orca-agentinstruct-1M-v1-cleaned / trainer_state.json
sedrickkeh's picture
End of training
b559e37 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9983489268024215,
"eval_steps": 500,
"global_step": 2724,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01100715465052284,
"grad_norm": 8.068985135850538,
"learning_rate": 5e-06,
"loss": 0.7005,
"step": 10
},
{
"epoch": 0.02201430930104568,
"grad_norm": 1.345068090353878,
"learning_rate": 5e-06,
"loss": 0.6377,
"step": 20
},
{
"epoch": 0.03302146395156852,
"grad_norm": 0.904010640164903,
"learning_rate": 5e-06,
"loss": 0.6063,
"step": 30
},
{
"epoch": 0.04402861860209136,
"grad_norm": 1.0016711496058677,
"learning_rate": 5e-06,
"loss": 0.5969,
"step": 40
},
{
"epoch": 0.0550357732526142,
"grad_norm": 0.9379200618665713,
"learning_rate": 5e-06,
"loss": 0.5714,
"step": 50
},
{
"epoch": 0.06604292790313704,
"grad_norm": 0.6938901282332245,
"learning_rate": 5e-06,
"loss": 0.5648,
"step": 60
},
{
"epoch": 0.07705008255365987,
"grad_norm": 1.2132887620233943,
"learning_rate": 5e-06,
"loss": 0.5611,
"step": 70
},
{
"epoch": 0.08805723720418272,
"grad_norm": 0.6871985890249172,
"learning_rate": 5e-06,
"loss": 0.5512,
"step": 80
},
{
"epoch": 0.09906439185470556,
"grad_norm": 0.5847039722347717,
"learning_rate": 5e-06,
"loss": 0.5485,
"step": 90
},
{
"epoch": 0.1100715465052284,
"grad_norm": 0.7554239910712166,
"learning_rate": 5e-06,
"loss": 0.5509,
"step": 100
},
{
"epoch": 0.12107870115575124,
"grad_norm": 0.66407741684268,
"learning_rate": 5e-06,
"loss": 0.5408,
"step": 110
},
{
"epoch": 0.13208585580627408,
"grad_norm": 0.8828744973826606,
"learning_rate": 5e-06,
"loss": 0.5454,
"step": 120
},
{
"epoch": 0.14309301045679693,
"grad_norm": 0.8332887833735565,
"learning_rate": 5e-06,
"loss": 0.547,
"step": 130
},
{
"epoch": 0.15410016510731975,
"grad_norm": 0.589582911422936,
"learning_rate": 5e-06,
"loss": 0.5355,
"step": 140
},
{
"epoch": 0.1651073197578426,
"grad_norm": 0.5752650409924749,
"learning_rate": 5e-06,
"loss": 0.5401,
"step": 150
},
{
"epoch": 0.17611447440836545,
"grad_norm": 0.6510988159474992,
"learning_rate": 5e-06,
"loss": 0.5382,
"step": 160
},
{
"epoch": 0.18712162905888827,
"grad_norm": 0.6600162733921413,
"learning_rate": 5e-06,
"loss": 0.5375,
"step": 170
},
{
"epoch": 0.19812878370941112,
"grad_norm": 0.7680493758340888,
"learning_rate": 5e-06,
"loss": 0.5293,
"step": 180
},
{
"epoch": 0.20913593835993396,
"grad_norm": 0.5886772247201477,
"learning_rate": 5e-06,
"loss": 0.529,
"step": 190
},
{
"epoch": 0.2201430930104568,
"grad_norm": 0.9873312548126073,
"learning_rate": 5e-06,
"loss": 0.5374,
"step": 200
},
{
"epoch": 0.23115024766097964,
"grad_norm": 0.6597424005720035,
"learning_rate": 5e-06,
"loss": 0.5244,
"step": 210
},
{
"epoch": 0.24215740231150248,
"grad_norm": 0.6487240352856705,
"learning_rate": 5e-06,
"loss": 0.5239,
"step": 220
},
{
"epoch": 0.25316455696202533,
"grad_norm": 0.5849183815528889,
"learning_rate": 5e-06,
"loss": 0.5208,
"step": 230
},
{
"epoch": 0.26417171161254815,
"grad_norm": 0.7002932795368584,
"learning_rate": 5e-06,
"loss": 0.5235,
"step": 240
},
{
"epoch": 0.275178866263071,
"grad_norm": 0.7692057600346355,
"learning_rate": 5e-06,
"loss": 0.5208,
"step": 250
},
{
"epoch": 0.28618602091359385,
"grad_norm": 0.6479188055510907,
"learning_rate": 5e-06,
"loss": 0.5221,
"step": 260
},
{
"epoch": 0.2971931755641167,
"grad_norm": 0.5960709917895178,
"learning_rate": 5e-06,
"loss": 0.5208,
"step": 270
},
{
"epoch": 0.3082003302146395,
"grad_norm": 0.6642753446042425,
"learning_rate": 5e-06,
"loss": 0.5197,
"step": 280
},
{
"epoch": 0.31920748486516237,
"grad_norm": 0.5612612572776104,
"learning_rate": 5e-06,
"loss": 0.5184,
"step": 290
},
{
"epoch": 0.3302146395156852,
"grad_norm": 0.6050955649607845,
"learning_rate": 5e-06,
"loss": 0.5212,
"step": 300
},
{
"epoch": 0.341221794166208,
"grad_norm": 0.6083727153184473,
"learning_rate": 5e-06,
"loss": 0.5184,
"step": 310
},
{
"epoch": 0.3522289488167309,
"grad_norm": 0.5945638816363161,
"learning_rate": 5e-06,
"loss": 0.5117,
"step": 320
},
{
"epoch": 0.3632361034672537,
"grad_norm": 0.5788925707542152,
"learning_rate": 5e-06,
"loss": 0.5168,
"step": 330
},
{
