rqadri's picture
Upload folder using huggingface_hub
3f80e87 verified
Raw History Blame Contribute Delete
180 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9476758953517908,
"eval_steps": 500,
"global_step": 11193,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008466683600033867,
"grad_norm": 2.1896274089813232,
"learning_rate": 1.1061797752808989e-06,
"loss": 0.9007,
"step": 10
},
{
"epoch": 0.0016933367200067733,
"grad_norm": 1.3733998537063599,
"learning_rate": 2.2241573033707866e-06,
"loss": 0.8719,
"step": 20
},
{
"epoch": 0.00254000508001016,
"grad_norm": 1.1982183456420898,
"learning_rate": 3.342134831460675e-06,
"loss": 0.8299,
"step": 30
},
{
"epoch": 0.0033866734400135466,
"grad_norm": 1.1160142421722412,
"learning_rate": 4.4601123595505624e-06,
"loss": 0.7803,
"step": 40
},
{
"epoch": 0.004233341800016934,
"grad_norm": 0.9138423204421997,
"learning_rate": 5.5780898876404495e-06,
"loss": 0.7622,
"step": 50
},
{
"epoch": 0.00508001016002032,
"grad_norm": 0.8700115084648132,
"learning_rate": 6.6960674157303374e-06,
"loss": 0.7332,
"step": 60
},
{
"epoch": 0.005926678520023707,
"grad_norm": 0.8024980425834656,
"learning_rate": 7.814044943820226e-06,
"loss": 0.7072,
"step": 70
},
{
"epoch": 0.006773346880027093,
"grad_norm": 0.8063226342201233,
"learning_rate": 8.932022471910112e-06,
"loss": 0.7082,
"step": 80
},
{
"epoch": 0.00762001524003048,
"grad_norm": 0.7324275970458984,
"learning_rate": 1.005e-05,
"loss": 0.7095,
"step": 90
},
{
"epoch": 0.008466683600033867,
"grad_norm": 0.8663532137870789,
"learning_rate": 1.1167977528089888e-05,
"loss": 0.6899,
"step": 100
},
{
"epoch": 0.009313351960037254,
"grad_norm": 0.8148631453514099,
"learning_rate": 1.2285955056179776e-05,
"loss": 0.6984,
"step": 110
},
{
"epoch": 0.01016002032004064,
"grad_norm": 0.7821786403656006,
"learning_rate": 1.3403932584269664e-05,
"loss": 0.7066,
"step": 120
},
{
"epoch": 0.011006688680044027,
"grad_norm": 0.7769770622253418,
"learning_rate": 1.4521910112359552e-05,
"loss": 0.6908,
"step": 130
},
{
"epoch": 0.011853357040047413,
"grad_norm": 0.9013803601264954,
"learning_rate": 1.563988764044944e-05,
"loss": 0.6885,
"step": 140
},
{
"epoch": 0.0127000254000508,
"grad_norm": 0.7101280689239502,
"learning_rate": 1.6757865168539328e-05,
"loss": 0.6886,
"step": 150
},
{
"epoch": 0.013546693760054187,
"grad_norm": 0.8616020679473877,
"learning_rate": 1.7875842696629214e-05,
"loss": 0.6849,
"step": 160
},
{
"epoch": 0.014393362120057573,
"grad_norm": 0.8392877578735352,
"learning_rate": 1.89938202247191e-05,
"loss": 0.6933,
"step": 170
},
{
"epoch": 0.01524003048006096,
"grad_norm": 0.766579806804657,
"learning_rate": 2e-05,
"loss": 0.7048,
"step": 180
},
{
"epoch": 0.016086698840064348,
"grad_norm": 0.7274855375289917,
"learning_rate": 2e-05,
"loss": 0.7039,
"step": 190
},
{
"epoch": 0.016933367200067734,
"grad_norm": 0.7656974792480469,
"learning_rate": 2e-05,
"loss": 0.6829,
"step": 200
},
{
"epoch": 0.01778003556007112,
"grad_norm": 0.7630816102027893,
"learning_rate": 2e-05,
"loss": 0.6948,
"step": 210
},
{
"epoch": 0.018626703920074508,
"grad_norm": 0.7607164978981018,
"learning_rate": 2e-05,
"loss": 0.6976,
"step": 220
},
{
"epoch": 0.019473372280077894,
"grad_norm": 0.6640747785568237,
"learning_rate": 2e-05,
"loss": 0.6529,
"step": 230
},
{
"epoch": 0.02032004064008128,
"grad_norm": 0.648815393447876,
"learning_rate": 2e-05,
"loss": 0.687,
"step": 240
},
{
"epoch": 0.021166709000084667,
"grad_norm": 0.5993350744247437,
"learning_rate": 2e-05,
"loss": 0.693,
"step": 250
},
{
"epoch": 0.022013377360088054,
"grad_norm": 0.6671707630157471,
"learning_rate": 2e-05,
"loss": 0.7208,
"step": 260
},
{
"epoch": 0.02286004572009144,
"grad_norm": 0.5551834106445312,
"learning_rate": 2e-05,
"loss": 0.6958,
"step": 270
},
{
"epoch": 0.023706714080094827,
"grad_norm": 0.5955666303634644,
"learning_rate": 2e-05,
"loss": 0.685,
"step": 280
},
{
"epoch": 0.024553382440098213,
"grad_norm": 0.5701448917388916,
"learning_rate": 2e-05,
"loss": 0.6796,
"step": 290
},
{
"epoch": 0.0254000508001016,
"grad_norm": 0.5824018716812134,
"learning_rate": 2e-05,
"loss": 0.6841,
"step": 300
},
{
"epoch": 0.026246719160104987,
"grad_norm": 0.576776921749115,
"learning_rate": 2e-05,
"loss": 0.6563,
"step": 310
},
{
"epoch": 0.027093387520108373,
"grad_norm": 0.5411778688430786,
"learning_rate": 2e-05,
"loss": 0.6835,
"step": 320
},
{
"epoch": 0.02794005588011176,
"grad_norm": 0.5345405340194702,
"learning_rate": 2e-05,
"loss": 0.6657,
"step": 330
},
{
"epoch": 0.028786724240115146,
"grad_norm": 0.5346488952636719,
"learning_rate": 2e-05,
"loss": 0.6951,
"step": 340
},
{
"epoch": 0.029633392600118533,
"grad_norm": 0.49902835488319397,
"learning_rate": 2e-05,
"loss": 0.664,
"step": 350
},
{
"epoch": 0.03048006096012192,
"grad_norm": 0.6449501514434814,
"learning_rate": 2e-05,
"loss": 0.6737,
"step": 360
},
{
"epoch": 0.031326729320125306,
"grad_norm": 0.487582802772522,
"learning_rate": 2e-05,
"loss": 0.6546,
"step": 370
},
{
"epoch": 0.032173397680128696,
"grad_norm": 0.5169985294342041,
"learning_rate": 2e-05,
"loss": 0.6731,
"step": 380
},
{
"epoch": 0.03302006604013208,
"grad_norm": 0.5427067279815674,
"learning_rate": 2e-05,
"loss": 0.6882,
"step": 390
},
{
"epoch": 0.03386673440013547,
"grad_norm": 0.5355451107025146,
"learning_rate": 2e-05,
"loss": 0.6955,
"step": 400
},
{
"epoch": 0.03471340276013885,
"grad_norm": 0.6196058392524719,
"learning_rate": 2e-05,
"loss": 0.6807,
"step": 410
},
{
"epoch": 0.03556007112014224,
"grad_norm": 0.5216856598854065,
"learning_rate": 2e-05,
"loss": 0.6602,
"step": 420
},
{
"epoch": 0.036406739480145625,
"grad_norm": 0.5485526323318481,
"learning_rate": 2e-05,
"loss": 0.6846,
"step": 430
},
{
"epoch": 0.037253407840149015,
"grad_norm": 0.48402827978134155,
"learning_rate": 2e-05,
"loss": 0.6669,
"step": 440
},
{
"epoch": 0.0381000762001524,
"grad_norm": 0.48090001940727234,
"learning_rate": 2e-05,
"loss": 0.6651,
"step": 450
},
{
"epoch": 0.03894674456015579,
"grad_norm": 1.9493638277053833,
"learning_rate": 2e-05,
"loss": 0.6813,
"step": 460
},
{
"epoch": 0.03979341292015917,
"grad_norm": 0.5349039435386658,
"learning_rate": 2e-05,
"loss": 0.6901,
"step": 470
},
{
"epoch": 0.04064008128016256,
"grad_norm": 0.4926290214061737,
"learning_rate": 2e-05,
"loss": 0.6514,
"step": 480
},
{
"epoch": 0.041486749640165944,
"grad_norm": 0.6464523077011108,
"learning_rate": 2e-05,
"loss": 0.6758,
"step": 490
},
{
"epoch": 0.042333418000169334,
"grad_norm": 0.5073714256286621,
"learning_rate": 2e-05,
"loss": 0.6941,
"step": 500
},
{
"epoch": 0.04318008636017272,
"grad_norm": 0.5042576193809509,
"learning_rate": 2e-05,
"loss": 0.6788,
"step": 510
},
{
"epoch": 0.04402675472017611,
"grad_norm": 0.4722915589809418,
"learning_rate": 2e-05,
"loss": 0.6555,
"step": 520
},
{
"epoch": 0.04487342308017949,
"grad_norm": 0.5186958312988281,
"learning_rate": 2e-05,
"loss": 0.657,
"step": 530
},
{
"epoch": 0.04572009144018288,
"grad_norm": 0.47601163387298584,
"learning_rate": 2e-05,
"loss": 0.6734,
"step": 540
},
{
"epoch": 0.046566759800186264,
"grad_norm": 0.4465620517730713,
"learning_rate": 2e-05,
"loss": 0.6834,
"step": 550
},
{
"epoch": 0.047413428160189654,
"grad_norm": 0.4941118359565735,
"learning_rate": 2e-05,
"loss": 0.6476,
"step": 560
},
{
"epoch": 0.048260096520193044,
"grad_norm": 0.479648232460022,
"learning_rate": 2e-05,
"loss": 0.6544,
"step": 570
},
{
"epoch": 0.04910676488019643,
"grad_norm": 0.5040650963783264,
"learning_rate": 2e-05,
"loss": 0.6754,
"step": 580
},
{
"epoch": 0.04995343324019982,
"grad_norm": 0.4866141378879547,
"learning_rate": 2e-05,
"loss": 0.6917,
"step": 590
},
{
"epoch": 0.0508001016002032,
"grad_norm": 0.46658095717430115,
"learning_rate": 2e-05,
"loss": 0.6811,
"step": 600
},
{
"epoch": 0.05164676996020659,
"grad_norm": 0.6377661228179932,
"learning_rate": 2e-05,
"loss": 0.6355,
"step": 610
},
{
"epoch": 0.05249343832020997,
"grad_norm": 0.4834534823894501,
"learning_rate": 2e-05,
"loss": 0.6957,
"step": 620
},
{
"epoch": 0.05334010668021336,
"grad_norm": 0.44412001967430115,
"learning_rate": 2e-05,
"loss": 0.6678,
"step": 630
},
{
"epoch": 0.054186775040216746,
"grad_norm": 0.5037946701049805,
"learning_rate": 2e-05,
"loss": 0.6785,
"step": 640
},
{
"epoch": 0.055033443400220136,
"grad_norm": 0.45366835594177246,
"learning_rate": 2e-05,
"loss": 0.676,
"step": 650
},
{
"epoch": 0.05588011176022352,
"grad_norm": 0.4277074337005615,
"learning_rate": 2e-05,
"loss": 0.6591,
"step": 660
},
{
"epoch": 0.05672678012022691,
"grad_norm": 0.4375869035720825,
"learning_rate": 2e-05,
"loss": 0.6616,
"step": 670
},
{
"epoch": 0.05757344848023029,
"grad_norm": 0.46945950388908386,
"learning_rate": 2e-05,
"loss": 0.6838,
"step": 680
},
{
"epoch": 0.05842011684023368,
"grad_norm": 0.4755280315876007,
"learning_rate": 2e-05,
"loss": 0.661,
"step": 690
},
{
"epoch": 0.059266785200237065,
"grad_norm": 0.4614129960536957,
"learning_rate": 2e-05,
"loss": 0.6465,
"step": 700
},
{
"epoch": 0.060113453560240455,
"grad_norm": 0.4619314968585968,
"learning_rate": 2e-05,
"loss": 0.6829,
"step": 710
},
{
"epoch": 0.06096012192024384,
"grad_norm": 0.4906548261642456,
"learning_rate": 2e-05,
"loss": 0.6863,
"step": 720
},
{
"epoch": 0.06180679028024723,
"grad_norm": 0.5654237866401672,
"learning_rate": 2e-05,
"loss": 0.6994,
"step": 730
},
{
"epoch": 0.06265345864025061,
"grad_norm": 0.4611152112483978,
"learning_rate": 2e-05,
"loss": 0.6601,
"step": 740
},
{
"epoch": 0.063500127000254,
"grad_norm": 0.4759562015533447,
"learning_rate": 2e-05,
"loss": 0.6537,
"step": 750
},
{
"epoch": 0.06434679536025739,
"grad_norm": 0.45463666319847107,
"learning_rate": 2e-05,
"loss": 0.6623,
"step": 760
},
{
"epoch": 0.06519346372026077,
"grad_norm": 0.45970118045806885,
"learning_rate": 2e-05,
"loss": 0.6557,
"step": 770
},
{
"epoch": 0.06604013208026416,
"grad_norm": 0.45690014958381653,
"learning_rate": 2e-05,
"loss": 0.6478,
"step": 780
},
{
"epoch": 0.06688680044026754,
"grad_norm": 0.45209041237831116,
"learning_rate": 2e-05,
"loss": 0.651,
"step": 790
},
{
"epoch": 0.06773346880027094,
"grad_norm": 0.5716219544410706,
"learning_rate": 2e-05,
"loss": 0.6647,
"step": 800
},
{
"epoch": 0.06858013716027432,
"grad_norm": 0.43732336163520813,
"learning_rate": 2e-05,
"loss": 0.6604,
"step": 810
},
{
"epoch": 0.0694268055202777,
"grad_norm": 0.4478982388973236,
"learning_rate": 2e-05,
"loss": 0.6509,
"step": 820
},
{
"epoch": 0.07027347388028109,
"grad_norm": 0.44605377316474915,
"learning_rate": 2e-05,
"loss": 0.6619,
"step": 830
},
{
"epoch": 0.07112014224028448,
"grad_norm": 0.4520704746246338,
"learning_rate": 2e-05,
"loss": 0.6541,
"step": 840
},
{
"epoch": 0.07196681060028787,
"grad_norm": 0.45137783885002136,
"learning_rate": 2e-05,
"loss": 0.6632,
"step": 850
},
{
"epoch": 0.07281347896029125,
"grad_norm": 0.4655689299106598,
"learning_rate": 2e-05,
"loss": 0.6519,
"step": 860
},
{
"epoch": 0.07366014732029465,
"grad_norm": 0.43631526827812195,
"learning_rate": 2e-05,
"loss": 0.6597,
"step": 870
},
{
"epoch": 0.07450681568029803,
"grad_norm": 0.42785879969596863,
"learning_rate": 2e-05,
"loss": 0.6464,
"step": 880
},
{
"epoch": 0.07535348404030141,
"grad_norm": 0.43011021614074707,
"learning_rate": 2e-05,
"loss": 0.6528,
"step": 890
},
{
"epoch": 0.0762001524003048,
"grad_norm": 0.46899306774139404,
"learning_rate": 2e-05,
"loss": 0.6666,
"step": 900
},
{
"epoch": 0.0770468207603082,
"grad_norm": 0.46042707562446594,
"learning_rate": 2e-05,
"loss": 0.645,
"step": 910
},
{
"epoch": 0.07789348912031158,
"grad_norm": 0.4511071741580963,
"learning_rate": 2e-05,
"loss": 0.6436,
"step": 920
},
{
"epoch": 0.07874015748031496,
"grad_norm": 0.4230646789073944,
"learning_rate": 2e-05,
"loss": 0.6743,
"step": 930
},
{
"epoch": 0.07958682584031834,
"grad_norm": 0.43698370456695557,
"learning_rate": 2e-05,
"loss": 0.6481,
"step": 940
},
{
"epoch": 0.08043349420032174,
"grad_norm": 0.4549170732498169,
"learning_rate": 2e-05,
"loss": 0.6514,
"step": 950
},
{
"epoch": 0.08128016256032512,
"grad_norm": 0.45507657527923584,
"learning_rate": 2e-05,
"loss": 0.6554,
"step": 960
},
{
"epoch": 0.0821268309203285,
"grad_norm": 0.42522671818733215,
"learning_rate": 2e-05,
"loss": 0.656,
"step": 970
},
{
"epoch": 0.08297349928033189,
"grad_norm": 0.43912380933761597,
"learning_rate": 2e-05,
"loss": 0.6608,
"step": 980
},
{
"epoch": 0.08382016764033529,
"grad_norm": 0.4183550179004669,
"learning_rate": 2e-05,
"loss": 0.6492,
"step": 990
},
{
"epoch": 0.08466683600033867,
"grad_norm": 0.44775786995887756,
"learning_rate": 2e-05,
"loss": 0.6292,
"step": 1000
},
{
"epoch": 0.08551350436034205,
"grad_norm": 0.44851788878440857,
"learning_rate": 2e-05,
"loss": 0.6579,
"step": 1010
},
{
"epoch": 0.08636017272034544,
"grad_norm": 0.45955589413642883,
"learning_rate": 2e-05,
"loss": 0.6468,
"step": 1020
},
{
"epoch": 0.08720684108034883,
"grad_norm": 0.4205484688282013,
"learning_rate": 2e-05,
"loss": 0.651,
"step": 1030
},
{
"epoch": 0.08805350944035222,
"grad_norm": 0.42118069529533386,
"learning_rate": 2e-05,
"loss": 0.648,
"step": 1040
},
{
"epoch": 0.0889001778003556,
"grad_norm": 0.45766347646713257,
"learning_rate": 2e-05,
"loss": 0.6386,
"step": 1050
},
{
"epoch": 0.08974684616035898,
"grad_norm": 0.4297139346599579,
"learning_rate": 2e-05,
"loss": 0.6334,
"step": 1060
},
{
"epoch": 0.09059351452036238,
"grad_norm": 0.4587555229663849,
"learning_rate": 2e-05,
"loss": 0.6688,
"step": 1070
},
{
"epoch": 0.09144018288036576,
"grad_norm": 0.4319729506969452,
"learning_rate": 2e-05,
"loss": 0.6453,
"step": 1080
},
{
"epoch": 0.09228685124036914,
"grad_norm": 0.4240010976791382,
"learning_rate": 2e-05,
"loss": 0.6387,
"step": 1090
},
{
"epoch": 0.09313351960037253,
"grad_norm": 0.41819435358047485,
"learning_rate": 2e-05,
"loss": 0.636,
"step": 1100
},
{
"epoch": 0.09398018796037592,
"grad_norm": 0.4749411344528198,
"learning_rate": 2e-05,
"loss": 0.6502,
"step": 1110
},
{
"epoch": 0.09482685632037931,
"grad_norm": 0.4842819571495056,
"learning_rate": 2e-05,
"loss": 0.6601,
"step": 1120
},
{
"epoch": 0.09567352468038269,
"grad_norm": 0.39176562428474426,
"learning_rate": 2e-05,
"loss": 0.6316,
"step": 1130
},
{
"epoch": 0.09652019304038609,
"grad_norm": 0.46135643124580383,
"learning_rate": 2e-05,
"loss": 0.6763,
"step": 1140
},
{
"epoch": 0.09736686140038947,
"grad_norm": 0.4732727110385895,
"learning_rate": 2e-05,
"loss": 0.6577,
"step": 1150
},
{
"epoch": 0.09821352976039285,
"grad_norm": 0.4651736319065094,
"learning_rate": 2e-05,
"loss": 0.6385,
"step": 1160
},
{
"epoch": 0.09906019812039624,
"grad_norm": 0.44102978706359863,
"learning_rate": 2e-05,
"loss": 0.644,
"step": 1170
},
{
"epoch": 0.09990686648039963,
"grad_norm": 0.399547815322876,
"learning_rate": 2e-05,
"loss": 0.6441,
"step": 1180
},
{
"epoch": 0.10075353484040302,
"grad_norm": 0.5150323510169983,
"learning_rate": 2e-05,
"loss": 0.6812,
"step": 1190
},
{
"epoch": 0.1016002032004064,
"grad_norm": 0.43167948722839355,
"learning_rate": 2e-05,
"loss": 0.6416,
"step": 1200
},
{
"epoch": 0.10244687156040978,
"grad_norm": 0.4367421567440033,
"learning_rate": 2e-05,
"loss": 0.6689,
"step": 1210
},
{
"epoch": 0.10329353992041318,
"grad_norm": 0.4407538175582886,
"learning_rate": 2e-05,
"loss": 0.6628,
"step": 1220
},
{
"epoch": 0.10414020828041656,
"grad_norm": 0.4248872995376587,
"learning_rate": 2e-05,
"loss": 0.6584,
"step": 1230
},
{
"epoch": 0.10498687664041995,
"grad_norm": 0.42799079418182373,
"learning_rate": 2e-05,
"loss": 0.6496,
"step": 1240
},
{
"epoch": 0.10583354500042333,
"grad_norm": 0.4394405484199524,
"learning_rate": 2e-05,
"loss": 0.6398,
"step": 1250
},
{
"epoch": 0.10668021336042673,
"grad_norm": 0.43604040145874023,
"learning_rate": 2e-05,
"loss": 0.6502,
"step": 1260
},
{
"epoch": 0.10752688172043011,
"grad_norm": 0.43875670433044434,
"learning_rate": 2e-05,
"loss": 0.6564,
"step": 1270
},
{
"epoch": 0.10837355008043349,
"grad_norm": 0.4250807762145996,
"learning_rate": 2e-05,
"loss": 0.6389,
"step": 1280
},
{
"epoch": 0.10922021844043688,
"grad_norm": 0.48220178484916687,
"learning_rate": 2e-05,
"loss": 0.6617,
"step": 1290
},
{
"epoch": 0.11006688680044027,
"grad_norm": 0.41790634393692017,
"learning_rate": 2e-05,
"loss": 0.636,
"step": 1300
},
{
"epoch": 0.11091355516044366,
"grad_norm": 0.5080624222755432,
"learning_rate": 2e-05,
"loss": 0.6733,
"step": 1310
},
{
"epoch": 0.11176022352044704,
"grad_norm": 0.4096316695213318,
"learning_rate": 2e-05,
"loss": 0.6447,
"step": 1320
},
{
"epoch": 0.11260689188045042,
"grad_norm": 0.4489736557006836,
"learning_rate": 2e-05,
"loss": 0.6723,
"step": 1330
},
{
"epoch": 0.11345356024045382,
"grad_norm": 0.4486621022224426,
"learning_rate": 2e-05,
"loss": 0.6536,
"step": 1340
},
{
"epoch": 0.1143002286004572,
"grad_norm": 0.7986853122711182,
"learning_rate": 2e-05,
"loss": 0.67,
"step": 1350
},
{
"epoch": 0.11514689696046058,
"grad_norm": 0.4286498427391052,
"learning_rate": 2e-05,
"loss": 0.6441,
"step": 1360
},
{
"epoch": 0.11599356532046397,
"grad_norm": 0.4120442271232605,
"learning_rate": 2e-05,
"loss": 0.6506,
"step": 1370
},
{
"epoch": 0.11684023368046736,
"grad_norm": 0.43085169792175293,
"learning_rate": 2e-05,
"loss": 0.6505,
"step": 1380
},
{
"epoch": 0.11768690204047075,
