andyjzhao's picture
Upload folder using huggingface_hub
5755a23 verified
{
"best_global_step": 6000,
"best_metric": 2.998067346037042,
"best_model_checkpoint": "/gpfs/scratch/guoh/DNAFM/output/gencode_human_12.8k_12800/HNet_BPT989_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": 1630.637939453125,
"loss": 88.6226,
"loss_ce": 60.03535461425781,
"loss_region": 0.10551077872514725,
"loss_total": 60.140865325927734,
"lr": 2.20454076850486e-05,
"router/selected_tokens_s0": 919.25,
"router/selected_tokens_s1": 207.375,
"step": 10,
"tokens_trained": 0.03276544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.005673758865248227,
"grad_norm": 479.0514221191406,
"loss": 44.5113,
"loss_ce": 25.269031524658203,
"loss_region": 0.9648033976554871,
"loss_total": 26.233835220336914,
"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": 338.2317810058594,
"loss": 14.8642,
"loss_ce": 7.425730228424072,
"loss_region": 0.9663561582565308,
"loss_total": 8.392086029052734,
"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": 492.4618835449219,
"loss": 7.0085,
"loss_ce": 7.411436557769775,
"loss_region": 0.9673476815223694,
"loss_total": 8.3787841796875,
"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": 441.222900390625,
"loss": 9.4864,
"loss_ce": 10.71827220916748,
"loss_region": 0.9682716727256775,
"loss_total": 11.686543464660645,
"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": 597.226806640625,
"loss": 15.1303,
"loss_ce": 20.19317626953125,
"loss_region": 0.968892514705658,
"loss_total": 21.16206932067871,
"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": 610.672607421875,
"loss": 13.1567,
"loss_ce": 11.587564468383789,
"loss_region": 0.9703285098075867,
"loss_total": 12.557892799377441,
"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": 364.7670593261719,
"loss": 10.966,
"loss_ce": 17.02631378173828,
"loss_region": 0.9707926511764526,
"loss_total": 17.997106552124023,
"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": 515.1493530273438,
"loss": 13.6219,
"loss_ce": 12.72504997253418,
"loss_region": 0.9703077673912048,
"loss_total": 13.695357322692871,
"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": 261.4297180175781,
"loss": 13.2669,
"loss_ce": 15.91538143157959,
"loss_region": 0.969863772392273,
"loss_total": 16.885244369506836,
"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": 537.6857299804688,
"loss": 14.7024,
"loss_ce": 17.717187881469727,
"loss_region": 0.9700204133987427,
"loss_total": 18.68720817565918,
"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": 300.2855529785156,
"loss": 11.4653,
"loss_ce": 8.877747535705566,
"loss_region": 0.10213130712509155,
"loss_total": 8.979878425598145,
"lr": 0.00029148927939119814,
"router/selected_tokens_s0": 2521.375,
"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": 480.1593933105469,
"loss": 10.5954,
"loss_ce": 12.311738967895508,
"loss_region": 0.12702159583568573,
"loss_total": 12.438760757446289,
"lr": 0.00031598417681902996,
"router/selected_tokens_s0": 3126.375,
"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": 325.0716247558594,
"loss": 11.277,
"loss_ce": 10.923357963562012,
"loss_region": 0.11427915096282959,
"loss_total": 11.037636756896973,
"lr": 0.00034047907424686173,
"router/selected_tokens_s0": 2800.375,
"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": 162.2258758544922,
"loss": 9.8598,
"loss_ce": 5.65625,
"loss_region": 0.13778820633888245,
"loss_total": 5.79403829574585,
"lr": 0.0003649739716746935,
"router/selected_tokens_s0": 3915.375,
"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": 286.8069763183594,
"loss": 6.7746,
"loss_ce": 9.406194686889648,
"loss_region": 0.07919373363256454,
"loss_total": 9.48538875579834,
"lr": 0.00038946886910252526,
"router/selected_tokens_s0": 1466.9375,
"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": 269.352783203125,
"loss": 5.7788,
"loss_ce": 9.565649032592773,
"loss_region": 0.9683924913406372,
"loss_total": 10.534041404724121,
"lr": 0.0004139637665303571,
"router/selected_tokens_s0": 1.0,
"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": 120.00736236572266,
"loss": 6.743,
"loss_ce": 5.809171199798584,
"loss_region": 0.11065831035375595,
"loss_total": 5.919829368591309,
"lr": 0.0004384586639581888,
"router/selected_tokens_s0": 2808.75,
"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": 143.41748046875,
"loss": 4.5633,
"loss_ce": 4.988459587097168,
"loss_region": 0.17456556856632233,
"loss_total": 5.163025379180908,
"lr": 0.0004629535613860206,
"router/selected_tokens_s0": 4780.4375,
"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": 198.15806579589844,
"loss": 3.8252,
"loss_ce": 5.1574931144714355,
"loss_region": 0.21408332884311676,
"loss_total": 5.371576309204102,
"lr": 0.00048744845881385244,
"router/selected_tokens_s0": 5731.9375,
"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": 178.36068725585938,
"loss": 6.8621,
"loss_ce": 6.98280668258667,
"loss_region": 0.07259761542081833,
"loss_total": 7.055404186248779,
"lr": 0.0005119433562416841,
"router/selected_tokens_s0": 1102.5,
"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": 123.39852142333984,
"loss": 5.1909,
"loss_ce": 4.071774482727051,
"loss_region": 0.11685775220394135,
"loss_total": 4.188632011413574,
"lr": 0.0005364382536695159,
"router/selected_tokens_s0": 3242.6875,
"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": 94.15641784667969,
"loss": 4.7615,
"loss_ce": 5.413005828857422,
"loss_region": 0.1339714229106903,
"loss_total": 5.5469770431518555,
"lr": 0.0005609331510973477,
"router/selected_tokens_s0": 3748.125,
"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": 68.37236022949219,
"loss": 3.3249,
"loss_ce": 1.9714446067810059,
"loss_region": 0.09609804302453995,
"loss_total": 2.067542552947998,
"lr": 0.0005854280485251795,
"router/selected_tokens_s0": 2231.875,
"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": 98.68827819824219,
"loss": 2.5161,
"loss_ce": 2.8443872928619385,
"loss_region": 0.10850368440151215,
"loss_total": 2.9528908729553223,
"lr": 0.0006099229459530113,
"router/selected_tokens_s0": 2888.375,
"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": 156.4917755126953,
"loss": 3.2518,
"loss_ce": 5.879138946533203,
"loss_region": 0.05636154115200043,
"loss_total": 5.935500621795654,
"lr": 0.0006344178433808431,
"router/selected_tokens_s0": 23.6875,
"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": 66.22383117675781,
"loss": 4.0904,
"loss_ce": 2.8470406532287598,
"loss_region": 0.19776995480060577,
"loss_total": 3.0448105335235596,
"lr": 0.0006589127408086749,
"router/selected_tokens_s0": 5504.0,
"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": 82.5650405883789,
"loss": 3.8749,
"loss_ce": 4.707574844360352,
"loss_region": 0.13613729178905487,
"loss_total": 4.843712329864502,
"lr": 0.0006834076382365066,
"router/selected_tokens_s0": 3865.3125,
"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": 49.25559997558594,
"loss": 3.7518,
"loss_ce": 3.217980146408081,
"loss_region": 0.07522433996200562,
"loss_total": 3.2932045459747314,
"lr": 0.0007079025356643384,
"router/selected_tokens_s0": 1294.875,
"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": 91.8722915649414,
"loss": 4.1724,
"loss_ce": 4.418632984161377,
"loss_region": 0.1931368112564087,
"loss_total": 4.611769676208496,
"lr": 0.0007323974330921702,
"router/selected_tokens_s0": 5670.5,
"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": 57.65898895263672,
"loss": 3.342,
"loss_ce": 1.7671482563018799,
"loss_region": 0.13846704363822937,
"loss_total": 1.9056153297424316,
"lr": 0.000756892330520002,
"router/selected_tokens_s0": 4120.75,
"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": 54.67989730834961,
"loss": 3.6009,
"loss_ce": 1.9458640813827515,
"loss_region": 0.10488849133253098,
"loss_total": 2.050752639770508,
"lr": 0.0007813872279478337,
"router/selected_tokens_s0": 2792.0,
"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": 81.29891204833984,
"loss": 3.6246,
"loss_ce": 2.3018128871917725,
"loss_region": 0.09965165704488754,
"loss_total": 2.4014644622802734,
"lr": 0.0008058821253756655,
"router/selected_tokens_s0": 2326.5,
"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": 59.7260856628418,
"loss": 2.717,
"loss_ce": 1.7813047170639038,
"loss_region": 0.11393033713102341,
"loss_total": 1.8952350616455078,
"lr": 0.0008303770228034974,
"router/selected_tokens_s0": 3166.5625,
"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": 39.44504165649414,
"loss": 1.8522,
"loss_ce": 1.858303427696228,
"loss_region": 0.07666981220245361,
"loss_total": 1.9349732398986816,
"lr": 0.0008548719202313291,
"router/selected_tokens_s0": 1411.5625,
"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": 46.70553207397461,
"loss": 2.1525,
"loss_ce": 1.846787452697754,
"loss_region": 0.10527511686086655,
"loss_total": 1.9520626068115234,
"lr": 0.0008793668176591608,
"router/selected_tokens_s0": 2740.6875,
"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": 42.21476745605469,
"loss": 2.2006,
"loss_ce": 1.8438307046890259,
"loss_region": 0.0864676907658577,
"loss_total": 1.9302984476089478,
"lr": 0.0009038617150869926,
"router/selected_tokens_s0": 1980.625,
"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": 104.00314331054688,
"loss": 2.3132,
"loss_ce": 3.442901849746704,
"loss_region": 0.0683647096157074,
"loss_total": 3.5112664699554443,
"lr": 0.0009283566125148244,
"router/selected_tokens_s0": 1006.5,
"router/selected_tokens_s1": 1.0,
"step": 380,
"tokens_trained": 1.2450722
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11063829787234042,
"grad_norm": 78.1941146850586,
"loss": 3.3132,
"loss_ce": 4.232690334320068,
"loss_region": 0.10663130134344101,
"loss_total": 4.339321613311768,
"lr": 0.0009528515099426562,
"router/selected_tokens_s0": 2983.6875,
"router/selected_tokens_s1": 2.0,
"step": 390,
"tokens_trained": 1.27783604
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11347517730496454,
"grad_norm": 95.86592102050781,
"loss": 2.8042,
"loss_ce": 4.492650032043457,
"loss_region": 0.14126580953598022,
"loss_total": 4.633915901184082,
"lr": 0.000977346407370488,
"router/selected_tokens_s0": 3625.0625,
"router/selected_tokens_s1": 336.1875,
"step": 400,
"tokens_trained": 1.31060148
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11631205673758865,
"grad_norm": 42.11272430419922,
"loss": 2.7845,
"loss_ce": 1.6918444633483887,
"loss_region": 0.05655944347381592,
"loss_total": 1.7484039068222046,
"lr": 0.0010018413047983197,
"router/selected_tokens_s0": 374.75,
"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": 46.05327224731445,
"loss": 2.3243,
"loss_ce": 1.7027208805084229,
"loss_region": 0.1161847934126854,
"loss_total": 1.8189057111740112,
"lr": 0.0010263362022261515,
"router/selected_tokens_s0": 3265.1875,
"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": 64.44268035888672,
"loss": 2.5778,
"loss_ce": 2.2099809646606445,
"loss_region": 0.056851863861083984,
"loss_total": 2.2668328285217285,
"lr": 0.0010508310996539833,
"router/selected_tokens_s0": 343.6875,
"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": 69.73699951171875,
"loss": 2.1567,
"loss_ce": 2.3271026611328125,
"loss_region": 0.08058959245681763,
"loss_total": 2.4076921939849854,
"lr": 0.0010753259970818151,
"router/selected_tokens_s0": 1795.1875,
"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": 41.13121032714844,
"loss": 1.6985,
"loss_ce": 1.7502132654190063,
"loss_region": 0.060783833265304565,
"loss_total": 1.8109971284866333,
"lr": 0.001099820894509647,
"router/selected_tokens_s0": 912.25,
"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": 23.884733200073242,
"loss": 1.8075,
"loss_ce": 1.7715412378311157,
"loss_region": 0.06649690866470337,
"loss_total": 1.8380382061004639,
"lr": 0.0011243157919374788,
"router/selected_tokens_s0": 803.75,
"router/selected_tokens_s1": 28.75,
"step": 460,
"tokens_trained": 1.50719412
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13333333333333333,
"grad_norm": 27.034103393554688,
"loss": 1.855,
"loss_ce": 1.4545748233795166,
"loss_region": 0.06679507344961166,
"loss_total": 1.5213699340820312,
"lr": 0.0011488106893653104,
"router/selected_tokens_s0": 1278.5,
"router/selected_tokens_s1": 6.1875,
"step": 470,
"tokens_trained": 1.53995956
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13617021276595745,
"grad_norm": 45.51372528076172,
"loss": 1.6442,
"loss_ce": 1.8091086149215698,
"loss_region": 0.06229155510663986,
"loss_total": 1.8714001178741455,
"lr": 0.0011733055867931422,
"router/selected_tokens_s0": 604.3125,
"router/selected_tokens_s1": 18.375,
"step": 480,
"tokens_trained": 1.5727242
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13900709219858157,
"grad_norm": 41.38487243652344,
"loss": 1.7489,
"loss_ce": 1.6256108283996582,
"loss_region": 0.07747390866279602,
"loss_total": 1.7030847072601318,
"lr": 0.001197800484220974,
"router/selected_tokens_s0": 1453.625,
"router/selected_tokens_s1": 75.0,
"step": 490,
"tokens_trained": 1.60548964
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.14184397163120568,
"grad_norm": 27.50923728942871,
"loss": 1.704,
"loss_ce": 1.4722363948822021,
"loss_region": 0.06361720710992813,
"loss_total": 1.535853624343872,
"lr": 0.0012222953816488059,
"router/selected_tokens_s0": 779.1875,
"router/selected_tokens_s1": 22.8125,
"step": 500,
"tokens_trained": 1.638252944
},
{
"epoch": 0.14184397163120568,
"eval_ppl": 5.020375679302198,
"eval_runtime": 2.2178,
"step": 500,
"tokens_trained": 1.638252944
},
{
"epoch": 0.14184397163120568,
"eval_F": 0.002412297835768419,
"eval_F_cds": 0.0005749708022639475,
"eval_F_dig": 0.001601687631846238,
"eval_F_exon": 0.002024979274540982,
"eval_F_intron": 0.0026823310403626226,
"eval_F_nig": 0.0027446730975761655,
"eval_F_promoter": 0.0013133514412650286,
"eval_F_utr": 0.0028351861523539506,
"eval_G": 0.025070100290056414,
"eval_G_cds": 0.006592529450408768,
"eval_G_dig": 0.013054837658215485,
"eval_G_exon": 0.0204957217641103,
"eval_G_intron": 0.0275639601731152,
"eval_G_nig": 0.029588715312590982,
"eval_G_promoter": 0.01396729528315357,
"eval_G_utr": 0.024487496469340553,
"eval_avg_bp_per_token": 414.5425101214575,
"eval_bp_per_token/cds": 1739.21875,
"eval_bp_per_token/dig": 624.3414634146342,
"eval_bp_per_token/exon": 493.8322147651007,
