rv2-gemma12b-v4-v4_code_review / 400M /trainer_state.json
rqadri's picture
Upload folder using huggingface_hub
8700952 verified
Raw History Blame Contribute Delete
70.3 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2195727233491584,
"eval_steps": 500,
"global_step": 4070,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005394907207596029,
"grad_norm": 369.69301600900053,
"learning_rate": 2.910112359550562e-06,
"loss": 1.8730627059936524,
"step": 10
},
{
"epoch": 0.0010789814415192059,
"grad_norm": 31.93478853689241,
"learning_rate": 3.921348314606742e-06,
"loss": 1.262525463104248,
"step": 20
},
{
"epoch": 0.0016184721622788088,
"grad_norm": 141.7556466471986,
"learning_rate": 4.932584269662922e-06,
"loss": 1.0669395446777343,
"step": 30
},
{
"epoch": 0.0021579628830384117,
"grad_norm": 127.98270782023548,
"learning_rate": 5.943820224719102e-06,
"loss": 1.1076365470886231,
"step": 40
},
{
"epoch": 0.002697453603798015,
"grad_norm": 101.43748401214339,
"learning_rate": 6.955056179775282e-06,
"loss": 1.0109930038452148,
"step": 50
},
{
"epoch": 0.0032369443245576176,
"grad_norm": 899.0086783565027,
"learning_rate": 7.966292134831462e-06,
"loss": 0.9515115737915039,
"step": 60
},
{
"epoch": 0.0037764350453172208,
"grad_norm": 15.557933246692217,
"learning_rate": 8.977528089887641e-06,
"loss": 0.9290966987609863,
"step": 70
},
{
"epoch": 0.0043159257660768235,
"grad_norm": 256.064896120912,
"learning_rate": 9.988764044943822e-06,
"loss": 1.1323322296142577,
"step": 80
},
{
"epoch": 0.004855416486836427,
"grad_norm": 20.848525026966247,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.088106918334961,
"step": 90
},
{
"epoch": 0.00539490720759603,
"grad_norm": 25.60593783327153,
"learning_rate": 1.2011235955056182e-05,
"loss": 0.9955007553100585,
"step": 100
},
{
"epoch": 0.005934397928355632,
"grad_norm": 11.664176937579581,
"learning_rate": 1.3022471910112362e-05,
"loss": 0.942236328125,
"step": 110
},
{
"epoch": 0.006473888649115235,
"grad_norm": 7.9248397322900646,
"learning_rate": 1.403370786516854e-05,
"loss": 0.9238415718078613,
"step": 120
},
{
"epoch": 0.007013379369874838,
"grad_norm": 26.682291952362966,
"learning_rate": 1.504494382022472e-05,
"loss": 0.9361964225769043,
"step": 130
},
{
"epoch": 0.0075528700906344415,
"grad_norm": 3.6691592434398466,
"learning_rate": 1.60561797752809e-05,
"loss": 0.927226448059082,
"step": 140
},
{
"epoch": 0.008092360811394044,
"grad_norm": 15.191132047351614,
"learning_rate": 1.706741573033708e-05,
"loss": 0.9375665664672852,
"step": 150
},
{
"epoch": 0.008631851532153647,
"grad_norm": 7.4209329049996455,
"learning_rate": 1.8078651685393256e-05,
"loss": 0.9221304893493653,
"step": 160
},
{
"epoch": 0.00917134225291325,
"grad_norm": 5.050234356436225,
"learning_rate": 1.908988764044944e-05,
"loss": 0.9327095031738282,
"step": 170
},
{
"epoch": 0.009710832973672853,
"grad_norm": 2.532425838265676,
"learning_rate": 2e-05,
"loss": 0.90814208984375,
"step": 180
},
{
"epoch": 0.010250323694432456,
"grad_norm": 2.8569985447993664,
"learning_rate": 2e-05,
"loss": 0.930181884765625,
"step": 190
},
{
"epoch": 0.01078981441519206,
"grad_norm": 3.7217733328209746,
"learning_rate": 2e-05,
"loss": 0.9137080192565918,
"step": 200
},
{
"epoch": 0.011329305135951661,
"grad_norm": 1.6856605125936686,
"learning_rate": 2e-05,
"loss": 0.9173044204711914,
"step": 210
},
{
"epoch": 0.011868795856711264,
"grad_norm": 4.042279257566151,
"learning_rate": 2e-05,
"loss": 0.9044102668762207,
"step": 220
},
{
"epoch": 0.012408286577470867,
"grad_norm": 7.693180928481417,
"learning_rate": 2e-05,
"loss": 0.9013534545898437,
"step": 230
},
{
"epoch": 0.01294777729823047,
"grad_norm": 3.5295771823615647,
"learning_rate": 2e-05,
"loss": 0.9148492813110352,
"step": 240
},
{
"epoch": 0.013487268018990074,
"grad_norm": 7.839029508109661,
"learning_rate": 2e-05,
"loss": 0.9837350845336914,
"step": 250
},
{
"epoch": 0.014026758739749677,
"grad_norm": 3.670914514568096,
"learning_rate": 2e-05,
"loss": 0.9146605491638183,
"step": 260
},
{
"epoch": 0.01456624946050928,
"grad_norm": 3.5577694379027,
"learning_rate": 2e-05,
"loss": 0.9401106834411621,
"step": 270
},
{
"epoch": 0.015105740181268883,
"grad_norm": 2.453202809896575,
"learning_rate": 2e-05,
"loss": 0.9477849960327148,
"step": 280
},
{
"epoch": 0.015645230902028486,
"grad_norm": 1.9729075743285769,
"learning_rate": 2e-05,
"loss": 0.9066492080688476,
"step": 290
},
{
"epoch": 0.016184721622788088,
"grad_norm": 2.8099192390223795,
"learning_rate": 2e-05,
"loss": 0.9063838958740235,
"step": 300
},
{
"epoch": 0.016724212343547692,
"grad_norm": 4.236623113420927,
"learning_rate": 2e-05,
"loss": 0.8637477874755859,
"step": 310
},
{
"epoch": 0.017263703064307294,
"grad_norm": 4.167628129961564,
"learning_rate": 2e-05,
"loss": 0.9061297416687012,
"step": 320
},
{
"epoch": 0.017803193785066895,
"grad_norm": 6.935834245033307,
"learning_rate": 2e-05,
"loss": 0.8871530532836914,
"step": 330
},
{
"epoch": 0.0183426845058265,
"grad_norm": 3.2423751981314384,
"learning_rate": 2e-05,
"loss": 0.9223550796508789,
"step": 340
},
{
"epoch": 0.0188821752265861,
"grad_norm": 30.606793216440163,
"learning_rate": 2e-05,
"loss": 3.54920654296875,
"step": 350
},
{
"epoch": 0.019421665947345707,
"grad_norm": 4.550939608135107,
"learning_rate": 2e-05,
"loss": 0.9992364883422852,
"step": 360
},
{
"epoch": 0.019961156668105308,
"grad_norm": 10.355788989674835,
"learning_rate": 2e-05,
"loss": 0.9463441848754883,
"step": 370
},
{
"epoch": 0.020500647388864913,
"grad_norm": 9.470092673566741,
"learning_rate": 2e-05,
"loss": 0.9165935516357422,
"step": 380
},
{
"epoch": 0.021040138109624514,
"grad_norm": 16.04366173130251,
"learning_rate": 2e-05,
"loss": 0.9199161529541016,
"step": 390
},
{
"epoch": 0.02157962883038412,
"grad_norm": 16.276111063417574,
"learning_rate": 2e-05,
"loss": 0.8900386810302734,
"step": 400
},
{
"epoch": 0.02211911955114372,
"grad_norm": 14.653812444903842,
"learning_rate": 2e-05,
"loss": 0.8979652404785157,
"step": 410
},
{
"epoch": 0.022658610271903322,
"grad_norm": 2.6977548589169094,
"learning_rate": 2e-05,
"loss": 0.9128728866577148,
"step": 420
},
{
"epoch": 0.023198100992662927,
"grad_norm": 23.582887550971233,
"learning_rate": 2e-05,
"loss": 0.8891826629638672,
"step": 430
},
{
"epoch": 0.023737591713422528,
"grad_norm": 2.9436146384915443,
"learning_rate": 2e-05,
"loss": 0.9091741561889648,
"step": 440
},
{
"epoch": 0.024277082434182133,
"grad_norm": 3.8178614247451996,
"learning_rate": 2e-05,
"loss": 0.9071731567382812,
"step": 450
},
{
"epoch": 0.024816573154941735,
"grad_norm": 9.900017833351434,
"learning_rate": 2e-05,
"loss": 0.8803417205810546,
"step": 460
},
{
"epoch": 0.02535606387570134,
"grad_norm": 11.377800042408293,
"learning_rate": 2e-05,
"loss": 0.9077526092529297,
"step": 470
},
{
"epoch": 0.02589555459646094,
