andyjzhao's picture
Upload folder using huggingface_hub
82870c5 verified
{
"best_global_step": 6000,
"best_metric": 2.9490778941081053,
"best_model_checkpoint": "/gpfs/scratch/guoh/DNAFM/output/gencode_human_12.8k_12800/HNet_BPT128_12.8K-100B/checkpoint-6000",
"epoch": 1.702127659574468,
"eval_steps": 500,
"global_step": 6000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.0028368794326241137,
"grad_norm": 1633.828125,
"loss": 88.481,
"loss_ce": 60.09074783325195,
"loss_region": 0.06510699540376663,
"loss_total": 60.155853271484375,
"lr": 2.20454076850486e-05,
"router/selected_tokens_s0": 919.375,
"router/selected_tokens_s1": 208.0625,
"step": 10,
"tokens_trained": 0.03276544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.005673758865248227,
"grad_norm": 466.1059875488281,
"loss": 44.1432,
"loss_ce": 25.237300872802734,
"loss_region": 0.36207184195518494,
"loss_total": 25.59937286376953,
"lr": 4.654030511288038e-05,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 20,
"tokens_trained": 0.06553088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.00851063829787234,
"grad_norm": 339.109375,
"loss": 14.1273,
"loss_ce": 7.768259525299072,
"loss_region": 0.3637296259403229,
"loss_total": 8.131989479064941,
"lr": 7.103520254071216e-05,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 30,
"tokens_trained": 0.09829632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.011347517730496455,
"grad_norm": 476.25433349609375,
"loss": 5.6328,
"loss_ce": 5.754528999328613,
"loss_region": 0.36484554409980774,
"loss_total": 6.119374752044678,
"lr": 9.553009996854394e-05,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 40,
"tokens_trained": 0.13106176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.014184397163120567,
"grad_norm": 555.9451904296875,
"loss": 4.3424,
"loss_ce": 5.022282123565674,
"loss_region": 0.36592456698417664,
"loss_total": 5.388206481933594,
"lr": 0.00012002499739637572,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 50,
"tokens_trained": 0.1638272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.01702127659574468,
"grad_norm": 365.4439392089844,
"loss": 5.3311,
"loss_ce": 4.102235317230225,
"loss_region": 0.3665260076522827,
"loss_total": 4.468761444091797,
"lr": 0.00014451989482420748,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 60,
"tokens_trained": 0.19659264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.019858156028368795,
"grad_norm": 675.146728515625,
"loss": 18.0367,
"loss_ce": 17.55718994140625,
"loss_region": 0.36727550625801086,
"loss_total": 17.92446517944336,
"lr": 0.00016901479225203927,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 70,
"tokens_trained": 0.22935808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.02269503546099291,
"grad_norm": 669.8828735351562,
"loss": 10.9644,
"loss_ce": 12.981254577636719,
"loss_region": 0.36880001425743103,
"loss_total": 13.350054740905762,
"lr": 0.00019350968967987104,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 80,
"tokens_trained": 0.26212272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.02553191489361702,
"grad_norm": 582.4469604492188,
"loss": 9.771,
"loss_ce": 9.486519813537598,
"loss_region": 0.3685120940208435,
"loss_total": 9.855031967163086,
"lr": 0.0002180045871077028,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 90,
"tokens_trained": 0.294888136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.028368794326241134,
"grad_norm": 399.1022033691406,
"loss": 12.1846,
"loss_ce": 15.043132781982422,
"loss_region": 0.3677713871002197,
"loss_total": 15.410903930664062,
"lr": 0.00024249948453553463,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 100,
"tokens_trained": 0.327653576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.031205673758865248,
"grad_norm": 572.5389404296875,
"loss": 8.1413,
"loss_ce": 7.673736572265625,
"loss_region": 0.3677681088447571,
"loss_total": 8.041504859924316,
"lr": 0.00026699438196336637,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 110,
"tokens_trained": 0.360419016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.03404255319148936,
"grad_norm": 305.3782043457031,
"loss": 9.9432,
"loss_ce": 13.94490909576416,
"loss_region": 0.3664073050022125,
"loss_total": 14.31131649017334,
"lr": 0.00029148927939119814,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 120,
"tokens_trained": 0.393182856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.03687943262411347,
"grad_norm": 385.6461181640625,
"loss": 13.2327,
"loss_ce": 11.810239791870117,
"loss_region": 0.36761465668678284,
"loss_total": 12.177854537963867,
"lr": 0.00031598417681902996,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 130,
"tokens_trained": 0.425948296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.03971631205673759,
"grad_norm": 325.9845275878906,
"loss": 10.9926,
"loss_ce": 11.57892894744873,
"loss_region": 0.3681558072566986,
"loss_total": 11.947084426879883,
"lr": 0.00034047907424686173,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 140,
"tokens_trained": 0.458713736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.0425531914893617,
"grad_norm": 375.1774597167969,
"loss": 10.6799,
"loss_ce": 7.312507152557373,
"loss_region": 0.36791399121284485,
"loss_total": 7.680421352386475,
"lr": 0.0003649739716746935,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 150,
"tokens_trained": 0.491474616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.04539007092198582,
"grad_norm": 355.0230407714844,
"loss": 8.5176,
"loss_ce": 21.199607849121094,
"loss_region": 0.06011432409286499,
"loss_total": 21.259721755981445,
"lr": 0.00038946886910252526,
"router/selected_tokens_s0": 160.875,
"router/selected_tokens_s1": 1.0,
"step": 160,
"tokens_trained": 0.524240056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.04822695035460993,
"grad_norm": 273.1413269042969,
"loss": 13.482,
"loss_ce": 17.121381759643555,
"loss_region": 0.0692189484834671,
"loss_total": 17.190601348876953,
"lr": 0.0004139637665303571,
"router/selected_tokens_s0": 2280.5,
"router/selected_tokens_s1": 1.0,
"step": 170,
"tokens_trained": 0.557004696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.05106382978723404,
"grad_norm": 249.40753173828125,
"loss": 10.4567,
"loss_ce": 9.94619083404541,
"loss_region": 0.08772184699773788,
"loss_total": 10.033912658691406,
"lr": 0.0004384586639581888,
"router/selected_tokens_s0": 3865.125,
"router/selected_tokens_s1": 1.0,
"step": 180,
"tokens_trained": 0.589768376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.05390070921985816,
"grad_norm": 222.1225128173828,
"loss": 9.2011,
"loss_ce": 6.419787406921387,
"loss_region": 0.11581941694021225,
"loss_total": 6.535606861114502,
"lr": 0.0004629535613860206,
"router/selected_tokens_s0": 5891.0625,
"router/selected_tokens_s1": 1.0,
"step": 190,
"tokens_trained": 0.622533016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.05673758865248227,
"grad_norm": 206.31980895996094,
"loss": 3.1707,
"loss_ce": 3.6852493286132812,
"loss_region": 0.12171252071857452,
"loss_total": 3.80696177482605,
"lr": 0.00048744845881385244,
"router/selected_tokens_s0": 6350.1875,
"router/selected_tokens_s1": 1.0,
"step": 200,
"tokens_trained": 0.655298456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.059574468085106386,
"grad_norm": 196.80050659179688,
"loss": 2.8133,
"loss_ce": 3.34086275100708,
"loss_region": 0.10963311791419983,
"loss_total": 3.450495958328247,
"lr": 0.0005119433562416841,
"router/selected_tokens_s0": 5418.75,
"router/selected_tokens_s1": 1.0,
"step": 210,
"tokens_trained": 0.688063096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.062411347517730496,
"grad_norm": 197.86050415039062,
"loss": 3.5837,
"loss_ce": 6.36979341506958,
"loss_region": 0.11656106263399124,
"loss_total": 6.486354351043701,
"lr": 0.0005364382536695159,
"router/selected_tokens_s0": 5989.125,
"router/selected_tokens_s1": 1.0,
"step": 220,
"tokens_trained": 0.720828536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.06524822695035461,
"grad_norm": 207.3871307373047,
"loss": 5.6426,
"loss_ce": 7.008437633514404,
"loss_region": 0.12679478526115417,
"loss_total": 7.135232448577881,
"lr": 0.0005609331510973477,
"router/selected_tokens_s0": 6642.625,
"router/selected_tokens_s1": 1.0,
"step": 230,
"tokens_trained": 0.753593976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.06808510638297872,
"grad_norm": 93.20205688476562,
"loss": 6.2345,
"loss_ce": 4.154336929321289,
"loss_region": 0.3657049834728241,
"loss_total": 4.5200419425964355,
"lr": 0.0005854280485251795,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 240,
"tokens_trained": 0.786359416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.07092198581560284,
"grad_norm": 164.30181884765625,
"loss": 4.8424,
"loss_ce": 5.935614585876465,
"loss_region": 0.3678229749202728,
"loss_total": 6.30343770980835,
"lr": 0.0006099229459530113,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 250,
"tokens_trained": 0.819124856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.07375886524822695,
"grad_norm": 87.75625610351562,
"loss": 6.6223,
"loss_ce": 2.8206207752227783,
"loss_region": 0.36699220538139343,
"loss_total": 3.187613010406494,
"lr": 0.0006344178433808431,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 260,
"tokens_trained": 0.851889496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.07659574468085106,
"grad_norm": 91.14336395263672,
"loss": 3.8191,
"loss_ce": 4.011717796325684,
"loss_region": 0.3666604161262512,
"loss_total": 4.378378391265869,
"lr": 0.0006589127408086749,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 270,
"tokens_trained": 0.884654936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.07943262411347518,
"grad_norm": 139.20018005371094,
"loss": 3.5321,
"loss_ce": 3.950164556503296,
"loss_region": 0.3653871715068817,
"loss_total": 4.3155517578125,
"lr": 0.0006834076382365066,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 280,
"tokens_trained": 0.91742036
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.08226950354609928,
"grad_norm": 73.47037506103516,
"loss": 4.4399,
"loss_ce": 4.244175910949707,
"loss_region": 0.36372801661491394,
"loss_total": 4.607903957366943,
"lr": 0.0007079025356643384,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 290,
"tokens_trained": 0.9501858
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.0851063829787234,
"grad_norm": 96.47210693359375,
"loss": 5.3423,
"loss_ce": 3.720698833465576,
"loss_region": 0.3621433675289154,
"loss_total": 4.0828423500061035,
"lr": 0.0007323974330921702,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 300,
"tokens_trained": 0.98295124
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.08794326241134752,
"grad_norm": 51.55535888671875,
"loss": 4.7622,
"loss_ce": 3.124469757080078,
"loss_region": 0.36035263538360596,
"loss_total": 3.4848222732543945,
"lr": 0.000756892330520002,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 310,
"tokens_trained": 1.01571668
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.09078014184397164,
"grad_norm": 100.0770034790039,
"loss": 4.7539,
"loss_ce": 2.9495983123779297,
"loss_region": 0.0525033101439476,
"loss_total": 3.0021016597747803,
"lr": 0.0007813872279478337,
"router/selected_tokens_s0": 182.5625,
"router/selected_tokens_s1": 1.0,
"step": 320,
"tokens_trained": 1.04848196
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.09361702127659574,
"grad_norm": 55.15224075317383,
"loss": 2.6889,
"loss_ce": 2.26753830909729,
"loss_region": 0.17705734074115753,
"loss_total": 2.4445955753326416,
"lr": 0.0008058821253756655,
"router/selected_tokens_s0": 10099.1875,
"router/selected_tokens_s1": 1.0,
"step": 330,
"tokens_trained": 1.0812466
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.09645390070921986,
"grad_norm": 45.57613754272461,
"loss": 1.9699,
"loss_ce": 1.9211128950119019,
"loss_region": 0.06836946308612823,
"loss_total": 1.9894824028015137,
"lr": 0.0008303770228034974,
"router/selected_tokens_s0": 26.25,
"router/selected_tokens_s1": 1.0,
"step": 340,
"tokens_trained": 1.11401204
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.09929078014184398,
"grad_norm": 63.2139778137207,
"loss": 2.5665,
"loss_ce": 1.9517995119094849,
"loss_region": 0.12128585577011108,
"loss_total": 2.073085308074951,
"lr": 0.0008548719202313291,
"router/selected_tokens_s0": 6079.3125,
"router/selected_tokens_s1": 1.0,
"step": 350,
"tokens_trained": 1.14677748
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.10212765957446808,
"grad_norm": 19.581270217895508,
"loss": 2.433,
"loss_ce": 1.3946959972381592,
"loss_region": 0.10749296098947525,
"loss_total": 1.5021889209747314,
"lr": 0.0008793668176591608,
"router/selected_tokens_s0": 4936.9375,
"router/selected_tokens_s1": 1.0,
"step": 360,
"tokens_trained": 1.17954212
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1049645390070922,
"grad_norm": 74.17733764648438,
"loss": 3.503,
"loss_ce": 3.7360174655914307,
"loss_region": 0.08607521653175354,
"loss_total": 3.8220927715301514,
"lr": 0.0009038617150869926,
"router/selected_tokens_s0": 3165.4375,
"router/selected_tokens_s1": 1.0,
"step": 370,
"tokens_trained": 1.21230756
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.10780141843971631,
"grad_norm": 67.1612548828125,
"loss": 2.989,
"loss_ce": 3.997297525405884,
"loss_region": 0.18156586587429047,
"loss_total": 4.178863525390625,
"lr": 0.0009283566125148244,
"router/selected_tokens_s0": 10333.6875,
"router/selected_tokens_s1": 1.0625,
"step": 380,
"tokens_trained": 1.2450722
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11063829787234042,
"grad_norm": 84.84760284423828,
"loss": 2.8334,
"loss_ce": 3.0769035816192627,
"loss_region": 0.050393715500831604,
"loss_total": 3.1272974014282227,
"lr": 0.0009528515099426562,
"router/selected_tokens_s0": 52.9375,
"router/selected_tokens_s1": 1.0,
"step": 390,
"tokens_trained": 1.27783604
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11347517730496454,
"grad_norm": 63.6200065612793,
"loss": 3.1662,
"loss_ce": 2.779733180999756,
"loss_region": 0.10030720382928848,
"loss_total": 2.880040407180786,
"lr": 0.000977346407370488,
"router/selected_tokens_s0": 12.625,
"router/selected_tokens_s1": 1.0,
"step": 400,
"tokens_trained": 1.31060148
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11631205673758865,
"grad_norm": 72.42300415039062,
"loss": 2.8148,
"loss_ce": 2.7900760173797607,
"loss_region": 0.19263741374015808,
"loss_total": 2.982713460922241,
"lr": 0.0010018413047983197,
"router/selected_tokens_s0": 10859.0625,
"router/selected_tokens_s1": 1.0,
"step": 410,
"tokens_trained": 1.34336692
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11914893617021277,
"grad_norm": 40.36540603637695,
"loss": 2.6625,
"loss_ce": 1.7843694686889648,
"loss_region": 0.10816018283367157,
"loss_total": 1.8925296068191528,
"lr": 0.0010263362022261515,
"router/selected_tokens_s0": 5132.5625,
"router/selected_tokens_s1": 1.0,
"step": 420,
"tokens_trained": 1.37613236
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.12198581560283688,
"grad_norm": 57.87046813964844,
"loss": 2.1447,
"loss_ce": 2.605336904525757,
"loss_region": 0.1274668127298355,
"loss_total": 2.7328038215637207,
"lr": 0.0010508310996539833,
"router/selected_tokens_s0": 6691.0625,
"router/selected_tokens_s1": 1.0,
"step": 430,
"tokens_trained": 1.4088978
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.12482269503546099,
"grad_norm": 46.76475143432617,
"loss": 2.2982,
"loss_ce": 2.855947971343994,
"loss_region": 0.06147913262248039,
"loss_total": 2.9174270629882812,
"lr": 0.0010753259970818151,
"router/selected_tokens_s0": 1345.9375,
"router/selected_tokens_s1": 1.0,
"step": 440,
"tokens_trained": 1.44166324
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1276595744680851,
"grad_norm": 26.56728172302246,
"loss": 2.1202,
"loss_ce": 2.314136505126953,
"loss_region": 0.1346735656261444,
"loss_total": 2.44881010055542,
"lr": 0.001099820894509647,
"router/selected_tokens_s0": 7680.125,
"router/selected_tokens_s1": 1.0,
"step": 450,
"tokens_trained": 1.47442868
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13049645390070921,
"grad_norm": 31.932329177856445,
"loss": 2.6495,
"loss_ce": 1.6046358346939087,
"loss_region": 0.07332747429609299,
"loss_total": 1.6779632568359375,
"lr": 0.0011243157919374788,
"router/selected_tokens_s0": 2986.0,
"router/selected_tokens_s1": 1.0,
"step": 460,
"tokens_trained": 1.50719412
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13333333333333333,
"grad_norm": 40.14197540283203,
"loss": 2.5686,
"loss_ce": 2.384312629699707,
"loss_region": 0.09212882071733475,
"loss_total": 2.4764413833618164,
"lr": 0.0011488106893653104,
"router/selected_tokens_s0": 4881.3125,
"router/selected_tokens_s1": 1.0,
"step": 470,
"tokens_trained": 1.53995956
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13617021276595745,
"grad_norm": 40.96647644042969,
"loss": 2.1554,
"loss_ce": 2.062847852706909,
"loss_region": 0.08483830839395523,
"loss_total": 2.147686243057251,
"lr": 0.0011733055867931422,
"router/selected_tokens_s0": 4314.5,
"router/selected_tokens_s1": 1.0,
"step": 480,
"tokens_trained": 1.5727242
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13900709219858157,
"grad_norm": 58.40409469604492,
"loss": 2.0697,
"loss_ce": 2.608842134475708,
"loss_region": 0.12910506129264832,
"loss_total": 2.7379472255706787,
"lr": 0.001197800484220974,
"router/selected_tokens_s0": 7422.8125,
"router/selected_tokens_s1": 1.0,
"step": 490,
"tokens_trained": 1.60548964
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.14184397163120568,
"grad_norm": 25.093971252441406,
"loss": 2.0358,
"loss_ce": 1.524597406387329,
"loss_region": 0.08822071552276611,
"loss_total": 1.6128181219100952,
"lr": 0.0012222953816488059,
"router/selected_tokens_s0": 4142.625,
"router/selected_tokens_s1": 1.0,
"step": 500,
"tokens_trained": 1.638252944
},
{
"epoch": 0.14184397163120568,
"eval_ppl": 5.238461214674061,
"eval_runtime": 2.1242,
"step": 500,
"tokens_trained": 1.638252944
},
{
"epoch": 0.14184397163120568,
"eval_F": 7.813110399249941e-05,
"eval_F_cds": 2.695175635612254e-05,
"eval_F_dig": 7.813110399249941e-05,
"eval_F_exon": 8.154278957883149e-05,
"eval_F_intron": 9.008829419540036e-05,
"eval_F_nig": 8.194492915137831e-05,
"eval_F_promoter": 3.947950224243573e-05,
"eval_F_utr": 7.461016190405133e-05,
"eval_G": 0.09749281352746117,
"eval_G_cds": 0.09038638220397988,
"eval_G_dig": 0.11551821065122275,
"eval_G_exon": 0.09913527481618896,
"eval_G_intron": 0.09883524461080323,
"eval_G_nig": 0.10110245416326033,
"eval_G_promoter": 0.08840385852915167,
"eval_G_utr": 0.09609994947160018,
"eval_avg_bp_per_token": 12799.0,
"eval_bp_per_token/cds": 37103.333333333336,
"eval_bp_per_token/dig": 12799.0,
"eval_bp_per_token/exon": 12263.5,
"eval_bp_per_token/intron": 11100.221276595745,
"eval_bp_per_token/nig": 12203.317647058824,
"eval_bp_per_token/promoter": 25329.6,
"eval_bp_per_token/utr": 13403.0,
"eval_ppl_cds": 5.197959664020222,
"eval_ppl_dig": 5.7282999910686785,
"eval_ppl_exon": 5.2613736013319095,
"eval_ppl_intron": 5.244331873829972,
"eval_ppl_nig": 5.31566409531509,
"eval_ppl_promoter": 5.143870486889258,
"eval_ppl_utr": 5.205834202019033,
"step": 500,
"tokens_trained": 1.638252944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.14468085106382977,
"grad_norm": 36.171993255615234,
"loss": 1.7069,
"loss_ce": 1.6758953332901,
"loss_region": 0.07858321815729141,
"loss_total": 1.7544785737991333,
"lr": 0.0012243786686061229,
"router/selected_tokens_s0": 3400.3125,
"router/selected_tokens_s1": 1.0,
"step": 510,
"tokens_trained": 1.671014152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1475177304964539,
"grad_norm": 33.956119537353516,
"loss": 1.6551,
"loss_ce": 1.5848710536956787,
"loss_region": 0.06811508536338806,
"loss_total": 1.6529861688613892,
"lr": 0.0012239717766222718,
"router/selected_tokens_s0": 2687.4375,
"router/selected_tokens_s1": 1.0,
"step": 520,
"tokens_trained": 1.703779592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.150354609929078,
"grad_norm": 28.901918411254883,
"loss": 1.6154,
"loss_ce": 1.5558669567108154,
"loss_region": 0.07830837368965149,
"loss_total": 1.6341753005981445,
"lr": 0.001223564884638421,
"router/selected_tokens_s0": 3778.375,
"router/selected_tokens_s1": 1.5,
"step": 530,
"tokens_trained": 1.736545032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.15319148936170213,
"grad_norm": 16.806047439575195,
"loss": 1.6273,
"loss_ce": 1.399499535560608,
"loss_region": 0.08511029928922653,
"loss_total": 1.484609842300415,
"lr": 0.00122315799265457,
"router/selected_tokens_s0": 4515.25,
"router/selected_tokens_s1": 1.1875,
"step": 540,
"tokens_trained": 1.769310472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.15602836879432624,
"grad_norm": 22.434467315673828,
"loss": 1.5519,
"loss_ce": 1.454548716545105,
"loss_region": 0.06522653251886368,
"loss_total": 1.5197752714157104,
"lr": 0.001222751100670719,
"router/selected_tokens_s0": 2753.5,
"router/selected_tokens_s1": 1.25,
"step": 550,
"tokens_trained": 1.802075912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.15886524822695036,
"grad_norm": 20.20318603515625,
"loss": 1.5147,
"loss_ce": 1.388825535774231,
"loss_region": 0.05828768387436867,
"loss_total": 1.447113275527954,
"lr": 0.001222344208686868,
"router/selected_tokens_s0": 2056.0,
"router/selected_tokens_s1": 1.0,
"step": 560,
"tokens_trained": 1.834841352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.16170212765957448,
"grad_norm": 28.31165885925293,
"loss": 1.5272,
"loss_ce": 1.5384010076522827,
"loss_region": 0.05947807803750038,
"loss_total": 1.5978790521621704,
"lr": 0.0012219373167030169,
"router/selected_tokens_s0": 2200.5,
"router/selected_tokens_s1": 1.0,
"step": 570,
"tokens_trained": 1.867606792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.16453900709219857,
"grad_norm": 17.549209594726562,
"loss": 1.494,
"loss_ce": 1.359383225440979,
"loss_region": 0.21121427416801453,
"loss_total": 1.570597529411316,
"lr": 0.0012215304247191658,
"router/selected_tokens_s0": 1947.6875,
"router/selected_tokens_s1": 1947.5625,
"step": 580,
"tokens_trained": 1.900370632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1673758865248227,
"grad_norm": 16.347366333007812,
"loss": 1.4343,
"loss_ce": 1.331540584564209,
"loss_region": 0.05151217430830002,
"loss_total": 1.3830527067184448,
"lr": 0.0012211235327353148,
"router/selected_tokens_s0": 1371.4375,
"router/selected_tokens_s1": 1.375,
"step": 590,
"tokens_trained": 1.933136072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1702127659574468,
"grad_norm": 20.583803176879883,
"loss": 1.3997,
"loss_ce": 1.466564416885376,
"loss_region": 0.054751571267843246,
"loss_total": 1.5213159322738647,
"lr": 0.0012207166407514638,
"router/selected_tokens_s0": 1821.1875,
"router/selected_tokens_s1": 2.0625,
"step": 600,
"tokens_trained": 1.965901512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17304964539007092,
"grad_norm": 28.91676139831543,
"loss": 1.8869,
"loss_ce": 1.7341006994247437,
"loss_region": 0.06411188840866089,
"loss_total": 1.7982125282287598,
"lr": 0.0012203097487676127,
"router/selected_tokens_s0": 2751.625,
"router/selected_tokens_s1": 1.0,
"step": 610,
"tokens_trained": 1.998666952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17588652482269504,
"grad_norm": 16.068174362182617,
"loss": 1.7234,
"loss_ce": 1.4155008792877197,
"loss_region": 0.10453462600708008,
"loss_total": 1.5200355052947998,
"lr": 0.0012199028567837617,
"router/selected_tokens_s0": 6356.5,
"router/selected_tokens_s1": 1.0,
"step": 620,
"tokens_trained": 2.031432392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17872340425531916,
"grad_norm": 12.171530723571777,
"loss": 1.4577,
"loss_ce": 1.3392314910888672,
"loss_region": 0.044366203248500824,
"loss_total": 1.383597731590271,
"lr": 0.0012194959647999107,
"router/selected_tokens_s0": 746.0,
"router/selected_tokens_s1": 1.0,
"step": 630,
"tokens_trained": 2.064197832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.18156028368794327,
"grad_norm": 14.937308311462402,
"loss": 1.5005,
"loss_ce": 1.3874304294586182,
"loss_region": 0.056757938116788864,
"loss_total": 1.4441883563995361,
"lr": 0.0012190890728160596,
"router/selected_tokens_s0": 1590.25,
"router/selected_tokens_s1": 62.5,
"step": 640,
"tokens_trained": 2.096963272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.18439716312056736,
"grad_norm": 15.287280082702637,
"loss": 1.468,
"loss_ce": 1.3241463899612427,
"loss_region": 0.052737943828105927,
"loss_total": 1.3768843412399292,
"lr": 0.0012186821808322086,
"router/selected_tokens_s0": 1661.375,
"router/selected_tokens_s1": 1.0,
"step": 650,
"tokens_trained": 2.129728712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.18723404255319148,
"grad_norm": 6.567054748535156,
"loss": 1.4058,
"loss_ce": 1.2686595916748047,
"loss_region": 0.04463791474699974,
"loss_total": 1.3132975101470947,
"lr": 0.0012182752888483576,
"router/selected_tokens_s0": 795.3125,
"router/selected_tokens_s1": 1.3125,
"step": 660,
"tokens_trained": 2.162494152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1900709219858156,
"grad_norm": 35.38864517211914,
"loss": 1.483,
"loss_ce": 1.6116914749145508,
"loss_region": 0.0765811875462532,
"loss_total": 1.6882727146148682,
"lr": 0.0012178683968645065,
"router/selected_tokens_s0": 4140.0,
"router/selected_tokens_s1": 7.625,
"step": 670,
"tokens_trained": 2.195259592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.19290780141843972,
"grad_norm": 19.182458877563477,
"loss": 1.6566,
"loss_ce": 1.384118676185608,
"loss_region": 0.050435055047273636,
"loss_total": 1.4345537424087524,
"lr": 0.0012174615048806555,
"router/selected_tokens_s0": 1329.1875,
"router/selected_tokens_s1": 1.0,
"step": 680,
"tokens_trained": 2.228025032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.19574468085106383,
"grad_norm": 19.877857208251953,
"loss": 1.4028,
"loss_ce": 1.4199568033218384,
"loss_region": 0.04767146706581116,
"loss_total": 1.4676282405853271,
"lr": 0.0012170546128968045,
"router/selected_tokens_s0": 1076.875,
"router/selected_tokens_s1": 1.625,
"step": 690,
"tokens_trained": 2.260790472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.19858156028368795,
"grad_norm": 16.101842880249023,
"loss": 1.3997,
"loss_ce": 1.364323616027832,
"loss_region": 0.06121417507529259,
"loss_total": 1.4255378246307373,
"lr": 0.0012166477209129534,
"router/selected_tokens_s0": 2551.3125,
"router/selected_tokens_s1": 1.5625,
"step": 700,
"tokens_trained": 2.293555912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20141843971631207,
"grad_norm": 22.22663688659668,
"loss": 1.3765,
"loss_ce": 1.3531076908111572,
"loss_region": 0.047868210822343826,
"loss_total": 1.4009759426116943,
"lr": 0.0012162408289291026,
"router/selected_tokens_s0": 1133.3125,
"router/selected_tokens_s1": 1.125,
"step": 710,
"tokens_trained": 2.326321352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20425531914893616,
"grad_norm": 31.300945281982422,
"loss": 1.4667,
"loss_ce": 1.442090630531311,
"loss_region": 0.07350843399763107,
"loss_total": 1.515599012374878,
"lr": 0.0012158339369452516,
"router/selected_tokens_s0": 3763.0625,
"router/selected_tokens_s1": 2.4375,
"step": 720,
"tokens_trained": 2.359086792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20709219858156028,
"grad_norm": 17.472919464111328,
"loss": 1.452,
"loss_ce": 1.3612605333328247,
"loss_region": 0.044522251933813095,
"loss_total": 1.4057828187942505,
"lr": 0.0012154270449614005,
"router/selected_tokens_s0": 111.875,
"router/selected_tokens_s1": 1.0,
"step": 730,
"tokens_trained": 2.391852232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2099290780141844,
"grad_norm": 23.76650047302246,
"loss": 1.4316,
"loss_ce": 1.5030287504196167,
"loss_region": 0.057180847972631454,
"loss_total": 1.5602096319198608,
"lr": 0.0012150201529775495,
"router/selected_tokens_s0": 2120.125,
"router/selected_tokens_s1": 1.8125,
"step": 740,
"tokens_trained": 2.424616064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2127659574468085,
"grad_norm": 8.664741516113281,
"loss": 1.3639,
"loss_ce": 1.2497303485870361,
"loss_region": 0.043838031589984894,
"loss_total": 1.2935683727264404,
"lr": 0.0012146132609936982,
"router/selected_tokens_s0": 625.625,
"router/selected_tokens_s1": 5.75,
"step": 750,
"tokens_trained": 2.457381496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.21560283687943263,
"grad_norm": 11.039902687072754,
"loss": 1.3213,
"loss_ce": 1.2822058200836182,
"loss_region": 0.06590178608894348,
"loss_total": 1.3481075763702393,
"lr": 0.0012142063690098472,
"router/selected_tokens_s0": 2828.875,
"router/selected_tokens_s1": 13.3125,
"step": 760,
"tokens_trained": 2.490146936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.21843971631205675,
"grad_norm": 12.05501937866211,
"loss": 1.3965,
"loss_ce": 1.312122106552124,
"loss_region": 0.17912708222866058,
"loss_total": 1.4912492036819458,
"lr": 0.0012137994770259962,
"router/selected_tokens_s0": 321.5,
"router/selected_tokens_s1": 284.0625,
"step": 770,
"tokens_trained": 2.522912376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22127659574468084,
"grad_norm": 19.33881378173828,
"loss": 1.3326,
"loss_ce": 1.362036943435669,
"loss_region": 0.06399328261613846,
"loss_total": 1.4260302782058716,
"lr": 0.0012133925850421454,
"router/selected_tokens_s0": 228.875,
"router/selected_tokens_s1": 2.5,
"step": 780,
"tokens_trained": 2.555677816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22411347517730495,
"grad_norm": 16.22661781311035,
"loss": 1.3875,
"loss_ce": 1.3392794132232666,
"loss_region": 0.047626323997974396,
"loss_total": 1.3869057893753052,