"epoch": 0.37424325811777653,
"grad_norm": 0.5651877110220476,
"learning_rate": 5e-06,
"loss": 0.5112,
"step": 340
},
{
"epoch": 0.3852504127682994,
"grad_norm": 0.5903776050613534,
"learning_rate": 5e-06,
"loss": 0.5093,
"step": 350
},
{
"epoch": 0.39625756741882223,
"grad_norm": 0.6395433132948327,
"learning_rate": 5e-06,
"loss": 0.5089,
"step": 360
},
{
"epoch": 0.40726472206934505,
"grad_norm": 0.6433507142958254,
"learning_rate": 5e-06,
"loss": 0.5119,
"step": 370
},
{
"epoch": 0.41827187671986793,
"grad_norm": 0.8112524575258614,
"learning_rate": 5e-06,
"loss": 0.5114,
"step": 380
},
{
"epoch": 0.42927903137039075,
"grad_norm": 0.5590784475229202,
"learning_rate": 5e-06,
"loss": 0.5099,
"step": 390
},
{
"epoch": 0.4402861860209136,
"grad_norm": 0.5742385149846626,
"learning_rate": 5e-06,
"loss": 0.5052,
"step": 400
},
{
"epoch": 0.45129334067143645,
"grad_norm": 0.5628215738544207,
"learning_rate": 5e-06,
"loss": 0.5101,
"step": 410
},
{
"epoch": 0.46230049532195927,
"grad_norm": 0.6019602301994744,
"learning_rate": 5e-06,
"loss": 0.5052,
"step": 420
},
{
"epoch": 0.4733076499724821,
"grad_norm": 0.6953045343066634,
"learning_rate": 5e-06,
"loss": 0.5071,
"step": 430
},
{
"epoch": 0.48431480462300497,
"grad_norm": 0.5819593216177834,
"learning_rate": 5e-06,
"loss": 0.5087,
"step": 440
},
{
"epoch": 0.4953219592735278,
"grad_norm": 0.6411981453679727,
"learning_rate": 5e-06,
"loss": 0.5037,
"step": 450
},
{
"epoch": 0.5063291139240507,
"grad_norm": 0.6349579201005676,
"learning_rate": 5e-06,
"loss": 0.5017,
"step": 460
},
{
"epoch": 0.5173362685745735,
"grad_norm": 0.5646584437790421,
"learning_rate": 5e-06,
"loss": 0.5027,
"step": 470
},
{
"epoch": 0.5283434232250963,
"grad_norm": 0.674711086918845,
"learning_rate": 5e-06,
"loss": 0.4956,
"step": 480
},
{
"epoch": 0.5393505778756191,
"grad_norm": 0.5072994063381644,
"learning_rate": 5e-06,
"loss": 0.508,
"step": 490
},
{
"epoch": 0.550357732526142,
"grad_norm": 0.585416024213119,
"learning_rate": 5e-06,
"loss": 0.5055,
"step": 500
},
{
"epoch": 0.5613648871766649,
"grad_norm": 0.5530035514034926,
"learning_rate": 5e-06,
"loss": 0.5039,
"step": 510
},
{
"epoch": 0.5723720418271877,
"grad_norm": 0.5538832120092045,
"learning_rate": 5e-06,
"loss": 0.4977,
"step": 520
},
{
"epoch": 0.5833791964777105,
"grad_norm": 0.6201922984553575,
"learning_rate": 5e-06,
"loss": 0.4998,
"step": 530
},
{
"epoch": 0.5943863511282333,
"grad_norm": 0.6430291554797398,
"learning_rate": 5e-06,
"loss": 0.5056,
"step": 540
},
{
"epoch": 0.6053935057787562,
"grad_norm": 0.6087664959789294,
"learning_rate": 5e-06,
"loss": 0.4987,
"step": 550
},
{
"epoch": 0.616400660429279,
"grad_norm": 0.5870342890959941,
"learning_rate": 5e-06,
"loss": 0.501,
"step": 560
},
{
"epoch": 0.6274078150798019,
"grad_norm": 0.5991431157137032,
"learning_rate": 5e-06,
"loss": 0.4962,
"step": 570
},
{
"epoch": 0.6384149697303247,
"grad_norm": 0.5967606556151732,
"learning_rate": 5e-06,
"loss": 0.4999,
"step": 580
},
{
"epoch": 0.6494221243808476,
"grad_norm": 0.5729038172611738,
"learning_rate": 5e-06,
"loss": 0.5039,
"step": 590
},
{
"epoch": 0.6604292790313704,
"grad_norm": 0.5505607805830717,
"learning_rate": 5e-06,
"loss": 0.4997,
"step": 600
},
{
"epoch": 0.6714364336818932,
"grad_norm": 0.5816855812426598,
"learning_rate": 5e-06,
"loss": 0.4953,
"step": 610
},
{
"epoch": 0.682443588332416,
"grad_norm": 0.5488625944674516,
"learning_rate": 5e-06,
"loss": 0.492,
"step": 620
},
{
"epoch": 0.693450742982939,
"grad_norm": 0.5614761187121621,
"learning_rate": 5e-06,
"loss": 0.4953,
"step": 630
},
{
"epoch": 0.7044578976334618,
"grad_norm": 0.5349325221018545,
"learning_rate": 5e-06,
"loss": 0.4889,
"step": 640
},
{
"epoch": 0.7154650522839846,
"grad_norm": 0.6719016887422193,
"learning_rate": 5e-06,
"loss": 0.5007,
"step": 650
},
{
"epoch": 0.7264722069345074,
"grad_norm": 0.6391959462190592,
"learning_rate": 5e-06,
"loss": 0.4938,
"step": 660
},
{
"epoch": 0.7374793615850302,
"grad_norm": 0.582953953743529,
"learning_rate": 5e-06,
"loss": 0.4999,
"step": 670
},
{
"epoch": 0.7484865162355531,
"grad_norm": 0.706306920990327,
"learning_rate": 5e-06,
"loss": 0.502,
"step": 680
},
{
"epoch": 0.759493670886076,
"grad_norm": 0.5848686111106695,