"grad_norm": 4.425640907224202,
"learning_rate": 2e-05,
"loss": 0.8951313018798828,
"step": 480
},
{
"epoch": 0.026435045317220542,
"grad_norm": 5.543696039922662,
"learning_rate": 2e-05,
"loss": 0.9170653343200683,
"step": 490
},
{
"epoch": 0.026974536037980147,
"grad_norm": 6.637675684831988,
"learning_rate": 2e-05,
"loss": 0.9328924179077148,
"step": 500
},
{
"epoch": 0.02751402675873975,
"grad_norm": 4.541587002846055,
"learning_rate": 2e-05,
"loss": 0.9184404373168945,
"step": 510
},
{
"epoch": 0.028053517479499353,
"grad_norm": 4.834955555833834,
"learning_rate": 2e-05,
"loss": 0.94840087890625,
"step": 520
},
{
"epoch": 0.028593008200258955,
"grad_norm": 2.7476196554801118,
"learning_rate": 2e-05,
"loss": 0.9112020492553711,
"step": 530
},
{
"epoch": 0.02913249892101856,
"grad_norm": 3.729222437612153,
"learning_rate": 2e-05,
"loss": 0.8715265274047852,
"step": 540
},
{
"epoch": 0.02967198964177816,
"grad_norm": 1.8986444153489899,
"learning_rate": 2e-05,
"loss": 0.8817804336547852,
"step": 550
},
{
"epoch": 0.030211480362537766,
"grad_norm": 19.652863197507482,
"learning_rate": 2e-05,
"loss": 0.9034578323364257,
"step": 560
},
{
"epoch": 0.030750971083297367,
"grad_norm": 4.893935787998432,
"learning_rate": 2e-05,
"loss": 0.9201476097106933,
"step": 570
},
{
"epoch": 0.03129046180405697,
"grad_norm": 2.121315677688142,
"learning_rate": 2e-05,
"loss": 0.9087504386901856,
"step": 580
},
{
"epoch": 0.031829952524816574,
"grad_norm": 1.6805303205822455,
"learning_rate": 2e-05,
"loss": 0.8938014030456543,
"step": 590
},
{
"epoch": 0.032369443245576175,
"grad_norm": 2.091016561123043,
"learning_rate": 2e-05,
"loss": 0.8701451301574707,
"step": 600
},
{
"epoch": 0.03290893396633578,
"grad_norm": 4.4795444497420345,
"learning_rate": 2e-05,
"loss": 0.8988707542419434,
"step": 610
},
{
"epoch": 0.033448424687095385,
"grad_norm": 1.40755956780777,
"learning_rate": 2e-05,
"loss": 0.8736795425415039,
"step": 620
},
{
"epoch": 0.033987915407854986,
"grad_norm": 1.9677540233275401,
"learning_rate": 2e-05,
"loss": 0.8994430541992188,
"step": 630
},
{
"epoch": 0.03452740612861459,
"grad_norm": 2.8537882081306605,
"learning_rate": 2e-05,
"loss": 0.8869138717651367,
"step": 640
},
{
"epoch": 0.03506689684937419,
"grad_norm": 2.3406412447640133,
"learning_rate": 2e-05,
"loss": 0.8736772537231445,
"step": 650
},
{
"epoch": 0.03560638757013379,
"grad_norm": 2.7002297840083647,
"learning_rate": 2e-05,
"loss": 0.8878070831298828,
"step": 660
},
{
"epoch": 0.0361458782908934,
"grad_norm": 5.478051955992026,
"learning_rate": 2e-05,
"loss": 0.9007582664489746,
"step": 670
},
{
"epoch": 0.036685369011653,
"grad_norm": 5.987775578117277,
"learning_rate": 2e-05,
"loss": 0.877619457244873,
"step": 680
},
{
"epoch": 0.0372248597324126,
"grad_norm": 4.062183705280081,
"learning_rate": 2e-05,
"loss": 0.9615988731384277,
"step": 690
},
{
"epoch": 0.0377643504531722,
"grad_norm": 1.7304116921547956,
"learning_rate": 2e-05,
"loss": 0.8999065399169922,
"step": 700
},
{
"epoch": 0.03830384117393181,
"grad_norm": 10.224091687714415,
"learning_rate": 2e-05,
"loss": 0.8775262832641602,
"step": 710
},
{
"epoch": 0.03884333189469141,
"grad_norm": 2.6973024084894885,
"learning_rate": 2e-05,
"loss": 0.88863525390625,
"step": 720
},
{
"epoch": 0.039382822615451014,
"grad_norm": 3.0097373941657186,
"learning_rate": 2e-05,
"loss": 0.8921207427978516,
"step": 730
},
{
"epoch": 0.039922313336210616,
"grad_norm": 2.4929780841655207,
"learning_rate": 2e-05,
"loss": 0.8870817184448242,
"step": 740
},
{
"epoch": 0.04046180405697022,
"grad_norm": 2.680211035148592,
"learning_rate": 2e-05,
"loss": 0.8718931198120117,
"step": 750
},
{
"epoch": 0.041001294777729826,
"grad_norm": 3.314725765838302,
"learning_rate": 2e-05,
"loss": 0.8696352005004883,
"step": 760
},
{
"epoch": 0.04154078549848943,
"grad_norm": 2.8067410842808824,
"learning_rate": 2e-05,
"loss": 0.8808348655700684,
"step": 770
},
{
"epoch": 0.04208027621924903,
"grad_norm": 4.568417784852867,
"learning_rate": 2e-05,
"loss": 0.8762812614440918,
"step": 780
},
{
"epoch": 0.04261976694000863,
"grad_norm": 1.591466243191371,
"learning_rate": 2e-05,
"loss": 0.8897010803222656,
"step": 790
},
{
"epoch": 0.04315925766076824,
"grad_norm": 1.7378624546635357,
"learning_rate": 2e-05,
"loss": 0.8871335983276367,
"step": 800
},
{
"epoch": 0.04369874838152784,
"grad_norm": 5.282884941300159,
"learning_rate": 2e-05,
"loss": 0.8862749099731445,
"step": 810
},
{
"epoch": 0.04423823910228744,
"grad_norm": 1.4282666163813993,
"learning_rate": 2e-05,
"loss": 0.9045479774475098,
"step": 820
},
{
"epoch": 0.04477772982304704,
"grad_norm": 1.804678546954577,
"learning_rate": 2e-05,
"loss": 0.8669574737548829,
"step": 830
},
{
"epoch": 0.045317220543806644,
"grad_norm": 2.7003745816690836,
"learning_rate": 2e-05,
"loss": 0.8664716720581055,
"step": 840
},
{
"epoch": 0.04585671126456625,
"grad_norm": 2.8347718319860626,
"learning_rate": 2e-05,
"loss": 0.8740848541259766,
"step": 850
},
{
"epoch": 0.046396201985325854,
"grad_norm": 2.3599301199842655,
"learning_rate": 2e-05,
"loss": 0.8661260604858398,
"step": 860
},
{
"epoch": 0.046935692706085455,
"grad_norm": 2.675130769028597,
"learning_rate": 2e-05,
"loss": 0.8940586090087891,
"step": 870
},
{
"epoch": 0.047475183426845056,
"grad_norm": 2.13219637159858,
"learning_rate": 2e-05,
"loss": 0.8656101226806641,
"step": 880
},
{
"epoch": 0.04801467414760466,
"grad_norm": 5.746935578097955,
"learning_rate": 2e-05,
"loss": 0.9049406051635742,
"step": 890
},
{
"epoch": 0.048554164868364266,
"grad_norm": 3.040442087390683,
"learning_rate": 2e-05,
"loss": 0.8673805236816406,
"step": 900
},
{
"epoch": 0.04909365558912387,
"grad_norm": 1.8033864790060448,
"learning_rate": 2e-05,
"loss": 0.9076686859130859,
"step": 910
},
{
"epoch": 0.04963314630988347,
"grad_norm": 3.7270371618478446,
"learning_rate": 2e-05,
"loss": 0.8856944084167481,
"step": 920
},
{
"epoch": 0.05017263703064307,
"grad_norm": 18.34533608060895,
"learning_rate": 2e-05,
"loss": 0.8803435325622558,
"step": 930
},
{
"epoch": 0.05071212775140268,
"grad_norm": 7.031326732375769,
"learning_rate": 2e-05,
"loss": 0.8922122955322266,
"step": 940
},
{
"epoch": 0.05125161847216228,
"grad_norm": 1.271585738790212,
"learning_rate": 2e-05,
"loss": 0.8702299118041992,
"step": 950
},
{
"epoch": 0.05179110919292188,
"grad_norm": 3.1087560610639984,
"learning_rate": 2e-05,
"loss": 0.869837474822998,
"step": 960
},
{
"epoch": 0.05233059991368148,
"grad_norm": 1.336885754811761,
"learning_rate": 2e-05,
"loss": 0.8768095016479492,
"step": 970
},
{
"epoch": 0.052870090634441085,
"grad_norm": 1.2937187665672654,
"learning_rate": 2e-05,
"loss": 0.8737648010253907,
"step": 980
},
{
"epoch": 0.05340958135520069,
"grad_norm": 6.496337599049736,
"learning_rate": 2e-05,
"loss": 0.8852460861206055,
"step": 990
},
{
