llama3-1_8b_dcft-it / trainer_state.json
gsmyrnis's picture
End of training
19eae51 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 4665,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006430868167202572,
"grad_norm": 4.730106830596924,
"learning_rate": 5e-06,
"loss": 0.8965,
"step": 10
},
{
"epoch": 0.012861736334405145,
"grad_norm": 2.0916528701782227,
"learning_rate": 5e-06,
"loss": 0.8501,
"step": 20
},
{
"epoch": 0.01929260450160772,
"grad_norm": 0.8616329431533813,
"learning_rate": 5e-06,
"loss": 0.8318,
"step": 30
},
{
"epoch": 0.02572347266881029,
"grad_norm": 0.7073356509208679,
"learning_rate": 5e-06,
"loss": 0.8193,
"step": 40
},
{
"epoch": 0.03215434083601286,
"grad_norm": 1.3553227186203003,
"learning_rate": 5e-06,
"loss": 0.8094,
"step": 50
},
{
"epoch": 0.03858520900321544,
"grad_norm": 0.6813921928405762,
"learning_rate": 5e-06,
"loss": 0.8042,
"step": 60
},
{
"epoch": 0.04501607717041801,
"grad_norm": 1.011812448501587,
"learning_rate": 5e-06,
"loss": 0.7912,
"step": 70
},
{
"epoch": 0.05144694533762058,
"grad_norm": 2.1421170234680176,
"learning_rate": 5e-06,
"loss": 0.7894,
"step": 80
},
{
"epoch": 0.05787781350482315,
"grad_norm": 1.2183887958526611,
"learning_rate": 5e-06,
"loss": 0.7799,
"step": 90
},
{
"epoch": 0.06430868167202572,
"grad_norm": 1.1371192932128906,
"learning_rate": 5e-06,
"loss": 0.7832,
"step": 100
},
{
"epoch": 0.0707395498392283,
"grad_norm": 1.3382622003555298,
"learning_rate": 5e-06,
"loss": 0.7791,
"step": 110
},
{
"epoch": 0.07717041800643087,
"grad_norm": 0.6512683629989624,
"learning_rate": 5e-06,
"loss": 0.7784,
"step": 120
},
{
"epoch": 0.08360128617363344,
"grad_norm": 0.632128894329071,
"learning_rate": 5e-06,
"loss": 0.7665,
"step": 130
},
{
"epoch": 0.09003215434083602,
"grad_norm": 0.4840221405029297,
"learning_rate": 5e-06,
"loss": 0.7643,
"step": 140
},
{
"epoch": 0.09646302250803858,
"grad_norm": 0.5068333745002747,
"learning_rate": 5e-06,
"loss": 0.7772,
"step": 150
},
{
"epoch": 0.10289389067524116,
"grad_norm": 0.5646687150001526,
"learning_rate": 5e-06,
"loss": 0.7679,
"step": 160
},
{
"epoch": 0.10932475884244373,
"grad_norm": 0.9486843943595886,
"learning_rate": 5e-06,
"loss": 0.7724,
"step": 170
},
{
"epoch": 0.1157556270096463,
"grad_norm": 0.5386438369750977,
"learning_rate": 5e-06,
"loss": 0.7615,
"step": 180
},
{
"epoch": 0.12218649517684887,
"grad_norm": 0.7876360416412354,
"learning_rate": 5e-06,
"loss": 0.767,
"step": 190
},
{
"epoch": 0.12861736334405144,
"grad_norm": 0.5463624596595764,
"learning_rate": 5e-06,
"loss": 0.7666,
"step": 200
},
{
"epoch": 0.13504823151125403,
"grad_norm": 0.7764928340911865,
"learning_rate": 5e-06,
"loss": 0.7564,
"step": 210
},
{
"epoch": 0.1414790996784566,
"grad_norm": 0.8027799725532532,
"learning_rate": 5e-06,
"loss": 0.7546,
"step": 220
},
{
"epoch": 0.14790996784565916,
"grad_norm": 1.3793781995773315,
"learning_rate": 5e-06,
"loss": 0.7597,
"step": 230
},
{
"epoch": 0.15434083601286175,
"grad_norm": 0.4461333155632019,
"learning_rate": 5e-06,
"loss": 0.7637,
"step": 240
},
{
"epoch": 0.1607717041800643,
"grad_norm": 0.5069792866706848,
"learning_rate": 5e-06,
"loss": 0.7663,
"step": 250
},
{
"epoch": 0.16720257234726688,
"grad_norm": 0.4338971972465515,
"learning_rate": 5e-06,
"loss": 0.7567,
"step": 260
},
{
"epoch": 0.17363344051446947,
"grad_norm": 0.5476683974266052,
"learning_rate": 5e-06,
"loss": 0.7581,
"step": 270
},
{
"epoch": 0.18006430868167203,
"grad_norm": 0.5481943488121033,
"learning_rate": 5e-06,
"loss": 0.7591,
"step": 280
},
{
"epoch": 0.1864951768488746,
"grad_norm": 0.5772653818130493,
"learning_rate": 5e-06,
"loss": 0.754,
"step": 290
},
{
"epoch": 0.19292604501607716,
"grad_norm": 0.455953449010849,
"learning_rate": 5e-06,
"loss": 0.7601,
"step": 300
},
{
"epoch": 0.19935691318327975,
"grad_norm": 0.5032763481140137,
"learning_rate": 5e-06,
"loss": 0.7534,
"step": 310
},
{
"epoch": 0.2057877813504823,
"grad_norm": 0.5598179697990417,
"learning_rate": 5e-06,
"loss": 0.7567,
"step": 320
},
{
"epoch": 0.21221864951768488,
"grad_norm": 0.5307891368865967,
"learning_rate": 5e-06,
"loss": 0.7701,
"step": 330
},
{
"epoch": 0.21864951768488747,
"grad_norm": 0.654017984867096,
"learning_rate": 5e-06,
"loss": 0.7565,
"step": 340
},
{
"epoch": 0.22508038585209003,
"grad_norm": 0.49319934844970703,
"learning_rate": 5e-06,
"loss": 0.7423,
"step": 350
},
{
"epoch": 0.2315112540192926,
"grad_norm": 0.5508062243461609,
"learning_rate": 5e-06,
"loss": 0.7569,
"step": 360
},
{
"epoch": 0.2379421221864952,
"grad_norm": 0.5229071378707886,
"learning_rate": 5e-06,
"loss": 0.7557,
"step": 370
},
{
"epoch": 0.24437299035369775,
"grad_norm": 0.5349363684654236,
"learning_rate": 5e-06,
"loss": 0.7569,
"step": 380
},
{
"epoch": 0.2508038585209003,
"grad_norm": 0.4683885872364044,
"learning_rate": 5e-06,
"loss": 0.7496,
"step": 390
},
{
"epoch": 0.2572347266881029,
"grad_norm": 0.4715147316455841,
"learning_rate": 5e-06,
"loss": 0.7528,
"step": 400
},
{
"epoch": 0.26366559485530544,
"grad_norm": 0.42438462376594543,
"learning_rate": 5e-06,
"loss": 0.7612,
"step": 410
},
{
"epoch": 0.27009646302250806,
"grad_norm": 0.7097042798995972,
"learning_rate": 5e-06,
"loss": 0.749,
"step": 420
},
{
"epoch": 0.2765273311897106,
"grad_norm": 0.43447116017341614,
"learning_rate": 5e-06,
"loss": 0.7396,
"step": 430
},
{
"epoch": 0.2829581993569132,
"grad_norm": 0.5114174485206604,
"learning_rate": 5e-06,
"loss": 0.7471,
"step": 440
},
{
"epoch": 0.28938906752411575,
"grad_norm": 0.4831767678260803,
"learning_rate": 5e-06,
"loss": 0.7449,
"step": 450
},
{
"epoch": 0.2958199356913183,
"grad_norm": 0.49875640869140625,
"learning_rate": 5e-06,
"loss": 0.7483,
"step": 460
},
{
"epoch": 0.3022508038585209,
"grad_norm": 0.489754855632782,
"learning_rate": 5e-06,
"loss": 0.7451,
"step": 470
},
{
"epoch": 0.3086816720257235,
"grad_norm": 0.5207638144493103,
"learning_rate": 5e-06,
"loss": 0.7463,
"step": 480
},
{
"epoch": 0.31511254019292606,
"grad_norm": 0.5335565805435181,
"learning_rate": 5e-06,
"loss": 0.7403,
"step": 490
},
{
"epoch": 0.3215434083601286,
"grad_norm": 0.5709009766578674,
"learning_rate": 5e-06,
"loss": 0.7425,
"step": 500
},
{
"epoch": 0.3279742765273312,
"grad_norm": 0.45602336525917053,
"learning_rate": 5e-06,
"loss": 0.7506,
"step": 510
},
{
"epoch": 0.33440514469453375,
"grad_norm": 0.49307122826576233,
"learning_rate": 5e-06,
"loss": 0.7404,
"step": 520
},
{
"epoch": 0.3408360128617363,
"grad_norm": 0.49949631094932556,
"learning_rate": 5e-06,
"loss": 0.7465,
"step": 530
},
{
"epoch": 0.34726688102893893,
"grad_norm": 0.43178921937942505,
"learning_rate": 5e-06,
"loss": 0.7531,
"step": 540
},
{
"epoch": 0.3536977491961415,
"grad_norm": 0.46599695086479187,
"learning_rate": 5e-06,
"loss": 0.7428,
"step": 550
},
{
"epoch": 0.36012861736334406,
"grad_norm": 0.4541228115558624,
"learning_rate": 5e-06,
"loss": 0.7427,
"step": 560
},
{
"epoch": 0.3665594855305466,
"grad_norm": 0.474062979221344,
"learning_rate": 5e-06,
"loss": 0.7408,
"step": 570
},
{
"epoch": 0.3729903536977492,
"grad_norm": 0.47080013155937195,
"learning_rate": 5e-06,
"loss": 0.7423,