"eval_bp_per_token/intron": 372.81006145490926,
"eval_bp_per_token/nig": 364.3421145064981,
"eval_bp_per_token/promoter": 761.4108216432866,
"eval_bp_per_token/utr": 352.7105263157895,
"eval_ppl_cds": 5.0745923462223805,
"eval_ppl_dig": 5.089918968649901,
"eval_ppl_exon": 5.0096468826855345,
"eval_ppl_intron": 5.023167391585644,
"eval_ppl_nig": 5.002412039213493,
"eval_ppl_promoter": 4.969192260932606,
"eval_ppl_utr": 4.995333125490376,
"step": 500,
"tokens_trained": 1.638252944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.14468085106382977,
"grad_norm": 18.730314254760742,
"loss": 1.6324,
"loss_ce": 1.4263192415237427,
"loss_region": 0.06919127702713013,
"loss_total": 1.4955105781555176,
"lr": 0.0012243786686061229,
"router/selected_tokens_s0": 1183.625,
"router/selected_tokens_s1": 46.0,
"step": 510,
"tokens_trained": 1.671014152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1475177304964539,
"grad_norm": 16.276996612548828,
"loss": 1.4786,
"loss_ce": 1.3790802955627441,
"loss_region": 0.060240939259529114,
"loss_total": 1.4393212795257568,
"lr": 0.0012239717766222718,
"router/selected_tokens_s0": 194.1875,
"router/selected_tokens_s1": 7.125,
"step": 520,
"tokens_trained": 1.703779592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.150354609929078,
"grad_norm": 24.13681983947754,
"loss": 1.6421,
"loss_ce": 1.6586048603057861,
"loss_region": 0.06046159565448761,
"loss_total": 1.7190665006637573,
"lr": 0.001223564884638421,
"router/selected_tokens_s0": 948.0,
"router/selected_tokens_s1": 9.0625,
"step": 530,
"tokens_trained": 1.736545032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.15319148936170213,
"grad_norm": 39.31205749511719,
"loss": 1.6168,
"loss_ce": 1.689642310142517,
"loss_region": 0.06132669746875763,
"loss_total": 1.7509690523147583,
"lr": 0.00122315799265457,
"router/selected_tokens_s0": 618.0,
"router/selected_tokens_s1": 18.0625,
"step": 540,
"tokens_trained": 1.769310472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.15602836879432624,
"grad_norm": 39.57848358154297,
"loss": 1.5849,
"loss_ce": 1.6077150106430054,
"loss_region": 0.05697261542081833,
"loss_total": 1.6646876335144043,
"lr": 0.001222751100670719,
"router/selected_tokens_s0": 451.8125,
"router/selected_tokens_s1": 6.3125,
"step": 550,
"tokens_trained": 1.802075912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.15886524822695036,
"grad_norm": 47.972530364990234,
"loss": 1.6857,
"loss_ce": 1.8609164953231812,
"loss_region": 0.05524138733744621,
"loss_total": 1.916157841682434,
"lr": 0.001222344208686868,
"router/selected_tokens_s0": 307.3125,
"router/selected_tokens_s1": 5.0,
"step": 560,
"tokens_trained": 1.834841352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.16170212765957448,
"grad_norm": 38.630558013916016,
"loss": 1.687,
"loss_ce": 1.7399615049362183,
"loss_region": 0.06043495982885361,
"loss_total": 1.80039644241333,
"lr": 0.0012219373167030169,
"router/selected_tokens_s0": 1151.625,
"router/selected_tokens_s1": 2.5625,
"step": 570,
"tokens_trained": 1.867606792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.16453900709219857,
"grad_norm": 28.116954803466797,
"loss": 1.5409,
"loss_ce": 1.4483039379119873,
"loss_region": 0.05134333670139313,
"loss_total": 1.4996472597122192,
"lr": 0.0012215304247191658,
"router/selected_tokens_s0": 275.0,
"router/selected_tokens_s1": 1.3125,
"step": 580,
"tokens_trained": 1.900370632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1673758865248227,
"grad_norm": 22.577993392944336,
"loss": 1.6098,
"loss_ce": 1.4538688659667969,
"loss_region": 0.05483899638056755,
"loss_total": 1.508707880973816,
"lr": 0.0012211235327353148,
"router/selected_tokens_s0": 305.0625,
"router/selected_tokens_s1": 5.25,
"step": 590,
"tokens_trained": 1.933136072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1702127659574468,
"grad_norm": 40.604774475097656,
"loss": 1.6165,
"loss_ce": 1.647032380104065,
"loss_region": 0.08088662475347519,
"loss_total": 1.7279189825057983,
"lr": 0.0012207166407514638,
"router/selected_tokens_s0": 253.9375,
"router/selected_tokens_s1": 20.1875,
"step": 600,
"tokens_trained": 1.965901512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17304964539007092,
"grad_norm": 15.52480697631836,
"loss": 1.5046,
"loss_ce": 1.347977638244629,
"loss_region": 0.05137379840016365,
"loss_total": 1.3993514776229858,
"lr": 0.0012203097487676127,
"router/selected_tokens_s0": 453.875,
"router/selected_tokens_s1": 2.875,
"step": 610,
"tokens_trained": 1.998666952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17588652482269504,
"grad_norm": 47.213138580322266,
"loss": 1.5088,
"loss_ce": 1.8579106330871582,
"loss_region": 0.05340619385242462,
"loss_total": 1.9113168716430664,
"lr": 0.0012199028567837617,
"router/selected_tokens_s0": 305.0,
"router/selected_tokens_s1": 3.5625,
"step": 620,
"tokens_trained": 2.031432392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17872340425531916,
"grad_norm": 23.589649200439453,
"loss": 1.4227,
"loss_ce": 1.362052083015442,
"loss_region": 0.06349397450685501,
"loss_total": 1.4255460500717163,
"lr": 0.0012194959647999107,
"router/selected_tokens_s0": 174.6875,
"router/selected_tokens_s1": 3.3125,
"step": 630,
"tokens_trained": 2.064197832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.18156028368794327,
"grad_norm": 11.682387351989746,
"loss": 1.3963,
"loss_ce": 1.3035075664520264,
"loss_region": 0.054032620042562485,
"loss_total": 1.3575401306152344,
"lr": 0.0012190890728160596,
"router/selected_tokens_s0": 574.5,
"router/selected_tokens_s1": 1.375,
"step": 640,
"tokens_trained": 2.096963272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.18439716312056736,
"grad_norm": 16.581283569335938,
"loss": 1.4373,
"loss_ce": 1.2942084074020386,
"loss_region": 0.06227206438779831,
"loss_total": 1.3564804792404175,
"lr": 0.0012186821808322086,
"router/selected_tokens_s0": 247.25,
"router/selected_tokens_s1": 9.125,
"step": 650,
"tokens_trained": 2.129728712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.18723404255319148,
"grad_norm": 17.90604019165039,
"loss": 1.5133,
"loss_ce": 1.3342182636260986,
"loss_region": 0.10024743527173996,
"loss_total": 1.4344656467437744,
"lr": 0.0012182752888483576,
"router/selected_tokens_s0": 1289.5625,
"router/selected_tokens_s1": 121.4375,
"step": 660,
"tokens_trained": 2.162494152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1900709219858156,
"grad_norm": 20.957000732421875,
"loss": 1.523,
"loss_ce": 1.3729053735733032,
"loss_region": 0.05556885898113251,
"loss_total": 1.4284741878509521,
"lr": 0.0012178683968645065,
"router/selected_tokens_s0": 160.25,
"router/selected_tokens_s1": 3.875,
"step": 670,
"tokens_trained": 2.195259592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.19290780141843972,
"grad_norm": 22.54232406616211,
"loss": 1.4559,
"loss_ce": 1.3261032104492188,
"loss_region": 0.055951084941625595,
"loss_total": 1.382054328918457,
"lr": 0.0012174615048806555,
"router/selected_tokens_s0": 96.125,
"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": 13.925896644592285,
"loss": 1.3547,
"loss_ce": 1.3023862838745117,
"loss_region": 0.05069010332226753,
"loss_total": 1.3530763387680054,
"lr": 0.0012170546128968045,
"router/selected_tokens_s0": 337.625,
"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": 12.42866039276123,
"loss": 1.3505,
"loss_ce": 1.2891850471496582,
"loss_region": 0.07324955612421036,
"loss_total": 1.3624346256256104,
"lr": 0.0012166477209129534,
"router/selected_tokens_s0": 643.0625,
"router/selected_tokens_s1": 35.4375,
"step": 700,
"tokens_trained": 2.293555912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20141843971631207,
"grad_norm": 25.85889434814453,
"loss": 1.3485,
"loss_ce": 1.3655128479003906,
"loss_region": 0.06356744468212128,
"loss_total": 1.4290802478790283,
"lr": 0.0012162408289291026,
"router/selected_tokens_s0": 453.1875,
"router/selected_tokens_s1": 18.125,
"step": 710,
"tokens_trained": 2.326321352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20425531914893616,
"grad_norm": 8.729594230651855,
"loss": 1.3482,
"loss_ce": 1.2156054973602295,
"loss_region": 0.05525539815425873,
"loss_total": 1.2708609104156494,
"lr": 0.0012158339369452516,
"router/selected_tokens_s0": 438.3125,
"router/selected_tokens_s1": 6.5625,
"step": 720,
"tokens_trained": 2.359086792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20709219858156028,
"grad_norm": 16.93632698059082,
"loss": 1.3283,
"loss_ce": 1.3369078636169434,
"loss_region": 0.05985880643129349,
"loss_total": 1.3967666625976562,
"lr": 0.0012154270449614005,
"router/selected_tokens_s0": 255.75,
"router/selected_tokens_s1": 9.25,
"step": 730,
"tokens_trained": 2.391852232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2099290780141844,
"grad_norm": 10.29341983795166,
"loss": 1.3212,
"loss_ce": 1.2369259595870972,
"loss_region": 0.0615067295730114,
"loss_total": 1.29843270778656,
"lr": 0.0012150201529775495,
"router/selected_tokens_s0": 504.125,
"router/selected_tokens_s1": 15.375,
"step": 740,
"tokens_trained": 2.424616064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2127659574468085,
"grad_norm": 12.911612510681152,
"loss": 1.3173,
"loss_ce": 1.2570594549179077,
"loss_region": 0.06437371671199799,
"loss_total": 1.321433186531067,
"lr": 0.0012146132609936982,
"router/selected_tokens_s0": 461.875,
"router/selected_tokens_s1": 17.9375,
"step": 750,
"tokens_trained": 2.457381496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.21560283687943263,
"grad_norm": 10.224205017089844,
"loss": 1.3042,
"loss_ce": 1.2603733539581299,
"loss_region": 0.062456872314214706,
"loss_total": 1.3228302001953125,
"lr": 0.0012142063690098472,
"router/selected_tokens_s0": 335.4375,
"router/selected_tokens_s1": 15.4375,
"step": 760,
"tokens_trained": 2.490146936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.21843971631205675,
"grad_norm": 6.643783092498779,
"loss": 1.296,
"loss_ce": 1.2319194078445435,
"loss_region": 0.0581849031150341,
"loss_total": 1.2901042699813843,
"lr": 0.0012137994770259962,
"router/selected_tokens_s0": 402.4375,
"router/selected_tokens_s1": 11.0,
"step": 770,
"tokens_trained": 2.522912376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22127659574468084,
"grad_norm": 8.539620399475098,
"loss": 1.2892,
"loss_ce": 1.2454586029052734,
"loss_region": 0.05890984833240509,
"loss_total": 1.304368495941162,
"lr": 0.0012133925850421454,
"router/selected_tokens_s0": 272.25,
"router/selected_tokens_s1": 8.625,
"step": 780,
"tokens_trained": 2.555677816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22411347517730495,
"grad_norm": 9.312758445739746,
"loss": 1.2829,
"loss_ce": 1.2416056394577026,
"loss_region": 0.05711473524570465,
"loss_total": 1.298720359802246,
"lr": 0.0012129856930582943,
"router/selected_tokens_s0": 412.1875,
"router/selected_tokens_s1": 8.6875,
"step": 790,
"tokens_trained": 2.588443256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22695035460992907,
"grad_norm": 13.046083450317383,
"loss": 1.2906,
"loss_ce": 1.230719804763794,
"loss_region": 0.05725303664803505,
"loss_total": 1.2879728078842163,
"lr": 0.0012125788010744433,
"router/selected_tokens_s0": 398.3125,
"router/selected_tokens_s1": 8.6875,
"step": 800,
"tokens_trained": 2.621208696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2297872340425532,
"grad_norm": 10.468182563781738,
"loss": 1.3095,
"loss_ce": 1.231147289276123,
"loss_region": 0.061947327107191086,
"loss_total": 1.2930946350097656,
"lr": 0.0012121719090905923,
"router/selected_tokens_s0": 618.0625,
"router/selected_tokens_s1": 16.9375,
"step": 810,
"tokens_trained": 2.653974128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2326241134751773,
"grad_norm": 13.493775367736816,
"loss": 1.3094,
"loss_ce": 1.288047194480896,
"loss_region": 0.07109444588422775,
"loss_total": 1.3591415882110596,
"lr": 0.0012117650171067412,
"router/selected_tokens_s0": 400.625,
"router/selected_tokens_s1": 21.5,
"step": 820,
"tokens_trained": 2.686739568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.23546099290780143,
"grad_norm": 11.455880165100098,
"loss": 1.3091,
"loss_ce": 1.2492051124572754,
"loss_region": 0.05696583166718483,
"loss_total": 1.30617094039917,
"lr": 0.0012113581251228902,
"router/selected_tokens_s0": 428.6875,
"router/selected_tokens_s1": 7.75,
"step": 830,
"tokens_trained": 2.719505008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.23829787234042554,
"grad_norm": 17.325927734375,
"loss": 1.3211,
"loss_ce": 1.2634320259094238,
"loss_region": 0.055105820298194885,
"loss_total": 1.3185378313064575,
"lr": 0.0012109512331390391,
"router/selected_tokens_s0": 383.9375,
"router/selected_tokens_s1": 7.5625,
"step": 840,
"tokens_trained": 2.752270448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24113475177304963,
"grad_norm": 7.47580623626709,
"loss": 1.2889,
"loss_ce": 1.1895134449005127,
"loss_region": 0.07138022780418396,
"loss_total": 1.260893702507019,
"lr": 0.0012105443411551881,
"router/selected_tokens_s0": 640.6875,
"router/selected_tokens_s1": 26.75,
"step": 850,
"tokens_trained": 2.785035888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24397163120567375,
"grad_norm": 7.988100528717041,
"loss": 1.2856,
"loss_ce": 1.2606642246246338,
"loss_region": 0.05701002851128578,
"loss_total": 1.3176742792129517,
"lr": 0.001210137449171337,
"router/selected_tokens_s0": 351.9375,
"router/selected_tokens_s1": 8.5,
"step": 860,
"tokens_trained": 2.817797816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24680851063829787,
"grad_norm": 8.923615455627441,
"loss": 1.2757,
"loss_ce": 1.233718752861023,
"loss_region": 0.061422333121299744,
"loss_total": 1.2951411008834839,
"lr": 0.001209730557187486,
"router/selected_tokens_s0": 302.5,
"router/selected_tokens_s1": 12.1875,
"step": 870,
"tokens_trained": 2.850563256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24964539007092199,
"grad_norm": 10.27121353149414,
"loss": 1.29,
"loss_ce": 1.2663887739181519,
"loss_region": 0.05221039056777954,
"loss_total": 1.3185992240905762,
"lr": 0.001209323665203635,
"router/selected_tokens_s0": 404.0625,
"router/selected_tokens_s1": 3.3125,
"step": 880,
"tokens_trained": 2.883328696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2524822695035461,
"grad_norm": 6.205187797546387,
"loss": 1.2855,
"loss_ce": 1.2068557739257812,