"grad_norm": 0.4295996129512787,
"learning_rate": 2e-05,
"loss": 0.6562,
"step": 1390
},
{
"epoch": 0.11853357040047413,
"grad_norm": 0.43393197655677795,
"learning_rate": 2e-05,
"loss": 0.6433,
"step": 1400
},
{
"epoch": 0.11938023876047753,
"grad_norm": 0.41177472472190857,
"learning_rate": 2e-05,
"loss": 0.6619,
"step": 1410
},
{
"epoch": 0.12022690712048091,
"grad_norm": 0.4898812174797058,
"learning_rate": 2e-05,
"loss": 0.6394,
"step": 1420
},
{
"epoch": 0.1210735754804843,
"grad_norm": 0.4619840085506439,
"learning_rate": 2e-05,
"loss": 0.6438,
"step": 1430
},
{
"epoch": 0.12192024384048768,
"grad_norm": 0.5120882987976074,
"learning_rate": 2e-05,
"loss": 0.6645,
"step": 1440
},
{
"epoch": 0.12276691220049107,
"grad_norm": 0.4201647937297821,
"learning_rate": 2e-05,
"loss": 0.6625,
"step": 1450
},
{
"epoch": 0.12361358056049446,
"grad_norm": 0.4196993112564087,
"learning_rate": 2e-05,
"loss": 0.6477,
"step": 1460
},
{
"epoch": 0.12446024892049784,
"grad_norm": 0.4666191637516022,
"learning_rate": 2e-05,
"loss": 0.6605,
"step": 1470
},
{
"epoch": 0.12530691728050122,
"grad_norm": 0.42628341913223267,
"learning_rate": 2e-05,
"loss": 0.6635,
"step": 1480
},
{
"epoch": 0.1261535856405046,
"grad_norm": 0.46635255217552185,
"learning_rate": 2e-05,
"loss": 0.6519,
"step": 1490
},
{
"epoch": 0.127000254000508,
"grad_norm": 0.39531210064888,
"learning_rate": 2e-05,
"loss": 0.6597,
"step": 1500
},
{
"epoch": 0.1278469223605114,
"grad_norm": 0.416293740272522,
"learning_rate": 2e-05,
"loss": 0.6476,
"step": 1510
},
{
"epoch": 0.12869359072051478,
"grad_norm": 0.4376610815525055,
"learning_rate": 2e-05,
"loss": 0.6471,
"step": 1520
},
{
"epoch": 0.12954025908051817,
"grad_norm": 0.9239709377288818,
"learning_rate": 2e-05,
"loss": 0.6483,
"step": 1530
},
{
"epoch": 0.13038692744052155,
"grad_norm": 0.44836151599884033,
"learning_rate": 2e-05,
"loss": 0.6476,
"step": 1540
},
{
"epoch": 0.13123359580052493,
"grad_norm": 0.40565115213394165,
"learning_rate": 2e-05,
"loss": 0.6477,
"step": 1550
},
{
"epoch": 0.13208026416052832,
"grad_norm": 0.4043814241886139,
"learning_rate": 2e-05,
"loss": 0.6422,
"step": 1560
},
{
"epoch": 0.1329269325205317,
"grad_norm": 0.48815831542015076,
"learning_rate": 2e-05,
"loss": 0.667,
"step": 1570
},
{
"epoch": 0.13377360088053508,
"grad_norm": 0.4149971902370453,
"learning_rate": 2e-05,
"loss": 0.6428,
"step": 1580
},
{
"epoch": 0.1346202692405385,
"grad_norm": 0.43481072783470154,
"learning_rate": 2e-05,
"loss": 0.6297,
"step": 1590
},
{
"epoch": 0.13546693760054188,
"grad_norm": 0.5290552377700806,
"learning_rate": 2e-05,
"loss": 0.6571,
"step": 1600
},
{
"epoch": 0.13631360596054526,
"grad_norm": 0.48005440831184387,
"learning_rate": 2e-05,
"loss": 0.6375,
"step": 1610
},
{
"epoch": 0.13716027432054864,
"grad_norm": 0.41244378685951233,
"learning_rate": 2e-05,
"loss": 0.6465,
"step": 1620
},
{
"epoch": 0.13800694268055202,
"grad_norm": 0.4275606572628021,
"learning_rate": 2e-05,
"loss": 0.6496,
"step": 1630
},
{
"epoch": 0.1388536110405554,
"grad_norm": 0.40932148694992065,
"learning_rate": 2e-05,
"loss": 0.6617,
"step": 1640
},
{
"epoch": 0.1397002794005588,
"grad_norm": 0.46909376978874207,
"learning_rate": 2e-05,
"loss": 0.654,
"step": 1650
},
{
"epoch": 0.14054694776056217,
"grad_norm": 0.40658414363861084,
"learning_rate": 2e-05,
"loss": 0.6148,
"step": 1660
},
{
"epoch": 0.14139361612056559,
"grad_norm": 0.45841172337532043,
"learning_rate": 2e-05,
"loss": 0.6511,
"step": 1670
},
{
"epoch": 0.14224028448056897,
"grad_norm": 0.4471743702888489,
"learning_rate": 2e-05,
"loss": 0.6448,
"step": 1680
},
{
"epoch": 0.14308695284057235,
"grad_norm": 0.43427541851997375,
"learning_rate": 2e-05,
"loss": 0.6435,
"step": 1690
},
{
"epoch": 0.14393362120057573,
"grad_norm": 0.4472843408584595,
"learning_rate": 2e-05,
"loss": 0.6357,
"step": 1700
},
{
"epoch": 0.14478028956057912,
"grad_norm": 0.42029255628585815,
"learning_rate": 2e-05,
"loss": 0.6575,
"step": 1710
},
{
"epoch": 0.1456269579205825,
"grad_norm": 0.4621073603630066,
"learning_rate": 2e-05,
"loss": 0.6361,
"step": 1720
},
{
"epoch": 0.14647362628058588,
"grad_norm": 0.4484656751155853,
"learning_rate": 2e-05,
"loss": 0.6355,
"step": 1730
},
{
"epoch": 0.1473202946405893,
"grad_norm": 0.4217395782470703,
"learning_rate": 2e-05,
"loss": 0.6682,
"step": 1740
},
{
"epoch": 0.14816696300059268,
"grad_norm": 0.42961055040359497,
"learning_rate": 2e-05,
"loss": 0.645,
"step": 1750
},
{
"epoch": 0.14901363136059606,
"grad_norm": 0.46678170561790466,
"learning_rate": 2e-05,
"loss": 0.6401,
"step": 1760
},
{
"epoch": 0.14986029972059944,
"grad_norm": 0.5399910807609558,
"learning_rate": 2e-05,
"loss": 0.6507,
"step": 1770
},
{
"epoch": 0.15070696808060283,
"grad_norm": 0.47768858075141907,
"learning_rate": 2e-05,
"loss": 0.6342,
"step": 1780
},
{
"epoch": 0.1515536364406062,
"grad_norm": 0.44225838780403137,
"learning_rate": 2e-05,
"loss": 0.6567,
"step": 1790
},
{
"epoch": 0.1524003048006096,
"grad_norm": 0.4229118227958679,
"learning_rate": 2e-05,
"loss": 0.6597,
"step": 1800
},
{
"epoch": 0.15324697316061298,
"grad_norm": 1.9519200325012207,
"learning_rate": 2e-05,
"loss": 0.6483,
"step": 1810
},
{
"epoch": 0.1540936415206164,
"grad_norm": 0.5570772290229797,
"learning_rate": 2e-05,
"loss": 0.646,
"step": 1820
},
{
"epoch": 0.15494030988061977,
"grad_norm": 0.42859718203544617,
"learning_rate": 2e-05,
"loss": 0.6163,
"step": 1830
},
{
"epoch": 0.15578697824062315,
"grad_norm": 0.4103221297264099,
"learning_rate": 2e-05,
"loss": 0.6527,
"step": 1840
},
{
"epoch": 0.15663364660062654,
"grad_norm": 0.4725561738014221,
"learning_rate": 2e-05,
"loss": 0.6624,
"step": 1850
},
{
"epoch": 0.15748031496062992,
"grad_norm": 0.43084171414375305,
"learning_rate": 2e-05,
"loss": 0.6424,
"step": 1860
},
{
"epoch": 0.1583269833206333,
"grad_norm": 0.4549056887626648,
"learning_rate": 2e-05,
"loss": 0.6319,
"step": 1870
},
{
"epoch": 0.15917365168063669,
"grad_norm": 0.43331679701805115,
"learning_rate": 2e-05,
"loss": 0.6443,
"step": 1880
},
{
"epoch": 0.16002032004064007,
"grad_norm": 0.4841455817222595,
"learning_rate": 2e-05,
"loss": 0.6349,
"step": 1890
},
{
"epoch": 0.16086698840064348,
"grad_norm": 0.4443437159061432,
"learning_rate": 2e-05,
"loss": 0.6631,
"step": 1900
},
{
"epoch": 0.16171365676064686,
"grad_norm": 0.44019854068756104,
"learning_rate": 2e-05,
"loss": 0.6318,
"step": 1910
},
{
"epoch": 0.16256032512065025,
"grad_norm": 0.45389479398727417,
"learning_rate": 2e-05,
"loss": 0.6717,
"step": 1920
},
{
"epoch": 0.16340699348065363,
"grad_norm": 0.4448392689228058,
"learning_rate": 2e-05,
"loss": 0.6636,
"step": 1930
},
{
"epoch": 0.164253661840657,
"grad_norm": 0.48700398206710815,
"learning_rate": 2e-05,
"loss": 0.6337,
"step": 1940
},
{
"epoch": 0.1651003302006604,
"grad_norm": 0.42143478989601135,
"learning_rate": 2e-05,
"loss": 0.6544,
"step": 1950
},
{
"epoch": 0.16594699856066378,
"grad_norm": 0.4352879524230957,
"learning_rate": 2e-05,
"loss": 0.6514,
"step": 1960
},
{
"epoch": 0.1667936669206672,
"grad_norm": 0.414305716753006,
"learning_rate": 2e-05,
"loss": 0.6481,
"step": 1970
},
{
"epoch": 0.16764033528067057,
"grad_norm": 0.39161503314971924,
"learning_rate": 2e-05,
"loss": 0.6566,
"step": 1980
},
{
"epoch": 0.16848700364067395,
"grad_norm": 0.421457976102829,
"learning_rate": 2e-05,
"loss": 0.6449,
"step": 1990
},
{
"epoch": 0.16933367200067734,
"grad_norm": 0.448140949010849,
"learning_rate": 2e-05,
"loss": 0.6477,
"step": 2000
},
{
"epoch": 0.17018034036068072,
"grad_norm": 0.4220173954963684,
"learning_rate": 2e-05,
"loss": 0.6366,
"step": 2010
},
{
"epoch": 0.1710270087206841,
"grad_norm": 0.3872855603694916,
"learning_rate": 2e-05,
"loss": 0.6646,
"step": 2020
},
{
"epoch": 0.1718736770806875,
"grad_norm": 0.5094623565673828,
"learning_rate": 2e-05,
"loss": 0.6433,
"step": 2030
},
{
"epoch": 0.17272034544069087,
"grad_norm": 0.43138524889945984,
"learning_rate": 2e-05,
"loss": 0.6399,
"step": 2040
},
{
"epoch": 0.17356701380069428,
"grad_norm": 0.4579676687717438,
"learning_rate": 2e-05,
"loss": 0.643,
"step": 2050
},
{
"epoch": 0.17441368216069766,
"grad_norm": 1.0642181634902954,
"learning_rate": 2e-05,
"loss": 0.6466,
"step": 2060
},
{
"epoch": 0.17526035052070105,
"grad_norm": 0.4300776422023773,
"learning_rate": 2e-05,
"loss": 0.6264,
"step": 2070
},
{
"epoch": 0.17610701888070443,
"grad_norm": 0.43561115860939026,
"learning_rate": 2e-05,
"loss": 0.6274,
"step": 2080
},
{
"epoch": 0.1769536872407078,
"grad_norm": 0.4419814348220825,
"learning_rate": 2e-05,
"loss": 0.6189,
"step": 2090
},
{
"epoch": 0.1778003556007112,
"grad_norm": 0.40943095088005066,
"learning_rate": 2e-05,
"loss": 0.6575,
"step": 2100
},
{
"epoch": 0.17864702396071458,
"grad_norm": 0.4220316708087921,
"learning_rate": 2e-05,
"loss": 0.6321,
"step": 2110
},
{
"epoch": 0.17949369232071796,
"grad_norm": 0.4069748818874359,
"learning_rate": 2e-05,
"loss": 0.6249,
"step": 2120
},
{
"epoch": 0.18034036068072137,
"grad_norm": 0.4093238115310669,
"learning_rate": 2e-05,
"loss": 0.6367,
"step": 2130
},
{
"epoch": 0.18118702904072476,
"grad_norm": 0.42871996760368347,
"learning_rate": 2e-05,
"loss": 0.6319,
"step": 2140
},
{
"epoch": 0.18203369740072814,
"grad_norm": 0.4586758613586426,
"learning_rate": 2e-05,
"loss": 0.6043,
"step": 2150
},
{
"epoch": 0.18288036576073152,
"grad_norm": 0.43323299288749695,
"learning_rate": 2e-05,
"loss": 0.6518,
"step": 2160
},
{
"epoch": 0.1837270341207349,
"grad_norm": 0.4545518159866333,
"learning_rate": 2e-05,
"loss": 0.6365,
"step": 2170
},
{
"epoch": 0.1845737024807383,
"grad_norm": 0.4953419268131256,
"learning_rate": 2e-05,
"loss": 0.6426,
"step": 2180
},
{
"epoch": 0.18542037084074167,
"grad_norm": 0.4099434018135071,
"learning_rate": 2e-05,
"loss": 0.6429,
"step": 2190
},
{
"epoch": 0.18626703920074505,
"grad_norm": 0.4271218180656433,
"learning_rate": 2e-05,
"loss": 0.6341,
"step": 2200
},
{
"epoch": 0.18711370756074847,
"grad_norm": 0.44617754220962524,
"learning_rate": 2e-05,
"loss": 0.6261,
"step": 2210
},
{
"epoch": 0.18796037592075185,
"grad_norm": 0.4889068901538849,
"learning_rate": 2e-05,
"loss": 0.6611,
"step": 2220
},
{
"epoch": 0.18880704428075523,
"grad_norm": 0.41321495175361633,
"learning_rate": 2e-05,
"loss": 0.645,
"step": 2230
},
{
"epoch": 0.18965371264075861,
"grad_norm": 0.3996637463569641,
"learning_rate": 2e-05,
"loss": 0.6471,
"step": 2240
},
{
"epoch": 0.190500381000762,
"grad_norm": 0.43380239605903625,
"learning_rate": 2e-05,
"loss": 0.6328,
"step": 2250
},
{
"epoch": 0.19134704936076538,
"grad_norm": 0.43314844369888306,
"learning_rate": 2e-05,
"loss": 0.6528,
"step": 2260
},
{
"epoch": 0.19219371772076876,
"grad_norm": 0.396233469247818,
"learning_rate": 2e-05,
"loss": 0.6331,
"step": 2270
},
{
"epoch": 0.19304038608077217,
"grad_norm": 0.42943382263183594,
"learning_rate": 2e-05,
"loss": 0.6604,
"step": 2280
},
{
"epoch": 0.19388705444077556,
"grad_norm": 0.5218196511268616,
"learning_rate": 2e-05,
"loss": 0.6573,
"step": 2290
},
{
"epoch": 0.19473372280077894,
"grad_norm": 0.4184105396270752,
"learning_rate": 2e-05,
"loss": 0.6361,
"step": 2300
},
{
"epoch": 0.19558039116078232,
"grad_norm": 0.5651347041130066,
"learning_rate": 2e-05,
"loss": 0.636,
"step": 2310
},
{
"epoch": 0.1964270595207857,
"grad_norm": 0.42529258131980896,
"learning_rate": 2e-05,
"loss": 0.6444,
"step": 2320
},
{
"epoch": 0.1972737278807891,
"grad_norm": 0.44605952501296997,
"learning_rate": 2e-05,
"loss": 0.6382,
"step": 2330
},
{
"epoch": 0.19812039624079247,
"grad_norm": 0.4468037188053131,
"learning_rate": 2e-05,
"loss": 0.6302,
"step": 2340
},
{
"epoch": 0.19896706460079586,
"grad_norm": 0.3863542973995209,
"learning_rate": 2e-05,
"loss": 0.6215,
"step": 2350
},
{
"epoch": 0.19981373296079927,
"grad_norm": 0.4320015013217926,
"learning_rate": 2e-05,
"loss": 0.6421,
"step": 2360
},
{
"epoch": 0.20066040132080265,
"grad_norm": 0.43013012409210205,
"learning_rate": 2e-05,
"loss": 0.6474,
"step": 2370
},
{
"epoch": 0.20150706968080603,
"grad_norm": 0.3912484049797058,
"learning_rate": 2e-05,
"loss": 0.6179,
"step": 2380
},
{
"epoch": 0.20235373804080942,
"grad_norm": 0.39495962858200073,
"learning_rate": 2e-05,
"loss": 0.6356,
"step": 2390
},
{
"epoch": 0.2032004064008128,
"grad_norm": 0.384694367647171,
"learning_rate": 2e-05,
"loss": 0.6634,
"step": 2400
},
{
"epoch": 0.20404707476081618,
"grad_norm": 0.6632846593856812,
"learning_rate": 2e-05,
"loss": 0.6283,
"step": 2410
},
{
"epoch": 0.20489374312081957,
"grad_norm": 0.4242749512195587,
"learning_rate": 2e-05,
"loss": 0.6316,
"step": 2420
},
{
"epoch": 0.20574041148082295,
"grad_norm": 0.41551467776298523,
"learning_rate": 2e-05,
"loss": 0.6519,
"step": 2430
},
{
"epoch": 0.20658707984082636,
"grad_norm": 0.3853192925453186,
"learning_rate": 2e-05,
"loss": 0.6487,
"step": 2440
},
{
"epoch": 0.20743374820082974,
"grad_norm": 0.4175145626068115,
"learning_rate": 2e-05,
"loss": 0.6397,
"step": 2450
},
{
"epoch": 0.20828041656083313,
"grad_norm": 0.41761279106140137,
"learning_rate": 2e-05,
"loss": 0.656,
"step": 2460
},
{
"epoch": 0.2091270849208365,
"grad_norm": 0.39868006110191345,
"learning_rate": 2e-05,
"loss": 0.6412,
"step": 2470
},
{
"epoch": 0.2099737532808399,
"grad_norm": 0.3972877264022827,
"learning_rate": 2e-05,
"loss": 0.6403,
"step": 2480
},
{
"epoch": 0.21082042164084328,
"grad_norm": 0.3830007314682007,
"learning_rate": 2e-05,
"loss": 0.6371,
"step": 2490
},
{
"epoch": 0.21166709000084666,
"grad_norm": 0.4232046604156494,
"learning_rate": 2e-05,
"loss": 0.6531,
"step": 2500
},
{
"epoch": 0.21251375836085004,
"grad_norm": 0.3900882303714752,
"learning_rate": 2e-05,
"loss": 0.6222,
"step": 2510
},
{
"epoch": 0.21336042672085345,
"grad_norm": 0.39245057106018066,
"learning_rate": 2e-05,
"loss": 0.6153,
"step": 2520
},
{
"epoch": 0.21420709508085684,
"grad_norm": 0.43386736512184143,
"learning_rate": 2e-05,
"loss": 0.6382,
"step": 2530
},
{
"epoch": 0.21505376344086022,
"grad_norm": 0.3844192326068878,
"learning_rate": 2e-05,
"loss": 0.6534,
"step": 2540
},
{
"epoch": 0.2159004318008636,
"grad_norm": 0.5519846081733704,
"learning_rate": 2e-05,
"loss": 0.6464,
"step": 2550
},
{
"epoch": 0.21674710016086698,
"grad_norm": 0.4004225432872772,
"learning_rate": 2e-05,
"loss": 0.6385,
"step": 2560
},
{
"epoch": 0.21759376852087037,
"grad_norm": 0.40917128324508667,
"learning_rate": 2e-05,
"loss": 0.6556,
"step": 2570
},
{
"epoch": 0.21844043688087375,
"grad_norm": 0.38037240505218506,
"learning_rate": 2e-05,
"loss": 0.6359,
"step": 2580
},
{
"epoch": 0.21928710524087716,
"grad_norm": 0.4489869475364685,
"learning_rate": 2e-05,
"loss": 0.655,
"step": 2590
},
{
"epoch": 0.22013377360088054,
"grad_norm": 0.41383644938468933,
"learning_rate": 2e-05,
"loss": 0.6554,
"step": 2600
},
{
"epoch": 0.22098044196088393,
"grad_norm": 0.3828672766685486,
"learning_rate": 2e-05,
"loss": 0.6588,
"step": 2610
},
{
"epoch": 0.2218271103208873,
"grad_norm": 0.41098809242248535,
"learning_rate": 2e-05,
"loss": 0.6185,
"step": 2620
},
{
"epoch": 0.2226737786808907,
"grad_norm": 0.3833703100681305,
"learning_rate": 2e-05,
"loss": 0.6419,
"step": 2630
},
{
"epoch": 0.22352044704089408,
"grad_norm": 0.4067264199256897,
"learning_rate": 2e-05,
"loss": 0.6289,
"step": 2640
},
{
"epoch": 0.22436711540089746,
"grad_norm": 0.40791037678718567,
"learning_rate": 2e-05,
"loss": 0.6379,
"step": 2650
},
{
"epoch": 0.22521378376090084,
"grad_norm": 0.43709638714790344,
"learning_rate": 2e-05,
"loss": 0.6357,
"step": 2660
},
{
"epoch": 0.22606045212090425,
"grad_norm": 0.4151391088962555,
"learning_rate": 2e-05,
"loss": 0.6571,
"step": 2670
},
{
"epoch": 0.22690712048090764,
"grad_norm": 0.4648939073085785,
"learning_rate": 2e-05,
"loss": 0.6519,
"step": 2680
},
{
"epoch": 0.22775378884091102,
"grad_norm": 0.42384690046310425,
"learning_rate": 2e-05,
"loss": 0.6406,
"step": 2690
},
{
"epoch": 0.2286004572009144,
"grad_norm": 0.40418389439582825,
"learning_rate": 2e-05,
"loss": 0.6352,
"step": 2700
},
{
"epoch": 0.2294471255609178,
"grad_norm": 0.4247417747974396,
"learning_rate": 2e-05,
"loss": 0.6246,
"step": 2710
},
{
"epoch": 0.23029379392092117,
"grad_norm": 0.39670681953430176,
"learning_rate": 2e-05,
"loss": 0.6463,
"step": 2720
},
{
"epoch": 0.23114046228092455,
"grad_norm": 0.45522087812423706,
"learning_rate": 2e-05,
"loss": 0.6687,
"step": 2730
},
{
"epoch": 0.23198713064092794,
"grad_norm": 0.4865119457244873,
"learning_rate": 2e-05,
"loss": 0.6498,
"step": 2740
},
{
"epoch": 0.23283379900093135,
"grad_norm": 0.4382932782173157,
"learning_rate": 2e-05,
"loss": 0.6406,
"step": 2750
},
{
"epoch": 0.23368046736093473,
"grad_norm": 0.42918914556503296,
"learning_rate": 2e-05,
"loss": 0.6431,
"step": 2760
},
{
"epoch": 0.2345271357209381,
"grad_norm": 0.41465798020362854,
"learning_rate": 2e-05,
"loss": 0.6406,
"step": 2770
},
{
"epoch": 0.2353738040809415,
"grad_norm": 0.4464358389377594,
"learning_rate": 2e-05,
"loss": 0.6491,
"step": 2780
},
{
"epoch": 0.23622047244094488,
"grad_norm": 0.4201108515262604,
"learning_rate": 2e-05,
"loss": 0.6199,
"step": 2790
},
{
"epoch": 0.23706714080094826,
"grad_norm": 0.4981282949447632,
"learning_rate": 2e-05,
"loss": 0.635,
"step": 2800
},
{
"epoch": 0.23791380916095164,