"learning_rate": 5e-06,
"loss": 0.4967,
"step": 690
},
{
"epoch": 0.7705008255365988,
"grad_norm": 0.6388534941572848,
"learning_rate": 5e-06,
"loss": 0.4927,
"step": 700
},
{
"epoch": 0.7815079801871216,
"grad_norm": 0.502841130639183,
"learning_rate": 5e-06,
"loss": 0.4896,
"step": 710
},
{
"epoch": 0.7925151348376445,
"grad_norm": 0.5461802758885927,
"learning_rate": 5e-06,
"loss": 0.4897,
"step": 720
},
{
"epoch": 0.8035222894881673,
"grad_norm": 0.5337214956421172,
"learning_rate": 5e-06,
"loss": 0.488,
"step": 730
},
{
"epoch": 0.8145294441386901,
"grad_norm": 0.5479459981678669,
"learning_rate": 5e-06,
"loss": 0.4934,
"step": 740
},
{
"epoch": 0.825536598789213,
"grad_norm": 0.518082392504643,
"learning_rate": 5e-06,
"loss": 0.4892,
"step": 750
},
{
"epoch": 0.8365437534397359,
"grad_norm": 0.5077982160853911,
"learning_rate": 5e-06,
"loss": 0.479,
"step": 760
},
{
"epoch": 0.8475509080902587,
"grad_norm": 0.55919091108616,
"learning_rate": 5e-06,
"loss": 0.4918,
"step": 770
},
{
"epoch": 0.8585580627407815,
"grad_norm": 0.5588406329671567,
"learning_rate": 5e-06,
"loss": 0.4936,
"step": 780
},
{
"epoch": 0.8695652173913043,
"grad_norm": 0.7100197464890179,
"learning_rate": 5e-06,
"loss": 0.4912,
"step": 790
},
{
"epoch": 0.8805723720418271,
"grad_norm": 0.6024300909723488,
"learning_rate": 5e-06,
"loss": 0.4874,
"step": 800
},
{
"epoch": 0.8915795266923501,
"grad_norm": 0.54622459399125,
"learning_rate": 5e-06,
"loss": 0.4898,
"step": 810
},
{
"epoch": 0.9025866813428729,
"grad_norm": 0.5233736919206922,
"learning_rate": 5e-06,
"loss": 0.4871,
"step": 820
},
{
"epoch": 0.9135938359933957,
"grad_norm": 0.5592995369334787,
"learning_rate": 5e-06,
"loss": 0.4874,
"step": 830
},
{
"epoch": 0.9246009906439185,
"grad_norm": 0.5287807518909434,
"learning_rate": 5e-06,
"loss": 0.4833,
"step": 840
},
{
"epoch": 0.9356081452944414,
"grad_norm": 0.5665869814810643,
"learning_rate": 5e-06,
"loss": 0.4854,
"step": 850
},
{
"epoch": 0.9466152999449642,
"grad_norm": 0.6023708712875594,
"learning_rate": 5e-06,
"loss": 0.4891,
"step": 860
},
{
"epoch": 0.9576224545954871,
"grad_norm": 0.6417033949225462,
"learning_rate": 5e-06,
"loss": 0.486,
"step": 870
},
{
"epoch": 0.9686296092460099,
"grad_norm": 0.5609342094974721,
"learning_rate": 5e-06,
"loss": 0.4865,
"step": 880
},
{
"epoch": 0.9796367638965328,
"grad_norm": 0.5141037922481443,
"learning_rate": 5e-06,
"loss": 0.487,
"step": 890
},
{
"epoch": 0.9906439185470556,
"grad_norm": 0.5249034479981126,
"learning_rate": 5e-06,
"loss": 0.4816,
"step": 900
},
{
"epoch": 0.9994496422674739,
"eval_loss": 0.4856513738632202,
"eval_runtime": 160.5131,
"eval_samples_per_second": 152.455,
"eval_steps_per_second": 0.598,
"step": 908
},
{
"epoch": 1.0016510731975785,
"grad_norm": 0.6956883866215322,
"learning_rate": 5e-06,
"loss": 0.481,
"step": 910
},
{
"epoch": 1.0126582278481013,
"grad_norm": 0.6716400752129513,
"learning_rate": 5e-06,
"loss": 0.4391,
"step": 920
},
{
"epoch": 1.0236653824986242,
"grad_norm": 0.6047593389115262,
"learning_rate": 5e-06,
"loss": 0.4375,
"step": 930
},
{
"epoch": 1.034672537149147,
"grad_norm": 0.587176642351734,
"learning_rate": 5e-06,
"loss": 0.4384,
"step": 940
},
{
"epoch": 1.0456796917996698,
"grad_norm": 0.6603546276646723,
"learning_rate": 5e-06,
"loss": 0.4369,
"step": 950
},
{
"epoch": 1.0566868464501926,
"grad_norm": 0.6689012217240984,
"learning_rate": 5e-06,
"loss": 0.4355,
"step": 960
},
{
"epoch": 1.0676940011007154,
"grad_norm": 0.7144569165196396,
"learning_rate": 5e-06,
"loss": 0.4355,
"step": 970
},
{
"epoch": 1.0787011557512383,
"grad_norm": 0.599379629228571,
"learning_rate": 5e-06,
"loss": 0.438,
"step": 980
},
{
"epoch": 1.089708310401761,
"grad_norm": 0.6661285634082297,
"learning_rate": 5e-06,
"loss": 0.4382,
"step": 990
},
{
"epoch": 1.100715465052284,
"grad_norm": 0.5873001825359626,
"learning_rate": 5e-06,
"loss": 0.4402,
"step": 1000
},
{
"epoch": 1.1117226197028067,
"grad_norm": 0.5874126889355209,
"learning_rate": 5e-06,
"loss": 0.4369,
"step": 1010
},
{
"epoch": 1.1227297743533298,
"grad_norm": 0.5917778529211078,
"learning_rate": 5e-06,
"loss": 0.4343,
"step": 1020
},
{
"epoch": 1.1337369290038526,