"loss_region": 0.06301470100879669,
"loss_total": 1.2698705196380615,
"lr": 0.001208916773219784,
"router/selected_tokens_s0": 376.5,
"router/selected_tokens_s1": 15.625,
"step": 890,
"tokens_trained": 2.916094136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2553191489361702,
"grad_norm": 1.0363818407058716,
"loss": 1.2721,
"loss_ce": 1.2075473070144653,
"loss_region": 0.05672357976436615,
"loss_total": 1.2642709016799927,
"lr": 0.001208509881235933,
"router/selected_tokens_s0": 444.0625,
"router/selected_tokens_s1": 9.75,
"step": 900,
"tokens_trained": 2.948859576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2581560283687943,
"grad_norm": 3.8346028327941895,
"loss": 1.2822,
"loss_ce": 1.211919903755188,
"loss_region": 0.05047914385795593,
"loss_total": 1.2623990774154663,
"lr": 0.001208102989252082,
"router/selected_tokens_s0": 251.9375,
"router/selected_tokens_s1": 2.875,
"step": 910,
"tokens_trained": 2.981619384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.26099290780141843,
"grad_norm": 10.03120231628418,
"loss": 1.2769,
"loss_ce": 1.2070960998535156,
"loss_region": 0.053904660046100616,
"loss_total": 1.2610007524490356,
"lr": 0.0012076960972682309,
"router/selected_tokens_s0": 419.0,
"router/selected_tokens_s1": 5.625,
"step": 920,
"tokens_trained": 3.014384824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.26382978723404255,
"grad_norm": 10.83735466003418,
"loss": 1.2681,
"loss_ce": 1.269758939743042,
"loss_region": 0.061172302812337875,
"loss_total": 1.3309311866760254,
"lr": 0.0012072892052843798,
"router/selected_tokens_s0": 413.5,
"router/selected_tokens_s1": 14.25,
"step": 930,
"tokens_trained": 3.047149464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.26666666666666666,
"grad_norm": 8.0000581741333,
"loss": 1.2667,
"loss_ce": 1.2282646894454956,
"loss_region": 0.055803608149290085,
"loss_total": 1.2840683460235596,
"lr": 0.0012068823133005288,
"router/selected_tokens_s0": 468.25,
"router/selected_tokens_s1": 8.0625,
"step": 940,
"tokens_trained": 3.079914904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2695035460992908,
"grad_norm": 6.741837501525879,
"loss": 1.272,
"loss_ce": 1.1557844877243042,
"loss_region": 0.06386042386293411,
"loss_total": 1.2196449041366577,
"lr": 0.0012064754213166778,
"router/selected_tokens_s0": 312.0,
"router/selected_tokens_s1": 12.1875,
"step": 950,
"tokens_trained": 3.112675728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2723404255319149,
"grad_norm": 7.861258506774902,
"loss": 1.2717,
"loss_ce": 1.2447525262832642,
"loss_region": 0.05689748376607895,
"loss_total": 1.301650047302246,
"lr": 0.001206068529332827,
"router/selected_tokens_s0": 551.4375,
"router/selected_tokens_s1": 9.3125,
"step": 960,
"tokens_trained": 3.145441168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.275177304964539,
"grad_norm": 2.8089139461517334,
"loss": 1.2699,
"loss_ce": 1.1975443363189697,
"loss_region": 0.06169455498456955,
"loss_total": 1.259238839149475,
"lr": 0.001205661637348976,
"router/selected_tokens_s0": 384.4375,
"router/selected_tokens_s1": 13.1875,
"step": 970,
"tokens_trained": 3.178206608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.27801418439716313,
"grad_norm": 1.8372883796691895,
"loss": 1.2593,
"loss_ce": 1.1845065355300903,
"loss_region": 0.060579411685466766,
"loss_total": 1.2450859546661377,
"lr": 0.0012052547453651249,
"router/selected_tokens_s0": 402.375,
"router/selected_tokens_s1": 12.3125,
"step": 980,
"tokens_trained": 3.210972048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.28085106382978725,
"grad_norm": 4.381184101104736,
"loss": 1.2706,
"loss_ce": 1.196001410484314,
"loss_region": 0.06673609465360641,
"loss_total": 1.262737512588501,
"lr": 0.0012048478533812738,
"router/selected_tokens_s0": 403.1875,
"router/selected_tokens_s1": 18.9375,
"step": 990,
"tokens_trained": 3.243737488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.28368794326241137,
"grad_norm": 8.494468688964844,
"loss": 1.2773,
"loss_ce": 1.209201693534851,
"loss_region": 0.06362592428922653,
"loss_total": 1.2728276252746582,
"lr": 0.0012044409613974226,
"router/selected_tokens_s0": 486.875,
"router/selected_tokens_s1": 18.0,
"step": 1000,
"tokens_trained": 3.276502928
},
{
"epoch": 0.28368794326241137,
"eval_ppl": 3.401584579757825,
"eval_runtime": 2.059,
"step": 1000,
"tokens_trained": 3.276502928
},
{
"epoch": 0.28368794326241137,
"eval_F": 0.0010583792212027433,
"eval_F_cds": 0.00044021202048333486,
"eval_F_dig": 0.003711227439643722,
"eval_F_exon": 0.0007474755711392887,
"eval_F_intron": 0.0010856597836654204,
"eval_F_nig": 0.0013487171280326855,
"eval_F_promoter": 0.0006250921188385657,
"eval_F_utr": 0.0008526875646177295,
"eval_G": 0.016025620951195235,
"eval_G_cds": 0.005563186427544695,
"eval_G_dig": 0.024053926942534574,
"eval_G_exon": 0.01363821736419728,
"eval_G_intron": 0.016894965668453225,
"eval_G_nig": 0.018964967608856607,
"eval_G_promoter": 0.010849314204034016,
"eval_G_utr": 0.013376785980750578,
"eval_avg_bp_per_token": 944.840922768305,
"eval_bp_per_token/cds": 2271.6326530612246,
"eval_bp_per_token/dig": 269.4526315789474,
"eval_bp_per_token/exon": 1337.8363636363636,
"eval_bp_per_token/intron": 921.0988700564972,
"eval_bp_per_token/nig": 741.445318084346,
"eval_bp_per_token/promoter": 1599.7642105263158,
"eval_bp_per_token/utr": 1172.7625,
"eval_ppl_cds": 3.9297508219385455,
"eval_ppl_dig": 2.056291383006035,
"eval_ppl_exon": 3.560263799656032,
"eval_ppl_intron": 3.399758405692712,
"eval_ppl_nig": 3.3399007425580884,
"eval_ppl_promoter": 3.552518241215457,
"eval_ppl_utr": 3.6236436039234974,
"step": 1000,
"tokens_trained": 3.276502928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2865248226950355,
"grad_norm": 4.319965362548828,
"loss": 1.2539,
"loss_ce": 1.1917036771774292,
"loss_region": 0.06307854503393173,
"loss_total": 1.2547821998596191,
"lr": 0.0012040340694135716,
"router/selected_tokens_s0": 447.625,
"router/selected_tokens_s1": 16.25,
"step": 1010,
"tokens_trained": 3.309267568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.28936170212765955,
"grad_norm": 7.788521766662598,
"loss": 1.2502,
"loss_ce": 1.1910172700881958,
"loss_region": 0.06294921785593033,
"loss_total": 1.2539664506912231,
"lr": 0.0012036271774297205,
"router/selected_tokens_s0": 517.625,
"router/selected_tokens_s1": 19.9375,
"step": 1020,
"tokens_trained": 3.342033008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.29219858156028367,
"grad_norm": 6.11482572555542,
"loss": 1.2644,
"loss_ce": 1.16280996799469,
"loss_region": 0.055934660136699677,
"loss_total": 1.2187446355819702,
"lr": 0.0012032202854458697,
"router/selected_tokens_s0": 781.125,
"router/selected_tokens_s1": 8.6875,
"step": 1030,
"tokens_trained": 3.374798448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2950354609929078,
"grad_norm": 4.647332668304443,
"loss": 1.2587,
"loss_ce": 1.1730914115905762,
"loss_region": 0.04860607162117958,
"loss_total": 1.221697449684143,
"lr": 0.0012028133934620187,
"router/selected_tokens_s0": 405.375,
"router/selected_tokens_s1": 1.375,
"step": 1040,
"tokens_trained": 3.407563888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2978723404255319,
"grad_norm": 9.93161392211914,
"loss": 1.2728,
"loss_ce": 1.2400729656219482,
"loss_region": 0.07498405873775482,
"loss_total": 1.3150570392608643,
"lr": 0.0012024065014781676,
"router/selected_tokens_s0": 532.25,
"router/selected_tokens_s1": 30.4375,
"step": 1050,
"tokens_trained": 3.440328528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.300709219858156,
"grad_norm": 7.319814205169678,
"loss": 1.251,
"loss_ce": 1.2057647705078125,
"loss_region": 0.06156269088387489,
"loss_total": 1.2673274278640747,
"lr": 0.0012019996094943166,
"router/selected_tokens_s0": 317.0,
"router/selected_tokens_s1": 11.3125,
"step": 1060,
"tokens_trained": 3.473093968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.30354609929078014,
"grad_norm": 3.660691022872925,
"loss": 1.2579,
"loss_ce": 1.201399803161621,
"loss_region": 0.06964390724897385,
"loss_total": 1.2710436582565308,
"lr": 0.0012015927175104656,
"router/selected_tokens_s0": 343.5625,
"router/selected_tokens_s1": 17.6875,
"step": 1070,
"tokens_trained": 3.505859408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.30638297872340425,
"grad_norm": 4.524622917175293,
"loss": 1.2455,
"loss_ce": 1.242870569229126,
"loss_region": 0.055044859647750854,
"loss_total": 1.2979154586791992,
"lr": 0.0012011858255266145,
"router/selected_tokens_s0": 431.25,
"router/selected_tokens_s1": 8.1875,
"step": 1080,
"tokens_trained": 3.538624848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.30921985815602837,
"grad_norm": 3.531444549560547,
"loss": 1.2507,
"loss_ce": 1.1871229410171509,
"loss_region": 0.05430071800947189,
"loss_total": 1.2414236068725586,
"lr": 0.0012007789335427635,
"router/selected_tokens_s0": 819.5625,
"router/selected_tokens_s1": 5.9375,
"step": 1090,
"tokens_trained": 3.571390288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3120567375886525,
"grad_norm": 5.396289348602295,
"loss": 1.2621,
"loss_ce": 1.1988043785095215,
"loss_region": 0.050519246608018875,
"loss_total": 1.2493236064910889,
"lr": 0.0012003720415589125,
"router/selected_tokens_s0": 485.875,
"router/selected_tokens_s1": 3.9375,
"step": 1100,
"tokens_trained": 3.604155728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3148936170212766,
"grad_norm": 5.735856056213379,
"loss": 1.2515,
"loss_ce": 1.1599225997924805,
"loss_region": 0.05765972658991814,
"loss_total": 1.21758234500885,
"lr": 0.0011999651495750614,
"router/selected_tokens_s0": 320.125,
"router/selected_tokens_s1": 8.8125,
"step": 1110,
"tokens_trained": 3.636921168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3177304964539007,
"grad_norm": 2.786902904510498,
"loss": 1.2463,
"loss_ce": 1.1695066690444946,
"loss_region": 0.060196422040462494,
"loss_total": 1.2297030687332153,
"lr": 0.0011995582575912104,
"router/selected_tokens_s0": 550.0,
"router/selected_tokens_s1": 15.1875,
"step": 1120,
"tokens_trained": 3.669686584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.32056737588652484,
"grad_norm": 7.254458427429199,
"loss": 1.254,
"loss_ce": 1.1615636348724365,
"loss_region": 0.06397742033004761,
"loss_total": 1.225541114807129,
"lr": 0.0011991513656073594,
"router/selected_tokens_s0": 454.4375,
"router/selected_tokens_s1": 17.5,
"step": 1130,
"tokens_trained": 3.702452024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.32340425531914896,
"grad_norm": 5.802817344665527,
"loss": 1.2488,
"loss_ce": 1.1627715826034546,
"loss_region": 0.06256798654794693,
"loss_total": 1.2253395318984985,
"lr": 0.0011987444736235083,
"router/selected_tokens_s0": 577.75,
"router/selected_tokens_s1": 19.0,
"step": 1140,
"tokens_trained": 3.735217464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3262411347517731,
"grad_norm": 1.8852355480194092,
"loss": 1.2334,
"loss_ce": 1.2047169208526611,
"loss_region": 0.061925701797008514,
"loss_total": 1.2666425704956055,
"lr": 0.0011983375816396573,
"router/selected_tokens_s0": 625.875,
"router/selected_tokens_s1": 19.6875,
"step": 1150,
"tokens_trained": 3.767982904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.32907801418439714,
"grad_norm": 6.557276725769043,
"loss": 1.2423,
"loss_ce": 1.1739070415496826,
"loss_region": 0.0680062547326088,
"loss_total": 1.2419133186340332,
"lr": 0.0011979306896558062,
"router/selected_tokens_s0": 354.0,
"router/selected_tokens_s1": 17.625,
"step": 1160,
"tokens_trained": 3.800748344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.33191489361702126,
"grad_norm": 3.2266619205474854,
"loss": 1.2305,
"loss_ce": 1.0980790853500366,
"loss_region": 0.05660313367843628,
"loss_total": 1.1546821594238281,
"lr": 0.0011975237976719552,
"router/selected_tokens_s0": 484.6875,
"router/selected_tokens_s1": 10.75,
"step": 1170,
"tokens_trained": 3.833513784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3347517730496454,
"grad_norm": 4.397397041320801,
"loss": 1.2297,
"loss_ce": 1.2073218822479248,
"loss_region": 0.049140799790620804,
"loss_total": 1.2564626932144165,
"lr": 0.0011971169056881042,
"router/selected_tokens_s0": 341.8125,
"router/selected_tokens_s1": 2.8125,
"step": 1180,
"tokens_trained": 3.866278424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3375886524822695,
"grad_norm": 4.493627071380615,
"loss": 1.2376,
"loss_ce": 1.1048059463500977,
"loss_region": 0.051098912954330444,
"loss_total": 1.1559048891067505,
"lr": 0.0011967100137042531,
"router/selected_tokens_s0": 546.4375,
"router/selected_tokens_s1": 4.75,
"step": 1190,
"tokens_trained": 3.899043864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3404255319148936,
"grad_norm": 6.189625263214111,
"loss": 1.2339,
"loss_ce": 1.1637437343597412,
"loss_region": 0.07028566300868988,
"loss_total": 1.2340294122695923,
"lr": 0.0011963031217204021,
"router/selected_tokens_s0": 495.8125,
"router/selected_tokens_s1": 26.0,
"step": 1200,
"tokens_trained": 3.931809304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3432624113475177,
"grad_norm": 5.87813663482666,
"loss": 1.242,
"loss_ce": 1.223149299621582,
"loss_region": 0.06371823698282242,
"loss_total": 1.2868674993515015,
"lr": 0.0011958962297365513,
"router/selected_tokens_s0": 239.8125,
"router/selected_tokens_s1": 10.125,
"step": 1210,
"tokens_trained": 3.964574744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.34609929078014184,
"grad_norm": 8.016247749328613,
"loss": 1.2328,
"loss_ce": 1.198567509651184,
"loss_region": 0.05910230800509453,
"loss_total": 1.2576698064804077,
"lr": 0.0011954893377527003,
"router/selected_tokens_s0": 410.75,
"router/selected_tokens_s1": 11.25,
"step": 1220,
"tokens_trained": 3.997337592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.34893617021276596,
"grad_norm": 6.139803886413574,
"loss": 1.2404,
"loss_ce": 1.1777026653289795,
"loss_region": 0.06743069738149643,
"loss_total": 1.245133399963379,
"lr": 0.0011950824457688492,
"router/selected_tokens_s0": 609.0625,
"router/selected_tokens_s1": 26.5,
"step": 1230,
"tokens_trained": 4.030103032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3517730496453901,
"grad_norm": 2.7356536388397217,
"loss": 1.2385,
"loss_ce": 1.1438438892364502,
"loss_region": 0.10062191635370255,
"loss_total": 1.2444658279418945,
"lr": 0.0011946755537849982,
"router/selected_tokens_s0": 515.625,