"grad_norm": 0.3868878483772278,
"learning_rate": 2e-05,
"loss": 0.6393,
"step": 2810
},
{
"epoch": 0.23876047752095506,
"grad_norm": 0.40685951709747314,
"learning_rate": 2e-05,
"loss": 0.6284,
"step": 2820
},
{
"epoch": 0.23960714588095844,
"grad_norm": 0.41393551230430603,
"learning_rate": 2e-05,
"loss": 0.6568,
"step": 2830
},
{
"epoch": 0.24045381424096182,
"grad_norm": 0.4491131603717804,
"learning_rate": 2e-05,
"loss": 0.6375,
"step": 2840
},
{
"epoch": 0.2413004826009652,
"grad_norm": 0.48691219091415405,
"learning_rate": 2e-05,
"loss": 0.6143,
"step": 2850
},
{
"epoch": 0.2421471509609686,
"grad_norm": 0.4507281184196472,
"learning_rate": 2e-05,
"loss": 0.6234,
"step": 2860
},
{
"epoch": 0.24299381932097197,
"grad_norm": 0.43581560254096985,
"learning_rate": 2e-05,
"loss": 0.6454,
"step": 2870
},
{
"epoch": 0.24384048768097535,
"grad_norm": 0.5282661318778992,
"learning_rate": 2e-05,
"loss": 0.6423,
"step": 2880
},
{
"epoch": 0.24468715604097874,
"grad_norm": 0.40446242690086365,
"learning_rate": 2e-05,
"loss": 0.6406,
"step": 2890
},
{
"epoch": 0.24553382440098215,
"grad_norm": 0.4218043088912964,
"learning_rate": 2e-05,
"loss": 0.6242,
"step": 2900
},
{
"epoch": 0.24638049276098553,
"grad_norm": 0.4034806191921234,
"learning_rate": 2e-05,
"loss": 0.6306,
"step": 2910
},
{
"epoch": 0.24722716112098891,
"grad_norm": 0.40466344356536865,
"learning_rate": 2e-05,
"loss": 0.6261,
"step": 2920
},
{
"epoch": 0.2480738294809923,
"grad_norm": 0.4296315312385559,
"learning_rate": 2e-05,
"loss": 0.6151,
"step": 2930
},
{
"epoch": 0.24892049784099568,
"grad_norm": 0.45331016182899475,
"learning_rate": 2e-05,
"loss": 0.6464,
"step": 2940
},
{
"epoch": 0.24976716620099906,
"grad_norm": 0.44625458121299744,
"learning_rate": 2e-05,
"loss": 0.6315,
"step": 2950
},
{
"epoch": 0.25061383456100245,
"grad_norm": 0.43744179606437683,
"learning_rate": 2e-05,
"loss": 0.619,
"step": 2960
},
{
"epoch": 0.25146050292100586,
"grad_norm": 0.4107581377029419,
"learning_rate": 2e-05,
"loss": 0.6306,
"step": 2970
},
{
"epoch": 0.2523071712810092,
"grad_norm": 0.39485299587249756,
"learning_rate": 2e-05,
"loss": 0.6261,
"step": 2980
},
{
"epoch": 0.2531538396410126,
"grad_norm": 0.4031531810760498,
"learning_rate": 2e-05,
"loss": 0.6257,
"step": 2990
},
{
"epoch": 0.254000508001016,
"grad_norm": 0.45026257634162903,
"learning_rate": 2e-05,
"loss": 0.6408,
"step": 3000
},
{
"epoch": 0.2548471763610194,
"grad_norm": 0.40911462903022766,
"learning_rate": 2e-05,
"loss": 0.624,
"step": 3010
},
{
"epoch": 0.2556938447210228,
"grad_norm": 0.3996413052082062,
"learning_rate": 2e-05,
"loss": 0.6388,
"step": 3020
},
{
"epoch": 0.25654051308102616,
"grad_norm": 0.4137783944606781,
"learning_rate": 2e-05,
"loss": 0.645,
"step": 3030
},
{
"epoch": 0.25738718144102957,
"grad_norm": 0.3941035866737366,
"learning_rate": 2e-05,
"loss": 0.6297,
"step": 3040
},
{
"epoch": 0.2582338498010329,
"grad_norm": 0.39765384793281555,
"learning_rate": 2e-05,
"loss": 0.675,
"step": 3050
},
{
"epoch": 0.25908051816103633,
"grad_norm": 0.42631596326828003,
"learning_rate": 2e-05,
"loss": 0.6185,
"step": 3060
},
{
"epoch": 0.2599271865210397,
"grad_norm": 0.4218185544013977,
"learning_rate": 2e-05,
"loss": 0.6385,
"step": 3070
},
{
"epoch": 0.2607738548810431,
"grad_norm": 0.42259150743484497,
"learning_rate": 2e-05,
"loss": 0.6464,
"step": 3080
},
{
"epoch": 0.2616205232410465,
"grad_norm": 0.3934686481952667,
"learning_rate": 2e-05,
"loss": 0.6399,
"step": 3090
},
{
"epoch": 0.26246719160104987,
"grad_norm": 0.4417162537574768,
"learning_rate": 2e-05,
"loss": 0.6473,
"step": 3100
},
{
"epoch": 0.2633138599610533,
"grad_norm": 0.4261956810951233,
"learning_rate": 2e-05,
"loss": 0.6135,
"step": 3110
},
{
"epoch": 0.26416052832105663,
"grad_norm": 0.4082337021827698,
"learning_rate": 2e-05,
"loss": 0.6437,
"step": 3120
},
{
"epoch": 0.26500719668106004,
"grad_norm": 0.4085938632488251,
"learning_rate": 2e-05,
"loss": 0.6214,
"step": 3130
},
{
"epoch": 0.2658538650410634,
"grad_norm": 0.42370662093162537,
"learning_rate": 2e-05,
"loss": 0.6624,
"step": 3140
},
{
"epoch": 0.2667005334010668,
"grad_norm": 0.9658306837081909,
"learning_rate": 2e-05,
"loss": 0.6355,
"step": 3150
},
{
"epoch": 0.26754720176107016,
"grad_norm": 0.3799201548099518,
"learning_rate": 2e-05,
"loss": 0.6338,
"step": 3160
},
{
"epoch": 0.2683938701210736,
"grad_norm": 0.4011082351207733,
"learning_rate": 2e-05,
"loss": 0.6205,
"step": 3170
},
{
"epoch": 0.269240538481077,
"grad_norm": 0.4082750976085663,
"learning_rate": 2e-05,
"loss": 0.646,
"step": 3180
},
{
"epoch": 0.27008720684108034,
"grad_norm": 0.3899262845516205,
"learning_rate": 2e-05,
"loss": 0.6287,
"step": 3190
},
{
"epoch": 0.27093387520108375,
"grad_norm": 0.4211922585964203,
"learning_rate": 2e-05,
"loss": 0.6306,
"step": 3200
},
{
"epoch": 0.2717805435610871,
"grad_norm": 0.41326385736465454,
"learning_rate": 2e-05,
"loss": 0.6235,
"step": 3210
},
{
"epoch": 0.2726272119210905,
"grad_norm": 0.41445034742355347,
"learning_rate": 2e-05,
"loss": 0.6239,
"step": 3220
},
{
"epoch": 0.2734738802810939,
"grad_norm": 0.4477451741695404,
"learning_rate": 2e-05,
"loss": 0.6308,
"step": 3230
},
{
"epoch": 0.2743205486410973,
"grad_norm": 0.42119231820106506,
"learning_rate": 2e-05,
"loss": 0.6257,
"step": 3240
},
{
"epoch": 0.2751672170011007,
"grad_norm": 0.4201563596725464,
"learning_rate": 2e-05,
"loss": 0.6225,
"step": 3250
},
{
"epoch": 0.27601388536110405,
"grad_norm": 0.42233985662460327,
"learning_rate": 2e-05,
"loss": 0.6166,
"step": 3260
},
{
"epoch": 0.27686055372110746,
"grad_norm": 0.40148264169692993,
"learning_rate": 2e-05,
"loss": 0.6442,
"step": 3270
},
{
"epoch": 0.2777072220811108,
"grad_norm": 0.3941594660282135,
"learning_rate": 2e-05,
"loss": 0.6369,
"step": 3280
},
{
"epoch": 0.2785538904411142,
"grad_norm": 0.40674856305122375,
"learning_rate": 2e-05,
"loss": 0.6351,
"step": 3290
},
{
"epoch": 0.2794005588011176,
"grad_norm": 0.39532068371772766,
"learning_rate": 2e-05,
"loss": 0.6355,
"step": 3300
},
{
"epoch": 0.280247227161121,
"grad_norm": 0.3713996708393097,
"learning_rate": 2e-05,
"loss": 0.6266,
"step": 3310
},
{
"epoch": 0.28109389552112435,
"grad_norm": 0.40361613035202026,
"learning_rate": 2e-05,
"loss": 0.6483,
"step": 3320
},
{
"epoch": 0.28194056388112776,
"grad_norm": 0.3825480341911316,
"learning_rate": 2e-05,
"loss": 0.6168,
"step": 3330
},
{
"epoch": 0.28278723224113117,
"grad_norm": 0.38089442253112793,
"learning_rate": 2e-05,
"loss": 0.629,
"step": 3340
},
{
"epoch": 0.2836339006011345,
"grad_norm": 0.49822020530700684,
"learning_rate": 2e-05,
"loss": 0.6532,
"step": 3350
},
{
"epoch": 0.28448056896113794,
"grad_norm": 0.4202452301979065,
"learning_rate": 2e-05,
"loss": 0.6299,
"step": 3360
},
{
"epoch": 0.2853272373211413,
"grad_norm": 0.37910890579223633,
"learning_rate": 2e-05,
"loss": 0.6348,
"step": 3370
},
{
"epoch": 0.2861739056811447,
"grad_norm": 0.39863014221191406,
"learning_rate": 2e-05,
"loss": 0.6369,
"step": 3380
},
{
"epoch": 0.28702057404114806,
"grad_norm": 0.5652646422386169,
"learning_rate": 2e-05,
"loss": 0.6184,
"step": 3390
},
{
"epoch": 0.28786724240115147,
"grad_norm": 0.37824442982673645,
"learning_rate": 2e-05,
"loss": 0.6184,
"step": 3400
},
{
"epoch": 0.2887139107611549,
"grad_norm": 0.4170939028263092,
"learning_rate": 2e-05,
"loss": 0.6304,
"step": 3410
},
{
"epoch": 0.28956057912115823,
"grad_norm": 0.5684532523155212,
"learning_rate": 2e-05,
"loss": 0.6384,
"step": 3420
},
{
"epoch": 0.29040724748116165,
"grad_norm": 0.4120194911956787,
"learning_rate": 2e-05,
"loss": 0.6106,
"step": 3430
},
{
"epoch": 0.291253915841165,
"grad_norm": 0.40495702624320984,
"learning_rate": 2e-05,
"loss": 0.6495,
"step": 3440
},
{
"epoch": 0.2921005842011684,
"grad_norm": 0.4259183704853058,
"learning_rate": 2e-05,
"loss": 0.638,
"step": 3450
},
{
"epoch": 0.29294725256117177,
"grad_norm": 0.4299517273902893,
"learning_rate": 2e-05,
"loss": 0.6245,
"step": 3460
},
{
"epoch": 0.2937939209211752,
"grad_norm": 0.43136143684387207,
"learning_rate": 2e-05,
"loss": 0.6302,
"step": 3470
},
{
"epoch": 0.2946405892811786,
"grad_norm": 0.37267258763313293,
"learning_rate": 2e-05,
"loss": 0.6227,
"step": 3480
},
{
"epoch": 0.29548725764118194,
"grad_norm": 0.4441055655479431,
"learning_rate": 2e-05,
"loss": 0.6242,
"step": 3490
},
{
"epoch": 0.29633392600118535,
"grad_norm": 0.43486303091049194,
"learning_rate": 2e-05,
"loss": 0.6218,
"step": 3500
},
{
"epoch": 0.2971805943611887,
"grad_norm": 0.4182334244251251,
"learning_rate": 2e-05,
"loss": 0.6393,
"step": 3510
},
{
"epoch": 0.2980272627211921,
"grad_norm": 0.4296554923057556,
"learning_rate": 2e-05,
"loss": 0.6545,
"step": 3520
},
{
"epoch": 0.2988739310811955,
"grad_norm": 0.4029640257358551,
"learning_rate": 2e-05,
"loss": 0.6267,
"step": 3530
},
{
"epoch": 0.2997205994411989,
"grad_norm": 0.5285282731056213,
"learning_rate": 2e-05,
"loss": 0.6334,
"step": 3540
},
{
"epoch": 0.30056726780120224,
"grad_norm": 0.4067811071872711,
"learning_rate": 2e-05,
"loss": 0.6183,
"step": 3550
},
{
"epoch": 0.30141393616120565,
"grad_norm": 0.40235307812690735,
"learning_rate": 2e-05,
"loss": 0.6463,
"step": 3560
},
{
"epoch": 0.30226060452120906,
"grad_norm": 0.39202913641929626,
"learning_rate": 2e-05,
"loss": 0.6578,
"step": 3570
},
{
"epoch": 0.3031072728812124,
"grad_norm": 0.43644803762435913,
"learning_rate": 2e-05,
"loss": 0.6139,
"step": 3580
},
{
"epoch": 0.30395394124121583,
"grad_norm": 0.4295779764652252,
"learning_rate": 2e-05,
"loss": 0.6569,
"step": 3590
},
{
"epoch": 0.3048006096012192,
"grad_norm": 0.3815408945083618,
"learning_rate": 2e-05,
"loss": 0.6371,
"step": 3600
},
{
"epoch": 0.3056472779612226,
"grad_norm": 0.3733167350292206,
"learning_rate": 2e-05,
"loss": 0.6311,
"step": 3610
},
{
"epoch": 0.30649394632122595,
"grad_norm": 0.40843579173088074,
"learning_rate": 2e-05,
"loss": 0.6308,
"step": 3620
},
{
"epoch": 0.30734061468122936,
"grad_norm": 0.39684557914733887,
"learning_rate": 2e-05,
"loss": 0.611,
"step": 3630
},
{
"epoch": 0.3081872830412328,
"grad_norm": 0.3786352872848511,
"learning_rate": 2e-05,
"loss": 0.6298,
"step": 3640
},
{
"epoch": 0.30903395140123613,
"grad_norm": 0.3809105157852173,
"learning_rate": 2e-05,
"loss": 0.6223,
"step": 3650
},
{
"epoch": 0.30988061976123954,
"grad_norm": 0.3611084818840027,
"learning_rate": 2e-05,
"loss": 0.623,
"step": 3660
},
{
"epoch": 0.3107272881212429,
"grad_norm": 0.4300227761268616,
"learning_rate": 2e-05,
"loss": 0.6246,
"step": 3670
},
{
"epoch": 0.3115739564812463,
"grad_norm": 0.38485798239707947,
"learning_rate": 2e-05,
"loss": 0.6279,
"step": 3680
},
{
"epoch": 0.31242062484124966,
"grad_norm": 0.4136834442615509,
"learning_rate": 2e-05,
"loss": 0.6415,
"step": 3690
},
{
"epoch": 0.31326729320125307,
"grad_norm": 0.3984295427799225,
"learning_rate": 2e-05,
"loss": 0.6462,
"step": 3700
},
{
"epoch": 0.3141139615612565,
"grad_norm": 0.4182433485984802,
"learning_rate": 2e-05,
"loss": 0.606,
"step": 3710
},
{
"epoch": 0.31496062992125984,
"grad_norm": 0.4438022971153259,
"learning_rate": 2e-05,
"loss": 0.6558,
"step": 3720
},
{
"epoch": 0.31580729828126325,
"grad_norm": 0.41767048835754395,
"learning_rate": 2e-05,
"loss": 0.6353,
"step": 3730
},
{
"epoch": 0.3166539666412666,
"grad_norm": 0.373098224401474,
"learning_rate": 2e-05,
"loss": 0.6089,
"step": 3740
},
{
"epoch": 0.31750063500127,
"grad_norm": 0.4146307408809662,
"learning_rate": 2e-05,
"loss": 0.6299,
"step": 3750
},
{
"epoch": 0.31834730336127337,
"grad_norm": 0.38848984241485596,
"learning_rate": 2e-05,
"loss": 0.6499,
"step": 3760
},
{
"epoch": 0.3191939717212768,
"grad_norm": 0.5025537610054016,
"learning_rate": 2e-05,
"loss": 0.6271,
"step": 3770
},
{
"epoch": 0.32004064008128014,
"grad_norm": 0.3962385058403015,
"learning_rate": 2e-05,
"loss": 0.6237,
"step": 3780
},
{
"epoch": 0.32088730844128355,
"grad_norm": 1.6572647094726562,
"learning_rate": 2e-05,
"loss": 0.6302,
"step": 3790
},
{
"epoch": 0.32173397680128696,
"grad_norm": 0.3944777548313141,
"learning_rate": 2e-05,
"loss": 0.6497,
"step": 3800
},
{
"epoch": 0.3225806451612903,
"grad_norm": 0.3777221739292145,
"learning_rate": 2e-05,
"loss": 0.6308,
"step": 3810
},
{
"epoch": 0.3234273135212937,
"grad_norm": 0.610248863697052,
"learning_rate": 2e-05,
"loss": 0.6372,
"step": 3820
},
{
"epoch": 0.3242739818812971,
"grad_norm": 0.47404029965400696,
"learning_rate": 2e-05,
"loss": 0.632,
"step": 3830
},
{
"epoch": 0.3251206502413005,
"grad_norm": 0.40445438027381897,
"learning_rate": 2e-05,
"loss": 0.6244,
"step": 3840
},
{
"epoch": 0.32596731860130385,
"grad_norm": 0.4113180339336395,
"learning_rate": 2e-05,
"loss": 0.6634,
"step": 3850
},
{
"epoch": 0.32681398696130726,
"grad_norm": 0.44300517439842224,
"learning_rate": 2e-05,
"loss": 0.6338,
"step": 3860
},
{
"epoch": 0.32766065532131067,
"grad_norm": 0.4578755497932434,
"learning_rate": 2e-05,
"loss": 0.6167,
"step": 3870
},
{
"epoch": 0.328507323681314,
"grad_norm": 0.4159300625324249,
"learning_rate": 2e-05,
"loss": 0.6118,
"step": 3880
},
{
"epoch": 0.32935399204131743,
"grad_norm": 0.3916099965572357,
"learning_rate": 2e-05,
"loss": 0.6112,
"step": 3890
},
{
"epoch": 0.3302006604013208,
"grad_norm": 0.37913331389427185,
"learning_rate": 2e-05,
"loss": 0.637,
"step": 3900
},
{
"epoch": 0.3310473287613242,
"grad_norm": 0.46422481536865234,
"learning_rate": 2e-05,
"loss": 0.6487,
"step": 3910
},
{
"epoch": 0.33189399712132756,
"grad_norm": 0.39226099848747253,
"learning_rate": 2e-05,
"loss": 0.6097,
"step": 3920
},
{
"epoch": 0.33274066548133097,
"grad_norm": 1.2026352882385254,
"learning_rate": 2e-05,
"loss": 0.6022,
"step": 3930
},
{
"epoch": 0.3335873338413344,
"grad_norm": 0.3941093385219574,
"learning_rate": 2e-05,
"loss": 0.6158,
"step": 3940
},
{
"epoch": 0.33443400220133773,
"grad_norm": 0.39497110247612,
"learning_rate": 2e-05,
"loss": 0.6191,
"step": 3950
},
{
"epoch": 0.33528067056134114,
"grad_norm": 0.3979906439781189,
"learning_rate": 2e-05,
"loss": 0.6527,
"step": 3960
},
{
"epoch": 0.3361273389213445,
"grad_norm": 0.41514596343040466,
"learning_rate": 2e-05,
"loss": 0.6497,
"step": 3970
},
{
"epoch": 0.3369740072813479,
"grad_norm": 0.3805382251739502,
"learning_rate": 2e-05,
"loss": 0.6523,
"step": 3980
},
{
"epoch": 0.33782067564135126,
"grad_norm": 0.38798990845680237,
"learning_rate": 2e-05,
"loss": 0.6435,
"step": 3990
},
{
"epoch": 0.3386673440013547,
"grad_norm": 0.3779199421405792,
"learning_rate": 2e-05,
"loss": 0.6047,
"step": 4000
},
{
"epoch": 0.33951401236135803,
"grad_norm": 0.43265098333358765,
"learning_rate": 2e-05,
"loss": 0.6488,
"step": 4010
},
{
"epoch": 0.34036068072136144,
"grad_norm": 0.4250130355358124,
"learning_rate": 2e-05,
"loss": 0.6166,
"step": 4020
},
{
"epoch": 0.34120734908136485,
"grad_norm": 0.3824594020843506,
"learning_rate": 2e-05,
"loss": 0.6584,
"step": 4030
},
{
"epoch": 0.3420540174413682,
"grad_norm": 0.3953022360801697,
"learning_rate": 2e-05,
"loss": 0.636,
"step": 4040
},
{
"epoch": 0.3429006858013716,
"grad_norm": 0.376534640789032,
"learning_rate": 2e-05,
"loss": 0.625,
"step": 4050
},
{
"epoch": 0.343747354161375,
"grad_norm": 0.4311833381652832,
"learning_rate": 2e-05,
"loss": 0.6194,
"step": 4060
},
{
"epoch": 0.3445940225213784,
"grad_norm": 0.3738897144794464,
"learning_rate": 2e-05,
"loss": 0.6239,
"step": 4070
},
{
"epoch": 0.34544069088138174,
"grad_norm": 0.38045012950897217,
"learning_rate": 2e-05,
"loss": 0.6083,
"step": 4080
},
{
"epoch": 0.34628735924138515,
"grad_norm": 0.3941081762313843,
"learning_rate": 2e-05,
"loss": 0.6256,
"step": 4090
},
{
"epoch": 0.34713402760138856,
"grad_norm": 0.39207085967063904,
"learning_rate": 2e-05,
"loss": 0.6153,
"step": 4100
},
{
"epoch": 0.3479806959613919,
"grad_norm": 0.38253340125083923,
"learning_rate": 2e-05,
"loss": 0.6183,
"step": 4110
},
{
"epoch": 0.34882736432139533,
"grad_norm": 0.42153647541999817,
"learning_rate": 2e-05,
"loss": 0.6389,
"step": 4120
},
{
"epoch": 0.3496740326813987,
"grad_norm": 0.37590694427490234,
"learning_rate": 2e-05,
"loss": 0.632,
"step": 4130
},
{
"epoch": 0.3505207010414021,
"grad_norm": 0.3831784427165985,
"learning_rate": 2e-05,
"loss": 0.6161,
"step": 4140
},
{
"epoch": 0.35136736940140545,
"grad_norm": 0.4095568358898163,
"learning_rate": 2e-05,
"loss": 0.6354,
"step": 4150
},
{
"epoch": 0.35221403776140886,
"grad_norm": 0.3940264582633972,
"learning_rate": 2e-05,
"loss": 0.6281,
"step": 4160
},
{
"epoch": 0.3530607061214122,
"grad_norm": 0.39979925751686096,
"learning_rate": 2e-05,
"loss": 0.6322,
"step": 4170
},
{
"epoch": 0.3539073744814156,
"grad_norm": 0.4350389540195465,
"learning_rate": 2e-05,
"loss": 0.6244,
"step": 4180
},
{
"epoch": 0.35475404284141904,
"grad_norm": 0.37078574299812317,
"learning_rate": 2e-05,
"loss": 0.6163,
"step": 4190
},
{
"epoch": 0.3556007112014224,
"grad_norm": 0.39877039194107056,
"learning_rate": 2e-05,
"loss": 0.6191,
"step": 4200
},
{
"epoch": 0.3564473795614258,
"grad_norm": 0.4154704511165619,
"learning_rate": 2e-05,
"loss": 0.6212,
"step": 4210
},
{
"epoch": 0.35729404792142916,
"grad_norm": 0.42669203877449036,
"learning_rate": 2e-05,
"loss": 0.6532,
"step": 4220
},
{
"epoch": 0.35814071628143257,
"grad_norm": 0.4079524874687195,
"learning_rate": 2e-05,
