175659,
"learning_rate": 9.75e-07,
"loss": 3.018001365661621,
"step": 40
},
{
"epoch": 0.0003771758330871213,
"grad_norm": 0.4779929220676422,
"learning_rate": 1.475e-06,
"loss": 3.1058986663818358,
"step": 60
},
{
"epoch": 0.0005029011107828285,
"grad_norm": 0.555294930934906,
"learning_rate": 1.975e-06,
"loss": 2.909657287597656,
"step": 80
},
{
"epoch": 0.0006286263884785355,
"grad_norm": 0.5354552865028381,
"learning_rate": 2.4750000000000004e-06,
"loss": 2.8872909545898438,
"step": 100
},
{
"epoch": 0.0007543516661742426,
"grad_norm": 0.5644583702087402,
"learning_rate": 2.975e-06,
"loss": 2.859341621398926,
"step": 120
},
{
"epoch": 0.0008800769438699498,
"grad_norm": 0.630761981010437,
"learning_rate": 3.4750000000000006e-06,
"loss": 2.933867835998535,
"step": 140
},
{
"epoch": 0.001005802221565657,
"grad_norm": 0.764999508857727,
"learning_rate": 3.975e-06,
"loss": 2.782645606994629,
"step": 160
},
{
"epoch": 0.001131527499261364,
"grad_norm": 1.0221054553985596,
"learning_rate": 4.475e-06,
"loss": 2.8541688919067383,
"step": 180
},
{
"epoch": 0.001257252776957071,
"grad_norm": 0.8221330046653748,
"learning_rate": 4.975000000000001e-06,
"loss": 2.6588584899902346,
"step": 200
},
{
"epoch": 0.0013829780546527782,
"grad_norm": 0.873559832572937,
"learning_rate": 5.475e-06,
"loss": 2.549220848083496,
"step": 220
},
{
"epoch": 0.0015087033323484852,
"grad_norm": 0.813358724117279,
"learning_rate": 5.975e-06,
"loss": 2.5854366302490233,
"step": 240
},
{
"epoch": 0.0016344286100441925,
"grad_norm": 0.856169581413269,
"learning_rate": 6.475000000000001e-06,
"loss": 2.5309289932250976,
"step": 260
},
{
"epoch": 0.0017601538877398996,
"grad_norm": 0.951108455657959,
"learning_rate": 6.975000000000001e-06,
"loss": 2.4736785888671875,
"step": 280
},
{
"epoch": 0.0018858791654356066,
"grad_norm": 0.8016313910484314,
"learning_rate": 7.4750000000000004e-06,
"loss": 2.2943771362304686,
"step": 300
},
{
"epoch": 0.002011604443131314,
"grad_norm": 0.915063202381134,
"learning_rate": 7.975e-06,
"loss": 2.3273014068603515,
"step": 320
},
{
"epoch": 0.0021373297208270208,
"grad_norm": 0.720587968826294,
"learning_rate": 8.475000000000001e-06,
"loss": 2.350560760498047,
"step": 340
},
{
"epoch": 0.002263054998522728,
"grad_norm": 0.711700439453125,
"learning_rate": 8.975e-06,
"loss": 2.3248199462890624,
"step": 360
},
{
"epoch": 0.002388780276218435,
"grad_norm": 0.8843226432800293,
"learning_rate": 9.475e-06,
"loss": 2.335201454162598,
"step": 380
},
{
"epoch": 0.002514505553914142,
"grad_norm": 0.4873352348804474,
"learning_rate": 9.975e-06,
"loss": 2.424860382080078,
"step": 400
},
{
"epoch": 0.0026402308316098495,
"grad_norm": 0.6487540602684021,
"learning_rate": 1.0475e-05,
"loss": 2.2071765899658202,
"step": 420
},
{
"epoch": 0.0027659561093055563,
"grad_norm": 0.6322605013847351,
"learning_rate": 1.0975e-05,
"loss": 2.2878080368041993,
"step": 440
},
{
"epoch": 0.0028916813870012636,
"grad_norm": 0.5939791798591614,
"learning_rate": 1.1475000000000001e-05,
"loss": 2.3425870895385743,
"step": 460
},
{
"epoch": 0.0030174066646969705,
"grad_norm": 0.6943904161453247,
"learning_rate": 1.1975e-05,
"loss": 2.2085947036743163,
"step": 480
},
{
"epoch": 0.0031431319423926777,
"grad_norm": 0.7218244075775146,
"learning_rate": 1.2475e-05,
"loss": 2.2360507965087892,
"step": 500
},
{
"epoch": 0.003268857220088385,
"grad_norm": 0.8252770900726318,
"learning_rate": 1.2975e-05,
"loss": 2.3641361236572265,
"step": 520
},
{
"epoch": 0.003394582497784092,
"grad_norm": 0.5744673013687134,
"learning_rate": 1.3475000000000002e-05,
"loss": 2.236039924621582,
"step": 540
},
{
"epoch": 0.003520307775479799,
"grad_norm": 0.6768812537193298,
"learning_rate": 1.3975000000000003e-05,
"loss": 2.2313003540039062,
"step": 560
},
{
"epoch": 0.003646033053175506,
"grad_norm": 0.6503052711486816,
"learning_rate": 1.4475e-05,
"loss": 2.2801786422729493,
"step": 580
},
{
"epoch": 0.0037717583308712133,
"grad_norm": 0.629787266254425,
"learning_rate": 1.4975e-05,
"loss": 2.346693420410156,
"step": 600
},
{
"epoch": 0.0038974836085669206,
"grad_norm": 0.6764146089553833,
"learning_rate": 1.5475e-05,
"loss": 2.093250274658203,
"step": 620
},
{
"epoch": 0.004023208886262628,
"grad_norm": 0.7266194224357605,
"learning_rate": 1.5975000000000002e-05,
"loss": 2.242112922668457,
"step": 640
},
{
"epoch": 0.004148934163958335,
"grad_norm": 0.5509718656539917,
"learning_rate": 1.6475e-05,
"loss": 2.2910560607910155,