"router/selected_tokens_s1": 60.5625,
"step": 1240,
"tokens_trained": 4.062868472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3546099290780142,
"grad_norm": 3.0639026165008545,
"loss": 1.2257,
"loss_ce": 1.152791142463684,
"loss_region": 0.06103505194187164,
"loss_total": 1.2138261795043945,
"lr": 0.001194268661801147,
"router/selected_tokens_s0": 408.625,
"router/selected_tokens_s1": 13.875,
"step": 1250,
"tokens_trained": 4.095633912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3574468085106383,
"grad_norm": 4.941549777984619,
"loss": 1.247,
"loss_ce": 1.141486644744873,
"loss_region": 0.07407496869564056,
"loss_total": 1.2155616283416748,
"lr": 0.001193861769817296,
"router/selected_tokens_s0": 486.0625,
"router/selected_tokens_s1": 32.6875,
"step": 1260,
"tokens_trained": 4.128399352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36028368794326243,
"grad_norm": 2.038921356201172,
"loss": 1.2258,
"loss_ce": 1.1693215370178223,
"loss_region": 0.05073130875825882,
"loss_total": 1.2200528383255005,
"lr": 0.0011934548778334449,
"router/selected_tokens_s0": 396.9375,
"router/selected_tokens_s1": 4.3125,
"step": 1270,
"tokens_trained": 4.161163992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36312056737588655,
"grad_norm": 7.992796421051025,
"loss": 1.2398,
"loss_ce": 1.2495265007019043,
"loss_region": 0.04827826842665672,
"loss_total": 1.2978047132492065,
"lr": 0.001193047985849594,
"router/selected_tokens_s0": 209.0625,
"router/selected_tokens_s1": 2.125,
"step": 1280,
"tokens_trained": 4.193929432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3659574468085106,
"grad_norm": 7.719239711761475,
"loss": 1.2413,
"loss_ce": 1.2265716791152954,
"loss_region": 0.048719920217990875,
"loss_total": 1.2752915620803833,
"lr": 0.001192641093865743,
"router/selected_tokens_s0": 424.375,
"router/selected_tokens_s1": 2.375,
"step": 1290,
"tokens_trained": 4.226694872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36879432624113473,
"grad_norm": 3.3148317337036133,
"loss": 1.2322,
"loss_ce": 1.1886953115463257,
"loss_region": 0.06017257645726204,
"loss_total": 1.2488678693771362,
"lr": 0.001192234201881892,
"router/selected_tokens_s0": 436.1875,
"router/selected_tokens_s1": 14.1875,
"step": 1300,
"tokens_trained": 4.259455304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.37163120567375885,
"grad_norm": 3.881063938140869,
"loss": 1.2232,
"loss_ce": 1.1405267715454102,
"loss_region": 0.05613284558057785,
"loss_total": 1.1966595649719238,
"lr": 0.001191827309898041,
"router/selected_tokens_s0": 488.125,
"router/selected_tokens_s1": 10.0625,
"step": 1310,
"tokens_trained": 4.292217888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.37446808510638296,
"grad_norm": 3.223666191101074,
"loss": 1.2262,
"loss_ce": 1.1618560552597046,
"loss_region": 0.054282836616039276,
"loss_total": 1.2161388397216797,
"lr": 0.00119142041791419,
"router/selected_tokens_s0": 387.5625,
"router/selected_tokens_s1": 7.25,
"step": 1320,
"tokens_trained": 4.324979816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3773049645390071,
"grad_norm": 2.419039726257324,
"loss": 1.2177,
"loss_ce": 1.0862337350845337,
"loss_region": 0.060854170471429825,
"loss_total": 1.1470879316329956,
"lr": 0.0011910135259303389,
"router/selected_tokens_s0": 542.1875,
"router/selected_tokens_s1": 17.3125,
"step": 1330,
"tokens_trained": 4.357745256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3801418439716312,
"grad_norm": 1.7404555082321167,
"loss": 1.2162,
"loss_ce": 1.1373934745788574,
"loss_region": 0.06797235459089279,
"loss_total": 1.205365777015686,
"lr": 0.0011906066339464878,
"router/selected_tokens_s0": 492.875,
"router/selected_tokens_s1": 23.625,
"step": 1340,
"tokens_trained": 4.390510696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3829787234042553,
"grad_norm": 1.9988096952438354,
"loss": 1.209,
"loss_ce": 1.1519917249679565,
"loss_region": 0.06009136512875557,
"loss_total": 1.212083101272583,
"lr": 0.0011901997419626368,
"router/selected_tokens_s0": 459.75,
"router/selected_tokens_s1": 14.75,
"step": 1350,
"tokens_trained": 4.423276136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.38581560283687943,
"grad_norm": 2.7944321632385254,
"loss": 1.2114,
"loss_ce": 1.1149932146072388,
"loss_region": 0.059466730803251266,
"loss_total": 1.1744599342346191,
"lr": 0.0011897928499787858,
"router/selected_tokens_s0": 399.0625,
"router/selected_tokens_s1": 11.75,
"step": 1360,
"tokens_trained": 4.456041576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.38865248226950355,
"grad_norm": 2.893796920776367,
"loss": 1.2176,
"loss_ce": 1.1631447076797485,
"loss_region": 0.05681516230106354,
"loss_total": 1.2199598550796509,
"lr": 0.0011893859579949347,
"router/selected_tokens_s0": 431.6875,
"router/selected_tokens_s1": 9.875,
"step": 1370,
"tokens_trained": 4.488807016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.39148936170212767,
"grad_norm": 1.3144123554229736,
"loss": 1.2112,
"loss_ce": 1.0997382402420044,
"loss_region": 0.057619161903858185,
"loss_total": 1.1573574542999268,
"lr": 0.0011889790660110837,
"router/selected_tokens_s0": 530.75,
"router/selected_tokens_s1": 13.0,
"step": 1380,
"tokens_trained": 4.521572456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3943262411347518,
"grad_norm": 2.78426456451416,
"loss": 1.2116,
"loss_ce": 1.1366982460021973,
"loss_region": 0.0555262453854084,
"loss_total": 1.1922245025634766,
"lr": 0.0011885721740272327,
"router/selected_tokens_s0": 451.5625,
"router/selected_tokens_s1": 8.9375,
"step": 1390,
"tokens_trained": 4.554337096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3971631205673759,
"grad_norm": 1.5746723413467407,
"loss": 1.2185,
"loss_ce": 1.0210630893707275,
"loss_region": 0.0583292655646801,
"loss_total": 1.0793923139572144,
"lr": 0.0011881652820433816,
"router/selected_tokens_s0": 428.0,
"router/selected_tokens_s1": 11.125,
"step": 1400,
"tokens_trained": 4.587102536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4,
"grad_norm": 5.932886123657227,
"loss": 1.2196,
"loss_ce": 1.1898956298828125,
"loss_region": 0.05531156435608864,
"loss_total": 1.2452071905136108,
"lr": 0.0011877583900595306,
"router/selected_tokens_s0": 421.6875,
"router/selected_tokens_s1": 9.0,
"step": 1410,
"tokens_trained": 4.619867976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.40283687943262414,
"grad_norm": 5.935864448547363,
"loss": 1.222,
"loss_ce": 1.2237108945846558,
"loss_region": 0.054401297122240067,
"loss_total": 1.2781121730804443,
"lr": 0.0011873514980756796,
"router/selected_tokens_s0": 434.25,
"router/selected_tokens_s1": 8.0625,
"step": 1420,
"tokens_trained": 4.652632616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4056737588652482,
"grad_norm": 3.4950997829437256,
"loss": 1.2222,
"loss_ce": 1.1726809740066528,
"loss_region": 0.0537344329059124,
"loss_total": 1.2264153957366943,
"lr": 0.0011869446060918285,
"router/selected_tokens_s0": 370.75,
"router/selected_tokens_s1": 6.4375,
"step": 1430,
"tokens_trained": 4.685398056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4085106382978723,
"grad_norm": 2.04207444190979,
"loss": 1.2198,
"loss_ce": 1.1512529850006104,
"loss_region": 0.062247976660728455,
"loss_total": 1.2135009765625,
"lr": 0.0011865377141079775,
"router/selected_tokens_s0": 454.1875,
"router/selected_tokens_s1": 16.375,
"step": 1440,
"tokens_trained": 4.718163496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.41134751773049644,
"grad_norm": 1.2782090902328491,
"loss": 1.2156,
"loss_ce": 1.1050682067871094,
"loss_region": 0.061748046427965164,
"loss_total": 1.166816234588623,
"lr": 0.0011861308221241265,
"router/selected_tokens_s0": 433.9375,
"router/selected_tokens_s1": 15.875,
"step": 1450,
"tokens_trained": 4.750928936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.41418439716312055,
"grad_norm": 1.481460452079773,
"loss": 1.2037,
"loss_ce": 1.2169268131256104,
"loss_region": 0.061500489711761475,
"loss_total": 1.2784273624420166,
"lr": 0.0011857239301402756,
"router/selected_tokens_s0": 409.9375,
"router/selected_tokens_s1": 14.125,
"step": 1460,
"tokens_trained": 4.783694376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.41702127659574467,
"grad_norm": 1.3822318315505981,
"loss": 1.2076,
"loss_ce": 1.154876947402954,
"loss_region": 0.06019541248679161,
"loss_total": 1.2150723934173584,
"lr": 0.0011853170381564246,
"router/selected_tokens_s0": 414.875,
"router/selected_tokens_s1": 13.125,
"step": 1470,
"tokens_trained": 4.816459816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4198581560283688,
"grad_norm": 1.4973548650741577,
"loss": 1.2036,
"loss_ce": 1.1452707052230835,
"loss_region": 0.06044153869152069,
"loss_total": 1.2057121992111206,
"lr": 0.0011849101461725736,
"router/selected_tokens_s0": 500.1875,
"router/selected_tokens_s1": 15.6875,
"step": 1480,
"tokens_trained": 4.849225256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4226950354609929,
"grad_norm": 1.2402268648147583,
"loss": 1.2057,
"loss_ce": 1.1824591159820557,
"loss_region": 0.058981362730264664,
"loss_total": 1.2414405345916748,
"lr": 0.0011845032541887225,
"router/selected_tokens_s0": 480.1875,
"router/selected_tokens_s1": 14.125,
"step": 1490,
"tokens_trained": 4.881990696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.425531914893617,
"grad_norm": 1.4796574115753174,
"loss": 1.211,
"loss_ce": 1.1951260566711426,
"loss_region": 0.05882687494158745,
"loss_total": 1.253952980041504,
"lr": 0.0011840963622048713,
"router/selected_tokens_s0": 468.125,
"router/selected_tokens_s1": 13.0625,
"step": 1500,
"tokens_trained": 4.914756056
},
{
"epoch": 0.425531914893617,
"eval_ppl": 3.1502154013198798,
"eval_runtime": 2.0571,
"step": 1500,
"tokens_trained": 4.914756056
},
{
"epoch": 0.425531914893617,
"eval_F": 0.001229291011186336,
"eval_F_cds": 0.001293684305093882,
"eval_F_dig": 0.0017970153918274866,
"eval_F_exon": 0.0010736467294546147,
"eval_F_intron": 0.0011918489644829776,
"eval_F_nig": 0.001490433652565069,
"eval_F_promoter": 0.0010369949255679784,
"eval_F_utr": 0.0008313703755022863,
"eval_G": 0.017374615319094434,
"eval_G_cds": 0.019024816671907287,
"eval_G_dig": 0.0214062438960075,
"eval_G_exon": 0.014820481637583071,
"eval_G_intron": 0.017102886037205698,
"eval_G_nig": 0.01946365484807892,
"eval_G_promoter": 0.015690876278806876,
"eval_G_utr": 0.01441579077445348,
"eval_avg_bp_per_token": 813.4770293609672,
"eval_bp_per_token/cds": 772.9861111111111,
"eval_bp_per_token/dig": 556.4782608695652,
"eval_bp_per_token/exon": 931.4050632911392,
"eval_bp_per_token/intron": 839.0324863300096,
"eval_bp_per_token/nig": 670.9456662354463,
"eval_bp_per_token/promoter": 964.3248730964467,
"eval_bp_per_token/utr": 1202.8333333333333,
"eval_ppl_cds": 3.7561527389283587,
"eval_ppl_dig": 1.3154554554553453,
"eval_ppl_exon": 3.3617922872366606,
"eval_ppl_intron": 3.1668774100622223,
"eval_ppl_nig": 3.048275380960171,
"eval_ppl_promoter": 3.3705226274627504,
"eval_ppl_utr": 3.4453219090888463,
"step": 1500,
"tokens_trained": 4.914756056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.42836879432624114,
"grad_norm": 2.848538875579834,
"loss": 1.2073,
"loss_ce": 1.1491812467575073,
"loss_region": 0.06309393793344498,
"loss_total": 1.2122751474380493,
"lr": 0.0011836894702210202,
"router/selected_tokens_s0": 435.6875,
"router/selected_tokens_s1": 16.5,
"step": 1510,
"tokens_trained": 4.947521496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.43120567375886526,
"grad_norm": 9.449421882629395,
"loss": 1.2125,
"loss_ce": 1.211773157119751,
"loss_region": 0.05893857032060623,
"loss_total": 1.2707117795944214,
"lr": 0.0011832825782371692,
"router/selected_tokens_s0": 496.5,
"router/selected_tokens_s1": 13.625,
"step": 1520,
"tokens_trained": 4.980286136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4340425531914894,
"grad_norm": 4.181710720062256,
"loss": 1.2218,
"loss_ce": 1.162986397743225,
"loss_region": 0.054903510957956314,
"loss_total": 1.2178899049758911,
"lr": 0.0011828756862533184,
"router/selected_tokens_s0": 706.5625,
"router/selected_tokens_s1": 9.75,
"step": 1530,
"tokens_trained": 5.013051576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4368794326241135,
"grad_norm": 3.0098717212677,
"loss": 1.2173,
"loss_ce": 1.1538748741149902,
"loss_region": 0.05533435568213463,
"loss_total": 1.2092092037200928,
"lr": 0.0011824687942694674,
"router/selected_tokens_s0": 588.375,
"router/selected_tokens_s1": 10.25,
"step": 1540,
"tokens_trained": 5.045813688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4397163120567376,
"grad_norm": 2.5773324966430664,
"loss": 1.2122,
"loss_ce": 1.095015525817871,
"loss_region": 0.054704807698726654,
"loss_total": 1.149720311164856,
"lr": 0.0011820619022856163,
"router/selected_tokens_s0": 423.625,
"router/selected_tokens_s1": 8.375,
"step": 1550,
"tokens_trained": 5.078578552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4425531914893617,
"grad_norm": 3.0698676109313965,
"loss": 1.2121,
"loss_ce": 1.1329262256622314,
"loss_region": 0.05666619539260864,
"loss_total": 1.1895923614501953,
"lr": 0.0011816550103017653,
"router/selected_tokens_s0": 360.3125,
"router/selected_tokens_s1": 8.8125,
"step": 1560,
"tokens_trained": 5.111343992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4453900709219858,
"grad_norm": 0.7125281095504761,
"loss": 1.2112,
"loss_ce": 1.218764305114746,
"loss_region": 0.05678607523441315,
"loss_total": 1.275550365447998,
"lr": 0.0011812481183179143,
"router/selected_tokens_s0": 374.1875,
"router/selected_tokens_s1": 9.0,
"step": 1570,
"tokens_trained": 5.144109432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4482269503546099,
"grad_norm": 1.8508944511413574,
"loss": 1.2046,
"loss_ce": 1.1496455669403076,
"loss_region": 0.06071101874113083,
"loss_total": 1.210356593132019,
"lr": 0.0011808412263340632,
"router/selected_tokens_s0": 447.25,
"router/selected_tokens_s1": 14.4375,
"step": 1580,
"tokens_trained": 5.176874072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.451063829787234,
"grad_norm": 0.30530375242233276,
"loss": 1.207,
"loss_ce": 1.1380561590194702,
"loss_region": 0.05641654506325722,
"loss_total": 1.1944726705551147,
"lr": 0.0011804343343502122,
"router/selected_tokens_s0": 441.125,
"router/selected_tokens_s1": 10.3125,
"step": 1590,