"loss": 0.6423,
"step": 4230
},
{
"epoch": 0.3589873846414359,
"grad_norm": 0.3937144875526428,
"learning_rate": 2e-05,
"loss": 0.6236,
"step": 4240
},
{
"epoch": 0.35983405300143934,
"grad_norm": 0.4334471523761749,
"learning_rate": 2e-05,
"loss": 0.6285,
"step": 4250
},
{
"epoch": 0.36068072136144275,
"grad_norm": 0.3907918334007263,
"learning_rate": 2e-05,
"loss": 0.6254,
"step": 4260
},
{
"epoch": 0.3615273897214461,
"grad_norm": 1.0858243703842163,
"learning_rate": 2e-05,
"loss": 0.6437,
"step": 4270
},
{
"epoch": 0.3623740580814495,
"grad_norm": 0.41078153252601624,
"learning_rate": 2e-05,
"loss": 0.6251,
"step": 4280
},
{
"epoch": 0.36322072644145287,
"grad_norm": 0.39965513348579407,
"learning_rate": 2e-05,
"loss": 0.6131,
"step": 4290
},
{
"epoch": 0.3640673948014563,
"grad_norm": 0.42311328649520874,
"learning_rate": 2e-05,
"loss": 0.5952,
"step": 4300
},
{
"epoch": 0.36491406316145963,
"grad_norm": 0.39749035239219666,
"learning_rate": 2e-05,
"loss": 0.6952,
"step": 4310
},
{
"epoch": 0.36576073152146305,
"grad_norm": 0.4066619575023651,
"learning_rate": 2e-05,
"loss": 0.6195,
"step": 4320
},
{
"epoch": 0.36660739988146646,
"grad_norm": 0.40869539976119995,
"learning_rate": 2e-05,
"loss": 0.6551,
"step": 4330
},
{
"epoch": 0.3674540682414698,
"grad_norm": 0.38594356179237366,
"learning_rate": 2e-05,
"loss": 0.6176,
"step": 4340
},
{
"epoch": 0.3683007366014732,
"grad_norm": 0.3964534103870392,
"learning_rate": 2e-05,
"loss": 0.6108,
"step": 4350
},
{
"epoch": 0.3691474049614766,
"grad_norm": 0.3941608965396881,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 4360
},
{
"epoch": 0.36999407332148,
"grad_norm": 0.38923901319503784,
"learning_rate": 2e-05,
"loss": 0.6089,
"step": 4370
},
{
"epoch": 0.37084074168148334,
"grad_norm": 0.4024799168109894,
"learning_rate": 2e-05,
"loss": 0.6444,
"step": 4380
},
{
"epoch": 0.37168741004148675,
"grad_norm": 0.42518913745880127,
"learning_rate": 2e-05,
"loss": 0.6339,
"step": 4390
},
{
"epoch": 0.3725340784014901,
"grad_norm": 0.40740522742271423,
"learning_rate": 2e-05,
"loss": 0.6365,
"step": 4400
},
{
"epoch": 0.3733807467614935,
"grad_norm": 0.41317957639694214,
"learning_rate": 2e-05,
"loss": 0.6253,
"step": 4410
},
{
"epoch": 0.37422741512149693,
"grad_norm": 0.3998070955276489,
"learning_rate": 2e-05,
"loss": 0.6328,
"step": 4420
},
{
"epoch": 0.3750740834815003,
"grad_norm": 0.3857688903808594,
"learning_rate": 2e-05,
"loss": 0.6482,
"step": 4430
},
{
"epoch": 0.3759207518415037,
"grad_norm": 0.38020142912864685,
"learning_rate": 2e-05,
"loss": 0.6165,
"step": 4440
},
{
"epoch": 0.37676742020150705,
"grad_norm": 0.5042953491210938,
"learning_rate": 2e-05,
"loss": 0.6215,
"step": 4450
},
{
"epoch": 0.37761408856151046,
"grad_norm": 0.386430948972702,
"learning_rate": 2e-05,
"loss": 0.6155,
"step": 4460
},
{
"epoch": 0.3784607569215138,
"grad_norm": 0.40141937136650085,
"learning_rate": 2e-05,
"loss": 0.6164,
"step": 4470
},
{
"epoch": 0.37930742528151723,
"grad_norm": 0.3964422941207886,
"learning_rate": 2e-05,
"loss": 0.62,
"step": 4480
},
{
"epoch": 0.38015409364152064,
"grad_norm": 0.4356025457382202,
"learning_rate": 2e-05,
"loss": 0.628,
"step": 4490
},
{
"epoch": 0.381000762001524,
"grad_norm": 0.4093104302883148,
"learning_rate": 2e-05,
"loss": 0.6206,
"step": 4500
},
{
"epoch": 0.3818474303615274,
"grad_norm": 0.3951672911643982,
"learning_rate": 2e-05,
"loss": 0.6189,
"step": 4510
},
{
"epoch": 0.38269409872153076,
"grad_norm": 0.4975200891494751,
"learning_rate": 2e-05,
"loss": 0.6353,
"step": 4520
},
{
"epoch": 0.3835407670815342,
"grad_norm": 0.3646867871284485,
"learning_rate": 2e-05,
"loss": 0.623,
"step": 4530
},
{
"epoch": 0.38438743544153753,
"grad_norm": 0.41711995005607605,
"learning_rate": 2e-05,
"loss": 0.6269,
"step": 4540
},
{
"epoch": 0.38523410380154094,
"grad_norm": 0.4198454022407532,
"learning_rate": 2e-05,
"loss": 0.6523,
"step": 4550
},
{
"epoch": 0.38608077216154435,
"grad_norm": 0.4093538820743561,
"learning_rate": 2e-05,
"loss": 0.6195,
"step": 4560
},
{
"epoch": 0.3869274405215477,
"grad_norm": 0.40226060152053833,
"learning_rate": 2e-05,
"loss": 0.6192,
"step": 4570
},
{
"epoch": 0.3877741088815511,
"grad_norm": 0.4073827862739563,
"learning_rate": 2e-05,
"loss": 0.6323,
"step": 4580
},
{
"epoch": 0.38862077724155447,
"grad_norm": 0.3588709533214569,
"learning_rate": 2e-05,
"loss": 0.6223,
"step": 4590
},
{
"epoch": 0.3894674456015579,
"grad_norm": 0.4277055859565735,
"learning_rate": 2e-05,
"loss": 0.6366,
"step": 4600
},
{
"epoch": 0.39031411396156124,
"grad_norm": 0.3982546031475067,
"learning_rate": 2e-05,
"loss": 0.6184,
"step": 4610
},
{
"epoch": 0.39116078232156465,
"grad_norm": 0.4190221428871155,
"learning_rate": 2e-05,
"loss": 0.5989,
"step": 4620
},
{
"epoch": 0.392007450681568,
"grad_norm": 0.4254496395587921,
"learning_rate": 2e-05,
"loss": 0.6337,
"step": 4630
},
{
"epoch": 0.3928541190415714,
"grad_norm": 0.4280596375465393,
"learning_rate": 2e-05,
"loss": 0.6368,
"step": 4640
},
{
"epoch": 0.3937007874015748,
"grad_norm": 0.3961775302886963,
"learning_rate": 2e-05,
"loss": 0.6065,
"step": 4650
},
{
"epoch": 0.3945474557615782,
"grad_norm": 0.4123854339122772,
"learning_rate": 2e-05,
"loss": 0.6153,
"step": 4660
},
{
"epoch": 0.3953941241215816,
"grad_norm": 0.48063772916793823,
"learning_rate": 2e-05,
"loss": 0.6202,
"step": 4670
},
{
"epoch": 0.39624079248158495,
"grad_norm": 0.40130090713500977,
"learning_rate": 2e-05,
"loss": 0.6355,
"step": 4680
},
{
"epoch": 0.39708746084158836,
"grad_norm": 0.4136877655982971,
"learning_rate": 2e-05,
"loss": 0.6247,
"step": 4690
},
{
"epoch": 0.3979341292015917,
"grad_norm": 0.36779603362083435,
"learning_rate": 2e-05,
"loss": 0.6238,
"step": 4700
},
{
"epoch": 0.3987807975615951,
"grad_norm": 0.40029042959213257,
"learning_rate": 2e-05,
"loss": 0.6176,
"step": 4710
},
{
"epoch": 0.39962746592159853,
"grad_norm": 0.43001070618629456,
"learning_rate": 2e-05,
"loss": 0.6214,
"step": 4720
},
{
"epoch": 0.4004741342816019,
"grad_norm": 0.3810120224952698,
"learning_rate": 2e-05,
"loss": 0.6356,
"step": 4730
},
{
"epoch": 0.4013208026416053,
"grad_norm": 0.39227691292762756,
"learning_rate": 2e-05,
"loss": 0.6086,
"step": 4740
},
{
"epoch": 0.40216747100160866,
"grad_norm": 0.3904576003551483,
"learning_rate": 2e-05,
"loss": 0.6474,
"step": 4750
},
{
"epoch": 0.40301413936161207,
"grad_norm": 0.391421377658844,
"learning_rate": 2e-05,
"loss": 0.6125,
"step": 4760
},
{
"epoch": 0.4038608077216154,
"grad_norm": 0.390818327665329,
"learning_rate": 2e-05,
"loss": 0.6332,
"step": 4770
},
{
"epoch": 0.40470747608161883,
"grad_norm": 0.3884637951850891,
"learning_rate": 2e-05,
"loss": 0.6234,
"step": 4780
},
{
"epoch": 0.40555414444162224,
"grad_norm": 0.39960721135139465,
"learning_rate": 2e-05,
"loss": 0.6069,
"step": 4790
},
{
"epoch": 0.4064008128016256,
"grad_norm": 0.38708916306495667,
"learning_rate": 2e-05,
"loss": 0.6039,
"step": 4800
},
{
"epoch": 0.407247481161629,
"grad_norm": 0.37994828820228577,
"learning_rate": 2e-05,
"loss": 0.6556,
"step": 4810
},
{
"epoch": 0.40809414952163237,
"grad_norm": 0.7117851972579956,
"learning_rate": 2e-05,
"loss": 0.652,
"step": 4820
},
{
"epoch": 0.4089408178816358,
"grad_norm": 0.3768075108528137,
"learning_rate": 2e-05,
"loss": 0.6307,
"step": 4830
},
{
"epoch": 0.40978748624163913,
"grad_norm": 0.3990342915058136,
"learning_rate": 2e-05,
"loss": 0.606,
"step": 4840
},
{
"epoch": 0.41063415460164254,
"grad_norm": 0.35445788502693176,
"learning_rate": 2e-05,
"loss": 0.6162,
"step": 4850
},
{
"epoch": 0.4114808229616459,
"grad_norm": 0.4304513931274414,
"learning_rate": 2e-05,
"loss": 0.6532,
"step": 4860
},
{
"epoch": 0.4123274913216493,
"grad_norm": 0.38317644596099854,
"learning_rate": 2e-05,
"loss": 0.6274,
"step": 4870
},
{
"epoch": 0.4131741596816527,
"grad_norm": 0.3761354684829712,
"learning_rate": 2e-05,
"loss": 0.6197,
"step": 4880
},
{
"epoch": 0.4140208280416561,
"grad_norm": 0.3854663074016571,
"learning_rate": 2e-05,
"loss": 0.6159,
"step": 4890
},
{
"epoch": 0.4148674964016595,
"grad_norm": 0.40026572346687317,
"learning_rate": 2e-05,
"loss": 0.6318,
"step": 4900
},
{
"epoch": 0.41571416476166284,
"grad_norm": 0.3976708948612213,
"learning_rate": 2e-05,
"loss": 0.6221,
"step": 4910
},
{
"epoch": 0.41656083312166625,
"grad_norm": 0.40661197900772095,
"learning_rate": 2e-05,
"loss": 0.6197,
"step": 4920
},
{
"epoch": 0.4174075014816696,
"grad_norm": 0.4020674526691437,
"learning_rate": 2e-05,
"loss": 0.6273,
"step": 4930
},
{
"epoch": 0.418254169841673,
"grad_norm": 0.3835592269897461,
"learning_rate": 2e-05,
"loss": 0.6139,
"step": 4940
},
{
"epoch": 0.41910083820167643,
"grad_norm": 0.7613312005996704,
"learning_rate": 2e-05,
"loss": 0.6188,
"step": 4950
},
{
"epoch": 0.4199475065616798,
"grad_norm": 0.35623157024383545,
"learning_rate": 2e-05,
"loss": 0.6257,
"step": 4960
},
{
"epoch": 0.4207941749216832,
"grad_norm": 0.4170803725719452,
"learning_rate": 2e-05,
"loss": 0.6251,
"step": 4970
},
{
"epoch": 0.42164084328168655,
"grad_norm": 0.4270610213279724,
"learning_rate": 2e-05,
"loss": 0.6199,
"step": 4980
},
{
"epoch": 0.42248751164168996,
"grad_norm": 0.37874191999435425,
"learning_rate": 2e-05,
"loss": 0.6253,
"step": 4990
},
{
"epoch": 0.4233341800016933,
"grad_norm": 0.38245901465415955,
"learning_rate": 2e-05,
"loss": 0.623,
"step": 5000
},
{
"epoch": 0.4241808483616967,
"grad_norm": 0.3769111931324005,
"learning_rate": 2e-05,
"loss": 0.6144,
"step": 5010
},
{
"epoch": 0.4250275167217001,
"grad_norm": 0.3969614803791046,
"learning_rate": 2e-05,
"loss": 0.6428,
"step": 5020
},
{
"epoch": 0.4258741850817035,
"grad_norm": 0.3712959885597229,
"learning_rate": 2e-05,
"loss": 0.6126,
"step": 5030
},
{
"epoch": 0.4267208534417069,
"grad_norm": 0.39354589581489563,
"learning_rate": 2e-05,
"loss": 0.6328,
"step": 5040
},
{
"epoch": 0.42756752180171026,
"grad_norm": 0.3992328345775604,
"learning_rate": 2e-05,
"loss": 0.6156,
"step": 5050
},
{
"epoch": 0.42841419016171367,
"grad_norm": 0.3825113773345947,
"learning_rate": 2e-05,
"loss": 0.6107,
"step": 5060
},
{
"epoch": 0.429260858521717,
"grad_norm": 0.4251422882080078,
"learning_rate": 2e-05,
"loss": 0.6335,
"step": 5070
},
{
"epoch": 0.43010752688172044,
"grad_norm": 0.38227295875549316,
"learning_rate": 2e-05,
"loss": 0.6166,
"step": 5080
},
{
"epoch": 0.4309541952417238,
"grad_norm": 0.4403885006904602,
"learning_rate": 2e-05,
"loss": 0.6371,
"step": 5090
},
{
"epoch": 0.4318008636017272,
"grad_norm": 0.3744010031223297,
"learning_rate": 2e-05,
"loss": 0.6087,
"step": 5100
},
{
"epoch": 0.4326475319617306,
"grad_norm": 0.45299652218818665,
"learning_rate": 2e-05,
"loss": 0.6404,
"step": 5110
},
{
"epoch": 0.43349420032173397,
"grad_norm": 0.3822351396083832,
"learning_rate": 2e-05,
"loss": 0.6431,
"step": 5120
},
{
"epoch": 0.4343408686817374,
"grad_norm": 0.4114062190055847,
"learning_rate": 2e-05,
"loss": 0.6014,
"step": 5130
},
{
"epoch": 0.43518753704174074,
"grad_norm": 0.5163050293922424,
"learning_rate": 2e-05,
"loss": 0.6297,
"step": 5140
},
{
"epoch": 0.43603420540174415,
"grad_norm": 0.44163233041763306,
"learning_rate": 2e-05,
"loss": 0.6284,
"step": 5150
},
{
"epoch": 0.4368808737617475,
"grad_norm": 0.3803614675998688,
"learning_rate": 2e-05,
"loss": 0.6127,
"step": 5160
},
{
"epoch": 0.4377275421217509,
"grad_norm": 0.39460161328315735,
"learning_rate": 2e-05,
"loss": 0.6221,
"step": 5170
},
{
"epoch": 0.4385742104817543,
"grad_norm": 0.3786770701408386,
"learning_rate": 2e-05,
"loss": 0.6366,
"step": 5180
},
{
"epoch": 0.4394208788417577,
"grad_norm": 0.36957380175590515,
"learning_rate": 2e-05,
"loss": 0.6167,
"step": 5190
},
{
"epoch": 0.4402675472017611,
"grad_norm": 0.44866517186164856,
"learning_rate": 2e-05,
"loss": 0.6023,
"step": 5200
},
{
"epoch": 0.44111421556176444,
"grad_norm": 0.4208207428455353,
"learning_rate": 2e-05,
"loss": 0.613,
"step": 5210
},
{
"epoch": 0.44196088392176786,
"grad_norm": 0.4040125608444214,
"learning_rate": 2e-05,
"loss": 0.6223,
"step": 5220
},
{
"epoch": 0.4428075522817712,
"grad_norm": 0.3763856589794159,
"learning_rate": 2e-05,
"loss": 0.6259,
"step": 5230
},
{
"epoch": 0.4436542206417746,
"grad_norm": 0.42872604727745056,
"learning_rate": 2e-05,
"loss": 0.609,
"step": 5240
},
{
"epoch": 0.444500889001778,
"grad_norm": 0.3778369426727295,
"learning_rate": 2e-05,
"loss": 0.5949,
"step": 5250
},
{
"epoch": 0.4453475573617814,
"grad_norm": 0.38003063201904297,
"learning_rate": 2e-05,
"loss": 0.6116,
"step": 5260
},
{
"epoch": 0.4461942257217848,
"grad_norm": 0.4087657630443573,
"learning_rate": 2e-05,
"loss": 0.6116,
"step": 5270
},
{
"epoch": 0.44704089408178815,
"grad_norm": 0.3919980227947235,
"learning_rate": 2e-05,
"loss": 0.6292,
"step": 5280
},
{
"epoch": 0.44788756244179156,
"grad_norm": 0.3907471299171448,
"learning_rate": 2e-05,
"loss": 0.6211,
"step": 5290
},
{
"epoch": 0.4487342308017949,
"grad_norm": 0.3696645498275757,
"learning_rate": 2e-05,
"loss": 0.6335,
"step": 5300
},
{
"epoch": 0.44958089916179833,
"grad_norm": 0.382074773311615,
"learning_rate": 2e-05,
"loss": 0.6111,
"step": 5310
},
{
"epoch": 0.4504275675218017,
"grad_norm": 0.379029780626297,
"learning_rate": 2e-05,
"loss": 0.6249,
"step": 5320
},
{
"epoch": 0.4512742358818051,
"grad_norm": 0.4117835760116577,
"learning_rate": 2e-05,
"loss": 0.6433,
"step": 5330
},
{
"epoch": 0.4521209042418085,
"grad_norm": 0.38409513235092163,
"learning_rate": 2e-05,
"loss": 0.6045,
"step": 5340
},
{
"epoch": 0.45296757260181186,
"grad_norm": 0.40082046389579773,
"learning_rate": 2e-05,
"loss": 0.6342,
"step": 5350
},
{
"epoch": 0.4538142409618153,
"grad_norm": 0.40909379720687866,
"learning_rate": 2e-05,
"loss": 0.6364,
"step": 5360
},
{
"epoch": 0.45466090932181863,
"grad_norm": 0.35277318954467773,
"learning_rate": 2e-05,
"loss": 0.6193,
"step": 5370
},
{
"epoch": 0.45550757768182204,
"grad_norm": 0.41141676902770996,
"learning_rate": 2e-05,
"loss": 0.6273,
"step": 5380
},
{
"epoch": 0.4563542460418254,
"grad_norm": 0.37007519602775574,
"learning_rate": 2e-05,
"loss": 0.6045,
"step": 5390
},
{
"epoch": 0.4572009144018288,
"grad_norm": 0.3860960006713867,
"learning_rate": 2e-05,
"loss": 0.6119,
"step": 5400
},
{
"epoch": 0.4580475827618322,
"grad_norm": 0.3925631046295166,
"learning_rate": 2e-05,
"loss": 0.6237,
"step": 5410
},
{
"epoch": 0.4588942511218356,
"grad_norm": 0.3930700123310089,
"learning_rate": 2e-05,
"loss": 0.6167,
"step": 5420
},
{
"epoch": 0.459740919481839,
"grad_norm": 0.43241187930107117,
"learning_rate": 2e-05,
"loss": 0.6327,
"step": 5430
},
{
"epoch": 0.46058758784184234,
"grad_norm": 0.34997665882110596,
"learning_rate": 2e-05,
"loss": 0.6269,
"step": 5440
},
{
"epoch": 0.46143425620184575,
"grad_norm": 0.790996253490448,
"learning_rate": 2e-05,
"loss": 0.5964,
"step": 5450
},
{
"epoch": 0.4622809245618491,
"grad_norm": 0.3868573009967804,
"learning_rate": 2e-05,
"loss": 0.6262,
"step": 5460
},
{
"epoch": 0.4631275929218525,
"grad_norm": 0.38071146607398987,
"learning_rate": 2e-05,
"loss": 0.6227,
"step": 5470
},
{
"epoch": 0.46397426128185587,
"grad_norm": 0.38451120257377625,
"learning_rate": 2e-05,
"loss": 0.626,
"step": 5480
},
{
"epoch": 0.4648209296418593,
"grad_norm": 0.38303887844085693,
"learning_rate": 2e-05,
"loss": 0.6064,
"step": 5490
},
{
"epoch": 0.4656675980018627,
"grad_norm": 0.3989908695220947,
"learning_rate": 2e-05,
"loss": 0.6275,
"step": 5500
},
{
"epoch": 0.46651426636186605,
"grad_norm": 0.3892296850681305,
"learning_rate": 2e-05,
"loss": 0.6088,
"step": 5510
},
{
"epoch": 0.46736093472186946,
"grad_norm": 0.5384352207183838,
"learning_rate": 2e-05,
"loss": 0.6199,
"step": 5520
},
{
"epoch": 0.4682076030818728,
"grad_norm": 0.6262787580490112,
"learning_rate": 2e-05,
"loss": 0.6307,
"step": 5530
},
{
"epoch": 0.4690542714418762,
"grad_norm": 0.3861103951931,
"learning_rate": 2e-05,
"loss": 0.6104,
"step": 5540
},
{
"epoch": 0.4699009398018796,
"grad_norm": 0.40356874465942383,
"learning_rate": 2e-05,
"loss": 0.627,
"step": 5550
},
{
"epoch": 0.470747608161883,
"grad_norm": 0.43609845638275146,
"learning_rate": 2e-05,
"loss": 0.5952,
"step": 5560
},
{
"epoch": 0.4715942765218864,
"grad_norm": 0.39195698499679565,
"learning_rate": 2e-05,
"loss": 0.6164,
"step": 5570
},
{
"epoch": 0.47244094488188976,
"grad_norm": 0.3546348810195923,
"learning_rate": 2e-05,
"loss": 0.6273,
"step": 5580
},
{
"epoch": 0.47328761324189317,
"grad_norm": 0.39188459515571594,
"learning_rate": 2e-05,
"loss": 0.6351,
"step": 5590
},
{
"epoch": 0.4741342816018965,
"grad_norm": 0.4113193154335022,
"learning_rate": 2e-05,
"loss": 0.6325,
"step": 5600
},
{
"epoch": 0.47498094996189993,
"grad_norm": 0.8631526827812195,
"learning_rate": 2e-05,
"loss": 0.6127,
"step": 5610
},
{
"epoch": 0.4758276183219033,
"grad_norm": 0.4838610887527466,
"learning_rate": 2e-05,
"loss": 0.6211,
"step": 5620
},
{
"epoch": 0.4766742866819067,
"grad_norm": 0.37433528900146484,
"learning_rate": 2e-05,
"loss": 0.6256,
"step": 5630
},
{
"epoch": 0.4775209550419101,
"grad_norm": 0.4030015468597412,
"learning_rate": 2e-05,
"loss": 0.6094,
"step": 5640
},
{
"epoch": 0.47836762340191347,
"grad_norm": 0.3941618800163269,
"learning_rate": 2e-05,
"loss": 0.6296,
"step": 5650
},
{
"epoch": 0.4792142917619169,