"lr": 0.0012129856930582943,
"router/selected_tokens_s0": 192.6875,
"router/selected_tokens_s1": 1.8125,
"step": 790,
"tokens_trained": 2.588443256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22695035460992907,
"grad_norm": 18.713428497314453,
"loss": 1.369,
"loss_ce": 1.3001604080200195,
"loss_region": 0.0622205026447773,
"loss_total": 1.362380862236023,
"lr": 0.0012125788010744433,
"router/selected_tokens_s0": 2593.3125,
"router/selected_tokens_s1": 1.1875,
"step": 800,
"tokens_trained": 2.621208696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2297872340425532,
"grad_norm": 21.459232330322266,
"loss": 1.4114,
"loss_ce": 1.3201086521148682,
"loss_region": 0.05014314129948616,
"loss_total": 1.3702517747879028,
"lr": 0.0012121719090905923,
"router/selected_tokens_s0": 1457.6875,
"router/selected_tokens_s1": 1.8125,
"step": 810,
"tokens_trained": 2.653974128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2326241134751773,
"grad_norm": 17.591365814208984,
"loss": 1.4042,
"loss_ce": 1.3406790494918823,
"loss_region": 0.07056135684251785,
"loss_total": 1.4112404584884644,
"lr": 0.0012117650171067412,
"router/selected_tokens_s0": 3305.5625,
"router/selected_tokens_s1": 1.875,
"step": 820,
"tokens_trained": 2.686739568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.23546099290780143,
"grad_norm": 12.04948616027832,
"loss": 1.3367,
"loss_ce": 1.2736438512802124,
"loss_region": 0.15874218940734863,
"loss_total": 1.432386040687561,
"lr": 0.0012113581251228902,
"router/selected_tokens_s0": 676.0,
"router/selected_tokens_s1": 474.0625,
"step": 830,
"tokens_trained": 2.719505008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.23829787234042554,
"grad_norm": 22.205650329589844,
"loss": 1.3664,
"loss_ce": 1.3812791109085083,
"loss_region": 0.045553792268037796,
"loss_total": 1.426832914352417,
"lr": 0.0012109512331390391,
"router/selected_tokens_s0": 1017.8125,
"router/selected_tokens_s1": 2.25,
"step": 840,
"tokens_trained": 2.752270448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24113475177304963,
"grad_norm": 13.030964851379395,
"loss": 1.3782,
"loss_ce": 1.2519162893295288,
"loss_region": 0.1624305546283722,
"loss_total": 1.4143468141555786,
"lr": 0.0012105443411551881,
"router/selected_tokens_s0": 917.4375,
"router/selected_tokens_s1": 681.625,
"step": 850,
"tokens_trained": 2.785035888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24397163120567375,
"grad_norm": 7.984014511108398,
"loss": 1.3127,
"loss_ce": 1.2660592794418335,
"loss_region": 0.04773706942796707,
"loss_total": 1.3137964010238647,
"lr": 0.001210137449171337,
"router/selected_tokens_s0": 1192.9375,
"router/selected_tokens_s1": 1.8125,
"step": 860,
"tokens_trained": 2.817797816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24680851063829787,
"grad_norm": 4.871339797973633,
"loss": 1.2833,
"loss_ce": 1.2215490341186523,
"loss_region": 0.05293113738298416,
"loss_total": 1.2744802236557007,
"lr": 0.001209730557187486,
"router/selected_tokens_s0": 1671.6875,
"router/selected_tokens_s1": 3.5625,
"step": 870,
"tokens_trained": 2.850563256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24964539007092199,
"grad_norm": 3.742021083831787,
"loss": 1.2882,
"loss_ce": 1.2314670085906982,
"loss_region": 0.04821491986513138,
"loss_total": 1.279681921005249,
"lr": 0.001209323665203635,
"router/selected_tokens_s0": 1251.0625,
"router/selected_tokens_s1": 3.0,
"step": 880,
"tokens_trained": 2.883328696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2524822695035461,
"grad_norm": 9.155281066894531,
"loss": 1.2934,
"loss_ce": 1.2408264875411987,
"loss_region": 0.04964429885149002,
"loss_total": 1.290470838546753,
"lr": 0.001208916773219784,
"router/selected_tokens_s0": 1380.125,
"router/selected_tokens_s1": 3.5625,
"step": 890,
"tokens_trained": 2.916094136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2553191489361702,
"grad_norm": 9.283857345581055,
"loss": 1.2886,
"loss_ce": 1.2425544261932373,
"loss_region": 0.043535713106393814,
"loss_total": 1.2860901355743408,
"lr": 0.001208509881235933,
"router/selected_tokens_s0": 811.5625,
"router/selected_tokens_s1": 1.0625,
"step": 900,
"tokens_trained": 2.948859576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2581560283687943,
"grad_norm": 13.81477165222168,
"loss": 1.3118,
"loss_ce": 1.2899353504180908,
"loss_region": 0.18143458664417267,
"loss_total": 1.471369981765747,
"lr": 0.001208102989252082,
"router/selected_tokens_s0": 833.1875,
"router/selected_tokens_s1": 739.5,
"step": 910,
"tokens_trained": 2.981619384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.26099290780141843,
"grad_norm": 10.127344131469727,
"loss": 1.3015,
"loss_ce": 1.2317105531692505,
"loss_region": 0.04436146095395088,
"loss_total": 1.2760720252990723,
"lr": 0.0012076960972682309,
"router/selected_tokens_s0": 756.25,
"router/selected_tokens_s1": 7.0625,
"step": 920,
"tokens_trained": 3.014384824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.26382978723404255,
"grad_norm": 7.185147285461426,
"loss": 1.2804,
"loss_ce": 1.2676362991333008,
"loss_region": 0.04398803040385246,
"loss_total": 1.31162428855896,
"lr": 0.0012072892052843798,
"router/selected_tokens_s0": 752.4375,
"router/selected_tokens_s1": 4.0,
"step": 930,
"tokens_trained": 3.047149464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.26666666666666666,
"grad_norm": 8.473845481872559,
"loss": 1.298,
"loss_ce": 1.2457917928695679,
"loss_region": 0.053872235119342804,
"loss_total": 1.29966402053833,
"lr": 0.0012068823133005288,
"router/selected_tokens_s0": 1438.5,
"router/selected_tokens_s1": 41.3125,
"step": 940,
"tokens_trained": 3.079914904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2695035460992908,
"grad_norm": 9.972776412963867,
"loss": 1.3166,
"loss_ce": 1.1854572296142578,
"loss_region": 0.04348060116171837,
"loss_total": 1.2289378643035889,
"lr": 0.0012064754213166778,
"router/selected_tokens_s0": 766.75,
"router/selected_tokens_s1": 2.1875,
"step": 950,
"tokens_trained": 3.112675728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2723404255319149,
"grad_norm": 7.5483622550964355,
"loss": 1.2805,
"loss_ce": 1.2480460405349731,
"loss_region": 0.06218457594513893,
"loss_total": 1.3102306127548218,
"lr": 0.001206068529332827,
"router/selected_tokens_s0": 1183.125,
"router/selected_tokens_s1": 123.9375,
"step": 960,
"tokens_trained": 3.145441168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.275177304964539,
"grad_norm": 2.173365354537964,
"loss": 1.2747,
"loss_ce": 1.206543207168579,
"loss_region": 0.13238129019737244,
"loss_total": 1.338924527168274,
"lr": 0.001205661637348976,
"router/selected_tokens_s0": 1298.875,
"router/selected_tokens_s1": 719.6875,
"step": 970,
"tokens_trained": 3.178206608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.27801418439716313,
"grad_norm": 5.311792373657227,
"loss": 1.3034,
"loss_ce": 1.224631428718567,
"loss_region": 0.05017566680908203,
"loss_total": 1.274807095527649,
"lr": 0.0012052547453651249,
"router/selected_tokens_s0": 1392.0625,
"router/selected_tokens_s1": 13.5625,
"step": 980,
"tokens_trained": 3.210972048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.28085106382978725,
"grad_norm": 9.337197303771973,
"loss": 1.3066,
"loss_ce": 1.247117042541504,
"loss_region": 0.16016621887683868,
"loss_total": 1.4072833061218262,
"lr": 0.0012048478533812738,
"router/selected_tokens_s0": 650.6875,
"router/selected_tokens_s1": 484.5625,
"step": 990,
"tokens_trained": 3.243737488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.28368794326241137,
"grad_norm": 6.30027961730957,
"loss": 1.3249,
"loss_ce": 1.234486699104309,
"loss_region": 0.04393050819635391,
"loss_total": 1.2784172296524048,
"lr": 0.0012044409613974226,
"router/selected_tokens_s0": 834.9375,
"router/selected_tokens_s1": 1.5625,
"step": 1000,
"tokens_trained": 3.276502928
},
{
"epoch": 0.28368794326241137,
"eval_ppl": 3.482606606572146,
"eval_runtime": 2.0593,
"step": 1000,
"tokens_trained": 3.276502928
},
{
"epoch": 0.28368794326241137,
"eval_F": 0.0001322708635525194,
"eval_F_cds": 2.695175635612254e-05,
"eval_F_dig": 0.0008203765919212438,
"eval_F_exon": 0.00012231418436824723,
"eval_F_intron": 0.00014299120738248654,
"eval_F_nig": 0.00015232116242256205,
"eval_F_promoter": 6.843113722022193e-05,
"eval_F_utr": 7.461016190405133e-05,
"eval_G": 0.027253320926880115,
"eval_G_cds": 0.01253249651873147,
"eval_G_dig": 0.06213467604891007,
"eval_G_exon": 0.024896961978975552,
"eval_G_intron": 0.028342175683099283,
"eval_G_nig": 0.02919129746961289,
"eval_G_promoter": 0.022597925718165046,
"eval_G_utr": 0.023054706568891827,
"eval_avg_bp_per_token": 7560.243980738363,
"eval_bp_per_token/cds": 37103.333333333336,
"eval_bp_per_token/dig": 1218.952380952381,
"eval_bp_per_token/exon": 8175.666666666667,
"eval_bp_per_token/intron": 6993.436997319035,
"eval_bp_per_token/nig": 6565.0759493670885,
"eval_bp_per_token/promoter": 14613.23076923077,
"eval_bp_per_token/utr": 13403.0,
"eval_ppl_cds": 3.943436136880756,
"eval_ppl_dig": 3.176018188461278,
"eval_ppl_exon": 3.6071938696456316,
"eval_ppl_intron": 3.4512226027500135,
"eval_ppl_nig": 3.448745566665228,
"eval_ppl_promoter": 3.613322540752091,
"eval_ppl_utr": 3.6552658587709104,
"step": 1000,
"tokens_trained": 3.276502928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2865248226950355,
"grad_norm": 11.638834953308105,
"loss": 1.2968,
"loss_ce": 1.2562685012817383,
"loss_region": 0.060554198920726776,
"loss_total": 1.3168226480484009,
"lr": 0.0012040340694135716,
"router/selected_tokens_s0": 1682.25,
"router/selected_tokens_s1": 97.0625,
"step": 1010,
"tokens_trained": 3.309267568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.28936170212765955,
"grad_norm": 5.937789440155029,
"loss": 1.2905,
"loss_ce": 1.187785029411316,
"loss_region": 0.04547436535358429,
"loss_total": 1.2332594394683838,
"lr": 0.0012036271774297205,
"router/selected_tokens_s0": 1010.0625,
"router/selected_tokens_s1": 1.4375,
"step": 1020,
"tokens_trained": 3.342033008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.29219858156028367,
"grad_norm": 3.617494583129883,
"loss": 1.2825,
"loss_ce": 1.1796470880508423,
"loss_region": 0.0736464411020279,
"loss_total": 1.253293514251709,
"lr": 0.0012032202854458697,
"router/selected_tokens_s0": 1146.0,
"router/selected_tokens_s1": 199.1875,
"step": 1030,
"tokens_trained": 3.374798448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2950354609929078,
"grad_norm": 2.3506853580474854,
"loss": 1.2695,
"loss_ce": 1.18293035030365,
"loss_region": 0.04785334691405296,
"loss_total": 1.2307837009429932,
"lr": 0.0012028133934620187,
"router/selected_tokens_s0": 1239.75,
"router/selected_tokens_s1": 3.0625,
"step": 1040,
"tokens_trained": 3.407563888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2978723404255319,
"grad_norm": 6.109251499176025,
"loss": 1.2707,
"loss_ce": 1.2379461526870728,
"loss_region": 0.045713216066360474,
"loss_total": 1.2836593389511108,
"lr": 0.0012024065014781676,
"router/selected_tokens_s0": 1013.0,
"router/selected_tokens_s1": 2.5625,
"step": 1050,
"tokens_trained": 3.440328528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.300709219858156,
"grad_norm": 3.1301839351654053,
"loss": 1.2889,
"loss_ce": 1.2027920484542847,
"loss_region": 0.16526439785957336,
"loss_total": 1.3680564165115356,
"lr": 0.0012019996094943166,
"router/selected_tokens_s0": 473.25,
"router/selected_tokens_s1": 370.125,
"step": 1060,
"tokens_trained": 3.473093968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.30354609929078014,
"grad_norm": 4.692104816436768,
"loss": 1.2901,
"loss_ce": 1.2338565587997437,
"loss_region": 0.04492371156811714,
"loss_total": 1.278780221939087,
"lr": 0.0012015927175104656,
"router/selected_tokens_s0": 879.5,
"router/selected_tokens_s1": 4.0625,
"step": 1070,
"tokens_trained": 3.505859408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.30638297872340425,
"grad_norm": 3.102351188659668,
"loss": 1.2657,
"loss_ce": 1.2443020343780518,
"loss_region": 0.05263407900929451,
"loss_total": 1.2969361543655396,
"lr": 0.0012011858255266145,
"router/selected_tokens_s0": 1711.9375,
"router/selected_tokens_s1": 5.3125,
"step": 1080,
"tokens_trained": 3.538624848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.30921985815602837,
"grad_norm": 5.832976341247559,
"loss": 1.294,
"loss_ce": 1.2071852684020996,
"loss_region": 0.04505143314599991,
"loss_total": 1.2522367238998413,
"lr": 0.0012007789335427635,
"router/selected_tokens_s0": 877.1875,
"router/selected_tokens_s1": 5.125,
"step": 1090,
"tokens_trained": 3.571390288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3120567375886525,
"grad_norm": 2.2769346237182617,
"loss": 1.256,
"loss_ce": 1.1854358911514282,
"loss_region": 0.044262707233428955,
"loss_total": 1.229698657989502,
"lr": 0.0012003720415589125,
"router/selected_tokens_s0": 823.875,
"router/selected_tokens_s1": 2.1875,
"step": 1100,
"tokens_trained": 3.604155728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3148936170212766,
"grad_norm": 3.1605770587921143,
"loss": 1.234,
"loss_ce": 1.1617177724838257,
"loss_region": 0.04650801420211792,
"loss_total": 1.2082257270812988,
"lr": 0.0011999651495750614,
"router/selected_tokens_s0": 1039.4375,
"router/selected_tokens_s1": 8.5625,
"step": 1110,
"tokens_trained": 3.636921168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3177304964539007,
"grad_norm": 4.28217077255249,
"loss": 1.244,
"loss_ce": 1.1768839359283447,
"loss_region": 0.04629362002015114,
"loss_total": 1.2231775522232056,
"lr": 0.0011995582575912104,
"router/selected_tokens_s0": 1077.6875,
"router/selected_tokens_s1": 3.125,
"step": 1120,
"tokens_trained": 3.669686584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.32056737588652484,
"grad_norm": 3.1309468746185303,
"loss": 1.2511,
"loss_ce": 1.1429551839828491,
"loss_region": 0.04654176905751228,
"loss_total": 1.1894969940185547,
"lr": 0.0011991513656073594,
"router/selected_tokens_s0": 909.5,
"router/selected_tokens_s1": 10.25,
"step": 1130,
"tokens_trained": 3.702452024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.32340425531914896,
"grad_norm": 3.077151298522949,
"loss": 1.2317,
"loss_ce": 1.1686514616012573,
"loss_region": 0.047968540340662,
"loss_total": 1.2166199684143066,
"lr": 0.0011987444736235083,
"router/selected_tokens_s0": 1251.25,
"router/selected_tokens_s1": 3.625,
"step": 1140,
"tokens_trained": 3.735217464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3262411347517731,
"grad_norm": 2.451178789138794,
"loss": 1.249,
"loss_ce": 1.2107584476470947,
"loss_region": 0.07213801145553589,
"loss_total": 1.2828965187072754,
"lr": 0.0011983375816396573,
"router/selected_tokens_s0": 1354.875,
"router/selected_tokens_s1": 211.875,
"step": 1150,
"tokens_trained": 3.767982904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.32907801418439714,
"grad_norm": 5.528106689453125,
"loss": 1.2417,
"loss_ce": 1.1774345636367798,
"loss_region": 0.049906354397535324,
"loss_total": 1.2273409366607666,
"lr": 0.0011979306896558062,
"router/selected_tokens_s0": 1311.375,
"router/selected_tokens_s1": 18.375,
"step": 1160,
"tokens_trained": 3.800748344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.33191489361702126,
"grad_norm": 2.824122667312622,
"loss": 1.2461,
"loss_ce": 1.1278353929519653,
"loss_region": 0.05486295744776726,
"loss_total": 1.182698369026184,
"lr": 0.0011975237976719552,
"router/selected_tokens_s0": 1045.125,
"router/selected_tokens_s1": 62.1875,
"step": 1170,
"tokens_trained": 3.833513784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3347517730496454,
"grad_norm": 7.002549171447754,
"loss": 1.2696,
"loss_ce": 1.245290994644165,
"loss_region": 0.05316196009516716,
"loss_total": 1.2984529733657837,
"lr": 0.0011971169056881042,
"router/selected_tokens_s0": 1337.0,
"router/selected_tokens_s1": 41.9375,
"step": 1180,
"tokens_trained": 3.866278424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3375886524822695,
"grad_norm": 3.7295656204223633,
"loss": 1.2499,
"loss_ce": 1.124242901802063,
"loss_region": 0.058403585106134415,
"loss_total": 1.1826465129852295,
"lr": 0.0011967100137042531,
"router/selected_tokens_s0": 1535.5,
"router/selected_tokens_s1": 107.8125,
"step": 1190,
"tokens_trained": 3.899043864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3404255319148936,
"grad_norm": 3.8166322708129883,
"loss": 1.2437,
"loss_ce": 1.1664611101150513,
"loss_region": 0.06889785826206207,
"loss_total": 1.2353589534759521,
"lr": 0.0011963031217204021,
"router/selected_tokens_s0": 952.4375,
"router/selected_tokens_s1": 147.5,
"step": 1200,
"tokens_trained": 3.931809304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3432624113475177,
"grad_norm": 3.671513080596924,
"loss": 1.2376,
"loss_ce": 1.2160379886627197,
"loss_region": 0.06595063954591751,
"loss_total": 1.2819886207580566,
"lr": 0.0011958962297365513,
"router/selected_tokens_s0": 921.4375,
"router/selected_tokens_s1": 125.75,
"step": 1210,
"tokens_trained": 3.964574744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.34609929078014184,
"grad_norm": 5.063389778137207,
"loss": 1.2304,
"loss_ce": 1.187891960144043,
"loss_region": 0.05452219769358635,
"loss_total": 1.242414116859436,
"lr": 0.0011954893377527003,
"router/selected_tokens_s0": 1445.0,
"router/selected_tokens_s1": 50.5,
"step": 1220,
"tokens_trained": 3.997337592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.34893617021276596,
"grad_norm": 3.887139320373535,
"loss": 1.2444,
"loss_ce": 1.176914930343628,
"loss_region": 0.1330278515815735,
"loss_total": 1.3099427223205566,
"lr": 0.0011950824457688492,
"router/selected_tokens_s0": 1880.9375,
"router/selected_tokens_s1": 972.0625,
"step": 1230,
"tokens_trained": 4.030103032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3517730496453901,
"grad_norm": 5.268446922302246,
"loss": 1.2329,
"loss_ce": 1.1647382974624634,
"loss_region": 0.04794379696249962,
"loss_total": 1.2126821279525757,
"lr": 0.0011946755537849982,
"router/selected_tokens_s0": 1246.9375,
"router/selected_tokens_s1": 5.8125,
"step": 1240,
"tokens_trained": 4.062868472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3546099290780142,
"grad_norm": 2.72017765045166,
"loss": 1.231,
"loss_ce": 1.1569784879684448,
"loss_region": 0.04461895301938057,
"loss_total": 1.2015974521636963,
"lr": 0.001194268661801147,
"router/selected_tokens_s0": 858.125,
"router/selected_tokens_s1": 2.4375,
"step": 1250,
"tokens_trained": 4.095633912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3574468085106383,
"grad_norm": 2.106952428817749,
"loss": 1.2326,
"loss_ce": 1.139892339706421,
"loss_region": 0.046058911830186844,
"loss_total": 1.1859512329101562,
"lr": 0.001193861769817296,
"router/selected_tokens_s0": 921.5,
"router/selected_tokens_s1": 8.6875,
"step": 1260,
"tokens_trained": 4.128399352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36028368794326243,
"grad_norm": 4.2245659828186035,
"loss": 1.2321,
"loss_ce": 1.185473918914795,
"loss_region": 0.04969760775566101,
"loss_total": 1.2351715564727783,
"lr": 0.0011934548778334449,
"router/selected_tokens_s0": 731.8125,
"router/selected_tokens_s1": 27.0,
"step": 1270,
"tokens_trained": 4.161163992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36312056737588655,
"grad_norm": 3.381363868713379,
"loss": 1.2321,
"loss_ce": 1.221541404724121,
"loss_region": 0.050035104155540466,
"loss_total": 1.2715765237808228,
"lr": 0.001193047985849594,
"router/selected_tokens_s0": 1033.125,
"router/selected_tokens_s1": 29.875,
"step": 1280,
"tokens_trained": 4.193929432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3659574468085106,
"grad_norm": 5.191988468170166,
"loss": 1.2362,
"loss_ce": 1.2151143550872803,
"loss_region": 0.04746318981051445,
"loss_total": 1.2625775337219238,
"lr": 0.001192641093865743,
"router/selected_tokens_s0": 889.4375,
"router/selected_tokens_s1": 17.5,
"step": 1290,
"tokens_trained": 4.226694872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36879432624113473,
"grad_norm": 1.7778940200805664,
"loss": 1.2405,
"loss_ce": 1.1877528429031372,
"loss_region": 0.05633685365319252,
"loss_total": 1.2440897226333618,
"lr": 0.001192234201881892,
"router/selected_tokens_s0": 1150.3125,
"router/selected_tokens_s1": 73.875,
"step": 1300,
"tokens_trained": 4.259455304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.37163120567375885,
"grad_norm": 4.316074371337891,
"loss": 1.2248,
"loss_ce": 1.1520181894302368,
"loss_region": 0.052013058215379715,
"loss_total": 1.204031229019165,
"lr": 0.001191827309898041,
"router/selected_tokens_s0": 1502.0,
"router/selected_tokens_s1": 21.5,
"step": 1310,
"tokens_trained": 4.292217888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.37446808510638296,
"grad_norm": 3.6426265239715576,
"loss": 1.2266,
"loss_ce": 1.172141432762146,
"loss_region": 0.05179239809513092,
"loss_total": 1.2239338159561157,
"lr": 0.00119142041791419,
"router/selected_tokens_s0": 1641.5625,
"router/selected_tokens_s1": 12.375,
"step": 1320,
"tokens_trained": 4.324979816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3773049645390071,
"grad_norm": 2.515777587890625,
"loss": 1.2224,
"loss_ce": 1.098609209060669,
"loss_region": 0.049831029027700424,
"loss_total": 1.1484402418136597,
"lr": 0.0011910135259303389,
"router/selected_tokens_s0": 1349.75,
"router/selected_tokens_s1": 16.375,
"step": 1330,
"tokens_trained": 4.357745256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3801418439716312,
"grad_norm": 1.4164339303970337,
"loss": 1.2221,
"loss_ce": 1.1411010026931763,
"loss_region": 0.08194732666015625,
"loss_total": 1.2230483293533325,
"lr": 0.0011906066339464878,
"router/selected_tokens_s0": 1443.875,
"router/selected_tokens_s1": 315.6875,
"step": 1340,
"tokens_trained": 4.390510696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3829787234042553,
"grad_norm": 0.7069838047027588,
"loss": 1.211,
"loss_ce": 1.1557698249816895,
"loss_region": 0.04843400791287422,
"loss_total": 1.2042038440704346,
"lr": 0.0011901997419626368,
"router/selected_tokens_s0": 1291.625,
"router/selected_tokens_s1": 6.375,
"step": 1350,
"tokens_trained": 4.423276136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.38581560283687943,
"grad_norm": 1.344914436340332,
"loss": 1.2166,
"loss_ce": 1.1191163063049316,
"loss_region": 0.05032026395201683,
"loss_total": 1.1694365739822388,
"lr": 0.0011897928499787858,
"router/selected_tokens_s0": 1199.625,
"router/selected_tokens_s1": 33.3125,
"step": 1360,
"tokens_trained": 4.456041576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.38865248226950355,
"grad_norm": 0.5033648610115051,
"loss": 1.2192,
"loss_ce": 1.1610416173934937,
"loss_region": 0.053894009441137314,
"loss_total": 1.2149356603622437,
"lr": 0.0011893859579949347,
"router/selected_tokens_s0": 1109.625,
"router/selected_tokens_s1": 58.6875,
"step": 1370,
"tokens_trained": 4.488807016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.39148936170212767,
"grad_norm": 1.1606615781784058,
"loss": 1.2223,
"loss_ce": 1.110776424407959,
"loss_region": 0.051735769957304,
"loss_total": 1.162512183189392,
"lr": 0.0011889790660110837,
"router/selected_tokens_s0": 1187.5625,
"router/selected_tokens_s1": 40.3125,
"step": 1380,
"tokens_trained": 4.521572456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3943262411347518,
"grad_norm": 4.230033874511719,
"loss": 1.2441,
"loss_ce": 1.173520803451538,
"loss_region": 0.060160037130117416,
"loss_total": 1.2336808443069458,
"lr": 0.0011885721740272327,
"router/selected_tokens_s0": 1960.1875,
"router/selected_tokens_s1": 84.4375,
"step": 1390,
"tokens_trained": 4.554337096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3971631205673759,
"grad_norm": 3.069769859313965,
"loss": 1.2342,
"loss_ce": 1.041337251663208,
"loss_region": 0.048631489276885986,
"loss_total": 1.0899686813354492,
"lr": 0.0011881652820433816,
"router/selected_tokens_s0": 1217.0,
"router/selected_tokens_s1": 14.1875,
"step": 1400,
"tokens_trained": 4.587102536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4,
"grad_norm": 3.1322920322418213,
"loss": 1.2287,
"loss_ce": 1.1824651956558228,
"loss_region": 0.058100152760744095,
"loss_total": 1.240565299987793,
"lr": 0.0011877583900595306,
"router/selected_tokens_s0": 1269.5625,
"router/selected_tokens_s1": 87.75,
"step": 1410,
"tokens_trained": 4.619867976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.40283687943262414,
"grad_norm": 3.767857074737549,
"loss": 1.2154,
"loss_ce": 1.2003581523895264,
"loss_region": 0.07572433352470398,
"loss_total": 1.2760825157165527,
"lr": 0.0011873514980756796,
"router/selected_tokens_s0": 1357.375,
"router/selected_tokens_s1": 241.75,
"step": 1420,
"tokens_trained": 4.652632616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4056737588652482,
"grad_norm": 2.0261361598968506,
"loss": 1.2207,
"loss_ce": 1.1732327938079834,
"loss_region": 0.0638844221830368,
"loss_total": 1.2371171712875366,
"lr": 0.0011869446060918285,
"router/selected_tokens_s0": 1132.5,
"router/selected_tokens_s1": 132.1875,
"step": 1430,
"tokens_trained": 4.685398056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4085106382978723,
"grad_norm": 1.6216543912887573,
"loss": 1.2201,
"loss_ce": 1.154977560043335,
"loss_region": 0.04831705614924431,
"loss_total": 1.2032946348190308,
"lr": 0.0011865377141079775,
"router/selected_tokens_s0": 1138.3125,
"router/selected_tokens_s1": 15.125,
"step": 1440,
"tokens_trained": 4.718163496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.41134751773049644,
"grad_norm": 1.2403500080108643,
"loss": 1.2158,
"loss_ce": 1.1079224348068237,
"loss_region": 0.049330513924360275,
"loss_total": 1.1572529077529907,
"lr": 0.0011861308221241265,
"router/selected_tokens_s0": 1109.0,
"router/selected_tokens_s1": 22.5625,
"step": 1450,
"tokens_trained": 4.750928936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.41418439716312055,
"grad_norm": 1.9023810625076294,
"loss": 1.2098,
"loss_ce": 1.2203904390335083,
"loss_region": 0.08725684881210327,
"loss_total": 1.3076472282409668,
"lr": 0.0011857239301402756,
"router/selected_tokens_s0": 1068.0625,
"router/selected_tokens_s1": 285.8125,
"step": 1460,
"tokens_trained": 4.783694376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.41702127659574467,
"grad_norm": 1.0339922904968262,
"loss": 1.2123,
"loss_ce": 1.1580380201339722,
"loss_region": 0.04887384921312332,
"loss_total": 1.2069119215011597,
"lr": 0.0011853170381564246,
"router/selected_tokens_s0": 1223.0625,
"router/selected_tokens_s1": 14.75,
"step": 1470,
"tokens_trained": 4.816459816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4198581560283688,
"grad_norm": 1.122446060180664,
"loss": 1.2059,
"loss_ce": 1.1485178470611572,
"loss_region": 0.050783149898052216,
"loss_total": 1.19930100440979,
"lr": 0.0011849101461725736,
"router/selected_tokens_s0": 1172.8125,
"router/selected_tokens_s1": 31.8125,
"step": 1480,
"tokens_trained": 4.849225256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4226950354609929,
"grad_norm": 1.6927247047424316,
"loss": 1.212,
"loss_ce": 1.1878578662872314,
"loss_region": 0.048136983066797256,
"loss_total": 1.235994815826416,
"lr": 0.0011845032541887225,
"router/selected_tokens_s0": 1040.125,
"router/selected_tokens_s1": 16.5,
"step": 1490,
"tokens_trained": 4.881990696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.425531914893617,
"grad_norm": 1.4076164960861206,
"loss": 1.2102,
"loss_ce": 1.1968106031417847,
"loss_region": 0.05341554060578346,
"loss_total": 1.2502261400222778,
"lr": 0.0011840963622048713,
"router/selected_tokens_s0": 1112.4375,
"router/selected_tokens_s1": 51.1875,
"step": 1500,
"tokens_trained": 4.914756056
},
{
"epoch": 0.425531914893617,
"eval_ppl": 3.1645482791951447,
"eval_runtime": 2.0297,
"step": 1500,
"tokens_trained": 4.914756056
},
{
"epoch": 0.425531914893617,
"eval_F": 0.05049732146193486,
"eval_F_cds": 0.06451352079777199,
"eval_F_dig": 0.0033987030236737243,
"eval_F_exon": 0.05309794648074911,
"eval_F_intron": 0.04964938402608037,
"eval_F_nig": 0.04548039973700498,
"eval_F_promoter": 0.0584770387214958,
"eval_F_utr": 0.05909124822800865,
"eval_G": 0.043056454668858934,
"eval_G_cds": 0.040746177623304285,
"eval_G_dig": 0.0450969069849207,
"eval_G_exon": 0.04159826309611177,
"eval_G_intron": 0.043054627385231345,
"eval_G_nig": 0.042699612123318444,
"eval_G_promoter": 0.04411404367732481,
"eval_G_utr": 0.04181456160534422,
"eval_avg_bp_per_token": 19.803030557844636,
"eval_bp_per_token/cds": 15.500626653669405,
"eval_bp_per_token/dig": 294.2298850574713,
"eval_bp_per_token/exon": 18.83312004095214,
"eval_bp_per_token/intron": 20.141236787040683,
"eval_bp_per_token/nig": 21.987493640834323,
"eval_bp_per_token/promoter": 17.100729138536323,
"eval_bp_per_token/utr": 16.9229797979798,
"eval_ppl_cds": 3.7596792967573776,
"eval_ppl_dig": 1.3696206224046767,
"eval_ppl_exon": 3.370696369681706,
"eval_ppl_intron": 3.179431822437879,
"eval_ppl_nig": 3.065018439879573,
"eval_ppl_promoter": 3.3819504463651193,
"eval_ppl_utr": 3.457320751431464,
"step": 1500,
"tokens_trained": 4.914756056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.42836879432624114,
"grad_norm": 1.4229851961135864,
"loss": 1.2147,
"loss_ce": 1.1474426984786987,
"loss_region": 0.11874866485595703,
"loss_total": 1.2661913633346558,
"lr": 0.0011836894702210202,
"router/selected_tokens_s0": 1256.0,
"router/selected_tokens_s1": 587.125,
"step": 1510,
"tokens_trained": 4.947521496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.43120567375886526,
"grad_norm": 2.1784424781799316,
"loss": 1.2044,
"loss_ce": 1.176586627960205,
"loss_region": 0.04810425266623497,
"loss_total": 1.2246909141540527,
"lr": 0.0011832825782371692,
"router/selected_tokens_s0": 1154.0625,
"router/selected_tokens_s1": 11.1875,