"grad_norm": 0.663635902953046,
"learning_rate": 5e-06,
"loss": 0.4407,
"step": 1030
},
{
"epoch": 1.1447440836543754,
"grad_norm": 0.5893496665741478,
"learning_rate": 5e-06,
"loss": 0.438,
"step": 1040
},
{
"epoch": 1.1557512383048982,
"grad_norm": 0.5717519892394852,
"learning_rate": 5e-06,
"loss": 0.4382,
"step": 1050
},
{
"epoch": 1.166758392955421,
"grad_norm": 0.575957675659784,
"learning_rate": 5e-06,
"loss": 0.442,
"step": 1060
},
{
"epoch": 1.1777655476059439,
"grad_norm": 0.5392139913019496,
"learning_rate": 5e-06,
"loss": 0.4338,
"step": 1070
},
{
"epoch": 1.1887727022564667,
"grad_norm": 0.5544306944478229,
"learning_rate": 5e-06,
"loss": 0.435,
"step": 1080
},
{
"epoch": 1.1997798569069895,
"grad_norm": 0.5778227037188679,
"learning_rate": 5e-06,
"loss": 0.4422,
"step": 1090
},
{
"epoch": 1.2107870115575123,
"grad_norm": 0.641697858461983,
"learning_rate": 5e-06,
"loss": 0.4372,
"step": 1100
},
{
"epoch": 1.2217941662080352,
"grad_norm": 0.5569895073916331,
"learning_rate": 5e-06,
"loss": 0.4321,
"step": 1110
},
{
"epoch": 1.232801320858558,
"grad_norm": 0.6241092113262656,
"learning_rate": 5e-06,
"loss": 0.439,
"step": 1120
},
{
"epoch": 1.243808475509081,
"grad_norm": 0.5943410374097372,
"learning_rate": 5e-06,
"loss": 0.4391,
"step": 1130
},
{
"epoch": 1.2548156301596038,
"grad_norm": 0.5836266123327419,
"learning_rate": 5e-06,
"loss": 0.4358,
"step": 1140
},
{
"epoch": 1.2658227848101267,
"grad_norm": 0.5894554462945597,
"learning_rate": 5e-06,
"loss": 0.4357,
"step": 1150
},
{
"epoch": 1.2768299394606495,
"grad_norm": 0.6101160325711262,
"learning_rate": 5e-06,
"loss": 0.4377,
"step": 1160
},
{
"epoch": 1.2878370941111723,
"grad_norm": 0.5499163190785714,
"learning_rate": 5e-06,
"loss": 0.4373,
"step": 1170
},
{
"epoch": 1.2988442487616951,
"grad_norm": 0.6570888233134892,
"learning_rate": 5e-06,
"loss": 0.4397,
"step": 1180
},
{
"epoch": 1.309851403412218,
"grad_norm": 0.5781370179708198,
"learning_rate": 5e-06,
"loss": 0.4317,
"step": 1190
},
{
"epoch": 1.3208585580627408,
"grad_norm": 0.5960093131033088,
"learning_rate": 5e-06,
"loss": 0.4388,
"step": 1200
},
{
"epoch": 1.3318657127132636,
"grad_norm": 0.5319356526638459,
"learning_rate": 5e-06,
"loss": 0.4296,
"step": 1210
},
{
"epoch": 1.3428728673637864,
"grad_norm": 0.6078975655308353,
"learning_rate": 5e-06,
"loss": 0.4399,
"step": 1220
},
{
"epoch": 1.3538800220143092,
"grad_norm": 0.5734565496131863,
"learning_rate": 5e-06,
"loss": 0.4364,
"step": 1230
},
{
"epoch": 1.364887176664832,
"grad_norm": 0.5839075048236241,
"learning_rate": 5e-06,
"loss": 0.4379,
"step": 1240
},
{
"epoch": 1.3758943313153549,
"grad_norm": 0.522698955157226,
"learning_rate": 5e-06,
"loss": 0.4417,
"step": 1250
},
{
"epoch": 1.3869014859658777,
"grad_norm": 0.535233080984122,
"learning_rate": 5e-06,
"loss": 0.44,
"step": 1260
},
{
"epoch": 1.3979086406164005,
"grad_norm": 0.5712349249996552,
"learning_rate": 5e-06,
"loss": 0.438,
"step": 1270
},
{
"epoch": 1.4089157952669236,
"grad_norm": 0.6316823548805974,
"learning_rate": 5e-06,
"loss": 0.4354,
"step": 1280
},
{
"epoch": 1.4199229499174464,
"grad_norm": 0.5521497995059079,
"learning_rate": 5e-06,
"loss": 0.4364,
"step": 1290
},
{
"epoch": 1.4309301045679692,
"grad_norm": 0.5287580252903409,
"learning_rate": 5e-06,
"loss": 0.433,
"step": 1300
},
{
"epoch": 1.441937259218492,
"grad_norm": 0.5402910458762741,
"learning_rate": 5e-06,
"loss": 0.4305,
"step": 1310
},
{
"epoch": 1.4529444138690149,
"grad_norm": 0.571274228135471,
"learning_rate": 5e-06,
"loss": 0.4372,
"step": 1320
},
{
"epoch": 1.4639515685195377,
"grad_norm": 0.5793180531222271,
"learning_rate": 5e-06,
"loss": 0.4317,
"step": 1330
},
{
"epoch": 1.4749587231700605,
"grad_norm": 0.5325510509092749,
"learning_rate": 5e-06,
"loss": 0.4393,
"step": 1340
},
{
"epoch": 1.4859658778205833,
"grad_norm": 0.594212182934655,
"learning_rate": 5e-06,
"loss": 0.4341,
"step": 1350
},
{
"epoch": 1.4969730324711064,
"grad_norm": 0.5712922063753643,
"learning_rate": 5e-06,
"loss": 0.4356,
"step": 1360
},
{
"epoch": 1.5079801871216292,
"grad_norm": 0.5274575368185872,
"learning_rate": 5e-06,
"loss": 0.4362,
"step": 1370
},
{
"epoch": 1.518987341772152,
"grad_norm": 0.5748764141955885,