"step": 580
},
{
"epoch": 0.37942122186495175,
"grad_norm": 0.46832209825515747,
"learning_rate": 5e-06,
"loss": 0.7383,
"step": 590
},
{
"epoch": 0.3858520900321543,
"grad_norm": 0.4157029986381531,
"learning_rate": 5e-06,
"loss": 0.7509,
"step": 600
},
{
"epoch": 0.39228295819935693,
"grad_norm": 0.512323260307312,
"learning_rate": 5e-06,
"loss": 0.7387,
"step": 610
},
{
"epoch": 0.3987138263665595,
"grad_norm": 0.4567117393016815,
"learning_rate": 5e-06,
"loss": 0.7379,
"step": 620
},
{
"epoch": 0.40514469453376206,
"grad_norm": 0.4581872522830963,
"learning_rate": 5e-06,
"loss": 0.7384,
"step": 630
},
{
"epoch": 0.4115755627009646,
"grad_norm": 0.43767768144607544,
"learning_rate": 5e-06,
"loss": 0.7349,
"step": 640
},
{
"epoch": 0.4180064308681672,
"grad_norm": 0.5342622399330139,
"learning_rate": 5e-06,
"loss": 0.7379,
"step": 650
},
{
"epoch": 0.42443729903536975,
"grad_norm": 0.561100423336029,
"learning_rate": 5e-06,
"loss": 0.7361,
"step": 660
},
{
"epoch": 0.43086816720257237,
"grad_norm": 0.4456179141998291,
"learning_rate": 5e-06,
"loss": 0.7373,
"step": 670
},
{
"epoch": 0.43729903536977494,
"grad_norm": 0.5494213104248047,
"learning_rate": 5e-06,
"loss": 0.7428,
"step": 680
},
{
"epoch": 0.4437299035369775,
"grad_norm": 0.6552912592887878,
"learning_rate": 5e-06,
"loss": 0.7397,
"step": 690
},
{
"epoch": 0.45016077170418006,
"grad_norm": 0.6181358098983765,
"learning_rate": 5e-06,
"loss": 0.7375,
"step": 700
},
{
"epoch": 0.4565916398713826,
"grad_norm": 0.45060378313064575,
"learning_rate": 5e-06,
"loss": 0.7352,
"step": 710
},
{
"epoch": 0.4630225080385852,
"grad_norm": 0.4362952411174774,
"learning_rate": 5e-06,
"loss": 0.7385,
"step": 720
},
{
"epoch": 0.4694533762057878,
"grad_norm": 0.4858558177947998,
"learning_rate": 5e-06,
"loss": 0.7364,
"step": 730
},
{
"epoch": 0.4758842443729904,
"grad_norm": 0.5299956202507019,
"learning_rate": 5e-06,
"loss": 0.7368,
"step": 740
},
{
"epoch": 0.48231511254019294,
"grad_norm": 0.6190028190612793,
"learning_rate": 5e-06,
"loss": 0.7286,
"step": 750
},
{
"epoch": 0.4887459807073955,
"grad_norm": 0.42335936427116394,
"learning_rate": 5e-06,
"loss": 0.7368,
"step": 760
},
{
"epoch": 0.49517684887459806,
"grad_norm": 0.5196449160575867,
"learning_rate": 5e-06,
"loss": 0.7432,
"step": 770
},
{
"epoch": 0.5016077170418006,
"grad_norm": 0.587582528591156,
"learning_rate": 5e-06,
"loss": 0.7405,
"step": 780
},
{
"epoch": 0.5080385852090032,
"grad_norm": 0.5125169157981873,
"learning_rate": 5e-06,
"loss": 0.7346,
"step": 790
},
{
"epoch": 0.5144694533762058,
"grad_norm": 0.42861226201057434,
"learning_rate": 5e-06,
"loss": 0.7343,
"step": 800
},
{
"epoch": 0.5209003215434084,
"grad_norm": 0.41551926732063293,
"learning_rate": 5e-06,
"loss": 0.7401,
"step": 810
},
{
"epoch": 0.5273311897106109,
"grad_norm": 0.511359453201294,
"learning_rate": 5e-06,
"loss": 0.7333,
"step": 820
},
{
"epoch": 0.5337620578778135,
"grad_norm": 0.4694862961769104,
"learning_rate": 5e-06,
"loss": 0.7405,
"step": 830
},
{
"epoch": 0.5401929260450161,
"grad_norm": 0.48257577419281006,
"learning_rate": 5e-06,
"loss": 0.735,
"step": 840
},
{
"epoch": 0.5466237942122186,
"grad_norm": 0.4408928155899048,
"learning_rate": 5e-06,
"loss": 0.7235,
"step": 850
},
{
"epoch": 0.5530546623794212,
"grad_norm": 0.5172277092933655,
"learning_rate": 5e-06,
"loss": 0.7398,
"step": 860
},
{
"epoch": 0.5594855305466238,
"grad_norm": 0.4982483983039856,
"learning_rate": 5e-06,
"loss": 0.7383,
"step": 870
},
{
"epoch": 0.5659163987138264,
"grad_norm": 0.4628170132637024,
"learning_rate": 5e-06,
"loss": 0.741,
"step": 880
},
{
"epoch": 0.572347266881029,
"grad_norm": 0.46205154061317444,
"learning_rate": 5e-06,
"loss": 0.7304,
"step": 890
},
{
"epoch": 0.5787781350482315,
"grad_norm": 0.4182255268096924,
"learning_rate": 5e-06,
"loss": 0.7351,
"step": 900
},
{
"epoch": 0.5852090032154341,
"grad_norm": 0.5075783729553223,
"learning_rate": 5e-06,
"loss": 0.732,
"step": 910
},
{
"epoch": 0.5916398713826366,
"grad_norm": 0.4244738817214966,
"learning_rate": 5e-06,
"loss": 0.7357,
"step": 920
},
{
"epoch": 0.5980707395498392,
"grad_norm": 0.473067969083786,
"learning_rate": 5e-06,
"loss": 0.739,
"step": 930
},
{
"epoch": 0.6045016077170418,
"grad_norm": 0.4673498272895813,
"learning_rate": 5e-06,
"loss": 0.7421,
"step": 940
},
{
"epoch": 0.6109324758842444,
"grad_norm": 0.41633403301239014,
"learning_rate": 5e-06,
"loss": 0.733,
"step": 950
},
{
"epoch": 0.617363344051447,
"grad_norm": 0.4132135212421417,
"learning_rate": 5e-06,
"loss": 0.7306,
"step": 960
},
{
"epoch": 0.6237942122186495,
"grad_norm": 0.48543354868888855,
"learning_rate": 5e-06,
"loss": 0.7267,
"step": 970
},
{
"epoch": 0.6302250803858521,
"grad_norm": 0.45808976888656616,
"learning_rate": 5e-06,
"loss": 0.7339,
"step": 980
},
{
"epoch": 0.6366559485530546,
"grad_norm": 0.46231311559677124,
"learning_rate": 5e-06,
"loss": 0.7321,
"step": 990
},
{
"epoch": 0.6430868167202572,
"grad_norm": 0.43952593207359314,
"learning_rate": 5e-06,
"loss": 0.7244,
"step": 1000
},
{
"epoch": 0.6495176848874598,
"grad_norm": 0.4417444169521332,
"learning_rate": 5e-06,
"loss": 0.7339,
"step": 1010
},
{
"epoch": 0.6559485530546624,
"grad_norm": 0.460893839597702,
"learning_rate": 5e-06,
"loss": 0.7317,
"step": 1020
},
{
"epoch": 0.662379421221865,
"grad_norm": 0.4568830728530884,
"learning_rate": 5e-06,
"loss": 0.7294,
"step": 1030
},
{
"epoch": 0.6688102893890675,
"grad_norm": 0.4672453999519348,
"learning_rate": 5e-06,
"loss": 0.7306,
"step": 1040
},
{
"epoch": 0.6752411575562701,
"grad_norm": 0.677759051322937,
"learning_rate": 5e-06,
"loss": 0.7234,
"step": 1050
},
{
"epoch": 0.6816720257234726,
"grad_norm": 0.6139099597930908,
"learning_rate": 5e-06,
"loss": 0.7346,
"step": 1060
},
{
"epoch": 0.6881028938906752,
"grad_norm": 0.4375672936439514,
"learning_rate": 5e-06,
"loss": 0.7323,
"step": 1070
},
{
"epoch": 0.6945337620578779,
"grad_norm": 0.39761385321617126,
"learning_rate": 5e-06,
"loss": 0.7348,
"step": 1080
},
{
"epoch": 0.7009646302250804,
"grad_norm": 0.4165497422218323,
"learning_rate": 5e-06,
"loss": 0.7267,
"step": 1090
},
{
"epoch": 0.707395498392283,
"grad_norm": 0.4338400661945343,
"learning_rate": 5e-06,
"loss": 0.7305,
"step": 1100
},
{
"epoch": 0.7138263665594855,
"grad_norm": 0.43742889165878296,
"learning_rate": 5e-06,
"loss": 0.7311,
"step": 1110
},
{
"epoch": 0.7202572347266881,
"grad_norm": 0.45418253540992737,
"learning_rate": 5e-06,
"loss": 0.7277,
"step": 1120
},
{
"epoch": 0.7266881028938906,
"grad_norm": 0.42107295989990234,
"learning_rate": 5e-06,
"loss": 0.7319,
"step": 1130
},
{
"epoch": 0.7331189710610932,
"grad_norm": 0.40914231538772583,
"learning_rate": 5e-06,
"loss": 0.7251,
"step": 1140
},
{
"epoch": 0.7395498392282959,
"grad_norm": 0.42050373554229736,
"learning_rate": 5e-06,
"loss": 0.7403,
"step": 1150
},
{
"epoch": 0.7459807073954984,
"grad_norm": 0.4320564568042755,
"learning_rate": 5e-06,
"loss": 0.7319,
"step": 1160
},
{
"epoch": 0.752411575562701,
"grad_norm": 0.4363013803958893,
"learning_rate": 5e-06,
"loss": 0.7315,
"step": 1170
},
{
"epoch": 0.7588424437299035,