"step": 1520,
"tokens_trained": 4.980286136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4340425531914894,
"grad_norm": 0.44625309109687805,
"loss": 1.2082,
"loss_ce": 1.1421223878860474,
"loss_region": 0.04860352724790573,
"loss_total": 1.1907259225845337,
"lr": 0.0011828756862533184,
"router/selected_tokens_s0": 1218.0625,
"router/selected_tokens_s1": 13.375,
"step": 1530,
"tokens_trained": 5.013051576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4368794326241135,
"grad_norm": 0.541300356388092,
"loss": 1.206,
"loss_ce": 1.1447055339813232,
"loss_region": 0.049634430557489395,
"loss_total": 1.1943399906158447,
"lr": 0.0011824687942694674,
"router/selected_tokens_s0": 1159.25,
"router/selected_tokens_s1": 23.4375,
"step": 1540,
"tokens_trained": 5.045813688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4397163120567376,
"grad_norm": 2.8496859073638916,
"loss": 1.2067,
"loss_ce": 1.0945407152175903,
"loss_region": 0.057181403040885925,
"loss_total": 1.1517220735549927,
"lr": 0.0011820619022856163,
"router/selected_tokens_s0": 1242.875,
"router/selected_tokens_s1": 81.8125,
"step": 1550,
"tokens_trained": 5.078578552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4425531914893617,
"grad_norm": 4.080273628234863,
"loss": 1.2214,
"loss_ce": 1.145821452140808,
"loss_region": 0.06584899872541428,
"loss_total": 1.2116703987121582,
"lr": 0.0011816550103017653,
"router/selected_tokens_s0": 1449.75,
"router/selected_tokens_s1": 161.375,
"step": 1560,
"tokens_trained": 5.111343992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4453900709219858,
"grad_norm": 2.364082098007202,
"loss": 1.2205,
"loss_ce": 1.2248941659927368,
"loss_region": 0.05984827131032944,
"loss_total": 1.2847424745559692,
"lr": 0.0011812481183179143,
"router/selected_tokens_s0": 1213.0,
"router/selected_tokens_s1": 101.8125,
"step": 1570,
"tokens_trained": 5.144109432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4482269503546099,
"grad_norm": 1.8271722793579102,
"loss": 1.2147,
"loss_ce": 1.1531490087509155,
"loss_region": 0.1430894285440445,
"loss_total": 1.2962384223937988,
"lr": 0.0011808412263340632,
"router/selected_tokens_s0": 1225.4375,
"router/selected_tokens_s1": 764.125,
"step": 1580,
"tokens_trained": 5.176874072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.451063829787234,
"grad_norm": 0.6056541800498962,
"loss": 1.2109,
"loss_ce": 1.139554738998413,
"loss_region": 0.05257788673043251,
"loss_total": 1.192132592201233,
"lr": 0.0011804343343502122,
"router/selected_tokens_s0": 1221.1875,
"router/selected_tokens_s1": 45.25,
"step": 1590,
"tokens_trained": 5.209639512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.45390070921985815,
"grad_norm": 1.3845616579055786,
"loss": 1.2054,
"loss_ce": 1.1697837114334106,
"loss_region": 0.05317477881908417,
"loss_total": 1.2229584455490112,
"lr": 0.0011800274423663611,
"router/selected_tokens_s0": 1122.25,
"router/selected_tokens_s1": 49.6875,
"step": 1600,
"tokens_trained": 5.242403352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.45673758865248226,
"grad_norm": 0.7946324944496155,
"loss": 1.204,
"loss_ce": 1.1398544311523438,
"loss_region": 0.0863887295126915,
"loss_total": 1.2262431383132935,
"lr": 0.0011796205503825101,
"router/selected_tokens_s0": 1121.625,
"router/selected_tokens_s1": 284.3125,
"step": 1610,
"tokens_trained": 5.275167992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4595744680851064,
"grad_norm": 1.388248085975647,
"loss": 1.2086,
"loss_ce": 1.1963084936141968,
"loss_region": 0.04745178297162056,
"loss_total": 1.2437602281570435,
"lr": 0.001179213658398659,
"router/selected_tokens_s0": 1122.8125,
"router/selected_tokens_s1": 7.625,
"step": 1620,
"tokens_trained": 5.307932632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4624113475177305,
"grad_norm": 1.0179280042648315,
"loss": 1.2065,
"loss_ce": 1.1650291681289673,
"loss_region": 0.047749392688274384,
"loss_total": 1.2127785682678223,
"lr": 0.001178806766414808,
"router/selected_tokens_s0": 1127.125,
"router/selected_tokens_s1": 9.625,
"step": 1630,
"tokens_trained": 5.340694016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4652482269503546,
"grad_norm": 0.6571646928787231,
"loss": 1.2057,
"loss_ce": 1.1609867811203003,
"loss_region": 0.05375194177031517,
"loss_total": 1.2147387266159058,
"lr": 0.001178399874430957,
"router/selected_tokens_s0": 1147.8125,
"router/selected_tokens_s1": 55.3125,
"step": 1640,
"tokens_trained": 5.373459456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.46808510638297873,
"grad_norm": 0.7328802347183228,
"loss": 1.2096,
"loss_ce": 1.1533145904541016,
"loss_region": 0.04775061458349228,
"loss_total": 1.201065182685852,
"lr": 0.001177992982447106,
"router/selected_tokens_s0": 1126.6875,
"router/selected_tokens_s1": 9.625,
"step": 1650,
"tokens_trained": 5.406224096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.47092198581560285,
"grad_norm": 2.1376028060913086,
"loss": 1.1969,
"loss_ce": 1.1875627040863037,
"loss_region": 0.06121131405234337,
"loss_total": 1.2487740516662598,
"lr": 0.001177586090463255,
"router/selected_tokens_s0": 1141.0,
"router/selected_tokens_s1": 111.25,
"step": 1660,
"tokens_trained": 5.438988736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.47375886524822697,
"grad_norm": 4.265078067779541,
"loss": 1.2112,
"loss_ce": 1.149315595626831,
"loss_region": 0.049465492367744446,
"loss_total": 1.198781132698059,
"lr": 0.001177179198479404,
"router/selected_tokens_s0": 1495.0625,
"router/selected_tokens_s1": 9.875,
"step": 1670,
"tokens_trained": 5.471754176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4765957446808511,
"grad_norm": 2.6948628425598145,
"loss": 1.222,
"loss_ce": 1.1160846948623657,
"loss_region": 0.05118577182292938,
"loss_total": 1.1672704219818115,
"lr": 0.0011767723064955529,
"router/selected_tokens_s0": 1128.25,
"router/selected_tokens_s1": 39.1875,
"step": 1680,
"tokens_trained": 5.504519616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4794326241134752,
"grad_norm": 1.4104028940200806,
"loss": 1.2114,
"loss_ce": 1.1637930870056152,
"loss_region": 0.05358956381678581,
"loss_total": 1.2173826694488525,
"lr": 0.0011763654145117018,
"router/selected_tokens_s0": 994.9375,
"router/selected_tokens_s1": 52.9375,
"step": 1690,
"tokens_trained": 5.537285056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.48226950354609927,
"grad_norm": 0.7200977206230164,
"loss": 1.2053,
"loss_ce": 1.1444610357284546,
"loss_region": 0.04805755242705345,
"loss_total": 1.1925185918807983,
"lr": 0.0011759585225278508,
"router/selected_tokens_s0": 1050.375,
"router/selected_tokens_s1": 14.0625,
"step": 1700,
"tokens_trained": 5.570050496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4851063829787234,
"grad_norm": 1.3361515998840332,
"loss": 1.2044,
"loss_ce": 1.1669089794158936,
"loss_region": 0.05295637622475624,
"loss_total": 1.219865322113037,
"lr": 0.001175551630544,
"router/selected_tokens_s0": 1105.625,
"router/selected_tokens_s1": 47.625,
"step": 1710,
"tokens_trained": 5.602815936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4879432624113475,
"grad_norm": 1.1902843713760376,
"loss": 1.2051,
"loss_ce": 1.1462538242340088,
"loss_region": 0.04917926713824272,
"loss_total": 1.1954331398010254,
"lr": 0.001175144738560149,
"router/selected_tokens_s0": 1159.9375,
"router/selected_tokens_s1": 20.625,
"step": 1720,
"tokens_trained": 5.635581376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4907801418439716,
"grad_norm": 0.38336893916130066,
"loss": 1.1996,
"loss_ce": 1.1662453413009644,
"loss_region": 0.0531914159655571,
"loss_total": 1.219436764717102,
"lr": 0.001174737846576298,
"router/selected_tokens_s0": 1226.1875,
"router/selected_tokens_s1": 49.9375,
"step": 1730,
"tokens_trained": 5.668346816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.49361702127659574,
"grad_norm": 1.0268887281417847,
"loss": 1.2059,
"loss_ce": 1.1835399866104126,
"loss_region": 0.050249867141246796,
"loss_total": 1.2337898015975952,
"lr": 0.0011743309545924469,
"router/selected_tokens_s0": 1129.75,
"router/selected_tokens_s1": 27.0625,
"step": 1740,
"tokens_trained": 5.701112256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.49645390070921985,
"grad_norm": 1.0396302938461304,
"loss": 1.2022,
"loss_ce": 1.1819915771484375,
"loss_region": 0.04947606101632118,
"loss_total": 1.231467604637146,
"lr": 0.0011739240626085956,
"router/selected_tokens_s0": 1276.6875,
"router/selected_tokens_s1": 19.0625,
"step": 1750,
"tokens_trained": 5.733877696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.49929078014184397,
"grad_norm": 1.0907139778137207,
"loss": 1.1996,
"loss_ce": 1.0990666151046753,
"loss_region": 0.058163322508335114,
"loss_total": 1.1572299003601074,
"lr": 0.0011735171706247446,
"router/selected_tokens_s0": 1144.0,
"router/selected_tokens_s1": 87.6875,
"step": 1760,
"tokens_trained": 5.766643136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.502127659574468,
"grad_norm": 1.3510611057281494,
"loss": 1.2023,
"loss_ce": 1.1430004835128784,
"loss_region": 0.051321737468242645,
"loss_total": 1.1943222284317017,
"lr": 0.0011731102786408936,
"router/selected_tokens_s0": 1124.75,
"router/selected_tokens_s1": 37.3125,
"step": 1770,
"tokens_trained": 5.799407776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5049645390070922,
"grad_norm": 1.4044612646102905,
"loss": 1.2061,
"loss_ce": 1.198064923286438,
"loss_region": 0.04685606434941292,
"loss_total": 1.2449209690093994,
"lr": 0.0011727033866570427,
"router/selected_tokens_s0": 1031.625,
"router/selected_tokens_s1": 5.75,
"step": 1780,
"tokens_trained": 5.832173216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5078014184397163,
"grad_norm": 1.5810678005218506,
"loss": 1.2003,
"loss_ce": 1.1610219478607178,
"loss_region": 0.049070414155721664,
"loss_total": 1.210092306137085,
"lr": 0.0011722964946731917,
"router/selected_tokens_s0": 1013.5,
"router/selected_tokens_s1": 20.6875,
"step": 1790,
"tokens_trained": 5.864938656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5106382978723404,
"grad_norm": 1.0402437448501587,
"loss": 1.2,
"loss_ce": 1.1509393453598022,
"loss_region": 0.08059847354888916,
"loss_total": 1.2315378189086914,
"lr": 0.0011718896026893407,
"router/selected_tokens_s0": 1129.0,
"router/selected_tokens_s1": 250.875,
"step": 1800,
"tokens_trained": 5.897704096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5134751773049645,
"grad_norm": 1.4817918539047241,
"loss": 1.1898,
"loss_ce": 1.2002263069152832,
"loss_region": 0.047367654740810394,
"loss_total": 1.2475939989089966,
"lr": 0.0011714827107054896,
"router/selected_tokens_s0": 1083.0625,
"router/selected_tokens_s1": 8.0,
"step": 1810,
"tokens_trained": 5.930469536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5163120567375886,
"grad_norm": 0.6873403787612915,
"loss": 1.1971,
"loss_ce": 1.1391804218292236,
"loss_region": 0.0709296390414238,
"loss_total": 1.210110068321228,
"lr": 0.0011710758187216386,
"router/selected_tokens_s0": 1092.5,
"router/selected_tokens_s1": 174.375,
"step": 1820,
"tokens_trained": 5.963234976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5191489361702127,
"grad_norm": 1.1967116594314575,
"loss": 1.2019,
"loss_ce": 1.0687319040298462,
"loss_region": 0.04903619363903999,
"loss_total": 1.1177680492401123,
"lr": 0.0011706689267377876,
"router/selected_tokens_s0": 1199.9375,
"router/selected_tokens_s1": 18.0,
"step": 1830,
"tokens_trained": 5.996000416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5219858156028369,
"grad_norm": 0.7093958854675293,
"loss": 1.1966,
"loss_ce": 1.1070630550384521,
"loss_region": 0.04815437272191048,
"loss_total": 1.1552174091339111,
"lr": 0.0011702620347539365,
"router/selected_tokens_s0": 1127.4375,
"router/selected_tokens_s1": 12.8125,
"step": 1840,
"tokens_trained": 6.02876568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.524822695035461,
"grad_norm": 1.3091318607330322,
"loss": 1.1942,
"loss_ce": 1.1178659200668335,
"loss_region": 0.048088669776916504,
"loss_total": 1.16595458984375,
"lr": 0.0011698551427700855,
"router/selected_tokens_s0": 1102.1875,
"router/selected_tokens_s1": 13.5,
"step": 1850,
"tokens_trained": 6.06153112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5276595744680851,
"grad_norm": 0.7635153532028198,
"loss": 1.2067,
"loss_ce": 1.1375563144683838,
"loss_region": 0.1209544762969017,
"loss_total": 1.2585108280181885,
"lr": 0.0011694482507862345,
"router/selected_tokens_s0": 1088.3125,
"router/selected_tokens_s1": 526.125,
"step": 1860,
"tokens_trained": 6.09429256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5304964539007092,
"grad_norm": 1.4109469652175903,
"loss": 1.1868,
"loss_ce": 1.1450139284133911,
"loss_region": 0.04958714172244072,
"loss_total": 1.194601058959961,
"lr": 0.0011690413588023834,
"router/selected_tokens_s0": 1270.3125,
"router/selected_tokens_s1": 21.6875,
"step": 1870,
"tokens_trained": 6.127058
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5333333333333333,
"grad_norm": 0.8178255558013916,
"loss": 1.2016,
"loss_ce": 1.1585605144500732,
"loss_region": 0.050786904990673065,
"loss_total": 1.2093473672866821,
"lr": 0.0011686344668185324,
"router/selected_tokens_s0": 1087.125,
"router/selected_tokens_s1": 32.3125,
"step": 1880,
"tokens_trained": 6.15982344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5361702127659574,
"grad_norm": 0.5921704769134521,
"loss": 1.1935,
"loss_ce": 1.1373960971832275,
"loss_region": 0.0489933118224144,
"loss_total": 1.186389446258545,
"lr": 0.0011682275748346814,
"router/selected_tokens_s0": 1191.6875,
"router/selected_tokens_s1": 18.0,
"step": 1890,
"tokens_trained": 6.19258888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5390070921985816,
"grad_norm": 0.452083945274353,
"loss": 1.1861,
"loss_ce": 1.1708186864852905,
"loss_region": 0.08669115602970123,
"loss_total": 1.2575098276138306,
"lr": 0.0011678206828508303,
"router/selected_tokens_s0": 1147.0625,
"router/selected_tokens_s1": 297.9375,
"step": 1900,
"tokens_trained": 6.22535432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5418439716312057,
"grad_norm": 0.6974602937698364,
"loss": 1.1975,
"loss_ce": 1.1292380094528198,
"loss_region": 0.06466572731733322,
"loss_total": 1.1939036846160889,
"lr": 0.0011674137908669793,
"router/selected_tokens_s0": 1140.625,
"router/selected_tokens_s1": 135.0,
"step": 1910,
"tokens_trained": 6.25811976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5446808510638298,
"grad_norm": 2.0106568336486816,
"loss": 1.1979,
"loss_ce": 1.1347987651824951,
"loss_region": 0.05081599950790405,
"loss_total": 1.185614824295044,
"lr": 0.0011670068988831283,
"router/selected_tokens_s0": 1291.625,
"router/selected_tokens_s1": 32.0625,
"step": 1920,
"tokens_trained": 6.2908852
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5475177304964539,
"grad_norm": 1.8177540302276611,
"loss": 1.1976,
"loss_ce": 1.1749643087387085,
"loss_region": 0.04952458664774895,
"loss_total": 1.2244888544082642,
"lr": 0.0011666000068992772,
"router/selected_tokens_s0": 1120.1875,
"router/selected_tokens_s1": 22.8125,
"step": 1930,
"tokens_trained": 6.32365064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.550354609929078,
"grad_norm": 0.6110920310020447,
"loss": 1.2036,
"loss_ce": 1.1350669860839844,
"loss_region": 0.07400424778461456,
"loss_total": 1.2090712785720825,
"lr": 0.0011661931149154262,
"router/selected_tokens_s0": 1123.625,
"router/selected_tokens_s1": 201.125,
"step": 1940,
"tokens_trained": 6.35641608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5531914893617021,
"grad_norm": 0.78255295753479,
"loss": 1.1923,
"loss_ce": 1.1034512519836426,
"loss_region": 0.055763859301805496,
"loss_total": 1.1592150926589966,
"lr": 0.0011657862229315751,
"router/selected_tokens_s0": 1213.375,
"router/selected_tokens_s1": 71.25,
"step": 1950,
"tokens_trained": 6.38918152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5560283687943263,
"grad_norm": 0.9850241541862488,
"loss": 1.1908,
"loss_ce": 1.0654675960540771,
"loss_region": 0.047422587871551514,
"loss_total": 1.1128902435302734,
"lr": 0.0011653793309477243,
"router/selected_tokens_s0": 1153.6875,
"router/selected_tokens_s1": 6.75,
"step": 1960,
"tokens_trained": 6.42194696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5588652482269504,
"grad_norm": 0.7804341912269592,
"loss": 1.1988,
"loss_ce": 1.11430025100708,
"loss_region": 0.0569145642220974,
"loss_total": 1.1712148189544678,
"lr": 0.0011649724389638733,
"router/selected_tokens_s0": 1115.1875,
"router/selected_tokens_s1": 77.375,
"step": 1970,
"tokens_trained": 6.4547124
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5617021276595745,
"grad_norm": 0.6811673641204834,
"loss": 1.2018,
"loss_ce": 1.179452657699585,
"loss_region": 0.061086151748895645,
"loss_total": 1.2405388355255127,
"lr": 0.0011645655469800223,
"router/selected_tokens_s0": 1153.8125,
"router/selected_tokens_s1": 110.875,
"step": 1980,
"tokens_trained": 6.48747784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5645390070921986,
"grad_norm": 1.0210864543914795,
"loss": 1.1931,
"loss_ce": 1.1308600902557373,
"loss_region": 0.049080073833465576,
"loss_total": 1.1799402236938477,
"lr": 0.0011641586549961712,
"router/selected_tokens_s0": 1134.1875,
"router/selected_tokens_s1": 19.5,
"step": 1990,
"tokens_trained": 6.52024328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5673758865248227,
"grad_norm": 0.5659611225128174,
"loss": 1.1891,
"loss_ce": 1.1048927307128906,
"loss_region": 0.048004768788814545,
"loss_total": 1.1528974771499634,
"lr": 0.00116375176301232,
"router/selected_tokens_s0": 1114.1875,
"router/selected_tokens_s1": 11.875,
"step": 2000,
"tokens_trained": 6.55300872
},
{
"epoch": 0.5673758865248227,
"eval_ppl": 3.1136783371919927,
"eval_runtime": 2.0276,
"step": 2000,
"tokens_trained": 6.55300872
},
{
"epoch": 0.5673758865248227,
"eval_F": 0.01069504411010371,
"eval_F_cds": 0.010861557811517384,
"eval_F_dig": 0.006484881631377452,
"eval_F_exon": 0.009934629863687637,
"eval_F_intron": 0.010966237207462225,
"eval_F_nig": 0.01021226628824177,
"eval_F_promoter": 0.010854231149853663,
"eval_F_utr": 0.00875070613188945,
"eval_G": 0.04274226492450051,
"eval_G_cds": 0.04430924894438954,
"eval_G_dig": 0.05328854121904055,
"eval_G_exon": 0.0431136795674155,
"eval_G_intron": 0.04271742073044739,
"eval_G_nig": 0.042630800601355275,
"eval_G_promoter": 0.04267057437658576,
"eval_G_utr": 0.040218208077082956,
"eval_avg_bp_per_token": 93.5012506451741,
"eval_bp_per_token/cds": 92.06782464846981,
"eval_bp_per_token/dig": 154.20481927710844,
"eval_bp_per_token/exon": 100.65800273597812,
"eval_bp_per_token/intron": 91.18898133258757,
"eval_bp_per_token/nig": 97.92145756631739,
"eval_bp_per_token/promoter": 92.12997090203686,
"eval_bp_per_token/utr": 114.27649208282583,
"eval_ppl_cds": 3.7525472911998365,
"eval_ppl_dig": 1.205216056365389,
"eval_ppl_exon": 3.3402803721577903,
"eval_ppl_intron": 3.1339518485780027,
"eval_ppl_nig": 2.9991873798849777,
"eval_ppl_promoter": 3.3500096344554424,
"eval_ppl_utr": 3.431926820268814,
"step": 2000,
"tokens_trained": 6.55300872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5702127659574469,
"grad_norm": 0.3684820234775543,
"loss": 1.1983,
"loss_ce": 1.14522385597229,
"loss_region": 0.047928690910339355,
"loss_total": 1.1931525468826294,
"lr": 0.001163344871028469,
"router/selected_tokens_s0": 1213.1875,
"router/selected_tokens_s1": 10.0,
"step": 2010,
"tokens_trained": 6.58577416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.573049645390071,
"grad_norm": 0.34278973937034607,
"loss": 1.1998,
"loss_ce": 1.0959526300430298,
"loss_region": 0.05933360382914543,
"loss_total": 1.155286192893982,
"lr": 0.001162937979044618,
"router/selected_tokens_s0": 1201.0625,
"router/selected_tokens_s1": 95.9375,
"step": 2020,
"tokens_trained": 6.6185396
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5758865248226951,
"grad_norm": 0.885452151298523,
"loss": 1.1935,
"loss_ce": 1.040181040763855,
"loss_region": 0.06413589417934418,
"loss_total": 1.1043169498443604,
"lr": 0.001162531087060767,
"router/selected_tokens_s0": 1029.1875,
"router/selected_tokens_s1": 119.9375,
"step": 2030,
"tokens_trained": 6.65130504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5787234042553191,
"grad_norm": 0.6951954364776611,
"loss": 1.1923,
"loss_ce": 1.115369439125061,
"loss_region": 0.06800974160432816,
"loss_total": 1.1833791732788086,
"lr": 0.001162124195076916,
"router/selected_tokens_s0": 1207.75,
"router/selected_tokens_s1": 168.9375,
"step": 2040,
"tokens_trained": 6.68407048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5815602836879432,
"grad_norm": 0.2609427571296692,
"loss": 1.1918,
"loss_ce": 1.1436803340911865,
"loss_region": 0.056535884737968445,
"loss_total": 1.2002161741256714,
"lr": 0.001161717303093065,
"router/selected_tokens_s0": 1019.75,
"router/selected_tokens_s1": 69.3125,
"step": 2050,
"tokens_trained": 6.71683512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5843971631205673,
"grad_norm": 0.9476459622383118,
"loss": 1.1933,
"loss_ce": 1.1254041194915771,
"loss_region": 0.055064037442207336,
"loss_total": 1.180468201637268,
"lr": 0.001161310411109214,
"router/selected_tokens_s0": 1176.8125,
"router/selected_tokens_s1": 65.375,
"step": 2060,
"tokens_trained": 6.74960056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5872340425531914,
"grad_norm": 0.971532940864563,
"loss": 1.1914,
"loss_ce": 1.1687484979629517,
"loss_region": 0.06600674241781235,
"loss_total": 1.234755277633667,
"lr": 0.001160903519125363,
"router/selected_tokens_s0": 1138.625,
"router/selected_tokens_s1": 144.75,
"step": 2070,
"tokens_trained": 6.782364224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5900709219858156,
"grad_norm": 0.7967547178268433,
"loss": 1.1971,
"loss_ce": 1.1594549417495728,
"loss_region": 0.06982410699129105,
"loss_total": 1.2292790412902832,
"lr": 0.001160496627141512,
"router/selected_tokens_s0": 1132.0625,
"router/selected_tokens_s1": 172.1875,
"step": 2080,
"tokens_trained": 6.815129664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5929078014184397,
"grad_norm": 0.5164719223976135,
"loss": 1.1943,
"loss_ce": 1.2028053998947144,
"loss_region": 0.051641225814819336,
"loss_total": 1.2544466257095337,
"lr": 0.0011600897351576609,
"router/selected_tokens_s0": 1053.375,
"router/selected_tokens_s1": 37.375,
"step": 2090,
"tokens_trained": 6.847895104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5957446808510638,
"grad_norm": 0.801796555519104,
"loss": 1.1852,
"loss_ce": 1.0660555362701416,
"loss_region": 0.08737988770008087,
"loss_total": 1.153435468673706,
"lr": 0.0011596828431738098,
"router/selected_tokens_s0": 1178.875,
"router/selected_tokens_s1": 311.375,
"step": 2100,
"tokens_trained": 6.880660544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5985815602836879,
"grad_norm": 0.8828497529029846,
"loss": 1.1881,
"loss_ce": 1.1242519617080688,
"loss_region": 0.0549292154610157,
"loss_total": 1.1791812181472778,
"lr": 0.0011592759511899588,
"router/selected_tokens_s0": 1131.3125,
"router/selected_tokens_s1": 62.0625,
"step": 2110,
"tokens_trained": 6.913423848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.601418439716312,
"grad_norm": 1.086348533630371,
"loss": 1.1924,
"loss_ce": 1.0381351709365845,
"loss_region": 0.06273744255304337,
"loss_total": 1.1008726358413696,
"lr": 0.0011588690592061078,
"router/selected_tokens_s0": 1137.0,
"router/selected_tokens_s1": 121.9375,
"step": 2120,
"tokens_trained": 6.946189128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6042553191489362,
"grad_norm": 1.3790611028671265,
"loss": 1.1905,
"loss_ce": 1.1533229351043701,
"loss_region": 0.05107864364981651,
"loss_total": 1.2044016122817993,
"lr": 0.0011584621672222567,
"router/selected_tokens_s0": 921.25,
"router/selected_tokens_s1": 32.25,
"step": 2130,
"tokens_trained": 6.978954568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6070921985815603,
"grad_norm": 0.5741104483604431,
"loss": 1.1958,
"loss_ce": 1.1531747579574585,
"loss_region": 0.06062934547662735,
"loss_total": 1.2138041257858276,
"lr": 0.0011580552752384057,
"router/selected_tokens_s0": 1092.3125,
"router/selected_tokens_s1": 102.125,
"step": 2140,
"tokens_trained": 7.011720008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6099290780141844,
"grad_norm": 0.3919357657432556,
"loss": 1.1936,
"loss_ce": 1.0967808961868286,
"loss_region": 0.058883871883153915,
"loss_total": 1.1556648015975952,
"lr": 0.0011576483832545547,
"router/selected_tokens_s0": 1085.1875,
"router/selected_tokens_s1": 88.75,
"step": 2150,
"tokens_trained": 7.044485448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6127659574468085,
"grad_norm": 1.0066328048706055,
"loss": 1.1928,
"loss_ce": 1.1479171514511108,
"loss_region": 0.0568971112370491,
"loss_total": 1.2048143148422241,
"lr": 0.0011572414912707036,
"router/selected_tokens_s0": 1115.6875,
"router/selected_tokens_s1": 76.6875,
"step": 2160,
"tokens_trained": 7.077250888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6156028368794326,
"grad_norm": 0.6049533486366272,
"loss": 1.1869,
"loss_ce": 1.1199055910110474,
"loss_region": 0.062149304896593094,
"loss_total": 1.182054877281189,
"lr": 0.0011568345992868526,
"router/selected_tokens_s0": 1205.0,
"router/selected_tokens_s1": 121.1875,
"step": 2170,
"tokens_trained": 7.110016328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6184397163120567,
"grad_norm": 0.3710135221481323,
"loss": 1.1891,
"loss_ce": 1.1549140214920044,
"loss_region": 0.049698520451784134,
"loss_total": 1.2046124935150146,
"lr": 0.0011564277073030016,
"router/selected_tokens_s0": 1194.3125,
"router/selected_tokens_s1": 23.625,
"step": 2180,
"tokens_trained": 7.1427786
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6212765957446809,
"grad_norm": 0.24183577299118042,
"loss": 1.1948,
"loss_ce": 1.1288636922836304,
"loss_region": 0.056807950139045715,
"loss_total": 1.1856716871261597,
"lr": 0.0011560208153191505,
"router/selected_tokens_s0": 1169.4375,
"router/selected_tokens_s1": 78.6875,
"step": 2190,
"tokens_trained": 7.17554404
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.624113475177305,
"grad_norm": 0.46073052287101746,
"loss": 1.191,
"loss_ce": 1.075547218322754,
"loss_region": 0.05498499423265457,
"loss_total": 1.1305322647094727,
"lr": 0.0011556139233352995,
"router/selected_tokens_s0": 1175.8125,
"router/selected_tokens_s1": 63.0625,
"step": 2200,
"tokens_trained": 7.20830948
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6269503546099291,
"grad_norm": 1.0049269199371338,
"loss": 1.1898,
"loss_ce": 1.1013010740280151,
"loss_region": 0.06765102595090866,
"loss_total": 1.1689521074295044,
"lr": 0.0011552070313514487,
"router/selected_tokens_s0": 1242.0,
"router/selected_tokens_s1": 169.625,
"step": 2210,
"tokens_trained": 7.24107492
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6297872340425532,
"grad_norm": 1.004379391670227,
"loss": 1.1946,
"loss_ce": 1.1723252534866333,
"loss_region": 0.059653084725141525,
"loss_total": 1.2319782972335815,
"lr": 0.0011548001393675976,
"router/selected_tokens_s0": 1147.875,
"router/selected_tokens_s1": 98.0,
"step": 2220,
"tokens_trained": 7.27384036
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6326241134751773,
"grad_norm": 0.47309768199920654,
"loss": 1.1923,
"loss_ce": 1.1086316108703613,
"loss_region": 0.061595749109983444,
"loss_total": 1.1702274084091187,
"lr": 0.0011543932473837466,
"router/selected_tokens_s0": 1165.5625,
"router/selected_tokens_s1": 115.375,
"step": 2230,
"tokens_trained": 7.3066058
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6354609929078014,
"grad_norm": 1.1624172925949097,
"loss": 1.1849,
"loss_ce": 1.1424520015716553,
"loss_region": 0.05363762006163597,
"loss_total": 1.1960896253585815,
"lr": 0.0011539863553998956,
"router/selected_tokens_s0": 1145.5625,
"router/selected_tokens_s1": 53.0625,
"step": 2240,
"tokens_trained": 7.33937124
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6382978723404256,
"grad_norm": 0.5090921521186829,
"loss": 1.1891,
"loss_ce": 1.0883148908615112,
"loss_region": 0.05045454576611519,
"loss_total": 1.1387693881988525,
"lr": 0.0011535794634160443,
"router/selected_tokens_s0": 1139.625,
"router/selected_tokens_s1": 30.5,
"step": 2250,
"tokens_trained": 7.37213668
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6411347517730497,
"grad_norm": 0.24586611986160278,
"loss": 1.1871,
"loss_ce": 1.122402548789978,
"loss_region": 0.05342685803771019,
"loss_total": 1.1758294105529785,
"lr": 0.0011531725714321933,
"router/selected_tokens_s0": 1129.75,
"router/selected_tokens_s1": 52.5,
"step": 2260,
"tokens_trained": 7.40490212
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6439716312056738,
"grad_norm": 1.1430929899215698,
"loss": 1.1878,
"loss_ce": 1.0667387247085571,
"loss_region": 0.05230208858847618,
"loss_total": 1.119040846824646,
"lr": 0.0011527656794483422,
"router/selected_tokens_s0": 1125.25,
"router/selected_tokens_s1": 43.8125,
"step": 2270,
"tokens_trained": 7.43766756
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6468085106382979,
"grad_norm": 1.836784839630127,
"loss": 1.1938,
"loss_ce": 1.1883622407913208,
"loss_region": 0.0947345495223999,
"loss_total": 1.2830967903137207,
"lr": 0.0011523587874644914,
"router/selected_tokens_s0": 1179.6875,
"router/selected_tokens_s1": 368.125,
"step": 2280,
"tokens_trained": 7.470433
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.649645390070922,
"grad_norm": 1.0409865379333496,
"loss": 1.1901,
"loss_ce": 1.1272953748703003,
"loss_region": 0.05049753561615944,
"loss_total": 1.1777929067611694,
"lr": 0.0011519518954806404,
"router/selected_tokens_s0": 1035.9375,