"grad_norm": 0.42247527837753296,
"learning_rate": 2e-05,
"loss": 0.6183,
"step": 5660
},
{
"epoch": 0.48006096012192023,
"grad_norm": 0.376878023147583,
"learning_rate": 2e-05,
"loss": 0.6068,
"step": 5670
},
{
"epoch": 0.48090762848192364,
"grad_norm": 0.37471485137939453,
"learning_rate": 2e-05,
"loss": 0.6231,
"step": 5680
},
{
"epoch": 0.481754296841927,
"grad_norm": 0.38369908928871155,
"learning_rate": 2e-05,
"loss": 0.6383,
"step": 5690
},
{
"epoch": 0.4826009652019304,
"grad_norm": 0.3918490409851074,
"learning_rate": 2e-05,
"loss": 0.619,
"step": 5700
},
{
"epoch": 0.48344763356193377,
"grad_norm": 0.5818098187446594,
"learning_rate": 2e-05,
"loss": 0.6293,
"step": 5710
},
{
"epoch": 0.4842943019219372,
"grad_norm": 0.4046247601509094,
"learning_rate": 2e-05,
"loss": 0.628,
"step": 5720
},
{
"epoch": 0.4851409702819406,
"grad_norm": 0.4430328905582428,
"learning_rate": 2e-05,
"loss": 0.6263,
"step": 5730
},
{
"epoch": 0.48598763864194394,
"grad_norm": 0.38619911670684814,
"learning_rate": 2e-05,
"loss": 0.641,
"step": 5740
},
{
"epoch": 0.48683430700194735,
"grad_norm": 0.38383662700653076,
"learning_rate": 2e-05,
"loss": 0.6432,
"step": 5750
},
{
"epoch": 0.4876809753619507,
"grad_norm": 0.3846624791622162,
"learning_rate": 2e-05,
"loss": 0.628,
"step": 5760
},
{
"epoch": 0.4885276437219541,
"grad_norm": 0.38642942905426025,
"learning_rate": 2e-05,
"loss": 0.6184,
"step": 5770
},
{
"epoch": 0.4893743120819575,
"grad_norm": 0.4044201672077179,
"learning_rate": 2e-05,
"loss": 0.6133,
"step": 5780
},
{
"epoch": 0.4902209804419609,
"grad_norm": 0.39951980113983154,
"learning_rate": 2e-05,
"loss": 0.6048,
"step": 5790
},
{
"epoch": 0.4910676488019643,
"grad_norm": 0.4093928039073944,
"learning_rate": 2e-05,
"loss": 0.616,
"step": 5800
},
{
"epoch": 0.49191431716196765,
"grad_norm": 0.3902198076248169,
"learning_rate": 2e-05,
"loss": 0.6186,
"step": 5810
},
{
"epoch": 0.49276098552197106,
"grad_norm": 0.38508084416389465,
"learning_rate": 2e-05,
"loss": 0.6347,
"step": 5820
},
{
"epoch": 0.4936076538819744,
"grad_norm": 0.36605313420295715,
"learning_rate": 2e-05,
"loss": 0.6244,
"step": 5830
},
{
"epoch": 0.49445432224197783,
"grad_norm": 0.4032215476036072,
"learning_rate": 2e-05,
"loss": 0.6234,
"step": 5840
},
{
"epoch": 0.4953009906019812,
"grad_norm": 0.40599551796913147,
"learning_rate": 2e-05,
"loss": 0.6175,
"step": 5850
},
{
"epoch": 0.4961476589619846,
"grad_norm": 0.37008124589920044,
"learning_rate": 2e-05,
"loss": 0.6096,
"step": 5860
},
{
"epoch": 0.49699432732198795,
"grad_norm": 0.3840043842792511,
"learning_rate": 2e-05,
"loss": 0.5977,
"step": 5870
},
{
"epoch": 0.49784099568199136,
"grad_norm": 0.37906673550605774,
"learning_rate": 2e-05,
"loss": 0.5994,
"step": 5880
},
{
"epoch": 0.49868766404199477,
"grad_norm": 0.3858088254928589,
"learning_rate": 2e-05,
"loss": 0.6175,
"step": 5890
},
{
"epoch": 0.4995343324019981,
"grad_norm": 0.3840956389904022,
"learning_rate": 2e-05,
"loss": 0.6038,
"step": 5900
},
{
"epoch": 0.5003810007620015,
"grad_norm": 0.3853210508823395,
"learning_rate": 2e-05,
"loss": 0.616,
"step": 5910
},
{
"epoch": 0.5012276691220049,
"grad_norm": 0.4054467976093292,
"learning_rate": 2e-05,
"loss": 0.633,
"step": 5920
},
{
"epoch": 0.5020743374820082,
"grad_norm": 0.3763441741466522,
"learning_rate": 2e-05,
"loss": 0.6273,
"step": 5930
},
{
"epoch": 0.5029210058420117,
"grad_norm": 0.3668249249458313,
"learning_rate": 2e-05,
"loss": 0.61,
"step": 5940
},
{
"epoch": 0.5037676742020151,
"grad_norm": 0.39875170588493347,
"learning_rate": 2e-05,
"loss": 0.6222,
"step": 5950
},
{
"epoch": 0.5046143425620184,
"grad_norm": 0.5287747979164124,
"learning_rate": 2e-05,
"loss": 0.6115,
"step": 5960
},
{
"epoch": 0.5054610109220219,
"grad_norm": 0.5001663565635681,
"learning_rate": 2e-05,
"loss": 0.6437,
"step": 5970
},
{
"epoch": 0.5063076792820252,
"grad_norm": 0.39348748326301575,
"learning_rate": 2e-05,
"loss": 0.6315,
"step": 5980
},
{
"epoch": 0.5071543476420286,
"grad_norm": 0.4100854694843292,
"learning_rate": 2e-05,
"loss": 0.6114,
"step": 5990
},
{
"epoch": 0.508001016002032,
"grad_norm": 0.35735663771629333,
"learning_rate": 2e-05,
"loss": 0.6265,
"step": 6000
},
{
"epoch": 0.5088476843620354,
"grad_norm": 0.3903975784778595,
"learning_rate": 2e-05,
"loss": 0.6249,
"step": 6010
},
{
"epoch": 0.5096943527220388,
"grad_norm": 0.41484081745147705,
"learning_rate": 2e-05,
"loss": 0.6108,
"step": 6020
},
{
"epoch": 0.5105410210820421,
"grad_norm": 0.3659946322441101,
"learning_rate": 2e-05,
"loss": 0.6284,
"step": 6030
},
{
"epoch": 0.5113876894420456,
"grad_norm": 0.39349204301834106,
"learning_rate": 2e-05,
"loss": 0.5987,
"step": 6040
},
{
"epoch": 0.512234357802049,
"grad_norm": 0.37909236550331116,
"learning_rate": 2e-05,
"loss": 0.6043,
"step": 6050
},
{
"epoch": 0.5130810261620523,
"grad_norm": 0.3876914978027344,
"learning_rate": 2e-05,
"loss": 0.6074,
"step": 6060
},
{
"epoch": 0.5139276945220557,
"grad_norm": 0.3759116232395172,
"learning_rate": 2e-05,
"loss": 0.6142,
"step": 6070
},
{
"epoch": 0.5147743628820591,
"grad_norm": 0.38986703753471375,
"learning_rate": 2e-05,
"loss": 0.5983,
"step": 6080
},
{
"epoch": 0.5156210312420625,
"grad_norm": 0.4110816419124603,
"learning_rate": 2e-05,
"loss": 0.6155,
"step": 6090
},
{
"epoch": 0.5164676996020658,
"grad_norm": 0.3793250322341919,
"learning_rate": 2e-05,
"loss": 0.6224,
"step": 6100
},
{
"epoch": 0.5173143679620693,
"grad_norm": 0.4130189120769501,
"learning_rate": 2e-05,
"loss": 0.6236,
"step": 6110
},
{
"epoch": 0.5181610363220727,
"grad_norm": 0.4239467978477478,
"learning_rate": 2e-05,
"loss": 0.6154,
"step": 6120
},
{
"epoch": 0.519007704682076,
"grad_norm": 0.4075891375541687,
"learning_rate": 2e-05,
"loss": 0.6238,
"step": 6130
},
{
"epoch": 0.5198543730420794,
"grad_norm": 0.7400830388069153,
"learning_rate": 2e-05,
"loss": 0.6218,
"step": 6140
},
{
"epoch": 0.5207010414020828,
"grad_norm": 0.3997366726398468,
"learning_rate": 2e-05,
"loss": 0.6205,
"step": 6150
},
{
"epoch": 0.5215477097620862,
"grad_norm": 0.40526220202445984,
"learning_rate": 2e-05,
"loss": 0.6206,
"step": 6160
},
{
"epoch": 0.5223943781220896,
"grad_norm": 0.3732961416244507,
"learning_rate": 2e-05,
"loss": 0.6306,
"step": 6170
},
{
"epoch": 0.523241046482093,
"grad_norm": 0.4446116089820862,
"learning_rate": 2e-05,
"loss": 0.6278,
"step": 6180
},
{
"epoch": 0.5240877148420964,
"grad_norm": 0.34746673703193665,
"learning_rate": 2e-05,
"loss": 0.6194,
"step": 6190
},
{
"epoch": 0.5249343832020997,
"grad_norm": 0.40655001997947693,
"learning_rate": 2e-05,
"loss": 0.6288,
"step": 6200
},
{
"epoch": 0.5257810515621031,
"grad_norm": 0.4144551753997803,
"learning_rate": 2e-05,
"loss": 0.6315,
"step": 6210
},
{
"epoch": 0.5266277199221066,
"grad_norm": 0.4305518567562103,
"learning_rate": 2e-05,
"loss": 0.6203,
"step": 6220
},
{
"epoch": 0.5274743882821099,
"grad_norm": 0.3971366286277771,
"learning_rate": 2e-05,
"loss": 0.6082,
"step": 6230
},
{
"epoch": 0.5283210566421133,
"grad_norm": 0.3746547996997833,
"learning_rate": 2e-05,
"loss": 0.6091,
"step": 6240
},
{
"epoch": 0.5291677250021166,
"grad_norm": 0.3898078501224518,
"learning_rate": 2e-05,
"loss": 0.6341,
"step": 6250
},
{
"epoch": 0.5300143933621201,
"grad_norm": 0.4017004072666168,
"learning_rate": 2e-05,
"loss": 0.6294,
"step": 6260
},
{
"epoch": 0.5308610617221234,
"grad_norm": 0.3839578926563263,
"learning_rate": 2e-05,
"loss": 0.6259,
"step": 6270
},
{
"epoch": 0.5317077300821268,
"grad_norm": 0.3924230635166168,
"learning_rate": 2e-05,
"loss": 0.6142,
"step": 6280
},
{
"epoch": 0.5325543984421303,
"grad_norm": 0.38458389043807983,
"learning_rate": 2e-05,
"loss": 0.6186,
"step": 6290
},
{
"epoch": 0.5334010668021336,
"grad_norm": 0.37602996826171875,
"learning_rate": 2e-05,
"loss": 0.6096,
"step": 6300
},
{
"epoch": 0.534247735162137,
"grad_norm": 0.37296441197395325,
"learning_rate": 2e-05,
"loss": 0.5899,
"step": 6310
},
{
"epoch": 0.5350944035221403,
"grad_norm": 0.39474377036094666,
"learning_rate": 2e-05,
"loss": 0.6237,
"step": 6320
},
{
"epoch": 0.5359410718821438,
"grad_norm": 0.4228913486003876,
"learning_rate": 2e-05,
"loss": 0.6202,
"step": 6330
},
{
"epoch": 0.5367877402421471,
"grad_norm": 0.4026711583137512,
"learning_rate": 2e-05,
"loss": 0.6107,
"step": 6340
},
{
"epoch": 0.5376344086021505,
"grad_norm": 0.3746722936630249,
"learning_rate": 2e-05,
"loss": 0.6406,
"step": 6350
},
{
"epoch": 0.538481076962154,
"grad_norm": 0.3888999819755554,
"learning_rate": 2e-05,
"loss": 0.6027,
"step": 6360
},
{
"epoch": 0.5393277453221573,
"grad_norm": 0.62255859375,
"learning_rate": 2e-05,
"loss": 0.6523,
"step": 6370
},
{
"epoch": 0.5401744136821607,
"grad_norm": 0.37910526990890503,
"learning_rate": 2e-05,
"loss": 0.6086,
"step": 6380
},
{
"epoch": 0.541021082042164,
"grad_norm": 0.41725194454193115,
"learning_rate": 2e-05,
"loss": 0.6056,
"step": 6390
},
{
"epoch": 0.5418677504021675,
"grad_norm": 0.4146798551082611,
"learning_rate": 2e-05,
"loss": 0.6145,
"step": 6400
},
{
"epoch": 0.5427144187621709,
"grad_norm": 0.391523152589798,
"learning_rate": 2e-05,
"loss": 0.6081,
"step": 6410
},
{
"epoch": 0.5435610871221742,
"grad_norm": 0.38605454564094543,
"learning_rate": 2e-05,
"loss": 0.6223,
"step": 6420
},
{
"epoch": 0.5444077554821777,
"grad_norm": 0.40026605129241943,
"learning_rate": 2e-05,
"loss": 0.6229,
"step": 6430
},
{
"epoch": 0.545254423842181,
"grad_norm": 0.39295217394828796,
"learning_rate": 2e-05,
"loss": 0.5966,
"step": 6440
},
{
"epoch": 0.5461010922021844,
"grad_norm": 0.3661985397338867,
"learning_rate": 2e-05,
"loss": 0.6241,
"step": 6450
},
{
"epoch": 0.5469477605621877,
"grad_norm": 0.3666883111000061,
"learning_rate": 2e-05,
"loss": 0.6037,
"step": 6460
},
{
"epoch": 0.5477944289221912,
"grad_norm": 0.425094336271286,
"learning_rate": 2e-05,
"loss": 0.6263,
"step": 6470
},
{
"epoch": 0.5486410972821946,
"grad_norm": 0.37346509099006653,
"learning_rate": 2e-05,
"loss": 0.6152,
"step": 6480
},
{
"epoch": 0.5494877656421979,
"grad_norm": 0.3733043670654297,
"learning_rate": 2e-05,
"loss": 0.648,
"step": 6490
},
{
"epoch": 0.5503344340022014,
"grad_norm": 0.3986981511116028,
"learning_rate": 2e-05,
"loss": 0.6094,
"step": 6500
},
{
"epoch": 0.5511811023622047,
"grad_norm": 0.4329341948032379,
"learning_rate": 2e-05,
"loss": 0.6293,
"step": 6510
},
{
"epoch": 0.5520277707222081,
"grad_norm": 0.5777575969696045,
"learning_rate": 2e-05,
"loss": 0.6099,
"step": 6520
},
{
"epoch": 0.5528744390822115,
"grad_norm": 0.38503754138946533,
"learning_rate": 2e-05,
"loss": 0.6017,
"step": 6530
},
{
"epoch": 0.5537211074422149,
"grad_norm": 0.3939046263694763,
"learning_rate": 2e-05,
"loss": 0.6176,
"step": 6540
},
{
"epoch": 0.5545677758022183,
"grad_norm": 0.41852498054504395,
"learning_rate": 2e-05,
"loss": 0.6178,
"step": 6550
},
{
"epoch": 0.5554144441622216,
"grad_norm": 0.4328558146953583,
"learning_rate": 2e-05,
"loss": 0.6277,
"step": 6560
},
{
"epoch": 0.5562611125222251,
"grad_norm": 0.37034040689468384,
"learning_rate": 2e-05,
"loss": 0.6274,
"step": 6570
},
{
"epoch": 0.5571077808822285,
"grad_norm": 0.38166680932044983,
"learning_rate": 2e-05,
"loss": 0.5946,
"step": 6580
},
{
"epoch": 0.5579544492422318,
"grad_norm": 0.41881346702575684,
"learning_rate": 2e-05,
"loss": 0.6257,
"step": 6590
},
{
"epoch": 0.5588011176022352,
"grad_norm": 0.37791213393211365,
"learning_rate": 2e-05,
"loss": 0.6138,
"step": 6600
},
{
"epoch": 0.5596477859622386,
"grad_norm": 0.36887291073799133,
"learning_rate": 2e-05,
"loss": 0.5967,
"step": 6610
},
{
"epoch": 0.560494454322242,
"grad_norm": 0.4268091917037964,
"learning_rate": 2e-05,
"loss": 0.6058,
"step": 6620
},
{
"epoch": 0.5613411226822453,
"grad_norm": 0.38210442662239075,
"learning_rate": 2e-05,
"loss": 0.6235,
"step": 6630
},
{
"epoch": 0.5621877910422487,
"grad_norm": 0.37808048725128174,
"learning_rate": 2e-05,
"loss": 0.611,
"step": 6640
},
{
"epoch": 0.5630344594022522,
"grad_norm": 0.3863983750343323,
"learning_rate": 2e-05,
"loss": 0.6146,
"step": 6650
},
{
"epoch": 0.5638811277622555,
"grad_norm": 0.36661502718925476,
"learning_rate": 2e-05,
"loss": 0.6295,
"step": 6660
},
{
"epoch": 0.5647277961222589,
"grad_norm": 0.39419591426849365,
"learning_rate": 2e-05,
"loss": 0.6026,
"step": 6670
},
{
"epoch": 0.5655744644822623,
"grad_norm": 0.3879638910293579,
"learning_rate": 2e-05,
"loss": 0.6256,
"step": 6680
},
{
"epoch": 0.5664211328422657,
"grad_norm": 0.4414083957672119,
"learning_rate": 2e-05,
"loss": 0.6216,
"step": 6690
},
{
"epoch": 0.567267801202269,
"grad_norm": 0.5547428131103516,
"learning_rate": 2e-05,
"loss": 0.5961,
"step": 6700
},
{
"epoch": 0.5681144695622724,
"grad_norm": 0.41286641359329224,
"learning_rate": 2e-05,
"loss": 0.612,
"step": 6710
},
{
"epoch": 0.5689611379222759,
"grad_norm": 0.39331957697868347,
"learning_rate": 2e-05,
"loss": 0.6135,
"step": 6720
},
{
"epoch": 0.5698078062822792,
"grad_norm": 0.37319085001945496,
"learning_rate": 2e-05,
"loss": 0.6146,
"step": 6730
},
{
"epoch": 0.5706544746422826,
"grad_norm": 0.3842022716999054,
"learning_rate": 2e-05,
"loss": 0.5906,
"step": 6740
},
{
"epoch": 0.571501143002286,
"grad_norm": 0.40025755763053894,
"learning_rate": 2e-05,
"loss": 0.6196,
"step": 6750
},
{
"epoch": 0.5723478113622894,
"grad_norm": 0.3739895522594452,
"learning_rate": 2e-05,
"loss": 0.6186,
"step": 6760
},
{
"epoch": 0.5731944797222928,
"grad_norm": 0.3994680643081665,
"learning_rate": 2e-05,
"loss": 0.6266,
"step": 6770
},
{
"epoch": 0.5740411480822961,
"grad_norm": 0.4288325011730194,
"learning_rate": 2e-05,
"loss": 0.6109,
"step": 6780
},
{
"epoch": 0.5748878164422996,
"grad_norm": 0.3739669620990753,
"learning_rate": 2e-05,
"loss": 0.6103,
"step": 6790
},
{
"epoch": 0.5757344848023029,
"grad_norm": 0.4007492661476135,
"learning_rate": 2e-05,
"loss": 0.598,
"step": 6800
},
{
"epoch": 0.5765811531623063,
"grad_norm": 0.44269534945487976,
"learning_rate": 2e-05,
"loss": 0.6317,
"step": 6810
},
{
"epoch": 0.5774278215223098,
"grad_norm": 0.3765222132205963,
"learning_rate": 2e-05,
"loss": 0.6046,
"step": 6820
},
{
"epoch": 0.5782744898823131,
"grad_norm": 0.4016408920288086,
"learning_rate": 2e-05,
"loss": 0.6196,
"step": 6830
},
{
"epoch": 0.5791211582423165,
"grad_norm": 0.4090782701969147,
"learning_rate": 2e-05,
"loss": 0.6149,
"step": 6840
},
{
"epoch": 0.5799678266023198,
"grad_norm": 1.7843128442764282,
"learning_rate": 2e-05,
"loss": 0.6016,
"step": 6850
},
{
"epoch": 0.5808144949623233,
"grad_norm": 0.38544028997421265,
"learning_rate": 2e-05,
"loss": 0.6305,
"step": 6860
},
{
"epoch": 0.5816611633223266,
"grad_norm": 0.38839665055274963,
"learning_rate": 2e-05,
"loss": 0.6188,
"step": 6870
},
{
"epoch": 0.58250783168233,
"grad_norm": 0.45434343814849854,
"learning_rate": 2e-05,
"loss": 0.6012,
"step": 6880
},
{
"epoch": 0.5833545000423335,
"grad_norm": 0.3811943531036377,
"learning_rate": 2e-05,
"loss": 0.6088,
"step": 6890
},
{
"epoch": 0.5842011684023368,
"grad_norm": 0.39027082920074463,
"learning_rate": 2e-05,
"loss": 0.6158,
"step": 6900
},
{
"epoch": 0.5850478367623402,
"grad_norm": 0.5465657114982605,
"learning_rate": 2e-05,
"loss": 0.6025,
"step": 6910
},
{
"epoch": 0.5858945051223435,
"grad_norm": 0.3801416754722595,
"learning_rate": 2e-05,
"loss": 0.6092,
"step": 6920
},
{
"epoch": 0.586741173482347,
"grad_norm": 0.4927064776420593,
"learning_rate": 2e-05,
"loss": 0.6192,
"step": 6930
},
{
"epoch": 0.5875878418423504,
"grad_norm": 0.35067012906074524,
"learning_rate": 2e-05,
"loss": 0.6187,
"step": 6940
},
{
"epoch": 0.5884345102023537,
"grad_norm": 0.4920819103717804,
"learning_rate": 2e-05,
"loss": 0.6376,
"step": 6950
},
{
"epoch": 0.5892811785623572,
"grad_norm": 0.3970767557621002,
"learning_rate": 2e-05,
"loss": 0.6387,
"step": 6960
},
{
"epoch": 0.5901278469223605,
"grad_norm": 0.36884695291519165,
"learning_rate": 2e-05,
"loss": 0.6085,
"step": 6970
},
{
"epoch": 0.5909745152823639,
"grad_norm": 0.38520318269729614,
"learning_rate": 2e-05,
"loss": 0.6252,
"step": 6980
},
{
"epoch": 0.5918211836423672,
"grad_norm": 0.40267571806907654,
"learning_rate": 2e-05,
"loss": 0.6209,
"step": 6990
},
{
"epoch": 0.5926678520023707,
"grad_norm": 0.35616549849510193,
"learning_rate": 2e-05,
"loss": 0.6157,
"step": 7000
},
{
"epoch": 0.5935145203623741,
"grad_norm": 0.4070214033126831,
"learning_rate": 2e-05,
"loss": 0.6158,
"step": 7010
},
{
"epoch": 0.5943611887223774,
"grad_norm": 0.41295188665390015,
"learning_rate": 2e-05,
"loss": 0.6375,
"step": 7020
},
{
"epoch": 0.5952078570823809,
"grad_norm": 0.3873959481716156,
"learning_rate": 2e-05,
"loss": 0.6116,
"step": 7030
},
{
"epoch": 0.5960545254423842,
"grad_norm": 0.3730942904949188,
"learning_rate": 2e-05,
"loss": 0.5992,
"step": 7040
},
{
"epoch": 0.5969011938023876,
"grad_norm": 0.39402008056640625,
"learning_rate": 2e-05,
"loss": 0.6135,
"step": 7050
},
{
"epoch": 0.597747862162391,
"grad_norm": 0.37656551599502563,
"learning_rate": 2e-05,
"loss": 0.5911,
"step": 7060
},
{
"epoch": 0.5985945305223944,
"grad_norm": 0.3850175738334656,
"learning_rate": 2e-05,
"loss": 0.5905,
"step": 7070
},
{
"epoch": 0.5994411988823978,
"grad_norm": 0.38224855065345764,
"learning_rate": 2e-05,
"loss": 0.612,
"step": 7080
},
{
"epoch": 0.6002878672424011,