"learning_rate": 5e-06,
"loss": 0.4382,
"step": 1380
},
{
"epoch": 1.5299944964226748,
"grad_norm": 0.5317801238843131,
"learning_rate": 5e-06,
"loss": 0.4273,
"step": 1390
},
{
"epoch": 1.5410016510731976,
"grad_norm": 0.551025561769828,
"learning_rate": 5e-06,
"loss": 0.4299,
"step": 1400
},
{
"epoch": 1.5520088057237205,
"grad_norm": 0.5944333674783141,
"learning_rate": 5e-06,
"loss": 0.4341,
"step": 1410
},
{
"epoch": 1.5630159603742433,
"grad_norm": 0.5788961613724642,
"learning_rate": 5e-06,
"loss": 0.4365,
"step": 1420
},
{
"epoch": 1.574023115024766,
"grad_norm": 0.5966888415992487,
"learning_rate": 5e-06,
"loss": 0.4351,
"step": 1430
},
{
"epoch": 1.585030269675289,
"grad_norm": 0.6442673539124382,
"learning_rate": 5e-06,
"loss": 0.4331,
"step": 1440
},
{
"epoch": 1.5960374243258117,
"grad_norm": 0.5537070014925163,
"learning_rate": 5e-06,
"loss": 0.4292,
"step": 1450
},
{
"epoch": 1.6070445789763346,
"grad_norm": 0.5708459825871977,
"learning_rate": 5e-06,
"loss": 0.4366,
"step": 1460
},
{
"epoch": 1.6180517336268574,
"grad_norm": 0.6397589448051699,
"learning_rate": 5e-06,
"loss": 0.4361,
"step": 1470
},
{
"epoch": 1.6290588882773802,
"grad_norm": 0.5719729721108842,
"learning_rate": 5e-06,
"loss": 0.4308,
"step": 1480
},
{
"epoch": 1.640066042927903,
"grad_norm": 0.5856092164801038,
"learning_rate": 5e-06,
"loss": 0.4312,
"step": 1490
},
{
"epoch": 1.6510731975784259,
"grad_norm": 0.5381801632251061,
"learning_rate": 5e-06,
"loss": 0.4332,
"step": 1500
},
{
"epoch": 1.6620803522289487,
"grad_norm": 0.5722118916397197,
"learning_rate": 5e-06,
"loss": 0.4329,
"step": 1510
},
{
"epoch": 1.6730875068794715,
"grad_norm": 0.522035618728827,
"learning_rate": 5e-06,
"loss": 0.4323,
"step": 1520
},
{
"epoch": 1.6840946615299945,
"grad_norm": 0.6205447482549835,
"learning_rate": 5e-06,
"loss": 0.4364,
"step": 1530
},
{
"epoch": 1.6951018161805174,
"grad_norm": 0.5443426263583215,
"learning_rate": 5e-06,
"loss": 0.4313,
"step": 1540
},
{
"epoch": 1.7061089708310402,
"grad_norm": 0.5386063701750604,
"learning_rate": 5e-06,
"loss": 0.4307,
"step": 1550
},
{
"epoch": 1.717116125481563,
"grad_norm": 0.6361585672978718,
"learning_rate": 5e-06,
"loss": 0.4353,
"step": 1560
},
{
"epoch": 1.7281232801320858,
"grad_norm": 0.6614840484986904,
"learning_rate": 5e-06,
"loss": 0.4328,
"step": 1570
},
{
"epoch": 1.7391304347826086,
"grad_norm": 0.570381119642231,
"learning_rate": 5e-06,
"loss": 0.4287,
"step": 1580
},
{
"epoch": 1.7501375894331317,
"grad_norm": 0.5090274244717806,
"learning_rate": 5e-06,
"loss": 0.4362,
"step": 1590
},
{
"epoch": 1.7611447440836545,
"grad_norm": 0.5446091771702728,
"learning_rate": 5e-06,
"loss": 0.4295,
"step": 1600
},
{
"epoch": 1.7721518987341773,
"grad_norm": 0.5647817172552334,
"learning_rate": 5e-06,
"loss": 0.4298,
"step": 1610
},
{
"epoch": 1.7831590533847002,
"grad_norm": 0.5140154798513348,
"learning_rate": 5e-06,
"loss": 0.4298,
"step": 1620
},
{
"epoch": 1.794166208035223,
"grad_norm": 0.5079001883970996,
"learning_rate": 5e-06,
"loss": 0.4317,
"step": 1630
},
{
"epoch": 1.8051733626857458,
"grad_norm": 0.5716780327717556,
"learning_rate": 5e-06,
"loss": 0.4335,
"step": 1640
},
{
"epoch": 1.8161805173362686,
"grad_norm": 0.5594834856156328,
"learning_rate": 5e-06,
"loss": 0.4369,
"step": 1650
},
{
"epoch": 1.8271876719867914,
"grad_norm": 0.5690421305195432,
"learning_rate": 5e-06,
"loss": 0.4372,
"step": 1660
},
{
"epoch": 1.8381948266373143,
"grad_norm": 0.5815766701653886,
"learning_rate": 5e-06,
"loss": 0.4268,
"step": 1670
},
{
"epoch": 1.849201981287837,
"grad_norm": 0.5370753144522138,
"learning_rate": 5e-06,
"loss": 0.4296,
"step": 1680
},
{
"epoch": 1.86020913593836,
"grad_norm": 0.537889959924609,
"learning_rate": 5e-06,
"loss": 0.4359,
"step": 1690
},
{
"epoch": 1.8712162905888827,
"grad_norm": 0.5542910246512667,
"learning_rate": 5e-06,
"loss": 0.438,
"step": 1700
},
{
"epoch": 1.8822234452394055,
"grad_norm": 0.5307067513174616,
"learning_rate": 5e-06,
"loss": 0.4312,
"step": 1710
},
{
"epoch": 1.8932305998899284,
"grad_norm": 0.6185255098388331,
"learning_rate": 5e-06,
"loss": 0.4336,
"step": 1720
},
{
"epoch": 1.9042377545404512,
"grad_norm": 0.6105302991591885,