"grad_norm": 0.50197434425354,
"learning_rate": 5e-06,
"loss": 0.7287,
"step": 1180
},
{
"epoch": 0.7652733118971061,
"grad_norm": 0.5218095183372498,
"learning_rate": 5e-06,
"loss": 0.7294,
"step": 1190
},
{
"epoch": 0.7717041800643086,
"grad_norm": 0.4605177044868469,
"learning_rate": 5e-06,
"loss": 0.7218,
"step": 1200
},
{
"epoch": 0.7781350482315113,
"grad_norm": 0.4640117287635803,
"learning_rate": 5e-06,
"loss": 0.7297,
"step": 1210
},
{
"epoch": 0.7845659163987139,
"grad_norm": 0.43073731660842896,
"learning_rate": 5e-06,
"loss": 0.7299,
"step": 1220
},
{
"epoch": 0.7909967845659164,
"grad_norm": 0.43865692615509033,
"learning_rate": 5e-06,
"loss": 0.7299,
"step": 1230
},
{
"epoch": 0.797427652733119,
"grad_norm": 0.4125821590423584,
"learning_rate": 5e-06,
"loss": 0.738,
"step": 1240
},
{
"epoch": 0.8038585209003215,
"grad_norm": 0.41375529766082764,
"learning_rate": 5e-06,
"loss": 0.7324,
"step": 1250
},
{
"epoch": 0.8102893890675241,
"grad_norm": 0.43837442994117737,
"learning_rate": 5e-06,
"loss": 0.7219,
"step": 1260
},
{
"epoch": 0.8167202572347267,
"grad_norm": 0.45211347937583923,
"learning_rate": 5e-06,
"loss": 0.725,
"step": 1270
},
{
"epoch": 0.8231511254019293,
"grad_norm": 0.4578869640827179,
"learning_rate": 5e-06,
"loss": 0.7307,
"step": 1280
},
{
"epoch": 0.8295819935691319,
"grad_norm": 0.42134717106819153,
"learning_rate": 5e-06,
"loss": 0.7203,
"step": 1290
},
{
"epoch": 0.8360128617363344,
"grad_norm": 0.4580245912075043,
"learning_rate": 5e-06,
"loss": 0.7242,
"step": 1300
},
{
"epoch": 0.842443729903537,
"grad_norm": 0.4085647165775299,
"learning_rate": 5e-06,
"loss": 0.7182,
"step": 1310
},
{
"epoch": 0.8488745980707395,
"grad_norm": 0.5211206674575806,
"learning_rate": 5e-06,
"loss": 0.7259,
"step": 1320
},
{
"epoch": 0.8553054662379421,
"grad_norm": 0.5008974671363831,
"learning_rate": 5e-06,
"loss": 0.7164,
"step": 1330
},
{
"epoch": 0.8617363344051447,
"grad_norm": 0.4538878798484802,
"learning_rate": 5e-06,
"loss": 0.7198,
"step": 1340
},
{
"epoch": 0.8681672025723473,
"grad_norm": 0.407697468996048,
"learning_rate": 5e-06,
"loss": 0.7255,
"step": 1350
},
{
"epoch": 0.8745980707395499,
"grad_norm": 0.4785331189632416,
"learning_rate": 5e-06,
"loss": 0.7273,
"step": 1360
},
{
"epoch": 0.8810289389067524,
"grad_norm": 0.4148114323616028,
"learning_rate": 5e-06,
"loss": 0.7247,
"step": 1370
},
{
"epoch": 0.887459807073955,
"grad_norm": 0.38368263840675354,
"learning_rate": 5e-06,
"loss": 0.7268,
"step": 1380
},
{
"epoch": 0.8938906752411575,
"grad_norm": 0.40352755784988403,
"learning_rate": 5e-06,
"loss": 0.7285,
"step": 1390
},
{
"epoch": 0.9003215434083601,
"grad_norm": 0.4232112467288971,
"learning_rate": 5e-06,
"loss": 0.7249,
"step": 1400
},
{
"epoch": 0.9067524115755627,
"grad_norm": 0.4366598129272461,
"learning_rate": 5e-06,
"loss": 0.7249,
"step": 1410
},
{
"epoch": 0.9131832797427653,
"grad_norm": 0.4052753150463104,
"learning_rate": 5e-06,
"loss": 0.7245,
"step": 1420
},
{
"epoch": 0.9196141479099679,
"grad_norm": 0.44511350989341736,
"learning_rate": 5e-06,
"loss": 0.7305,
"step": 1430
},
{
"epoch": 0.9260450160771704,
"grad_norm": 0.44077491760253906,
"learning_rate": 5e-06,
"loss": 0.7294,
"step": 1440
},
{
"epoch": 0.932475884244373,
"grad_norm": 0.48145055770874023,
"learning_rate": 5e-06,
"loss": 0.7215,
"step": 1450
},
{
"epoch": 0.9389067524115756,
"grad_norm": 0.42547109723091125,
"learning_rate": 5e-06,
"loss": 0.7292,
"step": 1460
},
{
"epoch": 0.9453376205787781,
"grad_norm": 0.4287051558494568,
"learning_rate": 5e-06,
"loss": 0.7155,
"step": 1470
},
{
"epoch": 0.9517684887459807,
"grad_norm": 0.4230569005012512,
"learning_rate": 5e-06,
"loss": 0.7198,
"step": 1480
},
{
"epoch": 0.9581993569131833,
"grad_norm": 0.4719720184803009,
"learning_rate": 5e-06,
"loss": 0.7297,
"step": 1490
},
{
"epoch": 0.9646302250803859,
"grad_norm": 0.43969443440437317,
"learning_rate": 5e-06,
"loss": 0.7287,
"step": 1500
},
{
"epoch": 0.9710610932475884,
"grad_norm": 0.4330804646015167,
"learning_rate": 5e-06,
"loss": 0.7209,
"step": 1510
},
{
"epoch": 0.977491961414791,
"grad_norm": 0.38477885723114014,
"learning_rate": 5e-06,
"loss": 0.7246,
"step": 1520
},
{
"epoch": 0.9839228295819936,
"grad_norm": 0.46622517704963684,
"learning_rate": 5e-06,
"loss": 0.7281,
"step": 1530
},
{
"epoch": 0.9903536977491961,
"grad_norm": 0.47588425874710083,
"learning_rate": 5e-06,
"loss": 0.7264,
"step": 1540
},
{
"epoch": 0.9967845659163987,
"grad_norm": 0.43833327293395996,
"learning_rate": 5e-06,
"loss": 0.7345,
"step": 1550
},
{
"epoch": 1.0,
"eval_loss": 0.7232183814048767,
"eval_runtime": 140.4382,
"eval_samples_per_second": 298.373,
"eval_steps_per_second": 1.168,
"step": 1555
},
{
"epoch": 1.0032154340836013,
"grad_norm": 0.6193146705627441,
"learning_rate": 5e-06,
"loss": 0.7137,
"step": 1560
},
{
"epoch": 1.0096463022508038,
"grad_norm": 0.4350009560585022,
"learning_rate": 5e-06,
"loss": 0.682,
"step": 1570
},
{
"epoch": 1.0160771704180065,
"grad_norm": 0.44338950514793396,
"learning_rate": 5e-06,
"loss": 0.6971,
"step": 1580
},
{
"epoch": 1.022508038585209,
"grad_norm": 0.4447615444660187,
"learning_rate": 5e-06,
"loss": 0.687,
"step": 1590
},
{
"epoch": 1.0289389067524115,
"grad_norm": 0.4388461112976074,
"learning_rate": 5e-06,
"loss": 0.6841,
"step": 1600
},
{
"epoch": 1.0353697749196142,
"grad_norm": 0.523465096950531,
"learning_rate": 5e-06,
"loss": 0.6922,
"step": 1610
},
{
"epoch": 1.0418006430868167,
"grad_norm": 0.46927884221076965,
"learning_rate": 5e-06,
"loss": 0.678,
"step": 1620
},
{
"epoch": 1.0482315112540193,
"grad_norm": 0.47517913579940796,
"learning_rate": 5e-06,
"loss": 0.6735,
"step": 1630
},
{
"epoch": 1.0546623794212218,
"grad_norm": 0.42782580852508545,
"learning_rate": 5e-06,
"loss": 0.6835,
"step": 1640
},
{
"epoch": 1.0610932475884245,
"grad_norm": 0.4523870348930359,
"learning_rate": 5e-06,
"loss": 0.6902,
"step": 1650
},
{
"epoch": 1.067524115755627,
"grad_norm": 0.46784067153930664,
"learning_rate": 5e-06,
"loss": 0.6814,
"step": 1660
},
{
"epoch": 1.0739549839228295,
"grad_norm": 0.43110141158103943,
"learning_rate": 5e-06,
"loss": 0.6793,
"step": 1670
},
{
"epoch": 1.0803858520900322,
"grad_norm": 0.44774794578552246,
"learning_rate": 5e-06,
"loss": 0.6853,
"step": 1680
},
{
"epoch": 1.0868167202572347,
"grad_norm": 0.5212559103965759,
"learning_rate": 5e-06,
"loss": 0.6863,
"step": 1690
},
{
"epoch": 1.0932475884244373,
"grad_norm": 0.49354031682014465,
"learning_rate": 5e-06,
"loss": 0.68,
"step": 1700
},
{
"epoch": 1.09967845659164,
"grad_norm": 0.4270998239517212,
"learning_rate": 5e-06,
"loss": 0.6845,
"step": 1710
},
{
"epoch": 1.1061093247588425,
"grad_norm": 0.43898463249206543,
"learning_rate": 5e-06,
"loss": 0.683,
"step": 1720
},
{
"epoch": 1.112540192926045,
"grad_norm": 0.413997083902359,
"learning_rate": 5e-06,
"loss": 0.6755,
"step": 1730
},
{
"epoch": 1.1189710610932475,
"grad_norm": 0.4593328833580017,
"learning_rate": 5e-06,
"loss": 0.6888,
"step": 1740
},
{
"epoch": 1.1254019292604502,
"grad_norm": 0.47585126757621765,
"learning_rate": 5e-06,
"loss": 0.6865,
"step": 1750
},
{
"epoch": 1.1318327974276527,