"epoch": 0.053949072075960294,
"grad_norm": 2.314909026977299,
"learning_rate": 2e-05,
"loss": 0.9168342590332031,
"step": 1000
},
{
"epoch": 0.054488562796719896,
"grad_norm": 1.3797589526126182,
"learning_rate": 2e-05,
"loss": 0.9012920379638671,
"step": 1010
},
{
"epoch": 0.0550280535174795,
"grad_norm": 1.7456393044082175,
"learning_rate": 2e-05,
"loss": 0.8839190483093262,
"step": 1020
},
{
"epoch": 0.055567544238239105,
"grad_norm": 2.2368924316262913,
"learning_rate": 2e-05,
"loss": 0.8841041564941406,
"step": 1030
},
{
"epoch": 0.05610703495899871,
"grad_norm": 2.3060976347623408,
"learning_rate": 2e-05,
"loss": 0.9180487632751465,
"step": 1040
},
{
"epoch": 0.05664652567975831,
"grad_norm": 2.2473033744197655,
"learning_rate": 2e-05,
"loss": 0.8983830451965332,
"step": 1050
},
{
"epoch": 0.05718601640051791,
"grad_norm": 3.33794913543599,
"learning_rate": 2e-05,
"loss": 0.9058303833007812,
"step": 1060
},
{
"epoch": 0.05772550712127751,
"grad_norm": 2.1863704996804874,
"learning_rate": 2e-05,
"loss": 0.8500079154968262,
"step": 1070
},
{
"epoch": 0.05826499784203712,
"grad_norm": 5.464104262184261,
"learning_rate": 2e-05,
"loss": 0.86676025390625,
"step": 1080
},
{
"epoch": 0.05880448856279672,
"grad_norm": 1.2580865472126652,
"learning_rate": 2e-05,
"loss": 0.8795917510986329,
"step": 1090
},
{
"epoch": 0.05934397928355632,
"grad_norm": 1.5392878698728925,
"learning_rate": 2e-05,
"loss": 0.855427360534668,
"step": 1100
},
{
"epoch": 0.059883470004315924,
"grad_norm": 1.6600456111757242,
"learning_rate": 2e-05,
"loss": 0.8580084800720215,
"step": 1110
},
{
"epoch": 0.06042296072507553,
"grad_norm": 1.9728666357091431,
"learning_rate": 2e-05,
"loss": 0.8592136383056641,
"step": 1120
},
{
"epoch": 0.060962451445835134,
"grad_norm": 2.622532245761096,
"learning_rate": 2e-05,
"loss": 0.8778785705566406,
"step": 1130
},
{
"epoch": 0.061501942166594735,
"grad_norm": 2.436300801764917,
"learning_rate": 2e-05,
"loss": 0.8558690071105957,
"step": 1140
},
{
"epoch": 0.062041432887354336,
"grad_norm": 2.072486307736441,
"learning_rate": 2e-05,
"loss": 0.8554096221923828,
"step": 1150
},
{
"epoch": 0.06258092360811394,
"grad_norm": 2.9578754600495105,
"learning_rate": 2e-05,
"loss": 0.8688982963562012,
"step": 1160
},
{
"epoch": 0.06312041432887354,
"grad_norm": 2.2185001887709106,
"learning_rate": 2e-05,
"loss": 0.8960395812988281,
"step": 1170
},
{
"epoch": 0.06365990504963315,
"grad_norm": 2.39317741084652,
"learning_rate": 2e-05,
"loss": 0.8809322357177735,
"step": 1180
},
{
"epoch": 0.06419939577039276,
"grad_norm": 7.053593954669792,
"learning_rate": 2e-05,
"loss": 0.8588828086853028,
"step": 1190
},
{
"epoch": 0.06473888649115235,
"grad_norm": 2.8316276030407392,
"learning_rate": 2e-05,
"loss": 0.863832664489746,
"step": 1200
},
{
"epoch": 0.06527837721191196,
"grad_norm": 55.263846840104094,
"learning_rate": 2e-05,
"loss": 0.8467828750610351,
"step": 1210
},
{
"epoch": 0.06581786793267155,
"grad_norm": 1.891195934618861,
"learning_rate": 2e-05,
"loss": 0.8810437202453614,
"step": 1220
},
{
"epoch": 0.06635735865343116,
"grad_norm": 4.262649131447584,
"learning_rate": 2e-05,
"loss": 0.8573444366455079,
"step": 1230
},
{
"epoch": 0.06689684937419077,
"grad_norm": 5.280398859967369,
"learning_rate": 2e-05,
"loss": 0.8775759696960449,
"step": 1240
},
{
"epoch": 0.06743634009495036,
"grad_norm": 13.161950494331434,
"learning_rate": 2e-05,
"loss": 0.8802067756652832,
"step": 1250
},
{
"epoch": 0.06797583081570997,
"grad_norm": 2.3840227633253708,
"learning_rate": 2e-05,
"loss": 0.8745565414428711,
"step": 1260
},
{
"epoch": 0.06851532153646957,
"grad_norm": 2.578881266139901,
"learning_rate": 2e-05,
"loss": 0.8929662704467773,
"step": 1270
},
{
"epoch": 0.06905481225722918,
"grad_norm": 1.3551093714665399,
"learning_rate": 2e-05,
"loss": 0.8856276512145996,
"step": 1280
},
{
"epoch": 0.06959430297798878,
"grad_norm": 1.421718866393892,
"learning_rate": 2e-05,
"loss": 0.8779384613037109,
"step": 1290
},
{
"epoch": 0.07013379369874838,
"grad_norm": 1.3412253586411367,
"learning_rate": 2e-05,
"loss": 0.8418590545654296,
"step": 1300
},
{
"epoch": 0.07067328441950799,
"grad_norm": 1.3164576570437523,
"learning_rate": 2e-05,
"loss": 0.8589597702026367,
"step": 1310
},
{
"epoch": 0.07121277514026758,
"grad_norm": 5.63391297375713,
"learning_rate": 2e-05,
"loss": 0.8794595718383789,
"step": 1320
},
{
"epoch": 0.07175226586102719,
"grad_norm": 1.3610004564150833,
"learning_rate": 2e-05,
"loss": 0.8666675567626954,
"step": 1330
},
{
"epoch": 0.0722917565817868,
"grad_norm": 1.7200672230946694,
"learning_rate": 2e-05,
"loss": 0.8707124710083007,
"step": 1340
},
{
"epoch": 0.07283124730254639,
"grad_norm": 1.3160601308789588,
"learning_rate": 2e-05,
"loss": 0.8457590103149414,
"step": 1350
},
{
"epoch": 0.073370738023306,
"grad_norm": 1.7778775450463142,
"learning_rate": 2e-05,
"loss": 0.8669673919677734,
"step": 1360
},
{
"epoch": 0.0739102287440656,
"grad_norm": 2.2742353103065485,
"learning_rate": 2e-05,
"loss": 0.920014762878418,
"step": 1370
},
{
"epoch": 0.0744497194648252,
"grad_norm": 4.185305052537614,
"learning_rate": 2e-05,
"loss": 0.9066905021667481,
"step": 1380
},
{
"epoch": 0.07498921018558481,
"grad_norm": 7.045183411349042,
"learning_rate": 2e-05,
"loss": 0.8720160484313965,
"step": 1390
},
{
"epoch": 0.0755287009063444,
"grad_norm": 2.377204425821727,
"learning_rate": 2e-05,
"loss": 0.9035792350769043,
"step": 1400
},
{
"epoch": 0.07606819162710401,
"grad_norm": 1.5514726466038995,
"learning_rate": 2e-05,
"loss": 0.8550067901611328,
"step": 1410
},
{
"epoch": 0.07660768234786362,
"grad_norm": 3.2194246326766627,
"learning_rate": 2e-05,
"loss": 0.8613847732543946,
"step": 1420
},
{
"epoch": 0.07714717306862322,
"grad_norm": 2.191413489389274,
"learning_rate": 2e-05,
"loss": 0.8483789443969727,
"step": 1430
},
{
"epoch": 0.07768666378938283,
"grad_norm": 2.561083258333701,
"learning_rate": 2e-05,
"loss": 0.8561199188232422,
"step": 1440
},
{
"epoch": 0.07822615451014242,
"grad_norm": 2.799486266864444,
"learning_rate": 2e-05,
"loss": 0.8749614715576172,
"step": 1450
},
{
"epoch": 0.07876564523090203,
"grad_norm": 1.6625068228812598,
"learning_rate": 2e-05,
"loss": 0.8524051666259765,
"step": 1460
},
{
"epoch": 0.07930513595166164,
"grad_norm": 1.5627273498445615,
"learning_rate": 2e-05,
"loss": 0.8613437652587891,
"step": 1470
},
{
"epoch": 0.07984462667242123,
"grad_norm": 3.1187718040693815,
"learning_rate": 2e-05,
"loss": 0.8489472389221191,
"step": 1480
},
{
"epoch": 0.08038411739318084,
"grad_norm": 1.999242227430214,
"learning_rate": 2e-05,
"loss": 0.8557394027709961,
"step": 1490
},
{
"epoch": 0.08092360811394043,
"grad_norm": 2.1662789248263086,
"learning_rate": 2e-05,
"loss": 0.8410913467407226,
"step": 1500
},
{
"epoch": 0.08146309883470004,
"grad_norm": 1.117593071600269,
"learning_rate": 2e-05,
