starcoder2_nim_finetune / trainer_state.json
tuix3's picture
Upload 13 files
f837da7 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.05660991522665195,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005660991522665195,
"grad_norm": 0.4538244605064392,
"learning_rate": 2e-05,
"loss": 3.4057,
"step": 10
},
{
"epoch": 0.001132198304533039,
"grad_norm": 0.5858215689659119,
"learning_rate": 4e-05,
"loss": 3.0604,
"step": 20
},
{
"epoch": 0.0016982974567995583,
"grad_norm": 0.612471342086792,
"learning_rate": 6e-05,
"loss": 3.3496,
"step": 30
},
{
"epoch": 0.002264396609066078,
"grad_norm": 0.9295674562454224,
"learning_rate": 8e-05,
"loss": 2.9204,
"step": 40
},
{
"epoch": 0.0028304957613325974,
"grad_norm": 0.7428744435310364,
"learning_rate": 0.0001,
"loss": 2.7989,
"step": 50
},
{
"epoch": 0.0033965949135991167,
"grad_norm": 39.52121353149414,
"learning_rate": 0.00012,
"loss": 2.3753,
"step": 60
},
{
"epoch": 0.003962694065865636,
"grad_norm": 1.2908339500427246,
"learning_rate": 0.00014,
"loss": 2.3282,
"step": 70
},
{
"epoch": 0.004528793218132156,
"grad_norm": 1.0259243249893188,
"learning_rate": 0.00016,
"loss": 2.0235,
"step": 80
},
{
"epoch": 0.0050948923703986754,
"grad_norm": 5.856877326965332,
"learning_rate": 0.00018,
"loss": 2.3282,
"step": 90
},
{
"epoch": 0.005660991522665195,
"grad_norm": 1.6842005252838135,
"learning_rate": 0.0002,
"loss": 2.1914,
"step": 100
},
{
"epoch": 0.006227090674931714,
"grad_norm": 1.1379739046096802,
"learning_rate": 0.0001999390827019096,
"loss": 2.1828,
"step": 110
},
{
"epoch": 0.006793189827198233,
"grad_norm": 1.5961283445358276,
"learning_rate": 0.00019975640502598244,
"loss": 2.1712,
"step": 120
},
{
"epoch": 0.0073592889794647535,
"grad_norm": 1.2035201787948608,
"learning_rate": 0.00019945218953682734,
"loss": 1.8216,
"step": 130
},
{
"epoch": 0.007925388131731272,
"grad_norm": 3.0688140392303467,
"learning_rate": 0.00019902680687415705,
"loss": 2.0315,
"step": 140
},
{
"epoch": 0.008491487283997793,
"grad_norm": 1.050741195678711,
"learning_rate": 0.00019848077530122083,
"loss": 1.9974,
"step": 150
},
{
"epoch": 0.009057586436264312,
"grad_norm": 1.5697944164276123,
"learning_rate": 0.00019781476007338058,
"loss": 1.8635,
"step": 160
},
{
"epoch": 0.009623685588530832,
"grad_norm": 1.8822702169418335,
"learning_rate": 0.00019702957262759965,
"loss": 1.7645,
"step": 170
},
{
"epoch": 0.010189784740797351,
"grad_norm": 6.6875224113464355,
"learning_rate": 0.0001961261695938319,
"loss": 2.0548,
"step": 180
},
{
"epoch": 0.01075588389306387,
"grad_norm": 1.6249600648880005,
"learning_rate": 0.00019510565162951537,
"loss": 1.9403,
"step": 190
},
{
"epoch": 0.01132198304533039,
"grad_norm": 1.3810372352600098,
"learning_rate": 0.00019396926207859084,
"loss": 1.8465,
"step": 200
},
{
"epoch": 0.011888082197596909,
"grad_norm": 1.6512261629104614,
"learning_rate": 0.00019271838545667876,
"loss": 1.764,
"step": 210
},
{
"epoch": 0.012454181349863428,
"grad_norm": 2.0129904747009277,
"learning_rate": 0.0001913545457642601,
"loss": 1.6833,
"step": 220
},
{
"epoch": 0.013020280502129947,
"grad_norm": 2.3854947090148926,
"learning_rate": 0.0001898794046299167,
"loss": 1.9643,
"step": 230
},
{
"epoch": 0.013586379654396467,
"grad_norm": 11.102593421936035,
"learning_rate": 0.00018829475928589271,
"loss": 1.8319,
"step": 240
},
{
"epoch": 0.014152478806662988,
"grad_norm": 1.0218788385391235,
"learning_rate": 0.00018660254037844388,
"loss": 1.7456,