"grad_norm": 0.40613213181495667,
"learning_rate": 2e-05,
"loss": 0.6326,
"step": 7090
},
{
"epoch": 0.6011345356024045,
"grad_norm": 0.39177948236465454,
"learning_rate": 2e-05,
"loss": 0.6066,
"step": 7100
},
{
"epoch": 0.601981203962408,
"grad_norm": 0.37043365836143494,
"learning_rate": 2e-05,
"loss": 0.6103,
"step": 7110
},
{
"epoch": 0.6028278723224113,
"grad_norm": 0.40762731432914734,
"learning_rate": 2e-05,
"loss": 0.6019,
"step": 7120
},
{
"epoch": 0.6036745406824147,
"grad_norm": 0.42319485545158386,
"learning_rate": 2e-05,
"loss": 0.6338,
"step": 7130
},
{
"epoch": 0.6045212090424181,
"grad_norm": 0.4047078788280487,
"learning_rate": 2e-05,
"loss": 0.6238,
"step": 7140
},
{
"epoch": 0.6053678774024215,
"grad_norm": 0.38978368043899536,
"learning_rate": 2e-05,
"loss": 0.6067,
"step": 7150
},
{
"epoch": 0.6062145457624248,
"grad_norm": 0.37449151277542114,
"learning_rate": 2e-05,
"loss": 0.6125,
"step": 7160
},
{
"epoch": 0.6070612141224282,
"grad_norm": 0.3653220236301422,
"learning_rate": 2e-05,
"loss": 0.6096,
"step": 7170
},
{
"epoch": 0.6079078824824317,
"grad_norm": 0.37788718938827515,
"learning_rate": 2e-05,
"loss": 0.6316,
"step": 7180
},
{
"epoch": 0.608754550842435,
"grad_norm": 0.49567627906799316,
"learning_rate": 2e-05,
"loss": 0.6044,
"step": 7190
},
{
"epoch": 0.6096012192024384,
"grad_norm": 0.3770660161972046,
"learning_rate": 2e-05,
"loss": 0.5993,
"step": 7200
},
{
"epoch": 0.6104478875624418,
"grad_norm": 0.390761137008667,
"learning_rate": 2e-05,
"loss": 0.5933,
"step": 7210
},
{
"epoch": 0.6112945559224452,
"grad_norm": 0.4019384980201721,
"learning_rate": 2e-05,
"loss": 0.6136,
"step": 7220
},
{
"epoch": 0.6121412242824485,
"grad_norm": 0.37608879804611206,
"learning_rate": 2e-05,
"loss": 0.6196,
"step": 7230
},
{
"epoch": 0.6129878926424519,
"grad_norm": 0.3891141414642334,
"learning_rate": 2e-05,
"loss": 0.6292,
"step": 7240
},
{
"epoch": 0.6138345610024554,
"grad_norm": 0.39163273572921753,
"learning_rate": 2e-05,
"loss": 0.638,
"step": 7250
},
{
"epoch": 0.6146812293624587,
"grad_norm": 0.4056644141674042,
"learning_rate": 2e-05,
"loss": 0.6398,
"step": 7260
},
{
"epoch": 0.6155278977224621,
"grad_norm": 0.44692912697792053,
"learning_rate": 2e-05,
"loss": 0.6121,
"step": 7270
},
{
"epoch": 0.6163745660824655,
"grad_norm": 0.49708330631256104,
"learning_rate": 2e-05,
"loss": 0.6258,
"step": 7280
},
{
"epoch": 0.6172212344424689,
"grad_norm": 0.4142015874385834,
"learning_rate": 2e-05,
"loss": 0.6102,
"step": 7290
},
{
"epoch": 0.6180679028024723,
"grad_norm": 0.3750077784061432,
"learning_rate": 2e-05,
"loss": 0.6009,
"step": 7300
},
{
"epoch": 0.6189145711624756,
"grad_norm": 0.4088134169578552,
"learning_rate": 2e-05,
"loss": 0.6212,
"step": 7310
},
{
"epoch": 0.6197612395224791,
"grad_norm": 0.4203443229198456,
"learning_rate": 2e-05,
"loss": 0.6213,
"step": 7320
},
{
"epoch": 0.6206079078824824,
"grad_norm": 0.40304455161094666,
"learning_rate": 2e-05,
"loss": 0.6051,
"step": 7330
},
{
"epoch": 0.6214545762424858,
"grad_norm": 0.41094863414764404,
"learning_rate": 2e-05,
"loss": 0.6184,
"step": 7340
},
{
"epoch": 0.6223012446024893,
"grad_norm": 0.38134077191352844,
"learning_rate": 2e-05,
"loss": 0.624,
"step": 7350
},
{
"epoch": 0.6231479129624926,
"grad_norm": 0.3820878267288208,
"learning_rate": 2e-05,
"loss": 0.6122,
"step": 7360
},
{
"epoch": 0.623994581322496,
"grad_norm": 0.40551233291625977,
"learning_rate": 2e-05,
"loss": 0.6109,
"step": 7370
},
{
"epoch": 0.6248412496824993,
"grad_norm": 0.3741089105606079,
"learning_rate": 2e-05,
"loss": 0.6098,
"step": 7380
},
{
"epoch": 0.6256879180425028,
"grad_norm": 0.43164291977882385,
"learning_rate": 2e-05,
"loss": 0.6074,
"step": 7390
},
{
"epoch": 0.6265345864025061,
"grad_norm": 0.42368006706237793,
"learning_rate": 2e-05,
"loss": 0.6138,
"step": 7400
},
{
"epoch": 0.6273812547625095,
"grad_norm": 0.3880939483642578,
"learning_rate": 2e-05,
"loss": 0.6311,
"step": 7410
},
{
"epoch": 0.628227923122513,
"grad_norm": 0.38041621446609497,
"learning_rate": 2e-05,
"loss": 0.5956,
"step": 7420
},
{
"epoch": 0.6290745914825163,
"grad_norm": 0.39767777919769287,
"learning_rate": 2e-05,
"loss": 0.6117,
"step": 7430
},
{
"epoch": 0.6299212598425197,
"grad_norm": 0.36305296421051025,
"learning_rate": 2e-05,
"loss": 0.6138,
"step": 7440
},
{
"epoch": 0.630767928202523,
"grad_norm": 0.42218583822250366,
"learning_rate": 2e-05,
"loss": 0.6092,
"step": 7450
},
{
"epoch": 0.6316145965625265,
"grad_norm": 0.3930489420890808,
"learning_rate": 2e-05,
"loss": 0.6146,
"step": 7460
},
{
"epoch": 0.6324612649225299,
"grad_norm": 0.37960752844810486,
"learning_rate": 2e-05,
"loss": 0.6124,
"step": 7470
},
{
"epoch": 0.6333079332825332,
"grad_norm": 0.36294469237327576,
"learning_rate": 2e-05,
"loss": 0.629,
"step": 7480
},
{
"epoch": 0.6341546016425366,
"grad_norm": 0.37860652804374695,
"learning_rate": 2e-05,
"loss": 0.6014,
"step": 7490
},
{
"epoch": 0.63500127000254,
"grad_norm": 0.3833153545856476,
"learning_rate": 2e-05,
"loss": 0.6047,
"step": 7500
},
{
"epoch": 0.6358479383625434,
"grad_norm": 0.3943714201450348,
"learning_rate": 2e-05,
"loss": 0.5853,
"step": 7510
},
{
"epoch": 0.6366946067225467,
"grad_norm": 0.4110625982284546,
"learning_rate": 2e-05,
"loss": 0.605,
"step": 7520
},
{
"epoch": 0.6375412750825502,
"grad_norm": 0.3853622376918793,
"learning_rate": 2e-05,
"loss": 0.6248,
"step": 7530
},
{
"epoch": 0.6383879434425536,
"grad_norm": 0.405790239572525,
"learning_rate": 2e-05,
"loss": 0.5908,
"step": 7540
},
{
"epoch": 0.6392346118025569,
"grad_norm": 0.38166117668151855,
"learning_rate": 2e-05,
"loss": 0.617,
"step": 7550
},
{
"epoch": 0.6400812801625603,
"grad_norm": 0.3837755024433136,
"learning_rate": 2e-05,
"loss": 0.5994,
"step": 7560
},
{
"epoch": 0.6409279485225637,
"grad_norm": 0.3500962555408478,
"learning_rate": 2e-05,
"loss": 0.599,
"step": 7570
},
{
"epoch": 0.6417746168825671,
"grad_norm": 0.3725585639476776,
"learning_rate": 2e-05,
"loss": 0.6124,
"step": 7580
},
{
"epoch": 0.6426212852425705,
"grad_norm": 0.394646555185318,
"learning_rate": 2e-05,
"loss": 0.6182,
"step": 7590
},
{
"epoch": 0.6434679536025739,
"grad_norm": 0.38706496357917786,
"learning_rate": 2e-05,
"loss": 0.6212,
"step": 7600
},
{
"epoch": 0.6443146219625773,
"grad_norm": 0.39222168922424316,
"learning_rate": 2e-05,
"loss": 0.6071,
"step": 7610
},
{
"epoch": 0.6451612903225806,
"grad_norm": 0.4095226228237152,
"learning_rate": 2e-05,
"loss": 0.621,
"step": 7620
},
{
"epoch": 0.646007958682584,
"grad_norm": 0.39292946457862854,
"learning_rate": 2e-05,
"loss": 0.6254,
"step": 7630
},
{
"epoch": 0.6468546270425874,
"grad_norm": 0.3694469928741455,
"learning_rate": 2e-05,
"loss": 0.6022,
"step": 7640
},
{
"epoch": 0.6477012954025908,
"grad_norm": 0.4038865864276886,
"learning_rate": 2e-05,
"loss": 0.603,
"step": 7650
},
{
"epoch": 0.6485479637625942,
"grad_norm": 0.3848786950111389,
"learning_rate": 2e-05,
"loss": 0.613,
"step": 7660
},
{
"epoch": 0.6493946321225976,
"grad_norm": 0.3714199364185333,
"learning_rate": 2e-05,
"loss": 0.6175,
"step": 7670
},
{
"epoch": 0.650241300482601,
"grad_norm": 0.38996753096580505,
"learning_rate": 2e-05,
"loss": 0.6242,
"step": 7680
},
{
"epoch": 0.6510879688426043,
"grad_norm": 0.404257208108902,
"learning_rate": 2e-05,
"loss": 0.6018,
"step": 7690
},
{
"epoch": 0.6519346372026077,
"grad_norm": 0.435696005821228,
"learning_rate": 2e-05,
"loss": 0.6163,
"step": 7700
},
{
"epoch": 0.6527813055626112,
"grad_norm": 0.38047581911087036,
"learning_rate": 2e-05,
"loss": 0.6165,
"step": 7710
},
{
"epoch": 0.6536279739226145,
"grad_norm": 0.38386592268943787,
"learning_rate": 2e-05,
"loss": 0.6165,
"step": 7720
},
{
"epoch": 0.6544746422826179,
"grad_norm": 0.3776492178440094,
"learning_rate": 2e-05,
"loss": 0.607,
"step": 7730
},
{
"epoch": 0.6553213106426213,
"grad_norm": 0.4103914499282837,
"learning_rate": 2e-05,
"loss": 0.6187,
"step": 7740
},
{
"epoch": 0.6561679790026247,
"grad_norm": 0.3560851812362671,
"learning_rate": 2e-05,
"loss": 0.598,
"step": 7750
},
{
"epoch": 0.657014647362628,
"grad_norm": 0.40717586874961853,
"learning_rate": 2e-05,
"loss": 0.6047,
"step": 7760
},
{
"epoch": 0.6578613157226314,
"grad_norm": 0.41484007239341736,
"learning_rate": 2e-05,
"loss": 0.631,
"step": 7770
},
{
"epoch": 0.6587079840826349,
"grad_norm": 0.3616902232170105,
"learning_rate": 2e-05,
"loss": 0.6027,
"step": 7780
},
{
"epoch": 0.6595546524426382,
"grad_norm": 0.37407729029655457,
"learning_rate": 2e-05,
"loss": 0.6039,
"step": 7790
},
{
"epoch": 0.6604013208026416,
"grad_norm": 0.3733294606208801,
"learning_rate": 2e-05,
"loss": 0.599,
"step": 7800
},
{
"epoch": 0.661247989162645,
"grad_norm": 0.40664204955101013,
"learning_rate": 2e-05,
"loss": 0.6102,
"step": 7810
},
{
"epoch": 0.6620946575226484,
"grad_norm": 0.3817388117313385,
"learning_rate": 2e-05,
"loss": 0.6246,
"step": 7820
},
{
"epoch": 0.6629413258826518,
"grad_norm": 0.3724527955055237,
"learning_rate": 2e-05,
"loss": 0.6147,
"step": 7830
},
{
"epoch": 0.6637879942426551,
"grad_norm": 0.3936074674129486,
"learning_rate": 2e-05,
"loss": 0.6367,
"step": 7840
},
{
"epoch": 0.6646346626026586,
"grad_norm": 0.35780492424964905,
"learning_rate": 2e-05,
"loss": 0.606,
"step": 7850
},
{
"epoch": 0.6654813309626619,
"grad_norm": 0.3824580907821655,
"learning_rate": 2e-05,
"loss": 0.6008,
"step": 7860
},
{
"epoch": 0.6663279993226653,
"grad_norm": 0.34928175806999207,
"learning_rate": 2e-05,
"loss": 0.6129,
"step": 7870
},
{
"epoch": 0.6671746676826688,
"grad_norm": 0.39645010232925415,
"learning_rate": 2e-05,
"loss": 0.6021,
"step": 7880
},
{
"epoch": 0.6680213360426721,
"grad_norm": 0.38476237654685974,
"learning_rate": 2e-05,
"loss": 0.6187,
"step": 7890
},
{
"epoch": 0.6688680044026755,
"grad_norm": 0.38974231481552124,
"learning_rate": 2e-05,
"loss": 0.6216,
"step": 7900
},
{
"epoch": 0.6697146727626788,
"grad_norm": 0.406893253326416,
"learning_rate": 2e-05,
"loss": 0.5928,
"step": 7910
},
{
"epoch": 0.6705613411226823,
"grad_norm": 0.4263247847557068,
"learning_rate": 2e-05,
"loss": 0.6133,
"step": 7920
},
{
"epoch": 0.6714080094826856,
"grad_norm": 0.48513466119766235,
"learning_rate": 2e-05,
"loss": 0.6272,
"step": 7930
},
{
"epoch": 0.672254677842689,
"grad_norm": 0.3819485008716583,
"learning_rate": 2e-05,
"loss": 0.6121,
"step": 7940
},
{
"epoch": 0.6731013462026924,
"grad_norm": 0.4394488036632538,
"learning_rate": 2e-05,
"loss": 0.606,
"step": 7950
},
{
"epoch": 0.6739480145626958,
"grad_norm": 0.39058947563171387,
"learning_rate": 2e-05,
"loss": 0.599,
"step": 7960
},
{
"epoch": 0.6747946829226992,
"grad_norm": 0.37886151671409607,
"learning_rate": 2e-05,
"loss": 0.6181,
"step": 7970
},
{
"epoch": 0.6756413512827025,
"grad_norm": 0.3999195694923401,
"learning_rate": 2e-05,
"loss": 0.5946,
"step": 7980
},
{
"epoch": 0.676488019642706,
"grad_norm": 0.41106507182121277,
"learning_rate": 2e-05,
"loss": 0.6113,
"step": 7990
},
{
"epoch": 0.6773346880027094,
"grad_norm": 0.40601998567581177,
"learning_rate": 2e-05,
"loss": 0.5951,
"step": 8000
},
{
"epoch": 0.6781813563627127,
"grad_norm": 0.39435434341430664,
"learning_rate": 2e-05,
"loss": 0.5888,
"step": 8010
},
{
"epoch": 0.6790280247227161,
"grad_norm": 0.39406082034111023,
"learning_rate": 2e-05,
"loss": 0.6145,
"step": 8020
},
{
"epoch": 0.6798746930827195,
"grad_norm": 0.38617005944252014,
"learning_rate": 2e-05,
"loss": 0.6351,
"step": 8030
},
{
"epoch": 0.6807213614427229,
"grad_norm": 0.374894380569458,
"learning_rate": 2e-05,
"loss": 0.6175,
"step": 8040
},
{
"epoch": 0.6815680298027262,
"grad_norm": 0.4400508403778076,
"learning_rate": 2e-05,
"loss": 0.5995,
"step": 8050
},
{
"epoch": 0.6824146981627297,
"grad_norm": 0.37848958373069763,
"learning_rate": 2e-05,
"loss": 0.6161,
"step": 8060
},
{
"epoch": 0.6832613665227331,
"grad_norm": 0.36910420656204224,
"learning_rate": 2e-05,
"loss": 0.6063,
"step": 8070
},
{
"epoch": 0.6841080348827364,
"grad_norm": 0.3791019022464752,
"learning_rate": 2e-05,
"loss": 0.6017,
"step": 8080
},
{
"epoch": 0.6849547032427398,
"grad_norm": 0.4173106551170349,
"learning_rate": 2e-05,
"loss": 0.6142,
"step": 8090
},
{
"epoch": 0.6858013716027432,
"grad_norm": 0.4436609447002411,
"learning_rate": 2e-05,
"loss": 0.6037,
"step": 8100
},
{
"epoch": 0.6866480399627466,
"grad_norm": 0.3702719211578369,
"learning_rate": 2e-05,
"loss": 0.635,
"step": 8110
},
{
"epoch": 0.68749470832275,
"grad_norm": 0.37786832451820374,
"learning_rate": 2e-05,
"loss": 0.6114,
"step": 8120
},
{
"epoch": 0.6883413766827534,
"grad_norm": 0.37227243185043335,
"learning_rate": 2e-05,
"loss": 0.627,
"step": 8130
},
{
"epoch": 0.6891880450427568,
"grad_norm": 0.4393289089202881,
"learning_rate": 2e-05,
"loss": 0.6054,
"step": 8140
},
{
"epoch": 0.6900347134027601,
"grad_norm": 0.3587683439254761,
"learning_rate": 2e-05,
"loss": 0.5979,
"step": 8150
},
{
"epoch": 0.6908813817627635,
"grad_norm": 0.42889073491096497,
"learning_rate": 2e-05,
"loss": 0.5956,
"step": 8160
},
{
"epoch": 0.691728050122767,
"grad_norm": 0.38590002059936523,
"learning_rate": 2e-05,
"loss": 0.6106,
"step": 8170
},
{
"epoch": 0.6925747184827703,
"grad_norm": 0.3669581115245819,
"learning_rate": 2e-05,
"loss": 0.6176,
"step": 8180
},
{
"epoch": 0.6934213868427737,
"grad_norm": 0.38695085048675537,
"learning_rate": 2e-05,
"loss": 0.6083,
"step": 8190
},
{
"epoch": 0.6942680552027771,
"grad_norm": 0.35388970375061035,
"learning_rate": 2e-05,
"loss": 0.6141,
"step": 8200
},
{
"epoch": 0.6951147235627805,
"grad_norm": 0.3946210443973541,
"learning_rate": 2e-05,
"loss": 0.6048,
"step": 8210
},
{
"epoch": 0.6959613919227838,
"grad_norm": 0.40805330872535706,
"learning_rate": 2e-05,
"loss": 0.615,
"step": 8220
},
{
"epoch": 0.6968080602827872,
"grad_norm": 0.3799391984939575,
"learning_rate": 2e-05,
"loss": 0.6061,
"step": 8230
},
{
"epoch": 0.6976547286427907,
"grad_norm": 0.4017302691936493,
"learning_rate": 2e-05,
"loss": 0.5979,
"step": 8240
},
{
"epoch": 0.698501397002794,
"grad_norm": 0.4113961458206177,
"learning_rate": 2e-05,
"loss": 0.5969,
"step": 8250
},
{
"epoch": 0.6993480653627974,
"grad_norm": 0.35288354754447937,
"learning_rate": 2e-05,
"loss": 0.6026,
"step": 8260
},
{
"epoch": 0.7001947337228008,
"grad_norm": 0.3655013144016266,
"learning_rate": 2e-05,
"loss": 0.6173,
"step": 8270
},
{
"epoch": 0.7010414020828042,
"grad_norm": 0.3742232620716095,
"learning_rate": 2e-05,
"loss": 0.6052,
"step": 8280
},
{
"epoch": 0.7018880704428075,
"grad_norm": 0.4151310324668884,
"learning_rate": 2e-05,
"loss": 0.5931,
"step": 8290
},
{
"epoch": 0.7027347388028109,
"grad_norm": 0.3754572570323944,
"learning_rate": 2e-05,
"loss": 0.6233,
"step": 8300
},
{
"epoch": 0.7035814071628144,
"grad_norm": 0.42071816325187683,
"learning_rate": 2e-05,
"loss": 0.6032,
"step": 8310
},
{
"epoch": 0.7044280755228177,
"grad_norm": 0.3675685226917267,
"learning_rate": 2e-05,
"loss": 0.6152,
"step": 8320
},
{
"epoch": 0.7052747438828211,
"grad_norm": 0.3739764988422394,
"learning_rate": 2e-05,
"loss": 0.6172,
"step": 8330
},
{
"epoch": 0.7061214122428244,
"grad_norm": 0.38897982239723206,
"learning_rate": 2e-05,
"loss": 0.6225,
"step": 8340
},
{
"epoch": 0.7069680806028279,
"grad_norm": 0.38103702664375305,
"learning_rate": 2e-05,
"loss": 0.6223,
"step": 8350
},
{
"epoch": 0.7078147489628313,
"grad_norm": 0.38617536425590515,
"learning_rate": 2e-05,
"loss": 0.6066,
"step": 8360
},
{
"epoch": 0.7086614173228346,
"grad_norm": 0.409368634223938,
"learning_rate": 2e-05,
"loss": 0.6308,
"step": 8370
},
{
"epoch": 0.7095080856828381,
"grad_norm": 0.36376938223838806,
"learning_rate": 2e-05,
"loss": 0.6207,
"step": 8380
},
{
"epoch": 0.7103547540428414,
"grad_norm": 0.3787282705307007,
"learning_rate": 2e-05,
"loss": 0.6237,
"step": 8390
},
{
"epoch": 0.7112014224028448,
"grad_norm": 0.38591137528419495,
"learning_rate": 2e-05,
"loss": 0.5924,
"step": 8400
},
{
"epoch": 0.7120480907628481,
"grad_norm": 0.365154892206192,
"learning_rate": 2e-05,
"loss": 0.6036,
"step": 8410
},
{
"epoch": 0.7128947591228516,
"grad_norm": 0.4766608476638794,
"learning_rate": 2e-05,
"loss": 0.6246,
"step": 8420
},
{
"epoch": 0.713741427482855,
"grad_norm": 0.4156077802181244,
"learning_rate": 2e-05,
"loss": 0.6055,
"step": 8430
},
{
"epoch": 0.7145880958428583,
"grad_norm": 0.44563063979148865,
"learning_rate": 2e-05,
"loss": 0.6203,
"step": 8440
},
{
"epoch": 0.7154347642028618,
"grad_norm": 0.3794260621070862,
"learning_rate": 2e-05,
"loss": 0.5925,
"step": 8450
},
{
"epoch": 0.7162814325628651,
"grad_norm": 0.3877285122871399,
"learning_rate": 2e-05,
"loss": 0.6047,
"step": 8460
},
{
"epoch": 0.7171281009228685,
"grad_norm": 0.4059469699859619,
"learning_rate": 2e-05,
"loss": 0.6208,
"step": 8470
},
{
"epoch": 0.7179747692828718,
"grad_norm": 0.37956446409225464,
"learning_rate": 2e-05,
"loss": 0.5919,
"step": 8480
},
{
"epoch": 0.7188214376428753,
"grad_norm": 0.39450889825820923,
"learning_rate": 2e-05,
"loss": 0.6062,
"step": 8490
},
{
"epoch": 0.7196681060028787,
"grad_norm": 0.45799970626831055,
"learning_rate": 2e-05,
"loss": 0.6019,
"step": 8500
},
{
"epoch": 0.720514774362882,
"grad_norm": 0.394918292760849,
"learning_rate": 2e-05,
"loss": 0.6113,
"step": 8510
},
{
"epoch": 0.7213614427228855,