"loss": 0.8719884872436523,
"step": 1510
},
{
"epoch": 0.08200258955545965,
"grad_norm": 1.7282463420500256,
"learning_rate": 2e-05,
"loss": 0.8429347991943359,
"step": 1520
},
{
"epoch": 0.08254208027621925,
"grad_norm": 1.10160222981424,
"learning_rate": 2e-05,
"loss": 0.8589319229125977,
"step": 1530
},
{
"epoch": 0.08308157099697885,
"grad_norm": 1.657648568922712,
"learning_rate": 2e-05,
"loss": 0.8519350051879883,
"step": 1540
},
{
"epoch": 0.08362106171773845,
"grad_norm": 1.2061011251185034,
"learning_rate": 2e-05,
"loss": 0.8548383712768555,
"step": 1550
},
{
"epoch": 0.08416055243849806,
"grad_norm": 1.6503845091419074,
"learning_rate": 2e-05,
"loss": 0.8504886627197266,
"step": 1560
},
{
"epoch": 0.08470004315925767,
"grad_norm": 1.650450748636652,
"learning_rate": 2e-05,
"loss": 0.8272921562194824,
"step": 1570
},
{
"epoch": 0.08523953388001726,
"grad_norm": 1.2153538779996496,
"learning_rate": 2e-05,
"loss": 0.8586090087890625,
"step": 1580
},
{
"epoch": 0.08577902460077687,
"grad_norm": 1.4119654167230689,
"learning_rate": 2e-05,
"loss": 0.8150126457214355,
"step": 1590
},
{
"epoch": 0.08631851532153648,
"grad_norm": 2.0481812733972435,
"learning_rate": 2e-05,
"loss": 0.8605268478393555,
"step": 1600
},
{
"epoch": 0.08685800604229607,
"grad_norm": 1.3493621359452488,
"learning_rate": 2e-05,
"loss": 0.8761652946472168,
"step": 1610
},
{
"epoch": 0.08739749676305568,
"grad_norm": 1.937128776151837,
"learning_rate": 2e-05,
"loss": 0.8717695236206054,
"step": 1620
},
{
"epoch": 0.08793698748381527,
"grad_norm": 1.2331164884742856,
"learning_rate": 2e-05,
"loss": 0.8695238113403321,
"step": 1630
},
{
"epoch": 0.08847647820457488,
"grad_norm": 1.0766868462241113,
"learning_rate": 2e-05,
"loss": 0.8439886093139648,
"step": 1640
},
{
"epoch": 0.08901596892533449,
"grad_norm": 4.825188821823706,
"learning_rate": 2e-05,
"loss": 0.8383602142333985,
"step": 1650
},
{
"epoch": 0.08955545964609408,
"grad_norm": 1.0473009888263762,
"learning_rate": 2e-05,
"loss": 0.8446158409118653,
"step": 1660
},
{
"epoch": 0.0900949503668537,
"grad_norm": 2.1550692634060407,
"learning_rate": 2e-05,
"loss": 0.8526595115661622,
"step": 1670
},
{
"epoch": 0.09063444108761329,
"grad_norm": 1.1805712525240586,
"learning_rate": 2e-05,
"loss": 0.8445590019226075,
"step": 1680
},
{
"epoch": 0.0911739318083729,
"grad_norm": 1.3154682778410502,
"learning_rate": 2e-05,
"loss": 0.8289753913879394,
"step": 1690
},
{
"epoch": 0.0917134225291325,
"grad_norm": 1.7425671016352309,
"learning_rate": 2e-05,
"loss": 0.8550616264343261,
"step": 1700
},
{
"epoch": 0.0922529132498921,
"grad_norm": 1.809326593705475,
"learning_rate": 2e-05,
"loss": 0.8592042922973633,
"step": 1710
},
{
"epoch": 0.09279240397065171,
"grad_norm": 2.294726987915818,
"learning_rate": 2e-05,
"loss": 0.8464397430419922,
"step": 1720
},
{
"epoch": 0.0933318946914113,
"grad_norm": 1.3341335707857838,
"learning_rate": 2e-05,
"loss": 0.8401545524597168,
"step": 1730
},
{
"epoch": 0.09387138541217091,
"grad_norm": 1.7059856939535623,
"learning_rate": 2e-05,
"loss": 0.850313663482666,
"step": 1740
},
{
"epoch": 0.09441087613293052,
"grad_norm": 1.1913305227905306,
"learning_rate": 2e-05,
"loss": 0.8246526718139648,
"step": 1750
},
{
"epoch": 0.09495036685369011,
"grad_norm": 2.4712263811656063,
"learning_rate": 2e-05,
"loss": 0.8324945449829102,
"step": 1760
},
{
"epoch": 0.09548985757444972,
"grad_norm": 1.2460535060628168,
"learning_rate": 2e-05,
"loss": 0.83499755859375,
"step": 1770
},
{
"epoch": 0.09602934829520932,
"grad_norm": 0.9541283688175325,
"learning_rate": 2e-05,
"loss": 0.8438259124755859,
"step": 1780
},
{
"epoch": 0.09656883901596892,
"grad_norm": 4.15270429876545,
"learning_rate": 2e-05,
"loss": 0.8374526977539063,
"step": 1790
},
{
"epoch": 0.09710832973672853,
"grad_norm": 1.2843301784727401,
"learning_rate": 2e-05,
"loss": 0.855588722229004,
"step": 1800
},
{
"epoch": 0.09764782045748813,
"grad_norm": 1.2852787584009888,
"learning_rate": 2e-05,
"loss": 0.8446294784545898,
"step": 1810
},
{
"epoch": 0.09818731117824774,
"grad_norm": 1.1732513743084148,
"learning_rate": 2e-05,
"loss": 0.8550775527954102,
"step": 1820
},
{
"epoch": 0.09872680189900734,
"grad_norm": 1.0484004988454474,
"learning_rate": 2e-05,
"loss": 0.8461496353149414,
"step": 1830
},
{
"epoch": 0.09926629261976694,
"grad_norm": 1.1796374157652922,
"learning_rate": 2e-05,
"loss": 0.8495699882507324,
"step": 1840
},
{
"epoch": 0.09980578334052655,
"grad_norm": 1.530009834654909,
"learning_rate": 2e-05,
"loss": 0.8529845237731933,
"step": 1850
},
{
"epoch": 0.10034527406128614,
"grad_norm": 1.3821515513567662,
"learning_rate": 2e-05,
"loss": 0.8383827209472656,
"step": 1860
},
{
"epoch": 0.10088476478204575,
"grad_norm": 1.433339075396923,
"learning_rate": 2e-05,
"loss": 0.8441427230834961,
"step": 1870
},
{
"epoch": 0.10142425550280536,
"grad_norm": 1.4202627926244262,
"learning_rate": 2e-05,
"loss": 0.8355476379394531,
"step": 1880
},
{
"epoch": 0.10196374622356495,
"grad_norm": 1.275529436709381,
"learning_rate": 2e-05,
"loss": 0.8475621223449707,
"step": 1890
},
{
"epoch": 0.10250323694432456,
"grad_norm": 4.886608266675648,
"learning_rate": 2e-05,
"loss": 0.8222907066345215,
"step": 1900
},
{
"epoch": 0.10304272766508416,
"grad_norm": 1.1032859405565207,
"learning_rate": 2e-05,
"loss": 0.8717263221740723,
"step": 1910
},
{
"epoch": 0.10358221838584376,
"grad_norm": 1.4792708796316567,
"learning_rate": 2e-05,
"loss": 0.8422025680541992,
"step": 1920
},
{
"epoch": 0.10412170910660337,
"grad_norm": 1.052829235330944,
"learning_rate": 2e-05,
"loss": 0.8275224685668945,
"step": 1930
},
{
"epoch": 0.10466119982736297,
"grad_norm": 1.5243538008576782,
"learning_rate": 2e-05,
"loss": 0.8201045989990234,
"step": 1940
},
{
"epoch": 0.10520069054812257,
"grad_norm": 1.8549508993672652,
"learning_rate": 2e-05,
"loss": 0.8507599830627441,
"step": 1950
},
{
"epoch": 0.10574018126888217,
"grad_norm": 3.2676775863279293,
"learning_rate": 2e-05,
"loss": 0.8315736770629882,
"step": 1960
},
{
"epoch": 0.10627967198964178,
"grad_norm": 3.170505632566329,
"learning_rate": 2e-05,
"loss": 0.8597011566162109,
"step": 1970
},
{
"epoch": 0.10681916271040139,
"grad_norm": 1.225518275743383,
"learning_rate": 2e-05,
"loss": 0.8449475288391113,
"step": 1980
},
{
"epoch": 0.10735865343116098,
"grad_norm": 1.7639666202458668,
"learning_rate": 2e-05,
"loss": 0.8267492294311524,
"step": 1990
},
{
"epoch": 0.10789814415192059,
"grad_norm": 1.7820697092202835,
"learning_rate": 2e-05,
"loss": 0.8312843322753907,
"step": 2000
},
{
"epoch": 0.10843763487268018,
"grad_norm": 4.015953726833389,
"learning_rate": 2e-05,
"loss": 0.8443691253662109,
"step": 2010
},
{
"epoch": 0.10897712559343979,
"grad_norm": 1.999195946930485,
"learning_rate": 2e-05,
"loss": 0.8289900779724121,
"step": 2020
},
{
"epoch": 0.1095166163141994,