"learning_rate": 5e-06,
"loss": 0.4296,
"step": 1730
},
{
"epoch": 1.915244909190974,
"grad_norm": 0.5505132542181409,
"learning_rate": 5e-06,
"loss": 0.4305,
"step": 1740
},
{
"epoch": 1.9262520638414968,
"grad_norm": 0.5987936899025984,
"learning_rate": 5e-06,
"loss": 0.4293,
"step": 1750
},
{
"epoch": 1.9372592184920197,
"grad_norm": 0.5243332176781547,
"learning_rate": 5e-06,
"loss": 0.4273,
"step": 1760
},
{
"epoch": 1.9482663731425427,
"grad_norm": 0.5649987091504026,
"learning_rate": 5e-06,
"loss": 0.4303,
"step": 1770
},
{
"epoch": 1.9592735277930655,
"grad_norm": 0.5698314583015734,
"learning_rate": 5e-06,
"loss": 0.4276,
"step": 1780
},
{
"epoch": 1.9702806824435883,
"grad_norm": 0.5541608664959677,
"learning_rate": 5e-06,
"loss": 0.43,
"step": 1790
},
{
"epoch": 1.9812878370941112,
"grad_norm": 0.530973092247837,
"learning_rate": 5e-06,
"loss": 0.4291,
"step": 1800
},
{
"epoch": 1.992294991744634,
"grad_norm": 0.5385780053649944,
"learning_rate": 5e-06,
"loss": 0.4296,
"step": 1810
},
{
"epoch": 2.0,
"eval_loss": 0.4724336564540863,
"eval_runtime": 160.867,
"eval_samples_per_second": 152.119,
"eval_steps_per_second": 0.597,
"step": 1817
},
{
"epoch": 2.003302146395157,
"grad_norm": 0.8967320351826643,
"learning_rate": 5e-06,
"loss": 0.4165,
"step": 1820
},
{
"epoch": 2.01430930104568,
"grad_norm": 0.6842852006791557,
"learning_rate": 5e-06,
"loss": 0.379,
"step": 1830
},
{
"epoch": 2.0253164556962027,
"grad_norm": 0.6497861759455246,
"learning_rate": 5e-06,
"loss": 0.3769,
"step": 1840
},
{
"epoch": 2.0363236103467255,
"grad_norm": 0.5695788867941572,
"learning_rate": 5e-06,
"loss": 0.3732,
"step": 1850
},
{
"epoch": 2.0473307649972483,
"grad_norm": 0.6311590318430164,
"learning_rate": 5e-06,
"loss": 0.379,
"step": 1860
},
{
"epoch": 2.058337919647771,
"grad_norm": 0.5735473186308736,
"learning_rate": 5e-06,
"loss": 0.3792,
"step": 1870
},
{
"epoch": 2.069345074298294,
"grad_norm": 0.6568929190707151,
"learning_rate": 5e-06,
"loss": 0.379,
"step": 1880
},
{
"epoch": 2.0803522289488168,
"grad_norm": 0.6518588834467927,
"learning_rate": 5e-06,
"loss": 0.378,
"step": 1890
},
{
"epoch": 2.0913593835993396,
"grad_norm": 0.6236301216107463,
"learning_rate": 5e-06,
"loss": 0.3776,
"step": 1900
},
{
"epoch": 2.1023665382498624,
"grad_norm": 0.6771820085707594,
"learning_rate": 5e-06,
"loss": 0.3737,
"step": 1910
},
{
"epoch": 2.1133736929003852,
"grad_norm": 0.6959842658376467,
"learning_rate": 5e-06,
"loss": 0.3772,
"step": 1920
},
{
"epoch": 2.124380847550908,
"grad_norm": 0.5691873810072571,
"learning_rate": 5e-06,
"loss": 0.3701,
"step": 1930
},
{
"epoch": 2.135388002201431,
"grad_norm": 0.587230812890123,
"learning_rate": 5e-06,
"loss": 0.3757,
"step": 1940
},
{
"epoch": 2.1463951568519537,
"grad_norm": 0.5676645980467607,
"learning_rate": 5e-06,
"loss": 0.375,
"step": 1950
},
{
"epoch": 2.1574023115024765,
"grad_norm": 0.5674195737996316,
"learning_rate": 5e-06,
"loss": 0.3814,
"step": 1960
},
{
"epoch": 2.1684094661529993,
"grad_norm": 0.5803828928264857,
"learning_rate": 5e-06,
"loss": 0.3744,
"step": 1970
},
{
"epoch": 2.179416620803522,
"grad_norm": 0.6171592569899994,
"learning_rate": 5e-06,
"loss": 0.3741,
"step": 1980
},
{
"epoch": 2.190423775454045,
"grad_norm": 0.658582470951269,
"learning_rate": 5e-06,
"loss": 0.378,
"step": 1990
},
{
"epoch": 2.201430930104568,
"grad_norm": 0.6562283922269005,
"learning_rate": 5e-06,
"loss": 0.3769,
"step": 2000
},
{
"epoch": 2.2124380847550906,
"grad_norm": 0.635240231582788,
"learning_rate": 5e-06,
"loss": 0.3775,
"step": 2010
},
{
"epoch": 2.2234452394056134,
"grad_norm": 0.6551353354672024,
"learning_rate": 5e-06,
"loss": 0.3809,
"step": 2020
},
{
"epoch": 2.2344523940561363,
"grad_norm": 0.5807020804645606,
"learning_rate": 5e-06,
"loss": 0.3741,
"step": 2030
},
{
"epoch": 2.2454595487066595,
"grad_norm": 0.6317711733432692,
"learning_rate": 5e-06,
"loss": 0.3811,
"step": 2040
},
{
"epoch": 2.2564667033571824,
"grad_norm": 0.5590373084758273,
"learning_rate": 5e-06,
"loss": 0.3759,
"step": 2050
},
{
"epoch": 2.267473858007705,
"grad_norm": 0.5529922073969795,
"learning_rate": 5e-06,
"loss": 0.3777,
"step": 2060
},
{
"epoch": 2.278481012658228,