"grad_norm": 0.4210260808467865,
"learning_rate": 5e-06,
"loss": 0.6833,
"step": 1760
},
{
"epoch": 1.1382636655948553,
"grad_norm": 0.44741642475128174,
"learning_rate": 5e-06,
"loss": 0.6849,
"step": 1770
},
{
"epoch": 1.144694533762058,
"grad_norm": 0.437013179063797,
"learning_rate": 5e-06,
"loss": 0.6876,
"step": 1780
},
{
"epoch": 1.1511254019292605,
"grad_norm": 0.45807886123657227,
"learning_rate": 5e-06,
"loss": 0.6858,
"step": 1790
},
{
"epoch": 1.157556270096463,
"grad_norm": 0.46383801102638245,
"learning_rate": 5e-06,
"loss": 0.6718,
"step": 1800
},
{
"epoch": 1.1639871382636655,
"grad_norm": 0.5218130946159363,
"learning_rate": 5e-06,
"loss": 0.6831,
"step": 1810
},
{
"epoch": 1.1704180064308682,
"grad_norm": 0.4491232931613922,
"learning_rate": 5e-06,
"loss": 0.6837,
"step": 1820
},
{
"epoch": 1.1768488745980707,
"grad_norm": 0.45633968710899353,
"learning_rate": 5e-06,
"loss": 0.6782,
"step": 1830
},
{
"epoch": 1.1832797427652733,
"grad_norm": 0.4493134915828705,
"learning_rate": 5e-06,
"loss": 0.685,
"step": 1840
},
{
"epoch": 1.189710610932476,
"grad_norm": 0.42465460300445557,
"learning_rate": 5e-06,
"loss": 0.6878,
"step": 1850
},
{
"epoch": 1.1961414790996785,
"grad_norm": 0.4019971787929535,
"learning_rate": 5e-06,
"loss": 0.677,
"step": 1860
},
{
"epoch": 1.202572347266881,
"grad_norm": 0.45171162486076355,
"learning_rate": 5e-06,
"loss": 0.686,
"step": 1870
},
{
"epoch": 1.2090032154340835,
"grad_norm": 0.43534427881240845,
"learning_rate": 5e-06,
"loss": 0.6816,
"step": 1880
},
{
"epoch": 1.2154340836012862,
"grad_norm": 0.4472478926181793,
"learning_rate": 5e-06,
"loss": 0.6839,
"step": 1890
},
{
"epoch": 1.2218649517684887,
"grad_norm": 0.41748490929603577,
"learning_rate": 5e-06,
"loss": 0.6913,
"step": 1900
},
{
"epoch": 1.2282958199356913,
"grad_norm": 0.4147058427333832,
"learning_rate": 5e-06,
"loss": 0.681,
"step": 1910
},
{
"epoch": 1.234726688102894,
"grad_norm": 0.41148611903190613,
"learning_rate": 5e-06,
"loss": 0.6819,
"step": 1920
},
{
"epoch": 1.2411575562700965,
"grad_norm": 0.4393286406993866,
"learning_rate": 5e-06,
"loss": 0.6903,
"step": 1930
},
{
"epoch": 1.247588424437299,
"grad_norm": 0.4369371235370636,
"learning_rate": 5e-06,
"loss": 0.6872,
"step": 1940
},
{
"epoch": 1.2540192926045015,
"grad_norm": 0.5068768858909607,
"learning_rate": 5e-06,
"loss": 0.6869,
"step": 1950
},
{
"epoch": 1.2604501607717042,
"grad_norm": 0.43698254227638245,
"learning_rate": 5e-06,
"loss": 0.6853,
"step": 1960
},
{
"epoch": 1.2668810289389068,
"grad_norm": 0.439619779586792,
"learning_rate": 5e-06,
"loss": 0.681,
"step": 1970
},
{
"epoch": 1.2733118971061093,
"grad_norm": 0.4120563566684723,
"learning_rate": 5e-06,
"loss": 0.6815,
"step": 1980
},
{
"epoch": 1.279742765273312,
"grad_norm": 0.39503830671310425,
"learning_rate": 5e-06,
"loss": 0.6789,
"step": 1990
},
{
"epoch": 1.2861736334405145,
"grad_norm": 0.46114471554756165,
"learning_rate": 5e-06,
"loss": 0.6858,
"step": 2000
},
{
"epoch": 1.292604501607717,
"grad_norm": 0.44008398056030273,
"learning_rate": 5e-06,
"loss": 0.6916,
"step": 2010
},
{
"epoch": 1.2990353697749195,
"grad_norm": 0.41201072931289673,
"learning_rate": 5e-06,
"loss": 0.6832,
"step": 2020
},
{
"epoch": 1.3054662379421222,
"grad_norm": 0.42483213543891907,
"learning_rate": 5e-06,
"loss": 0.6876,
"step": 2030
},
{
"epoch": 1.3118971061093248,
"grad_norm": 0.4412234127521515,
"learning_rate": 5e-06,
"loss": 0.6736,
"step": 2040
},
{
"epoch": 1.3183279742765273,
"grad_norm": 0.42483067512512207,
"learning_rate": 5e-06,
"loss": 0.6866,
"step": 2050
},
{
"epoch": 1.32475884244373,
"grad_norm": 0.412567675113678,
"learning_rate": 5e-06,
"loss": 0.6877,
"step": 2060
},
{
"epoch": 1.3311897106109325,
"grad_norm": 0.4586575925350189,
"learning_rate": 5e-06,
"loss": 0.6898,
"step": 2070
},
{
"epoch": 1.337620578778135,
"grad_norm": 0.41622015833854675,
"learning_rate": 5e-06,
"loss": 0.6836,
"step": 2080
},
{
"epoch": 1.3440514469453375,
"grad_norm": 0.4891818165779114,
"learning_rate": 5e-06,
"loss": 0.6825,
"step": 2090
},
{
"epoch": 1.3504823151125402,
"grad_norm": 0.42719897627830505,
"learning_rate": 5e-06,
"loss": 0.6915,
"step": 2100
},
{
"epoch": 1.3569131832797428,
"grad_norm": 0.4267047643661499,
"learning_rate": 5e-06,
"loss": 0.6829,
"step": 2110
},
{
"epoch": 1.3633440514469453,
"grad_norm": 0.48593926429748535,
"learning_rate": 5e-06,
"loss": 0.6865,
"step": 2120
},
{
"epoch": 1.369774919614148,
"grad_norm": 0.46337270736694336,
"learning_rate": 5e-06,
"loss": 0.6784,
"step": 2130
},
{
"epoch": 1.3762057877813505,
"grad_norm": 0.42621052265167236,
"learning_rate": 5e-06,
"loss": 0.6815,
"step": 2140
},
{
"epoch": 1.382636655948553,
"grad_norm": 0.4374221861362457,
"learning_rate": 5e-06,
"loss": 0.6823,
"step": 2150
},
{
"epoch": 1.3890675241157555,
"grad_norm": 0.49710190296173096,
"learning_rate": 5e-06,
"loss": 0.6788,
"step": 2160
},
{
"epoch": 1.3954983922829582,
"grad_norm": 0.43773987889289856,
"learning_rate": 5e-06,
"loss": 0.6897,
"step": 2170
},
{
"epoch": 1.4019292604501608,
"grad_norm": 0.420480877161026,
"learning_rate": 5e-06,
"loss": 0.6877,
"step": 2180
},
{
"epoch": 1.4083601286173635,
"grad_norm": 0.41698333621025085,
"learning_rate": 5e-06,
"loss": 0.6782,
"step": 2190
},
{
"epoch": 1.414790996784566,
"grad_norm": 0.45082971453666687,
"learning_rate": 5e-06,
"loss": 0.6884,
"step": 2200
},
{
"epoch": 1.4212218649517685,
"grad_norm": 0.44047510623931885,
"learning_rate": 5e-06,
"loss": 0.68,
"step": 2210
},
{
"epoch": 1.427652733118971,
"grad_norm": 0.43505367636680603,
"learning_rate": 5e-06,
"loss": 0.684,
"step": 2220
},
{
"epoch": 1.4340836012861735,
"grad_norm": 0.42423659563064575,
"learning_rate": 5e-06,
"loss": 0.6852,
"step": 2230
},
{
"epoch": 1.4405144694533762,
"grad_norm": 0.5248254537582397,
"learning_rate": 5e-06,
"loss": 0.6796,
"step": 2240
},
{
"epoch": 1.4469453376205788,
"grad_norm": 0.47595280408859253,
"learning_rate": 5e-06,
"loss": 0.6812,
"step": 2250
},
{
"epoch": 1.4533762057877815,
"grad_norm": 0.41155120730400085,
"learning_rate": 5e-06,
"loss": 0.6894,
"step": 2260
},
{
"epoch": 1.459807073954984,
"grad_norm": 0.4290079176425934,
"learning_rate": 5e-06,
"loss": 0.684,
"step": 2270
},
{
"epoch": 1.4662379421221865,
"grad_norm": 0.4066310226917267,
"learning_rate": 5e-06,
"loss": 0.6823,
"step": 2280
},
{
"epoch": 1.472668810289389,
"grad_norm": 0.4360986351966858,
"learning_rate": 5e-06,
"loss": 0.6886,
"step": 2290
},
{
"epoch": 1.4790996784565915,
"grad_norm": 0.3978036642074585,
"learning_rate": 5e-06,
"loss": 0.6849,
"step": 2300
},
{
"epoch": 1.4855305466237942,
"grad_norm": 0.41997137665748596,
"learning_rate": 5e-06,
"loss": 0.6834,
"step": 2310
},
{
"epoch": 1.4919614147909968,
"grad_norm": 0.4409499764442444,
"learning_rate": 5e-06,
"loss": 0.6873,
"step": 2320
},
{
"epoch": 1.4983922829581995,
"grad_norm": 0.44297707080841064,
"learning_rate": 5e-06,
"loss": 0.682,
"step": 2330
},
{
"epoch": 1.504823151125402,
"grad_norm": 0.4389215409755707,
"learning_rate": 5e-06,
"loss": 0.6892,
"step": 2340
},
{
"epoch": 1.5112540192926045,