"grad_norm": 1.8651265962731969,
"learning_rate": 2e-05,
"loss": 0.840304946899414,
"step": 2030
},
{
"epoch": 0.110056107034959,
"grad_norm": 1.7034465477351663,
"learning_rate": 2e-05,
"loss": 0.8282983779907227,
"step": 2040
},
{
"epoch": 0.1105955977557186,
"grad_norm": 1.292874343679415,
"learning_rate": 2e-05,
"loss": 0.8187969207763672,
"step": 2050
},
{
"epoch": 0.11113508847647821,
"grad_norm": 9.900066428760711,
"learning_rate": 2e-05,
"loss": 0.8275846481323242,
"step": 2060
},
{
"epoch": 0.1116745791972378,
"grad_norm": 1.4024064010510686,
"learning_rate": 2e-05,
"loss": 0.8306047439575195,
"step": 2070
},
{
"epoch": 0.11221406991799741,
"grad_norm": 2.400290796313511,
"learning_rate": 2e-05,
"loss": 0.8676346778869629,
"step": 2080
},
{
"epoch": 0.11275356063875701,
"grad_norm": 3.514349150867208,
"learning_rate": 2e-05,
"loss": 0.8274039268493653,
"step": 2090
},
{
"epoch": 0.11329305135951662,
"grad_norm": 5.088709612171823,
"learning_rate": 2e-05,
"loss": 0.8288514137268066,
"step": 2100
},
{
"epoch": 0.11383254208027623,
"grad_norm": 2.098725303443767,
"learning_rate": 2e-05,
"loss": 0.8381128311157227,
"step": 2110
},
{
"epoch": 0.11437203280103582,
"grad_norm": 1.3305492466588589,
"learning_rate": 2e-05,
"loss": 0.8685014724731446,
"step": 2120
},
{
"epoch": 0.11491152352179543,
"grad_norm": 2.7110556064904956,
"learning_rate": 2e-05,
"loss": 0.8481921195983887,
"step": 2130
},
{
"epoch": 0.11545101424255502,
"grad_norm": 1.10367668589633,
"learning_rate": 2e-05,
"loss": 0.8573419570922851,
"step": 2140
},
{
"epoch": 0.11599050496331463,
"grad_norm": 2.138417581209623,
"learning_rate": 2e-05,
"loss": 0.8302045822143554,
"step": 2150
},
{
"epoch": 0.11652999568407424,
"grad_norm": 1.1112744471980331,
"learning_rate": 2e-05,
"loss": 0.8130320549011231,
"step": 2160
},
{
"epoch": 0.11706948640483383,
"grad_norm": 1.6334189344204764,
"learning_rate": 2e-05,
"loss": 0.8478602409362793,
"step": 2170
},
{
"epoch": 0.11760897712559344,
"grad_norm": 2.7583960750005816,
"learning_rate": 2e-05,
"loss": 0.8246549606323242,
"step": 2180
},
{
"epoch": 0.11814846784635304,
"grad_norm": 1.9058948199400891,
"learning_rate": 2e-05,
"loss": 0.8250743865966796,
"step": 2190
},
{
"epoch": 0.11868795856711264,
"grad_norm": 1.586316165202703,
"learning_rate": 2e-05,
"loss": 0.8306868553161622,
"step": 2200
},
{
"epoch": 0.11922744928787225,
"grad_norm": 3.6562916703913606,
"learning_rate": 2e-05,
"loss": 0.8404013633728027,
"step": 2210
},
{
"epoch": 0.11976694000863185,
"grad_norm": 1.914570415791936,
"learning_rate": 2e-05,
"loss": 0.8350730895996094,
"step": 2220
},
{
"epoch": 0.12030643072939146,
"grad_norm": 1.4049455715505264,
"learning_rate": 2e-05,
"loss": 0.8396036148071289,
"step": 2230
},
{
"epoch": 0.12084592145015106,
"grad_norm": 1.1836748795523662,
"learning_rate": 2e-05,
"loss": 0.8288493156433105,
"step": 2240
},
{
"epoch": 0.12138541217091066,
"grad_norm": 2.5165436971018735,
"learning_rate": 2e-05,
"loss": 0.8394759178161622,
"step": 2250
},
{
"epoch": 0.12192490289167027,
"grad_norm": 1.8023654123652022,
"learning_rate": 2e-05,
"loss": 0.8561839103698731,
"step": 2260
},
{
"epoch": 0.12246439361242986,
"grad_norm": 2.197758047068318,
"learning_rate": 2e-05,
"loss": 0.8342147827148437,
"step": 2270
},
{
"epoch": 0.12300388433318947,
"grad_norm": 1.3512470884395074,
"learning_rate": 2e-05,
"loss": 0.8416089057922364,
"step": 2280
},
{
"epoch": 0.12354337505394908,
"grad_norm": 1.158221169858105,
"learning_rate": 2e-05,
"loss": 0.815174674987793,
"step": 2290
},
{
"epoch": 0.12408286577470867,
"grad_norm": 2.1931315632737336,
"learning_rate": 2e-05,
"loss": 0.8198381423950195,
"step": 2300
},
{
"epoch": 0.12462235649546828,
"grad_norm": 1.2020698197548285,
"learning_rate": 2e-05,
"loss": 0.8212334632873535,
"step": 2310
},
{
"epoch": 0.1251618472162279,
"grad_norm": 1.2630839020259081,
"learning_rate": 2e-05,
"loss": 0.8234346389770508,
"step": 2320
},
{
"epoch": 0.12570133793698748,
"grad_norm": 1.05835478339789,
"learning_rate": 2e-05,
"loss": 0.8266730308532715,
"step": 2330
},
{
"epoch": 0.12624082865774708,
"grad_norm": 1.153807197212215,
"learning_rate": 2e-05,
"loss": 0.8297053337097168,
"step": 2340
},
{
"epoch": 0.1267803193785067,
"grad_norm": 1.081701471063699,
"learning_rate": 2e-05,
"loss": 0.850483512878418,
"step": 2350
},
{
"epoch": 0.1273198100992663,
"grad_norm": 1.1032276472226967,
"learning_rate": 2e-05,
"loss": 0.8351642608642578,
"step": 2360
},
{
"epoch": 0.1278593008200259,
"grad_norm": 0.9373186180851497,
"learning_rate": 2e-05,
"loss": 0.850758171081543,
"step": 2370
},
{
"epoch": 0.1283987915407855,
"grad_norm": 0.9185447727528806,
"learning_rate": 2e-05,
"loss": 0.8138019561767578,
"step": 2380
},
{
"epoch": 0.1289382822615451,
"grad_norm": 1.4547050261067835,
"learning_rate": 2e-05,
"loss": 0.8109475135803222,
"step": 2390
},
{
"epoch": 0.1294777729823047,
"grad_norm": 0.8962680388570466,
"learning_rate": 2e-05,
"loss": 0.8358553886413574,
"step": 2400
},
{
"epoch": 0.1300172637030643,
"grad_norm": 0.9967276931315883,
"learning_rate": 2e-05,
"loss": 0.8311929702758789,
"step": 2410
},
{
"epoch": 0.13055675442382392,
"grad_norm": 1.171890528912994,
"learning_rate": 2e-05,
"loss": 0.8504758834838867,
"step": 2420
},
{
"epoch": 0.1310962451445835,
"grad_norm": 0.9664067450616619,
"learning_rate": 2e-05,
"loss": 0.8218025207519531,
"step": 2430
},
{
"epoch": 0.1316357358653431,
"grad_norm": 1.0236162825206507,
"learning_rate": 2e-05,
"loss": 0.8196083068847656,
"step": 2440
},
{
"epoch": 0.13217522658610273,
"grad_norm": 1.9012584301013733,
"learning_rate": 2e-05,
"loss": 0.823670768737793,
"step": 2450
},
{
"epoch": 0.13271471730686232,
"grad_norm": 1.1023811611206806,
"learning_rate": 2e-05,
"loss": 0.8224227905273438,
"step": 2460
},
{
"epoch": 0.13325420802762192,
"grad_norm": 9.134961938530486,
"learning_rate": 2e-05,
"loss": 0.8160662651062012,
"step": 2470
},
{
"epoch": 0.13379369874838154,
"grad_norm": 4.065113504605792,
"learning_rate": 2e-05,
"loss": 0.842041015625,
"step": 2480
},
{
"epoch": 0.13433318946914113,
"grad_norm": 6.789485151507618,
"learning_rate": 2e-05,
"loss": 0.8334197998046875,
"step": 2490
},
{
"epoch": 0.13487268018990073,
"grad_norm": 3.755408787739404,
"learning_rate": 2e-05,
"loss": 0.8373711585998536,
"step": 2500
},
{
"epoch": 0.13541217091066032,
"grad_norm": 4.1766718888496115,
"learning_rate": 2e-05,
"loss": 0.826263427734375,
"step": 2510
},
{
"epoch": 0.13595166163141995,
"grad_norm": 1.4503676530546985,
"learning_rate": 2e-05,
"loss": 0.8411909103393554,
"step": 2520
},
{
"epoch": 0.13649115235217954,
"grad_norm": 2.9419252466356443,
"learning_rate": 2e-05,
"loss": 0.8234809875488281,
"step": 2530
},
{
"epoch": 0.13703064307293913,
"grad_norm": 3.2828905803244144,
"learning_rate": 2e-05,
"loss": 0.8695075035095214,