"step": 660
},
{
"epoch": 0.0042746594416540416,
"grad_norm": 0.7285779714584351,
"learning_rate": 1.6975000000000003e-05,
"loss": 2.480996322631836,
"step": 680
},
{
"epoch": 0.004400384719349749,
"grad_norm": 0.5729554295539856,
"learning_rate": 1.7475e-05,
"loss": 2.1267959594726564,
"step": 700
},
{
"epoch": 0.004526109997045456,
"grad_norm": 0.6237987279891968,
"learning_rate": 1.7975e-05,
"loss": 2.3381301879882814,
"step": 720
},
{
"epoch": 0.004651835274741163,
"grad_norm": 0.6548975110054016,
"learning_rate": 1.8475000000000002e-05,
"loss": 2.1999746322631837,
"step": 740
},
{
"epoch": 0.00477756055243687,
"grad_norm": 0.614876389503479,
"learning_rate": 1.8975e-05,
"loss": 2.3489891052246095,
"step": 760
},
{
"epoch": 0.0049032858301325775,
"grad_norm": 0.6543737053871155,
"learning_rate": 1.9475000000000002e-05,
"loss": 2.261593055725098,
"step": 780
},
{
"epoch": 0.005029011107828284,
"grad_norm": 0.6650403141975403,
"learning_rate": 1.9975e-05,
"loss": 2.307338523864746,
"step": 800
},
{
"epoch": 0.005154736385523991,
"grad_norm": 0.691130518913269,
"learning_rate": 2.0475e-05,
"loss": 2.2411531448364257,
"step": 820
},
{
"epoch": 0.005280461663219699,
"grad_norm": 0.6249509453773499,
"learning_rate": 2.0975e-05,
"loss": 2.437354850769043,
"step": 840
},
{
"epoch": 0.005406186940915406,
"grad_norm": 0.7308785319328308,
"learning_rate": 2.1475e-05,
"loss": 2.16713924407959,
"step": 860
},
{
"epoch": 0.005531912218611113,
"grad_norm": 0.7222583889961243,
"learning_rate": 2.1975000000000002e-05,
"loss": 2.2146921157836914,
"step": 880
},
{
"epoch": 0.00565763749630682,
"grad_norm": 0.8205286264419556,
"learning_rate": 2.2475e-05,
"loss": 2.1331754684448243,
"step": 900
},
{
"epoch": 0.005783362774002527,
"grad_norm": 0.8732596635818481,
"learning_rate": 2.2975000000000003e-05,
"loss": 2.3930585861206053,
"step": 920
},
{
"epoch": 0.005909088051698234,
"grad_norm": 0.8867924213409424,
"learning_rate": 2.3475e-05,
"loss": 2.325008773803711,
"step": 940
},
{
"epoch": 0.006034813329393941,
"grad_norm": 0.6259322762489319,
"learning_rate": 2.3975e-05,
"loss": 2.1665245056152345,
"step": 960
},
{
"epoch": 0.006160538607089649,
"grad_norm": 0.7788486480712891,
"learning_rate": 2.4475000000000002e-05,
"loss": 2.0807886123657227,
"step": 980
},
{
"epoch": 0.0062862638847853555,
"grad_norm": 0.7346381545066833,
"learning_rate": 2.4975e-05,
"loss": 2.2518342971801757,
"step": 1000
},
{
"epoch": 0.006411989162481062,
"grad_norm": 0.6551724672317505,
"learning_rate": 2.5475e-05,
"loss": 2.2025928497314453,
"step": 1020
},
{
"epoch": 0.00653771444017677,
"grad_norm": 0.42648759484291077,
"learning_rate": 2.5974999999999998e-05,
"loss": 2.2169179916381836,
"step": 1040
},
{
"epoch": 0.006663439717872477,
"grad_norm": 0.6696974039077759,
"learning_rate": 2.6475e-05,
"loss": 2.2179336547851562,
"step": 1060
},
{
"epoch": 0.006789164995568184,
"grad_norm": 0.6720432043075562,
"learning_rate": 2.6975000000000002e-05,
"loss": 2.1793497085571287,
"step": 1080
},
{
"epoch": 0.0069148902732638915,
"grad_norm": 0.7858997583389282,
"learning_rate": 2.7475e-05,
"loss": 2.2960178375244142,
"step": 1100
},
{
"epoch": 0.007040615550959598,
"grad_norm": 0.6754783987998962,
"learning_rate": 2.7975000000000002e-05,
"loss": 2.193424415588379,
"step": 1120
},
{
"epoch": 0.007166340828655305,
"grad_norm": 0.8978444933891296,
"learning_rate": 2.8475e-05,
"loss": 2.245846748352051,
"step": 1140
},
{
"epoch": 0.007292066106351012,
"grad_norm": 0.6270891427993774,
"learning_rate": 2.8975000000000003e-05,
"loss": 2.222321891784668,
"step": 1160
},
{
"epoch": 0.00741779138404672,
"grad_norm": 0.8105082511901855,
"learning_rate": 2.9475e-05,
"loss": 2.2370512008666994,
"step": 1180
},
{
"epoch": 0.007543516661742427,
"grad_norm": 0.8254700303077698,
"learning_rate": 2.9975000000000004e-05,
"loss": 2.2856861114501954,
"step": 1200
},
{
"epoch": 0.0076692419394381334,
"grad_norm": 0.7499117851257324,
"learning_rate": 3.0475000000000002e-05,
"loss": 2.145079803466797,
"step": 1220
},
{
"epoch": 0.007794967217133841,
"grad_norm": 0.5796831846237183,
"learning_rate": 3.0975e-05,
"loss": 2.2193859100341795,
"step": 1240
},
{
"epoch": 0.007920692494829547,
"grad_norm": 0.7580195069313049,
"learning_rate": 3.1475e-05,
"loss": 2.325836181640625,
"step": 1260
},
{
"epoch": 0.008046417772525256,
"grad_norm": 0.7444676756858826,
"learning_rate": 3.1975e-05,
"loss": 2.176131820678711,
"step": 1280