"tokens_trained": 5.209639512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.45390070921985815,
"grad_norm": 2.42014479637146,
"loss": 1.2082,
"loss_ce": 1.1705315113067627,
"loss_region": 0.0601993128657341,
"loss_total": 1.2307307720184326,
"lr": 0.0011800274423663611,
"router/selected_tokens_s0": 471.625,
"router/selected_tokens_s1": 14.4375,
"step": 1600,
"tokens_trained": 5.242403352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.45673758865248226,
"grad_norm": 1.9463731050491333,
"loss": 1.2037,
"loss_ce": 1.137668251991272,
"loss_region": 0.059560373425483704,
"loss_total": 1.1972286701202393,
"lr": 0.0011796205503825101,
"router/selected_tokens_s0": 430.125,
"router/selected_tokens_s1": 13.375,
"step": 1610,
"tokens_trained": 5.275167992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4595744680851064,
"grad_norm": 1.944096326828003,
"loss": 1.2095,
"loss_ce": 1.1958094835281372,
"loss_region": 0.05815673992037773,
"loss_total": 1.253966212272644,
"lr": 0.001179213658398659,
"router/selected_tokens_s0": 438.0625,
"router/selected_tokens_s1": 11.875,
"step": 1620,
"tokens_trained": 5.307932632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4624113475177305,
"grad_norm": 0.5991163849830627,
"loss": 1.2036,
"loss_ce": 1.1603964567184448,
"loss_region": 0.058173276484012604,
"loss_total": 1.2185697555541992,
"lr": 0.001178806766414808,
"router/selected_tokens_s0": 421.25,
"router/selected_tokens_s1": 11.5625,
"step": 1630,
"tokens_trained": 5.340694016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4652482269503546,
"grad_norm": 1.0851240158081055,
"loss": 1.206,
"loss_ce": 1.1598323583602905,
"loss_region": 0.05617981776595116,
"loss_total": 1.2160121202468872,
"lr": 0.001178399874430957,
"router/selected_tokens_s0": 385.4375,
"router/selected_tokens_s1": 9.0,
"step": 1640,
"tokens_trained": 5.373459456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.46808510638297873,
"grad_norm": 0.9609947204589844,
"loss": 1.2045,
"loss_ce": 1.1532255411148071,
"loss_region": 0.06535308808088303,
"loss_total": 1.218578577041626,
"lr": 0.001177992982447106,
"router/selected_tokens_s0": 450.0625,
"router/selected_tokens_s1": 19.25,
"step": 1650,
"tokens_trained": 5.406224096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.47092198581560285,
"grad_norm": 0.9339040517807007,
"loss": 1.1979,
"loss_ce": 1.1834607124328613,
"loss_region": 0.06303829699754715,
"loss_total": 1.2464990615844727,
"lr": 0.001177586090463255,
"router/selected_tokens_s0": 362.5625,
"router/selected_tokens_s1": 14.1875,
"step": 1660,
"tokens_trained": 5.438988736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.47375886524822697,
"grad_norm": 1.7706341743469238,
"loss": 1.2017,
"loss_ce": 1.1299399137496948,
"loss_region": 0.059476908296346664,
"loss_total": 1.189416766166687,
"lr": 0.001177179198479404,
"router/selected_tokens_s0": 475.5,
"router/selected_tokens_s1": 13.875,
"step": 1670,
"tokens_trained": 5.471754176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4765957446808511,
"grad_norm": 1.8785125017166138,
"loss": 1.1999,
"loss_ce": 1.0933830738067627,
"loss_region": 0.06130226328969002,
"loss_total": 1.154685378074646,
"lr": 0.0011767723064955529,
"router/selected_tokens_s0": 452.5625,
"router/selected_tokens_s1": 15.125,
"step": 1680,
"tokens_trained": 5.504519616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4794326241134752,
"grad_norm": 1.1370394229888916,
"loss": 1.1996,
"loss_ce": 1.1579982042312622,
"loss_region": 0.05934907868504524,
"loss_total": 1.217347264289856,
"lr": 0.0011763654145117018,
"router/selected_tokens_s0": 394.25,
"router/selected_tokens_s1": 12.0625,
"step": 1690,
"tokens_trained": 5.537285056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.48226950354609927,
"grad_norm": 1.047006607055664,
"loss": 1.1999,
"loss_ce": 1.1407577991485596,
"loss_region": 0.06121063977479935,
"loss_total": 1.2019684314727783,
"lr": 0.0011759585225278508,
"router/selected_tokens_s0": 430.375,
"router/selected_tokens_s1": 14.9375,
"step": 1700,
"tokens_trained": 5.570050496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4851063829787234,
"grad_norm": 0.6814096570014954,
"loss": 1.2015,
"loss_ce": 1.1641886234283447,
"loss_region": 0.057673294097185135,
"loss_total": 1.2218619585037231,
"lr": 0.001175551630544,
"router/selected_tokens_s0": 437.875,
"router/selected_tokens_s1": 11.4375,
"step": 1710,
"tokens_trained": 5.602815936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4879432624113475,
"grad_norm": 1.2100872993469238,
"loss": 1.199,
"loss_ce": 1.1427383422851562,
"loss_region": 0.06006227061152458,
"loss_total": 1.2028006315231323,
"lr": 0.001175144738560149,
"router/selected_tokens_s0": 399.0,
"router/selected_tokens_s1": 12.875,
"step": 1720,
"tokens_trained": 5.635581376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4907801418439716,
"grad_norm": 2.063210964202881,
"loss": 1.1993,
"loss_ce": 1.1663732528686523,
"loss_region": 0.06088735908269882,
"loss_total": 1.2272605895996094,
"lr": 0.001174737846576298,
"router/selected_tokens_s0": 430.4375,
"router/selected_tokens_s1": 14.3125,
"step": 1730,
"tokens_trained": 5.668346816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.49361702127659574,
"grad_norm": 2.0260696411132812,
"loss": 1.2099,
"loss_ce": 1.1854848861694336,
"loss_region": 0.06261169165372849,
"loss_total": 1.2480965852737427,
"lr": 0.0011743309545924469,
"router/selected_tokens_s0": 341.5,
"router/selected_tokens_s1": 13.1875,
"step": 1740,
"tokens_trained": 5.701112256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.49645390070921985,
"grad_norm": 1.5324933528900146,
"loss": 1.2132,
"loss_ce": 1.183475136756897,
"loss_region": 0.06018225848674774,
"loss_total": 1.2436573505401611,
"lr": 0.0011739240626085956,
"router/selected_tokens_s0": 372.25,
"router/selected_tokens_s1": 12.1875,
"step": 1750,
"tokens_trained": 5.733877696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.49929078014184397,
"grad_norm": 2.0786314010620117,
"loss": 1.206,
"loss_ce": 1.1014961004257202,
"loss_region": 0.059073276817798615,
"loss_total": 1.160569429397583,
"lr": 0.0011735171706247446,
"router/selected_tokens_s0": 516.875,
"router/selected_tokens_s1": 14.125,
"step": 1760,
"tokens_trained": 5.766643136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.502127659574468,
"grad_norm": 1.221889615058899,
"loss": 1.2006,
"loss_ce": 1.1406219005584717,
"loss_region": 0.05831628665328026,
"loss_total": 1.1989381313323975,
"lr": 0.0011731102786408936,
"router/selected_tokens_s0": 365.0625,
"router/selected_tokens_s1": 10.125,
"step": 1770,
"tokens_trained": 5.799407776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5049645390070922,
"grad_norm": 1.8206592798233032,
"loss": 1.2039,
"loss_ce": 1.197525143623352,
"loss_region": 0.06177800893783569,
"loss_total": 1.259303092956543,
"lr": 0.0011727033866570427,
"router/selected_tokens_s0": 393.5625,
"router/selected_tokens_s1": 14.0,
"step": 1780,
"tokens_trained": 5.832173216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5078014184397163,
"grad_norm": 1.2375364303588867,
"loss": 1.1982,
"loss_ce": 1.15640127658844,
"loss_region": 0.057916007936000824,
"loss_total": 1.2143173217773438,
"lr": 0.0011722964946731917,
"router/selected_tokens_s0": 469.875,
"router/selected_tokens_s1": 12.375,
"step": 1790,
"tokens_trained": 5.864938656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5106382978723404,
"grad_norm": 1.060533046722412,
"loss": 1.1963,
"loss_ce": 1.1505051851272583,
"loss_region": 0.05862096697092056,
"loss_total": 1.2091261148452759,
"lr": 0.0011718896026893407,
"router/selected_tokens_s0": 431.5625,
"router/selected_tokens_s1": 12.375,
"step": 1800,
"tokens_trained": 5.897704096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5134751773049645,
"grad_norm": 0.39916256070137024,
"loss": 1.194,
"loss_ce": 1.19837486743927,
"loss_region": 0.06013888120651245,
"loss_total": 1.2585136890411377,
"lr": 0.0011714827107054896,
"router/selected_tokens_s0": 451.6875,
"router/selected_tokens_s1": 14.25,
"step": 1810,
"tokens_trained": 5.930469536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5163120567375886,
"grad_norm": 2.187572479248047,
"loss": 1.1932,
"loss_ce": 1.1421654224395752,
"loss_region": 0.057629093527793884,
"loss_total": 1.1997945308685303,
"lr": 0.0011710758187216386,
"router/selected_tokens_s0": 468.0,
"router/selected_tokens_s1": 12.0,
"step": 1820,
"tokens_trained": 5.963234976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5191489361702127,
"grad_norm": 1.2308872938156128,
"loss": 1.1995,
"loss_ce": 1.0662407875061035,
"loss_region": 0.05716879665851593,
"loss_total": 1.123409628868103,
"lr": 0.0011706689267377876,
"router/selected_tokens_s0": 509.75,
"router/selected_tokens_s1": 12.25,
"step": 1830,
"tokens_trained": 5.996000416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5219858156028369,
"grad_norm": 1.3613312244415283,
"loss": 1.1964,
"loss_ce": 1.105545163154602,
"loss_region": 0.057579901069402695,
"loss_total": 1.1631250381469727,
"lr": 0.0011702620347539365,
"router/selected_tokens_s0": 426.125,
"router/selected_tokens_s1": 11.4375,
"step": 1840,
"tokens_trained": 6.02876568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.524822695035461,
"grad_norm": 1.1689107418060303,
"loss": 1.195,
"loss_ce": 1.1149792671203613,
"loss_region": 0.05797363072633743,
"loss_total": 1.1729528903961182,
"lr": 0.0011698551427700855,
"router/selected_tokens_s0": 453.5,
"router/selected_tokens_s1": 12.0,
"step": 1850,
"tokens_trained": 6.06153112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5276595744680851,
"grad_norm": 1.1174789667129517,
"loss": 1.2006,
"loss_ce": 1.137022614479065,
"loss_region": 0.056159064173698425,
"loss_total": 1.1931816339492798,
"lr": 0.0011694482507862345,
"router/selected_tokens_s0": 419.625,
"router/selected_tokens_s1": 10.0,
"step": 1860,
"tokens_trained": 6.09429256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5304964539007092,
"grad_norm": 1.199244737625122,
"loss": 1.1887,
"loss_ce": 1.1424124240875244,
"loss_region": 0.058031920343637466,
"loss_total": 1.2004443407058716,
"lr": 0.0011690413588023834,
"router/selected_tokens_s0": 445.5625,
"router/selected_tokens_s1": 12.0,
"step": 1870,
"tokens_trained": 6.127058
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5333333333333333,
"grad_norm": 1.2622954845428467,
"loss": 1.1974,
"loss_ce": 1.158575177192688,
"loss_region": 0.059437863528728485,
"loss_total": 1.218013048171997,
"lr": 0.0011686344668185324,
"router/selected_tokens_s0": 399.75,
"router/selected_tokens_s1": 12.3125,
"step": 1880,
"tokens_trained": 6.15982344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5361702127659574,
"grad_norm": 1.0283706188201904,
"loss": 1.1981,
"loss_ce": 1.137675166130066,
"loss_region": 0.0630335733294487,
"loss_total": 1.2007087469100952,
"lr": 0.0011682275748346814,
"router/selected_tokens_s0": 346.75,
"router/selected_tokens_s1": 13.625,
"step": 1890,
"tokens_trained": 6.19258888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5390070921985816,
"grad_norm": 1.3320529460906982,
"loss": 1.1866,
"loss_ce": 1.1702394485473633,
"loss_region": 0.057980410754680634,
"loss_total": 1.2282198667526245,
"lr": 0.0011678206828508303,
"router/selected_tokens_s0": 374.8125,
"router/selected_tokens_s1": 10.1875,
"step": 1900,
"tokens_trained": 6.22535432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5418439716312057,
"grad_norm": 1.0204395055770874,
"loss": 1.1974,
"loss_ce": 1.1290398836135864,
"loss_region": 0.06040707230567932,
"loss_total": 1.1894469261169434,
"lr": 0.0011674137908669793,
"router/selected_tokens_s0": 506.0625,
"router/selected_tokens_s1": 15.625,
"step": 1910,
"tokens_trained": 6.25811976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5446808510638298,
"grad_norm": 1.0836961269378662,
"loss": 1.1942,
"loss_ce": 1.1287145614624023,
"loss_region": 0.061726104468107224,
"loss_total": 1.1904406547546387,
"lr": 0.0011670068988831283,
"router/selected_tokens_s0": 471.25,
"router/selected_tokens_s1": 16.25,
"step": 1920,
"tokens_trained": 6.2908852
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5475177304964539,
"grad_norm": 1.853095293045044,
"loss": 1.1915,
"loss_ce": 1.1728310585021973,
"loss_region": 0.06108897551894188,
"loss_total": 1.2339199781417847,
"lr": 0.0011666000068992772,
"router/selected_tokens_s0": 377.0625,
"router/selected_tokens_s1": 13.1875,
"step": 1930,
"tokens_trained": 6.32365064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.550354609929078,
"grad_norm": 0.9053633213043213,
"loss": 1.1988,
"loss_ce": 1.1357173919677734,
"loss_region": 0.058883197605609894,
"loss_total": 1.1946005821228027,
"lr": 0.0011661931149154262,
"router/selected_tokens_s0": 392.9375,
"router/selected_tokens_s1": 11.875,
"step": 1940,
"tokens_trained": 6.35641608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5531914893617021,
"grad_norm": 0.5790743827819824,
"loss": 1.193,
"loss_ce": 1.1007791757583618,
"loss_region": 0.06010182946920395,
"loss_total": 1.1608810424804688,
"lr": 0.0011657862229315751,
"router/selected_tokens_s0": 448.8125,
"router/selected_tokens_s1": 13.625,
"step": 1950,
"tokens_trained": 6.38918152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5560283687943263,
"grad_norm": 2.2684543132781982,
"loss": 1.1929,
"loss_ce": 1.06866455078125,
"loss_region": 0.05867019668221474,
"loss_total": 1.127334713935852,
"lr": 0.0011653793309477243,
"router/selected_tokens_s0": 506.125,
"router/selected_tokens_s1": 13.8125,
"step": 1960,
"tokens_trained": 6.42194696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5588652482269504,
"grad_norm": 1.153763771057129,
"loss": 1.1983,
"loss_ce": 1.112860083580017,
"loss_region": 0.05813064053654671,
"loss_total": 1.1709907054901123,
"lr": 0.0011649724389638733,
"router/selected_tokens_s0": 454.9375,
"router/selected_tokens_s1": 12.0625,
"step": 1970,
"tokens_trained": 6.4547124
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5617021276595745,
"grad_norm": 1.0854955911636353,
"loss": 1.1992,
"loss_ce": 1.1787145137786865,
"loss_region": 0.060824230313301086,
"loss_total": 1.2395387887954712,
"lr": 0.0011645655469800223,
"router/selected_tokens_s0": 456.375,
"router/selected_tokens_s1": 14.875,
"step": 1980,
"tokens_trained": 6.48747784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5645390070921986,