"grad_norm": 0.6310391701743894,
"learning_rate": 5e-06,
"loss": 0.3809,
"step": 2070
},
{
"epoch": 2.289488167308751,
"grad_norm": 0.5608628930620043,
"learning_rate": 5e-06,
"loss": 0.3748,
"step": 2080
},
{
"epoch": 2.3004953219592736,
"grad_norm": 0.596887560066522,
"learning_rate": 5e-06,
"loss": 0.3774,
"step": 2090
},
{
"epoch": 2.3115024766097965,
"grad_norm": 0.7051450098820579,
"learning_rate": 5e-06,
"loss": 0.3802,
"step": 2100
},
{
"epoch": 2.3225096312603193,
"grad_norm": 0.6327972937976852,
"learning_rate": 5e-06,
"loss": 0.3835,
"step": 2110
},
{
"epoch": 2.333516785910842,
"grad_norm": 0.6126330718992958,
"learning_rate": 5e-06,
"loss": 0.378,
"step": 2120
},
{
"epoch": 2.344523940561365,
"grad_norm": 0.6036183605384906,
"learning_rate": 5e-06,
"loss": 0.378,
"step": 2130
},
{
"epoch": 2.3555310952118877,
"grad_norm": 0.6690011983226686,
"learning_rate": 5e-06,
"loss": 0.3854,
"step": 2140
},
{
"epoch": 2.3665382498624106,
"grad_norm": 0.6167807719553883,
"learning_rate": 5e-06,
"loss": 0.3818,
"step": 2150
},
{
"epoch": 2.3775454045129334,
"grad_norm": 0.5936760728734222,
"learning_rate": 5e-06,
"loss": 0.3818,
"step": 2160
},
{
"epoch": 2.388552559163456,
"grad_norm": 0.6122872538963571,
"learning_rate": 5e-06,
"loss": 0.3772,
"step": 2170
},
{
"epoch": 2.399559713813979,
"grad_norm": 0.6544080290873076,
"learning_rate": 5e-06,
"loss": 0.3811,
"step": 2180
},
{
"epoch": 2.410566868464502,
"grad_norm": 0.6449188335513784,
"learning_rate": 5e-06,
"loss": 0.3783,
"step": 2190
},
{
"epoch": 2.4215740231150247,
"grad_norm": 0.7022837872059463,
"learning_rate": 5e-06,
"loss": 0.3793,
"step": 2200
},
{
"epoch": 2.4325811777655475,
"grad_norm": 0.7249310561789513,
"learning_rate": 5e-06,
"loss": 0.3803,
"step": 2210
},
{
"epoch": 2.4435883324160703,
"grad_norm": 0.6971979338410507,
"learning_rate": 5e-06,
"loss": 0.3788,
"step": 2220
},
{
"epoch": 2.454595487066593,
"grad_norm": 0.7707114044625848,
"learning_rate": 5e-06,
"loss": 0.3817,
"step": 2230
},
{
"epoch": 2.465602641717116,
"grad_norm": 0.6434741663311266,
"learning_rate": 5e-06,
"loss": 0.3778,
"step": 2240
},
{
"epoch": 2.476609796367639,
"grad_norm": 0.5911942930693944,
"learning_rate": 5e-06,
"loss": 0.3805,
"step": 2250
},
{
"epoch": 2.487616951018162,
"grad_norm": 0.570304109670699,
"learning_rate": 5e-06,
"loss": 0.3805,
"step": 2260
},
{
"epoch": 2.498624105668685,
"grad_norm": 0.5925907114220025,
"learning_rate": 5e-06,
"loss": 0.3779,
"step": 2270
},
{
"epoch": 2.5096312603192077,
"grad_norm": 0.6612757174277469,
"learning_rate": 5e-06,
"loss": 0.3818,
"step": 2280
},
{
"epoch": 2.5206384149697305,
"grad_norm": 0.6067689054978976,
"learning_rate": 5e-06,
"loss": 0.3774,
"step": 2290
},
{
"epoch": 2.5316455696202533,
"grad_norm": 0.5874728722311394,
"learning_rate": 5e-06,
"loss": 0.3787,
"step": 2300
},
{
"epoch": 2.542652724270776,
"grad_norm": 0.662103385837326,
"learning_rate": 5e-06,
"loss": 0.3826,
"step": 2310
},
{
"epoch": 2.553659878921299,
"grad_norm": 0.6026661354255178,
"learning_rate": 5e-06,
"loss": 0.3825,
"step": 2320
},
{
"epoch": 2.564667033571822,
"grad_norm": 0.5787785406337395,
"learning_rate": 5e-06,
"loss": 0.3794,
"step": 2330
},
{
"epoch": 2.5756741882223446,
"grad_norm": 0.5514615800252736,
"learning_rate": 5e-06,
"loss": 0.38,
"step": 2340
},
{
"epoch": 2.5866813428728674,
"grad_norm": 0.5961731505130763,
"learning_rate": 5e-06,
"loss": 0.3782,
"step": 2350
},
{
"epoch": 2.5976884975233903,
"grad_norm": 0.5893895677043864,
"learning_rate": 5e-06,
"loss": 0.3839,
"step": 2360
},
{
"epoch": 2.608695652173913,
"grad_norm": 0.5859569035794123,
"learning_rate": 5e-06,
"loss": 0.3834,
"step": 2370
},
{
"epoch": 2.619702806824436,
"grad_norm": 0.5997751859191552,
"learning_rate": 5e-06,
"loss": 0.3768,
"step": 2380
},
{
"epoch": 2.6307099614749587,
"grad_norm": 0.6368216879726575,
"learning_rate": 5e-06,
"loss": 0.3809,
"step": 2390
},
{
"epoch": 2.6417171161254815,
"grad_norm": 0.5877707286837056,
"learning_rate": 5e-06,
"loss": 0.379,
"step": 2400
},
{
"epoch": 2.6527242707760044,
"grad_norm": 0.5430913424974279,
"learning_rate": 5e-06,
"loss": 0.3794,
"step": 2410
},
{
"epoch": 2.663731425426527,
"grad_norm": 0.6318440202771097,