"grad_norm": 0.3932916224002838,
"learning_rate": 2e-05,
"loss": 0.6023,
"step": 8520
},
{
"epoch": 0.7222081110828888,
"grad_norm": 0.40540504455566406,
"learning_rate": 2e-05,
"loss": 0.6033,
"step": 8530
},
{
"epoch": 0.7230547794428922,
"grad_norm": 0.39818504452705383,
"learning_rate": 2e-05,
"loss": 0.5997,
"step": 8540
},
{
"epoch": 0.7239014478028956,
"grad_norm": 0.4087052047252655,
"learning_rate": 2e-05,
"loss": 0.634,
"step": 8550
},
{
"epoch": 0.724748116162899,
"grad_norm": 0.38303884863853455,
"learning_rate": 2e-05,
"loss": 0.5961,
"step": 8560
},
{
"epoch": 0.7255947845229024,
"grad_norm": 0.4175228476524353,
"learning_rate": 2e-05,
"loss": 0.6081,
"step": 8570
},
{
"epoch": 0.7264414528829057,
"grad_norm": 0.41134655475616455,
"learning_rate": 2e-05,
"loss": 0.5937,
"step": 8580
},
{
"epoch": 0.7272881212429092,
"grad_norm": 0.39889252185821533,
"learning_rate": 2e-05,
"loss": 0.6225,
"step": 8590
},
{
"epoch": 0.7281347896029126,
"grad_norm": 0.3769337236881256,
"learning_rate": 2e-05,
"loss": 0.5984,
"step": 8600
},
{
"epoch": 0.7289814579629159,
"grad_norm": 0.39363840222358704,
"learning_rate": 2e-05,
"loss": 0.5996,
"step": 8610
},
{
"epoch": 0.7298281263229193,
"grad_norm": 0.3953545093536377,
"learning_rate": 2e-05,
"loss": 0.6335,
"step": 8620
},
{
"epoch": 0.7306747946829227,
"grad_norm": 0.4219764173030853,
"learning_rate": 2e-05,
"loss": 0.6325,
"step": 8630
},
{
"epoch": 0.7315214630429261,
"grad_norm": 0.4934154450893402,
"learning_rate": 2e-05,
"loss": 0.6003,
"step": 8640
},
{
"epoch": 0.7323681314029294,
"grad_norm": 0.3680473864078522,
"learning_rate": 2e-05,
"loss": 0.6428,
"step": 8650
},
{
"epoch": 0.7332147997629329,
"grad_norm": 0.37619748711586,
"learning_rate": 2e-05,
"loss": 0.6137,
"step": 8660
},
{
"epoch": 0.7340614681229363,
"grad_norm": 0.4080664813518524,
"learning_rate": 2e-05,
"loss": 0.6246,
"step": 8670
},
{
"epoch": 0.7349081364829396,
"grad_norm": 0.40325847268104553,
"learning_rate": 2e-05,
"loss": 0.5921,
"step": 8680
},
{
"epoch": 0.735754804842943,
"grad_norm": 0.42735210061073303,
"learning_rate": 2e-05,
"loss": 0.6306,
"step": 8690
},
{
"epoch": 0.7366014732029464,
"grad_norm": 0.38058769702911377,
"learning_rate": 2e-05,
"loss": 0.6135,
"step": 8700
},
{
"epoch": 0.7374481415629498,
"grad_norm": 0.37063926458358765,
"learning_rate": 2e-05,
"loss": 0.5956,
"step": 8710
},
{
"epoch": 0.7382948099229532,
"grad_norm": 0.37500154972076416,
"learning_rate": 2e-05,
"loss": 0.5907,
"step": 8720
},
{
"epoch": 0.7391414782829566,
"grad_norm": 0.39320120215415955,
"learning_rate": 2e-05,
"loss": 0.61,
"step": 8730
},
{
"epoch": 0.73998814664296,
"grad_norm": 0.39450380206108093,
"learning_rate": 2e-05,
"loss": 0.5892,
"step": 8740
},
{
"epoch": 0.7408348150029633,
"grad_norm": 0.3705025315284729,
"learning_rate": 2e-05,
"loss": 0.595,
"step": 8750
},
{
"epoch": 0.7416814833629667,
"grad_norm": 0.4006616473197937,
"learning_rate": 2e-05,
"loss": 0.6033,
"step": 8760
},
{
"epoch": 0.7425281517229702,
"grad_norm": 0.39911988377571106,
"learning_rate": 2e-05,
"loss": 0.6138,
"step": 8770
},
{
"epoch": 0.7433748200829735,
"grad_norm": 0.41875290870666504,
"learning_rate": 2e-05,
"loss": 0.6087,
"step": 8780
},
{
"epoch": 0.7442214884429769,
"grad_norm": 0.3814185559749603,
"learning_rate": 2e-05,
"loss": 0.6143,
"step": 8790
},
{
"epoch": 0.7450681568029802,
"grad_norm": 0.4036637544631958,
"learning_rate": 2e-05,
"loss": 0.5822,
"step": 8800
},
{
"epoch": 0.7459148251629837,
"grad_norm": 0.38150280714035034,
"learning_rate": 2e-05,
"loss": 0.6168,
"step": 8810
},
{
"epoch": 0.746761493522987,
"grad_norm": 0.4064708650112152,
"learning_rate": 2e-05,
"loss": 0.6132,
"step": 8820
},
{
"epoch": 0.7476081618829904,
"grad_norm": 0.37701642513275146,
"learning_rate": 2e-05,
"loss": 0.6162,
"step": 8830
},
{
"epoch": 0.7484548302429939,
"grad_norm": 0.43275558948516846,
"learning_rate": 2e-05,
"loss": 0.601,
"step": 8840
},
{
"epoch": 0.7493014986029972,
"grad_norm": 0.39675280451774597,
"learning_rate": 2e-05,
"loss": 0.5937,
"step": 8850
},
{
"epoch": 0.7501481669630006,
"grad_norm": 0.3701160252094269,
"learning_rate": 2e-05,
"loss": 0.57,
"step": 8860
},
{
"epoch": 0.7509948353230039,
"grad_norm": 0.40066125988960266,
"learning_rate": 2e-05,
"loss": 0.6178,
"step": 8870
},
{
"epoch": 0.7518415036830074,
"grad_norm": 0.40293705463409424,
"learning_rate": 2e-05,
"loss": 0.5862,
"step": 8880
},
{
"epoch": 0.7526881720430108,
"grad_norm": 0.4285898804664612,
"learning_rate": 2e-05,
"loss": 0.5985,
"step": 8890
},
{
"epoch": 0.7535348404030141,
"grad_norm": 0.5093976259231567,
"learning_rate": 2e-05,
"loss": 0.5978,
"step": 8900
},
{
"epoch": 0.7543815087630176,
"grad_norm": 0.3918039798736572,
"learning_rate": 2e-05,
"loss": 0.6119,
"step": 8910
},
{
"epoch": 0.7552281771230209,
"grad_norm": 0.4051649272441864,
"learning_rate": 2e-05,
"loss": 0.5891,
"step": 8920
},
{
"epoch": 0.7560748454830243,
"grad_norm": 0.3853020668029785,
"learning_rate": 2e-05,
"loss": 0.5848,
"step": 8930
},
{
"epoch": 0.7569215138430276,
"grad_norm": 0.37184423208236694,
"learning_rate": 2e-05,
"loss": 0.6225,
"step": 8940
},
{
"epoch": 0.7577681822030311,
"grad_norm": 0.40315571427345276,
"learning_rate": 2e-05,
"loss": 0.6074,
"step": 8950
},
{
"epoch": 0.7586148505630345,
"grad_norm": 0.4277465045452118,
"learning_rate": 2e-05,
"loss": 0.6274,
"step": 8960
},
{
"epoch": 0.7594615189230378,
"grad_norm": 0.4054996371269226,
"learning_rate": 2e-05,
"loss": 0.6047,
"step": 8970
},
{
"epoch": 0.7603081872830413,
"grad_norm": 0.4016954004764557,
"learning_rate": 2e-05,
"loss": 0.589,
"step": 8980
},
{
"epoch": 0.7611548556430446,
"grad_norm": 0.3748454451560974,
"learning_rate": 2e-05,
"loss": 0.612,
"step": 8990
},
{
"epoch": 0.762001524003048,
"grad_norm": 0.39344123005867004,
"learning_rate": 2e-05,
"loss": 0.5933,
"step": 9000
},
{
"epoch": 0.7628481923630513,
"grad_norm": 0.42951688170433044,
"learning_rate": 2e-05,
"loss": 0.6123,
"step": 9010
},
{
"epoch": 0.7636948607230548,
"grad_norm": 0.40750110149383545,
"learning_rate": 2e-05,
"loss": 0.5853,
"step": 9020
},
{
"epoch": 0.7645415290830582,
"grad_norm": 0.3759666085243225,
"learning_rate": 2e-05,
"loss": 0.5946,
"step": 9030
},
{
"epoch": 0.7653881974430615,
"grad_norm": 0.40986594557762146,
"learning_rate": 2e-05,
"loss": 0.6026,
"step": 9040
},
{
"epoch": 0.766234865803065,
"grad_norm": 0.5344463586807251,
"learning_rate": 2e-05,
"loss": 0.6085,
"step": 9050
},
{
"epoch": 0.7670815341630683,
"grad_norm": 0.37710586190223694,
"learning_rate": 2e-05,
"loss": 0.5937,
"step": 9060
},
{
"epoch": 0.7679282025230717,
"grad_norm": 0.4051751494407654,
"learning_rate": 2e-05,
"loss": 0.598,
"step": 9070
},
{
"epoch": 0.7687748708830751,
"grad_norm": 0.4041481614112854,
"learning_rate": 2e-05,
"loss": 0.5934,
"step": 9080
},
{
"epoch": 0.7696215392430785,
"grad_norm": 0.40506118535995483,
"learning_rate": 2e-05,
"loss": 0.5892,
"step": 9090
},
{
"epoch": 0.7704682076030819,
"grad_norm": 0.40913790464401245,
"learning_rate": 2e-05,
"loss": 0.6176,
"step": 9100
},
{
"epoch": 0.7713148759630852,
"grad_norm": 0.3746597170829773,
"learning_rate": 2e-05,
"loss": 0.5979,
"step": 9110
},
{
"epoch": 0.7721615443230887,
"grad_norm": 0.3760552406311035,
"learning_rate": 2e-05,
"loss": 0.6053,
"step": 9120
},
{
"epoch": 0.773008212683092,
"grad_norm": 0.37211862206459045,
"learning_rate": 2e-05,
"loss": 0.6113,
"step": 9130
},
{
"epoch": 0.7738548810430954,
"grad_norm": 0.367471307516098,
"learning_rate": 2e-05,
"loss": 0.5996,
"step": 9140
},
{
"epoch": 0.7747015494030988,
"grad_norm": 0.3900797367095947,
"learning_rate": 2e-05,
"loss": 0.6029,
"step": 9150
},
{
"epoch": 0.7755482177631022,
"grad_norm": 0.3866053819656372,
"learning_rate": 2e-05,
"loss": 0.5912,
"step": 9160
},
{
"epoch": 0.7763948861231056,
"grad_norm": 0.38991448283195496,
"learning_rate": 2e-05,
"loss": 0.6122,
"step": 9170
},
{
"epoch": 0.7772415544831089,
"grad_norm": 0.3757704198360443,
"learning_rate": 2e-05,
"loss": 0.6098,
"step": 9180
},
{
"epoch": 0.7780882228431123,
"grad_norm": 0.3902888000011444,
"learning_rate": 2e-05,
"loss": 0.5953,
"step": 9190
},
{
"epoch": 0.7789348912031158,
"grad_norm": 0.3717533349990845,
"learning_rate": 2e-05,
"loss": 0.6095,
"step": 9200
},
{
"epoch": 0.7797815595631191,
"grad_norm": 0.41047364473342896,
"learning_rate": 2e-05,
"loss": 0.5962,
"step": 9210
},
{
"epoch": 0.7806282279231225,
"grad_norm": 0.39431434869766235,
"learning_rate": 2e-05,
"loss": 0.625,
"step": 9220
},
{
"epoch": 0.7814748962831259,
"grad_norm": 0.3538172245025635,
"learning_rate": 2e-05,
"loss": 0.5972,
"step": 9230
},
{
"epoch": 0.7823215646431293,
"grad_norm": 0.39997097849845886,
"learning_rate": 2e-05,
"loss": 0.592,
"step": 9240
},
{
"epoch": 0.7831682330031327,
"grad_norm": 0.3972622752189636,
"learning_rate": 2e-05,
"loss": 0.6104,
"step": 9250
},
{
"epoch": 0.784014901363136,
"grad_norm": 0.38872411847114563,
"learning_rate": 2e-05,
"loss": 0.6041,
"step": 9260
},
{
"epoch": 0.7848615697231395,
"grad_norm": 0.36306217312812805,
"learning_rate": 2e-05,
"loss": 0.59,
"step": 9270
},
{
"epoch": 0.7857082380831428,
"grad_norm": 0.394020140171051,
"learning_rate": 2e-05,
"loss": 0.6087,
"step": 9280
},
{
"epoch": 0.7865549064431462,
"grad_norm": 0.4496012032032013,
"learning_rate": 2e-05,
"loss": 0.5987,
"step": 9290
},
{
"epoch": 0.7874015748031497,
"grad_norm": 0.415387362241745,
"learning_rate": 2e-05,
"loss": 0.6055,
"step": 9300
},
{
"epoch": 0.788248243163153,
"grad_norm": 0.44512197375297546,
"learning_rate": 2e-05,
"loss": 0.6032,
"step": 9310
},
{
"epoch": 0.7890949115231564,
"grad_norm": 0.44583505392074585,
"learning_rate": 2e-05,
"loss": 0.6085,
"step": 9320
},
{
"epoch": 0.7899415798831597,
"grad_norm": 0.41276854276657104,
"learning_rate": 2e-05,
"loss": 0.6206,
"step": 9330
},
{
"epoch": 0.7907882482431632,
"grad_norm": 0.38308656215667725,
"learning_rate": 2e-05,
"loss": 0.59,
"step": 9340
},
{
"epoch": 0.7916349166031665,
"grad_norm": 0.437049925327301,
"learning_rate": 2e-05,
"loss": 0.5963,
"step": 9350
},
{
"epoch": 0.7924815849631699,
"grad_norm": 0.3866311311721802,
"learning_rate": 2e-05,
"loss": 0.5994,
"step": 9360
},
{
"epoch": 0.7933282533231734,
"grad_norm": 0.42114999890327454,
"learning_rate": 2e-05,
"loss": 0.6172,
"step": 9370
},
{
"epoch": 0.7941749216831767,
"grad_norm": 0.3968478739261627,
"learning_rate": 2e-05,
"loss": 0.6027,
"step": 9380
},
{
"epoch": 0.7950215900431801,
"grad_norm": 0.44920459389686584,
"learning_rate": 2e-05,
"loss": 0.5929,
"step": 9390
},
{
"epoch": 0.7958682584031834,
"grad_norm": 0.45039042830467224,
"learning_rate": 2e-05,
"loss": 0.6104,
"step": 9400
},
{
"epoch": 0.7967149267631869,
"grad_norm": 0.3940369188785553,
"learning_rate": 2e-05,
"loss": 0.6059,
"step": 9410
},
{
"epoch": 0.7975615951231902,
"grad_norm": 0.35691148042678833,
"learning_rate": 2e-05,
"loss": 0.6023,
"step": 9420
},
{
"epoch": 0.7984082634831936,
"grad_norm": 0.42013436555862427,
"learning_rate": 2e-05,
"loss": 0.6324,
"step": 9430
},
{
"epoch": 0.7992549318431971,
"grad_norm": 0.38049906492233276,
"learning_rate": 2e-05,
"loss": 0.6057,
"step": 9440
},
{
"epoch": 0.8001016002032004,
"grad_norm": 0.4230620563030243,
"learning_rate": 2e-05,
"loss": 0.6058,
"step": 9450
},
{
"epoch": 0.8009482685632038,
"grad_norm": 0.39889097213745117,
"learning_rate": 2e-05,
"loss": 0.5889,
"step": 9460
},
{
"epoch": 0.8017949369232071,
"grad_norm": 0.37639039754867554,
"learning_rate": 2e-05,
"loss": 0.5929,
"step": 9470
},
{
"epoch": 0.8026416052832106,
"grad_norm": 0.3882730007171631,
"learning_rate": 2e-05,
"loss": 0.6064,
"step": 9480
},
{
"epoch": 0.803488273643214,
"grad_norm": 0.39904358983039856,
"learning_rate": 2e-05,
"loss": 0.6021,
"step": 9490
},
{
"epoch": 0.8043349420032173,
"grad_norm": 0.3637270927429199,
"learning_rate": 2e-05,
"loss": 0.615,
"step": 9500
},
{
"epoch": 0.8051816103632208,
"grad_norm": 0.41030174493789673,
"learning_rate": 2e-05,
"loss": 0.6082,
"step": 9510
},
{
"epoch": 0.8060282787232241,
"grad_norm": 0.4089955985546112,
"learning_rate": 2e-05,
"loss": 0.6023,
"step": 9520
},
{
"epoch": 0.8068749470832275,
"grad_norm": 0.3826632797718048,
"learning_rate": 2e-05,
"loss": 0.6163,
"step": 9530
},
{
"epoch": 0.8077216154432308,
"grad_norm": 0.4477853775024414,
"learning_rate": 2e-05,
"loss": 0.6076,
"step": 9540
},
{
"epoch": 0.8085682838032343,
"grad_norm": 0.6286106705665588,
"learning_rate": 2e-05,
"loss": 0.6058,
"step": 9550
},
{
"epoch": 0.8094149521632377,
"grad_norm": 0.38646039366722107,
"learning_rate": 2e-05,
"loss": 0.614,
"step": 9560
},
{
"epoch": 0.810261620523241,
"grad_norm": 0.3947027325630188,
"learning_rate": 2e-05,
"loss": 0.5975,
"step": 9570
},
{
"epoch": 0.8111082888832445,
"grad_norm": 0.4293883442878723,
"learning_rate": 2e-05,
"loss": 0.591,
"step": 9580
},
{
"epoch": 0.8119549572432478,
"grad_norm": 0.3688395917415619,
"learning_rate": 2e-05,
"loss": 0.6036,
"step": 9590
},
{
"epoch": 0.8128016256032512,
"grad_norm": 0.4206239879131317,
"learning_rate": 2e-05,
"loss": 0.5943,
"step": 9600
},
{
"epoch": 0.8136482939632546,
"grad_norm": 0.4022585153579712,
"learning_rate": 2e-05,
"loss": 0.6083,
"step": 9610
},
{
"epoch": 0.814494962323258,
"grad_norm": 0.37902072072029114,
"learning_rate": 2e-05,
"loss": 0.5944,
"step": 9620
},
{
"epoch": 0.8153416306832614,
"grad_norm": 0.38892993330955505,
"learning_rate": 2e-05,
"loss": 0.6037,
"step": 9630
},
{
"epoch": 0.8161882990432647,
"grad_norm": 0.39761650562286377,
"learning_rate": 2e-05,
"loss": 0.6091,
"step": 9640
},
{
"epoch": 0.8170349674032681,
"grad_norm": 0.3798573613166809,
"learning_rate": 2e-05,
"loss": 0.6109,
"step": 9650
},
{
"epoch": 0.8178816357632716,
"grad_norm": 0.42083317041397095,
"learning_rate": 2e-05,
"loss": 0.585,
"step": 9660
},
{
"epoch": 0.8187283041232749,
"grad_norm": 0.4126664996147156,
"learning_rate": 2e-05,
"loss": 0.5903,
"step": 9670
},
{
"epoch": 0.8195749724832783,
"grad_norm": 0.38387686014175415,
"learning_rate": 2e-05,
"loss": 0.5935,
"step": 9680
},
{
"epoch": 0.8204216408432817,
"grad_norm": 0.39875295758247375,
"learning_rate": 2e-05,
"loss": 0.5734,
"step": 9690
},
{
"epoch": 0.8212683092032851,
"grad_norm": 0.4429735243320465,
"learning_rate": 2e-05,
"loss": 0.6193,
"step": 9700
},
{
"epoch": 0.8221149775632884,
"grad_norm": 0.39496341347694397,
"learning_rate": 2e-05,
"loss": 0.612,
"step": 9710
},
{
"epoch": 0.8229616459232918,
"grad_norm": 0.5135132670402527,
"learning_rate": 2e-05,
"loss": 0.6054,
"step": 9720
},
{
"epoch": 0.8238083142832953,
"grad_norm": 0.39860033988952637,
"learning_rate": 2e-05,
"loss": 0.6077,
"step": 9730
},
{
"epoch": 0.8246549826432986,
"grad_norm": 0.3776315748691559,
"learning_rate": 2e-05,
"loss": 0.609,
"step": 9740
},
{
"epoch": 0.825501651003302,
"grad_norm": 0.36576783657073975,
"learning_rate": 2e-05,
"loss": 0.5817,
"step": 9750
},
{
"epoch": 0.8263483193633054,
"grad_norm": 0.4033512771129608,
"learning_rate": 2e-05,
"loss": 0.6189,
"step": 9760
},
{
"epoch": 0.8271949877233088,
"grad_norm": 0.3823210299015045,
"learning_rate": 2e-05,
"loss": 0.5684,
"step": 9770
},
{
"epoch": 0.8280416560833121,
"grad_norm": 0.3893999457359314,
"learning_rate": 2e-05,
"loss": 0.5916,
"step": 9780
},
{
"epoch": 0.8288883244433155,
"grad_norm": 0.38226866722106934,
"learning_rate": 2e-05,
"loss": 0.6117,
"step": 9790
},
{
"epoch": 0.829734992803319,
"grad_norm": 0.38761594891548157,
"learning_rate": 2e-05,
"loss": 0.585,
"step": 9800
},
{
"epoch": 0.8305816611633223,
"grad_norm": 0.5508137345314026,
"learning_rate": 2e-05,
"loss": 0.6115,
"step": 9810
},
{
"epoch": 0.8314283295233257,
"grad_norm": 0.40430906414985657,
"learning_rate": 2e-05,
"loss": 0.5815,
"step": 9820
},
{
"epoch": 0.8322749978833291,
"grad_norm": 0.39865976572036743,
"learning_rate": 2e-05,
"loss": 0.5926,
"step": 9830
},
{
"epoch": 0.8331216662433325,
"grad_norm": 0.3848314881324768,
"learning_rate": 2e-05,
"loss": 0.6239,
"step": 9840
},
{
"epoch": 0.8339683346033359,
"grad_norm": 0.35395070910453796,
"learning_rate": 2e-05,
"loss": 0.5978,
"step": 9850
},
{
"epoch": 0.8348150029633392,
"grad_norm": 0.44156140089035034,
"learning_rate": 2e-05,
"loss": 0.5892,
"step": 9860
},
{
"epoch": 0.8356616713233427,
"grad_norm": 0.3768967092037201,
"learning_rate": 2e-05,
"loss": 0.6051,
"step": 9870
},
{
"epoch": 0.836508339683346,
"grad_norm": 0.3962550163269043,
"learning_rate": 2e-05,
"loss": 0.5797,
"step": 9880
},
{
"epoch": 0.8373550080433494,
"grad_norm": 0.3716156780719757,
"learning_rate": 2e-05,
"loss": 0.5938,
"step": 9890
},
{
"epoch": 0.8382016764033529,
"grad_norm": 0.3599317669868469,
"learning_rate": 2e-05,
"loss": 0.5839,
"step": 9900
},
{
"epoch": 0.8390483447633562,
"grad_norm": 0.3897750973701477,
"learning_rate": 2e-05,
"loss": 0.617,
"step": 9910
},
{
"epoch": 0.8398950131233596,
"grad_norm": 0.3710968792438507,
"learning_rate": 2e-05,
"loss": 0.5904,
"step": 9920
},
{
"epoch": 0.8407416814833629,
"grad_norm": 0.4039498269557953,
"learning_rate": 2e-05,
"loss": 0.6041,
"step": 9930
},
{
"epoch": 0.8415883498433664,
"grad_norm": 0.39304158091545105,
"learning_rate": 2e-05,
"loss": 0.5879,
"step": 9940
},
{
"epoch": 0.8424350182033697,
"grad_norm": 0.4112839996814728,