},
{
"epoch": 0.008172143050220963,
"grad_norm": 0.9642544984817505,
"learning_rate": 3.2474999999999997e-05,
"loss": 2.139938735961914,
"step": 1300
},
{
"epoch": 0.00829786832791667,
"grad_norm": 0.8218713998794556,
"learning_rate": 3.2975e-05,
"loss": 2.2411163330078123,
"step": 1320
},
{
"epoch": 0.008423593605612376,
"grad_norm": 1.0058637857437134,
"learning_rate": 3.3475e-05,
"loss": 2.2701160430908205,
"step": 1340
},
{
"epoch": 0.008549318883308083,
"grad_norm": 0.9082450270652771,
"learning_rate": 3.3975e-05,
"loss": 2.223080635070801,
"step": 1360
},
{
"epoch": 0.00867504416100379,
"grad_norm": 1.5511119365692139,
"learning_rate": 3.4475000000000005e-05,
"loss": 2.2058855056762696,
"step": 1380
},
{
"epoch": 0.008800769438699499,
"grad_norm": 0.9214478731155396,
"learning_rate": 3.4975e-05,
"loss": 2.275226593017578,
"step": 1400
},
{
"epoch": 0.008926494716395205,
"grad_norm": 0.7495436668395996,
"learning_rate": 3.5475e-05,
"loss": 2.0992334365844725,
"step": 1420
},
{
"epoch": 0.009052219994090912,
"grad_norm": 0.7678313851356506,
"learning_rate": 3.5975e-05,
"loss": 2.151212692260742,
"step": 1440
},
{
"epoch": 0.009177945271786619,
"grad_norm": 0.8514085412025452,
"learning_rate": 3.6475000000000006e-05,
"loss": 2.3009883880615236,
"step": 1460
},
{
"epoch": 0.009303670549482326,
"grad_norm": 0.7245936393737793,
"learning_rate": 3.6975000000000004e-05,
"loss": 2.2095823287963867,
"step": 1480
},
{
"epoch": 0.009429395827178033,
"grad_norm": 0.576258659362793,
"learning_rate": 3.7475e-05,
"loss": 2.2135459899902346,
"step": 1500
},
{
"epoch": 0.00955512110487374,
"grad_norm": 0.7789803147315979,
"learning_rate": 3.7975e-05,
"loss": 2.172737884521484,
"step": 1520
},
{
"epoch": 0.009680846382569448,
"grad_norm": 0.6502222418785095,
"learning_rate": 3.8475e-05,
"loss": 2.202811622619629,
"step": 1540
},
{
"epoch": 0.009806571660265155,
"grad_norm": 0.7619134783744812,
"learning_rate": 3.8975e-05,
"loss": 2.120333671569824,
"step": 1560
},
{
"epoch": 0.009932296937960862,
"grad_norm": 0.624914824962616,
"learning_rate": 3.9475000000000004e-05,
"loss": 2.133666229248047,
"step": 1580
},
{
"epoch": 0.010058022215656569,
"grad_norm": 0.8268408179283142,
"learning_rate": 3.9975e-05,
"loss": 2.2280460357666017,
"step": 1600
},
{
"epoch": 0.010183747493352276,
"grad_norm": 1.2030913829803467,
"learning_rate": 4.0475e-05,
"loss": 2.2895408630371095,
"step": 1620
},
{
"epoch": 0.010309472771047982,
"grad_norm": 0.5576544404029846,
"learning_rate": 4.0975e-05,
"loss": 2.143132781982422,
"step": 1640
},
{
"epoch": 0.01043519804874369,
"grad_norm": 0.6146367192268372,
"learning_rate": 4.1475000000000005e-05,
"loss": 2.0781791687011717,
"step": 1660
},
{
"epoch": 0.010560923326439398,
"grad_norm": 0.637881875038147,
"learning_rate": 4.1975000000000004e-05,
"loss": 2.269753265380859,
"step": 1680
},
{
"epoch": 0.010686648604135105,
"grad_norm": 1.2377184629440308,
"learning_rate": 4.2475e-05,
"loss": 2.3090824127197265,
"step": 1700
},
{
"epoch": 0.010812373881830812,
"grad_norm": 1.0414743423461914,
"learning_rate": 4.2975e-05,
"loss": 2.2602685928344726,
"step": 1720
},
{
"epoch": 0.010938099159526518,
"grad_norm": 0.7796839475631714,
"learning_rate": 4.3475000000000006e-05,
"loss": 2.3865522384643554,
"step": 1740
},
{
"epoch": 0.011063824437222225,
"grad_norm": 0.7342143654823303,
"learning_rate": 4.3975e-05,
"loss": 2.3370746612548827,
"step": 1760
},
{
"epoch": 0.011189549714917932,
"grad_norm": 0.6339659094810486,
"learning_rate": 4.4475e-05,
"loss": 2.2576133728027346,
"step": 1780
},
{
"epoch": 0.01131527499261364,
"grad_norm": 0.6305493116378784,
"learning_rate": 4.4975e-05,
"loss": 2.146904945373535,
"step": 1800
},
{
"epoch": 0.011441000270309348,
"grad_norm": 0.7393673658370972,
"learning_rate": 4.5475e-05,
"loss": 2.207014465332031,
"step": 1820
},
{
"epoch": 0.011566725548005054,
"grad_norm": 0.5975062847137451,
"learning_rate": 4.5975e-05,
"loss": 2.2376119613647463,
"step": 1840
},
{
"epoch": 0.011692450825700761,
"grad_norm": 0.8439088463783264,
"learning_rate": 4.6475000000000005e-05,
"loss": 2.172005844116211,
"step": 1860
},
{
"epoch": 0.011818176103396468,
"grad_norm": 0.9270113110542297,
"learning_rate": 4.6975000000000003e-05,
"loss": 2.373341369628906,
"step": 1880
},
{
"epoch": 0.011943901381092175,
"grad_norm": 0.8112410306930542,
"learning_rate": 4.7475e-05,
"loss": 2.2132829666137694,
"step": 1900
},
{
"epoch": 0.012069626658787882,