"learning_rate": 5e-06,
"loss": 0.3776,
"step": 2420
},
{
"epoch": 2.67473858007705,
"grad_norm": 0.659647040239042,
"learning_rate": 5e-06,
"loss": 0.3809,
"step": 2430
},
{
"epoch": 2.685745734727573,
"grad_norm": 0.6377513270884255,
"learning_rate": 5e-06,
"loss": 0.379,
"step": 2440
},
{
"epoch": 2.6967528893780957,
"grad_norm": 0.6437694613754824,
"learning_rate": 5e-06,
"loss": 0.3777,
"step": 2450
},
{
"epoch": 2.7077600440286185,
"grad_norm": 0.6227150600183708,
"learning_rate": 5e-06,
"loss": 0.381,
"step": 2460
},
{
"epoch": 2.7187671986791413,
"grad_norm": 0.6074943535217816,
"learning_rate": 5e-06,
"loss": 0.3829,
"step": 2470
},
{
"epoch": 2.729774353329664,
"grad_norm": 0.6059099193970705,
"learning_rate": 5e-06,
"loss": 0.3798,
"step": 2480
},
{
"epoch": 2.740781507980187,
"grad_norm": 0.5639872940942946,
"learning_rate": 5e-06,
"loss": 0.3803,
"step": 2490
},
{
"epoch": 2.7517886626307098,
"grad_norm": 0.6138763737267989,
"learning_rate": 5e-06,
"loss": 0.3836,
"step": 2500
},
{
"epoch": 2.7627958172812326,
"grad_norm": 0.6174392484182389,
"learning_rate": 5e-06,
"loss": 0.3771,
"step": 2510
},
{
"epoch": 2.7738029719317554,
"grad_norm": 0.5813465334873451,
"learning_rate": 5e-06,
"loss": 0.3832,
"step": 2520
},
{
"epoch": 2.7848101265822782,
"grad_norm": 0.5939709459181249,
"learning_rate": 5e-06,
"loss": 0.3758,
"step": 2530
},
{
"epoch": 2.795817281232801,
"grad_norm": 0.6100879294250667,
"learning_rate": 5e-06,
"loss": 0.3846,
"step": 2540
},
{
"epoch": 2.8068244358833243,
"grad_norm": 0.5849829885439275,
"learning_rate": 5e-06,
"loss": 0.3805,
"step": 2550
},
{
"epoch": 2.817831590533847,
"grad_norm": 0.614871493034729,
"learning_rate": 5e-06,
"loss": 0.3814,
"step": 2560
},
{
"epoch": 2.82883874518437,
"grad_norm": 0.5972503634442111,
"learning_rate": 5e-06,
"loss": 0.3833,
"step": 2570
},
{
"epoch": 2.8398458998348928,
"grad_norm": 0.7445333487223286,
"learning_rate": 5e-06,
"loss": 0.3785,
"step": 2580
},
{
"epoch": 2.8508530544854156,
"grad_norm": 0.622730774203719,
"learning_rate": 5e-06,
"loss": 0.3791,
"step": 2590
},
{
"epoch": 2.8618602091359384,
"grad_norm": 0.6588152521106931,
"learning_rate": 5e-06,
"loss": 0.3771,
"step": 2600
},
{
"epoch": 2.8728673637864612,
"grad_norm": 0.6021676282902743,
"learning_rate": 5e-06,
"loss": 0.3814,
"step": 2610
},
{
"epoch": 2.883874518436984,
"grad_norm": 0.5852769901706747,
"learning_rate": 5e-06,
"loss": 0.3879,
"step": 2620
},
{
"epoch": 2.894881673087507,
"grad_norm": 0.6163235754681848,
"learning_rate": 5e-06,
"loss": 0.3756,
"step": 2630
},
{
"epoch": 2.9058888277380297,
"grad_norm": 0.6116839094719151,
"learning_rate": 5e-06,
"loss": 0.3791,
"step": 2640
},
{
"epoch": 2.9168959823885525,
"grad_norm": 0.5676400582470854,
"learning_rate": 5e-06,
"loss": 0.383,
"step": 2650
},
{
"epoch": 2.9279031370390753,
"grad_norm": 0.6768408000572769,
"learning_rate": 5e-06,
"loss": 0.3838,
"step": 2660
},
{
"epoch": 2.938910291689598,
"grad_norm": 0.6506353755745358,
"learning_rate": 5e-06,
"loss": 0.3805,
"step": 2670
},
{
"epoch": 2.949917446340121,
"grad_norm": 0.5611923951294836,
"learning_rate": 5e-06,
"loss": 0.379,
"step": 2680
},
{
"epoch": 2.960924600990644,
"grad_norm": 0.5857791831118236,
"learning_rate": 5e-06,
"loss": 0.3779,
"step": 2690
},
{
"epoch": 2.9719317556411666,
"grad_norm": 0.5961118998765907,
"learning_rate": 5e-06,
"loss": 0.3791,
"step": 2700
},
{
"epoch": 2.9829389102916894,
"grad_norm": 0.6132753371779015,
"learning_rate": 5e-06,
"loss": 0.377,
"step": 2710
},
{
"epoch": 2.9939460649422127,
"grad_norm": 0.5713537011568807,
"learning_rate": 5e-06,
"loss": 0.3803,
"step": 2720
},
{
"epoch": 2.9983489268024215,
"eval_loss": 0.47213879227638245,
"eval_runtime": 158.6207,
"eval_samples_per_second": 154.274,
"eval_steps_per_second": 0.605,
"step": 2724
},
{
"epoch": 2.9983489268024215,
"step": 2724,
"total_flos": 4561963937955840.0,
"train_loss": 0.44294929530652083,
"train_runtime": 23449.9729,
"train_samples_per_second": 59.48,
"train_steps_per_second": 0.116
}
],
"logging_steps": 10,
"max_steps": 2724,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 4561963937955840.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}