"grad_norm": 0.44480717182159424,
"learning_rate": 5e-06,
"loss": 0.6884,
"step": 2350
},
{
"epoch": 1.517684887459807,
"grad_norm": 0.44355508685112,
"learning_rate": 5e-06,
"loss": 0.6876,
"step": 2360
},
{
"epoch": 1.5241157556270095,
"grad_norm": 0.46087756752967834,
"learning_rate": 5e-06,
"loss": 0.6828,
"step": 2370
},
{
"epoch": 1.5305466237942122,
"grad_norm": 0.4672592580318451,
"learning_rate": 5e-06,
"loss": 0.6871,
"step": 2380
},
{
"epoch": 1.5369774919614148,
"grad_norm": 0.3982642889022827,
"learning_rate": 5e-06,
"loss": 0.6819,
"step": 2390
},
{
"epoch": 1.5434083601286175,
"grad_norm": 0.40598487854003906,
"learning_rate": 5e-06,
"loss": 0.6838,
"step": 2400
},
{
"epoch": 1.54983922829582,
"grad_norm": 0.4345811605453491,
"learning_rate": 5e-06,
"loss": 0.6815,
"step": 2410
},
{
"epoch": 1.5562700964630225,
"grad_norm": 0.43568089604377747,
"learning_rate": 5e-06,
"loss": 0.6911,
"step": 2420
},
{
"epoch": 1.562700964630225,
"grad_norm": 0.43922844529151917,
"learning_rate": 5e-06,
"loss": 0.6834,
"step": 2430
},
{
"epoch": 1.5691318327974275,
"grad_norm": 0.4793626368045807,
"learning_rate": 5e-06,
"loss": 0.6833,
"step": 2440
},
{
"epoch": 1.5755627009646302,
"grad_norm": 0.45686307549476624,
"learning_rate": 5e-06,
"loss": 0.6864,
"step": 2450
},
{
"epoch": 1.5819935691318328,
"grad_norm": 0.41061604022979736,
"learning_rate": 5e-06,
"loss": 0.6768,
"step": 2460
},
{
"epoch": 1.5884244372990355,
"grad_norm": 0.45562943816185,
"learning_rate": 5e-06,
"loss": 0.6743,
"step": 2470
},
{
"epoch": 1.594855305466238,
"grad_norm": 0.4296809136867523,
"learning_rate": 5e-06,
"loss": 0.6802,
"step": 2480
},
{
"epoch": 1.6012861736334405,
"grad_norm": 0.4218539595603943,
"learning_rate": 5e-06,
"loss": 0.6857,
"step": 2490
},
{
"epoch": 1.607717041800643,
"grad_norm": 0.45991575717926025,
"learning_rate": 5e-06,
"loss": 0.684,
"step": 2500
},
{
"epoch": 1.6141479099678455,
"grad_norm": 0.43671083450317383,
"learning_rate": 5e-06,
"loss": 0.6872,
"step": 2510
},
{
"epoch": 1.6205787781350482,
"grad_norm": 0.4566083550453186,
"learning_rate": 5e-06,
"loss": 0.6808,
"step": 2520
},
{
"epoch": 1.6270096463022508,
"grad_norm": 0.4394720792770386,
"learning_rate": 5e-06,
"loss": 0.6841,
"step": 2530
},
{
"epoch": 1.6334405144694535,
"grad_norm": 0.4831625521183014,
"learning_rate": 5e-06,
"loss": 0.6846,
"step": 2540
},
{
"epoch": 1.639871382636656,
"grad_norm": 0.4193684458732605,
"learning_rate": 5e-06,
"loss": 0.6858,
"step": 2550
},
{
"epoch": 1.6463022508038585,
"grad_norm": 0.47811901569366455,
"learning_rate": 5e-06,
"loss": 0.6758,
"step": 2560
},
{
"epoch": 1.652733118971061,
"grad_norm": 0.4748084545135498,
"learning_rate": 5e-06,
"loss": 0.6861,
"step": 2570
},
{
"epoch": 1.6591639871382635,
"grad_norm": 0.42245808243751526,
"learning_rate": 5e-06,
"loss": 0.6745,
"step": 2580
},
{
"epoch": 1.6655948553054662,
"grad_norm": 0.4233896732330322,
"learning_rate": 5e-06,
"loss": 0.6862,
"step": 2590
},
{
"epoch": 1.6720257234726688,
"grad_norm": 0.4050581455230713,
"learning_rate": 5e-06,
"loss": 0.676,
"step": 2600
},
{
"epoch": 1.6784565916398715,
"grad_norm": 0.41761529445648193,
"learning_rate": 5e-06,
"loss": 0.6802,
"step": 2610
},
{
"epoch": 1.684887459807074,
"grad_norm": 0.4060108959674835,
"learning_rate": 5e-06,
"loss": 0.684,
"step": 2620
},
{
"epoch": 1.6913183279742765,
"grad_norm": 0.40532317757606506,
"learning_rate": 5e-06,
"loss": 0.68,
"step": 2630
},
{
"epoch": 1.697749196141479,
"grad_norm": 0.47850868105888367,
"learning_rate": 5e-06,
"loss": 0.6879,
"step": 2640
},
{
"epoch": 1.7041800643086815,
"grad_norm": 0.4595736861228943,
"learning_rate": 5e-06,
"loss": 0.6861,
"step": 2650
},
{
"epoch": 1.7106109324758842,
"grad_norm": 0.3999944031238556,
"learning_rate": 5e-06,
"loss": 0.6811,
"step": 2660
},
{
"epoch": 1.717041800643087,
"grad_norm": 0.4152866303920746,
"learning_rate": 5e-06,
"loss": 0.676,
"step": 2670
},
{
"epoch": 1.7234726688102895,
"grad_norm": 0.5088204741477966,
"learning_rate": 5e-06,
"loss": 0.6868,
"step": 2680
},
{
"epoch": 1.729903536977492,
"grad_norm": 0.4383102059364319,
"learning_rate": 5e-06,
"loss": 0.6818,
"step": 2690
},
{
"epoch": 1.7363344051446945,
"grad_norm": 0.4219019114971161,
"learning_rate": 5e-06,
"loss": 0.6767,
"step": 2700
},
{
"epoch": 1.742765273311897,
"grad_norm": 0.4663357138633728,
"learning_rate": 5e-06,
"loss": 0.6783,
"step": 2710
},
{
"epoch": 1.7491961414790995,
"grad_norm": 0.43959125876426697,
"learning_rate": 5e-06,
"loss": 0.6824,
"step": 2720
},
{
"epoch": 1.7556270096463023,
"grad_norm": 0.43940484523773193,
"learning_rate": 5e-06,
"loss": 0.6769,
"step": 2730
},
{
"epoch": 1.762057877813505,
"grad_norm": 0.4071805477142334,
"learning_rate": 5e-06,
"loss": 0.6893,
"step": 2740
},
{
"epoch": 1.7684887459807075,
"grad_norm": 0.40912047028541565,
"learning_rate": 5e-06,
"loss": 0.6877,
"step": 2750
},
{
"epoch": 1.77491961414791,
"grad_norm": 0.4339078366756439,
"learning_rate": 5e-06,
"loss": 0.6788,
"step": 2760
},
{
"epoch": 1.7813504823151125,
"grad_norm": 0.4326707720756531,
"learning_rate": 5e-06,
"loss": 0.6831,
"step": 2770
},
{
"epoch": 1.787781350482315,
"grad_norm": 0.4307939410209656,
"learning_rate": 5e-06,
"loss": 0.6878,
"step": 2780
},
{
"epoch": 1.7942122186495175,
"grad_norm": 0.3918740749359131,
"learning_rate": 5e-06,
"loss": 0.6912,
"step": 2790
},
{
"epoch": 1.8006430868167203,
"grad_norm": 0.40045326948165894,
"learning_rate": 5e-06,
"loss": 0.6852,
"step": 2800
},
{
"epoch": 1.807073954983923,
"grad_norm": 0.40693676471710205,
"learning_rate": 5e-06,
"loss": 0.6842,
"step": 2810
},
{
"epoch": 1.8135048231511255,
"grad_norm": 0.3957662284374237,
"learning_rate": 5e-06,
"loss": 0.6777,
"step": 2820
},
{
"epoch": 1.819935691318328,
"grad_norm": 0.4147331714630127,
"learning_rate": 5e-06,
"loss": 0.679,
"step": 2830
},
{
"epoch": 1.8263665594855305,
"grad_norm": 0.421351820230484,
"learning_rate": 5e-06,
"loss": 0.6872,
"step": 2840
},
{
"epoch": 1.832797427652733,
"grad_norm": 0.4355145990848541,
"learning_rate": 5e-06,
"loss": 0.6847,
"step": 2850
},
{
"epoch": 1.8392282958199357,
"grad_norm": 0.41382715106010437,
"learning_rate": 5e-06,
"loss": 0.6777,
"step": 2860
},
{
"epoch": 1.8456591639871383,
"grad_norm": 0.4280456006526947,
"learning_rate": 5e-06,
"loss": 0.6781,
"step": 2870
},
{
"epoch": 1.852090032154341,
"grad_norm": 0.49057596921920776,
"learning_rate": 5e-06,
"loss": 0.6844,
"step": 2880
},
{
"epoch": 1.8585209003215435,
"grad_norm": 0.41203203797340393,
"learning_rate": 5e-06,
"loss": 0.6858,
"step": 2890
},
{
"epoch": 1.864951768488746,
"grad_norm": 0.4137505888938904,
"learning_rate": 5e-06,
"loss": 0.6808,
"step": 2900
},
{
"epoch": 1.8713826366559485,
"grad_norm": 0.46201327443122864,
"learning_rate": 5e-06,
"loss": 0.6798,
"step": 2910
},
{
"epoch": 1.877813504823151,
"grad_norm": 0.4486853778362274,
"learning_rate": 5e-06,
"loss": 0.6862,
"step": 2920
},
{
"epoch": 1.8842443729903537,
"grad_norm": 0.4082019329071045,
"learning_rate": 5e-06,
"loss": 0.6843,
"step": 2930
},
{
"epoch": 1.8906752411575563,
"grad_norm": 0.48371437191963196,
"learning_rate": 5e-06,