"step": 2540
},
{
"epoch": 0.13757013379369876,
"grad_norm": 1.096460041177136,
"learning_rate": 2e-05,
"loss": 0.8468042373657226,
"step": 2550
},
{
"epoch": 0.13810962451445835,
"grad_norm": 1.0597785888179652,
"learning_rate": 2e-05,
"loss": 0.8341262817382813,
"step": 2560
},
{
"epoch": 0.13864911523521795,
"grad_norm": 9.087223552942303,
"learning_rate": 2e-05,
"loss": 0.8169255256652832,
"step": 2570
},
{
"epoch": 0.13918860595597757,
"grad_norm": 7.72894258287119,
"learning_rate": 2e-05,
"loss": 0.8361001014709473,
"step": 2580
},
{
"epoch": 0.13972809667673716,
"grad_norm": 1.84749896259604,
"learning_rate": 2e-05,
"loss": 0.8118861198425293,
"step": 2590
},
{
"epoch": 0.14026758739749676,
"grad_norm": 1.499923768048581,
"learning_rate": 2e-05,
"loss": 0.8059223175048829,
"step": 2600
},
{
"epoch": 0.14080707811825638,
"grad_norm": 2.469774702348604,
"learning_rate": 2e-05,
"loss": 0.8464885711669922,
"step": 2610
},
{
"epoch": 0.14134656883901597,
"grad_norm": 1.4562619868061146,
"learning_rate": 2e-05,
"loss": 0.855031681060791,
"step": 2620
},
{
"epoch": 0.14188605955977557,
"grad_norm": 1.1580412885044675,
"learning_rate": 2e-05,
"loss": 0.8250855445861817,
"step": 2630
},
{
"epoch": 0.14242555028053516,
"grad_norm": 5.85834983160985,
"learning_rate": 2e-05,
"loss": 0.8170978546142578,
"step": 2640
},
{
"epoch": 0.14296504100129478,
"grad_norm": 2.1118214513392153,
"learning_rate": 2e-05,
"loss": 0.8098548889160156,
"step": 2650
},
{
"epoch": 0.14350453172205438,
"grad_norm": 14.992058801195402,
"learning_rate": 2e-05,
"loss": 0.8217266082763672,
"step": 2660
},
{
"epoch": 0.14404402244281397,
"grad_norm": 2.3085553913502035,
"learning_rate": 2e-05,
"loss": 0.8170116424560547,
"step": 2670
},
{
"epoch": 0.1445835131635736,
"grad_norm": 17.707266771089483,
"learning_rate": 2e-05,
"loss": 0.8280685424804688,
"step": 2680
},
{
"epoch": 0.1451230038843332,
"grad_norm": 3.1378615826812766,
"learning_rate": 2e-05,
"loss": 0.8434804916381836,
"step": 2690
},
{
"epoch": 0.14566249460509278,
"grad_norm": 2.5515862288748354,
"learning_rate": 2e-05,
"loss": 0.8259258270263672,
"step": 2700
},
{
"epoch": 0.1462019853258524,
"grad_norm": 3.9230866849646424,
"learning_rate": 2e-05,
"loss": 0.8185581207275391,
"step": 2710
},
{
"epoch": 0.146741476046612,
"grad_norm": 3.2217451837996975,
"learning_rate": 2e-05,
"loss": 0.8379020690917969,
"step": 2720
},
{
"epoch": 0.1472809667673716,
"grad_norm": 1.557738526634509,
"learning_rate": 2e-05,
"loss": 0.8445243835449219,
"step": 2730
},
{
"epoch": 0.1478204574881312,
"grad_norm": 1.5481180648756823,
"learning_rate": 2e-05,
"loss": 0.8328718185424805,
"step": 2740
},
{
"epoch": 0.1483599482088908,
"grad_norm": 1.4388832631294857,
"learning_rate": 2e-05,
"loss": 0.8253545761108398,
"step": 2750
},
{
"epoch": 0.1488994389296504,
"grad_norm": 1.0539255503501914,
"learning_rate": 2e-05,
"loss": 0.8445590972900391,
"step": 2760
},
{
"epoch": 0.14943892965041,
"grad_norm": 4.95376827487241,
"learning_rate": 2e-05,
"loss": 0.8173467636108398,
"step": 2770
},
{
"epoch": 0.14997842037116962,
"grad_norm": 4.600755881351036,
"learning_rate": 2e-05,
"loss": 0.8473451614379883,
"step": 2780
},
{
"epoch": 0.15051791109192922,
"grad_norm": 1.3528051911908148,
"learning_rate": 2e-05,
"loss": 0.8311235427856445,
"step": 2790
},
{
"epoch": 0.1510574018126888,
"grad_norm": 2.5244296910788786,
"learning_rate": 2e-05,
"loss": 0.8462516784667968,
"step": 2800
},
{
"epoch": 0.15159689253344844,
"grad_norm": 1.3547145890263894,
"learning_rate": 2e-05,
"loss": 0.8145876884460449,
"step": 2810
},
{
"epoch": 0.15213638325420803,
"grad_norm": 4.904666690029179,
"learning_rate": 2e-05,
"loss": 0.8427519798278809,
"step": 2820
},
{
"epoch": 0.15267587397496762,
"grad_norm": 1.609216240729035,
"learning_rate": 2e-05,
"loss": 0.8435686111450196,
"step": 2830
},
{
"epoch": 0.15321536469572725,
"grad_norm": 1.4281030100315293,
"learning_rate": 2e-05,
"loss": 0.8191211700439454,
"step": 2840
},
{
"epoch": 0.15375485541648684,
"grad_norm": 1.7798898314789362,
"learning_rate": 2e-05,
"loss": 0.8122947692871094,
"step": 2850
},
{
"epoch": 0.15429434613724644,
"grad_norm": 2.830774437932546,
"learning_rate": 2e-05,
"loss": 0.8318849563598633,
"step": 2860
},
{
"epoch": 0.15483383685800603,
"grad_norm": 5.397744742205086,
"learning_rate": 2e-05,
"loss": 0.8305788993835449,
"step": 2870
},
{
"epoch": 0.15537332757876565,
"grad_norm": 2.898600936491205,
"learning_rate": 2e-05,
"loss": 0.8408110618591309,
"step": 2880
},
{
"epoch": 0.15591281829952525,
"grad_norm": 8.773413677216482,
"learning_rate": 2e-05,
"loss": 0.8318193435668946,
"step": 2890
},
{
"epoch": 0.15645230902028484,
"grad_norm": 2.3331580039530095,
"learning_rate": 2e-05,
"loss": 0.8389785766601563,
"step": 2900
},
{
"epoch": 0.15699179974104446,
"grad_norm": 2.568113164269533,
"learning_rate": 2e-05,
"loss": 0.8040918350219727,
"step": 2910
},
{
"epoch": 0.15753129046180406,
"grad_norm": 1.4668399503612397,
"learning_rate": 2e-05,
"loss": 0.8159090042114258,
"step": 2920
},
{
"epoch": 0.15807078118256365,
"grad_norm": 4.911971870615249,
"learning_rate": 2e-05,
"loss": 0.8376889228820801,
"step": 2930
},
{
"epoch": 0.15861027190332327,
"grad_norm": 2.981636311233402,
"learning_rate": 2e-05,
"loss": 0.8562882423400879,
"step": 2940
},
{
"epoch": 0.15914976262408287,
"grad_norm": 7.625355317159627,
"learning_rate": 2e-05,
"loss": 0.8109912872314453,
"step": 2950
},
{
"epoch": 0.15968925334484246,
"grad_norm": 2.1473747341723555,
"learning_rate": 2e-05,
"loss": 0.852902603149414,
"step": 2960
},
{
"epoch": 0.16022874406560206,
"grad_norm": 4.307544898725762,
"learning_rate": 2e-05,
"loss": 0.8281949043273926,
"step": 2970
},
{
"epoch": 0.16076823478636168,
"grad_norm": 5.656390266767483,
"learning_rate": 2e-05,
"loss": 0.7931592464447021,
"step": 2980
},
{
"epoch": 0.16130772550712127,
"grad_norm": 2.595677289608645,
"learning_rate": 2e-05,
"loss": 0.8464061737060546,
"step": 2990
},
{
"epoch": 0.16184721622788087,
"grad_norm": 2.5286497672098376,
"learning_rate": 2e-05,
"loss": 0.8217041015625,
"step": 3000
},
{
"epoch": 0.1623867069486405,
"grad_norm": 1.6815165067247406,
"learning_rate": 2e-05,
"loss": 0.8131906509399414,
"step": 3010
},
{
"epoch": 0.16292619766940009,
"grad_norm": 4.470085181162879,
"learning_rate": 2e-05,
"loss": 0.8476617813110352,
"step": 3020
},
{
"epoch": 0.16346568839015968,
"grad_norm": 57.757712059800895,
"learning_rate": 2e-05,
"loss": 0.8235321044921875,
"step": 3030
},
{
"epoch": 0.1640051791109193,
"grad_norm": 1.3196900653412662,
"learning_rate": 2e-05,
"loss": 0.8411979675292969,
"step": 3040
},
{
"epoch": 0.1645446698316789,
"grad_norm": 1.3565437997414518,
"learning_rate": 2e-05,
"loss": 0.8321975708007813,
"step": 3050
},
{
"epoch": 0.1650841605524385,
"grad_norm": 1.9250529621406256,