"grad_norm": 0.7576470971107483,
"learning_rate": 4.7975e-05,
"loss": 2.1676565170288087,
"step": 1920
},
{
"epoch": 0.01219535193648359,
"grad_norm": 0.6396933794021606,
"learning_rate": 4.8475000000000006e-05,
"loss": 2.1356874465942384,
"step": 1940
},
{
"epoch": 0.012321077214179297,
"grad_norm": 0.9815897941589355,
"learning_rate": 4.8975000000000005e-05,
"loss": 2.153605651855469,
"step": 1960
},
{
"epoch": 0.012446802491875004,
"grad_norm": 1.0716313123703003,
"learning_rate": 4.9475e-05,
"loss": 2.237149238586426,
"step": 1980
},
{
"epoch": 0.012572527769570711,
"grad_norm": 0.7417507171630859,
"learning_rate": 4.9975e-05,
"loss": 2.3103559494018553,
"step": 2000
},
{
"epoch": 0.012698253047266418,
"grad_norm": 0.9836956858634949,
"learning_rate": 5.047500000000001e-05,
"loss": 2.226584243774414,
"step": 2020
},
{
"epoch": 0.012823978324962125,
"grad_norm": 0.9194190502166748,
"learning_rate": 5.0975000000000006e-05,
"loss": 2.152355766296387,
"step": 2040
},
{
"epoch": 0.012949703602657832,
"grad_norm": 0.9516499638557434,
"learning_rate": 5.1475000000000004e-05,
"loss": 2.230098342895508,
"step": 2060
},
{
"epoch": 0.01307542888035354,
"grad_norm": 0.631192147731781,
"learning_rate": 5.197500000000001e-05,
"loss": 2.298840141296387,
"step": 2080
},
{
"epoch": 0.013201154158049247,
"grad_norm": 0.6552205085754395,
"learning_rate": 5.247500000000001e-05,
"loss": 2.2214452743530275,
"step": 2100
},
{
"epoch": 0.013326879435744954,
"grad_norm": 0.9227390289306641,
"learning_rate": 5.297500000000001e-05,
"loss": 2.2039995193481445,
"step": 2120
},
{
"epoch": 0.01345260471344066,
"grad_norm": 0.9626750946044922,
"learning_rate": 5.3475e-05,
"loss": 2.200083541870117,
"step": 2140
},
{
"epoch": 0.013578329991136368,
"grad_norm": 0.7620527148246765,
"learning_rate": 5.3975e-05,
"loss": 2.1179471969604493,
"step": 2160
},
{
"epoch": 0.013704055268832074,
"grad_norm": 0.7514252066612244,
"learning_rate": 5.4474999999999996e-05,
"loss": 2.0252569198608397,
"step": 2180
},
{
"epoch": 0.013829780546527783,
"grad_norm": 0.6158234477043152,
"learning_rate": 5.4975e-05,
"loss": 2.165945625305176,
"step": 2200
},
{
"epoch": 0.01395550582422349,
"grad_norm": 0.7800559401512146,
"learning_rate": 5.5475e-05,
"loss": 2.0259613037109374,
"step": 2220
},
{
"epoch": 0.014081231101919197,
"grad_norm": 0.4745946526527405,
"learning_rate": 5.5975e-05,
"loss": 2.166629409790039,
"step": 2240
},
{
"epoch": 0.014206956379614903,
"grad_norm": 0.6183483004570007,
"learning_rate": 5.6475e-05,
"loss": 2.2248981475830076,
"step": 2260
},
{
"epoch": 0.01433268165731061,
"grad_norm": 0.9926730990409851,
"learning_rate": 5.6975e-05,
"loss": 2.2324359893798826,
"step": 2280
},
{
"epoch": 0.014458406935006317,
"grad_norm": 0.6978363394737244,
"learning_rate": 5.7475e-05,
"loss": 2.2633106231689455,
"step": 2300
},
{
"epoch": 0.014584132212702024,
"grad_norm": 0.6764455437660217,
"learning_rate": 5.7975e-05,
"loss": 2.2547515869140624,
"step": 2320
},
{
"epoch": 0.014709857490397733,
"grad_norm": 0.6333333253860474,
"learning_rate": 5.8475000000000005e-05,
"loss": 2.2785802841186524,
"step": 2340
},
{
"epoch": 0.01483558276809344,
"grad_norm": 1.1081982851028442,
"learning_rate": 5.8975000000000004e-05,
"loss": 2.1292343139648438,
"step": 2360
},
{
"epoch": 0.014961308045789146,
"grad_norm": 0.69389808177948,
"learning_rate": 5.9475e-05,
"loss": 2.2307294845581054,
"step": 2380
},
{
"epoch": 0.015087033323484853,
"grad_norm": 0.8631381988525391,
"learning_rate": 5.9975e-05,
"loss": 2.2449098587036134,
"step": 2400
},
{
"epoch": 0.01521275860118056,
"grad_norm": 0.9202216863632202,
"learning_rate": 6.0475000000000006e-05,
"loss": 2.1659168243408202,
"step": 2420
},
{
"epoch": 0.015338483878876267,
"grad_norm": 0.7391654253005981,
"learning_rate": 6.0975000000000005e-05,
"loss": 2.0840213775634764,
"step": 2440
},
{
"epoch": 0.015464209156571974,
"grad_norm": 0.8017479181289673,
"learning_rate": 6.1475e-05,
"loss": 2.17960205078125,
"step": 2460
},
{
"epoch": 0.015589934434267682,
"grad_norm": 0.8878335952758789,
"learning_rate": 6.1975e-05,
"loss": 2.1136425018310545,
"step": 2480
},
{
"epoch": 0.015715659711963387,
"grad_norm": 0.8109790086746216,
"learning_rate": 6.2475e-05,
"loss": 2.047270584106445,
"step": 2500
},
{
"epoch": 0.015841384989659094,
"grad_norm": 0.6094740629196167,
"learning_rate": 6.297500000000001e-05,
"loss": 2.1872735977172852,
"step": 2520
},
{
"epoch": 0.015967110267354805,