"step": 250
},
{
"epoch": 0.014718577958929507,
"grad_norm": 2.1926181316375732,
"learning_rate": 0.0001848048096156426,
"loss": 1.7705,
"step": 260
},
{
"epoch": 0.015284677111196026,
"grad_norm": 1.2894445657730103,
"learning_rate": 0.00018290375725550417,
"loss": 1.759,
"step": 270
},
{
"epoch": 0.015850776263462544,
"grad_norm": 1.2821546792984009,
"learning_rate": 0.00018090169943749476,
"loss": 1.7809,
"step": 280
},
{
"epoch": 0.016416875415729067,
"grad_norm": 1.6037951707839966,
"learning_rate": 0.00017880107536067218,
"loss": 1.6338,
"step": 290
},
{
"epoch": 0.016982974567995586,
"grad_norm": 1.6165717840194702,
"learning_rate": 0.0001766044443118978,
"loss": 1.59,
"step": 300
},
{
"epoch": 0.017549073720262105,
"grad_norm": 1.3858145475387573,
"learning_rate": 0.00017431448254773944,
"loss": 1.7459,
"step": 310
},
{
"epoch": 0.018115172872528625,
"grad_norm": 1.5735255479812622,
"learning_rate": 0.0001719339800338651,
"loss": 1.7295,
"step": 320
},
{
"epoch": 0.018681272024795144,
"grad_norm": 1.284432053565979,
"learning_rate": 0.00016946583704589973,
"loss": 1.769,
"step": 330
},
{
"epoch": 0.019247371177061663,
"grad_norm": 0.984366238117218,
"learning_rate": 0.00016691306063588583,
"loss": 1.6516,
"step": 340
},
{
"epoch": 0.019813470329328182,
"grad_norm": 1.6160484552383423,
"learning_rate": 0.00016427876096865394,
"loss": 1.529,
"step": 350
},
{
"epoch": 0.020379569481594702,
"grad_norm": 1.8237900733947754,
"learning_rate": 0.0001615661475325658,
"loss": 1.7505,
"step": 360
},
{
"epoch": 0.02094566863386122,
"grad_norm": 1.297549843788147,
"learning_rate": 0.00015877852522924732,
"loss": 1.7133,
"step": 370
},
{
"epoch": 0.02151176778612774,
"grad_norm": 2.0918915271759033,
"learning_rate": 0.0001559192903470747,
"loss": 1.6225,
"step": 380
},
{
"epoch": 0.02207786693839426,
"grad_norm": 1.0555062294006348,
"learning_rate": 0.0001529919264233205,
"loss": 1.6404,
"step": 390
},
{
"epoch": 0.02264396609066078,
"grad_norm": 1.5048798322677612,
"learning_rate": 0.00015000000000000001,
"loss": 1.6544,
"step": 400
},
{
"epoch": 0.0232100652429273,
"grad_norm": 1.7201550006866455,
"learning_rate": 0.00014694715627858908,
"loss": 1.5341,
"step": 410
},
{
"epoch": 0.023776164395193818,
"grad_norm": 1.2342567443847656,
"learning_rate": 0.00014383711467890774,
"loss": 1.5762,
"step": 420
},
{
"epoch": 0.024342263547460337,
"grad_norm": 0.8844823241233826,
"learning_rate": 0.00014067366430758004,
"loss": 1.4964,
"step": 430
},
{
"epoch": 0.024908362699726856,
"grad_norm": 2.017977714538574,
"learning_rate": 0.00013746065934159123,
"loss": 1.5507,
"step": 440
},
{
"epoch": 0.025474461851993375,
"grad_norm": 1.0709903240203857,
"learning_rate": 0.00013420201433256689,
"loss": 1.51,
"step": 450
},
{
"epoch": 0.026040561004259895,
"grad_norm": 0.863139271736145,
"learning_rate": 0.00013090169943749476,
"loss": 1.5191,
"step": 460
},
{
"epoch": 0.026606660156526414,
"grad_norm": 1.096670389175415,
"learning_rate": 0.0001275637355816999,
"loss": 1.6605,
"step": 470
},
{
"epoch": 0.027172759308792933,
"grad_norm": 0.9680797457695007,
"learning_rate": 0.00012419218955996676,
"loss": 1.6433,
"step": 480
},
{
"epoch": 0.027738858461059456,
"grad_norm": 1.6639995574951172,
"learning_rate": 0.00012079116908177593,
"loss": 1.5499,
"step": 490
},
{
"epoch": 0.028304957613325975,
"grad_norm": 1.3906327486038208,
"learning_rate": 0.00011736481776669306,
"loss": 1.5884,
"step": 500
},
{
"epoch": 0.028871056765592495,