"grad_norm": 1.0839793682098389,
"loss": 1.1938,
"loss_ce": 1.1302708387374878,
"loss_region": 0.05648130550980568,
"loss_total": 1.186752200126648,
"lr": 0.0011641586549961712,
"router/selected_tokens_s0": 445.125,
"router/selected_tokens_s1": 10.3125,
"step": 1990,
"tokens_trained": 6.52024328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5673758865248227,
"grad_norm": 1.595931887626648,
"loss": 1.1913,
"loss_ce": 1.1068353652954102,
"loss_region": 0.058468256145715714,
"loss_total": 1.1653035879135132,
"lr": 0.00116375176301232,
"router/selected_tokens_s0": 455.125,
"router/selected_tokens_s1": 12.3125,
"step": 2000,
"tokens_trained": 6.55300872
},
{
"epoch": 0.5673758865248227,
"eval_ppl": 3.1223812712711436,
"eval_runtime": 2.1243,
"step": 2000,
"tokens_trained": 6.55300872
},
{
"epoch": 0.5673758865248227,
"eval_F": 0.0011084850378935854,
"eval_F_cds": 0.0012667325487377595,
"eval_F_dig": 0.0036330963356512227,
"eval_F_exon": 0.0010736467294546147,
"eval_F_intron": 0.001082592948118343,
"eval_F_nig": 0.0010864933547482748,
"eval_F_promoter": 0.0011212178636851747,
"eval_F_utr": 0.00111915242856077,
"eval_G": 0.016599176883909706,
"eval_G_cds": 0.021858506086604976,
"eval_G_dig": 0.02974574734842566,
"eval_G_exon": 0.014798423675948955,
"eval_G_intron": 0.016208956635712073,
"eval_G_nig": 0.017406812648344424,
"eval_G_promoter": 0.016065857011987292,
"eval_G_utr": 0.014424679875774081,
"eval_avg_bp_per_token": 902.1321585903083,
"eval_bp_per_token/cds": 789.4326241134752,
"eval_bp_per_token/dig": 275.247311827957,
"eval_bp_per_token/exon": 931.4050632911392,
"eval_bp_per_token/intron": 923.7082152974505,
"eval_bp_per_token/nig": 920.3921916592724,
"eval_bp_per_token/promoter": 891.887323943662,
"eval_bp_per_token/utr": 893.5333333333333,
"eval_ppl_cds": 3.745216707137465,
"eval_ppl_dig": 1.1877180783796364,
"eval_ppl_exon": 3.3494194089611438,
"eval_ppl_intron": 3.1455625493500388,
"eval_ppl_nig": 3.0053043691065953,
"eval_ppl_promoter": 3.3584421148317247,
"eval_ppl_utr": 3.4473742076146077,
"step": 2000,
"tokens_trained": 6.55300872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5702127659574469,
"grad_norm": 2.117267608642578,
"loss": 1.1965,
"loss_ce": 1.1464393138885498,
"loss_region": 0.059396736323833466,
"loss_total": 1.2058360576629639,
"lr": 0.001163344871028469,
"router/selected_tokens_s0": 464.8125,
"router/selected_tokens_s1": 13.375,
"step": 2010,
"tokens_trained": 6.58577416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.573049645390071,
"grad_norm": 2.818798303604126,
"loss": 1.2032,
"loss_ce": 1.1034953594207764,
"loss_region": 0.05682379752397537,
"loss_total": 1.160319209098816,
"lr": 0.001162937979044618,
"router/selected_tokens_s0": 477.375,
"router/selected_tokens_s1": 10.875,
"step": 2020,
"tokens_trained": 6.6185396
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5758865248226951,
"grad_norm": 2.917182207107544,
"loss": 1.201,
"loss_ce": 1.0508410930633545,
"loss_region": 0.05919254571199417,
"loss_total": 1.110033631324768,
"lr": 0.001162531087060767,
"router/selected_tokens_s0": 583.3125,
"router/selected_tokens_s1": 15.3125,
"step": 2030,
"tokens_trained": 6.65130504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5787234042553191,
"grad_norm": 0.7146549224853516,
"loss": 1.1938,
"loss_ce": 1.1160414218902588,
"loss_region": 0.0593046136200428,
"loss_total": 1.17534601688385,
"lr": 0.001162124195076916,
"router/selected_tokens_s0": 425.0,
"router/selected_tokens_s1": 12.9375,
"step": 2040,
"tokens_trained": 6.68407048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5815602836879432,
"grad_norm": 0.6383615136146545,
"loss": 1.1903,
"loss_ce": 1.1438560485839844,
"loss_region": 0.05890098586678505,
"loss_total": 1.2027570009231567,
"lr": 0.001161717303093065,
"router/selected_tokens_s0": 421.0,
"router/selected_tokens_s1": 12.1875,
"step": 2050,
"tokens_trained": 6.71683512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5843971631205673,
"grad_norm": 0.9087597131729126,
"loss": 1.1919,
"loss_ce": 1.1244920492172241,
"loss_region": 0.060024410486221313,
"loss_total": 1.184516429901123,
"lr": 0.001161310411109214,
"router/selected_tokens_s0": 444.1875,
"router/selected_tokens_s1": 14.25,
"step": 2060,
"tokens_trained": 6.74960056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5872340425531914,
"grad_norm": 0.4662902355194092,
"loss": 1.1897,
"loss_ce": 1.1663501262664795,
"loss_region": 0.06032518297433853,
"loss_total": 1.226675271987915,
"lr": 0.001160903519125363,
"router/selected_tokens_s0": 445.5,
"router/selected_tokens_s1": 14.125,
"step": 2070,
"tokens_trained": 6.782364224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5900709219858156,
"grad_norm": 1.13335382938385,
"loss": 1.1972,
"loss_ce": 1.1606361865997314,
"loss_region": 0.05782872810959816,
"loss_total": 1.218464970588684,
"lr": 0.001160496627141512,
"router/selected_tokens_s0": 456.8125,
"router/selected_tokens_s1": 11.9375,
"step": 2080,
"tokens_trained": 6.815129664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5929078014184397,
"grad_norm": 0.8821171522140503,
"loss": 1.1893,
"loss_ce": 1.2031593322753906,
"loss_region": 0.056816309690475464,
"loss_total": 1.2599756717681885,
"lr": 0.0011600897351576609,
"router/selected_tokens_s0": 408.1875,
"router/selected_tokens_s1": 9.8125,
"step": 2090,
"tokens_trained": 6.847895104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5957446808510638,
"grad_norm": 2.006725549697876,
"loss": 1.1914,
"loss_ce": 1.069053053855896,
"loss_region": 0.06600474566221237,
"loss_total": 1.135057806968689,
"lr": 0.0011596828431738098,
"router/selected_tokens_s0": 493.0625,
"router/selected_tokens_s1": 22.75,
"step": 2100,
"tokens_trained": 6.880660544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5985815602836879,
"grad_norm": 0.902592122554779,
"loss": 1.1893,
"loss_ce": 1.1250122785568237,
"loss_region": 0.061842553317546844,
"loss_total": 1.1868548393249512,
"lr": 0.0011592759511899588,
"router/selected_tokens_s0": 457.9375,
"router/selected_tokens_s1": 16.25,
"step": 2110,
"tokens_trained": 6.913423848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.601418439716312,
"grad_norm": 1.49269700050354,
"loss": 1.1907,
"loss_ce": 1.0372364521026611,
"loss_region": 0.05842522904276848,
"loss_total": 1.0956616401672363,
"lr": 0.0011588690592061078,
"router/selected_tokens_s0": 508.0625,
"router/selected_tokens_s1": 12.625,
"step": 2120,
"tokens_trained": 6.946189128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6042553191489362,
"grad_norm": 0.784643828868866,
"loss": 1.19,
"loss_ce": 1.148450255393982,
"loss_region": 0.05916881933808327,
"loss_total": 1.207619071006775,
"lr": 0.0011584621672222567,
"router/selected_tokens_s0": 464.8125,
"router/selected_tokens_s1": 13.5,
"step": 2130,
"tokens_trained": 6.978954568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6070921985815603,
"grad_norm": 1.5643503665924072,
"loss": 1.1929,
"loss_ce": 1.1538206338882446,
"loss_region": 0.056670140475034714,
"loss_total": 1.2104908227920532,
"lr": 0.0011580552752384057,
"router/selected_tokens_s0": 373.3125,
"router/selected_tokens_s1": 9.25,
"step": 2140,
"tokens_trained": 7.011720008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6099290780141844,
"grad_norm": 1.9936473369598389,
"loss": 1.1945,
"loss_ce": 1.0993125438690186,
"loss_region": 0.062473952770233154,
"loss_total": 1.1617865562438965,
"lr": 0.0011576483832545547,
"router/selected_tokens_s0": 536.8125,
"router/selected_tokens_s1": 19.0625,
"step": 2150,
"tokens_trained": 7.044485448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6127659574468085,
"grad_norm": 1.7021753787994385,
"loss": 1.1961,
"loss_ce": 1.1517091989517212,
"loss_region": 0.05705780163407326,
"loss_total": 1.208767056465149,
"lr": 0.0011572414912707036,
"router/selected_tokens_s0": 389.75,
"router/selected_tokens_s1": 9.875,
"step": 2160,
"tokens_trained": 7.077250888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6156028368794326,
"grad_norm": 0.9088471531867981,
"loss": 1.187,
"loss_ce": 1.1205592155456543,
"loss_region": 0.0625070258975029,
"loss_total": 1.1830662488937378,
"lr": 0.0011568345992868526,
"router/selected_tokens_s0": 414.3125,
"router/selected_tokens_s1": 15.5,
"step": 2170,
"tokens_trained": 7.110016328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6184397163120567,
"grad_norm": 0.7021254301071167,
"loss": 1.1904,
"loss_ce": 1.1545506715774536,
"loss_region": 0.05998982861638069,
"loss_total": 1.2145404815673828,
"lr": 0.0011564277073030016,
"router/selected_tokens_s0": 416.6875,
"router/selected_tokens_s1": 13.0625,
"step": 2180,
"tokens_trained": 7.1427786
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6212765957446809,
"grad_norm": 3.0147488117218018,
"loss": 1.191,
"loss_ce": 1.1359323263168335,
"loss_region": 0.05584647133946419,
"loss_total": 1.1917787790298462,
"lr": 0.0011560208153191505,
"router/selected_tokens_s0": 396.875,
"router/selected_tokens_s1": 8.8125,
"step": 2190,
"tokens_trained": 7.17554404
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.624113475177305,
"grad_norm": 2.2795827388763428,
"loss": 1.2038,
"loss_ce": 1.0853055715560913,
"loss_region": 0.06210076063871384,
"loss_total": 1.1474063396453857,
"lr": 0.0011556139233352995,
"router/selected_tokens_s0": 380.9375,
"router/selected_tokens_s1": 14.25,
"step": 2200,
"tokens_trained": 7.20830948
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6269503546099291,
"grad_norm": 1.8677184581756592,
"loss": 1.2053,
"loss_ce": 1.108307957649231,
"loss_region": 0.057143088430166245,
"loss_total": 1.1654510498046875,
"lr": 0.0011552070313514487,
"router/selected_tokens_s0": 272.5625,
"router/selected_tokens_s1": 7.6875,
"step": 2210,
"tokens_trained": 7.24107492
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6297872340425532,
"grad_norm": 0.9489080309867859,
"loss": 1.1974,
"loss_ce": 1.173215389251709,
"loss_region": 0.05955825746059418,
"loss_total": 1.2327736616134644,
"lr": 0.0011548001393675976,
"router/selected_tokens_s0": 375.0625,
"router/selected_tokens_s1": 11.875,
"step": 2220,
"tokens_trained": 7.27384036
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6326241134751773,
"grad_norm": 0.8159853219985962,
"loss": 1.1931,
"loss_ce": 1.1084233522415161,
"loss_region": 0.05950550734996796,
"loss_total": 1.1679288148880005,
"lr": 0.0011543932473837466,
"router/selected_tokens_s0": 468.75,
"router/selected_tokens_s1": 14.0,
"step": 2230,
"tokens_trained": 7.3066058
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6354609929078014,
"grad_norm": 1.2158466577529907,
"loss": 1.1847,
"loss_ce": 1.1424072980880737,
"loss_region": 0.061019301414489746,
"loss_total": 1.2034265995025635,
"lr": 0.0011539863553998956,
"router/selected_tokens_s0": 405.5,
"router/selected_tokens_s1": 13.75,
"step": 2240,
"tokens_trained": 7.33937124
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6382978723404256,
"grad_norm": 0.38309988379478455,
"loss": 1.1872,
"loss_ce": 1.0867244005203247,
"loss_region": 0.06173141673207283,
"loss_total": 1.1484558582305908,
"lr": 0.0011535794634160443,
"router/selected_tokens_s0": 432.4375,
"router/selected_tokens_s1": 14.9375,
"step": 2250,
"tokens_trained": 7.37213668
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6411347517730497,
"grad_norm": 1.231326937675476,
"loss": 1.1891,
"loss_ce": 1.1232706308364868,
"loss_region": 0.061620455235242844,
"loss_total": 1.1848911046981812,
"lr": 0.0011531725714321933,
"router/selected_tokens_s0": 425.25,
"router/selected_tokens_s1": 14.625,
"step": 2260,
"tokens_trained": 7.40490212
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6439716312056738,
"grad_norm": 0.6881319284439087,
"loss": 1.1885,
"loss_ce": 1.0646520853042603,
"loss_region": 0.061182402074337006,
"loss_total": 1.1258344650268555,
"lr": 0.0011527656794483422,
"router/selected_tokens_s0": 436.5,
"router/selected_tokens_s1": 14.375,
"step": 2270,
"tokens_trained": 7.43766756
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6468085106382979,
"grad_norm": 0.5453615784645081,
"loss": 1.1857,
"loss_ce": 1.183090329170227,
"loss_region": 0.06025899201631546,
"loss_total": 1.243349313735962,
"lr": 0.0011523587874644914,
"router/selected_tokens_s0": 389.5,
"router/selected_tokens_s1": 12.6875,
"step": 2280,
"tokens_trained": 7.470433
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.649645390070922,
"grad_norm": 0.4796663224697113,
"loss": 1.1928,
"loss_ce": 1.1268420219421387,
"loss_region": 0.058640334755182266,
"loss_total": 1.185482382774353,
"lr": 0.0011519518954806404,
"router/selected_tokens_s0": 434.125,
"router/selected_tokens_s1": 12.25,
"step": 2290,
"tokens_trained": 7.503197136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6524822695035462,
"grad_norm": 1.9199693202972412,
"loss": 1.1889,
"loss_ce": 1.1117569208145142,
"loss_region": 0.061376579105854034,
"loss_total": 1.1731334924697876,
"lr": 0.0011515450034967894,
"router/selected_tokens_s0": 396.0,
"router/selected_tokens_s1": 14.125,
"step": 2300,
"tokens_trained": 7.535962576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6553191489361702,
"grad_norm": 1.2376593351364136,
"loss": 1.1913,
"loss_ce": 1.1556870937347412,
"loss_region": 0.0595984049141407,
"loss_total": 1.2152855396270752,
"lr": 0.0011511381115129383,
"router/selected_tokens_s0": 356.375,
"router/selected_tokens_s1": 11.1875,
"step": 2310,
"tokens_trained": 7.568726416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6581560283687943,
"grad_norm": 0.6415485739707947,
"loss": 1.1884,
"loss_ce": 1.15511155128479,
"loss_region": 0.06067604944109917,
"loss_total": 1.215787649154663,
"lr": 0.0011507312195290873,
"router/selected_tokens_s0": 492.75,
"router/selected_tokens_s1": 15.625,
"step": 2320,
"tokens_trained": 7.601491056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6609929078014184,
"grad_norm": 0.5361623764038086,
"loss": 1.1881,
"loss_ce": 1.1369774341583252,
"loss_region": 0.06078004837036133,
"loss_total": 1.1977574825286865,
"lr": 0.0011503243275452363,
"router/selected_tokens_s0": 371.25,
"router/selected_tokens_s1": 12.6875,
"step": 2330,
"tokens_trained": 7.634256496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6638297872340425,
"grad_norm": 1.0889244079589844,
"loss": 1.1856,
"loss_ce": 1.1064252853393555,
"loss_region": 0.05778004229068756,