"loss": 0.6781,
"step": 2940
},
{
"epoch": 1.897106109324759,
"grad_norm": 0.4703909456729889,
"learning_rate": 5e-06,
"loss": 0.6843,
"step": 2950
},
{
"epoch": 1.9035369774919615,
"grad_norm": 0.40100324153900146,
"learning_rate": 5e-06,
"loss": 0.6838,
"step": 2960
},
{
"epoch": 1.909967845659164,
"grad_norm": 0.4890632629394531,
"learning_rate": 5e-06,
"loss": 0.6771,
"step": 2970
},
{
"epoch": 1.9163987138263665,
"grad_norm": 0.4435786008834839,
"learning_rate": 5e-06,
"loss": 0.6812,
"step": 2980
},
{
"epoch": 1.922829581993569,
"grad_norm": 0.43092137575149536,
"learning_rate": 5e-06,
"loss": 0.6723,
"step": 2990
},
{
"epoch": 1.9292604501607717,
"grad_norm": 0.45887503027915955,
"learning_rate": 5e-06,
"loss": 0.6811,
"step": 3000
},
{
"epoch": 1.9356913183279743,
"grad_norm": 0.4193710386753082,
"learning_rate": 5e-06,
"loss": 0.6801,
"step": 3010
},
{
"epoch": 1.942122186495177,
"grad_norm": 0.45064231753349304,
"learning_rate": 5e-06,
"loss": 0.6718,
"step": 3020
},
{
"epoch": 1.9485530546623795,
"grad_norm": 0.42754465341567993,
"learning_rate": 5e-06,
"loss": 0.6736,
"step": 3030
},
{
"epoch": 1.954983922829582,
"grad_norm": 0.41854625940322876,
"learning_rate": 5e-06,
"loss": 0.6818,
"step": 3040
},
{
"epoch": 1.9614147909967845,
"grad_norm": 0.4096625745296478,
"learning_rate": 5e-06,
"loss": 0.6787,
"step": 3050
},
{
"epoch": 1.967845659163987,
"grad_norm": 0.41215813159942627,
"learning_rate": 5e-06,
"loss": 0.6752,
"step": 3060
},
{
"epoch": 1.9742765273311897,
"grad_norm": 0.47351738810539246,
"learning_rate": 5e-06,
"loss": 0.6835,
"step": 3070
},
{
"epoch": 1.9807073954983923,
"grad_norm": 0.4130474925041199,
"learning_rate": 5e-06,
"loss": 0.6803,
"step": 3080
},
{
"epoch": 1.987138263665595,
"grad_norm": 0.41312044858932495,
"learning_rate": 5e-06,
"loss": 0.6729,
"step": 3090
},
{
"epoch": 1.9935691318327975,
"grad_norm": 0.40591350197792053,
"learning_rate": 5e-06,
"loss": 0.6722,
"step": 3100
},
{
"epoch": 2.0,
"grad_norm": 0.40826907753944397,
"learning_rate": 5e-06,
"loss": 0.686,
"step": 3110
},
{
"epoch": 2.0,
"eval_loss": 0.7126035690307617,
"eval_runtime": 139.886,
"eval_samples_per_second": 299.551,
"eval_steps_per_second": 1.172,
"step": 3110
},
{
"epoch": 2.0064308681672025,
"grad_norm": 0.561937153339386,
"learning_rate": 5e-06,
"loss": 0.6404,
"step": 3120
},
{
"epoch": 2.012861736334405,
"grad_norm": 0.5182865858078003,
"learning_rate": 5e-06,
"loss": 0.64,
"step": 3130
},
{
"epoch": 2.0192926045016075,
"grad_norm": 0.5018469095230103,
"learning_rate": 5e-06,
"loss": 0.6359,
"step": 3140
},
{
"epoch": 2.0257234726688105,
"grad_norm": 0.4944702982902527,
"learning_rate": 5e-06,
"loss": 0.6381,
"step": 3150
},
{
"epoch": 2.032154340836013,
"grad_norm": 0.4453904330730438,
"learning_rate": 5e-06,
"loss": 0.6372,
"step": 3160
},
{
"epoch": 2.0385852090032155,
"grad_norm": 0.43754857778549194,
"learning_rate": 5e-06,
"loss": 0.6394,
"step": 3170
},
{
"epoch": 2.045016077170418,
"grad_norm": 0.43891504406929016,
"learning_rate": 5e-06,
"loss": 0.6429,
"step": 3180
},
{
"epoch": 2.0514469453376205,
"grad_norm": 0.42905229330062866,
"learning_rate": 5e-06,
"loss": 0.6352,
"step": 3190
},
{
"epoch": 2.057877813504823,
"grad_norm": 0.4976702928543091,
"learning_rate": 5e-06,
"loss": 0.6394,
"step": 3200
},
{
"epoch": 2.0643086816720255,
"grad_norm": 0.4487721621990204,
"learning_rate": 5e-06,
"loss": 0.6367,
"step": 3210
},
{
"epoch": 2.0707395498392285,
"grad_norm": 0.48409563302993774,
"learning_rate": 5e-06,
"loss": 0.6364,
"step": 3220
},
{
"epoch": 2.077170418006431,
"grad_norm": 0.4372307360172272,
"learning_rate": 5e-06,
"loss": 0.6441,
"step": 3230
},
{
"epoch": 2.0836012861736335,
"grad_norm": 0.46748873591423035,
"learning_rate": 5e-06,
"loss": 0.6364,
"step": 3240
},
{
"epoch": 2.090032154340836,
"grad_norm": 0.46158337593078613,
"learning_rate": 5e-06,
"loss": 0.6334,
"step": 3250
},
{
"epoch": 2.0964630225080385,
"grad_norm": 0.43315762281417847,
"learning_rate": 5e-06,
"loss": 0.6395,
"step": 3260
},
{
"epoch": 2.102893890675241,
"grad_norm": 0.4499836564064026,
"learning_rate": 5e-06,
"loss": 0.6444,
"step": 3270
},
{
"epoch": 2.1093247588424435,
"grad_norm": 0.45043113827705383,
"learning_rate": 5e-06,
"loss": 0.6384,
"step": 3280
},
{
"epoch": 2.1157556270096465,
"grad_norm": 0.4223954677581787,
"learning_rate": 5e-06,
"loss": 0.638,
"step": 3290
},
{
"epoch": 2.122186495176849,
"grad_norm": 0.45464426279067993,
"learning_rate": 5e-06,
"loss": 0.6466,
"step": 3300
},
{
"epoch": 2.1286173633440515,
"grad_norm": 0.4449687898159027,
"learning_rate": 5e-06,
"loss": 0.6297,
"step": 3310
},
{
"epoch": 2.135048231511254,
"grad_norm": 0.4286421537399292,
"learning_rate": 5e-06,
"loss": 0.6408,
"step": 3320
},
{
"epoch": 2.1414790996784565,
"grad_norm": 0.4531044065952301,
"learning_rate": 5e-06,
"loss": 0.6416,
"step": 3330
},
{
"epoch": 2.147909967845659,
"grad_norm": 0.44140374660491943,
"learning_rate": 5e-06,
"loss": 0.636,
"step": 3340
},
{
"epoch": 2.154340836012862,
"grad_norm": 0.4317072927951813,
"learning_rate": 5e-06,
"loss": 0.6395,
"step": 3350
},
{
"epoch": 2.1607717041800645,
"grad_norm": 0.47132372856140137,
"learning_rate": 5e-06,
"loss": 0.6233,
"step": 3360
},
{
"epoch": 2.167202572347267,
"grad_norm": 0.4424266815185547,
"learning_rate": 5e-06,
"loss": 0.6417,
"step": 3370
},
{
"epoch": 2.1736334405144695,
"grad_norm": 0.42858994007110596,
"learning_rate": 5e-06,
"loss": 0.6418,
"step": 3380
},
{
"epoch": 2.180064308681672,
"grad_norm": 0.4775191843509674,
"learning_rate": 5e-06,
"loss": 0.6369,
"step": 3390
},
{
"epoch": 2.1864951768488745,
"grad_norm": 0.46210339665412903,
"learning_rate": 5e-06,
"loss": 0.6427,
"step": 3400
},
{
"epoch": 2.192926045016077,
"grad_norm": 0.46885842084884644,
"learning_rate": 5e-06,
"loss": 0.6456,
"step": 3410
},
{
"epoch": 2.19935691318328,
"grad_norm": 0.4760117828845978,
"learning_rate": 5e-06,
"loss": 0.6435,
"step": 3420
},
{
"epoch": 2.2057877813504825,
"grad_norm": 0.5036518573760986,
"learning_rate": 5e-06,
"loss": 0.6383,
"step": 3430
},
{
"epoch": 2.212218649517685,
"grad_norm": 0.4869937002658844,
"learning_rate": 5e-06,
"loss": 0.634,
"step": 3440
},
{
"epoch": 2.2186495176848875,
"grad_norm": 0.4235919117927551,
"learning_rate": 5e-06,
"loss": 0.6383,
"step": 3450
},
{
"epoch": 2.22508038585209,
"grad_norm": 0.4805637001991272,
"learning_rate": 5e-06,
"loss": 0.6413,
"step": 3460
},
{
"epoch": 2.2315112540192925,
"grad_norm": 0.4369070827960968,
"learning_rate": 5e-06,
"loss": 0.6348,
"step": 3470
},
{
"epoch": 2.237942122186495,
"grad_norm": 0.43729808926582336,
"learning_rate": 5e-06,
"loss": 0.6489,
"step": 3480
},
{
"epoch": 2.244372990353698,
"grad_norm": 0.514873206615448,
"learning_rate": 5e-06,
"loss": 0.6451,
"step": 3490
},
{
"epoch": 2.2508038585209005,
"grad_norm": 0.4235300123691559,
"learning_rate": 5e-06,
"loss": 0.6355,
"step": 3500
},
{
"epoch": 2.257234726688103,
"grad_norm": 0.4553775191307068,
"learning_rate": 5e-06,
"loss": 0.6374,
"step": 3510
},
{
"epoch": 2.2636655948553055,
"grad_norm": 0.444014310836792,
"learning_rate": 5e-06,