"grad_norm": 1.403045654296875,
"learning_rate": 0.00011391731009600654,
"loss": 1.4895,
"step": 510
},
{
"epoch": 0.029437155917859014,
"grad_norm": 1.4162797927856445,
"learning_rate": 0.00011045284632676536,
"loss": 1.7302,
"step": 520
},
{
"epoch": 0.030003255070125533,
"grad_norm": 1.0728657245635986,
"learning_rate": 0.00010697564737441252,
"loss": 1.6658,
"step": 530
},
{
"epoch": 0.030569354222392053,
"grad_norm": 0.9048101902008057,
"learning_rate": 0.00010348994967025012,
"loss": 1.6423,
"step": 540
},
{
"epoch": 0.031135453374658572,
"grad_norm": 4.7274250984191895,
"learning_rate": 0.0001,
"loss": 1.6433,
"step": 550
},
{
"epoch": 0.03170155252692509,
"grad_norm": 1.6377885341644287,
"learning_rate": 9.651005032974994e-05,
"loss": 1.6475,
"step": 560
},
{
"epoch": 0.03226765167919161,
"grad_norm": 2.1424057483673096,
"learning_rate": 9.302435262558747e-05,
"loss": 1.5888,
"step": 570
},
{
"epoch": 0.03283375083145813,
"grad_norm": 0.9035511612892151,
"learning_rate": 8.954715367323468e-05,
"loss": 1.6005,
"step": 580
},
{
"epoch": 0.03339984998372465,
"grad_norm": 1.209153413772583,
"learning_rate": 8.608268990399349e-05,
"loss": 1.6187,
"step": 590
},
{
"epoch": 0.03396594913599117,
"grad_norm": 1.4936399459838867,
"learning_rate": 8.263518223330697e-05,
"loss": 1.6622,
"step": 600
},
{
"epoch": 0.03453204828825769,
"grad_norm": 0.9744408130645752,
"learning_rate": 7.920883091822408e-05,
"loss": 1.5553,
"step": 610
},
{
"epoch": 0.03509814744052421,
"grad_norm": 1.1214041709899902,
"learning_rate": 7.580781044003324e-05,
"loss": 1.4749,
"step": 620
},
{
"epoch": 0.03566424659279073,
"grad_norm": 1.5141066312789917,
"learning_rate": 7.243626441830009e-05,
"loss": 1.6162,
"step": 630
},
{
"epoch": 0.03623034574505725,
"grad_norm": 1.1192114353179932,
"learning_rate": 6.909830056250527e-05,
"loss": 1.6655,
"step": 640
},
{
"epoch": 0.03679644489732377,
"grad_norm": 0.8808345794677734,
"learning_rate": 6.579798566743314e-05,
"loss": 1.5585,
"step": 650
},
{
"epoch": 0.03736254404959029,
"grad_norm": 1.2207506895065308,
"learning_rate": 6.25393406584088e-05,
"loss": 1.5282,
"step": 660
},
{
"epoch": 0.03792864320185681,
"grad_norm": 0.8557892441749573,
"learning_rate": 5.9326335692419995e-05,
"loss": 1.6304,
"step": 670
},
{
"epoch": 0.038494742354123326,
"grad_norm": 1.4455292224884033,
"learning_rate": 5.616288532109225e-05,
"loss": 1.7623,
"step": 680
},
{
"epoch": 0.039060841506389846,
"grad_norm": 1.7669495344161987,
"learning_rate": 5.305284372141095e-05,
"loss": 1.5934,
"step": 690
},
{
"epoch": 0.039626940658656365,
"grad_norm": 2.2413482666015625,
"learning_rate": 5.000000000000002e-05,
"loss": 1.692,
"step": 700
},
{
"epoch": 0.040193039810922884,
"grad_norm": 0.9742591977119446,
"learning_rate": 4.700807357667952e-05,
"loss": 1.5471,
"step": 710
},
{
"epoch": 0.040759138963189404,
"grad_norm": 1.437410593032837,
"learning_rate": 4.4080709652925336e-05,
"loss": 1.5466,
"step": 720
},
{
"epoch": 0.04132523811545592,
"grad_norm": 1.625700831413269,
"learning_rate": 4.12214747707527e-05,
"loss": 1.5798,
"step": 730
},
{
"epoch": 0.04189133726772244,
"grad_norm": 0.8843604922294617,
"learning_rate": 3.843385246743417e-05,
"loss": 1.5987,
"step": 740
},
{
"epoch": 0.04245743641998896,
"grad_norm": 1.7022398710250854,
"learning_rate": 3.5721239031346066e-05,
"loss": 1.7433,
"step": 750
},
{
"epoch": 0.04302353557225548,
"grad_norm": 0.8799572587013245,
"learning_rate": 3.308693936411421e-05,