"learning_rate": 2e-05,
"loss": 0.8183302879333496,
"step": 3060
},
{
"epoch": 0.1656236512731981,
"grad_norm": 1.6665163841705182,
"learning_rate": 2e-05,
"loss": 0.8212745666503907,
"step": 3070
},
{
"epoch": 0.1661631419939577,
"grad_norm": 0.9624218525439471,
"learning_rate": 2e-05,
"loss": 0.8360950469970703,
"step": 3080
},
{
"epoch": 0.1667026327147173,
"grad_norm": 1.6154798724669914,
"learning_rate": 2e-05,
"loss": 0.8246768951416016,
"step": 3090
},
{
"epoch": 0.1672421234354769,
"grad_norm": 1.4309300679224686,
"learning_rate": 2e-05,
"loss": 0.8143646240234375,
"step": 3100
},
{
"epoch": 0.16778161415623652,
"grad_norm": 1.1954152653837478,
"learning_rate": 2e-05,
"loss": 0.8255207061767578,
"step": 3110
},
{
"epoch": 0.1683211048769961,
"grad_norm": 3.874535720645589,
"learning_rate": 2e-05,
"loss": 0.8268468856811524,
"step": 3120
},
{
"epoch": 0.1688605955977557,
"grad_norm": 1.666585578869163,
"learning_rate": 2e-05,
"loss": 0.8370718955993652,
"step": 3130
},
{
"epoch": 0.16940008631851533,
"grad_norm": 2.1122716764285214,
"learning_rate": 2e-05,
"loss": 0.8222600936889648,
"step": 3140
},
{
"epoch": 0.16993957703927492,
"grad_norm": 1.626502422759658,
"learning_rate": 2e-05,
"loss": 0.8307378768920899,
"step": 3150
},
{
"epoch": 0.17047906776003452,
"grad_norm": 1.249709631021305,
"learning_rate": 2e-05,
"loss": 0.8274057388305665,
"step": 3160
},
{
"epoch": 0.17101855848079414,
"grad_norm": 1.2755622837169793,
"learning_rate": 2e-05,
"loss": 0.8418668746948242,
"step": 3170
},
{
"epoch": 0.17155804920155374,
"grad_norm": 1.1471931685322956,
"learning_rate": 2e-05,
"loss": 0.8037077903747558,
"step": 3180
},
{
"epoch": 0.17209753992231333,
"grad_norm": 2.731067427188893,
"learning_rate": 2e-05,
"loss": 0.7964674949645996,
"step": 3190
},
{
"epoch": 0.17263703064307295,
"grad_norm": 1.4738003450064086,
"learning_rate": 2e-05,
"loss": 0.8007509231567382,
"step": 3200
},
{
"epoch": 0.17317652136383255,
"grad_norm": 1.310820117633026,
"learning_rate": 2e-05,
"loss": 0.8201332092285156,
"step": 3210
},
{
"epoch": 0.17371601208459214,
"grad_norm": 1.3355379129188545,
"learning_rate": 2e-05,
"loss": 0.8006715774536133,
"step": 3220
},
{
"epoch": 0.17425550280535174,
"grad_norm": 2.5523015565267078,
"learning_rate": 2e-05,
"loss": 0.8170543670654297,
"step": 3230
},
{
"epoch": 0.17479499352611136,
"grad_norm": 7.648994384982638,
"learning_rate": 2e-05,
"loss": 0.7966285705566406,
"step": 3240
},
{
"epoch": 0.17533448424687095,
"grad_norm": 2.2291376008212502,
"learning_rate": 2e-05,
"loss": 0.8066202163696289,
"step": 3250
},
{
"epoch": 0.17587397496763055,
"grad_norm": 1.9013943798842645,
"learning_rate": 2e-05,
"loss": 0.8028726577758789,
"step": 3260
},
{
"epoch": 0.17641346568839017,
"grad_norm": 1.2094542057997177,
"learning_rate": 2e-05,
"loss": 0.8179764747619629,
"step": 3270
},
{
"epoch": 0.17695295640914976,
"grad_norm": 2.7367851475598,
"learning_rate": 2e-05,
"loss": 0.8103551864624023,
"step": 3280
},
{
"epoch": 0.17749244712990936,
"grad_norm": 2.9058412897859656,
"learning_rate": 2e-05,
"loss": 0.8264286041259765,
"step": 3290
},
{
"epoch": 0.17803193785066898,
"grad_norm": 3.226004030131601,
"learning_rate": 2e-05,
"loss": 0.8190610885620118,
"step": 3300
},
{
"epoch": 0.17857142857142858,
"grad_norm": 1.8721988330858943,
"learning_rate": 2e-05,
"loss": 0.8306256294250488,
"step": 3310
},
{
"epoch": 0.17911091929218817,
"grad_norm": 1.3899444238570022,
"learning_rate": 2e-05,
"loss": 0.8446199417114257,
"step": 3320
},
{
"epoch": 0.17965041001294776,
"grad_norm": 1.0929088079648228,
"learning_rate": 2e-05,
"loss": 0.7976521968841552,
"step": 3330
},
{
"epoch": 0.1801899007337074,
"grad_norm": 1.1793561049774377,
"learning_rate": 2e-05,
"loss": 0.8168546676635742,
"step": 3340
},
{
"epoch": 0.18072939145446698,
"grad_norm": 15.176731004709248,
"learning_rate": 2e-05,
"loss": 0.8124425888061524,
"step": 3350
},
{
"epoch": 0.18126888217522658,
"grad_norm": 1.0594125222809312,
"learning_rate": 2e-05,
"loss": 0.806308364868164,
"step": 3360
},
{
"epoch": 0.1818083728959862,
"grad_norm": 1.9453105377863469,
"learning_rate": 2e-05,
"loss": 0.8045181274414063,
"step": 3370
},
{
"epoch": 0.1823478636167458,
"grad_norm": 0.9815060321000388,
"learning_rate": 2e-05,
"loss": 0.8289067268371582,
"step": 3380
},
{
"epoch": 0.1828873543375054,
"grad_norm": 1.107626410337324,
"learning_rate": 2e-05,
"loss": 0.8187108993530273,
"step": 3390
},
{
"epoch": 0.183426845058265,
"grad_norm": 1.3713782627751003,
"learning_rate": 2e-05,
"loss": 0.8212367057800293,
"step": 3400
},
{
"epoch": 0.1839663357790246,
"grad_norm": 1.1934434763982462,
"learning_rate": 2e-05,
"loss": 0.8170612335205079,
"step": 3410
},
{
"epoch": 0.1845058264997842,
"grad_norm": 1.0151425442795299,
"learning_rate": 2e-05,
"loss": 0.8014205932617188,
"step": 3420
},
{
"epoch": 0.18504531722054382,
"grad_norm": 0.9339054423212217,
"learning_rate": 2e-05,
"loss": 0.8339118003845215,
"step": 3430
},
{
"epoch": 0.18558480794130341,
"grad_norm": 0.967368753176617,
"learning_rate": 2e-05,
"loss": 0.8132877349853516,
"step": 3440
},
{
"epoch": 0.186124298662063,
"grad_norm": 2.162294345081955,
"learning_rate": 2e-05,
"loss": 0.8348134994506836,
"step": 3450
},
{
"epoch": 0.1866637893828226,
"grad_norm": 2.687504589015093,
"learning_rate": 2e-05,
"loss": 0.8514577865600585,
"step": 3460
},
{
"epoch": 0.18720328010358223,
"grad_norm": 1.3616314045359637,
"learning_rate": 2e-05,
"loss": 0.8360185623168945,
"step": 3470
},
{
"epoch": 0.18774277082434182,
"grad_norm": 0.7945412849733318,
"learning_rate": 2e-05,
"loss": 0.8060104370117187,
"step": 3480
},
{
"epoch": 0.18828226154510141,
"grad_norm": 1.2865284566965982,
"learning_rate": 2e-05,
"loss": 0.8192827224731445,
"step": 3490
},
{
"epoch": 0.18882175226586104,
"grad_norm": 1.0470430689868928,
"learning_rate": 2e-05,
"loss": 0.8104745864868164,
"step": 3500
},
{
"epoch": 0.18936124298662063,
"grad_norm": 1.0033888590154632,
"learning_rate": 2e-05,
"loss": 0.8070037841796875,
"step": 3510
},
{
"epoch": 0.18990073370738023,
"grad_norm": 1.4237596335672749,
"learning_rate": 2e-05,
"loss": 0.7981664657592773,
"step": 3520
},
{
"epoch": 0.19044022442813985,
"grad_norm": 0.9746666528478075,
"learning_rate": 2e-05,
"loss": 0.8370217323303223,
"step": 3530
},
{
"epoch": 0.19097971514889944,
"grad_norm": 2.370032426413775,
"learning_rate": 2e-05,
"loss": 0.8089248657226562,
"step": 3540
},
{
"epoch": 0.19151920586965904,
"grad_norm": 1.4096737349425104,
"learning_rate": 2e-05,
"loss": 0.8232223510742187,
"step": 3550
},
{
"epoch": 0.19205869659041863,
"grad_norm": 1.5464845999590675,
"learning_rate": 2e-05,
"loss": 0.8215899467468262,
"step": 3560
},
{
"epoch": 0.19259818731117825,
"grad_norm": 1.8902013609436816,
"learning_rate": 2e-05,
"loss": 0.8071002960205078,
"step": 3570
},
{
"epoch": 0.19313767803193785,