"grad_norm": 0.6133264303207397,
"learning_rate": 6.347500000000001e-05,
"loss": 2.3266223907470702,
"step": 2540
},
{
"epoch": 0.01609283554505051,
"grad_norm": 0.924880862236023,
"learning_rate": 6.397500000000001e-05,
"loss": 2.1481760025024412,
"step": 2560
},
{
"epoch": 0.01621856082274622,
"grad_norm": 0.8004190325737,
"learning_rate": 6.447500000000001e-05,
"loss": 2.2322179794311525,
"step": 2580
},
{
"epoch": 0.016344286100441925,
"grad_norm": 0.6677139401435852,
"learning_rate": 6.497500000000001e-05,
"loss": 2.293388557434082,
"step": 2600
},
{
"epoch": 0.016470011378137632,
"grad_norm": 1.3870952129364014,
"learning_rate": 6.5475e-05,
"loss": 2.204412651062012,
"step": 2620
},
{
"epoch": 0.01659573665583334,
"grad_norm": 0.722831130027771,
"learning_rate": 6.5975e-05,
"loss": 2.2492038726806642,
"step": 2640
},
{
"epoch": 0.016721461933529046,
"grad_norm": 0.7346879243850708,
"learning_rate": 6.6475e-05,
"loss": 2.193736457824707,
"step": 2660
},
{
"epoch": 0.016847187211224753,
"grad_norm": 0.5910217761993408,
"learning_rate": 6.6975e-05,
"loss": 2.1651554107666016,
"step": 2680
},
{
"epoch": 0.01697291248892046,
"grad_norm": 0.647753119468689,
"learning_rate": 6.7475e-05,
"loss": 2.2381689071655275,
"step": 2700
},
{
"epoch": 0.017098637766616166,
"grad_norm": 0.6268242001533508,
"learning_rate": 6.7975e-05,
"loss": 2.1789567947387694,
"step": 2720
},
{
"epoch": 0.017224363044311873,
"grad_norm": 0.6920773983001709,
"learning_rate": 6.8475e-05,
"loss": 2.273392677307129,
"step": 2740
},
{
"epoch": 0.01735008832200758,
"grad_norm": 0.8666326999664307,
"learning_rate": 6.8975e-05,
"loss": 2.1571945190429687,
"step": 2760
},
{
"epoch": 0.017475813599703287,
"grad_norm": 0.6093314290046692,
"learning_rate": 6.9475e-05,
"loss": 2.1972126007080077,
"step": 2780
},
{
"epoch": 0.017601538877398997,
"grad_norm": 0.5214780569076538,
"learning_rate": 6.997500000000001e-05,
"loss": 2.2142589569091795,
"step": 2800
},
{
"epoch": 0.017727264155094704,
"grad_norm": 1.0918712615966797,
"learning_rate": 7.0475e-05,
"loss": 2.0404659271240235,
"step": 2820
},
{
"epoch": 0.01785298943279041,
"grad_norm": 0.7436941266059875,
"learning_rate": 7.0975e-05,
"loss": 2.133719062805176,
"step": 2840
},
{
"epoch": 0.017978714710486118,
"grad_norm": 0.7502368092536926,
"learning_rate": 7.1475e-05,
"loss": 2.201572036743164,
"step": 2860
},
{
"epoch": 0.018104439988181825,
"grad_norm": 0.8413222432136536,
"learning_rate": 7.1975e-05,
"loss": 2.1762102127075194,
"step": 2880
},
{
"epoch": 0.01823016526587753,
"grad_norm": 0.5973228812217712,
"learning_rate": 7.2475e-05,
"loss": 2.0592535018920897,
"step": 2900
},
{
"epoch": 0.018355890543573238,
"grad_norm": 0.8865782022476196,
"learning_rate": 7.2975e-05,
"loss": 2.1160760879516602,
"step": 2920
},
{
"epoch": 0.018481615821268945,
"grad_norm": 0.8475161194801331,
"learning_rate": 7.347500000000001e-05,
"loss": 2.220221519470215,
"step": 2940
},
{
"epoch": 0.018607341098964652,
"grad_norm": 0.7635546922683716,
"learning_rate": 7.397500000000001e-05,
"loss": 2.2616430282592774,
"step": 2960
},
{
"epoch": 0.01873306637666036,
"grad_norm": 0.6724838018417358,
"learning_rate": 7.447500000000001e-05,
"loss": 2.2418001174926756,
"step": 2980
},
{
"epoch": 0.018858791654356066,
"grad_norm": 0.7106826305389404,
"learning_rate": 7.4975e-05,
"loss": 2.1272777557373046,
"step": 3000
},
{
"epoch": 0.018984516932051772,
"grad_norm": 0.6232185959815979,
"learning_rate": 7.5475e-05,
"loss": 2.2246204376220704,
"step": 3020
},
{
"epoch": 0.01911024220974748,
"grad_norm": 1.5051827430725098,
"learning_rate": 7.5975e-05,
"loss": 2.0963869094848633,
"step": 3040
},
{
"epoch": 0.019235967487443186,
"grad_norm": 0.7139873504638672,
"learning_rate": 7.6475e-05,
"loss": 2.0114721298217773,
"step": 3060
},
{
"epoch": 0.019361692765138896,
"grad_norm": 0.7590590119361877,
"learning_rate": 7.697500000000001e-05,
"loss": 2.1946556091308596,
"step": 3080
},
{
"epoch": 0.019487418042834603,
"grad_norm": 0.6973894834518433,
"learning_rate": 7.747500000000001e-05,
"loss": 2.1527034759521486,
"step": 3100
},
{
"epoch": 0.01961314332053031,
"grad_norm": 0.538654088973999,
"learning_rate": 7.797500000000001e-05,
"loss": 2.1023521423339844,
"step": 3120
},
{
"epoch": 0.019738868598226017,
"grad_norm": 0.5581122040748596,
"learning_rate": 7.8475e-05,
"loss": 2.1083656311035157,
"step": 3140
},
{
"epoch": 0.019864593875921724,
"grad_norm": 0.6352174282073975,