"loss": 0.6504,
"step": 3520
},
{
"epoch": 2.270096463022508,
"grad_norm": 0.4582684636116028,
"learning_rate": 5e-06,
"loss": 0.6338,
"step": 3530
},
{
"epoch": 2.2765273311897105,
"grad_norm": 0.5020269751548767,
"learning_rate": 5e-06,
"loss": 0.634,
"step": 3540
},
{
"epoch": 2.282958199356913,
"grad_norm": 0.44650107622146606,
"learning_rate": 5e-06,
"loss": 0.6382,
"step": 3550
},
{
"epoch": 2.289389067524116,
"grad_norm": 0.46265995502471924,
"learning_rate": 5e-06,
"loss": 0.6351,
"step": 3560
},
{
"epoch": 2.2958199356913185,
"grad_norm": 0.44239240884780884,
"learning_rate": 5e-06,
"loss": 0.6406,
"step": 3570
},
{
"epoch": 2.302250803858521,
"grad_norm": 0.49851298332214355,
"learning_rate": 5e-06,
"loss": 0.6373,
"step": 3580
},
{
"epoch": 2.3086816720257235,
"grad_norm": 0.44977161288261414,
"learning_rate": 5e-06,
"loss": 0.637,
"step": 3590
},
{
"epoch": 2.315112540192926,
"grad_norm": 0.47006750106811523,
"learning_rate": 5e-06,
"loss": 0.6429,
"step": 3600
},
{
"epoch": 2.3215434083601285,
"grad_norm": 0.43386831879615784,
"learning_rate": 5e-06,
"loss": 0.6411,
"step": 3610
},
{
"epoch": 2.327974276527331,
"grad_norm": 0.4304748475551605,
"learning_rate": 5e-06,
"loss": 0.6404,
"step": 3620
},
{
"epoch": 2.334405144694534,
"grad_norm": 0.4528113901615143,
"learning_rate": 5e-06,
"loss": 0.6409,
"step": 3630
},
{
"epoch": 2.3408360128617365,
"grad_norm": 0.43319591879844666,
"learning_rate": 5e-06,
"loss": 0.6397,
"step": 3640
},
{
"epoch": 2.347266881028939,
"grad_norm": 0.45046094059944153,
"learning_rate": 5e-06,
"loss": 0.6437,
"step": 3650
},
{
"epoch": 2.3536977491961415,
"grad_norm": 0.4646282494068146,
"learning_rate": 5e-06,
"loss": 0.6473,
"step": 3660
},
{
"epoch": 2.360128617363344,
"grad_norm": 0.4470469355583191,
"learning_rate": 5e-06,
"loss": 0.6337,
"step": 3670
},
{
"epoch": 2.3665594855305465,
"grad_norm": 0.45889395475387573,
"learning_rate": 5e-06,
"loss": 0.6393,
"step": 3680
},
{
"epoch": 2.372990353697749,
"grad_norm": 0.41356027126312256,
"learning_rate": 5e-06,
"loss": 0.6354,
"step": 3690
},
{
"epoch": 2.379421221864952,
"grad_norm": 0.4529729187488556,
"learning_rate": 5e-06,
"loss": 0.6403,
"step": 3700
},
{
"epoch": 2.3858520900321545,
"grad_norm": 0.4174403250217438,
"learning_rate": 5e-06,
"loss": 0.6377,
"step": 3710
},
{
"epoch": 2.392282958199357,
"grad_norm": 0.4575382173061371,
"learning_rate": 5e-06,
"loss": 0.6391,
"step": 3720
},
{
"epoch": 2.3987138263665595,
"grad_norm": 0.4538198709487915,
"learning_rate": 5e-06,
"loss": 0.6415,
"step": 3730
},
{
"epoch": 2.405144694533762,
"grad_norm": 0.4399804472923279,
"learning_rate": 5e-06,
"loss": 0.6348,
"step": 3740
},
{
"epoch": 2.4115755627009645,
"grad_norm": 0.4382459819316864,
"learning_rate": 5e-06,
"loss": 0.6415,
"step": 3750
},
{
"epoch": 2.418006430868167,
"grad_norm": 0.42854952812194824,
"learning_rate": 5e-06,
"loss": 0.6377,
"step": 3760
},
{
"epoch": 2.42443729903537,
"grad_norm": 0.4322606921195984,
"learning_rate": 5e-06,
"loss": 0.6435,
"step": 3770
},
{
"epoch": 2.4308681672025725,
"grad_norm": 0.45412078499794006,
"learning_rate": 5e-06,
"loss": 0.6401,
"step": 3780
},
{
"epoch": 2.437299035369775,
"grad_norm": 0.4531524181365967,
"learning_rate": 5e-06,
"loss": 0.6454,
"step": 3790
},
{
"epoch": 2.4437299035369775,
"grad_norm": 0.44421976804733276,
"learning_rate": 5e-06,
"loss": 0.6484,
"step": 3800
},
{
"epoch": 2.45016077170418,
"grad_norm": 0.4720653295516968,
"learning_rate": 5e-06,
"loss": 0.6431,
"step": 3810
},
{
"epoch": 2.4565916398713825,
"grad_norm": 0.4742264747619629,
"learning_rate": 5e-06,
"loss": 0.6371,
"step": 3820
},
{
"epoch": 2.463022508038585,
"grad_norm": 0.43964919447898865,
"learning_rate": 5e-06,
"loss": 0.6398,
"step": 3830
},
{
"epoch": 2.469453376205788,
"grad_norm": 0.43848881125450134,
"learning_rate": 5e-06,
"loss": 0.6419,
"step": 3840
},
{
"epoch": 2.4758842443729905,
"grad_norm": 0.4461026191711426,
"learning_rate": 5e-06,
"loss": 0.6379,
"step": 3850
},
{
"epoch": 2.482315112540193,
"grad_norm": 0.4415052831172943,
"learning_rate": 5e-06,
"loss": 0.6439,
"step": 3860
},
{
"epoch": 2.4887459807073955,
"grad_norm": 0.4191666543483734,
"learning_rate": 5e-06,
"loss": 0.6446,
"step": 3870
},
{
"epoch": 2.495176848874598,
"grad_norm": 0.43842655420303345,
"learning_rate": 5e-06,
"loss": 0.6439,
"step": 3880
},
{
"epoch": 2.5016077170418005,
"grad_norm": 0.4282081127166748,
"learning_rate": 5e-06,
"loss": 0.6479,
"step": 3890
},
{
"epoch": 2.508038585209003,
"grad_norm": 0.4626299738883972,
"learning_rate": 5e-06,
"loss": 0.6448,
"step": 3900
},
{
"epoch": 2.514469453376206,
"grad_norm": 0.44208213686943054,
"learning_rate": 5e-06,
"loss": 0.6439,
"step": 3910
},
{
"epoch": 2.5209003215434085,
"grad_norm": 0.43402865529060364,
"learning_rate": 5e-06,
"loss": 0.6369,
"step": 3920
},
{
"epoch": 2.527331189710611,
"grad_norm": 0.475366473197937,
"learning_rate": 5e-06,
"loss": 0.6446,
"step": 3930
},
{
"epoch": 2.5337620578778135,
"grad_norm": 0.4425564408302307,
"learning_rate": 5e-06,
"loss": 0.6384,
"step": 3940
},
{
"epoch": 2.540192926045016,
"grad_norm": 0.43618571758270264,
"learning_rate": 5e-06,
"loss": 0.6408,
"step": 3950
},
{
"epoch": 2.5466237942122185,
"grad_norm": 0.49698591232299805,
"learning_rate": 5e-06,
"loss": 0.6303,
"step": 3960
},
{
"epoch": 2.553054662379421,
"grad_norm": 0.5115300416946411,
"learning_rate": 5e-06,
"loss": 0.651,
"step": 3970
},
{
"epoch": 2.559485530546624,
"grad_norm": 0.6572542190551758,
"learning_rate": 5e-06,
"loss": 0.643,
"step": 3980
},
{
"epoch": 2.5659163987138265,
"grad_norm": 0.42369475960731506,
"learning_rate": 5e-06,
"loss": 0.6388,
"step": 3990
},
{
"epoch": 2.572347266881029,
"grad_norm": 0.44530463218688965,
"learning_rate": 5e-06,
"loss": 0.6418,
"step": 4000
},
{
"epoch": 2.5787781350482315,
"grad_norm": 0.49780553579330444,
"learning_rate": 5e-06,
"loss": 0.6334,
"step": 4010
},
{
"epoch": 2.585209003215434,
"grad_norm": 0.45106691122055054,
"learning_rate": 5e-06,
"loss": 0.6398,
"step": 4020
},
{
"epoch": 2.5916398713826365,
"grad_norm": 0.43149319291114807,
"learning_rate": 5e-06,
"loss": 0.6392,
"step": 4030
},
{
"epoch": 2.598070739549839,
"grad_norm": 0.44727641344070435,
"learning_rate": 5e-06,
"loss": 0.643,
"step": 4040
},
{
"epoch": 2.604501607717042,
"grad_norm": 0.46136513352394104,
"learning_rate": 5e-06,
"loss": 0.6407,
"step": 4050
},
{
"epoch": 2.6109324758842445,
"grad_norm": 0.43373093008995056,
"learning_rate": 5e-06,
"loss": 0.635,
"step": 4060
},
{
"epoch": 2.617363344051447,
"grad_norm": 0.42928022146224976,
"learning_rate": 5e-06,
"loss": 0.6364,
"step": 4070
},
{
"epoch": 2.6237942122186495,
"grad_norm": 0.4322867691516876,
"learning_rate": 5e-06,
"loss": 0.6411,
"step": 4080
},
{
"epoch": 2.630225080385852,
"grad_norm": 0.4528902471065521,
"learning_rate": 5e-06,
"loss": 0.6382,
"step": 4090
},
{
"epoch": 2.6366559485530545,
"grad_norm": 0.45928648114204407,
"learning_rate": 5e-06,
"loss": 0.6429,
"step": 4100
},
{
"epoch": 2.643086816720257,
"grad_norm": 0.4491860270500183,
"learning_rate": 5e-06,
"loss": 0.6378,
"step": 4110
},
{