"router/selected_tokens_s1": 29.125,
"step": 2290,
"tokens_trained": 7.503197136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6524822695035462,
"grad_norm": 0.5576117038726807,
"loss": 1.1885,
"loss_ce": 1.1093772649765015,
"loss_region": 0.060273103415966034,
"loss_total": 1.1696503162384033,
"lr": 0.0011515450034967894,
"router/selected_tokens_s0": 1215.9375,
"router/selected_tokens_s1": 109.25,
"step": 2300,
"tokens_trained": 7.535962576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6553191489361702,
"grad_norm": 0.5205599069595337,
"loss": 1.1924,
"loss_ce": 1.1544609069824219,
"loss_region": 0.07660765200853348,
"loss_total": 1.2310686111450195,
"lr": 0.0011511381115129383,
"router/selected_tokens_s0": 1092.9375,
"router/selected_tokens_s1": 214.5625,
"step": 2310,
"tokens_trained": 7.568726416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6581560283687943,
"grad_norm": 0.447685569524765,
"loss": 1.1869,
"loss_ce": 1.153815746307373,
"loss_region": 0.06783945858478546,
"loss_total": 1.221655249595642,
"lr": 0.0011507312195290873,
"router/selected_tokens_s0": 1045.5625,
"router/selected_tokens_s1": 147.75,
"step": 2320,
"tokens_trained": 7.601491056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6609929078014184,
"grad_norm": 0.5006564855575562,
"loss": 1.1865,
"loss_ce": 1.137509822845459,
"loss_region": 0.053064778447151184,
"loss_total": 1.1905746459960938,
"lr": 0.0011503243275452363,
"router/selected_tokens_s0": 1098.0,
"router/selected_tokens_s1": 48.3125,
"step": 2330,
"tokens_trained": 7.634256496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6638297872340425,
"grad_norm": 0.992090106010437,
"loss": 1.1858,
"loss_ce": 1.1077237129211426,
"loss_region": 0.048039667308330536,
"loss_total": 1.1557633876800537,
"lr": 0.0011499174355613852,
"router/selected_tokens_s0": 1037.875,
"router/selected_tokens_s1": 13.0625,
"step": 2340,
"tokens_trained": 7.667021936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6666666666666666,
"grad_norm": 0.38324639201164246,
"loss": 1.1885,
"loss_ce": 1.105891466140747,
"loss_region": 0.05229361355304718,
"loss_total": 1.1581851243972778,
"lr": 0.0011495105435775342,
"router/selected_tokens_s0": 1107.125,
"router/selected_tokens_s1": 42.0625,
"step": 2350,
"tokens_trained": 7.699787376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6695035460992907,
"grad_norm": 0.492826372385025,
"loss": 1.1861,
"loss_ce": 1.1159106492996216,
"loss_region": 0.06743160635232925,
"loss_total": 1.1833422183990479,
"lr": 0.0011491036515936831,
"router/selected_tokens_s0": 1241.4375,
"router/selected_tokens_s1": 166.9375,
"step": 2360,
"tokens_trained": 7.732552016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6723404255319149,
"grad_norm": 0.8682832717895508,
"loss": 1.1788,
"loss_ce": 1.1449956893920898,
"loss_region": 0.0556202307343483,
"loss_total": 1.2006158828735352,
"lr": 0.0011486967596098321,
"router/selected_tokens_s0": 1085.375,
"router/selected_tokens_s1": 66.125,
"step": 2370,
"tokens_trained": 7.765317456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.675177304964539,
"grad_norm": 0.831288754940033,
"loss": 1.1866,
"loss_ce": 1.192410945892334,
"loss_region": 0.06446831673383713,
"loss_total": 1.256879210472107,
"lr": 0.001148289867625981,
"router/selected_tokens_s0": 1148.75,
"router/selected_tokens_s1": 134.0625,
"step": 2380,
"tokens_trained": 7.798082896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6780141843971631,
"grad_norm": 0.7338893413543701,
"loss": 1.1885,
"loss_ce": 1.0737974643707275,
"loss_region": 0.06012767180800438,
"loss_total": 1.1339250802993774,
"lr": 0.00114788297564213,
"router/selected_tokens_s0": 1175.625,
"router/selected_tokens_s1": 104.1875,
"step": 2390,
"tokens_trained": 7.830848336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6808510638297872,
"grad_norm": 1.1017957925796509,
"loss": 1.1932,
"loss_ce": 1.0649081468582153,
"loss_region": 0.05181884765625,
"loss_total": 1.1167269945144653,
"lr": 0.001147476083658279,
"router/selected_tokens_s0": 1137.1875,
"router/selected_tokens_s1": 38.1875,
"step": 2400,
"tokens_trained": 7.863613776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6836879432624113,
"grad_norm": 0.42400914430618286,
"loss": 1.1884,
"loss_ce": 1.120243787765503,
"loss_region": 0.05012480542063713,
"loss_total": 1.1703685522079468,
"lr": 0.001147069191674428,
"router/selected_tokens_s0": 1099.8125,
"router/selected_tokens_s1": 26.5625,
"step": 2410,
"tokens_trained": 7.896379216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6865248226950355,
"grad_norm": 0.6636138558387756,
"loss": 1.1873,
"loss_ce": 1.103990912437439,
"loss_region": 0.05863885208964348,
"loss_total": 1.1626297235488892,
"lr": 0.001146662299690577,
"router/selected_tokens_s0": 1077.1875,
"router/selected_tokens_s1": 86.1875,
"step": 2420,
"tokens_trained": 7.929144656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6893617021276596,
"grad_norm": 0.20607493817806244,
"loss": 1.1821,
"loss_ce": 1.1684622764587402,
"loss_region": 0.058312416076660156,
"loss_total": 1.2267746925354004,
"lr": 0.001146255407706726,
"router/selected_tokens_s0": 1127.375,
"router/selected_tokens_s1": 87.875,
"step": 2430,
"tokens_trained": 7.961910096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6921985815602837,
"grad_norm": 1.6605172157287598,
"loss": 1.191,
"loss_ce": 1.1512646675109863,
"loss_region": 0.09868698567152023,
"loss_total": 1.2499516010284424,
"lr": 0.0011458485157228749,
"router/selected_tokens_s0": 1190.125,
"router/selected_tokens_s1": 405.4375,
"step": 2440,
"tokens_trained": 7.994675536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6950354609929078,
"grad_norm": 0.6036321520805359,
"loss": 1.1824,
"loss_ce": 1.0932222604751587,
"loss_region": 0.06464701145887375,
"loss_total": 1.1578692197799683,
"lr": 0.0011454416237390238,
"router/selected_tokens_s0": 1218.6875,
"router/selected_tokens_s1": 147.1875,
"step": 2450,
"tokens_trained": 8.027440976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6978723404255319,
"grad_norm": 0.5354553461074829,
"loss": 1.1819,
"loss_ce": 1.1074717044830322,
"loss_region": 0.05404704064130783,
"loss_total": 1.1615186929702759,
"lr": 0.001145034731755173,
"router/selected_tokens_s0": 1221.5625,
"router/selected_tokens_s1": 58.6875,
"step": 2460,
"tokens_trained": 8.060206416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.700709219858156,
"grad_norm": 0.3824005722999573,
"loss": 1.1821,
"loss_ce": 1.1669650077819824,
"loss_region": 0.05842549353837967,
"loss_total": 1.2253905534744263,
"lr": 0.001144627839771322,
"router/selected_tokens_s0": 1060.1875,
"router/selected_tokens_s1": 83.875,
"step": 2470,
"tokens_trained": 8.092971856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7035460992907802,
"grad_norm": 1.2816966772079468,
"loss": 1.1884,
"loss_ce": 1.1886110305786133,
"loss_region": 0.05507363751530647,
"loss_total": 1.2436846494674683,
"lr": 0.001144220947787471,
"router/selected_tokens_s0": 1096.6875,
"router/selected_tokens_s1": 62.4375,
"step": 2480,
"tokens_trained": 8.125737296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7063829787234043,
"grad_norm": 0.8357634544372559,
"loss": 1.1849,
"loss_ce": 1.1635318994522095,
"loss_region": 0.05851307883858681,
"loss_total": 1.2220449447631836,
"lr": 0.00114381405580362,
"router/selected_tokens_s0": 1201.75,
"router/selected_tokens_s1": 92.6875,
"step": 2490,
"tokens_trained": 8.158502728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7092198581560284,
"grad_norm": 0.6387074589729309,
"loss": 1.1841,
"loss_ce": 1.1415513753890991,
"loss_region": 0.06358432024717331,
"loss_total": 1.205135703086853,
"lr": 0.0011434071638197687,
"router/selected_tokens_s0": 1124.5,
"router/selected_tokens_s1": 125.5,
"step": 2500,
"tokens_trained": 8.191268168
},
{
"epoch": 0.7092198581560284,
"eval_ppl": 3.085261030890577,
"eval_runtime": 1.9932,
"step": 2500,
"tokens_trained": 8.191268168
},
{
"epoch": 0.7092198581560284,
"eval_F": 0.00680101536465145,
"eval_F_cds": 0.005210672895517025,
"eval_F_dig": 0.02410344558168607,
"eval_F_exon": 0.00631956619235944,
"eval_F_intron": 0.006854377447718121,
"eval_F_nig": 0.007284422172562524,
"eval_F_promoter": 0.005771903227844103,
"eval_F_utr": 0.005851568412189169,
"eval_G": 0.042142292222616534,
"eval_G_cds": 0.04027827688437696,
"eval_G_dig": 0.05870552936264552,
"eval_G_exon": 0.04071618352563841,
"eval_G_intron": 0.04184660939886382,
"eval_G_nig": 0.0422879405323239,
"eval_G_promoter": 0.0431433928215408,
"eval_G_utr": 0.03945561894458597,
"eval_avg_bp_per_token": 147.03686822963817,
"eval_bp_per_token/cds": 191.91379310344828,
"eval_bp_per_token/dig": 41.487844408427875,
"eval_bp_per_token/exon": 158.23870967741937,
"eval_bp_per_token/intron": 145.89217002237137,
"eval_bp_per_token/nig": 137.27924827951296,
"eval_bp_per_token/promoter": 173.2530779753762,
"eval_bp_per_token/utr": 170.8943533697632,
"eval_ppl_cds": 3.733989189183948,
"eval_ppl_dig": 1.1368362702896024,
"eval_ppl_exon": 3.317643101731427,
"eval_ppl_intron": 3.108811822776569,
"eval_ppl_nig": 2.961271125541008,
"eval_ppl_promoter": 3.3320430827111296,
"eval_ppl_utr": 3.4181474720617597,
"step": 2500,
"tokens_trained": 8.191268168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7120567375886525,
"grad_norm": 0.5213884711265564,
"loss": 1.183,
"loss_ce": 1.0932352542877197,
"loss_region": 0.05128668248653412,
"loss_total": 1.144521951675415,
"lr": 0.0011430002718359176,
"router/selected_tokens_s0": 1219.3125,
"router/selected_tokens_s1": 36.625,
"step": 2510,
"tokens_trained": 8.224033608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7148936170212766,
"grad_norm": 1.4375683069229126,
"loss": 1.1813,
"loss_ce": 1.1448945999145508,
"loss_region": 0.049260806292295456,
"loss_total": 1.1941554546356201,
"lr": 0.0011425933798520666,
"router/selected_tokens_s0": 1164.6875,
"router/selected_tokens_s1": 21.0625,
"step": 2520,
"tokens_trained": 8.25679904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7177304964539007,
"grad_norm": 1.0103474855422974,
"loss": 1.1899,
"loss_ce": 1.1087768077850342,
"loss_region": 0.07257764041423798,
"loss_total": 1.1813544034957886,
"lr": 0.0011421864878682158,
"router/selected_tokens_s0": 1230.375,
"router/selected_tokens_s1": 206.625,
"step": 2530,
"tokens_trained": 8.28956448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7205673758865249,
"grad_norm": 0.5543859004974365,
"loss": 1.1836,
"loss_ce": 1.1301989555358887,
"loss_region": 0.0570821538567543,
"loss_total": 1.1872811317443848,
"lr": 0.0011417795958843647,
"router/selected_tokens_s0": 1275.3125,
"router/selected_tokens_s1": 85.4375,
"step": 2540,
"tokens_trained": 8.322329544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.723404255319149,
"grad_norm": 0.3695959150791168,
"loss": 1.1844,
"loss_ce": 1.1506540775299072,
"loss_region": 0.06053993105888367,
"loss_total": 1.2111940383911133,
"lr": 0.0011413727039005137,
"router/selected_tokens_s0": 1140.1875,
"router/selected_tokens_s1": 104.0625,
"step": 2550,
"tokens_trained": 8.355094984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7262411347517731,
"grad_norm": 0.6553955078125,
"loss": 1.1802,
"loss_ce": 1.0622395277023315,
"loss_region": 0.06116200238466263,
"loss_total": 1.1234015226364136,
"lr": 0.0011409658119166627,
"router/selected_tokens_s0": 1214.0625,
"router/selected_tokens_s1": 113.875,
"step": 2560,
"tokens_trained": 8.3878584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7290780141843972,
"grad_norm": 0.6573439836502075,
"loss": 1.1833,
"loss_ce": 1.0715194940567017,
"loss_region": 0.058225441724061966,
"loss_total": 1.1297448873519897,
"lr": 0.0011405589199328116,
"router/selected_tokens_s0": 1251.125,
"router/selected_tokens_s1": 93.75,
"step": 2570,
"tokens_trained": 8.42062384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7319148936170212,
"grad_norm": 1.2631888389587402,
"loss": 1.1845,
"loss_ce": 1.1702756881713867,
"loss_region": 0.06478434056043625,
"loss_total": 1.2350599765777588,
"lr": 0.0011401520279489606,
"router/selected_tokens_s0": 1134.0625,
"router/selected_tokens_s1": 133.8125,
"step": 2580,
"tokens_trained": 8.453389256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7347517730496453,
"grad_norm": 0.5682166218757629,
"loss": 1.1859,
"loss_ce": 1.0891146659851074,
"loss_region": 0.04887212812900543,
"loss_total": 1.1379867792129517,
"lr": 0.0011397451359651096,
"router/selected_tokens_s0": 1188.375,
"router/selected_tokens_s1": 17.375,
"step": 2590,
"tokens_trained": 8.486154696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7375886524822695,
"grad_norm": 0.6613340973854065,
"loss": 1.1837,
"loss_ce": 1.175453543663025,
"loss_region": 0.060148756951093674,
"loss_total": 1.2356022596359253,
"lr": 0.0011393382439812585,
"router/selected_tokens_s0": 1084.1875,
"router/selected_tokens_s1": 97.0625,
"step": 2600,
"tokens_trained": 8.518920136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7404255319148936,
"grad_norm": 0.6439635157585144,
"loss": 1.1797,
"loss_ce": 1.1248722076416016,
"loss_region": 0.057590316981077194,
"loss_total": 1.1824625730514526,
"lr": 0.0011389313519974075,
"router/selected_tokens_s0": 1128.875,
"router/selected_tokens_s1": 82.875,
"step": 2610,
"tokens_trained": 8.551685576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7432624113475177,
"grad_norm": 0.5331895351409912,
"loss": 1.1837,
"loss_ce": 1.1927634477615356,
"loss_region": 0.06320803612470627,
"loss_total": 1.2559714317321777,
"lr": 0.0011385244600135565,
"router/selected_tokens_s0": 1140.3125,
"router/selected_tokens_s1": 122.25,
"step": 2620,
"tokens_trained": 8.584451016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7460992907801418,
"grad_norm": 0.9306845664978027,
"loss": 1.1796,
"loss_ce": 1.0927690267562866,
"loss_region": 0.054515350610017776,
"loss_total": 1.1472843885421753,
"lr": 0.0011381175680297054,
"router/selected_tokens_s0": 1099.1875,
"router/selected_tokens_s1": 58.125,
"step": 2630,
"tokens_trained": 8.617213968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7489361702127659,
"grad_norm": 0.803848922252655,
"loss": 1.1831,
"loss_ce": 1.100754976272583,
"loss_region": 0.06052076816558838,
"loss_total": 1.1612757444381714,
"lr": 0.0011377106760458544,
"router/selected_tokens_s0": 1250.6875,
"router/selected_tokens_s1": 111.0625,
"step": 2640,
"tokens_trained": 8.649979408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.75177304964539,
"grad_norm": 0.5596192479133606,
"loss": 1.1831,
"loss_ce": 1.1097190380096436,
"loss_region": 0.06077639386057854,
"loss_total": 1.1704953908920288,
"lr": 0.0011373037840620034,
"router/selected_tokens_s0": 1206.5625,
"router/selected_tokens_s1": 113.125,
"step": 2650,
"tokens_trained": 8.682744848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7546099290780142,
"grad_norm": 0.3111552894115448,
"loss": 1.1797,
"loss_ce": 1.1402360200881958,
"loss_region": 0.059760384261608124,
"loss_total": 1.1999963521957397,
"lr": 0.0011368968920781523,
"router/selected_tokens_s0": 1139.125,
"router/selected_tokens_s1": 98.9375,
"step": 2660,
"tokens_trained": 8.715510288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7574468085106383,
"grad_norm": 0.43657973408699036,
"loss": 1.1812,
"loss_ce": 1.1205332279205322,
"loss_region": 0.06205965578556061,
"loss_total": 1.1825928688049316,
"lr": 0.0011364900000943013,
"router/selected_tokens_s0": 1233.3125,
"router/selected_tokens_s1": 122.6875,
"step": 2670,
"tokens_trained": 8.748275728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7602836879432624,
"grad_norm": 0.826763927936554,
"loss": 1.1865,
"loss_ce": 1.163713812828064,
"loss_region": 0.0501738004386425,
"loss_total": 1.2138875722885132,
"lr": 0.0011360831081104503,
"router/selected_tokens_s0": 1197.4375,
"router/selected_tokens_s1": 27.1875,
"step": 2680,
"tokens_trained": 8.781041168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7631205673758865,
"grad_norm": 0.6090939044952393,
"loss": 1.1884,
"loss_ce": 1.1616290807724,
"loss_region": 0.05640416964888573,
"loss_total": 1.2180331945419312,
"lr": 0.0011356762161265992,
"router/selected_tokens_s0": 1076.5,
"router/selected_tokens_s1": 70.0625,
"step": 2690,
"tokens_trained": 8.813806448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7659574468085106,
"grad_norm": 0.6091976761817932,
"loss": 1.1743,
"loss_ce": 1.102664589881897,
"loss_region": 0.06204209849238396,
"loss_total": 1.1647067070007324,
"lr": 0.0011352693241427482,
"router/selected_tokens_s0": 1058.5625,
"router/selected_tokens_s1": 106.5625,
"step": 2700,
"tokens_trained": 8.846571888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7687943262411348,
"grad_norm": 0.4059768617153168,
"loss": 1.1818,
"loss_ce": 1.071120262145996,
"loss_region": 0.06557711958885193,
"loss_total": 1.1366974115371704,
"lr": 0.0011348624321588974,
"router/selected_tokens_s0": 1169.625,
"router/selected_tokens_s1": 145.1875,
"step": 2710,
"tokens_trained": 8.879337328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7716312056737589,
"grad_norm": 0.8343297839164734,
"loss": 1.177,
"loss_ce": 1.1214219331741333,
"loss_region": 0.05871148779988289,
"loss_total": 1.1801334619522095,
"lr": 0.0011344555401750463,
"router/selected_tokens_s0": 1201.0625,
"router/selected_tokens_s1": 94.125,
"step": 2720,
"tokens_trained": 8.912102768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.774468085106383,
"grad_norm": 0.7600639462471008,
"loss": 1.1865,
"loss_ce": 1.1025841236114502,
"loss_region": 0.05945834890007973,
"loss_total": 1.162042498588562,
"lr": 0.0011340486481911953,
"router/selected_tokens_s0": 1277.125,
"router/selected_tokens_s1": 104.8125,
"step": 2730,
"tokens_trained": 8.944868208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7773049645390071,
"grad_norm": 0.7523510456085205,
"loss": 1.1837,
"loss_ce": 1.153456211090088,
"loss_region": 0.057424623519182205,
"loss_total": 1.2108808755874634,
"lr": 0.001133641756207344,
"router/selected_tokens_s0": 1197.8125,
"router/selected_tokens_s1": 84.5,
"step": 2740,
"tokens_trained": 8.977633592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7801418439716312,
"grad_norm": 0.4456590414047241,
"loss": 1.1812,
"loss_ce": 1.1360499858856201,
"loss_region": 0.05489301681518555,
"loss_total": 1.1909430027008057,
"lr": 0.001133234864223493,
"router/selected_tokens_s0": 1138.875,
"router/selected_tokens_s1": 62.375,
"step": 2750,
"tokens_trained": 9.010399032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7829787234042553,
"grad_norm": 0.5763502717018127,
"loss": 1.1776,
"loss_ce": 1.0765600204467773,
"loss_region": 0.060738228261470795,
"loss_total": 1.1372982263565063,
"lr": 0.001132827972239642,
"router/selected_tokens_s0": 1198.5625,
"router/selected_tokens_s1": 111.3125,
"step": 2760,
"tokens_trained": 9.043164472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7858156028368795,
"grad_norm": 0.8224549293518066,
"loss": 1.1853,
"loss_ce": 1.1184666156768799,
"loss_region": 0.06167374178767204,
"loss_total": 1.1801403760910034,
"lr": 0.001132421080255791,
"router/selected_tokens_s0": 1232.4375,
"router/selected_tokens_s1": 119.0625,
"step": 2770,
"tokens_trained": 9.075929912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7886524822695036,
"grad_norm": 0.3950735330581665,
"loss": 1.183,
"loss_ce": 1.0782346725463867,
"loss_region": 0.07110589742660522,
"loss_total": 1.1493406295776367,
"lr": 0.0011320141882719401,
"router/selected_tokens_s0": 1241.25,
"router/selected_tokens_s1": 193.5625,
"step": 2780,
"tokens_trained": 9.108695352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7914893617021277,
"grad_norm": 0.29622024297714233,
"loss": 1.1782,
"loss_ce": 1.0680986642837524,
"loss_region": 0.06274113059043884,
"loss_total": 1.1308398246765137,
"lr": 0.001131607296288089,
"router/selected_tokens_s0": 1081.9375,
"router/selected_tokens_s1": 116.3125,
"step": 2790,
"tokens_trained": 9.141456136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7943262411347518,
"grad_norm": 0.7131189107894897,
"loss": 1.1795,
"loss_ce": 1.1580817699432373,
"loss_region": 0.07048571854829788,
"loss_total": 1.2285674810409546,
"lr": 0.001131200404304238,
"router/selected_tokens_s0": 1201.375,
"router/selected_tokens_s1": 186.6875,
"step": 2800,
"tokens_trained": 9.174221576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7971631205673759,
"grad_norm": 0.4363972246646881,
"loss": 1.1811,
"loss_ce": 1.112588882446289,
"loss_region": 0.06408771872520447,
"loss_total": 1.176676630973816,
"lr": 0.001130793512320387,
"router/selected_tokens_s0": 1164.625,
"router/selected_tokens_s1": 133.25,
"step": 2810,
"tokens_trained": 9.206987016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8,
"grad_norm": 1.0044184923171997,
"loss": 1.1797,
"loss_ce": 1.0698281526565552,
"loss_region": 0.06786457449197769,
"loss_total": 1.1376926898956299,
"lr": 0.001130386620336536,
"router/selected_tokens_s0": 1299.0,
"router/selected_tokens_s1": 176.875,
"step": 2820,
"tokens_trained": 9.239752456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8028368794326242,
"grad_norm": 0.6597614288330078,
"loss": 1.1803,
"loss_ce": 1.121903896331787,
"loss_region": 0.05995731055736542,
"loss_total": 1.181861162185669,
"lr": 0.001129979728352685,
"router/selected_tokens_s0": 1300.3125,
"router/selected_tokens_s1": 108.9375,
"step": 2830,
"tokens_trained": 9.272517896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8056737588652483,
"grad_norm": 0.5861411690711975,
"loss": 1.1824,
"loss_ce": 1.1209691762924194,
"loss_region": 0.05859311297535896,
"loss_total": 1.1795623302459717,
"lr": 0.001129572836368834,
"router/selected_tokens_s0": 1184.3125,
"router/selected_tokens_s1": 92.75,
"step": 2840,
"tokens_trained": 9.305283336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8085106382978723,
"grad_norm": 0.8662428855895996,
"loss": 1.1801,
"loss_ce": 1.1683619022369385,
"loss_region": 0.05122409388422966,
"loss_total": 1.2195860147476196,
"lr": 0.0011291659443849829,
"router/selected_tokens_s0": 1079.9375,
"router/selected_tokens_s1": 34.8125,
"step": 2850,
"tokens_trained": 9.338048776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8113475177304964,
"grad_norm": 0.602667510509491,
"loss": 1.1796,
"loss_ce": 1.1227927207946777,
"loss_region": 0.060959592461586,
"loss_total": 1.1837522983551025,
"lr": 0.0011287590524011318,
"router/selected_tokens_s0": 1168.9375,
"router/selected_tokens_s1": 109.5625,
"step": 2860,
"tokens_trained": 9.370814216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8141843971631205,
"grad_norm": 0.3715594708919525,
"loss": 1.1777,
"loss_ce": 1.1824853420257568,
"loss_region": 0.05484374985098839,
"loss_total": 1.237329125404358,
"lr": 0.0011283521604172808,
"router/selected_tokens_s0": 933.75,
"router/selected_tokens_s1": 54.3125,
"step": 2870,
"tokens_trained": 9.403579656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8170212765957446,
"grad_norm": 0.36632469296455383,
"loss": 1.1781,
"loss_ce": 1.083885908126831,
"loss_region": 0.06635577231645584,
"loss_total": 1.150241732597351,
"lr": 0.0011279452684334298,
"router/selected_tokens_s0": 1268.1875,
"router/selected_tokens_s1": 160.25,
"step": 2880,
"tokens_trained": 9.436345096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8198581560283688,
"grad_norm": 0.25131088495254517,
"loss": 1.1792,
"loss_ce": 1.1564133167266846,
"loss_region": 0.0669500008225441,
"loss_total": 1.2233632802963257,
"lr": 0.0011275383764495787,
"router/selected_tokens_s0": 1166.75,
"router/selected_tokens_s1": 155.375,
"step": 2890,
"tokens_trained": 9.469110536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8226950354609929,
"grad_norm": 0.860545814037323,
"loss": 1.1846,
"loss_ce": 1.1339890956878662,
"loss_region": 0.0660734623670578,
"loss_total": 1.2000625133514404,
"lr": 0.0011271314844657277,
"router/selected_tokens_s0": 1135.4375,
"router/selected_tokens_s1": 145.1875,
"step": 2900,
"tokens_trained": 9.501875176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.825531914893617,
"grad_norm": 0.1526106297969818,
"loss": 1.178,
"loss_ce": 1.1420540809631348,
"loss_region": 0.062213458120822906,
"loss_total": 1.2042675018310547,
"lr": 0.0011267245924818767,
"router/selected_tokens_s0": 1171.875,
"router/selected_tokens_s1": 119.25,
"step": 2910,
"tokens_trained": 9.534640608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8283687943262411,
"grad_norm": 0.25495970249176025,
"loss": 1.1782,
"loss_ce": 1.0953720808029175,
"loss_region": 0.06660070270299911,
"loss_total": 1.1619727611541748,
"lr": 0.0011263177004980256,
"router/selected_tokens_s0": 1110.8125,
"router/selected_tokens_s1": 146.125,
"step": 2920,
"tokens_trained": 9.567405248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8312056737588652,
"grad_norm": 0.32902929186820984,
"loss": 1.1811,
"loss_ce": 1.1160013675689697,
"loss_region": 0.06135803461074829,
"loss_total": 1.1773593425750732,
"lr": 0.0011259108085141746,
"router/selected_tokens_s0": 1077.6875,
"router/selected_tokens_s1": 106.3125,
"step": 2930,
"tokens_trained": 9.600170688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8340425531914893,
"grad_norm": 0.25194478034973145,
"loss": 1.1796,
"loss_ce": 1.133124589920044,
"loss_region": 0.04943273961544037,
"loss_total": 1.1825573444366455,
"lr": 0.0011255039165303236,
"router/selected_tokens_s0": 1135.625,
"router/selected_tokens_s1": 21.9375,
"step": 2940,
"tokens_trained": 9.632932368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8368794326241135,
"grad_norm": 0.5080149173736572,
"loss": 1.1806,
"loss_ce": 1.1138414144515991,
"loss_region": 0.060192253440618515,
"loss_total": 1.1740336418151855,
"lr": 0.0011250970245464725,
"router/selected_tokens_s0": 1200.0,
"router/selected_tokens_s1": 106.4375,
"step": 2950,
"tokens_trained": 9.665697808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8397163120567376,
"grad_norm": 0.8673221468925476,
"loss": 1.1768,
"loss_ce": 1.1572374105453491,
"loss_region": 0.055664122104644775,
"loss_total": 1.2129015922546387,
"lr": 0.0011246901325626217,
"router/selected_tokens_s0": 1227.5,
"router/selected_tokens_s1": 72.0,
"step": 2960,
"tokens_trained": 9.698463248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8425531914893617,
"grad_norm": 0.33562785387039185,
"loss": 1.1762,
"loss_ce": 1.088935136795044,
"loss_region": 0.053266432136297226,
"loss_total": 1.142201542854309,
"lr": 0.0011242832405787707,
"router/selected_tokens_s0": 1065.8125,
"router/selected_tokens_s1": 48.4375,
"step": 2970,
"tokens_trained": 9.731228528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8453900709219858,
"grad_norm": 0.5114731788635254,
"loss": 1.178,
"loss_ce": 1.1897213459014893,
"loss_region": 0.05429379269480705,
"loss_total": 1.244015097618103,
"lr": 0.0011238763485949196,
"router/selected_tokens_s0": 1213.8125,
"router/selected_tokens_s1": 60.6875,
"step": 2980,
"tokens_trained": 9.763992368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8482269503546099,
"grad_norm": 0.26606935262680054,
"loss": 1.1757,
"loss_ce": 1.068314790725708,
"loss_region": 0.05756586790084839,
"loss_total": 1.1258807182312012,
"lr": 0.0011234694566110684,
"router/selected_tokens_s0": 1233.625,
"router/selected_tokens_s1": 87.25,
"step": 2990,
"tokens_trained": 9.796757008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.851063829787234,
"grad_norm": 0.770910918712616,
"loss": 1.1768,
"loss_ce": 1.161916732788086,
"loss_region": 0.060496315360069275,
"loss_total": 1.2224130630493164,
"lr": 0.0011230625646272174,
"router/selected_tokens_s0": 1139.5625,
"router/selected_tokens_s1": 104.625,
"step": 3000,
"tokens_trained": 9.829522448
},
{
"epoch": 0.851063829787234,
"eval_ppl": 3.0685293746125137,
"eval_runtime": 2.0114,
"step": 3000,
"tokens_trained": 9.829522448
},
{
"epoch": 0.851063829787234,
"eval_F": 0.00586938687465393,
"eval_F_cds": 0.004950139250741174,
"eval_F_dig": 0.010235174623017424,
"eval_F_exon": 0.005857490384746062,
"eval_F_intron": 0.0057576003851945445,
"eval_F_nig": 0.00577470736019713,
"eval_F_promoter": 0.006416735097803887,
"eval_F_utr": 0.005499834791784355,
"eval_G": 0.04278435178691461,
"eval_G_cds": 0.037835809058036116,
"eval_G_dig": 0.05814518285119931,
"eval_G_exon": 0.042680271146763434,
"eval_G_intron": 0.043167546982243406,
"eval_G_nig": 0.04354123851445412,
"eval_G_promoter": 0.04100065054817289,
"eval_G_utr": 0.039970458206318414,
"eval_avg_bp_per_token": 170.3755471152107,
"eval_bp_per_token/cds": 202.01451905626135,
"eval_bp_per_token/dig": 97.70229007633588,
"eval_bp_per_token/exon": 170.7215777262181,
"eval_bp_per_token/intron": 173.6834676076969,
"eval_bp_per_token/nig": 173.16894824707848,
"eval_bp_per_token/promoter": 155.8424938474159,
"eval_bp_per_token/utr": 181.82364341085272,
"eval_ppl_cds": 3.743007889924154,
"eval_ppl_dig": 1.1305635385016664,
"eval_ppl_exon": 3.308204537970067,
"eval_ppl_intron": 3.091991802801204,
"eval_ppl_nig": 2.9335253140217743,
"eval_ppl_promoter": 3.326653273455676,
"eval_ppl_utr": 3.4125763618627047,
"step": 3000,
"tokens_trained": 9.829522448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8539007092198582,
"grad_norm": 0.29383108019828796,
"loss": 1.17,
"loss_ce": 1.1111640930175781,
"loss_region": 0.057751886546611786,
"loss_total": 1.1689159870147705,
"lr": 0.0011226556726433663,
"router/selected_tokens_s0": 1105.25,
"router/selected_tokens_s1": 82.75,
"step": 3010,
"tokens_trained": 9.862287888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8567375886524823,
"grad_norm": 0.34174391627311707,
"loss": 1.1735,
"loss_ce": 1.113343358039856,
"loss_region": 0.058337848633527756,
"loss_total": 1.1716811656951904,
"lr": 0.0011222487806595153,
"router/selected_tokens_s0": 1087.4375,