"loss": 1.4654,
"step": 760
},
{
"epoch": 0.043589634724522,
"grad_norm": 0.8340188264846802,
"learning_rate": 3.053416295410026e-05,
"loss": 1.5339,
"step": 770
},
{
"epoch": 0.04415573387678852,
"grad_norm": 1.684546947479248,
"learning_rate": 2.8066019966134904e-05,
"loss": 1.5587,
"step": 780
},
{
"epoch": 0.04472183302905504,
"grad_norm": 1.205370306968689,
"learning_rate": 2.5685517452260567e-05,
"loss": 1.3387,
"step": 790
},
{
"epoch": 0.04528793218132156,
"grad_norm": 1.310747504234314,
"learning_rate": 2.339555568810221e-05,
"loss": 1.538,
"step": 800
},
{
"epoch": 0.04585403133358808,
"grad_norm": 2.451975107192993,
"learning_rate": 2.119892463932781e-05,
"loss": 1.6725,
"step": 810
},
{
"epoch": 0.0464201304858546,
"grad_norm": 2.1125898361206055,
"learning_rate": 1.9098300562505266e-05,
"loss": 1.4746,
"step": 820
},
{
"epoch": 0.046986229638121116,
"grad_norm": 0.9616561532020569,
"learning_rate": 1.7096242744495837e-05,
"loss": 1.4724,
"step": 830
},
{
"epoch": 0.047552328790387635,
"grad_norm": 1.1507611274719238,
"learning_rate": 1.5195190384357404e-05,
"loss": 1.4674,
"step": 840
},
{
"epoch": 0.048118427942654154,
"grad_norm": 1.4164016246795654,
"learning_rate": 1.339745962155613e-05,
"loss": 1.5415,
"step": 850
},
{
"epoch": 0.048684527094920674,
"grad_norm": 1.2756904363632202,
"learning_rate": 1.1705240714107302e-05,
"loss": 1.4425,
"step": 860
},
{
"epoch": 0.04925062624718719,
"grad_norm": 1.3417842388153076,
"learning_rate": 1.0120595370083318e-05,
"loss": 1.4356,
"step": 870
},
{
"epoch": 0.04981672539945371,
"grad_norm": 2.374289035797119,
"learning_rate": 8.645454235739903e-06,
"loss": 1.4808,
"step": 880
},
{
"epoch": 0.05038282455172023,
"grad_norm": 3.114461660385132,
"learning_rate": 7.281614543321269e-06,
"loss": 1.6683,
"step": 890
},
{
"epoch": 0.05094892370398675,
"grad_norm": 1.7116568088531494,
"learning_rate": 6.030737921409169e-06,
"loss": 1.6627,
"step": 900
},
{
"epoch": 0.05151502285625327,
"grad_norm": 1.497970461845398,
"learning_rate": 4.8943483704846475e-06,
"loss": 1.4333,
"step": 910
},
{
"epoch": 0.05208112200851979,
"grad_norm": 1.462307333946228,
"learning_rate": 3.873830406168111e-06,
"loss": 1.3954,
"step": 920
},
{
"epoch": 0.05264722116078631,
"grad_norm": 0.9947201609611511,
"learning_rate": 2.970427372400353e-06,
"loss": 1.5113,
"step": 930
},
{
"epoch": 0.05321332031305283,
"grad_norm": 1.0234606266021729,
"learning_rate": 2.1852399266194314e-06,
"loss": 1.5614,
"step": 940
},
{
"epoch": 0.05377941946531935,
"grad_norm": 1.0096086263656616,
"learning_rate": 1.5192246987791981e-06,
"loss": 1.4893,
"step": 950
},
{
"epoch": 0.05434551861758587,
"grad_norm": 1.2131421566009521,
"learning_rate": 9.731931258429638e-07,
"loss": 1.5647,
"step": 960
},
{
"epoch": 0.05491161776985239,
"grad_norm": 1.0574455261230469,
"learning_rate": 5.478104631726711e-07,
"loss": 1.3718,
"step": 970
},
{
"epoch": 0.05547771692211891,
"grad_norm": 1.1654020547866821,
"learning_rate": 2.4359497401758024e-07,
"loss": 1.6251,
"step": 980
},
{
"epoch": 0.05604381607438543,
"grad_norm": 1.3310041427612305,
"learning_rate": 6.09172980904238e-08,
"loss": 1.6333,
"step": 990
},
{
"epoch": 0.05660991522665195,
"grad_norm": 1.0006204843521118,
"learning_rate": 0.0,
"loss": 1.534,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 1000,
"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": 2.297589686332416e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}