"loss_total": 1.1642053127288818,
"lr": 0.0011499174355613852,
"router/selected_tokens_s0": 391.8125,
"router/selected_tokens_s1": 10.3125,
"step": 2340,
"tokens_trained": 7.667021936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6666666666666666,
"grad_norm": 1.2836039066314697,
"loss": 1.1873,
"loss_ce": 1.1070295572280884,
"loss_region": 0.05989352613687515,
"loss_total": 1.1669230461120605,
"lr": 0.0011495105435775342,
"router/selected_tokens_s0": 372.5625,
"router/selected_tokens_s1": 11.875,
"step": 2350,
"tokens_trained": 7.699787376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6695035460992907,
"grad_norm": 0.9303162097930908,
"loss": 1.1863,
"loss_ce": 1.1171040534973145,
"loss_region": 0.0614146888256073,
"loss_total": 1.1785187721252441,
"lr": 0.0011491036515936831,
"router/selected_tokens_s0": 455.9375,
"router/selected_tokens_s1": 15.5625,
"step": 2360,
"tokens_trained": 7.732552016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6723404255319149,
"grad_norm": 1.983481764793396,
"loss": 1.1806,
"loss_ce": 1.1478883028030396,
"loss_region": 0.05946619436144829,
"loss_total": 1.2073545455932617,
"lr": 0.0011486967596098321,
"router/selected_tokens_s0": 448.5,
"router/selected_tokens_s1": 13.375,
"step": 2370,
"tokens_trained": 7.765317456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.675177304964539,
"grad_norm": 1.7260289192199707,
"loss": 1.1894,
"loss_ce": 1.1961910724639893,
"loss_region": 0.05941138043999672,
"loss_total": 1.255602478981018,
"lr": 0.001148289867625981,
"router/selected_tokens_s0": 517.4375,
"router/selected_tokens_s1": 14.9375,
"step": 2380,
"tokens_trained": 7.798082896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6780141843971631,
"grad_norm": 1.469610571861267,
"loss": 1.1915,
"loss_ce": 1.075291395187378,
"loss_region": 0.058670733124017715,
"loss_total": 1.1339621543884277,
"lr": 0.00114788297564213,
"router/selected_tokens_s0": 471.375,
"router/selected_tokens_s1": 12.9375,
"step": 2390,
"tokens_trained": 7.830848336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6808510638297872,
"grad_norm": 0.5615185499191284,
"loss": 1.1925,
"loss_ce": 1.0627862215042114,
"loss_region": 0.05851579084992409,
"loss_total": 1.1213020086288452,
"lr": 0.001147476083658279,
"router/selected_tokens_s0": 436.0625,
"router/selected_tokens_s1": 12.125,
"step": 2400,
"tokens_trained": 7.863613776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6836879432624113,
"grad_norm": 0.3367394506931305,
"loss": 1.1881,
"loss_ce": 1.120520830154419,
"loss_region": 0.05808383971452713,
"loss_total": 1.1786047220230103,
"lr": 0.001147069191674428,
"router/selected_tokens_s0": 428.5,
"router/selected_tokens_s1": 11.4375,
"step": 2410,
"tokens_trained": 7.896379216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6865248226950355,
"grad_norm": 1.269070029258728,
"loss": 1.1858,
"loss_ce": 1.1046808958053589,
"loss_region": 0.06424061954021454,
"loss_total": 1.1689214706420898,
"lr": 0.001146662299690577,
"router/selected_tokens_s0": 459.5625,
"router/selected_tokens_s1": 19.0625,
"step": 2420,
"tokens_trained": 7.929144656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6893617021276596,
"grad_norm": 0.5868048667907715,
"loss": 1.1849,
"loss_ce": 1.170312762260437,
"loss_region": 0.05978027358651161,
"loss_total": 1.230093002319336,
"lr": 0.001146255407706726,
"router/selected_tokens_s0": 452.9375,
"router/selected_tokens_s1": 13.9375,
"step": 2430,
"tokens_trained": 7.961910096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6921985815602837,
"grad_norm": 1.2158846855163574,
"loss": 1.1891,
"loss_ce": 1.1489698886871338,
"loss_region": 0.05716322362422943,
"loss_total": 1.2061331272125244,
"lr": 0.0011458485157228749,
"router/selected_tokens_s0": 397.5,
"router/selected_tokens_s1": 9.9375,
"step": 2440,
"tokens_trained": 7.994675536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6950354609929078,
"grad_norm": 0.8825588822364807,
"loss": 1.1826,
"loss_ce": 1.0938084125518799,
"loss_region": 0.0573706328868866,
"loss_total": 1.1511790752410889,
"lr": 0.0011454416237390238,
"router/selected_tokens_s0": 475.25,
"router/selected_tokens_s1": 11.5625,
"step": 2450,
"tokens_trained": 8.027440976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6978723404255319,
"grad_norm": 1.0089329481124878,
"loss": 1.1837,
"loss_ce": 1.1076617240905762,
"loss_region": 0.0649326741695404,
"loss_total": 1.172594428062439,
"lr": 0.001145034731755173,
"router/selected_tokens_s0": 442.0,
"router/selected_tokens_s1": 19.3125,
"step": 2460,
"tokens_trained": 8.060206416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.700709219858156,
"grad_norm": 1.4214838743209839,
"loss": 1.1831,
"loss_ce": 1.1698490381240845,
"loss_region": 0.06358074396848679,
"loss_total": 1.2334297895431519,
"lr": 0.001144627839771322,
"router/selected_tokens_s0": 476.4375,
"router/selected_tokens_s1": 18.4375,
"step": 2470,
"tokens_trained": 8.092971856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7035460992907802,
"grad_norm": 0.659936249256134,
"loss": 1.1903,
"loss_ce": 1.1888149976730347,
"loss_region": 0.059051670134067535,
"loss_total": 1.2478666305541992,
"lr": 0.001144220947787471,
"router/selected_tokens_s0": 398.9375,
"router/selected_tokens_s1": 11.75,
"step": 2480,
"tokens_trained": 8.125737296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7063829787234043,
"grad_norm": 0.5858396887779236,
"loss": 1.1837,
"loss_ce": 1.1628644466400146,
"loss_region": 0.05618392676115036,
"loss_total": 1.2190483808517456,
"lr": 0.00114381405580362,
"router/selected_tokens_s0": 418.3125,
"router/selected_tokens_s1": 9.4375,
"step": 2490,
"tokens_trained": 8.158502728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7092198581560284,
"grad_norm": 0.7732462882995605,
"loss": 1.1838,
"loss_ce": 1.1414825916290283,
"loss_region": 0.05881210044026375,
"loss_total": 1.2002947330474854,
"lr": 0.0011434071638197687,
"router/selected_tokens_s0": 458.6875,
"router/selected_tokens_s1": 12.9375,
"step": 2500,
"tokens_trained": 8.191268168
},
{
"epoch": 0.7092198581560284,
"eval_ppl": 3.088251523031909,
"eval_runtime": 2.0713,
"step": 2500,
"tokens_trained": 8.191268168
},
{
"epoch": 0.7092198581560284,
"eval_F": 0.0013405429092626122,
"eval_F_cds": 0.0019225586200700745,
"eval_F_dig": 0.001992343151808735,
"eval_F_exon": 0.0010600562645248094,
"eval_F_intron": 0.0012945879553100724,
"eval_F_nig": 0.0013708904618030583,
"eval_F_promoter": 0.0013752026614448445,
"eval_F_utr": 0.0013536415088306456,
"eval_G": 0.016355751570530732,
"eval_G_cds": 0.017110347088087324,
"eval_G_dig": 0.024907799193296352,
"eval_G_exon": 0.01501345562203558,
"eval_G_intron": 0.01610771212822286,
"eval_G_nig": 0.017513512402485533,
"eval_G_promoter": 0.01555233561146511,
"eval_G_utr": 0.014783220840749938,
"eval_avg_bp_per_token": 745.9664238200824,
"eval_bp_per_token/cds": 520.1401869158879,
"eval_bp_per_token/dig": 501.921568627451,
"eval_bp_per_token/exon": 943.3461538461538,
"eval_bp_per_token/intron": 772.4465501924785,
"eval_bp_per_token/nig": 729.4528832630099,
"eval_bp_per_token/promoter": 727.1655502392344,
"eval_bp_per_token/utr": 738.7480314960629,
"eval_ppl_cds": 3.741853201441482,
"eval_ppl_dig": 1.134775489212344,
"eval_ppl_exon": 3.3239018881446203,
"eval_ppl_intron": 3.1123804579035923,
"eval_ppl_nig": 2.962110202365204,
"eval_ppl_promoter": 3.3370101406004844,
"eval_ppl_utr": 3.4205064986888787,
"step": 2500,
"tokens_trained": 8.191268168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7120567375886525,
"grad_norm": 0.7734953165054321,
"loss": 1.1844,
"loss_ce": 1.0916640758514404,
"loss_region": 0.06200540438294411,
"loss_total": 1.1536694765090942,
"lr": 0.0011430002718359176,
"router/selected_tokens_s0": 502.0,
"router/selected_tokens_s1": 17.75,
"step": 2510,
"tokens_trained": 8.224033608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7148936170212766,
"grad_norm": 1.9390835762023926,
"loss": 1.1836,
"loss_ce": 1.1503256559371948,
"loss_region": 0.05846535786986351,
"loss_total": 1.2087910175323486,
"lr": 0.0011425933798520666,
"router/selected_tokens_s0": 334.75,
"router/selected_tokens_s1": 9.4375,
"step": 2520,
"tokens_trained": 8.25679904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7177304964539007,
"grad_norm": 1.4347184896469116,
"loss": 1.1931,
"loss_ce": 1.1123408079147339,
"loss_region": 0.060282111167907715,
"loss_total": 1.1726229190826416,
"lr": 0.0011421864878682158,
"router/selected_tokens_s0": 568.0,
"router/selected_tokens_s1": 17.1875,
"step": 2530,
"tokens_trained": 8.28956448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7205673758865249,
"grad_norm": 0.858637273311615,
"loss": 1.1863,
"loss_ce": 1.1312373876571655,
"loss_region": 0.0616295225918293,
"loss_total": 1.1928669214248657,
"lr": 0.0011417795958843647,
"router/selected_tokens_s0": 501.75,
"router/selected_tokens_s1": 17.1875,
"step": 2540,
"tokens_trained": 8.322329544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.723404255319149,
"grad_norm": 1.4742088317871094,
"loss": 1.1857,
"loss_ce": 1.1528387069702148,
"loss_region": 0.05786595121026039,
"loss_total": 1.2107046842575073,
"lr": 0.0011413727039005137,
"router/selected_tokens_s0": 439.6875,
"router/selected_tokens_s1": 11.8125,
"step": 2550,
"tokens_trained": 8.355094984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7262411347517731,
"grad_norm": 0.3498552739620209,
"loss": 1.1811,
"loss_ce": 1.0615895986557007,
"loss_region": 0.06257026642560959,
"loss_total": 1.124159812927246,
"lr": 0.0011409658119166627,
"router/selected_tokens_s0": 490.8125,
"router/selected_tokens_s1": 17.8125,
"step": 2560,
"tokens_trained": 8.3878584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7290780141843972,
"grad_norm": 1.282585859298706,
"loss": 1.1838,
"loss_ce": 1.071786642074585,
"loss_region": 0.05918266996741295,
"loss_total": 1.1309692859649658,
"lr": 0.0011405589199328116,
"router/selected_tokens_s0": 412.4375,
"router/selected_tokens_s1": 12.25,
"step": 2570,
"tokens_trained": 8.42062384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7319148936170212,
"grad_norm": 0.8695186972618103,
"loss": 1.1852,
"loss_ce": 1.1701353788375854,
"loss_region": 0.05956278741359711,
"loss_total": 1.2296981811523438,
"lr": 0.0011401520279489606,
"router/selected_tokens_s0": 362.6875,
"router/selected_tokens_s1": 11.5,
"step": 2580,
"tokens_trained": 8.453389256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7347517730496453,
"grad_norm": 1.7512108087539673,
"loss": 1.1873,
"loss_ce": 1.0919519662857056,
"loss_region": 0.06304050981998444,
"loss_total": 1.1549924612045288,
"lr": 0.0011397451359651096,
"router/selected_tokens_s0": 493.125,
"router/selected_tokens_s1": 18.8125,
"step": 2590,
"tokens_trained": 8.486154696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7375886524822695,
"grad_norm": 1.4450966119766235,
"loss": 1.1868,
"loss_ce": 1.1768208742141724,
"loss_region": 0.06446579843759537,
"loss_total": 1.2412866353988647,
"lr": 0.0011393382439812585,
"router/selected_tokens_s0": 372.875,
"router/selected_tokens_s1": 16.125,
"step": 2600,
"tokens_trained": 8.518920136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7404255319148936,
"grad_norm": 0.3035755753517151,
"loss": 1.1798,
"loss_ce": 1.1247832775115967,
"loss_region": 0.05857830122113228,
"loss_total": 1.183361530303955,
"lr": 0.0011389313519974075,
"router/selected_tokens_s0": 464.9375,
"router/selected_tokens_s1": 12.9375,
"step": 2610,
"tokens_trained": 8.551685576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7432624113475177,
"grad_norm": 1.2541152238845825,
"loss": 1.1852,
"loss_ce": 1.1951887607574463,
"loss_region": 0.06222536042332649,
"loss_total": 1.2574141025543213,
"lr": 0.0011385244600135565,
"router/selected_tokens_s0": 338.875,
"router/selected_tokens_s1": 12.875,
"step": 2620,
"tokens_trained": 8.584451016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7460992907801418,
"grad_norm": 0.5121674537658691,
"loss": 1.1806,
"loss_ce": 1.0926810503005981,
"loss_region": 0.05847754701972008,
"loss_total": 1.1511585712432861,
"lr": 0.0011381175680297054,
"router/selected_tokens_s0": 476.875,
"router/selected_tokens_s1": 12.875,
"step": 2630,
"tokens_trained": 8.617213968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7489361702127659,
"grad_norm": 1.1699979305267334,
"loss": 1.1829,
"loss_ce": 1.0987080335617065,
"loss_region": 0.06216296926140785,
"loss_total": 1.1608710289001465,
"lr": 0.0011377106760458544,
"router/selected_tokens_s0": 442.9375,
"router/selected_tokens_s1": 16.3125,
"step": 2640,
"tokens_trained": 8.649979408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.75177304964539,
"grad_norm": 0.7619943618774414,
"loss": 1.1842,
"loss_ce": 1.1102006435394287,
"loss_region": 0.05994445085525513,
"loss_total": 1.170145034790039,
"lr": 0.0011373037840620034,
"router/selected_tokens_s0": 414.1875,
"router/selected_tokens_s1": 12.9375,
"step": 2650,
"tokens_trained": 8.682744848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7546099290780142,
"grad_norm": 0.7444802522659302,
"loss": 1.1803,
"loss_ce": 1.1419343948364258,
"loss_region": 0.06051338091492653,
"loss_total": 1.202447772026062,
"lr": 0.0011368968920781523,
"router/selected_tokens_s0": 428.5625,
"router/selected_tokens_s1": 13.9375,
"step": 2660,
"tokens_trained": 8.715510288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7574468085106383,
"grad_norm": 1.5269882678985596,
"loss": 1.1867,
"loss_ce": 1.1233625411987305,
"loss_region": 0.0623200386762619,
"loss_total": 1.1856825351715088,
"lr": 0.0011364900000943013,
"router/selected_tokens_s0": 402.25,
"router/selected_tokens_s1": 15.0625,
"step": 2670,
"tokens_trained": 8.748275728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7602836879432624,
"grad_norm": 0.7747791409492493,
"loss": 1.1861,
"loss_ce": 1.15846586227417,
"loss_region": 0.05765581130981445,
"loss_total": 1.2161216735839844,
"lr": 0.0011360831081104503,
"router/selected_tokens_s0": 354.5,
"router/selected_tokens_s1": 9.1875,
"step": 2680,
"tokens_trained": 8.781041168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7631205673758865,
"grad_norm": 1.0417836904525757,
"loss": 1.1889,
"loss_ce": 1.1638587713241577,
"loss_region": 0.057558320462703705,
"loss_total": 1.2214170694351196,
"lr": 0.0011356762161265992,