"learning_rate": 2e-05,
"loss": 0.583,
"step": 9950
},
{
"epoch": 0.8432816865633731,
"grad_norm": 0.3861272633075714,
"learning_rate": 2e-05,
"loss": 0.6111,
"step": 9960
},
{
"epoch": 0.8441283549233766,
"grad_norm": 0.46878281235694885,
"learning_rate": 2e-05,
"loss": 0.5885,
"step": 9970
},
{
"epoch": 0.8449750232833799,
"grad_norm": 0.39621326327323914,
"learning_rate": 2e-05,
"loss": 0.5914,
"step": 9980
},
{
"epoch": 0.8458216916433833,
"grad_norm": 0.39243268966674805,
"learning_rate": 2e-05,
"loss": 0.6189,
"step": 9990
},
{
"epoch": 0.8466683600033866,
"grad_norm": 0.41455838084220886,
"learning_rate": 2e-05,
"loss": 0.6139,
"step": 10000
},
{
"epoch": 0.8475150283633901,
"grad_norm": 0.3877462148666382,
"learning_rate": 2e-05,
"loss": 0.6021,
"step": 10010
},
{
"epoch": 0.8483616967233935,
"grad_norm": 0.3965286910533905,
"learning_rate": 2e-05,
"loss": 0.6051,
"step": 10020
},
{
"epoch": 0.8492083650833968,
"grad_norm": 0.4080818295478821,
"learning_rate": 2e-05,
"loss": 0.5993,
"step": 10030
},
{
"epoch": 0.8500550334434002,
"grad_norm": 0.3806658387184143,
"learning_rate": 2e-05,
"loss": 0.5971,
"step": 10040
},
{
"epoch": 0.8509017018034036,
"grad_norm": 0.4122281074523926,
"learning_rate": 2e-05,
"loss": 0.6055,
"step": 10050
},
{
"epoch": 0.851748370163407,
"grad_norm": 0.3960241675376892,
"learning_rate": 2e-05,
"loss": 0.6045,
"step": 10060
},
{
"epoch": 0.8525950385234103,
"grad_norm": 0.3817008137702942,
"learning_rate": 2e-05,
"loss": 0.5899,
"step": 10070
},
{
"epoch": 0.8534417068834138,
"grad_norm": 0.40316328406333923,
"learning_rate": 2e-05,
"loss": 0.6062,
"step": 10080
},
{
"epoch": 0.8542883752434172,
"grad_norm": 0.406048983335495,
"learning_rate": 2e-05,
"loss": 0.5956,
"step": 10090
},
{
"epoch": 0.8551350436034205,
"grad_norm": 0.42371147871017456,
"learning_rate": 2e-05,
"loss": 0.6081,
"step": 10100
},
{
"epoch": 0.8559817119634239,
"grad_norm": 0.4046058654785156,
"learning_rate": 2e-05,
"loss": 0.6032,
"step": 10110
},
{
"epoch": 0.8568283803234273,
"grad_norm": 0.3874751627445221,
"learning_rate": 2e-05,
"loss": 0.6052,
"step": 10120
},
{
"epoch": 0.8576750486834307,
"grad_norm": 0.38550081849098206,
"learning_rate": 2e-05,
"loss": 0.5952,
"step": 10130
},
{
"epoch": 0.858521717043434,
"grad_norm": 0.36764973402023315,
"learning_rate": 2e-05,
"loss": 0.5852,
"step": 10140
},
{
"epoch": 0.8593683854034375,
"grad_norm": 0.3904081881046295,
"learning_rate": 2e-05,
"loss": 0.6148,
"step": 10150
},
{
"epoch": 0.8602150537634409,
"grad_norm": 0.3823360502719879,
"learning_rate": 2e-05,
"loss": 0.5974,
"step": 10160
},
{
"epoch": 0.8610617221234442,
"grad_norm": 0.42833980917930603,
"learning_rate": 2e-05,
"loss": 0.6237,
"step": 10170
},
{
"epoch": 0.8619083904834476,
"grad_norm": 0.6880196928977966,
"learning_rate": 1.999957274187931e-05,
"loss": 0.5981,
"step": 10180
},
{
"epoch": 0.862755058843451,
"grad_norm": 0.363347589969635,
"learning_rate": 1.9991978062682906e-05,
"loss": 0.599,
"step": 10190
},
{
"epoch": 0.8636017272034544,
"grad_norm": 0.39425960183143616,
"learning_rate": 1.997489709987378e-05,
"loss": 0.5972,
"step": 10200
},
{
"epoch": 0.8644483955634578,
"grad_norm": 0.4055992066860199,
"learning_rate": 1.9948346151502135e-05,
"loss": 0.6068,
"step": 10210
},
{
"epoch": 0.8652950639234612,
"grad_norm": 0.4094567596912384,
"learning_rate": 1.991235055154325e-05,
"loss": 0.5989,
"step": 10220
},
{
"epoch": 0.8661417322834646,
"grad_norm": 0.4379693865776062,
"learning_rate": 1.9866944645724693e-05,
"loss": 0.5839,
"step": 10230
},
{
"epoch": 0.8669884006434679,
"grad_norm": 0.4112693667411804,
"learning_rate": 1.9812171758754842e-05,
"loss": 0.5988,
"step": 10240
},
{
"epoch": 0.8678350690034713,
"grad_norm": 0.4229643642902374,
"learning_rate": 1.9748084152983987e-05,
"loss": 0.5942,
"step": 10250
},
{
"epoch": 0.8686817373634748,
"grad_norm": 0.4654715061187744,
"learning_rate": 1.967474297853744e-05,
"loss": 0.6312,
"step": 10260
},
{
"epoch": 0.8695284057234781,
"grad_norm": 0.4212554693222046,
"learning_rate": 1.9592218214968256e-05,
"loss": 0.5904,
"step": 10270
},
{
"epoch": 0.8703750740834815,
"grad_norm": 0.3878800570964813,
"learning_rate": 1.9500588604485213e-05,
"loss": 0.5751,
"step": 10280
},
{
"epoch": 0.8712217424434849,
"grad_norm": 0.40103572607040405,
"learning_rate": 1.939994157681979e-05,
"loss": 0.5977,
"step": 10290
},
{
"epoch": 0.8720684108034883,
"grad_norm": 0.41372302174568176,
"learning_rate": 1.9290373165803803e-05,
"loss": 0.5927,
"step": 10300
},
{
"epoch": 0.8729150791634916,
"grad_norm": 0.4061325490474701,
"learning_rate": 1.9171987917737328e-05,
"loss": 0.6205,
"step": 10310
},
{
"epoch": 0.873761747523495,
"grad_norm": 0.3708367347717285,
"learning_rate": 1.9044898791634322e-05,
"loss": 0.5969,
"step": 10320
},
{
"epoch": 0.8746084158834985,
"grad_norm": 0.39036187529563904,
"learning_rate": 1.8909227051441126e-05,
"loss": 0.5745,
"step": 10330
},
{
"epoch": 0.8754550842435018,
"grad_norm": 0.3698790371417999,
"learning_rate": 1.8765102150330692e-05,
"loss": 0.5984,
"step": 10340
},
{
"epoch": 0.8763017526035052,
"grad_norm": 0.41296541690826416,
"learning_rate": 1.861266160718297e-05,
"loss": 0.6081,
"step": 10350
},
{
"epoch": 0.8771484209635086,
"grad_norm": 0.3573046028614044,
"learning_rate": 1.845205087536923e-05,
"loss": 0.5689,
"step": 10360
},
{
"epoch": 0.877995089323512,
"grad_norm": 0.41128793358802795,
"learning_rate": 1.8283423203965633e-05,
"loss": 0.5934,
"step": 10370
},
{
"epoch": 0.8788417576835154,
"grad_norm": 0.380269855260849,
"learning_rate": 1.810693949152835e-05,
"loss": 0.5907,
"step": 10380
},
{
"epoch": 0.8796884260435187,
"grad_norm": 0.3998042345046997,
"learning_rate": 1.7922768132569902e-05,
"loss": 0.5911,
"step": 10390
},
{
"epoch": 0.8805350944035222,
"grad_norm": 0.35871461033821106,
"learning_rate": 1.773108485688302e-05,
"loss": 0.5975,
"step": 10400
},
{
"epoch": 0.8813817627635255,
"grad_norm": 0.36145204305648804,
"learning_rate": 1.7532072561865537e-05,
"loss": 0.5922,
"step": 10410
},
{
"epoch": 0.8822284311235289,
"grad_norm": 0.3756173551082611,
"learning_rate": 1.732592113800616e-05,
"loss": 0.6147,
"step": 10420
},
{
"epoch": 0.8830750994835324,
"grad_norm": 0.4014023542404175,
"learning_rate": 1.7112827287697668e-05,
"loss": 0.5875,
"step": 10430
},
{
"epoch": 0.8839217678435357,
"grad_norm": 0.4148462116718292,
"learning_rate": 1.6892994337550452e-05,
"loss": 0.5943,
"step": 10440
},
{
"epoch": 0.8847684362035391,
"grad_norm": 0.4367964565753937,
"learning_rate": 1.6666632044385487e-05,
"loss": 0.597,
"step": 10450
},
{
"epoch": 0.8856151045635424,
"grad_norm": 0.440523236989975,
"learning_rate": 1.6433956395091757e-05,
"loss": 0.6169,
"step": 10460
},
{
"epoch": 0.8864617729235459,
"grad_norm": 0.3791385293006897,
"learning_rate": 1.6195189400539238e-05,
"loss": 0.5991,
"step": 10470
},
{
"epoch": 0.8873084412835492,
"grad_norm": 0.70876544713974,
"learning_rate": 1.595055888374398e-05,
"loss": 0.5927,
"step": 10480
},
{
"epoch": 0.8881551096435526,
"grad_norm": 0.40011459589004517,
"learning_rate": 1.5700298262487434e-05,
"loss": 0.5982,
"step": 10490
},
{
"epoch": 0.889001778003556,
"grad_norm": 0.3757799565792084,
"learning_rate": 1.5444646326597467e-05,
"loss": 0.5797,
"step": 10500
},
{
"epoch": 0.8898484463635594,
"grad_norm": 0.47506874799728394,
"learning_rate": 1.5183847010103586e-05,
"loss": 0.5704,
"step": 10510
},
{
"epoch": 0.8906951147235628,
"grad_norm": 0.3836280107498169,
"learning_rate": 1.4918149158483686e-05,
"loss": 0.6007,
"step": 10520
},
{
"epoch": 0.8915417830835661,
"grad_norm": 0.413482666015625,
"learning_rate": 1.464780629122452e-05,
"loss": 0.6018,
"step": 10530
},
{
"epoch": 0.8923884514435696,
"grad_norm": 0.3784448504447937,
"learning_rate": 1.4373076359922374e-05,
"loss": 0.5863,
"step": 10540
},
{
"epoch": 0.893235119803573,
"grad_norm": 0.374307781457901,
"learning_rate": 1.4094221502154774e-05,
"loss": 0.5779,
"step": 10550
},
{
"epoch": 0.8940817881635763,
"grad_norm": 0.391169935464859,
"learning_rate": 1.3811507791358113e-05,
"loss": 0.6042,
"step": 10560
},
{
"epoch": 0.8949284565235797,
"grad_norm": 0.42855170369148254,
"learning_rate": 1.3525204982949753e-05,
"loss": 0.5815,
"step": 10570
},
{
"epoch": 0.8957751248835831,
"grad_norm": 0.4763769805431366,
"learning_rate": 1.3235586256936996e-05,
"loss": 0.5941,
"step": 10580
},
{
"epoch": 0.8966217932435865,
"grad_norm": 0.3874017298221588,
"learning_rate": 1.294292795725836e-05,
"loss": 0.5884,
"step": 10590
},
{
"epoch": 0.8974684616035898,
"grad_norm": 0.3798024356365204,
"learning_rate": 1.2647509328105978e-05,
"loss": 0.6073,
"step": 10600
},
{
"epoch": 0.8983151299635933,
"grad_norm": 0.37498512864112854,
"learning_rate": 1.2349612247480686e-05,
"loss": 0.6024,
"step": 10610
},
{
"epoch": 0.8991617983235967,
"grad_norm": 0.7758206725120544,
"learning_rate": 1.2049520958234e-05,
"loss": 0.5798,
"step": 10620
},
{
"epoch": 0.9000084666836,
"grad_norm": 0.38066551089286804,
"learning_rate": 1.1747521796853638e-05,
"loss": 0.5837,
"step": 10630
},
{
"epoch": 0.9008551350436034,
"grad_norm": 0.41683727502822876,
"learning_rate": 1.1443902920251395e-05,
"loss": 0.609,
"step": 10640
},
{
"epoch": 0.9017018034036068,
"grad_norm": 0.36746421456336975,
"learning_rate": 1.1138954030814009e-05,
"loss": 0.5835,
"step": 10650
},
{
"epoch": 0.9025484717636102,
"grad_norm": 0.4123273193836212,
"learning_rate": 1.0832966099979388e-05,
"loss": 0.6024,
"step": 10660
},
{
"epoch": 0.9033951401236135,
"grad_norm": 0.3546232581138611,
"learning_rate": 1.0526231090601969e-05,
"loss": 0.5981,
"step": 10670
},
{
"epoch": 0.904241808483617,
"grad_norm": 0.4065309464931488,
"learning_rate": 1.0219041678372106e-05,
"loss": 0.6139,
"step": 10680
},
{
"epoch": 0.9050884768436204,
"grad_norm": 0.37122365832328796,
"learning_rate": 9.911690972555268e-06,
"loss": 0.5784,
"step": 10690
},
{
"epoch": 0.9059351452036237,
"grad_norm": 0.39508020877838135,
"learning_rate": 9.604472236317541e-06,
"loss": 0.5965,
"step": 10700
},
{
"epoch": 0.9067818135636271,
"grad_norm": 0.36885911226272583,
"learning_rate": 9.297678606904335e-06,
"loss": 0.6037,
"step": 10710
},
{
"epoch": 0.9076284819236305,
"grad_norm": 0.42489999532699585,
"learning_rate": 8.991602815939155e-06,
"loss": 0.6131,
"step": 10720
},
{
"epoch": 0.9084751502836339,
"grad_norm": 0.3915928602218628,
"learning_rate": 8.686536910109464e-06,
"loss": 0.5983,
"step": 10730
},
{
"epoch": 0.9093218186436373,
"grad_norm": 0.3702114224433899,
"learning_rate": 8.382771972506084e-06,
"loss": 0.5985,
"step": 10740
},
{
"epoch": 0.9101684870036407,
"grad_norm": 0.3594807982444763,
"learning_rate": 8.08059784488198e-06,
"loss": 0.5779,
"step": 10750
},
{
"epoch": 0.9110151553636441,
"grad_norm": 0.3783262073993683,
"learning_rate": 7.780302851095544e-06,
"loss": 0.5822,
"step": 10760
},
{
"epoch": 0.9118618237236474,
"grad_norm": 0.4087844789028168,
"learning_rate": 7.482173522002166e-06,
"loss": 0.5877,
"step": 10770
},
{
"epoch": 0.9127084920836508,
"grad_norm": 0.378827303647995,
"learning_rate": 7.186494322056624e-06,
"loss": 0.6034,
"step": 10780
},
{
"epoch": 0.9135551604436543,
"grad_norm": 0.40156781673431396,
"learning_rate": 6.893547377887183e-06,
"loss": 0.5956,
"step": 10790
},
{
"epoch": 0.9144018288036576,
"grad_norm": 0.41311174631118774,
"learning_rate": 6.6036122091003365e-06,
"loss": 0.5813,
"step": 10800
},
{
"epoch": 0.915248497163661,
"grad_norm": 0.375812828540802,
"learning_rate": 6.316965461573097e-06,
"loss": 0.6064,
"step": 10810
},
{
"epoch": 0.9160951655236644,
"grad_norm": 0.43626660108566284,
"learning_rate": 6.0338806434872965e-06,
"loss": 0.5702,
"step": 10820
},
{
"epoch": 0.9169418338836678,
"grad_norm": 0.3960444927215576,
"learning_rate": 5.754627864357749e-06,
"loss": 0.5892,
"step": 10830
},
{
"epoch": 0.9177885022436711,
"grad_norm": 0.38290396332740784,
"learning_rate": 5.479473577303319e-06,
"loss": 0.5751,
"step": 10840
},
{
"epoch": 0.9186351706036745,
"grad_norm": 0.41256606578826904,
"learning_rate": 5.208680324806778e-06,
"loss": 0.5809,
"step": 10850
},
{
"epoch": 0.919481838963678,
"grad_norm": 0.3761991858482361,
"learning_rate": 4.94250648820606e-06,
"loss": 0.5891,
"step": 10860
},
{
"epoch": 0.9203285073236813,
"grad_norm": 0.3638654947280884,
"learning_rate": 4.681206041155951e-06,
"loss": 0.5657,
"step": 10870
},
{
"epoch": 0.9211751756836847,
"grad_norm": 0.3918462097644806,
"learning_rate": 4.42502830729538e-06,
"loss": 0.5865,
"step": 10880
},
{
"epoch": 0.922021844043688,
"grad_norm": 0.37534892559051514,
"learning_rate": 4.174217722351669e-06,
"loss": 0.5794,
"step": 10890
},
{
"epoch": 0.9228685124036915,
"grad_norm": 0.38715600967407227,
"learning_rate": 3.929013600908575e-06,
"loss": 0.5936,
"step": 10900
},
{
"epoch": 0.9237151807636949,
"grad_norm": 0.4242173433303833,
"learning_rate": 3.689649908060807e-06,
"loss": 0.5706,
"step": 10910
},
{
"epoch": 0.9245618491236982,
"grad_norm": 0.41797444224357605,
"learning_rate": 3.4563550361728028e-06,
"loss": 0.598,
"step": 10920
},
{
"epoch": 0.9254085174837017,
"grad_norm": 0.3691329061985016,
"learning_rate": 3.2293515869548216e-06,
"loss": 0.572,
"step": 10930
},
{
"epoch": 0.926255185843705,
"grad_norm": 0.3548983633518219,
"learning_rate": 3.0088561590642746e-06,
"loss": 0.5822,
"step": 10940
},
{
"epoch": 0.9271018542037084,
"grad_norm": 0.40792351961135864,
"learning_rate": 2.795079141434941e-06,
"loss": 0.5883,
"step": 10950
},
{
"epoch": 0.9279485225637117,
"grad_norm": 0.4250456988811493,
"learning_rate": 2.588224512531299e-06,
"loss": 0.6012,
"step": 10960
},
{
"epoch": 0.9287951909237152,
"grad_norm": 0.4174085855484009,
"learning_rate": 2.388489645719495e-06,
"loss": 0.5812,
"step": 10970
},
{
"epoch": 0.9296418592837186,
"grad_norm": 0.4629608690738678,
"learning_rate": 2.196065120940663e-06,
"loss": 0.5782,
"step": 10980
},
{
"epoch": 0.9304885276437219,
"grad_norm": 0.37794700264930725,
"learning_rate": 2.0111345428662808e-06,
"loss": 0.5776,
"step": 10990
},
{
"epoch": 0.9313351960037254,
"grad_norm": 0.4090331196784973,
"learning_rate": 1.8338743657091102e-06,
"loss": 0.5876,
"step": 11000
},
{
"epoch": 0.9321818643637287,
"grad_norm": 0.3792206943035126,
"learning_rate": 1.6644537248568113e-06,
"loss": 0.5929,
"step": 11010
},
{
"epoch": 0.9330285327237321,
"grad_norm": 0.35595670342445374,
"learning_rate": 1.503034275488951e-06,
"loss": 0.5738,
"step": 11020
},
{
"epoch": 0.9338752010837355,
"grad_norm": 0.3989730477333069,
"learning_rate": 1.3497700383313495e-06,
"loss": 0.5888,
"step": 11030
},
{
"epoch": 0.9347218694437389,
"grad_norm": 0.37127962708473206,
"learning_rate": 1.2048072526949562e-06,
"loss": 0.5852,
"step": 11040
},
{
"epoch": 0.9355685378037423,
"grad_norm": 0.3817967176437378,
"learning_rate": 1.0682842369394756e-06,
"loss": 0.5803,
"step": 11050
},
{
"epoch": 0.9364152061637456,
"grad_norm": 0.3994688391685486,
"learning_rate": 9.403312564948792e-07,
"loss": 0.5666,
"step": 11060
},
{
"epoch": 0.9372618745237491,
"grad_norm": 0.37342002987861633,
"learning_rate": 8.210703995667471e-07,
"loss": 0.5807,
"step": 11070
},
{
"epoch": 0.9381085428837524,
"grad_norm": 0.36906084418296814,
"learning_rate": 7.106154606440245e-07,
"loss": 0.5745,
"step": 11080
},
{
"epoch": 0.9389552112437558,
"grad_norm": 0.33559003472328186,
"learning_rate": 6.090718319203393e-07,
"loss": 0.5849,
"step": 11090
},
{
"epoch": 0.9398018796037592,
"grad_norm": 0.39128148555755615,
"learning_rate": 5.165364027325089e-07,
"loss": 0.5878,
"step": 11100
},
{
"epoch": 0.9406485479637626,
"grad_norm": 0.3877893090248108,
"learning_rate": 4.330974671121585e-07,
"loss": 0.557,
"step": 11110
},
{
"epoch": 0.941495216323766,
"grad_norm": 0.43245813250541687,
"learning_rate": 3.588346395386846e-07,
"loss": 0.5955,
"step": 11120
},
{
"epoch": 0.9423418846837693,
"grad_norm": 0.6879938244819641,
"learning_rate": 2.938187789739395e-07,
"loss": 0.569,
"step": 11130
},
{
"epoch": 0.9431885530437728,
"grad_norm": 0.40914833545684814,
"learning_rate": 2.3811192125110724e-07,
"loss": 0.582,
"step": 11140
},
{
"epoch": 0.9440352214037762,
"grad_norm": 0.3765310049057007,
"learning_rate": 1.917672198823177e-07,
"loss": 0.5937,
"step": 11150
},
{
"epoch": 0.9448818897637795,
"grad_norm": 0.380909264087677,
"learning_rate": 1.5482889534143795e-07,
"loss": 0.6108,
"step": 11160
},
{
"epoch": 0.9457285581237829,
"grad_norm": 0.3695523142814636,
"learning_rate": 1.273321928704694e-07,
"loss": 0.5839,
"step": 11170
},
{
"epoch": 0.9465752264837863,
"grad_norm": 0.3967580199241638,
"learning_rate": 1.0930334884977866e-07,
"loss": 0.5795,
"step": 11180
},
{
"epoch": 0.9474218948437897,
"grad_norm": 0.38119664788246155,
"learning_rate": 1.0075956576427487e-07,
"loss": 0.5749,
"step": 11190
},
{
"epoch": 0.9476758953517908,
"step": 11193,
"total_flos": 4.9965855215861105e+19,
"train_loss": 0.053643203022375,
"train_runtime": 11403.7075,
"train_samples_per_second": 11.778,
"train_steps_per_second": 0.982
}
],
"logging_steps": 10,
"max_steps": 11193,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 636,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.9965855215861105e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}