"grad_norm": 1.0834961800168135,
"learning_rate": 2e-05,
"loss": 0.818499755859375,
"step": 3580
},
{
"epoch": 0.19367716875269744,
"grad_norm": 1.469175436322324,
"learning_rate": 2e-05,
"loss": 0.8098075866699219,
"step": 3590
},
{
"epoch": 0.19421665947345707,
"grad_norm": 1.4457828669467623,
"learning_rate": 2e-05,
"loss": 0.8190594673156738,
"step": 3600
},
{
"epoch": 0.19475615019421666,
"grad_norm": 1.2339738565051197,
"learning_rate": 2e-05,
"loss": 0.8001772880554199,
"step": 3610
},
{
"epoch": 0.19529564091497625,
"grad_norm": 1.0129969586529555,
"learning_rate": 2e-05,
"loss": 0.8169227600097656,
"step": 3620
},
{
"epoch": 0.19583513163573588,
"grad_norm": 1.8405886663060382,
"learning_rate": 2e-05,
"loss": 0.8161848068237305,
"step": 3630
},
{
"epoch": 0.19637462235649547,
"grad_norm": 0.8630501803188849,
"learning_rate": 2e-05,
"loss": 0.7952068328857422,
"step": 3640
},
{
"epoch": 0.19691411307725507,
"grad_norm": 0.9252474483323625,
"learning_rate": 2e-05,
"loss": 0.836590576171875,
"step": 3650
},
{
"epoch": 0.1974536037980147,
"grad_norm": 0.9338702892336649,
"learning_rate": 2e-05,
"loss": 0.8275209426879883,
"step": 3660
},
{
"epoch": 0.19799309451877428,
"grad_norm": 0.9675019978413074,
"learning_rate": 2e-05,
"loss": 0.8117290496826172,
"step": 3670
},
{
"epoch": 0.19853258523953388,
"grad_norm": 0.8692908353972926,
"learning_rate": 2e-05,
"loss": 0.8203290939331055,
"step": 3680
},
{
"epoch": 0.19907207596029347,
"grad_norm": 0.9432619722907122,
"learning_rate": 2e-05,
"loss": 0.8062999725341797,
"step": 3690
},
{
"epoch": 0.1996115666810531,
"grad_norm": 0.9465547041865168,
"learning_rate": 2e-05,
"loss": 0.8359698295593262,
"step": 3700
},
{
"epoch": 0.2001510574018127,
"grad_norm": 0.8544475554924795,
"learning_rate": 2e-05,
"loss": 0.8113945960998535,
"step": 3710
},
{
"epoch": 0.20069054812257228,
"grad_norm": 1.0261458270031636,
"learning_rate": 2e-05,
"loss": 0.8012717247009278,
"step": 3720
},
{
"epoch": 0.2012300388433319,
"grad_norm": 2.3510637262715686,
"learning_rate": 2e-05,
"loss": 0.7971127510070801,
"step": 3730
},
{
"epoch": 0.2017695295640915,
"grad_norm": 1.0401878649419207,
"learning_rate": 2e-05,
"loss": 0.8233554840087891,
"step": 3740
},
{
"epoch": 0.2023090202848511,
"grad_norm": 1.6871599880351058,
"learning_rate": 2e-05,
"loss": 0.8121973037719726,
"step": 3750
},
{
"epoch": 0.20284851100561072,
"grad_norm": 0.9834662903562297,
"learning_rate": 2e-05,
"loss": 0.799620532989502,
"step": 3760
},
{
"epoch": 0.2033880017263703,
"grad_norm": 13.856106429547337,
"learning_rate": 2e-05,
"loss": 0.8100821495056152,
"step": 3770
},
{
"epoch": 0.2039274924471299,
"grad_norm": 1.7971124760415595,
"learning_rate": 2e-05,
"loss": 0.822230339050293,
"step": 3780
},
{
"epoch": 0.2044669831678895,
"grad_norm": 1.898826077210772,
"learning_rate": 2e-05,
"loss": 0.8280195236206055,
"step": 3790
},
{
"epoch": 0.20500647388864912,
"grad_norm": 1.5690048084284152,
"learning_rate": 2e-05,
"loss": 0.7768063545227051,
"step": 3800
},
{
"epoch": 0.20554596460940872,
"grad_norm": 1.2924271342168896,
"learning_rate": 2e-05,
"loss": 0.8139206886291503,
"step": 3810
},
{
"epoch": 0.2060854553301683,
"grad_norm": 1.713906617227459,
"learning_rate": 2e-05,
"loss": 0.8099102020263672,
"step": 3820
},
{
"epoch": 0.20662494605092793,
"grad_norm": 1.0000768599712642,
"learning_rate": 2e-05,
"loss": 0.8023160934448242,
"step": 3830
},
{
"epoch": 0.20716443677168753,
"grad_norm": 1.8923446682002336,
"learning_rate": 2e-05,
"loss": 0.8316279411315918,
"step": 3840
},
{
"epoch": 0.20770392749244712,
"grad_norm": 0.9410427812888499,
"learning_rate": 2e-05,
"loss": 0.8073904037475585,
"step": 3850
},
{
"epoch": 0.20824341821320674,
"grad_norm": 1.8310165996432775,
"learning_rate": 2e-05,
"loss": 0.8441598892211915,
"step": 3860
},
{
"epoch": 0.20878290893396634,
"grad_norm": 3.2539518984867444,
"learning_rate": 2e-05,
"loss": 0.8111666679382324,
"step": 3870
},
{
"epoch": 0.20932239965472593,
"grad_norm": 1.0747584520027538,
"learning_rate": 2e-05,
"loss": 0.8289793968200684,
"step": 3880
},
{
"epoch": 0.20986189037548555,
"grad_norm": 1.1928486588388492,
"learning_rate": 2e-05,
"loss": 0.7862348556518555,
"step": 3890
},
{
"epoch": 0.21040138109624515,
"grad_norm": 1.7434197055178486,
"learning_rate": 2e-05,
"loss": 0.8227115631103515,
"step": 3900
},
{
"epoch": 0.21094087181700474,
"grad_norm": 1.0267098850458918,
"learning_rate": 2e-05,
"loss": 0.8255733489990235,
"step": 3910
},
{
"epoch": 0.21148036253776434,
"grad_norm": 1.2265343976727108,
"learning_rate": 2e-05,
"loss": 0.7926362514495849,
"step": 3920
},
{
"epoch": 0.21201985325852396,
"grad_norm": 0.9373764058253546,
"learning_rate": 2e-05,
"loss": 0.7910985469818115,
"step": 3930
},
{
"epoch": 0.21255934397928355,
"grad_norm": 1.194071164302341,
"learning_rate": 2e-05,
"loss": 0.8127195358276367,
"step": 3940
},
{
"epoch": 0.21309883470004315,
"grad_norm": 1.260475572232143,
"learning_rate": 2e-05,
"loss": 0.8285701751708985,
"step": 3950
},
{
"epoch": 0.21363832542080277,
"grad_norm": 0.9898466932738494,
"learning_rate": 2e-05,
"loss": 0.816091251373291,
"step": 3960
},
{
"epoch": 0.21417781614156237,
"grad_norm": 1.0090063218881065,
"learning_rate": 2e-05,
"loss": 0.7883634090423584,
"step": 3970
},
{
"epoch": 0.21471730686232196,
"grad_norm": 1.6131569146168403,
"learning_rate": 2e-05,
"loss": 0.8127913475036621,
"step": 3980
},
{
"epoch": 0.21525679758308158,
"grad_norm": 1.1595573594793847,
"learning_rate": 2e-05,
"loss": 0.8038475036621093,
"step": 3990
},
{
"epoch": 0.21579628830384118,
"grad_norm": 1.9569762958682257,
"learning_rate": 2e-05,
"loss": 0.8159636497497559,
"step": 4000
},
{
"epoch": 0.21633577902460077,
"grad_norm": 2.335005979386267,
"learning_rate": 2e-05,
"loss": 0.8046688079833985,
"step": 4010
},
{
"epoch": 0.21687526974536037,
"grad_norm": 1.0399747803957953,
"learning_rate": 2e-05,
"loss": 0.8062277793884277,
"step": 4020
},
{
"epoch": 0.21741476046612,
"grad_norm": 2.0436577055413636,
"learning_rate": 2e-05,
"loss": 0.7829396724700928,
"step": 4030
},
{
"epoch": 0.21795425118687958,
"grad_norm": 3.7324962194464963,
"learning_rate": 2e-05,
"loss": 0.779371976852417,
"step": 4040
},
{
"epoch": 0.21849374190763918,
"grad_norm": 1.1382565851810948,
"learning_rate": 2e-05,
"loss": 0.7965741634368897,
"step": 4050
},
{
"epoch": 0.2190332326283988,
"grad_norm": 1.8123028132941512,
"learning_rate": 2e-05,
"loss": 0.7883219718933105,
"step": 4060
},
{
"epoch": 0.2195727233491584,
"grad_norm": 1.0506410293373154,
"learning_rate": 2e-05,
"loss": 0.797592306137085,
"step": 4070
}
],
"logging_steps": 10,
"max_steps": 5935,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2035,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1927226987642880.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}