"learning_rate": 7.8975e-05,
"loss": 2.1281736373901365,
"step": 3160
},
{
"epoch": 0.01999031915361743,
"grad_norm": 0.6354402303695679,
"learning_rate": 7.9475e-05,
"loss": 2.2377193450927733,
"step": 3180
},
{
"epoch": 0.020116044431313138,
"grad_norm": 0.4512730538845062,
"learning_rate": 7.9975e-05,
"loss": 2.1053667068481445,
"step": 3200
},
{
"epoch": 0.020241769709008844,
"grad_norm": 0.7477418780326843,
"learning_rate": 8.0475e-05,
"loss": 2.237176704406738,
"step": 3220
},
{
"epoch": 0.02036749498670455,
"grad_norm": 0.8833841681480408,
"learning_rate": 8.0975e-05,
"loss": 2.269827651977539,
"step": 3240
},
{
"epoch": 0.020493220264400258,
"grad_norm": 0.9374681711196899,
"learning_rate": 8.1475e-05,
"loss": 2.1439802169799806,
"step": 3260
},
{
"epoch": 0.020618945542095965,
"grad_norm": 0.8119531273841858,
"learning_rate": 8.1975e-05,
"loss": 2.208771514892578,
"step": 3280
},
{
"epoch": 0.020744670819791672,
"grad_norm": 0.7813240885734558,
"learning_rate": 8.2475e-05,
"loss": 2.1550825119018553,
"step": 3300
},
{
"epoch": 0.02087039609748738,
"grad_norm": 0.6853654384613037,
"learning_rate": 8.2975e-05,
"loss": 2.0903724670410155,
"step": 3320
},
{
"epoch": 0.02099612137518309,
"grad_norm": 0.722632884979248,
"learning_rate": 8.347500000000001e-05,
"loss": 2.191097450256348,
"step": 3340
},
{
"epoch": 0.021121846652878796,
"grad_norm": 0.640600323677063,
"learning_rate": 8.397500000000001e-05,
"loss": 1.9992816925048829,
"step": 3360
},
{
"epoch": 0.021247571930574503,
"grad_norm": 0.6054248213768005,
"learning_rate": 8.447500000000001e-05,
"loss": 1.9980829238891602,
"step": 3380
},
{
"epoch": 0.02137329720827021,
"grad_norm": 0.8357540965080261,
"learning_rate": 8.4975e-05,
"loss": 2.0778709411621095,
"step": 3400
},
{
"epoch": 0.021499022485965916,
"grad_norm": 0.6165632009506226,
"learning_rate": 8.5475e-05,
"loss": 2.1318584442138673,
"step": 3420
},
{
"epoch": 0.021624747763661623,
"grad_norm": 0.4567464292049408,
"learning_rate": 8.5975e-05,
"loss": 2.1998617172241213,
"step": 3440
},
{
"epoch": 0.02175047304135733,
"grad_norm": 0.9256274104118347,
"learning_rate": 8.6475e-05,
"loss": 2.215155601501465,
"step": 3460
},
{
"epoch": 0.021876198319053037,
"grad_norm": 0.6517425179481506,
"learning_rate": 8.6975e-05,
"loss": 2.113406944274902,
"step": 3480
},
{
"epoch": 0.022001923596748744,
"grad_norm": 0.800165593624115,
"learning_rate": 8.747500000000001e-05,
"loss": 2.0685216903686525,
"step": 3500
},
{
"epoch": 0.02212764887444445,
"grad_norm": 0.7264109253883362,
"learning_rate": 8.797500000000001e-05,
"loss": 2.228927421569824,
"step": 3520
},
{
"epoch": 0.022253374152140157,
"grad_norm": 0.621918797492981,
"learning_rate": 8.847500000000001e-05,
"loss": 2.163255310058594,
"step": 3540
},
{
"epoch": 0.022379099429835864,
"grad_norm": 0.7633965611457825,
"learning_rate": 8.897500000000001e-05,
"loss": 2.0805002212524415,
"step": 3560
},
{
"epoch": 0.02250482470753157,
"grad_norm": 1.0345146656036377,
"learning_rate": 8.9475e-05,
"loss": 2.173696517944336,
"step": 3580
},
{
"epoch": 0.02263054998522728,
"grad_norm": 0.5648631453514099,
"learning_rate": 8.9975e-05,
"loss": 2.23458194732666,
"step": 3600
},
{
"epoch": 0.02275627526292299,
"grad_norm": 0.5693984627723694,
"learning_rate": 9.0475e-05,
"loss": 2.102839469909668,
"step": 3620
},
{
"epoch": 0.022882000540618695,
"grad_norm": 0.7708291411399841,
"learning_rate": 9.0975e-05,
"loss": 2.1710891723632812,
"step": 3640
},
{
"epoch": 0.023007725818314402,
"grad_norm": 0.6380087733268738,
"learning_rate": 9.1475e-05,
"loss": 2.1137651443481444,
"step": 3660
},
{
"epoch": 0.02313345109601011,
"grad_norm": 0.8363099694252014,
"learning_rate": 9.1975e-05,
"loss": 2.249873924255371,
"step": 3680
},
{
"epoch": 0.023259176373705816,
"grad_norm": 0.9241217970848083,
"learning_rate": 9.2475e-05,
"loss": 2.171980857849121,
"step": 3700
},
{
"epoch": 0.023384901651401523,
"grad_norm": 0.9299995303153992,
"learning_rate": 9.2975e-05,
"loss": 2.0629114151000976,
"step": 3720
},
{
"epoch": 0.02351062692909723,
"grad_norm": 0.8281742334365845,
"learning_rate": 9.3475e-05,
"loss": 2.118360137939453,
"step": 3740
},
{
"epoch": 0.023636352206792936,
"grad_norm": 0.735012412071228,
"learning_rate": 9.397500000000001e-05,
"loss": 2.0829288482666017,
"step": 3760
},
{
"epoch": 0.023762077484488643,
"grad_norm": 0.6220835447311401,
"learning_rate": 9.4475e-05,
"loss": 2.288552665710449,
"step": 3780