"router/selected_tokens_s1": 85.375,
"step": 3020,
"tokens_trained": 9.895048312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8595744680851064,
"grad_norm": 1.0063222646713257,
"loss": 1.1733,
"loss_ce": 1.1626818180084229,
"loss_region": 0.06576195359230042,
"loss_total": 1.2284437417984009,
"lr": 0.0011218418886756645,
"router/selected_tokens_s0": 1179.3125,
"router/selected_tokens_s1": 148.0,
"step": 3030,
"tokens_trained": 9.927812952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8624113475177305,
"grad_norm": 0.5856843590736389,
"loss": 1.1789,
"loss_ce": 1.1485878229141235,
"loss_region": 0.054565493017435074,
"loss_total": 1.203153371810913,
"lr": 0.0011214349966918134,
"router/selected_tokens_s0": 1048.875,
"router/selected_tokens_s1": 56.625,
"step": 3040,
"tokens_trained": 9.960578392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8652482269503546,
"grad_norm": 0.4607069194316864,
"loss": 1.1797,
"loss_ce": 1.0936951637268066,
"loss_region": 0.05745574086904526,
"loss_total": 1.1511509418487549,
"lr": 0.0011210281047079624,
"router/selected_tokens_s0": 1223.0625,
"router/selected_tokens_s1": 84.8125,
"step": 3050,
"tokens_trained": 9.993343832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8680851063829788,
"grad_norm": 0.3751443028450012,
"loss": 1.1749,
"loss_ce": 1.165441870689392,
"loss_region": 0.0589909553527832,
"loss_total": 1.2244328260421753,
"lr": 0.0011206212127241114,
"router/selected_tokens_s0": 1145.6875,
"router/selected_tokens_s1": 93.25,
"step": 3060,
"tokens_trained": 10.026108952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8709219858156029,
"grad_norm": 0.7878003716468811,
"loss": 1.1757,
"loss_ce": 1.1027661561965942,
"loss_region": 0.059977948665618896,
"loss_total": 1.1627440452575684,
"lr": 0.0011202143207402603,
"router/selected_tokens_s0": 1153.9375,
"router/selected_tokens_s1": 99.5,
"step": 3070,
"tokens_trained": 10.058874392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.873758865248227,
"grad_norm": 0.39917951822280884,
"loss": 1.1833,
"loss_ce": 1.0899752378463745,
"loss_region": 0.06287148594856262,
"loss_total": 1.1528466939926147,
"lr": 0.0011198074287564093,
"router/selected_tokens_s0": 1250.375,
"router/selected_tokens_s1": 131.25,
"step": 3080,
"tokens_trained": 10.091635328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8765957446808511,
"grad_norm": 0.45243528485298157,
"loss": 1.1808,
"loss_ce": 1.1440991163253784,
"loss_region": 0.05864295735955238,
"loss_total": 1.202742099761963,
"lr": 0.0011194005367725583,
"router/selected_tokens_s0": 1195.125,
"router/selected_tokens_s1": 93.625,
"step": 3090,
"tokens_trained": 10.124400768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8794326241134752,
"grad_norm": 0.42869076132774353,
"loss": 1.1785,
"loss_ce": 1.150432825088501,
"loss_region": 0.06204836070537567,
"loss_total": 1.212481141090393,
"lr": 0.0011189936447887072,
"router/selected_tokens_s0": 1170.875,
"router/selected_tokens_s1": 117.6875,
"step": 3100,
"tokens_trained": 10.157166208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8822695035460993,
"grad_norm": 0.19406476616859436,
"loss": 1.1745,
"loss_ce": 1.101540207862854,
"loss_region": 0.059803955256938934,
"loss_total": 1.1613441705703735,
"lr": 0.0011185867528048562,
"router/selected_tokens_s0": 1204.625,
"router/selected_tokens_s1": 102.625,
"step": 3110,
"tokens_trained": 10.189931648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8851063829787233,
"grad_norm": 0.6000205278396606,
"loss": 1.1775,
"loss_ce": 1.1167505979537964,
"loss_region": 0.054472386837005615,
"loss_total": 1.1712229251861572,
"lr": 0.0011181798608210052,
"router/selected_tokens_s0": 1106.0625,
"router/selected_tokens_s1": 58.25,
"step": 3120,
"tokens_trained": 10.22269608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8879432624113475,
"grad_norm": 0.16923663020133972,
"loss": 1.1796,
"loss_ce": 1.0365309715270996,
"loss_region": 0.06018022075295448,
"loss_total": 1.0967111587524414,
"lr": 0.0011177729688371541,
"router/selected_tokens_s0": 1182.1875,
"router/selected_tokens_s1": 104.125,
"step": 3130,
"tokens_trained": 10.25546152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8907801418439716,
"grad_norm": 0.4746827781200409,
"loss": 1.1731,
"loss_ce": 1.1875536441802979,
"loss_region": 0.060806721448898315,
"loss_total": 1.2483603954315186,
"lr": 0.001117366076853303,
"router/selected_tokens_s0": 1150.125,
"router/selected_tokens_s1": 104.5,
"step": 3140,
"tokens_trained": 10.28822616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8936170212765957,
"grad_norm": 0.4047585129737854,
"loss": 1.1774,
"loss_ce": 1.0648419857025146,
"loss_region": 0.06984846293926239,
"loss_total": 1.1346904039382935,
"lr": 0.001116959184869452,
"router/selected_tokens_s0": 1133.0625,
"router/selected_tokens_s1": 173.875,
"step": 3150,
"tokens_trained": 10.3209916
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8964539007092198,
"grad_norm": 0.38032910227775574,
"loss": 1.1728,
"loss_ce": 1.1230207681655884,
"loss_region": 0.05686573311686516,
"loss_total": 1.1798864603042603,
"lr": 0.001116552292885601,
"router/selected_tokens_s0": 1178.75,
"router/selected_tokens_s1": 79.1875,
"step": 3160,
"tokens_trained": 10.35375624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8992907801418439,
"grad_norm": 0.4329375922679901,
"loss": 1.1768,
"loss_ce": 1.0851696729660034,
"loss_region": 0.06354688107967377,
"loss_total": 1.1487165689468384,
"lr": 0.00111614540090175,
"router/selected_tokens_s0": 1165.875,
"router/selected_tokens_s1": 129.125,
"step": 3170,
"tokens_trained": 10.38652168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.902127659574468,
"grad_norm": 0.476487398147583,
"loss": 1.1823,
"loss_ce": 1.1869922876358032,
"loss_region": 0.06617600470781326,
"loss_total": 1.2531683444976807,
"lr": 0.001115738508917899,
"router/selected_tokens_s0": 1150.25,
"router/selected_tokens_s1": 150.25,
"step": 3180,
"tokens_trained": 10.41928712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9049645390070922,
"grad_norm": 0.3666301667690277,
"loss": 1.1782,
"loss_ce": 1.0683258771896362,
"loss_region": 0.06172625347971916,
"loss_total": 1.130052089691162,
"lr": 0.001115331616934048,
"router/selected_tokens_s0": 1138.4375,
"router/selected_tokens_s1": 112.625,
"step": 3190,
"tokens_trained": 10.45205256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9078014184397163,
"grad_norm": 0.5340037941932678,
"loss": 1.1745,
"loss_ce": 1.140019416809082,
"loss_region": 0.05862601846456528,
"loss_total": 1.1986454725265503,
"lr": 0.0011149247249501969,
"router/selected_tokens_s0": 1137.0625,
"router/selected_tokens_s1": 89.75,
"step": 3200,
"tokens_trained": 10.4848172
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9106382978723404,
"grad_norm": 0.5549784302711487,
"loss": 1.1714,
"loss_ce": 1.1285208463668823,
"loss_region": 0.055352479219436646,
"loss_total": 1.1838732957839966,
"lr": 0.001114517832966346,
"router/selected_tokens_s0": 1075.1875,
"router/selected_tokens_s1": 63.3125,
"step": 3210,
"tokens_trained": 10.51758264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9134751773049645,
"grad_norm": 0.33541953563690186,
"loss": 1.1744,
"loss_ce": 1.1551395654678345,
"loss_region": 0.059686705470085144,
"loss_total": 1.214826226234436,
"lr": 0.001114110940982495,
"router/selected_tokens_s0": 1107.1875,
"router/selected_tokens_s1": 96.4375,
"step": 3220,
"tokens_trained": 10.55034808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9163120567375886,
"grad_norm": 0.40579476952552795,
"loss": 1.1768,
"loss_ce": 1.1274559497833252,
"loss_region": 0.057040877640247345,
"loss_total": 1.1844968795776367,
"lr": 0.001113704048998644,
"router/selected_tokens_s0": 1134.5,
"router/selected_tokens_s1": 78.5,
"step": 3230,
"tokens_trained": 10.58311352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9191489361702128,
"grad_norm": 0.5760875940322876,
"loss": 1.1751,
"loss_ce": 1.1354435682296753,
"loss_region": 0.06056402251124382,
"loss_total": 1.1960076093673706,
"lr": 0.0011132971570147927,
"router/selected_tokens_s0": 1090.8125,
"router/selected_tokens_s1": 101.25,
"step": 3240,
"tokens_trained": 10.61587896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9219858156028369,
"grad_norm": 0.38739120960235596,
"loss": 1.1773,
"loss_ce": 1.105566143989563,
"loss_region": 0.060275085270404816,
"loss_total": 1.1658412218093872,
"lr": 0.0011128902650309417,
"router/selected_tokens_s0": 1192.9375,
"router/selected_tokens_s1": 105.75,
"step": 3250,
"tokens_trained": 10.6486444
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.924822695035461,
"grad_norm": 0.3400448262691498,
"loss": 1.1631,
"loss_ce": 1.1183065176010132,
"loss_region": 0.05988531932234764,
"loss_total": 1.1781917810440063,
"lr": 0.0011124833730470907,
"router/selected_tokens_s0": 1182.9375,
"router/selected_tokens_s1": 102.9375,
"step": 3260,
"tokens_trained": 10.68140984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9276595744680851,
"grad_norm": 0.5918727517127991,
"loss": 1.1708,
"loss_ce": 1.0822169780731201,
"loss_region": 0.05995599180459976,
"loss_total": 1.142172932624817,
"lr": 0.0011120764810632396,
"router/selected_tokens_s0": 1097.0625,
"router/selected_tokens_s1": 96.125,
"step": 3270,
"tokens_trained": 10.714171944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9304964539007092,
"grad_norm": 0.6673521995544434,
"loss": 1.172,
"loss_ce": 1.0720325708389282,
"loss_region": 0.05878286063671112,
"loss_total": 1.1308153867721558,
"lr": 0.0011116695890793888,
"router/selected_tokens_s0": 1054.0,
"router/selected_tokens_s1": 84.75,
"step": 3280,
"tokens_trained": 10.746937384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9333333333333333,
"grad_norm": 0.3518356382846832,
"loss": 1.1647,
"loss_ce": 1.1526938676834106,
"loss_region": 0.061706800013780594,
"loss_total": 1.2144006490707397,
"lr": 0.0011112626970955378,
"router/selected_tokens_s0": 1207.1875,
"router/selected_tokens_s1": 118.6875,
"step": 3290,
"tokens_trained": 10.779702824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9361702127659575,
"grad_norm": 0.9049731492996216,
"loss": 1.1696,
"loss_ce": 1.2116420269012451,
"loss_region": 0.060429565608501434,
"loss_total": 1.2720715999603271,
"lr": 0.0011108558051116867,
"router/selected_tokens_s0": 1074.625,
"router/selected_tokens_s1": 98.875,
"step": 3300,
"tokens_trained": 10.812468264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9390070921985816,
"grad_norm": 0.40723493695259094,
"loss": 1.1751,
"loss_ce": 1.027906060218811,
"loss_region": 0.062023263424634933,
"loss_total": 1.0899293422698975,
"lr": 0.0011104489131278357,
"router/selected_tokens_s0": 1176.875,
"router/selected_tokens_s1": 119.5625,
"step": 3310,
"tokens_trained": 10.845230648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9418439716312057,
"grad_norm": 0.2104732096195221,
"loss": 1.1716,
"loss_ce": 1.0564253330230713,
"loss_region": 0.07024026662111282,
"loss_total": 1.1266655921936035,
"lr": 0.0011100420211439847,
"router/selected_tokens_s0": 1101.1875,
"router/selected_tokens_s1": 170.5625,
"step": 3320,
"tokens_trained": 10.877996088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9446808510638298,
"grad_norm": 0.6985082030296326,
"loss": 1.1758,
"loss_ce": 1.1633176803588867,
"loss_region": 0.057024937123060226,
"loss_total": 1.2203426361083984,
"lr": 0.0011096351291601336,
"router/selected_tokens_s0": 1152.0625,
"router/selected_tokens_s1": 78.9375,
"step": 3330,
"tokens_trained": 10.910761528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9475177304964539,
"grad_norm": 0.5326957106590271,
"loss": 1.1734,
"loss_ce": 1.1307435035705566,
"loss_region": 0.05962308123707771,
"loss_total": 1.1903666257858276,
"lr": 0.0011092282371762826,
"router/selected_tokens_s0": 1052.8125,
"router/selected_tokens_s1": 91.3125,
"step": 3340,
"tokens_trained": 10.943526968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.950354609929078,
"grad_norm": 0.4644201397895813,
"loss": 1.1747,
"loss_ce": 1.1294314861297607,
"loss_region": 0.059848666191101074,
"loss_total": 1.1892801523208618,
"lr": 0.0011088213451924316,
"router/selected_tokens_s0": 1206.9375,
"router/selected_tokens_s1": 103.0,
"step": 3350,
"tokens_trained": 10.976292408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9531914893617022,
"grad_norm": 0.519744873046875,
"loss": 1.1695,
"loss_ce": 1.0610030889511108,
"loss_region": 0.06155804172158241,
"loss_total": 1.1225610971450806,
"lr": 0.0011084144532085805,
"router/selected_tokens_s0": 1226.5,
"router/selected_tokens_s1": 118.375,
"step": 3360,
"tokens_trained": 11.009057848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9560283687943263,
"grad_norm": 0.4544057250022888,
"loss": 1.1712,
"loss_ce": 1.036798357963562,
"loss_region": 0.05716359615325928,
"loss_total": 1.0939619541168213,
"lr": 0.0011080075612247295,
"router/selected_tokens_s0": 1070.8125,
"router/selected_tokens_s1": 76.125,
"step": 3370,
"tokens_trained": 11.041823288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9588652482269504,
"grad_norm": 0.48027774691581726,
"loss": 1.1747,
"loss_ce": 1.0815472602844238,
"loss_region": 0.058336447924375534,
"loss_total": 1.1398837566375732,
"lr": 0.0011076006692408785,
"router/selected_tokens_s0": 1209.5625,
"router/selected_tokens_s1": 91.6875,
"step": 3380,
"tokens_trained": 11.074587928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9617021276595744,
"grad_norm": 0.40910616517066956,
"loss": 1.1696,
"loss_ce": 1.1013418436050415,
"loss_region": 0.059236638247966766,
"loss_total": 1.1605784893035889,
"lr": 0.0011071937772570274,
"router/selected_tokens_s0": 1173.5,
"router/selected_tokens_s1": 97.125,
"step": 3390,
"tokens_trained": 11.107353368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9645390070921985,
"grad_norm": 0.6562957763671875,
"loss": 1.1791,
"loss_ce": 1.15192711353302,
"loss_region": 0.06069476902484894,
"loss_total": 1.2126219272613525,
"lr": 0.0011067868852731764,
"router/selected_tokens_s0": 1176.25,
"router/selected_tokens_s1": 108.5,
"step": 3400,
"tokens_trained": 11.140118808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9673758865248226,
"grad_norm": 0.6277413964271545,
"loss": 1.1721,
"loss_ce": 1.1012977361679077,
"loss_region": 0.05599859729409218,
"loss_total": 1.1572962999343872,
"lr": 0.0011063799932893254,
"router/selected_tokens_s0": 1253.3125,
"router/selected_tokens_s1": 75.5,
"step": 3410,
"tokens_trained": 11.172884248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9702127659574468,
"grad_norm": 0.6205341815948486,
"loss": 1.1722,
"loss_ce": 1.1080474853515625,
"loss_region": 0.06207379698753357,
"loss_total": 1.1701213121414185,
"lr": 0.0011059731013054743,
"router/selected_tokens_s0": 1329.125,
"router/selected_tokens_s1": 130.3125,
"step": 3420,
"tokens_trained": 11.205649688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9730496453900709,
"grad_norm": 0.29150086641311646,
"loss": 1.1658,
"loss_ce": 1.180068850517273,
"loss_region": 0.058709632605314255,
"loss_total": 1.2387784719467163,
"lr": 0.0011055662093216233,
"router/selected_tokens_s0": 1133.125,
"router/selected_tokens_s1": 90.125,
"step": 3430,
"tokens_trained": 11.238415128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.975886524822695,
"grad_norm": 0.041430745273828506,
"loss": 1.174,
"loss_ce": 1.1881239414215088,
"loss_region": 0.06059211492538452,
"loss_total": 1.248716115951538,
"lr": 0.0011051593173377723,
"router/selected_tokens_s0": 1123.5625,
"router/selected_tokens_s1": 103.875,
"step": 3440,
"tokens_trained": 11.27117724
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9787234042553191,
"grad_norm": 0.3598027527332306,
"loss": 1.1723,
"loss_ce": 1.0409948825836182,
"loss_region": 0.06112197786569595,
"loss_total": 1.1021168231964111,
"lr": 0.0011047524253539212,
"router/selected_tokens_s0": 1166.875,
"router/selected_tokens_s1": 111.4375,
"step": 3450,
"tokens_trained": 11.30394268
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9815602836879432,
"grad_norm": 0.21557830274105072,
"loss": 1.1673,
"loss_ce": 1.0955760478973389,
"loss_region": 0.06010117009282112,
"loss_total": 1.1556771993637085,
"lr": 0.0011043455333700704,
"router/selected_tokens_s0": 1128.0,
"router/selected_tokens_s1": 100.25,
"step": 3460,
"tokens_trained": 11.33670812
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9843971631205674,
"grad_norm": 0.7135093808174133,
"loss": 1.1701,
"loss_ce": 1.1059309244155884,
"loss_region": 0.05792264640331268,
"loss_total": 1.1638535261154175,
"lr": 0.0011039386413862194,
"router/selected_tokens_s0": 1225.5625,
"router/selected_tokens_s1": 90.0,
"step": 3470,
"tokens_trained": 11.369471136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9872340425531915,
"grad_norm": 0.7960752844810486,
"loss": 1.1644,
"loss_ce": 1.0885987281799316,
"loss_region": 0.057787343859672546,
"loss_total": 1.1463860273361206,
"lr": 0.0011035317494023683,
"router/selected_tokens_s0": 1155.75,
"router/selected_tokens_s1": 84.8125,
"step": 3480,
"tokens_trained": 11.402236576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9900709219858156,
"grad_norm": 0.406982958316803,
"loss": 1.1727,
"loss_ce": 1.0770787000656128,
"loss_region": 0.06020737439393997,
"loss_total": 1.1372860670089722,
"lr": 0.001103124857418517,
"router/selected_tokens_s0": 1090.6875,
"router/selected_tokens_s1": 98.5625,
"step": 3490,
"tokens_trained": 11.435000416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9929078014184397,
"grad_norm": 0.3447991609573364,
"loss": 1.1623,
"loss_ce": 1.0214577913284302,
"loss_region": 0.05888646841049194,
"loss_total": 1.0803442001342773,
"lr": 0.001102717965434666,
"router/selected_tokens_s0": 1209.5625,
"router/selected_tokens_s1": 96.125,
"step": 3500,
"tokens_trained": 11.467765856
},
{
"epoch": 0.9929078014184397,
"eval_ppl": 3.038240767914852,
"eval_runtime": 2.008,
"step": 3500,
"tokens_trained": 11.467765856
},
{
"epoch": 0.9929078014184397,
"eval_F": 0.00850206537874902,
"eval_F_cds": 0.00689964962716737,
"eval_F_dig": 0.014923040862567388,
"eval_F_exon": 0.00789606012421685,
"eval_F_intron": 0.008428047437812242,
"eval_F_nig": 0.00872954509959683,
"eval_F_promoter": 0.008634167140420694,
"eval_F_utr": 0.007599577919655515,
"eval_G": 0.046269897373441414,
"eval_G_cds": 0.04158991148032522,
"eval_G_dig": 0.05773201885889523,
"eval_G_exon": 0.04576241340325628,
"eval_G_intron": 0.04624071162133245,
"eval_G_nig": 0.04734882132161264,
"eval_G_promoter": 0.04556376903981245,
"eval_G_utr": 0.04369505411235224,
"eval_avg_bp_per_token": 117.61847921088776,
"eval_bp_per_token/cds": 144.93489583333334,
"eval_bp_per_token/dig": 67.01047120418848,
"eval_bp_per_token/exon": 126.64543889845095,
"eval_bp_per_token/intron": 118.65144416647715,
"eval_bp_per_token/nig": 114.55350635008283,
"eval_bp_per_token/promoter": 115.81893004115226,
"eval_bp_per_token/utr": 131.58625525946704,
"eval_ppl_cds": 3.7194951394016527,
"eval_ppl_dig": 1.1234349213687769,
"eval_ppl_exon": 3.2792592230741118,
"eval_ppl_intron": 3.0595564329951,
"eval_ppl_nig": 2.8979520169575914,
"eval_ppl_promoter": 3.3032037253575854,
"eval_ppl_utr": 3.397446939966626,
"step": 3500,
"tokens_trained": 11.467765856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9957446808510638,
"grad_norm": 0.3863132894039154,
"loss": 1.1693,
"loss_ce": 1.1104393005371094,
"loss_region": 0.06132273003458977,
"loss_total": 1.1717619895935059,
"lr": 0.001102311073450815,
"router/selected_tokens_s0": 1200.25,
"router/selected_tokens_s1": 114.75,
"step": 3510,
"tokens_trained": 11.500531296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9985815602836879,
"grad_norm": 0.36480513215065,
"loss": 1.1735,
"loss_ce": 1.152591347694397,
"loss_region": 0.06367353349924088,
"loss_total": 1.2162648439407349,
"lr": 0.001101904181466964,
"router/selected_tokens_s0": 1090.5,
"router/selected_tokens_s1": 124.8125,
"step": 3520,
"tokens_trained": 11.533296736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.001418439716312,
"grad_norm": 0.4523515999317169,
"loss": 1.1662,
"loss_ce": 1.1153082847595215,
"loss_region": 0.058803122490644455,
"loss_total": 1.1741113662719727,
"lr": 0.0011014972894831132,
"router/selected_tokens_s0": 1205.0,
"router/selected_tokens_s1": 95.3125,
"step": 3530,
"tokens_trained": 11.566062176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.004255319148936,
"grad_norm": 0.43514934182167053,
"loss": 1.1669,
"loss_ce": 1.129390001296997,
"loss_region": 0.058623556047677994,
"loss_total": 1.1880135536193848,
"lr": 0.0011010903974992621,
"router/selected_tokens_s0": 1195.875,
"router/selected_tokens_s1": 92.9375,
"step": 3540,
"tokens_trained": 11.598827616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0070921985815602,
"grad_norm": 0.6533243060112,
"loss": 1.1678,
"loss_ce": 1.1146398782730103,
"loss_region": 0.061271265149116516,
"loss_total": 1.1759111881256104,
"lr": 0.001100683505515411,
"router/selected_tokens_s0": 1133.4375,
"router/selected_tokens_s1": 109.125,
"step": 3550,
"tokens_trained": 11.631593056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0099290780141843,
"grad_norm": 0.49821382761001587,
"loss": 1.1726,
"loss_ce": 1.166283130645752,
"loss_region": 0.06056985631585121,
"loss_total": 1.2268530130386353,
"lr": 0.00110027661353156,
"router/selected_tokens_s0": 1262.8125,
"router/selected_tokens_s1": 112.0,
"step": 3560,
"tokens_trained": 11.664358496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0127659574468084,
"grad_norm": 0.26887351274490356,
"loss": 1.1715,
"loss_ce": 1.030143141746521,
"loss_region": 0.06456618756055832,
"loss_total": 1.0947092771530151,
"lr": 0.001099869721547709,
"router/selected_tokens_s0": 1178.4375,
"router/selected_tokens_s1": 138.125,
"step": 3570,
"tokens_trained": 11.697123936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0156028368794325,
"grad_norm": 0.40560099482536316,
"loss": 1.1731,
"loss_ce": 1.1501858234405518,
"loss_region": 0.06369136273860931,
"loss_total": 1.2138772010803223,
"lr": 0.001099462829563858,
"router/selected_tokens_s0": 1185.0,
"router/selected_tokens_s1": 132.1875,
"step": 3580,
"tokens_trained": 11.729887776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0184397163120567,
"grad_norm": 0.6615747809410095,
"loss": 1.1718,
"loss_ce": 1.0754194259643555,
"loss_region": 0.058519624173641205,
"loss_total": 1.1339390277862549,
"lr": 0.001099055937580007,
"router/selected_tokens_s0": 1184.375,
"router/selected_tokens_s1": 91.1875,
"step": 3590,
"tokens_trained": 11.762653216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0212765957446808,
"grad_norm": 0.22958390414714813,
"loss": 1.1725,
"loss_ce": 1.121917486190796,
"loss_region": 0.057618919759988785,
"loss_total": 1.1795364618301392,
"lr": 0.001098649045596156,
"router/selected_tokens_s0": 1027.0625,
"router/selected_tokens_s1": 76.125,
"step": 3600,
"tokens_trained": 11.795417056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0241134751773049,
"grad_norm": 0.37797319889068604,
"loss": 1.1711,
"loss_ce": 1.1041591167449951,
"loss_region": 0.05944184213876724,
"loss_total": 1.1636009216308594,
"lr": 0.0010982421536123049,
"router/selected_tokens_s0": 1129.5625,
"router/selected_tokens_s1": 95.1875,
"step": 3610,
"tokens_trained": 11.828182496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.026950354609929,
"grad_norm": 0.2652418613433838,
"loss": 1.1693,
"loss_ce": 1.1603299379348755,
"loss_region": 0.06184834986925125,
"loss_total": 1.222178339958191,
"lr": 0.0010978352616284538,
"router/selected_tokens_s0": 1040.3125,
"router/selected_tokens_s1": 106.3125,
"step": 3620,
"tokens_trained": 11.860946336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0297872340425531,
"grad_norm": 0.1825254261493683,
"loss": 1.1628,
"loss_ce": 1.0894384384155273,
"loss_region": 0.06096874922513962,
"loss_total": 1.1504071950912476,
"lr": 0.0010974283696446028,
"router/selected_tokens_s0": 1087.5,
"router/selected_tokens_s1": 103.625,
"step": 3630,
"tokens_trained": 11.893711776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0326241134751772,
"grad_norm": 0.6617575287818909,
"loss": 1.1621,
"loss_ce": 1.007035493850708,
"loss_region": 0.06269294023513794,
"loss_total": 1.0697283744812012,
"lr": 0.0010970214776607518,
"router/selected_tokens_s0": 1297.125,
"router/selected_tokens_s1": 135.875,
"step": 3640,
"tokens_trained": 11.926477216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0354609929078014,
"grad_norm": 0.3751685321331024,
"loss": 1.1598,
"loss_ce": 1.1335476636886597,
"loss_region": 0.059122197329998016,
"loss_total": 1.1926698684692383,
"lr": 0.0010966145856769007,
"router/selected_tokens_s0": 1139.875,
"router/selected_tokens_s1": 93.25,
"step": 3650,
"tokens_trained": 11.959242656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0382978723404255,
"grad_norm": 0.22427456080913544,
"loss": 1.1729,
"loss_ce": 1.051111102104187,
"loss_region": 0.05901859700679779,
"loss_total": 1.110129714012146,
"lr": 0.0010962076936930497,
"router/selected_tokens_s0": 1197.5625,
"router/selected_tokens_s1": 96.0,
"step": 3660,
"tokens_trained": 11.992008096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0411347517730496,
"grad_norm": 0.5057801604270935,
"loss": 1.1656,
"loss_ce": 1.129104495048523,
"loss_region": 0.05949552729725838,
"loss_total": 1.1886000633239746,
"lr": 0.0010958008017091987,
"router/selected_tokens_s0": 1171.25,
"router/selected_tokens_s1": 99.0,
"step": 3670,
"tokens_trained": 12.024773536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0439716312056737,
"grad_norm": 0.2510657012462616,
"loss": 1.1706,
"loss_ce": 1.0839104652404785,
"loss_region": 0.060210950672626495,
"loss_total": 1.1441214084625244,
"lr": 0.0010953939097253476,
"router/selected_tokens_s0": 1161.6875,
"router/selected_tokens_s1": 102.1875,
"step": 3680,
"tokens_trained": 12.057538976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0468085106382978,
"grad_norm": 0.2641873061656952,
"loss": 1.1578,
"loss_ce": 1.1306475400924683,
"loss_region": 0.06020496413111687,
"loss_total": 1.1908525228500366,
"lr": 0.0010949870177414966,
"router/selected_tokens_s0": 1051.5625,
"router/selected_tokens_s1": 95.3125,
"step": 3690,
"tokens_trained": 12.090304416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.049645390070922,
"grad_norm": 0.44993430376052856,
"loss": 1.1666,
"loss_ce": 1.0936851501464844,
"loss_region": 0.06084345653653145,
"loss_total": 1.1545286178588867,
"lr": 0.0010945801257576456,
"router/selected_tokens_s0": 1209.5625,
"router/selected_tokens_s1": 111.5,
"step": 3700,
"tokens_trained": 12.123069856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.052482269503546,
"grad_norm": 1.0144351720809937,
"loss": 1.1686,
"loss_ce": 1.113016128540039,
"loss_region": 0.06407901644706726,
"loss_total": 1.1770951747894287,
"lr": 0.0010941732337737947,
"router/selected_tokens_s0": 981.5,
"router/selected_tokens_s1": 114.9375,
"step": 3710,
"tokens_trained": 12.155835296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0553191489361702,
"grad_norm": 0.5086681842803955,
"loss": 1.1676,
"loss_ce": 1.087952733039856,
"loss_region": 0.06016521528363228,
"loss_total": 1.1481178998947144,
"lr": 0.0010937663417899437,
"router/selected_tokens_s0": 1133.25,
"router/selected_tokens_s1": 100.625,
"step": 3720,
"tokens_trained": 12.188600576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0581560283687943,
"grad_norm": 0.2624291181564331,
"loss": 1.166,
"loss_ce": 1.1549427509307861,
"loss_region": 0.060712967067956924,
"loss_total": 1.2156556844711304,
"lr": 0.0010933594498060927,
"router/selected_tokens_s0": 1177.875,
"router/selected_tokens_s1": 108.5,
"step": 3730,
"tokens_trained": 12.221366016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0609929078014184,
"grad_norm": 0.1420605629682541,
"loss": 1.1632,
"loss_ce": 1.1388192176818848,
"loss_region": 0.05755767226219177,
"loss_total": 1.196376919746399,
"lr": 0.0010929525578222414,
"router/selected_tokens_s0": 1136.75,
"router/selected_tokens_s1": 82.0625,
"step": 3740,
"tokens_trained": 12.254131456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0638297872340425,
"grad_norm": 0.24459026753902435,
"loss": 1.1666,
"loss_ce": 1.0850238800048828,
"loss_region": 0.05748440697789192,
"loss_total": 1.1425082683563232,
"lr": 0.0010925456658383904,
"router/selected_tokens_s0": 1181.0,
"router/selected_tokens_s1": 83.125,
"step": 3750,
"tokens_trained": 12.286896896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0666666666666667,
"grad_norm": 0.3674156963825226,
"loss": 1.1656,
"loss_ce": 1.1350717544555664,
"loss_region": 0.060446847230196,
"loss_total": 1.1955186128616333,
"lr": 0.0010921387738545394,
"router/selected_tokens_s0": 1207.0,
"router/selected_tokens_s1": 108.0625,
"step": 3760,
"tokens_trained": 12.319662336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0695035460992908,
"grad_norm": 0.3036234378814697,
"loss": 1.159,
"loss_ce": 1.0529462099075317,
"loss_region": 0.06247229501605034,
"loss_total": 1.115418553352356,
"lr": 0.0010917318818706883,
"router/selected_tokens_s0": 1305.6875,
"router/selected_tokens_s1": 132.8125,
"step": 3770,
"tokens_trained": 12.352427776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0723404255319149,
"grad_norm": 0.6468788385391235,
"loss": 1.1664,
"loss_ce": 1.1280831098556519,
"loss_region": 0.06378360092639923,
"loss_total": 1.1918667554855347,
"lr": 0.0010913249898868375,
"router/selected_tokens_s0": 1151.0,
"router/selected_tokens_s1": 129.5625,
"step": 3780,
"tokens_trained": 12.385193216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.075177304964539,
"grad_norm": 0.2749446630477905,
"loss": 1.166,