"epoch": 2.64951768488746,
"grad_norm": 0.44847381114959717,
"learning_rate": 5e-06,
"loss": 0.6444,
"step": 4120
},
{
"epoch": 2.6559485530546625,
"grad_norm": 0.42893797159194946,
"learning_rate": 5e-06,
"loss": 0.6424,
"step": 4130
},
{
"epoch": 2.662379421221865,
"grad_norm": 0.4790765345096588,
"learning_rate": 5e-06,
"loss": 0.6402,
"step": 4140
},
{
"epoch": 2.6688102893890675,
"grad_norm": 0.4363596737384796,
"learning_rate": 5e-06,
"loss": 0.6402,
"step": 4150
},
{
"epoch": 2.67524115755627,
"grad_norm": 0.4559105634689331,
"learning_rate": 5e-06,
"loss": 0.6475,
"step": 4160
},
{
"epoch": 2.6816720257234725,
"grad_norm": 0.4630337059497833,
"learning_rate": 5e-06,
"loss": 0.6443,
"step": 4170
},
{
"epoch": 2.688102893890675,
"grad_norm": 0.4628975987434387,
"learning_rate": 5e-06,
"loss": 0.6425,
"step": 4180
},
{
"epoch": 2.694533762057878,
"grad_norm": 0.507043719291687,
"learning_rate": 5e-06,
"loss": 0.6385,
"step": 4190
},
{
"epoch": 2.7009646302250805,
"grad_norm": 0.4438357353210449,
"learning_rate": 5e-06,
"loss": 0.6415,
"step": 4200
},
{
"epoch": 2.707395498392283,
"grad_norm": 0.4772716462612152,
"learning_rate": 5e-06,
"loss": 0.6392,
"step": 4210
},
{
"epoch": 2.7138263665594855,
"grad_norm": 0.4417891502380371,
"learning_rate": 5e-06,
"loss": 0.6365,
"step": 4220
},
{
"epoch": 2.720257234726688,
"grad_norm": 0.44056421518325806,
"learning_rate": 5e-06,
"loss": 0.6365,
"step": 4230
},
{
"epoch": 2.7266881028938905,
"grad_norm": 0.4614117741584778,
"learning_rate": 5e-06,
"loss": 0.6425,
"step": 4240
},
{
"epoch": 2.733118971061093,
"grad_norm": 0.5050578117370605,
"learning_rate": 5e-06,
"loss": 0.6471,
"step": 4250
},
{
"epoch": 2.739549839228296,
"grad_norm": 0.4652516543865204,
"learning_rate": 5e-06,
"loss": 0.6356,
"step": 4260
},
{
"epoch": 2.7459807073954985,
"grad_norm": 0.44051194190979004,
"learning_rate": 5e-06,
"loss": 0.647,
"step": 4270
},
{
"epoch": 2.752411575562701,
"grad_norm": 0.45722419023513794,
"learning_rate": 5e-06,
"loss": 0.64,
"step": 4280
},
{
"epoch": 2.7588424437299035,
"grad_norm": 0.4401618242263794,
"learning_rate": 5e-06,
"loss": 0.6439,
"step": 4290
},
{
"epoch": 2.765273311897106,
"grad_norm": 0.4500727653503418,
"learning_rate": 5e-06,
"loss": 0.6355,
"step": 4300
},
{
"epoch": 2.7717041800643085,
"grad_norm": 0.44464367628097534,
"learning_rate": 5e-06,
"loss": 0.641,
"step": 4310
},
{
"epoch": 2.778135048231511,
"grad_norm": 0.433173805475235,
"learning_rate": 5e-06,
"loss": 0.6479,
"step": 4320
},
{
"epoch": 2.784565916398714,
"grad_norm": 0.44234412908554077,
"learning_rate": 5e-06,
"loss": 0.6474,
"step": 4330
},
{
"epoch": 2.7909967845659165,
"grad_norm": 0.4479934275150299,
"learning_rate": 5e-06,
"loss": 0.6428,
"step": 4340
},
{
"epoch": 2.797427652733119,
"grad_norm": 0.44619840383529663,
"learning_rate": 5e-06,
"loss": 0.6441,
"step": 4350
},
{
"epoch": 2.8038585209003215,
"grad_norm": 0.4315251111984253,
"learning_rate": 5e-06,
"loss": 0.6477,
"step": 4360
},
{
"epoch": 2.810289389067524,
"grad_norm": 0.43586409091949463,
"learning_rate": 5e-06,
"loss": 0.6504,
"step": 4370
},
{
"epoch": 2.816720257234727,
"grad_norm": 0.4625302851200104,
"learning_rate": 5e-06,
"loss": 0.6523,
"step": 4380
},
{
"epoch": 2.823151125401929,
"grad_norm": 0.46072930097579956,
"learning_rate": 5e-06,
"loss": 0.6423,
"step": 4390
},
{
"epoch": 2.829581993569132,
"grad_norm": 0.4475337266921997,
"learning_rate": 5e-06,
"loss": 0.6483,
"step": 4400
},
{
"epoch": 2.8360128617363345,
"grad_norm": 0.43071475625038147,
"learning_rate": 5e-06,
"loss": 0.6426,
"step": 4410
},
{
"epoch": 2.842443729903537,
"grad_norm": 0.4402061700820923,
"learning_rate": 5e-06,
"loss": 0.6383,
"step": 4420
},
{
"epoch": 2.8488745980707395,
"grad_norm": 0.47659188508987427,
"learning_rate": 5e-06,
"loss": 0.6378,
"step": 4430
},
{
"epoch": 2.855305466237942,
"grad_norm": 0.44324415922164917,
"learning_rate": 5e-06,
"loss": 0.6445,
"step": 4440
},
{
"epoch": 2.861736334405145,
"grad_norm": 0.5019335746765137,
"learning_rate": 5e-06,
"loss": 0.6429,
"step": 4450
},
{
"epoch": 2.868167202572347,
"grad_norm": 0.47943827509880066,
"learning_rate": 5e-06,
"loss": 0.6403,
"step": 4460
},
{
"epoch": 2.87459807073955,
"grad_norm": 0.4461328387260437,
"learning_rate": 5e-06,
"loss": 0.6423,
"step": 4470
},
{
"epoch": 2.8810289389067525,
"grad_norm": 0.4263225495815277,
"learning_rate": 5e-06,
"loss": 0.6379,
"step": 4480
},
{
"epoch": 2.887459807073955,
"grad_norm": 0.45077577233314514,
"learning_rate": 5e-06,
"loss": 0.6419,
"step": 4490
},
{
"epoch": 2.8938906752411575,
"grad_norm": 0.4050474762916565,
"learning_rate": 5e-06,
"loss": 0.6361,
"step": 4500
},
{
"epoch": 2.90032154340836,
"grad_norm": 0.4340299069881439,
"learning_rate": 5e-06,
"loss": 0.6386,
"step": 4510
},
{
"epoch": 2.906752411575563,
"grad_norm": 0.42679664492607117,
"learning_rate": 5e-06,
"loss": 0.6423,
"step": 4520
},
{
"epoch": 2.913183279742765,
"grad_norm": 0.4645717144012451,
"learning_rate": 5e-06,
"loss": 0.6422,
"step": 4530
},
{
"epoch": 2.919614147909968,
"grad_norm": 0.471055805683136,
"learning_rate": 5e-06,
"loss": 0.6333,
"step": 4540
},
{
"epoch": 2.9260450160771705,
"grad_norm": 0.5037959814071655,
"learning_rate": 5e-06,
"loss": 0.6419,
"step": 4550
},
{
"epoch": 2.932475884244373,
"grad_norm": 0.4540598690509796,
"learning_rate": 5e-06,
"loss": 0.6393,
"step": 4560
},
{
"epoch": 2.9389067524115755,
"grad_norm": 0.44270047545433044,
"learning_rate": 5e-06,
"loss": 0.6367,
"step": 4570
},
{
"epoch": 2.945337620578778,
"grad_norm": 0.43946129083633423,
"learning_rate": 5e-06,
"loss": 0.6402,
"step": 4580
},
{
"epoch": 2.951768488745981,
"grad_norm": 0.46501582860946655,
"learning_rate": 5e-06,
"loss": 0.6372,
"step": 4590
},
{
"epoch": 2.958199356913183,
"grad_norm": 0.4638145864009857,
"learning_rate": 5e-06,
"loss": 0.6479,
"step": 4600
},
{
"epoch": 2.964630225080386,
"grad_norm": 0.4363510310649872,
"learning_rate": 5e-06,
"loss": 0.6391,
"step": 4610
},
{
"epoch": 2.9710610932475885,
"grad_norm": 0.42436662316322327,
"learning_rate": 5e-06,
"loss": 0.643,
"step": 4620
},
{
"epoch": 2.977491961414791,
"grad_norm": 0.4569937288761139,
"learning_rate": 5e-06,
"loss": 0.6369,
"step": 4630
},
{
"epoch": 2.9839228295819935,
"grad_norm": 0.4475838243961334,
"learning_rate": 5e-06,
"loss": 0.6402,
"step": 4640
},
{
"epoch": 2.990353697749196,
"grad_norm": 0.47496703267097473,
"learning_rate": 5e-06,
"loss": 0.6315,
"step": 4650
},
{
"epoch": 2.996784565916399,
"grad_norm": 0.4460706114768982,
"learning_rate": 5e-06,
"loss": 0.6421,
"step": 4660
},
{
"epoch": 3.0,
"eval_loss": 0.7122252583503723,
"eval_runtime": 140.1434,
"eval_samples_per_second": 299.001,
"eval_steps_per_second": 1.17,
"step": 4665
},
{
"epoch": 3.0,
"step": 4665,
"total_flos": 2.2026686217575832e+20,
"train_loss": 0.6892199146274841,
"train_runtime": 30399.4314,
"train_samples_per_second": 78.569,
"train_steps_per_second": 0.153
}
],
"logging_steps": 10,
"max_steps": 4665,
"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": 2.2026686217575832e+20,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}