},
{
"epoch": 0.02388780276218435,
"grad_norm": 0.5044544339179993,
"learning_rate": 9.4975e-05,
"loss": 2.2265188217163088,
"step": 3800
},
{
"epoch": 0.024013528039880057,
"grad_norm": 0.6451289057731628,
"learning_rate": 9.5475e-05,
"loss": 2.161042022705078,
"step": 3820
},
{
"epoch": 0.024139253317575764,
"grad_norm": 1.0589903593063354,
"learning_rate": 9.5975e-05,
"loss": 2.1686399459838865,
"step": 3840
},
{
"epoch": 0.024264978595271474,
"grad_norm": 0.7059029340744019,
"learning_rate": 9.6475e-05,
"loss": 2.109272766113281,
"step": 3860
},
{
"epoch": 0.02439070387296718,
"grad_norm": 0.5941277146339417,
"learning_rate": 9.6975e-05,
"loss": 2.057619094848633,
"step": 3880
},
{
"epoch": 0.024516429150662888,
"grad_norm": 0.5671762824058533,
"learning_rate": 9.747500000000001e-05,
"loss": 2.014023208618164,
"step": 3900
},
{
"epoch": 0.024642154428358595,
"grad_norm": 0.6943921446800232,
"learning_rate": 9.797500000000001e-05,
"loss": 2.1530567169189454,
"step": 3920
},
{
"epoch": 0.0247678797060543,
"grad_norm": 0.6907370686531067,
"learning_rate": 9.847500000000001e-05,
"loss": 2.2318679809570314,
"step": 3940
},
{
"epoch": 0.02489360498375001,
"grad_norm": 0.7025376558303833,
"learning_rate": 9.897500000000001e-05,
"loss": 2.0632183074951174,
"step": 3960
},
{
"epoch": 0.025019330261445715,
"grad_norm": 0.4425835609436035,
"learning_rate": 9.9475e-05,
"loss": 2.0571531295776366,
"step": 3980
},
{
"epoch": 0.025145055539141422,
"grad_norm": 0.7280085682868958,
"learning_rate": 9.9975e-05,
"loss": 2.011970329284668,
"step": 4000
},
{
"epoch": 0.02527078081683713,
"grad_norm": 0.5700169205665588,
"learning_rate": 0.000100475,
"loss": 2.162436866760254,
"step": 4020
},
{
"epoch": 0.025396506094532836,
"grad_norm": 0.612692654132843,
"learning_rate": 0.000100975,
"loss": 2.0830350875854493,
"step": 4040
},
{
"epoch": 0.025522231372228543,
"grad_norm": 0.6931089758872986,
"learning_rate": 0.00010147500000000001,
"loss": 2.118963623046875,
"step": 4060
},
{
"epoch": 0.02564795664992425,
"grad_norm": 0.8360069990158081,
"learning_rate": 0.000101975,
"loss": 2.146648406982422,
"step": 4080
},
{
"epoch": 0.025773681927619956,
"grad_norm": 0.6365113258361816,
"learning_rate": 0.00010247500000000001,
"loss": 2.1310033798217773,
"step": 4100
},
{
"epoch": 0.025899407205315663,
"grad_norm": 0.6738468408584595,
"learning_rate": 0.000102975,
"loss": 2.176763343811035,
"step": 4120
},
{
"epoch": 0.026025132483011373,
"grad_norm": 0.6279870271682739,
"learning_rate": 0.00010347500000000001,
"loss": 2.033766174316406,
"step": 4140
},
{
"epoch": 0.02615085776070708,
"grad_norm": 0.7508738040924072,
"learning_rate": 0.000103975,
"loss": 2.2269708633422853,
"step": 4160
},
{
"epoch": 0.026276583038402787,
"grad_norm": 0.840672492980957,
"learning_rate": 0.000104475,
"loss": 2.030698776245117,
"step": 4180
},
{
"epoch": 0.026402308316098494,
"grad_norm": 0.7917266488075256,
"learning_rate": 0.000104975,
"loss": 2.251175308227539,
"step": 4200
},
{
"epoch": 0.0265280335937942,
"grad_norm": 0.5847408771514893,
"learning_rate": 0.00010547500000000002,
"loss": 2.0700811386108398,
"step": 4220
},
{
"epoch": 0.026653758871489908,
"grad_norm": 0.6782088875770569,
"learning_rate": 0.000105975,
"loss": 2.197639274597168,
"step": 4240
},
{
"epoch": 0.026779484149185614,
"grad_norm": 0.9398831725120544,
"learning_rate": 0.00010647500000000001,
"loss": 2.1179847717285156,
"step": 4260
},
{
"epoch": 0.02690520942688132,
"grad_norm": 0.7190554738044739,
"learning_rate": 0.000106975,
"loss": 2.0518001556396483,
"step": 4280
},
{
"epoch": 0.027030934704577028,
"grad_norm": 0.704131543636322,
"learning_rate": 0.00010747500000000001,
"loss": 2.146711730957031,
"step": 4300
},
{
"epoch": 0.027156659982272735,
"grad_norm": 0.8494829535484314,
"learning_rate": 0.00010797500000000001,
"loss": 2.0805326461791993,
"step": 4320
},
{
"epoch": 0.027282385259968442,
"grad_norm": 0.7388854026794434,
"learning_rate": 0.00010847500000000002,
"loss": 2.139107513427734,
"step": 4340
},
{
"epoch": 0.02740811053766415,
"grad_norm": 0.5768877863883972,
"learning_rate": 0.000108975,
"loss": 2.0558916091918946,
"step": 4360
},
{
"epoch": 0.027533835815359856,
"grad_norm": 1.1913079023361206,
"learning_rate": 0.00010947499999999999,
"loss": 2.055363082885742,
"step": 4380
},
{
"epoch": 0.027659561093055566,
"grad_norm": 0.6604535579681396,
"learning_rate": 0.000109975,
"loss": 1.9485313415527343,
"step": 4400
},