"loss_ce": 1.115018367767334,
"loss_region": 0.05860990658402443,
"loss_total": 1.173628330230713,
"lr": 0.0010909180979029865,
"router/selected_tokens_s0": 1103.9375,
"router/selected_tokens_s1": 87.1875,
"step": 3790,
"tokens_trained": 12.417958656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0780141843971631,
"grad_norm": 0.3598608076572418,
"loss": 1.1649,
"loss_ce": 1.0172104835510254,
"loss_region": 0.05948943644762039,
"loss_total": 1.07669997215271,
"lr": 0.0010905112059191354,
"router/selected_tokens_s0": 1112.375,
"router/selected_tokens_s1": 94.125,
"step": 3800,
"tokens_trained": 12.450724096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0808510638297872,
"grad_norm": 0.3002602458000183,
"loss": 1.1664,
"loss_ce": 1.0674883127212524,
"loss_region": 0.05848415940999985,
"loss_total": 1.1259725093841553,
"lr": 0.0010901043139352844,
"router/selected_tokens_s0": 1162.125,
"router/selected_tokens_s1": 90.0,
"step": 3810,
"tokens_trained": 12.483489536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0836879432624114,
"grad_norm": 0.3532373309135437,
"loss": 1.1578,
"loss_ce": 1.1755656003952026,
"loss_region": 0.0601661391556263,
"loss_total": 1.2357317209243774,
"lr": 0.0010896974219514334,
"router/selected_tokens_s0": 1189.0625,
"router/selected_tokens_s1": 103.5625,
"step": 3820,
"tokens_trained": 12.516254976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0865248226950355,
"grad_norm": 0.3577895760536194,
"loss": 1.1682,
"loss_ce": 1.184386134147644,
"loss_region": 0.06025141850113869,
"loss_total": 1.2446376085281372,
"lr": 0.0010892905299675823,
"router/selected_tokens_s0": 1258.5,
"router/selected_tokens_s1": 109.8125,
"step": 3830,
"tokens_trained": 12.549020416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0893617021276596,
"grad_norm": 0.3110039234161377,
"loss": 1.1665,
"loss_ce": 1.101610541343689,
"loss_region": 0.05868781730532646,
"loss_total": 1.1602983474731445,
"lr": 0.0010888836379837313,
"router/selected_tokens_s0": 1235.0,
"router/selected_tokens_s1": 95.5625,
"step": 3840,
"tokens_trained": 12.581785856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0921985815602837,
"grad_norm": 0.35310038924217224,
"loss": 1.1656,
"loss_ce": 1.0989956855773926,
"loss_region": 0.05978355556726456,
"loss_total": 1.158779263496399,
"lr": 0.0010884767459998803,
"router/selected_tokens_s0": 1111.4375,
"router/selected_tokens_s1": 96.6875,
"step": 3850,
"tokens_trained": 12.614549696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0950354609929078,
"grad_norm": 0.12972678244113922,
"loss": 1.1596,
"loss_ce": 1.0401544570922852,
"loss_region": 0.05898905545473099,
"loss_total": 1.0991435050964355,
"lr": 0.0010880698540160292,
"router/selected_tokens_s0": 1188.875,
"router/selected_tokens_s1": 95.0625,
"step": 3860,
"tokens_trained": 12.647315136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.097872340425532,
"grad_norm": 0.5242721438407898,
"loss": 1.1574,
"loss_ce": 1.0777604579925537,
"loss_region": 0.06169040501117706,
"loss_total": 1.1394509077072144,
"lr": 0.0010876629620321782,
"router/selected_tokens_s0": 1112.3125,
"router/selected_tokens_s1": 110.4375,
"step": 3870,
"tokens_trained": 12.680079808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.100709219858156,
"grad_norm": 0.27978047728538513,
"loss": 1.1627,
"loss_ce": 1.0561823844909668,
"loss_region": 0.06105148047208786,
"loss_total": 1.1172338724136353,
"lr": 0.0010872560700483272,
"router/selected_tokens_s0": 1237.75,
"router/selected_tokens_s1": 114.375,
"step": 3880,
"tokens_trained": 12.712844448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1035460992907802,
"grad_norm": 0.6515991687774658,
"loss": 1.1645,
"loss_ce": 1.1110643148422241,
"loss_region": 0.05981144309043884,
"loss_total": 1.1708757877349854,
"lr": 0.0010868491780644761,
"router/selected_tokens_s0": 1082.875,
"router/selected_tokens_s1": 95.0,
"step": 3890,
"tokens_trained": 12.745609888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1063829787234043,
"grad_norm": 0.38111910223960876,
"loss": 1.1597,
"loss_ce": 1.1041885614395142,
"loss_region": 0.0614677332341671,
"loss_total": 1.165656328201294,
"lr": 0.001086442286080625,
"router/selected_tokens_s0": 1140.0,
"router/selected_tokens_s1": 111.4375,
"step": 3900,
"tokens_trained": 12.778375328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1092198581560284,
"grad_norm": 0.18037572503089905,
"loss": 1.1681,
"loss_ce": 1.0915865898132324,
"loss_region": 0.06151479482650757,
"loss_total": 1.1531014442443848,
"lr": 0.001086035394096774,
"router/selected_tokens_s0": 1100.375,
"router/selected_tokens_s1": 108.5,
"step": 3910,
"tokens_trained": 12.811139968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1120567375886525,
"grad_norm": 0.4105333983898163,
"loss": 1.1675,
"loss_ce": 1.118082880973816,
"loss_region": 0.058428194373846054,
"loss_total": 1.1765110492706299,
"lr": 0.001085628502112923,
"router/selected_tokens_s0": 1064.75,
"router/selected_tokens_s1": 84.5625,
"step": 3920,
"tokens_trained": 12.843905408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1148936170212767,
"grad_norm": 0.31400883197784424,
"loss": 1.1628,
"loss_ce": 1.0323964357376099,
"loss_region": 0.05940539017319679,
"loss_total": 1.0918018817901611,
"lr": 0.001085221610129072,
"router/selected_tokens_s0": 1196.875,
"router/selected_tokens_s1": 98.8125,
"step": 3930,
"tokens_trained": 12.876670848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1177304964539008,
"grad_norm": 0.30934834480285645,
"loss": 1.1643,
"loss_ce": 1.0789693593978882,
"loss_region": 0.05930301174521446,
"loss_total": 1.1382724046707153,
"lr": 0.001084814718145221,
"router/selected_tokens_s0": 1260.875,
"router/selected_tokens_s1": 103.0,
"step": 3940,
"tokens_trained": 12.909436288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1205673758865249,
"grad_norm": 0.13591480255126953,
"loss": 1.1572,
"loss_ce": 1.131282925605774,
"loss_region": 0.0612853579223156,
"loss_total": 1.192568302154541,
"lr": 0.00108440782616137,
"router/selected_tokens_s0": 1195.6875,
"router/selected_tokens_s1": 114.375,
"step": 3950,
"tokens_trained": 12.942201728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.123404255319149,
"grad_norm": 0.5181418657302856,
"loss": 1.155,
"loss_ce": 1.0501888990402222,
"loss_region": 0.060443535447120667,
"loss_total": 1.1106324195861816,
"lr": 0.001084000934177519,
"router/selected_tokens_s0": 1220.875,
"router/selected_tokens_s1": 108.0,
"step": 3960,
"tokens_trained": 12.974967168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1262411347517731,
"grad_norm": 0.5863410234451294,
"loss": 1.1628,
"loss_ce": 1.0781110525131226,
"loss_region": 0.057768795639276505,
"loss_total": 1.1358798742294312,
"lr": 0.001083594042193668,
"router/selected_tokens_s0": 1121.0,
"router/selected_tokens_s1": 81.8125,
"step": 3970,
"tokens_trained": 13.007732608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1290780141843972,
"grad_norm": 0.3233559727668762,
"loss": 1.1578,
"loss_ce": 1.1254554986953735,
"loss_region": 0.06000566482543945,
"loss_total": 1.185461163520813,
"lr": 0.001083187150209817,
"router/selected_tokens_s0": 1204.9375,
"router/selected_tokens_s1": 104.3125,
"step": 3980,
"tokens_trained": 13.040497248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1319148936170214,
"grad_norm": 0.6287395358085632,
"loss": 1.1612,
"loss_ce": 1.0396240949630737,
"loss_region": 0.06029755249619484,
"loss_total": 1.099921703338623,
"lr": 0.0010827802582259658,
"router/selected_tokens_s0": 1285.6875,
"router/selected_tokens_s1": 113.0625,
"step": 3990,
"tokens_trained": 13.073261888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1347517730496455,
"grad_norm": 0.3079366385936737,
"loss": 1.1648,
"loss_ce": 1.0844305753707886,
"loss_region": 0.058176081627607346,
"loss_total": 1.1426066160202026,
"lr": 0.0010823733662421147,
"router/selected_tokens_s0": 1028.875,
"router/selected_tokens_s1": 79.375,
"step": 4000,
"tokens_trained": 13.106027328
},
{
"epoch": 1.1347517730496455,
"eval_ppl": 3.0168909900495806,
"eval_runtime": 2.0409,
"step": 4000,
"tokens_trained": 13.106027328
},
{
"epoch": 1.1347517730496455,
"eval_F": 0.008799303274372658,
"eval_F_cds": 0.007753121911777918,
"eval_F_dig": 0.010547699038987422,
"eval_F_exon": 0.00823582174746198,
"eval_F_intron": 0.008802201374555693,
"eval_F_nig": 0.008589756691044479,
"eval_F_promoter": 0.00924873139199461,
"eval_F_utr": 0.008601485808081346,
"eval_G": 0.04391245460885404,
"eval_G_cds": 0.038505093460830114,
"eval_G_dig": 0.05892092399796859,
"eval_G_exon": 0.0432158734931572,
"eval_G_intron": 0.04394914080325982,
"eval_G_nig": 0.044819965408996784,
"eval_G_promoter": 0.043103368419918464,
"eval_G_utr": 0.04227885581319747,
"eval_avg_bp_per_token": 113.64536132223428,
"eval_bp_per_token/cds": 128.9803012746234,
"eval_bp_per_token/dig": 94.80740740740741,
"eval_bp_per_token/exon": 121.42079207920793,
"eval_bp_per_token/intron": 113.60794390488219,
"eval_bp_per_token/nig": 116.41773288439956,
"eval_bp_per_token/promoter": 108.12293682413204,
"eval_bp_per_token/utr": 116.25898389095416,
"eval_ppl_cds": 3.71392302020704,
"eval_ppl_dig": 1.1094123517044365,
"eval_ppl_exon": 3.2568894446430092,
"eval_ppl_intron": 3.037550000900063,
"eval_ppl_nig": 2.8726060355692917,
"eval_ppl_promoter": 3.291369088440733,
"eval_ppl_utr": 3.3899334301119,
"step": 4000,
"tokens_trained": 13.106027328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1375886524822696,
"grad_norm": 0.3257603943347931,
"loss": 1.158,
"loss_ce": 1.1083933115005493,
"loss_region": 0.06035665422677994,
"loss_total": 1.1687499284744263,
"lr": 0.0010819664742582637,
"router/selected_tokens_s0": 1088.5,
"router/selected_tokens_s1": 99.5625,
"step": 4010,
"tokens_trained": 13.138791968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1404255319148937,
"grad_norm": 0.3850681185722351,
"loss": 1.1573,
"loss_ce": 1.131569504737854,
"loss_region": 0.059893906116485596,
"loss_total": 1.1914634704589844,
"lr": 0.0010815595822744127,
"router/selected_tokens_s0": 1119.5,
"router/selected_tokens_s1": 98.0,
"step": 4020,
"tokens_trained": 13.171557408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1432624113475178,
"grad_norm": 0.39153483510017395,
"loss": 1.1633,
"loss_ce": 1.0569000244140625,
"loss_region": 0.058693308383226395,
"loss_total": 1.1155933141708374,
"lr": 0.0010811526902905618,
"router/selected_tokens_s0": 1058.75,
"router/selected_tokens_s1": 85.125,
"step": 4030,
"tokens_trained": 13.204322848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1460992907801417,
"grad_norm": 0.26381781697273254,
"loss": 1.1584,
"loss_ce": 1.073149561882019,
"loss_region": 0.06016290560364723,
"loss_total": 1.133312463760376,
"lr": 0.0010807457983067108,
"router/selected_tokens_s0": 1159.875,
"router/selected_tokens_s1": 102.625,
"step": 4040,
"tokens_trained": 13.237088288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.148936170212766,
"grad_norm": 0.45886608958244324,
"loss": 1.1609,
"loss_ce": 1.0923855304718018,
"loss_region": 0.06084444373846054,
"loss_total": 1.1532299518585205,
"lr": 0.0010803389063228598,
"router/selected_tokens_s0": 1083.25,
"router/selected_tokens_s1": 102.1875,
"step": 4050,
"tokens_trained": 13.269853704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.15177304964539,
"grad_norm": 0.5070511698722839,
"loss": 1.1679,
"loss_ce": 1.1500152349472046,
"loss_region": 0.06119634956121445,
"loss_total": 1.2112115621566772,
"lr": 0.0010799320143390087,
"router/selected_tokens_s0": 1188.3125,
"router/selected_tokens_s1": 112.9375,
"step": 4060,
"tokens_trained": 13.302619144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1546099290780143,
"grad_norm": 0.33511748909950256,
"loss": 1.1592,
"loss_ce": 1.1047053337097168,
"loss_region": 0.059827499091625214,
"loss_total": 1.1645327806472778,
"lr": 0.0010795251223551577,
"router/selected_tokens_s0": 1166.8125,
"router/selected_tokens_s1": 100.875,
"step": 4070,
"tokens_trained": 13.335384584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1574468085106382,
"grad_norm": 0.457485556602478,
"loss": 1.1593,
"loss_ce": 1.0707032680511475,
"loss_region": 0.06051037833094597,
"loss_total": 1.131213665008545,
"lr": 0.0010791182303713067,
"router/selected_tokens_s0": 1190.8125,
"router/selected_tokens_s1": 107.6875,
"step": 4080,
"tokens_trained": 13.368150024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1602836879432625,
"grad_norm": 0.22557711601257324,
"loss": 1.1636,
"loss_ce": 1.1058050394058228,
"loss_region": 0.06027519330382347,
"loss_total": 1.1660802364349365,
"lr": 0.0010787113383874556,
"router/selected_tokens_s0": 1245.875,
"router/selected_tokens_s1": 109.8125,
"step": 4090,
"tokens_trained": 13.400914384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1631205673758864,
"grad_norm": 0.2770388126373291,
"loss": 1.1638,
"loss_ce": 1.115969181060791,
"loss_region": 0.06104355677962303,
"loss_total": 1.1770126819610596,
"lr": 0.0010783044464036046,
"router/selected_tokens_s0": 1222.9375,
"router/selected_tokens_s1": 115.0625,
"step": 4100,
"tokens_trained": 13.433677248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1659574468085105,
"grad_norm": 0.32032445073127747,
"loss": 1.1597,
"loss_ce": 1.1212356090545654,
"loss_region": 0.05913654342293739,
"loss_total": 1.1803721189498901,
"lr": 0.0010778975544197536,
"router/selected_tokens_s0": 1088.9375,
"router/selected_tokens_s1": 90.5625,
"step": 4110,
"tokens_trained": 13.466442688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1687943262411347,
"grad_norm": 0.52224200963974,
"loss": 1.1598,
"loss_ce": 1.11467707157135,
"loss_region": 0.058027200400829315,
"loss_total": 1.1727042198181152,
"lr": 0.0010774906624359025,
"router/selected_tokens_s0": 1134.0,
"router/selected_tokens_s1": 84.875,
"step": 4120,
"tokens_trained": 13.499207928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1716312056737588,
"grad_norm": 0.31186333298683167,
"loss": 1.1604,
"loss_ce": 1.1230143308639526,
"loss_region": 0.06094019487500191,
"loss_total": 1.1839544773101807,
"lr": 0.0010770837704520515,
"router/selected_tokens_s0": 1114.4375,
"router/selected_tokens_s1": 105.6875,
"step": 4130,
"tokens_trained": 13.531973368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.174468085106383,
"grad_norm": 0.5124596953392029,
"loss": 1.1671,
"loss_ce": 1.1359376907348633,
"loss_region": 0.05806201323866844,
"loss_total": 1.1939996480941772,
"lr": 0.0010766768784682005,
"router/selected_tokens_s0": 1088.4375,
"router/selected_tokens_s1": 82.125,
"step": 4140,
"tokens_trained": 13.564734752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.177304964539007,
"grad_norm": 0.4620847702026367,
"loss": 1.1632,
"loss_ce": 1.1566661596298218,
"loss_region": 0.06023990362882614,
"loss_total": 1.2169060707092285,
"lr": 0.0010762699864843494,
"router/selected_tokens_s0": 1154.9375,
"router/selected_tokens_s1": 103.625,
"step": 4150,
"tokens_trained": 13.597500192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1801418439716311,
"grad_norm": 0.1790580153465271,
"loss": 1.1489,
"loss_ce": 1.0375577211380005,
"loss_region": 0.05896264687180519,
"loss_total": 1.0965204238891602,
"lr": 0.0010758630945004984,
"router/selected_tokens_s0": 1118.625,
"router/selected_tokens_s1": 90.9375,
"step": 4160,
"tokens_trained": 13.630265632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1829787234042553,
"grad_norm": 0.43203845620155334,
"loss": 1.156,
"loss_ce": 1.1000916957855225,
"loss_region": 0.05994558706879616,
"loss_total": 1.1600372791290283,
"lr": 0.0010754562025166474,
"router/selected_tokens_s0": 1172.6875,
"router/selected_tokens_s1": 102.4375,
"step": 4170,
"tokens_trained": 13.663031072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1858156028368794,
"grad_norm": 0.2970203459262848,
"loss": 1.1578,
"loss_ce": 1.1184784173965454,
"loss_region": 0.06149717792868614,
"loss_total": 1.1799756288528442,
"lr": 0.0010750493105327963,
"router/selected_tokens_s0": 1102.0,
"router/selected_tokens_s1": 108.875,
"step": 4180,
"tokens_trained": 13.695793424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1886524822695035,
"grad_norm": 0.18619275093078613,
"loss": 1.1542,
"loss_ce": 1.0847108364105225,
"loss_region": 0.05977150425314903,
"loss_total": 1.1444823741912842,
"lr": 0.0010746424185489453,
"router/selected_tokens_s0": 1201.125,
"router/selected_tokens_s1": 102.5,
"step": 4190,
"tokens_trained": 13.728557088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1914893617021276,
"grad_norm": 0.4238639175891876,
"loss": 1.1619,
"loss_ce": 1.0785303115844727,
"loss_region": 0.06018838286399841,
"loss_total": 1.1387187242507935,
"lr": 0.0010742355265650943,
"router/selected_tokens_s0": 1141.3125,
"router/selected_tokens_s1": 101.8125,
"step": 4200,
"tokens_trained": 13.761322528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1943262411347517,
"grad_norm": 0.25106480717658997,
"loss": 1.1582,
"loss_ce": 1.0537445545196533,
"loss_region": 0.06022384390234947,
"loss_total": 1.1139683723449707,
"lr": 0.0010738286345812434,
"router/selected_tokens_s0": 1278.625,
"router/selected_tokens_s1": 112.1875,
"step": 4210,
"tokens_trained": 13.794087968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1971631205673758,
"grad_norm": 0.5989421606063843,
"loss": 1.1702,
"loss_ce": 1.1273736953735352,
"loss_region": 0.06084655970335007,
"loss_total": 1.1882202625274658,
"lr": 0.0010734217425973924,
"router/selected_tokens_s0": 1064.9375,
"router/selected_tokens_s1": 101.0625,
"step": 4220,
"tokens_trained": 13.826853408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2,
"grad_norm": 0.27547699213027954,
"loss": 1.1629,
"loss_ce": 1.063729166984558,
"loss_region": 0.05869840458035469,
"loss_total": 1.1224275827407837,
"lr": 0.0010730148506135414,
"router/selected_tokens_s0": 1075.6875,
"router/selected_tokens_s1": 86.0625,
"step": 4230,
"tokens_trained": 13.859618048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.202836879432624,
"grad_norm": 0.3737616240978241,
"loss": 1.155,
"loss_ce": 1.0955439805984497,
"loss_region": 0.05996520072221756,
"loss_total": 1.1555092334747314,
"lr": 0.0010726079586296901,
"router/selected_tokens_s0": 1201.9375,
"router/selected_tokens_s1": 104.0625,
"step": 4240,
"tokens_trained": 13.892383488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2056737588652482,
"grad_norm": 0.22606416046619415,
"loss": 1.1549,
"loss_ce": 1.1174266338348389,
"loss_region": 0.060742564499378204,
"loss_total": 1.1781692504882812,
"lr": 0.001072201066645839,
"router/selected_tokens_s0": 1183.0,
"router/selected_tokens_s1": 108.875,
"step": 4250,
"tokens_trained": 13.925146528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2085106382978723,
"grad_norm": 0.2320932000875473,
"loss": 1.1593,
"loss_ce": 1.0501296520233154,
"loss_region": 0.0594555027782917,
"loss_total": 1.109585165977478,
"lr": 0.001071794174661988,
"router/selected_tokens_s0": 1174.625,
"router/selected_tokens_s1": 96.5,
"step": 4260,
"tokens_trained": 13.957911968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2113475177304964,
"grad_norm": 0.28906700015068054,
"loss": 1.1569,
"loss_ce": 1.0986992120742798,
"loss_region": 0.05964815616607666,
"loss_total": 1.1583473682403564,
"lr": 0.0010713872826781372,
"router/selected_tokens_s0": 1062.25,
"router/selected_tokens_s1": 92.6875,
"step": 4270,
"tokens_trained": 13.990673272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2141843971631205,
"grad_norm": 0.2225026935338974,
"loss": 1.1536,
"loss_ce": 1.060550570487976,
"loss_region": 0.059843163937330246,
"loss_total": 1.1203937530517578,
"lr": 0.0010709803906942862,
"router/selected_tokens_s0": 1115.375,
"router/selected_tokens_s1": 97.375,
"step": 4280,
"tokens_trained": 14.023438712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2170212765957447,
"grad_norm": 0.20924420654773712,
"loss": 1.16,
"loss_ce": 1.0435292720794678,
"loss_region": 0.05888236686587334,
"loss_total": 1.1024116277694702,
"lr": 0.0010705734987104352,
"router/selected_tokens_s0": 1131.125,
"router/selected_tokens_s1": 91.0625,
"step": 4290,
"tokens_trained": 14.056204152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2198581560283688,
"grad_norm": 0.2678433656692505,
"loss": 1.1598,
"loss_ce": 1.075086236000061,
"loss_region": 0.06008180230855942,
"loss_total": 1.1351680755615234,
"lr": 0.0010701666067265841,
"router/selected_tokens_s0": 1239.25,
"router/selected_tokens_s1": 107.4375,
"step": 4300,
"tokens_trained": 14.088969592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.222695035460993,
"grad_norm": 0.1258992999792099,
"loss": 1.1546,
"loss_ce": 1.0750923156738281,
"loss_region": 0.05863800272345543,
"loss_total": 1.1337302923202515,
"lr": 0.001069759714742733,
"router/selected_tokens_s0": 1133.375,
"router/selected_tokens_s1": 89.625,
"step": 4310,
"tokens_trained": 14.121735032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.225531914893617,
"grad_norm": 0.2875233292579651,
"loss": 1.1516,
"loss_ce": 1.1637287139892578,
"loss_region": 0.05875501036643982,
"loss_total": 1.22248375415802,
"lr": 0.001069352822758882,
"router/selected_tokens_s0": 1170.875,
"router/selected_tokens_s1": 92.9375,
"step": 4320,
"tokens_trained": 14.154499672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2283687943262411,
"grad_norm": 0.2648707926273346,
"loss": 1.156,
"loss_ce": 1.1075119972229004,
"loss_region": 0.062029022723436356,
"loss_total": 1.1695410013198853,
"lr": 0.001068945930775031,
"router/selected_tokens_s0": 1142.9375,
"router/selected_tokens_s1": 116.0,
"step": 4330,
"tokens_trained": 14.187265112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2312056737588652,
"grad_norm": 0.1432296186685562,
"loss": 1.1563,
"loss_ce": 1.0992697477340698,
"loss_region": 0.05967455357313156,
"loss_total": 1.1589442491531372,
"lr": 0.00106853903879118,
"router/selected_tokens_s0": 1193.75,
"router/selected_tokens_s1": 100.875,
"step": 4340,
"tokens_trained": 14.220030552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2340425531914894,
"grad_norm": 0.3481175899505615,
"loss": 1.1505,
"loss_ce": 1.050426721572876,
"loss_region": 0.060125932097435,
"loss_total": 1.1105526685714722,
"lr": 0.001068132146807329,
"router/selected_tokens_s0": 1168.6875,
"router/selected_tokens_s1": 103.3125,
"step": 4350,
"tokens_trained": 14.252795992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2368794326241135,
"grad_norm": 0.4038959741592407,
"loss": 1.1534,
"loss_ce": 1.0327410697937012,
"loss_region": 0.05936980992555618,
"loss_total": 1.0921108722686768,
"lr": 0.001067725254823478,
"router/selected_tokens_s0": 1323.1875,
"router/selected_tokens_s1": 103.6875,
"step": 4360,
"tokens_trained": 14.285561432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2397163120567376,
"grad_norm": 0.2256237119436264,
"loss": 1.155,
"loss_ce": 1.1195412874221802,
"loss_region": 0.059909120202064514,
"loss_total": 1.1794503927230835,
"lr": 0.0010673183628396269,
"router/selected_tokens_s0": 1134.25,
"router/selected_tokens_s1": 99.75,
"step": 4370,
"tokens_trained": 14.318326792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2425531914893617,
"grad_norm": 0.29938000440597534,
"loss": 1.1542,
"loss_ce": 1.0233904123306274,
"loss_region": 0.060831498354673386,
"loss_total": 1.0842219591140747,
"lr": 0.0010669114708557758,
"router/selected_tokens_s0": 1160.1875,
"router/selected_tokens_s1": 107.8125,
"step": 4380,
"tokens_trained": 14.351092216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2453900709219858,
"grad_norm": 0.13847291469573975,
"loss": 1.1538,
"loss_ce": 1.1036982536315918,
"loss_region": 0.060592759400606155,
"loss_total": 1.1642910242080688,
"lr": 0.0010665045788719248,
"router/selected_tokens_s0": 1177.9375,
"router/selected_tokens_s1": 108.25,
"step": 4390,
"tokens_trained": 14.383857656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.24822695035461,
"grad_norm": 0.23555094003677368,
"loss": 1.1552,
"loss_ce": 1.0954946279525757,
"loss_region": 0.058905620127916336,
"loss_total": 1.1544002294540405,
"lr": 0.0010660976868880738,
"router/selected_tokens_s0": 1160.3125,
"router/selected_tokens_s1": 93.0,
"step": 4400,
"tokens_trained": 14.416623096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.251063829787234,
"grad_norm": 0.3022359609603882,
"loss": 1.1594,
"loss_ce": 0.9607714414596558,
"loss_region": 0.05570393428206444,
"loss_total": 1.0164753198623657,
"lr": 0.0010656907949042227,
"router/selected_tokens_s0": 1184.0,
"router/selected_tokens_s1": 67.9375,
"step": 4410,
"tokens_trained": 14.449387936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2539007092198582,
"grad_norm": 0.2786804437637329,
"loss": 1.1606,
"loss_ce": 1.0460023880004883,
"loss_region": 0.06192931532859802,
"loss_total": 1.1079317331314087,
"lr": 0.0010652839029203717,
"router/selected_tokens_s0": 1173.0625,
"router/selected_tokens_s1": 117.5,
"step": 4420,
"tokens_trained": 14.48214904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2567375886524823,
"grad_norm": 0.3700876533985138,
"loss": 1.1532,
"loss_ce": 1.1097447872161865,
"loss_region": 0.05792572721838951,
"loss_total": 1.167670488357544,
"lr": 0.0010648770109365207,
"router/selected_tokens_s0": 1125.5,
"router/selected_tokens_s1": 83.5625,
"step": 4430,
"tokens_trained": 14.51491448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2595744680851064,
"grad_norm": 0.2731934189796448,
"loss": 1.1575,
"loss_ce": 1.1346114873886108,
"loss_region": 0.061083775013685226,
"loss_total": 1.1956952810287476,
"lr": 0.0010644701189526696,
"router/selected_tokens_s0": 1189.125,
"router/selected_tokens_s1": 112.0625,
"step": 4440,
"tokens_trained": 14.54767992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2624113475177305,
"grad_norm": 0.36961379647254944,
"loss": 1.1538,
"loss_ce": 1.0246363878250122,
"loss_region": 0.05892600491642952,
"loss_total": 1.0835623741149902,
"lr": 0.0010640632269688186,
"router/selected_tokens_s0": 1223.9375,
"router/selected_tokens_s1": 95.8125,
"step": 4450,
"tokens_trained": 14.58044536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2652482269503547,
"grad_norm": 0.14416196942329407,
"loss": 1.1549,
"loss_ce": 1.117681622505188,
"loss_region": 0.06037626788020134,
"loss_total": 1.1780579090118408,
"lr": 0.0010636563349849678,
"router/selected_tokens_s0": 1238.3125,
"router/selected_tokens_s1": 109.9375,
"step": 4460,
"tokens_trained": 14.613210784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2680851063829788,
"grad_norm": 0.4883098304271698,
"loss": 1.1595,
"loss_ce": 1.0619388818740845,
"loss_region": 0.061121564358472824,
"loss_total": 1.1230604648590088,
"lr": 0.0010632494430011167,
"router/selected_tokens_s0": 1183.125,
"router/selected_tokens_s1": 112.5625,
"step": 4470,
"tokens_trained": 14.645976224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.270921985815603,
"grad_norm": 0.1840326339006424,
"loss": 1.1592,
"loss_ce": 1.0874097347259521,
"loss_region": 0.05963713675737381,
"loss_total": 1.1470469236373901,
"lr": 0.0010628425510172657,
"router/selected_tokens_s0": 1231.875,
"router/selected_tokens_s1": 103.1875,
"step": 4480,
"tokens_trained": 14.678741664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.273758865248227,
"grad_norm": 0.20033717155456543,
"loss": 1.159,
"loss_ce": 1.1302992105484009,
"loss_region": 0.05996955186128616,
"loss_total": 1.1902687549591064,
"lr": 0.0010624356590334145,
"router/selected_tokens_s0": 1110.875,
"router/selected_tokens_s1": 98.25,
"step": 4490,
"tokens_trained": 14.711504648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2765957446808511,
"grad_norm": 0.2271454632282257,
"loss": 1.1473,
"loss_ce": 1.1464464664459229,
"loss_region": 0.06053486838936806,
"loss_total": 1.2069813013076782,
"lr": 0.0010620287670495634,
"router/selected_tokens_s0": 1056.5,
"router/selected_tokens_s1": 98.4375,
"step": 4500,
"tokens_trained": 14.744270088
},
{
"epoch": 1.2765957446808511,
"eval_ppl": 2.9954127013498857,
"eval_runtime": 2.0087,
"step": 4500,
"tokens_trained": 14.744270088
},
{
"epoch": 1.2765957446808511,
"eval_F": 0.008274678388596935,
"eval_F_cds": 0.0066031803072500225,
"eval_F_dig": 0.014141729822642394,
"eval_F_exon": 0.008004783843655291,
"eval_F_intron": 0.007904768622592151,
"eval_F_nig": 0.009468013519949251,
"eval_F_promoter": 0.00811172172741246,
"eval_F_utr": 0.007279820082923866,
"eval_G": 0.04156769006890505,
"eval_G_cds": 0.035999211801500314,
"eval_G_dig": 0.05599459369384327,
"eval_G_exon": 0.04039431247536728,
"eval_G_intron": 0.04149980615442974,
"eval_G_nig": 0.04239440492074479,
"eval_G_promoter": 0.04131640431714937,
"eval_G_utr": 0.03994073071993477,
"eval_avg_bp_per_token": 120.85061836095859,
"eval_bp_per_token/cds": 151.4421768707483,
"eval_bp_per_token/dig": 70.71270718232044,
"eval_bp_per_token/exon": 124.92529711375212,
"eval_bp_per_token/intron": 126.50591658583899,
"eval_bp_per_token/nig": 105.61877609204765,
"eval_bp_per_token/promoter": 123.27839065541856,
"eval_bp_per_token/utr": 137.36603221083456,
"eval_ppl_cds": 3.7043501190815795,
"eval_ppl_dig": 1.0892991213759757,
"eval_ppl_exon": 3.23873666990306,
"eval_ppl_intron": 3.016729298210796,
"eval_ppl_nig": 2.8426754714039,
"eval_ppl_promoter": 3.277698950952891,
"eval_ppl_utr": 3.3800323407396746,
"step": 4500,
"tokens_trained": 14.744270088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2794326241134752,
"grad_norm": 0.07886938750743866,
"loss": 1.1559,
"loss_ce": 1.0758130550384521,
"loss_region": 0.06231748312711716,
"loss_total": 1.13813054561615,
"lr": 0.0010616218750657124,
"router/selected_tokens_s0": 1096.1875,
"router/selected_tokens_s1": 114.75,
"step": 4510,
"tokens_trained": 14.777033928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2822695035460994,