{
"epoch": 0.027785286370751273,
"grad_norm": 0.7500801682472229,
"learning_rate": 0.000110475,
"loss": 2.038515090942383,
"step": 4420
},
{
"epoch": 0.02791101164844698,
"grad_norm": 0.6994207501411438,
"learning_rate": 0.000110975,
"loss": 2.1263587951660154,
"step": 4440
},
{
"epoch": 0.028036736926142686,
"grad_norm": 0.5363154411315918,
"learning_rate": 0.000111475,
"loss": 2.1651823043823244,
"step": 4460
},
{
"epoch": 0.028162462203838393,
"grad_norm": 0.8857939839363098,
"learning_rate": 0.00011197500000000001,
"loss": 2.0685266494750976,
"step": 4480
},
{
"epoch": 0.0282881874815341,
"grad_norm": 0.7441563010215759,
"learning_rate": 0.000112475,
"loss": 2.1119768142700197,
"step": 4500
},
{
"epoch": 0.028413912759229807,
"grad_norm": 0.8807816505432129,
"learning_rate": 0.00011297500000000001,
"loss": 2.078415107727051,
"step": 4520
},
{
"epoch": 0.028539638036925514,
"grad_norm": 0.512524425983429,
"learning_rate": 0.000113475,
"loss": 2.110816764831543,
"step": 4540
},
{
"epoch": 0.02866536331462122,
"grad_norm": 0.6433947086334229,
"learning_rate": 0.000113975,
"loss": 2.164168930053711,
"step": 4560
},
{
"epoch": 0.028791088592316928,
"grad_norm": 0.8011267781257629,
"learning_rate": 0.000114475,
"loss": 2.0980674743652346,
"step": 4580
},
{
"epoch": 0.028916813870012634,
"grad_norm": 0.8300204873085022,
"learning_rate": 0.00011497500000000002,
"loss": 2.0424530029296877,
"step": 4600
},
{
"epoch": 0.02904253914770834,
"grad_norm": 0.7402482628822327,
"learning_rate": 0.000115475,
"loss": 2.131890296936035,
"step": 4620
},
{
"epoch": 0.029168264425404048,
"grad_norm": 0.6597459316253662,
"learning_rate": 0.00011597500000000001,
"loss": 2.004606819152832,
"step": 4640
},
{
"epoch": 0.02929398970309976,
"grad_norm": 0.7173661589622498,
"learning_rate": 0.000116475,
"loss": 2.0047943115234377,
"step": 4660
},
{
"epoch": 0.029419714980795465,
"grad_norm": 0.6268314123153687,
"learning_rate": 0.00011697500000000001,
"loss": 2.158557319641113,
"step": 4680
},
{
"epoch": 0.029545440258491172,
"grad_norm": 0.7198747396469116,
"learning_rate": 0.000117475,
"loss": 2.1982650756835938,
"step": 4700
},
{
"epoch": 0.02967116553618688,
"grad_norm": 0.8585025668144226,
"learning_rate": 0.00011797500000000001,
"loss": 1.9955005645751953,
"step": 4720
},
{
"epoch": 0.029796890813882586,
"grad_norm": 0.7360095381736755,
"learning_rate": 0.000118475,
"loss": 2.175639533996582,
"step": 4740
},
{
"epoch": 0.029922616091578293,
"grad_norm": 0.6923116445541382,
"learning_rate": 0.00011897500000000002,
"loss": 2.063397026062012,
"step": 4760
},
{
"epoch": 0.030048341369274,
"grad_norm": 0.4510480463504791,
"learning_rate": 0.000119475,
"loss": 2.0311891555786135,
"step": 4780
},
{
"epoch": 0.030174066646969706,
"grad_norm": 0.6425082087516785,
"learning_rate": 0.00011997500000000002,
"loss": 2.069586181640625,
"step": 4800
},
{
"epoch": 0.030299791924665413,
"grad_norm": 0.8543846607208252,
"learning_rate": 0.000120475,
"loss": 2.1314723968505858,
"step": 4820
},
{
"epoch": 0.03042551720236112,
"grad_norm": 0.714083731174469,
"learning_rate": 0.00012097500000000001,
"loss": 2.157556915283203,
"step": 4840
},
{
"epoch": 0.030551242480056827,
"grad_norm": 0.7829552888870239,
"learning_rate": 0.00012147500000000001,
"loss": 2.1580076217651367,
"step": 4860
},
{
"epoch": 0.030676967757752534,
"grad_norm": 0.5753886699676514,
"learning_rate": 0.000121975,
"loss": 2.0693853378295897,
"step": 4880
},
{
"epoch": 0.03080269303544824,
"grad_norm": 0.6424887776374817,
"learning_rate": 0.000122475,
"loss": 1.977574348449707,
"step": 4900
},
{
"epoch": 0.030928418313143947,
"grad_norm": 0.7698935270309448,
"learning_rate": 0.000122975,
"loss": 2.153335762023926,
"step": 4920
},
{
"epoch": 0.031054143590839658,
"grad_norm": 0.5171162486076355,
"learning_rate": 0.000123475,
"loss": 1.9920032501220704,
"step": 4940
},
{
"epoch": 0.031179868868535365,
"grad_norm": 0.6690151691436768,
"learning_rate": 0.000123975,
"loss": 2.1288196563720705,
"step": 4960
},
{
"epoch": 0.03130559414623107,
"grad_norm": 0.6242818236351013,
"learning_rate": 0.000124475,
"loss": 2.09140625,
"step": 4980
},
{
"epoch": 0.031431319423926775,
"grad_norm": 0.6279743909835815,
"learning_rate": 0.000124975,
"loss": 2.168587303161621,
"step": 5000
}
],
"logging_steps": 20,
"max_steps": 160000,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.0878718733962854e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}