"grad_norm": 0.5984835624694824,
"loss": 1.1483,
"loss_ce": 1.105970025062561,
"loss_region": 0.05724368616938591,
"loss_total": 1.1632137298583984,
"lr": 0.0010612149830818616,
"router/selected_tokens_s0": 1149.875,
"router/selected_tokens_s1": 79.625,
"step": 4520,
"tokens_trained": 14.809799368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2851063829787235,
"grad_norm": 0.4306280016899109,
"loss": 1.1542,
"loss_ce": 1.1445868015289307,
"loss_region": 0.06630415469408035,
"loss_total": 1.2108910083770752,
"lr": 0.0010608080910980105,
"router/selected_tokens_s0": 1140.625,
"router/selected_tokens_s1": 148.4375,
"step": 4530,
"tokens_trained": 14.842564808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2879432624113476,
"grad_norm": 0.1167333573102951,
"loss": 1.16,
"loss_ce": 1.031152367591858,
"loss_region": 0.060010798275470734,
"loss_total": 1.091163158416748,
"lr": 0.0010604011991141595,
"router/selected_tokens_s0": 1240.1875,
"router/selected_tokens_s1": 106.9375,
"step": 4540,
"tokens_trained": 14.875330248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2907801418439715,
"grad_norm": 0.5103814005851746,
"loss": 1.1598,
"loss_ce": 1.1224370002746582,
"loss_region": 0.05744566395878792,
"loss_total": 1.1798826456069946,
"lr": 0.0010599943071303085,
"router/selected_tokens_s0": 1076.0,
"router/selected_tokens_s1": 77.125,
"step": 4550,
"tokens_trained": 14.908095688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2936170212765958,
"grad_norm": 0.12912671267986298,
"loss": 1.1535,
"loss_ce": 1.1043033599853516,
"loss_region": 0.06229260936379433,
"loss_total": 1.1665959358215332,
"lr": 0.0010595874151464574,
"router/selected_tokens_s0": 1132.125,
"router/selected_tokens_s1": 117.3125,
"step": 4560,
"tokens_trained": 14.940861128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2964539007092197,
"grad_norm": 0.25441470742225647,
"loss": 1.1488,
"loss_ce": 0.9986916184425354,
"loss_region": 0.062223441898822784,
"loss_total": 1.0609151124954224,
"lr": 0.0010591805231626064,
"router/selected_tokens_s0": 1216.125,
"router/selected_tokens_s1": 121.75,
"step": 4570,
"tokens_trained": 14.973625768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.299290780141844,
"grad_norm": 0.2726980745792389,
"loss": 1.1528,
"loss_ce": 1.057322382926941,
"loss_region": 0.058404162526130676,
"loss_total": 1.1157265901565552,
"lr": 0.0010587736311787554,
"router/selected_tokens_s0": 1172.5625,
"router/selected_tokens_s1": 90.375,
"step": 4580,
"tokens_trained": 15.006387136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.302127659574468,
"grad_norm": 0.31760281324386597,
"loss": 1.1548,
"loss_ce": 1.113600730895996,
"loss_region": 0.058456115424633026,
"loss_total": 1.172056794166565,
"lr": 0.0010583667391949043,
"router/selected_tokens_s0": 1064.375,
"router/selected_tokens_s1": 83.8125,
"step": 4590,
"tokens_trained": 15.039152576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3049645390070923,
"grad_norm": 0.1993570178747177,
"loss": 1.1595,
"loss_ce": 1.0727800130844116,
"loss_region": 0.05827302485704422,
"loss_total": 1.13105309009552,
"lr": 0.0010579598472110533,
"router/selected_tokens_s0": 1154.6875,
"router/selected_tokens_s1": 88.0,
"step": 4600,
"tokens_trained": 15.071918016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3078014184397162,
"grad_norm": 0.16275088489055634,
"loss": 1.1532,
"loss_ce": 1.1068168878555298,
"loss_region": 0.060309939086437225,
"loss_total": 1.1671267747879028,
"lr": 0.0010575529552272023,
"router/selected_tokens_s0": 1102.875,
"router/selected_tokens_s1": 100.75,
"step": 4610,
"tokens_trained": 15.104683456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3106382978723405,
"grad_norm": 0.2760368585586548,
"loss": 1.156,
"loss_ce": 1.1134077310562134,
"loss_region": 0.06077075004577637,
"loss_total": 1.1741784811019897,
"lr": 0.0010571460632433512,
"router/selected_tokens_s0": 1141.5625,
"router/selected_tokens_s1": 106.25,
"step": 4620,
"tokens_trained": 15.137448096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3134751773049644,
"grad_norm": 0.0931464284658432,
"loss": 1.1559,
"loss_ce": 1.072306752204895,
"loss_region": 0.059092313051223755,
"loss_total": 1.1313990354537964,
"lr": 0.0010567391712595002,
"router/selected_tokens_s0": 1171.75,
"router/selected_tokens_s1": 95.125,
"step": 4630,
"tokens_trained": 15.170210824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3163120567375888,
"grad_norm": 0.16534562408924103,
"loss": 1.1556,
"loss_ce": 1.1088744401931763,
"loss_region": 0.059825487434864044,
"loss_total": 1.1686999797821045,
"lr": 0.0010563322792756492,
"router/selected_tokens_s0": 1191.25,
"router/selected_tokens_s1": 102.6875,
"step": 4640,
"tokens_trained": 15.202976264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3191489361702127,
"grad_norm": 0.4237407445907593,
"loss": 1.1544,
"loss_ce": 1.0543153285980225,
"loss_region": 0.058653030544519424,
"loss_total": 1.1129683256149292,
"lr": 0.0010559253872917981,
"router/selected_tokens_s0": 1030.9375,
"router/selected_tokens_s1": 83.25,
"step": 4650,
"tokens_trained": 15.235741704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.321985815602837,
"grad_norm": 0.17439590394496918,
"loss": 1.1521,
"loss_ce": 1.1104930639266968,
"loss_region": 0.05929058790206909,
"loss_total": 1.169783592224121,
"lr": 0.001055518495307947,
"router/selected_tokens_s0": 1081.25,
"router/selected_tokens_s1": 91.1875,
"step": 4660,
"tokens_trained": 15.268507144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.324822695035461,
"grad_norm": 0.3554675877094269,
"loss": 1.1561,
"loss_ce": 1.1227957010269165,
"loss_region": 0.059759471565485,
"loss_total": 1.1825551986694336,
"lr": 0.001055111603324096,
"router/selected_tokens_s0": 1069.25,
"router/selected_tokens_s1": 94.1875,
"step": 4670,
"tokens_trained": 15.30127256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.327659574468085,
"grad_norm": 0.23464754223823547,
"loss": 1.1521,
"loss_ce": 1.1011435985565186,
"loss_region": 0.05946500226855278,
"loss_total": 1.1606086492538452,
"lr": 0.001054704711340245,
"router/selected_tokens_s0": 1173.1875,
"router/selected_tokens_s1": 97.4375,
"step": 4680,
"tokens_trained": 15.334037984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3304964539007091,
"grad_norm": 0.3527086675167084,
"loss": 1.1585,
"loss_ce": 1.0524513721466064,
"loss_region": 0.060822706669569016,
"loss_total": 1.113274097442627,
"lr": 0.001054297819356394,
"router/selected_tokens_s0": 1101.25,
"router/selected_tokens_s1": 103.0625,
"step": 4690,
"tokens_trained": 15.366803424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3333333333333333,
"grad_norm": 0.19632120430469513,
"loss": 1.151,
"loss_ce": 1.102612853050232,
"loss_region": 0.06399323046207428,
"loss_total": 1.166606068611145,
"lr": 0.0010538909273725432,
"router/selected_tokens_s0": 1176.5625,
"router/selected_tokens_s1": 134.375,
"step": 4700,
"tokens_trained": 15.399568864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3361702127659574,
"grad_norm": 0.2851898670196533,
"loss": 1.151,
"loss_ce": 1.15898597240448,
"loss_region": 0.0606791190803051,
"loss_total": 1.2196650505065918,
"lr": 0.0010534840353886921,
"router/selected_tokens_s0": 1198.0625,
"router/selected_tokens_s1": 109.25,
"step": 4710,
"tokens_trained": 15.432334288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3390070921985815,
"grad_norm": 0.1474008411169052,
"loss": 1.1528,
"loss_ce": 0.9653110504150391,
"loss_region": 0.05874474346637726,
"loss_total": 1.0240558385849,
"lr": 0.001053077143404841,
"router/selected_tokens_s0": 1149.625,
"router/selected_tokens_s1": 91.8125,
"step": 4720,
"tokens_trained": 15.465099728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3418439716312056,
"grad_norm": 0.31901198625564575,
"loss": 1.15,
"loss_ce": 1.0836107730865479,
"loss_region": 0.058840882033109665,
"loss_total": 1.1424516439437866,
"lr": 0.0010526702514209898,
"router/selected_tokens_s0": 1199.3125,
"router/selected_tokens_s1": 94.9375,
"step": 4730,
"tokens_trained": 15.497864368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3446808510638297,
"grad_norm": 0.2621752917766571,
"loss": 1.1487,
"loss_ce": 1.131207823753357,
"loss_region": 0.06052137166261673,
"loss_total": 1.191729187965393,
"lr": 0.0010522633594371388,
"router/selected_tokens_s0": 1059.5,
"router/selected_tokens_s1": 98.25,
"step": 4740,
"tokens_trained": 15.530629808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3475177304964538,
"grad_norm": 0.37631991505622864,
"loss": 1.151,
"loss_ce": 1.1528443098068237,
"loss_region": 0.06003797799348831,
"loss_total": 1.2128822803497314,
"lr": 0.0010518564674532878,
"router/selected_tokens_s0": 1172.875,
"router/selected_tokens_s1": 102.75,
"step": 4750,
"tokens_trained": 15.563395248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.350354609929078,
"grad_norm": 0.251646488904953,
"loss": 1.1564,
"loss_ce": 1.126339077949524,
"loss_region": 0.06007569283246994,
"loss_total": 1.1864147186279297,
"lr": 0.0010514495754694367,
"router/selected_tokens_s0": 1109.3125,
"router/selected_tokens_s1": 99.0625,
"step": 4760,
"tokens_trained": 15.596158264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.353191489361702,
"grad_norm": 0.38772666454315186,
"loss": 1.1487,
"loss_ce": 1.1305615901947021,
"loss_region": 0.06020316854119301,
"loss_total": 1.1907647848129272,
"lr": 0.001051042683485586,
"router/selected_tokens_s0": 1102.625,
"router/selected_tokens_s1": 99.3125,
"step": 4770,
"tokens_trained": 15.628923704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3560283687943262,
"grad_norm": 0.245202898979187,
"loss": 1.1532,
"loss_ce": 1.166459321975708,
"loss_region": 0.05978211760520935,
"loss_total": 1.2262414693832397,
"lr": 0.0010506357915017349,
"router/selected_tokens_s0": 1139.75,
"router/selected_tokens_s1": 98.4375,
"step": 4780,
"tokens_trained": 15.661689144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3588652482269503,
"grad_norm": 0.4050356149673462,
"loss": 1.1557,
"loss_ce": 1.081703782081604,
"loss_region": 0.060910604894161224,
"loss_total": 1.1426143646240234,
"lr": 0.0010502288995178838,
"router/selected_tokens_s0": 1165.0,
"router/selected_tokens_s1": 109.375,
"step": 4790,
"tokens_trained": 15.694454584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3617021276595744,
"grad_norm": 0.14703965187072754,
"loss": 1.1565,
"loss_ce": 1.0962260961532593,
"loss_region": 0.0606972873210907,
"loss_total": 1.1569234132766724,
"lr": 0.0010498220075340328,
"router/selected_tokens_s0": 1093.625,
"router/selected_tokens_s1": 102.75,
"step": 4800,
"tokens_trained": 15.727220024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3645390070921986,
"grad_norm": 0.5923725962638855,
"loss": 1.1497,
"loss_ce": 1.1643304824829102,
"loss_region": 0.05974184721708298,
"loss_total": 1.2240723371505737,
"lr": 0.0010494151155501818,
"router/selected_tokens_s0": 1086.3125,
"router/selected_tokens_s1": 94.1875,
"step": 4810,
"tokens_trained": 15.759985464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3673758865248227,
"grad_norm": 0.08134971559047699,
"loss": 1.1468,
"loss_ce": 1.1429718732833862,
"loss_region": 0.06080538406968117,
"loss_total": 1.2037773132324219,
"lr": 0.0010490082235663307,
"router/selected_tokens_s0": 1200.8125,
"router/selected_tokens_s1": 110.4375,
"step": 4820,
"tokens_trained": 15.792750904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3702127659574468,
"grad_norm": 0.32185447216033936,
"loss": 1.1552,
"loss_ce": 1.062546730041504,
"loss_region": 0.06265987455844879,
"loss_total": 1.1252065896987915,
"lr": 0.0010486013315824797,
"router/selected_tokens_s0": 1130.375,
"router/selected_tokens_s1": 122.375,
"step": 4830,
"tokens_trained": 15.825515544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.373049645390071,
"grad_norm": 0.19900231063365936,
"loss": 1.1491,
"loss_ce": 1.0900709629058838,
"loss_region": 0.06174982339143753,
"loss_total": 1.1518207788467407,
"lr": 0.0010481944395986287,
"router/selected_tokens_s0": 1148.875,
"router/selected_tokens_s1": 114.8125,
"step": 4840,
"tokens_trained": 15.858280984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.375886524822695,
"grad_norm": 0.20787717401981354,
"loss": 1.1468,
"loss_ce": 1.1013059616088867,
"loss_region": 0.05997852236032486,
"loss_total": 1.1612844467163086,
"lr": 0.0010477875476147776,
"router/selected_tokens_s0": 1236.5625,
"router/selected_tokens_s1": 106.375,
"step": 4850,
"tokens_trained": 15.891045624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3787234042553191,
"grad_norm": 0.09310303628444672,
"loss": 1.1474,
"loss_ce": 1.0274229049682617,
"loss_region": 0.05929532274603844,
"loss_total": 1.086718201637268,
"lr": 0.0010473806556309266,
"router/selected_tokens_s0": 1027.0,
"router/selected_tokens_s1": 88.0,
"step": 4860,
"tokens_trained": 15.923810264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3815602836879433,
"grad_norm": 0.2037133127450943,
"loss": 1.1491,
"loss_ce": 1.0613118410110474,
"loss_region": 0.058327823877334595,
"loss_total": 1.1196396350860596,
"lr": 0.0010469737636470756,
"router/selected_tokens_s0": 1138.3125,
"router/selected_tokens_s1": 87.4375,
"step": 4870,
"tokens_trained": 15.956575704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3843971631205674,
"grad_norm": 0.5275424122810364,
"loss": 1.1516,
"loss_ce": 1.0648127794265747,
"loss_region": 0.0595739372074604,
"loss_total": 1.1243866682052612,
"lr": 0.0010465668716632245,
"router/selected_tokens_s0": 1167.5625,
"router/selected_tokens_s1": 98.625,
"step": 4880,
"tokens_trained": 15.989339352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3872340425531915,
"grad_norm": 0.11888913810253143,
"loss": 1.1478,
"loss_ce": 1.0950626134872437,
"loss_region": 0.061253614723682404,
"loss_total": 1.1563162803649902,
"lr": 0.0010461599796793735,
"router/selected_tokens_s0": 1192.125,
"router/selected_tokens_s1": 114.375,
"step": 4890,
"tokens_trained": 16.022103992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3900709219858156,
"grad_norm": 0.3772846460342407,
"loss": 1.1548,
"loss_ce": 1.051941156387329,
"loss_region": 0.06041061133146286,
"loss_total": 1.1123517751693726,
"lr": 0.0010457530876955225,
"router/selected_tokens_s0": 1167.25,
"router/selected_tokens_s1": 105.8125,
"step": 4900,
"tokens_trained": 16.054869432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3929078014184397,
"grad_norm": 0.12513701617717743,
"loss": 1.1473,
"loss_ce": 1.0917131900787354,
"loss_region": 0.05870034545660019,
"loss_total": 1.1504135131835938,
"lr": 0.0010453461957116714,
"router/selected_tokens_s0": 1071.0625,
"router/selected_tokens_s1": 86.3125,
"step": 4910,
"tokens_trained": 16.087634872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3957446808510638,
"grad_norm": 0.12635989487171173,
"loss": 1.1531,
"loss_ce": 1.0633745193481445,
"loss_region": 0.05978614464402199,
"loss_total": 1.123160719871521,
"lr": 0.0010449393037278204,
"router/selected_tokens_s0": 1174.75,
"router/selected_tokens_s1": 101.1875,
"step": 4920,
"tokens_trained": 16.120400312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.398581560283688,
"grad_norm": 0.23901410400867462,
"loss": 1.1491,
"loss_ce": 1.1176151037216187,
"loss_region": 0.060138314962387085,
"loss_total": 1.1777534484863281,
"lr": 0.0010445324117439694,
"router/selected_tokens_s0": 1158.0,
"router/selected_tokens_s1": 102.875,
"step": 4930,
"tokens_trained": 16.153164952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.401418439716312,
"grad_norm": 0.2883402407169342,
"loss": 1.1479,
"loss_ce": 1.0584120750427246,
"loss_region": 0.0600699856877327,
"loss_total": 1.1184821128845215,
"lr": 0.0010441255197601183,
"router/selected_tokens_s0": 1139.75,
"router/selected_tokens_s1": 100.75,
"step": 4940,
"tokens_trained": 16.185929592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4042553191489362,
"grad_norm": 0.22571124136447906,
"loss": 1.1499,
"loss_ce": 1.0989696979522705,
"loss_region": 0.060364458709955215,
"loss_total": 1.1593341827392578,
"lr": 0.0010437186277762675,
"router/selected_tokens_s0": 1116.0625,
"router/selected_tokens_s1": 101.9375,
"step": 4950,
"tokens_trained": 16.218695032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4070921985815603,
"grad_norm": 0.16999152302742004,
"loss": 1.1483,
"loss_ce": 0.9374291300773621,
"loss_region": 0.061014510691165924,
"loss_total": 0.9984436631202698,
"lr": 0.0010433117357924165,
"router/selected_tokens_s0": 1167.875,
"router/selected_tokens_s1": 109.6875,
"step": 4960,
"tokens_trained": 16.251457848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4099290780141844,
"grad_norm": 0.28172990679740906,
"loss": 1.149,
"loss_ce": 0.9092438220977783,
"loss_region": 0.06049266830086708,
"loss_total": 0.9697365164756775,
"lr": 0.0010429048438085654,
"router/selected_tokens_s0": 1190.75,
"router/selected_tokens_s1": 107.8125,
"step": 4970,
"tokens_trained": 16.284222488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4127659574468086,
"grad_norm": 0.1335156410932541,
"loss": 1.149,
"loss_ce": 1.0608166456222534,
"loss_region": 0.06012177839875221,
"loss_total": 1.1209384202957153,
"lr": 0.0010424979518247142,
"router/selected_tokens_s0": 1143.9375,
"router/selected_tokens_s1": 101.1875,
"step": 4980,
"tokens_trained": 16.316987928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4156028368794327,
"grad_norm": 0.23958002030849457,
"loss": 1.1491,
"loss_ce": 1.0881507396697998,
"loss_region": 0.06042102724313736,
"loss_total": 1.1485717296600342,
"lr": 0.0010420910598408631,
"router/selected_tokens_s0": 1250.75,
"router/selected_tokens_s1": 110.6875,
"step": 4990,
"tokens_trained": 16.349753368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4184397163120568,
"grad_norm": 0.21790561079978943,
"loss": 1.1451,
"loss_ce": 0.9417971968650818,
"loss_region": 0.05981254577636719,
"loss_total": 1.0016098022460938,
"lr": 0.0010416841678570121,
"router/selected_tokens_s0": 1176.1875,
"router/selected_tokens_s1": 100.5,
"step": 5000,
"tokens_trained": 16.382518808
},
{
"epoch": 1.4184397163120568,
"eval_ppl": 2.9786423782514446,
"eval_runtime": 2.0133,
"step": 5000,
"tokens_trained": 16.382518808
},
{
"epoch": 1.4184397163120568,
"eval_F": 0.00745578798615381,
"eval_F_cds": 0.0064055340939717905,
"eval_F_dig": 0.006016095007422455,
"eval_F_exon": 0.007338851062094834,
"eval_F_intron": 0.0075233309514243915,
"eval_F_nig": 0.007254536374872021,
"eval_F_promoter": 0.007780093908576001,
"eval_F_utr": 0.006906769273403609,
"eval_G": 0.04323960886173385,
"eval_G_cds": 0.038285373478348754,
"eval_G_dig": 0.04923907629502305,
"eval_G_exon": 0.04191793100460717,
"eval_G_intron": 0.0434455328629159,
"eval_G_nig": 0.04368769436312883,
"eval_G_promoter": 0.04268276778535126,
"eval_G_utr": 0.04234763705620277,
"eval_avg_bp_per_token": 134.1239855340718,
"eval_bp_per_token/cds": 156.11500701262273,
"eval_bp_per_token/dig": 166.2207792207792,
"eval_bp_per_token/exon": 136.26111111111112,
"eval_bp_per_token/intron": 132.91984713375797,
"eval_bp_per_token/nig": 137.84478405315613,
"eval_bp_per_token/promoter": 128.53315290933693,
"eval_bp_per_token/utr": 144.7854938271605,
"eval_ppl_cds": 3.705528766814986,
"eval_ppl_dig": 1.111293449006548,
"eval_ppl_exon": 3.22906865700876,
"eval_ppl_intron": 3.0000279510956616,
"eval_ppl_nig": 2.818634276623224,
"eval_ppl_promoter": 3.2703718751969526,
"eval_ppl_utr": 3.3763462248263023,
"step": 5000,
"tokens_trained": 16.382518808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.421276595744681,
"grad_norm": 0.22912006080150604,
"loss": 1.152,
"loss_ce": 1.0372974872589111,
"loss_region": 0.06194760277867317,
"loss_total": 1.0992450714111328,
"lr": 0.001041277275873161,
"router/selected_tokens_s0": 1172.375,
"router/selected_tokens_s1": 118.1875,
"step": 5010,
"tokens_trained": 16.415284248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.424113475177305,
"grad_norm": 0.1888241171836853,
"loss": 1.1498,
"loss_ce": 1.0258610248565674,
"loss_region": 0.05821385234594345,
"loss_total": 1.084074854850769,
"lr": 0.0010408703838893103,
"router/selected_tokens_s0": 1103.25,
"router/selected_tokens_s1": 84.0,
"step": 5020,
"tokens_trained": 16.448049688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4269503546099291,
"grad_norm": 0.4081474840641022,
"loss": 1.1433,
"loss_ce": 1.069995641708374,
"loss_region": 0.059390418231487274,
"loss_total": 1.129386067390442,
"lr": 0.0010404634919054592,
"router/selected_tokens_s0": 1208.75,
"router/selected_tokens_s1": 100.0,
"step": 5030,
"tokens_trained": 16.480814968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4297872340425533,
"grad_norm": 0.07389332354068756,
"loss": 1.1419,
"loss_ce": 1.0573478937149048,
"loss_region": 0.06128464266657829,
"loss_total": 1.1186325550079346,
"lr": 0.0010400565999216082,
"router/selected_tokens_s0": 1172.6875,
"router/selected_tokens_s1": 112.9375,
"step": 5040,
"tokens_trained": 16.513576176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4326241134751774,
"grad_norm": 0.17676013708114624,
"loss": 1.1429,
"loss_ce": 1.131528615951538,
"loss_region": 0.06025056540966034,
"loss_total": 1.1917791366577148,
"lr": 0.0010396497079377572,
"router/selected_tokens_s0": 1229.875,
"router/selected_tokens_s1": 108.375,
"step": 5050,
"tokens_trained": 16.546341616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4354609929078015,
"grad_norm": 0.3632008731365204,
"loss": 1.151,
"loss_ce": 1.1298102140426636,
"loss_region": 0.06115425005555153,
"loss_total": 1.1909644603729248,
"lr": 0.0010392428159539061,
"router/selected_tokens_s0": 1190.9375,
"router/selected_tokens_s1": 113.125,
"step": 5060,
"tokens_trained": 16.579105456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4382978723404256,
"grad_norm": 0.1857968270778656,
"loss": 1.1465,
"loss_ce": 1.088350534439087,
"loss_region": 0.06075309216976166,
"loss_total": 1.1491036415100098,
"lr": 0.001038835923970055,
"router/selected_tokens_s0": 1197.25,
"router/selected_tokens_s1": 110.3125,
"step": 5070,
"tokens_trained": 16.611870896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4411347517730497,
"grad_norm": 0.13964325189590454,
"loss": 1.1525,
"loss_ce": 1.1231189966201782,
"loss_region": 0.06125170364975929,
"loss_total": 1.184370756149292,
"lr": 0.001038429031986204,
"router/selected_tokens_s0": 1174.625,
"router/selected_tokens_s1": 112.375,
"step": 5080,
"tokens_trained": 16.644635536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4439716312056738,
"grad_norm": 0.16897931694984436,
"loss": 1.1499,
"loss_ce": 0.9999305605888367,
"loss_region": 0.06121806427836418,
"loss_total": 1.0611486434936523,
"lr": 0.001038022140002353,
"router/selected_tokens_s0": 1144.0625,
"router/selected_tokens_s1": 109.5,
"step": 5090,
"tokens_trained": 16.67739828
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4468085106382977,
"grad_norm": 0.186988964676857,
"loss": 1.1429,
"loss_ce": 1.0923733711242676,
"loss_region": 0.060399770736694336,
"loss_total": 1.152773141860962,
"lr": 0.001037615248018502,
"router/selected_tokens_s0": 1190.125,
"router/selected_tokens_s1": 106.75,
"step": 5100,
"tokens_trained": 16.71016372
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.449645390070922,
"grad_norm": 0.28807076811790466,
"loss": 1.1477,
"loss_ce": 1.1130632162094116,
"loss_region": 0.060432370752096176,
"loss_total": 1.1734955310821533,
"lr": 0.001037208356034651,
"router/selected_tokens_s0": 1142.375,
"router/selected_tokens_s1": 104.1875,
"step": 5110,
"tokens_trained": 16.74292916
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.452482269503546,
"grad_norm": 0.30830657482147217,
"loss": 1.1468,
"loss_ce": 1.2115405797958374,
"loss_region": 0.05969396233558655,
"loss_total": 1.2712345123291016,
"lr": 0.0010368014640508,
"router/selected_tokens_s0": 1125.125,
"router/selected_tokens_s1": 97.1875,
"step": 5120,
"tokens_trained": 16.775691312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4553191489361703,
"grad_norm": 0.21221929788589478,
"loss": 1.1512,
"loss_ce": 1.0514652729034424,
"loss_region": 0.06042499095201492,
"loss_total": 1.1118903160095215,
"lr": 0.0010363945720669489,
"router/selected_tokens_s0": 1199.625,
"router/selected_tokens_s1": 107.875,
"step": 5130,
"tokens_trained": 16.808456752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4581560283687942,
"grad_norm": 0.22854673862457275,
"loss": 1.1463,
"loss_ce": 1.0557891130447388,
"loss_region": 0.05936175957322121,
"loss_total": 1.1151509284973145,
"lr": 0.0010359876800830978,
"router/selected_tokens_s0": 1169.375,
"router/selected_tokens_s1": 97.5625,
"step": 5140,
"tokens_trained": 16.841222192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4609929078014185,
"grad_norm": 0.2368224710226059,
"loss": 1.1428,
"loss_ce": 1.0367987155914307,
"loss_region": 0.058588556945323944,
"loss_total": 1.0953872203826904,
"lr": 0.0010355807880992468,
"router/selected_tokens_s0": 1064.75,
"router/selected_tokens_s1": 84.625,
"step": 5150,
"tokens_trained": 16.873987632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4638297872340424,
"grad_norm": 0.3368516266345978,
"loss": 1.1402,
"loss_ce": 1.1748027801513672,
"loss_region": 0.0609104186296463,
"loss_total": 1.235713243484497,
"lr": 0.0010351738961153958,
"router/selected_tokens_s0": 1230.6875,
"router/selected_tokens_s1": 113.5,
"step": 5160,
"tokens_trained": 16.906753072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4666666666666668,
"grad_norm": 0.16690143942832947,
"loss": 1.1482,
"loss_ce": 1.0459595918655396,
"loss_region": 0.0586651973426342,
"loss_total": 1.1046247482299805,
"lr": 0.0010347670041315447,
"router/selected_tokens_s0": 1180.0,
"router/selected_tokens_s1": 91.6875,
"step": 5170,
"tokens_trained": 16.939515096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4695035460992907,
"grad_norm": 0.06549862027168274,
"loss": 1.1451,
"loss_ce": 1.068226933479309,
"loss_region": 0.05954112857580185,
"loss_total": 1.1277680397033691,
"lr": 0.0010343601121476937,
"router/selected_tokens_s0": 1166.0625,
"router/selected_tokens_s1": 98.125,
"step": 5180,
"tokens_trained": 16.972279352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.472340425531915,
"grad_norm": 0.11069296300411224,
"loss": 1.1482,
"loss_ce": 1.1082299947738647,
"loss_region": 0.06221709027886391,
"loss_total": 1.1704471111297607,
"lr": 0.0010339532201638427,
"router/selected_tokens_s0": 1137.9375,
"router/selected_tokens_s1": 117.75,
"step": 5190,
"tokens_trained": 17.005044792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.475177304964539,
"grad_norm": 0.19471175968647003,
"loss": 1.1496,
"loss_ce": 0.9849838614463806,
"loss_region": 0.06120489165186882,
"loss_total": 1.0461887121200562,
"lr": 0.0010335463281799918,
"router/selected_tokens_s0": 1154.8125,
"router/selected_tokens_s1": 110.375,
"step": 5200,
"tokens_trained": 17.037810232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4780141843971633,
"grad_norm": 0.2414424866437912,
"loss": 1.1426,
"loss_ce": 1.130875825881958,
"loss_region": 0.05976984649896622,
"loss_total": 1.190645694732666,
"lr": 0.0010331394361961408,
"router/selected_tokens_s0": 1123.875,
"router/selected_tokens_s1": 97.4375,
"step": 5210,
"tokens_trained": 17.070575672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4808510638297872,
"grad_norm": 0.16089095175266266,
"loss": 1.1384,
"loss_ce": 1.1152632236480713,
"loss_region": 0.058639250695705414,
"loss_total": 1.1739025115966797,
"lr": 0.0010327325442122898,
"router/selected_tokens_s0": 1069.625,
"router/selected_tokens_s1": 85.5625,
"step": 5220,
"tokens_trained": 17.103341112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4836879432624113,
"grad_norm": 0.17800533771514893,
"loss": 1.148,
"loss_ce": 1.0959079265594482,
"loss_region": 0.05997302010655403,
"loss_total": 1.1558809280395508,
"lr": 0.0010323256522284385,
"router/selected_tokens_s0": 1127.75,
"router/selected_tokens_s1": 99.5,
"step": 5230,
"tokens_trained": 17.136106552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4865248226950354,
"grad_norm": 0.22666983306407928,
"loss": 1.1402,
"loss_ce": 1.1192185878753662,
"loss_region": 0.06110667809844017,
"loss_total": 1.1803252696990967,
"lr": 0.0010319187602445875,
"router/selected_tokens_s0": 1163.9375,
"router/selected_tokens_s1": 111.0,
"step": 5240,
"tokens_trained": 17.168867192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4893617021276595,
"grad_norm": 0.25073131918907166,
"loss": 1.1476,
"loss_ce": 1.1026537418365479,
"loss_region": 0.060530051589012146,
"loss_total": 1.1631838083267212,
"lr": 0.0010315118682607365,
"router/selected_tokens_s0": 1173.875,
"router/selected_tokens_s1": 106.8125,
"step": 5250,
"tokens_trained": 17.201632632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4921985815602836,
"grad_norm": 0.0783478245139122,
"loss": 1.1492,
"loss_ce": 1.0499285459518433,
"loss_region": 0.059468407183885574,
"loss_total": 1.1093969345092773,
"lr": 0.0010311049762768854,
"router/selected_tokens_s0": 1137.625,
"router/selected_tokens_s1": 95.875,
"step": 5260,
"tokens_trained": 17.234398072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4950354609929077,
"grad_norm": 0.2490188032388687,
"loss": 1.1451,
"loss_ce": 1.102023959159851,
"loss_region": 0.057921264320611954,
"loss_total": 1.1599452495574951,
"lr": 0.0010306980842930346,
"router/selected_tokens_s0": 1199.375,
"router/selected_tokens_s1": 86.75,
"step": 5270,
"tokens_trained": 17.26716272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4978723404255319,
"grad_norm": 0.15398019552230835,
"loss": 1.1414,
"loss_ce": 1.0141432285308838,
"loss_region": 0.059863440692424774,
"loss_total": 1.0740066766738892,
"lr": 0.0010302911923091836,
"router/selected_tokens_s0": 1164.5625,
"router/selected_tokens_s1": 101.5625,
"step": 5280,
"tokens_trained": 17.29992816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.500709219858156,
"grad_norm": 0.3028818964958191,
"loss": 1.152,
"loss_ce": 1.1121013164520264,
"loss_region": 0.06068980693817139,
"loss_total": 1.1727911233901978,
"lr": 0.0010298843003253325,
"router/selected_tokens_s0": 1153.375,
"router/selected_tokens_s1": 106.875,
"step": 5290,
"tokens_trained": 17.3326928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.50354609929078,
"grad_norm": 0.23320052027702332,
"loss": 1.1442,
"loss_ce": 1.097700834274292,
"loss_region": 0.06065419316291809,
"loss_total": 1.1583549976348877,
"lr": 0.0010294774083414815,
"router/selected_tokens_s0": 1174.5625,
"router/selected_tokens_s1": 107.3125,
"step": 5300,
"tokens_trained": 17.36545824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5063829787234042,
"grad_norm": 0.18858042359352112,
"loss": 1.149,
"loss_ce": 1.0849069356918335,
"loss_region": 0.05857797712087631,
"loss_total": 1.1434849500656128,
"lr": 0.0010290705163576305,
"router/selected_tokens_s0": 1167.3125,
"router/selected_tokens_s1": 90.5625,
"step": 5310,
"tokens_trained": 17.39822368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5092198581560283,
"grad_norm": 0.07173584401607513,
"loss": 1.1478,
"loss_ce": 1.1023950576782227,
"loss_region": 0.05886488035321236,
"loss_total": 1.1612598896026611,
"lr": 0.0010286636243737794,
"router/selected_tokens_s0": 1112.6875,
"router/selected_tokens_s1": 89.75,
"step": 5320,
"tokens_trained": 17.43098912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5120567375886524,
"grad_norm": 0.2823182940483093,
"loss": 1.1423,
"loss_ce": 1.0714432001113892,
"loss_region": 0.05882066488265991,
"loss_total": 1.1302638053894043,
"lr": 0.0010282567323899284,
"router/selected_tokens_s0": 1078.875,
"router/selected_tokens_s1": 87.625,
"step": 5330,
"tokens_trained": 17.46375296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5148936170212766,
"grad_norm": 0.14734476804733276,
"loss": 1.1442,
"loss_ce": 1.1149892807006836,
"loss_region": 0.06177487596869469,
"loss_total": 1.1767641305923462,
"lr": 0.0010278498404060774,
"router/selected_tokens_s0": 1133.125,
"router/selected_tokens_s1": 113.9375,
"step": 5340,
"tokens_trained": 17.4965184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5177304964539007,
"grad_norm": 0.21337512135505676,
"loss": 1.1498,
"loss_ce": 1.0628228187561035,
"loss_region": 0.06133369356393814,
"loss_total": 1.1241564750671387,
"lr": 0.0010274429484222263,
"router/selected_tokens_s0": 1139.5,
"router/selected_tokens_s1": 111.3125,
"step": 5350,
"tokens_trained": 17.52928304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5205673758865248,
"grad_norm": 0.10551182180643082,
"loss": 1.147,
"loss_ce": 1.094645619392395,
"loss_region": 0.05717579647898674,
"loss_total": 1.1518213748931885,
"lr": 0.0010270360564383753,
"router/selected_tokens_s0": 1127.8125,
"router/selected_tokens_s1": 77.75,
"step": 5360,
"tokens_trained": 17.56204848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.523404255319149,
"grad_norm": 0.07315859943628311,
"loss": 1.1433,
"loss_ce": 1.0663042068481445,
"loss_region": 0.05805211514234543,
"loss_total": 1.1243562698364258,
"lr": 0.0010266291644545243,
"router/selected_tokens_s0": 1129.4375,
"router/selected_tokens_s1": 84.375,
"step": 5370,
"tokens_trained": 17.59481392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.526241134751773,
"grad_norm": 0.2523398697376251,
"loss": 1.145,
"loss_ce": 1.0977721214294434,
"loss_region": 0.06312695890665054,
"loss_total": 1.160899043083191,
"lr": 0.0010262222724706732,
"router/selected_tokens_s0": 1144.1875,
"router/selected_tokens_s1": 125.375,
"step": 5380,
"tokens_trained": 17.62757936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5290780141843971,
"grad_norm": 0.1691519170999527,
"loss": 1.1479,
"loss_ce": 1.086019515991211,
"loss_region": 0.05966857820749283,
"loss_total": 1.1456880569458008,
"lr": 0.0010258153804868222,
"router/selected_tokens_s0": 1151.3125,
"router/selected_tokens_s1": 98.3125,
"step": 5390,
"tokens_trained": 17.6603448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5319148936170213,
"grad_norm": 0.1503233015537262,
"loss": 1.1455,
"loss_ce": 1.0918323993682861,
"loss_region": 0.05891592800617218,
"loss_total": 1.150748372077942,
"lr": 0.0010254084885029712,
"router/selected_tokens_s0": 1151.9375,
"router/selected_tokens_s1": 92.5,
"step": 5400,
"tokens_trained": 17.69310944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5347517730496454,
"grad_norm": 0.21977928280830383,
"loss": 1.1464,
"loss_ce": 1.1513240337371826,
"loss_region": 0.06481648981571198,
"loss_total": 1.2161405086517334,
"lr": 0.0010250015965191201,
"router/selected_tokens_s0": 1131.125,
"router/selected_tokens_s1": 137.625,
"step": 5410,
"tokens_trained": 17.72587488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5375886524822695,
"grad_norm": 0.07182486355304718,
"loss": 1.1442,
"loss_ce": 1.0516289472579956,
"loss_region": 0.060127370059490204,
"loss_total": 1.1117563247680664,
"lr": 0.001024594704535269,
"router/selected_tokens_s0": 1144.5,
"router/selected_tokens_s1": 101.0,
"step": 5420,
"tokens_trained": 17.75863776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5404255319148936,
"grad_norm": 0.19044677913188934,
"loss": 1.1445,
"loss_ce": 1.1150530576705933,
"loss_region": 0.058283500373363495,
"loss_total": 1.1733365058898926,
"lr": 0.001024187812551418,
"router/selected_tokens_s0": 1191.125,
"router/selected_tokens_s1": 89.4375,
"step": 5430,
"tokens_trained": 17.7914032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5432624113475177,
"grad_norm": 0.1769535392522812,
"loss": 1.1404,
"loss_ce": 1.0554611682891846,
"loss_region": 0.05861309543251991,
"loss_total": 1.1140742301940918,
"lr": 0.001023780920567567,
"router/selected_tokens_s0": 1110.5,
"router/selected_tokens_s1": 87.9375,
"step": 5440,
"tokens_trained": 17.824165472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5460992907801419,
"grad_norm": 0.21434129774570465,
"loss": 1.1434,
"loss_ce": 1.0828922986984253,
"loss_region": 0.059199750423431396,
"loss_total": 1.142091989517212,
"lr": 0.0010233740285837162,
"router/selected_tokens_s0": 1188.8125,
"router/selected_tokens_s1": 97.0625,
"step": 5450,
"tokens_trained": 17.856930912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.548936170212766,
"grad_norm": 0.16277895867824554,
"loss": 1.1462,
"loss_ce": 1.077553153038025,
"loss_region": 0.05955193191766739,
"loss_total": 1.137105107307434,
"lr": 0.0010229671365998652,
"router/selected_tokens_s0": 1180.5,
"router/selected_tokens_s1": 100.125,
"step": 5460,
"tokens_trained": 17.88969364
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.55177304964539,
"grad_norm": 0.16868393123149872,
"loss": 1.1464,
"loss_ce": 1.1285775899887085,
"loss_region": 0.06097865477204323,
"loss_total": 1.1895562410354614,
"lr": 0.0010225602446160141,
"router/selected_tokens_s0": 1179.125,
"router/selected_tokens_s1": 111.5,
"step": 5470,
"tokens_trained": 17.92245908
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5546099290780142,
"grad_norm": 0.25248610973358154,
"loss": 1.1386,
"loss_ce": 1.1028388738632202,
"loss_region": 0.06022004038095474,
"loss_total": 1.163058876991272,
"lr": 0.0010221533526321629,
"router/selected_tokens_s0": 1154.9375,
"router/selected_tokens_s1": 103.25,
"step": 5480,
"tokens_trained": 17.95522452
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5574468085106383,
"grad_norm": 0.20562683045864105,
"loss": 1.1459,
"loss_ce": 1.1231143474578857,
"loss_region": 0.05964804068207741,
"loss_total": 1.1827623844146729,
"lr": 0.0010217464606483118,
"router/selected_tokens_s0": 1227.75,
"router/selected_tokens_s1": 103.25,
"step": 5490,
"tokens_trained": 17.98798996
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5602836879432624,
"grad_norm": 0.14120644330978394,
"loss": 1.1477,
"loss_ce": 1.1169317960739136,
"loss_region": 0.05971687659621239,
"loss_total": 1.1766486167907715,
"lr": 0.0010213395686644608,
"router/selected_tokens_s0": 1178.625,
"router/selected_tokens_s1": 100.9375,
"step": 5500,
"tokens_trained": 18.0207554
},
{
"epoch": 1.5602836879432624,
"eval_ppl": 2.9629568937224073,
"eval_runtime": 1.9917,
"step": 5500,
"tokens_trained": 18.0207554
},
{
"epoch": 1.5602836879432624,
"eval_F": 0.008238585215556923,
"eval_F_cds": 0.008130446500763633,
"eval_F_dig": 0.00812563481521994,
"eval_F_exon": 0.008018374308585097,
"eval_F_intron": 0.008284289521542986,
"eval_F_nig": 0.008239803640668593,
"eval_F_promoter": 0.008147253279430652,
"eval_F_utr": 0.008025921701964379,
"eval_G": 0.0443550707796412,
"eval_G_cds": 0.038759398021291885,
"eval_G_dig": 0.05333020096784905,
"eval_G_exon": 0.0435424958973784,
"eval_G_intron": 0.04454719544837519,
"eval_G_nig": 0.044568092078624715,
"eval_G_promoter": 0.0440533747859882,
"eval_G_utr": 0.043928981118299744,
"eval_avg_bp_per_token": 121.38006391093701,
"eval_bp_per_token/cds": 122.99447513812154,
"eval_bp_per_token/dig": 123.0673076923077,
"eval_bp_per_token/exon": 124.7135593220339,
"eval_bp_per_token/intron": 120.71041184636742,
"eval_bp_per_token/nig": 121.36211536211536,
"eval_bp_per_token/promoter": 122.7407527055403,
"eval_bp_per_token/utr": 124.59628154050465,
"eval_ppl_cds": 3.699772662007796,
"eval_ppl_dig": 1.1000550286613988,
"eval_ppl_exon": 3.211033716184067,
"eval_ppl_intron": 2.983289329218932,
"eval_ppl_nig": 2.796906691689632,
"eval_ppl_promoter": 3.2596719050972514,
"eval_ppl_utr": 3.3708124471025247,
"step": 5500,
"tokens_trained": 18.0207554
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5631205673758866,
"grad_norm": 0.12358555197715759,
"loss": 1.1408,
"loss_ce": 1.1074210405349731,
"loss_region": 0.058581963181495667,
"loss_total": 1.1660029888153076,
"lr": 0.0010209326766806098,
"router/selected_tokens_s0": 1055.125,
"router/selected_tokens_s1": 84.375,
"step": 5510,
"tokens_trained": 18.05352084
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5659574468085107,
"grad_norm": 0.15037629008293152,
"loss": 1.1411,
"loss_ce": 1.0207792520523071,
"loss_region": 0.05887831747531891,
"loss_total": 1.0796575546264648,
"lr": 0.001020525784696759,
"router/selected_tokens_s0": 1158.5625,
"router/selected_tokens_s1": 92.75,
"step": 5520,
"tokens_trained": 18.08628548
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5687943262411348,
"grad_norm": 0.1223883107304573,
"loss": 1.1397,
"loss_ce": 1.0867618322372437,
"loss_region": 0.058768656104803085,
"loss_total": 1.1455304622650146,
"lr": 0.001020118892712908,
"router/selected_tokens_s0": 1178.5625,
"router/selected_tokens_s1": 92.9375,
"step": 5530,
"tokens_trained": 18.11905092
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.571631205673759,
"grad_norm": 0.29459166526794434,
"loss": 1.1411,
"loss_ce": 1.0979646444320679,
"loss_region": 0.06032467633485794,
"loss_total": 1.1582893133163452,
"lr": 0.0010197120007290569,
"router/selected_tokens_s0": 1156.3125,
"router/selected_tokens_s1": 104.25,
"step": 5540,
"tokens_trained": 18.15181636
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.574468085106383,
"grad_norm": 0.13428881764411926,
"loss": 1.1447,
"loss_ce": 1.0458506345748901,
"loss_region": 0.059695612639188766,
"loss_total": 1.105546236038208,
"lr": 0.0010193051087452058,
"router/selected_tokens_s0": 1157.5,
"router/selected_tokens_s1": 99.1875,
"step": 5550,
"tokens_trained": 18.1845818
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5773049645390071,
"grad_norm": 0.16526272892951965,
"loss": 1.1439,
"loss_ce": 1.0565471649169922,
"loss_region": 0.05908852443099022,
"loss_total": 1.115635633468628,
"lr": 0.0010188982167613548,
"router/selected_tokens_s0": 1177.4375,
"router/selected_tokens_s1": 95.3125,
"step": 5560,
"tokens_trained": 18.2173404
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.580141843971631,
"grad_norm": 0.2615581452846527,
"loss": 1.147,
"loss_ce": 0.9654809832572937,
"loss_region": 0.061932649463415146,
"loss_total": 1.0274136066436768,
"lr": 0.0010184913247775038,
"router/selected_tokens_s0": 1226.0625,
"router/selected_tokens_s1": 120.375,
"step": 5570,
"tokens_trained": 18.25010584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5829787234042554,
"grad_norm": 0.2581145465373993,
"loss": 1.1447,
"loss_ce": 1.0666128396987915,
"loss_region": 0.06014023721218109,
"loss_total": 1.1267530918121338,
"lr": 0.0010180844327936527,
"router/selected_tokens_s0": 1150.25,
"router/selected_tokens_s1": 102.5625,
"step": 5580,
"tokens_trained": 18.28287128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5858156028368793,
"grad_norm": 0.13884904980659485,
"loss": 1.1394,
"loss_ce": 1.1608939170837402,
"loss_region": 0.05978744477033615,
"loss_total": 1.2206813097000122,
"lr": 0.0010176775408098017,
"router/selected_tokens_s0": 1212.5,
"router/selected_tokens_s1": 103.375,
"step": 5590,
"tokens_trained": 18.31563672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5886524822695036,
"grad_norm": 0.266236275434494,
"loss": 1.1399,
"loss_ce": 1.0968828201293945,
"loss_region": 0.06059946119785309,
"loss_total": 1.1574822664260864,
"lr": 0.0010172706488259507,
"router/selected_tokens_s0": 1098.5625,
"router/selected_tokens_s1": 102.25,
"step": 5600,
"tokens_trained": 18.34840216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5914893617021275,
"grad_norm": 0.16597892343997955,
"loss": 1.1417,
"loss_ce": 1.0729858875274658,
"loss_region": 0.059629738330841064,
"loss_total": 1.132615566253662,
"lr": 0.0010168637568420996,
"router/selected_tokens_s0": 1152.125,
"router/selected_tokens_s1": 98.5625,
"step": 5610,
"tokens_trained": 18.38116752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5943262411347519,
"grad_norm": 0.15744268894195557,
"loss": 1.1383,
"loss_ce": 0.9952933192253113,
"loss_region": 0.06122814118862152,
"loss_total": 1.0565214157104492,
"lr": 0.0010164568648582486,
"router/selected_tokens_s0": 1184.8125,
"router/selected_tokens_s1": 113.6875,
"step": 5620,
"tokens_trained": 18.41393296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5971631205673757,
"grad_norm": 0.1597251147031784,
"loss": 1.1399,
"loss_ce": 1.1098027229309082,
"loss_region": 0.05966440215706825,
"loss_total": 1.1694670915603638,
"lr": 0.0010160499728743976,
"router/selected_tokens_s0": 1083.4375,
"router/selected_tokens_s1": 94.0625,
"step": 5630,
"tokens_trained": 18.4466984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6,
"grad_norm": 0.1583746075630188,
"loss": 1.1391,
"loss_ce": 1.0872089862823486,
"loss_region": 0.058888886123895645,
"loss_total": 1.1460978984832764,
"lr": 0.0010156430808905465,
"router/selected_tokens_s0": 1156.1875,
"router/selected_tokens_s1": 92.3125,
"step": 5640,
"tokens_trained": 18.47946384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.602836879432624,
"grad_norm": 0.1457541137933731,
"loss": 1.1407,
"loss_ce": 1.0596680641174316,
"loss_region": 0.059955596923828125,
"loss_total": 1.1196236610412598,
"lr": 0.0010152361889066955,
"router/selected_tokens_s0": 1146.125,
"router/selected_tokens_s1": 100.1875,
"step": 5650,
"tokens_trained": 18.51222928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6056737588652483,
"grad_norm": 0.11980196088552475,
"loss": 1.1417,
"loss_ce": 1.1236000061035156,
"loss_region": 0.06000308692455292,
"loss_total": 1.183603048324585,
"lr": 0.0010148292969228445,
"router/selected_tokens_s0": 1151.8125,
"router/selected_tokens_s1": 101.3125,
"step": 5660,
"tokens_trained": 18.54499392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6085106382978722,
"grad_norm": 0.13803839683532715,
"loss": 1.1414,
"loss_ce": 1.1239171028137207,
"loss_region": 0.06013445928692818,
"loss_total": 1.184051513671875,
"lr": 0.0010144224049389934,
"router/selected_tokens_s0": 1134.5,
"router/selected_tokens_s1": 101.1875,
"step": 5670,
"tokens_trained": 18.57775936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6113475177304966,
"grad_norm": 0.145533949136734,
"loss": 1.1348,
"loss_ce": 1.0382026433944702,
"loss_region": 0.06151394546031952,
"loss_total": 1.0997165441513062,
"lr": 0.0010140155129551424,
"router/selected_tokens_s0": 1162.4375,
"router/selected_tokens_s1": 114.25,
"step": 5680,
"tokens_trained": 18.6105248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6141843971631205,
"grad_norm": 0.16145651042461395,
"loss": 1.1371,
"loss_ce": 1.1397801637649536,
"loss_region": 0.05963653698563576,
"loss_total": 1.1994167566299438,
"lr": 0.0010136086209712914,
"router/selected_tokens_s0": 1064.5625,
"router/selected_tokens_s1": 92.5,
"step": 5690,
"tokens_trained": 18.64329024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6170212765957448,
"grad_norm": 0.23432840406894684,
"loss": 1.1401,
"loss_ce": 1.08021879196167,
"loss_region": 0.06039845198392868,
"loss_total": 1.1406172513961792,
"lr": 0.0010132017289874405,
"router/selected_tokens_s0": 1131.4375,
"router/selected_tokens_s1": 103.0,
"step": 5700,
"tokens_trained": 18.67605568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6198581560283687,
"grad_norm": 0.12430011481046677,
"loss": 1.142,
"loss_ce": 1.0135034322738647,
"loss_region": 0.0579909011721611,
"loss_total": 1.0714943408966064,
"lr": 0.0010127948370035895,
"router/selected_tokens_s0": 1141.875,
"router/selected_tokens_s1": 84.5,
"step": 5710,
"tokens_trained": 18.70882112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.622695035460993,
"grad_norm": 0.09644272178411484,
"loss": 1.1433,
"loss_ce": 1.1016589403152466,
"loss_region": 0.062197744846343994,
"loss_total": 1.1638567447662354,
"lr": 0.0010123879450197385,
"router/selected_tokens_s0": 1114.4375,
"router/selected_tokens_s1": 115.5,
"step": 5720,
"tokens_trained": 18.74158656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.625531914893617,
"grad_norm": 0.11881081759929657,
"loss": 1.1444,
"loss_ce": 1.1430163383483887,
"loss_region": 0.06135653704404831,
"loss_total": 1.2043728828430176,
"lr": 0.0010119810530358872,
"router/selected_tokens_s0": 1128.8125,
"router/selected_tokens_s1": 110.4375,
"step": 5730,
"tokens_trained": 18.774352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6283687943262413,
"grad_norm": 0.3889363706111908,
"loss": 1.145,
"loss_ce": 1.0896387100219727,
"loss_region": 0.05884133279323578,
"loss_total": 1.1484800577163696,
"lr": 0.0010115741610520362,
"router/selected_tokens_s0": 1127.0625,
"router/selected_tokens_s1": 90.5,
"step": 5740,
"tokens_trained": 18.80711744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6312056737588652,
"grad_norm": 0.14049233496189117,
"loss": 1.1398,
"loss_ce": 1.072272777557373,
"loss_region": 0.058674365282058716,
"loss_total": 1.1309471130371094,
"lr": 0.0010111672690681851,
"router/selected_tokens_s0": 1157.8125,
"router/selected_tokens_s1": 91.125,
"step": 5750,
"tokens_trained": 18.83988288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6340425531914895,
"grad_norm": 0.3472958207130432,
"loss": 1.1394,
"loss_ce": 1.0463656187057495,
"loss_region": 0.060423437505960464,
"loss_total": 1.1067891120910645,
"lr": 0.0010107603770843341,
"router/selected_tokens_s0": 1203.5,
"router/selected_tokens_s1": 106.75,
"step": 5760,
"tokens_trained": 18.87264832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6368794326241134,
"grad_norm": 0.08495907485485077,
"loss": 1.1408,
"loss_ce": 1.1229298114776611,
"loss_region": 0.05851162225008011,
"loss_total": 1.1814414262771606,
"lr": 0.0010103534851004833,
"router/selected_tokens_s0": 1148.0,
"router/selected_tokens_s1": 89.0625,
"step": 5770,
"tokens_trained": 18.90541376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6397163120567377,
"grad_norm": 0.07788603007793427,
"loss": 1.1404,
"loss_ce": 1.0718777179718018,
"loss_region": 0.05956518277525902,
"loss_total": 1.131442904472351,
"lr": 0.0010099465931166323,
"router/selected_tokens_s0": 1167.0625,
"router/selected_tokens_s1": 98.8125,
"step": 5780,
"tokens_trained": 18.9381792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6425531914893616,
"grad_norm": 0.1432577669620514,
"loss": 1.1341,
"loss_ce": 0.9698552489280701,
"loss_region": 0.058856260031461716,
"loss_total": 1.0287115573883057,
"lr": 0.0010095397011327812,
"router/selected_tokens_s0": 1131.625,
"router/selected_tokens_s1": 90.875,
"step": 5790,
"tokens_trained": 18.97094464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.645390070921986,
"grad_norm": 0.15056516230106354,
"loss": 1.1392,
"loss_ce": 1.0646241903305054,
"loss_region": 0.06081939488649368,
"loss_total": 1.1254435777664185,
"lr": 0.0010091328091489302,
"router/selected_tokens_s0": 1152.5,
"router/selected_tokens_s1": 107.625,
"step": 5800,
"tokens_trained": 19.00370848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6482269503546099,
"grad_norm": 0.22324803471565247,
"loss": 1.1385,
"loss_ce": 1.1039924621582031,
"loss_region": 0.0615408755838871,
"loss_total": 1.1655333042144775,
"lr": 0.0010087259171650792,
"router/selected_tokens_s0": 1144.4375,
"router/selected_tokens_s1": 113.0625,
"step": 5810,
"tokens_trained": 19.03647392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6510638297872342,
"grad_norm": 0.12950165569782257,
"loss": 1.1386,
"loss_ce": 1.0333588123321533,
"loss_region": 0.06084536015987396,
"loss_total": 1.0942041873931885,
"lr": 0.0010083190251812281,
"router/selected_tokens_s0": 1100.9375,
"router/selected_tokens_s1": 103.4375,
"step": 5820,
"tokens_trained": 19.06923936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.653900709219858,
"grad_norm": 0.20259711146354675,
"loss": 1.1362,
"loss_ce": 1.0697150230407715,
"loss_region": 0.059984240680933,
"loss_total": 1.1296992301940918,
"lr": 0.001007912133197377,
"router/selected_tokens_s0": 1126.5,
"router/selected_tokens_s1": 99.625,
"step": 5830,
"tokens_trained": 19.1020048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6567375886524822,
"grad_norm": 0.13350364565849304,
"loss": 1.1393,
"loss_ce": 1.0918112993240356,
"loss_region": 0.06063058227300644,
"loss_total": 1.1524418592453003,
"lr": 0.001007505241213526,
"router/selected_tokens_s0": 1143.375,
"router/selected_tokens_s1": 105.8125,
"step": 5840,
"tokens_trained": 19.13477024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6595744680851063,
"grad_norm": 0.11386194825172424,
"loss": 1.1365,
"loss_ce": 1.1211421489715576,
"loss_region": 0.060025155544281006,
"loss_total": 1.1811673641204834,
"lr": 0.001007098349229675,
"router/selected_tokens_s0": 1107.6875,
"router/selected_tokens_s1": 98.3125,
"step": 5850,
"tokens_trained": 19.16753568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6624113475177305,
"grad_norm": 0.1893109381198883,
"loss": 1.1351,
"loss_ce": 0.9979044795036316,
"loss_region": 0.05941358953714371,
"loss_total": 1.057318091392517,
"lr": 0.001006691457245824,
"router/selected_tokens_s0": 1135.0625,
"router/selected_tokens_s1": 95.5,
"step": 5860,
"tokens_trained": 19.20030112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6652482269503546,
"grad_norm": 0.12390246987342834,
"loss": 1.1378,
"loss_ce": 1.0217939615249634,
"loss_region": 0.060103025287389755,
"loss_total": 1.0818970203399658,
"lr": 0.001006284565261973,
"router/selected_tokens_s0": 1175.25,
"router/selected_tokens_s1": 103.875,
"step": 5870,
"tokens_trained": 19.23306656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6680851063829787,
"grad_norm": 0.20230291783809662,
"loss": 1.1366,
"loss_ce": 1.1150033473968506,
"loss_region": 0.05922327935695648,
"loss_total": 1.1742266416549683,
"lr": 0.001005877673278122,
"router/selected_tokens_s0": 1175.5,
"router/selected_tokens_s1": 96.3125,
"step": 5880,
"tokens_trained": 19.265832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6709219858156028,
"grad_norm": 0.14319747686386108,
"loss": 1.136,
"loss_ce": 1.08858060836792,
"loss_region": 0.06075606867671013,
"loss_total": 1.1493366956710815,
"lr": 0.0010054707812942709,
"router/selected_tokens_s0": 1206.375,
"router/selected_tokens_s1": 111.1875,
"step": 5890,
"tokens_trained": 19.29859664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.673758865248227,
"grad_norm": 0.11091051995754242,
"loss": 1.1405,
"loss_ce": 1.085661768913269,
"loss_region": 0.0598275251686573,
"loss_total": 1.1454893350601196,
"lr": 0.0010050638893104198,
"router/selected_tokens_s0": 1169.3125,
"router/selected_tokens_s1": 101.0,
"step": 5900,
"tokens_trained": 19.33136116
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.676595744680851,
"grad_norm": 0.10978376865386963,
"loss": 1.1381,
"loss_ce": 1.100111961364746,
"loss_region": 0.059790026396512985,
"loss_total": 1.1599019765853882,
"lr": 0.0010046569973265688,
"router/selected_tokens_s0": 1142.875,
"router/selected_tokens_s1": 98.9375,
"step": 5910,
"tokens_trained": 19.3641258
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6794326241134752,
"grad_norm": 0.11382731050252914,
"loss": 1.1353,
"loss_ce": 1.0841070413589478,
"loss_region": 0.05912192910909653,
"loss_total": 1.1432290077209473,
"lr": 0.0010042501053427178,
"router/selected_tokens_s0": 1135.125,
"router/selected_tokens_s1": 93.5,
"step": 5920,
"tokens_trained": 19.39688964
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6822695035460993,
"grad_norm": 0.1101735383272171,
"loss": 1.1405,
"loss_ce": 1.071196436882019,
"loss_region": 0.06145774573087692,
"loss_total": 1.1326541900634766,
"lr": 0.0010038432133588667,
"router/selected_tokens_s0": 1174.125,
"router/selected_tokens_s1": 114.8125,
"step": 5930,
"tokens_trained": 19.42965508
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6851063829787234,
"grad_norm": 0.13230785727500916,
"loss": 1.1363,
"loss_ce": 1.0845067501068115,
"loss_region": 0.05920430272817612,
"loss_total": 1.1437110900878906,
"lr": 0.0010034363213750157,
"router/selected_tokens_s0": 1170.875,
"router/selected_tokens_s1": 95.9375,
"step": 5940,
"tokens_trained": 19.46241972
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6879432624113475,
"grad_norm": 0.13463565707206726,
"loss": 1.1389,
"loss_ce": 1.1332194805145264,
"loss_region": 0.061460621654987335,
"loss_total": 1.194680094718933,
"lr": 0.0010030294293911649,
"router/selected_tokens_s0": 1147.4375,
"router/selected_tokens_s1": 113.125,
"step": 5950,
"tokens_trained": 19.49518516
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6907801418439716,
"grad_norm": 0.105684794485569,
"loss": 1.1375,
"loss_ce": 1.1408146619796753,
"loss_region": 0.06131913885474205,
"loss_total": 1.2021337747573853,
"lr": 0.0010026225374073139,
"router/selected_tokens_s0": 1148.3125,
"router/selected_tokens_s1": 111.9375,
"step": 5960,
"tokens_trained": 19.5279506
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6936170212765957,
"grad_norm": 0.1298324316740036,
"loss": 1.1405,
"loss_ce": 1.1013529300689697,
"loss_region": 0.05970582365989685,
"loss_total": 1.161058783531189,
"lr": 0.0010022156454234628,
"router/selected_tokens_s0": 1179.0625,
"router/selected_tokens_s1": 100.375,
"step": 5970,
"tokens_trained": 19.56071604
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6964539007092199,
"grad_norm": 0.12999854981899261,
"loss": 1.1337,
"loss_ce": 1.073915958404541,
"loss_region": 0.06164190545678139,
"loss_total": 1.1355578899383545,
"lr": 0.0010018087534396116,
"router/selected_tokens_s0": 1153.875,
"router/selected_tokens_s1": 114.8125,
"step": 5980,
"tokens_trained": 19.59348068
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.699290780141844,
"grad_norm": 0.12657859921455383,
"loss": 1.1349,
"loss_ce": 1.0706164836883545,
"loss_region": 0.06009352579712868,
"loss_total": 1.1307100057601929,
"lr": 0.0010014018614557605,
"router/selected_tokens_s0": 1185.6875,
"router/selected_tokens_s1": 104.1875,
"step": 5990,
"tokens_trained": 19.62624612
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.702127659574468,
"grad_norm": 0.2500196099281311,
"loss": 1.1404,
"loss_ce": 1.060509204864502,
"loss_region": 0.05948161706328392,
"loss_total": 1.1199908256530762,
"lr": 0.0010009949694719095,
"router/selected_tokens_s0": 1287.75,
"router/selected_tokens_s1": 104.875,
"step": 6000,
"tokens_trained": 19.659011552
},
{
"epoch": 1.702127659574468,
"eval_ppl": 2.9490778941081053,
"eval_runtime": 2.0059,
"step": 6000,
"tokens_trained": 19.659011552
},
{
"epoch": 1.702127659574468,
"eval_F": 0.0071978279553090085,
"eval_F_cds": 0.00597430599227383,
"eval_F_dig": 0.010078912415032424,
"eval_F_exon": 0.00709422269335834,
"eval_F_intron": 0.007232748283338803,
"eval_F_nig": 0.007415534059204729,
"eval_F_promoter": 0.006979975996462637,
"eval_F_utr": 0.0063312051672866415,
"eval_G": 0.04385200061737903,
"eval_G_cds": 0.03808590240656724,
"eval_G_dig": 0.06461251550414095,
"eval_G_exon": 0.04268873864346774,
"eval_G_intron": 0.043968640216871274,
"eval_G_nig": 0.044211571383191844,
"eval_G_promoter": 0.04331874247010744,
"eval_G_utr": 0.04304163230380192,
"eval_avg_bp_per_token": 138.93080054274085,
"eval_bp_per_token/cds": 167.38345864661653,
"eval_bp_per_token/dig": 99.21705426356588,
"eval_bp_per_token/exon": 140.95977011494253,
"eval_bp_per_token/intron": 138.26003074150634,
"eval_bp_per_token/nig": 134.85205408216328,
"eval_bp_per_token/promoter": 143.26696832579185,
"eval_bp_per_token/utr": 157.94781144781146,
"eval_ppl_cds": 3.6903768655540383,
"eval_ppl_dig": 1.0884380017066235,
"eval_ppl_exon": 3.198014478374761,
"eval_ppl_intron": 2.9685884822623727,
"eval_ppl_nig": 2.7787749476744623,
"eval_ppl_promoter": 3.2509216061956865,
"eval_ppl_utr": 3.3628005411378803,
"step": 6000,
"tokens_trained": 19.659011552
}
],
"logging_steps": 10,
"max_steps": 30600,
"num_input_tokens_seen": 0,
"num_train_epochs": 9,
"save_steps": 3000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}