"router/selected_tokens_s0": 439.75,
"router/selected_tokens_s1": 11.0,
"step": 2690,
"tokens_trained": 8.813806448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7659574468085106,
"grad_norm": 1.2498610019683838,
"loss": 1.1761,
"loss_ce": 1.1044461727142334,
"loss_region": 0.05698206275701523,
"loss_total": 1.1614282131195068,
"lr": 0.0011352693241427482,
"router/selected_tokens_s0": 423.875,
"router/selected_tokens_s1": 10.5,
"step": 2700,
"tokens_trained": 8.846571888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7687943262411348,
"grad_norm": 0.5136662125587463,
"loss": 1.1832,
"loss_ce": 1.072133183479309,
"loss_region": 0.05974389612674713,
"loss_total": 1.131877064704895,
"lr": 0.0011348624321588974,
"router/selected_tokens_s0": 457.4375,
"router/selected_tokens_s1": 13.875,
"step": 2710,
"tokens_trained": 8.879337328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7716312056737589,
"grad_norm": 1.5680474042892456,
"loss": 1.1811,
"loss_ce": 1.1259905099868774,
"loss_region": 0.06005231291055679,
"loss_total": 1.1860427856445312,
"lr": 0.0011344555401750463,
"router/selected_tokens_s0": 474.875,
"router/selected_tokens_s1": 14.6875,
"step": 2720,
"tokens_trained": 8.912102768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.774468085106383,
"grad_norm": 1.0861411094665527,
"loss": 1.1884,
"loss_ce": 1.1043437719345093,
"loss_region": 0.06049416959285736,
"loss_total": 1.1648379564285278,
"lr": 0.0011340486481911953,
"router/selected_tokens_s0": 508.75,
"router/selected_tokens_s1": 15.8125,
"step": 2730,
"tokens_trained": 8.944868208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7773049645390071,
"grad_norm": 0.502753496170044,
"loss": 1.1859,
"loss_ce": 1.155367136001587,
"loss_region": 0.06546095013618469,
"loss_total": 1.2208280563354492,
"lr": 0.001133641756207344,
"router/selected_tokens_s0": 431.5625,
"router/selected_tokens_s1": 19.0625,
"step": 2740,
"tokens_trained": 8.977633592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7801418439716312,
"grad_norm": 0.863655149936676,
"loss": 1.1828,
"loss_ce": 1.136635661125183,
"loss_region": 0.0639290139079094,
"loss_total": 1.2005646228790283,
"lr": 0.001133234864223493,
"router/selected_tokens_s0": 403.4375,
"router/selected_tokens_s1": 16.4375,
"step": 2750,
"tokens_trained": 9.010399032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7829787234042553,
"grad_norm": 1.6406680345535278,
"loss": 1.1787,
"loss_ce": 1.0808862447738647,
"loss_region": 0.05786607041954994,
"loss_total": 1.1387523412704468,
"lr": 0.001132827972239642,
"router/selected_tokens_s0": 499.5625,
"router/selected_tokens_s1": 12.75,
"step": 2760,
"tokens_trained": 9.043164472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7858156028368795,
"grad_norm": 1.7592346668243408,
"loss": 1.1895,
"loss_ce": 1.1217154264450073,
"loss_region": 0.057540249079465866,
"loss_total": 1.179255723953247,
"lr": 0.001132421080255791,
"router/selected_tokens_s0": 420.25,
"router/selected_tokens_s1": 10.5625,
"step": 2770,
"tokens_trained": 9.075929912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7886524822695036,
"grad_norm": 2.4455196857452393,
"loss": 1.1903,
"loss_ce": 1.0879745483398438,
"loss_region": 0.0601075105369091,
"loss_total": 1.1480820178985596,
"lr": 0.0011320141882719401,
"router/selected_tokens_s0": 386.9375,
"router/selected_tokens_s1": 11.625,
"step": 2780,
"tokens_trained": 9.108695352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7914893617021277,
"grad_norm": 0.37144532799720764,
"loss": 1.1867,
"loss_ce": 1.0730124711990356,
"loss_region": 0.05783551186323166,
"loss_total": 1.1308479309082031,
"lr": 0.001131607296288089,
"router/selected_tokens_s0": 433.375,
"router/selected_tokens_s1": 11.375,
"step": 2790,
"tokens_trained": 9.141456136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7943262411347518,
"grad_norm": 0.5975992679595947,
"loss": 1.1831,
"loss_ce": 1.1580114364624023,
"loss_region": 0.05659972503781319,
"loss_total": 1.2146111726760864,
"lr": 0.001131200404304238,
"router/selected_tokens_s0": 395.875,
"router/selected_tokens_s1": 9.25,
"step": 2800,
"tokens_trained": 9.174221576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7971631205673759,
"grad_norm": 0.7188255786895752,
"loss": 1.1828,
"loss_ce": 1.1139250993728638,
"loss_region": 0.059663042426109314,
"loss_total": 1.1735881567001343,
"lr": 0.001130793512320387,
"router/selected_tokens_s0": 467.5,
"router/selected_tokens_s1": 14.25,
"step": 2810,
"tokens_trained": 9.206987016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8,
"grad_norm": 0.35444915294647217,
"loss": 1.1823,
"loss_ce": 1.0711995363235474,
"loss_region": 0.0630360022187233,
"loss_total": 1.1342355012893677,
"lr": 0.001130386620336536,
"router/selected_tokens_s0": 442.3125,
"router/selected_tokens_s1": 16.75,
"step": 2820,
"tokens_trained": 9.239752456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8028368794326242,
"grad_norm": 1.3028233051300049,
"loss": 1.1818,
"loss_ce": 1.1242021322250366,
"loss_region": 0.06099163740873337,
"loss_total": 1.1851937770843506,
"lr": 0.001129979728352685,
"router/selected_tokens_s0": 402.5625,
"router/selected_tokens_s1": 13.875,
"step": 2830,
"tokens_trained": 9.272517896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8056737588652483,
"grad_norm": 1.156672716140747,
"loss": 1.1866,
"loss_ce": 1.125891923904419,
"loss_region": 0.05897829309105873,
"loss_total": 1.1848702430725098,
"lr": 0.001129572836368834,
"router/selected_tokens_s0": 472.3125,
"router/selected_tokens_s1": 13.4375,
"step": 2840,
"tokens_trained": 9.305283336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8085106382978723,
"grad_norm": 0.48895296454429626,
"loss": 1.1846,
"loss_ce": 1.1702710390090942,
"loss_region": 0.061904530972242355,
"loss_total": 1.232175588607788,
"lr": 0.0011291659443849829,
"router/selected_tokens_s0": 442.25,
"router/selected_tokens_s1": 15.75,
"step": 2850,
"tokens_trained": 9.338048776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8113475177304964,
"grad_norm": 0.7052562832832336,
"loss": 1.1794,
"loss_ce": 1.1244450807571411,
"loss_region": 0.06674501299858093,
"loss_total": 1.1911901235580444,
"lr": 0.0011287590524011318,
"router/selected_tokens_s0": 462.25,
"router/selected_tokens_s1": 21.8125,
"step": 2860,
"tokens_trained": 9.370814216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8141843971631205,
"grad_norm": 0.4975396394729614,
"loss": 1.1789,
"loss_ce": 1.1839637756347656,
"loss_region": 0.059558697044849396,
"loss_total": 1.2435225248336792,
"lr": 0.0011283521604172808,
"router/selected_tokens_s0": 375.125,
"router/selected_tokens_s1": 11.8125,
"step": 2870,
"tokens_trained": 9.403579656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8170212765957446,
"grad_norm": 1.2806240320205688,
"loss": 1.1816,
"loss_ce": 1.0861955881118774,
"loss_region": 0.059288810938596725,
"loss_total": 1.145484447479248,
"lr": 0.0011279452684334298,
"router/selected_tokens_s0": 510.375,
"router/selected_tokens_s1": 14.625,
"step": 2880,
"tokens_trained": 9.436345096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8198581560283688,
"grad_norm": 0.5983365774154663,
"loss": 1.1837,
"loss_ce": 1.1588997840881348,
"loss_region": 0.059880323708057404,
"loss_total": 1.2187801599502563,
"lr": 0.0011275383764495787,
"router/selected_tokens_s0": 381.0625,
"router/selected_tokens_s1": 12.0625,
"step": 2890,
"tokens_trained": 9.469110536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8226950354609929,
"grad_norm": 1.5357625484466553,
"loss": 1.1892,
"loss_ce": 1.138158917427063,
"loss_region": 0.058603640645742416,
"loss_total": 1.1967625617980957,
"lr": 0.0011271314844657277,
"router/selected_tokens_s0": 493.5,
"router/selected_tokens_s1": 13.3125,
"step": 2900,
"tokens_trained": 9.501875176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.825531914893617,
"grad_norm": 1.3005295991897583,
"loss": 1.1821,
"loss_ce": 1.1475462913513184,
"loss_region": 0.0588202029466629,
"loss_total": 1.2063665390014648,
"lr": 0.0011267245924818767,
"router/selected_tokens_s0": 450.0,
"router/selected_tokens_s1": 12.625,
"step": 2910,
"tokens_trained": 9.534640608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8283687943262411,
"grad_norm": 1.562443494796753,
"loss": 1.1826,
"loss_ce": 1.0995811223983765,
"loss_region": 0.059245094656944275,
"loss_total": 1.158826231956482,
"lr": 0.0011263177004980256,
"router/selected_tokens_s0": 436.25,
"router/selected_tokens_s1": 12.75,
"step": 2920,
"tokens_trained": 9.567405248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8312056737588652,
"grad_norm": 1.1646053791046143,
"loss": 1.1852,
"loss_ce": 1.1184066534042358,
"loss_region": 0.06138136610388756,
"loss_total": 1.1797879934310913,
"lr": 0.0011259108085141746,
"router/selected_tokens_s0": 416.6875,
"router/selected_tokens_s1": 14.25,
"step": 2930,
"tokens_trained": 9.600170688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8340425531914893,
"grad_norm": 1.9767482280731201,
"loss": 1.1857,
"loss_ce": 1.1399308443069458,
"loss_region": 0.05815236270427704,
"loss_total": 1.1980831623077393,
"lr": 0.0011255039165303236,
"router/selected_tokens_s0": 421.5625,
"router/selected_tokens_s1": 11.1875,
"step": 2940,
"tokens_trained": 9.632932368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8368794326241135,
"grad_norm": 0.7609412670135498,
"loss": 1.1829,
"loss_ce": 1.115827202796936,
"loss_region": 0.058818917721509933,
"loss_total": 1.1746461391448975,
"lr": 0.0011250970245464725,
"router/selected_tokens_s0": 552.375,
"router/selected_tokens_s1": 14.5,
"step": 2950,
"tokens_trained": 9.665697808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8397163120567376,
"grad_norm": 1.6597883701324463,
"loss": 1.1808,
"loss_ce": 1.1614501476287842,
"loss_region": 0.05823326110839844,
"loss_total": 1.2196834087371826,
"lr": 0.0011246901325626217,
"router/selected_tokens_s0": 361.875,
"router/selected_tokens_s1": 9.8125,
"step": 2960,
"tokens_trained": 9.698463248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8425531914893617,
"grad_norm": 1.3326839208602905,
"loss": 1.1815,
"loss_ce": 1.0941112041473389,
"loss_region": 0.05796293914318085,
"loss_total": 1.1520740985870361,
"lr": 0.0011242832405787707,
"router/selected_tokens_s0": 536.125,
"router/selected_tokens_s1": 13.25,
"step": 2970,
"tokens_trained": 9.731228528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8453900709219858,
"grad_norm": 1.1672005653381348,
"loss": 1.183,
"loss_ce": 1.1921038627624512,
"loss_region": 0.06101511791348457,
"loss_total": 1.2531189918518066,
"lr": 0.0011238763485949196,
"router/selected_tokens_s0": 378.5,
"router/selected_tokens_s1": 13.0625,
"step": 2980,
"tokens_trained": 9.763992368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8482269503546099,
"grad_norm": 2.5261764526367188,
"loss": 1.1802,
"loss_ce": 1.0772920846939087,
"loss_region": 0.06559628993272781,
"loss_total": 1.1428884267807007,
"lr": 0.0011234694566110684,
"router/selected_tokens_s0": 440.75,
"router/selected_tokens_s1": 19.5625,
"step": 2990,
"tokens_trained": 9.796757008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.851063829787234,
"grad_norm": 1.7378714084625244,
"loss": 1.1819,
"loss_ce": 1.1687030792236328,
"loss_region": 0.06797832995653152,
"loss_total": 1.2366814613342285,
"lr": 0.0011230625646272174,
"router/selected_tokens_s0": 416.25,
"router/selected_tokens_s1": 21.375,
"step": 3000,
"tokens_trained": 9.829522448
},
{
"epoch": 0.851063829787234,
"eval_ppl": 3.074431694876341,
"eval_runtime": 2.047,
"step": 3000,
"tokens_trained": 9.829522448
},
{
"epoch": 0.851063829787234,
"eval_F": 0.0011498860304983065,
"eval_F_cds": 0.0007995687718983021,
"eval_F_dig": 0.002109539807797484,
"eval_F_exon": 0.0011823704488930567,
"eval_F_intron": 0.0011857152933888225,
"eval_F_nig": 0.0012426707491309018,
"eval_F_promoter": 0.0009290842861053208,
"eval_F_utr": 0.0010445422666567187,
"eval_G": 0.011293016012815836,
"eval_G_cds": 0.010612061051343095,
"eval_G_dig": 0.018157775387725603,
"eval_G_exon": 0.010093654229692448,
"eval_G_intron": 0.011264918238164315,
"eval_G_nig": 0.01205549809200873,
"eval_G_promoter": 0.010501267435957667,
"eval_G_utr": 0.009932436168341843,
"eval_avg_bp_per_token": 869.6514032496307,
"eval_bp_per_token/cds": 1250.6741573033707,
"eval_bp_per_token/dig": 474.037037037037,
"eval_bp_per_token/exon": 845.7586206896551,
"eval_bp_per_token/intron": 843.3727772389266,
"eval_bp_per_token/nig": 804.7183863460046,
"eval_bp_per_token/promoter": 1076.328611898017,
"eval_bp_per_token/utr": 957.3571428571429,
"eval_ppl_cds": 3.727089112409837,
"eval_ppl_dig": 1.1362078085496616,
"eval_ppl_exon": 3.3139976145435175,
"eval_ppl_intron": 3.099196725149016,
"eval_ppl_nig": 2.941734635306602,
"eval_ppl_promoter": 3.3293378412790497,
"eval_ppl_utr": 3.420161176488646,
"step": 3000,
"tokens_trained": 9.829522448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8539007092198582,
"grad_norm": 1.2796287536621094,
"loss": 1.1722,
"loss_ce": 1.1145899295806885,
"loss_region": 0.06270541250705719,
"loss_total": 1.1772953271865845,
"lr": 0.0011226556726433663,
"router/selected_tokens_s0": 373.0625,
"router/selected_tokens_s1": 14.375,
"step": 3010,
"tokens_trained": 9.862287888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8567375886524823,
"grad_norm": 1.7585965394973755,
"loss": 1.1785,
"loss_ce": 1.1197354793548584,
"loss_region": 0.057484500110149384,
"loss_total": 1.1772199869155884,
"lr": 0.0011222487806595153,
"router/selected_tokens_s0": 470.375,
"router/selected_tokens_s1": 11.4375,
"step": 3020,
"tokens_trained": 9.895048312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8595744680851064,
"grad_norm": 2.1293466091156006,
"loss": 1.1776,
"loss_ce": 1.1695561408996582,
"loss_region": 0.05918756127357483,
"loss_total": 1.2287436723709106,
"lr": 0.0011218418886756645,
"router/selected_tokens_s0": 343.0625,
"router/selected_tokens_s1": 10.5,
"step": 3030,
"tokens_trained": 9.927812952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8624113475177305,
"grad_norm": 0.6708946228027344,
"loss": 1.1847,
"loss_ce": 1.1524713039398193,
"loss_region": 0.057949285954236984,
"loss_total": 1.2104206085205078,
"lr": 0.0011214349966918134,
"router/selected_tokens_s0": 389.5625,
"router/selected_tokens_s1": 10.3125,
"step": 3040,
"tokens_trained": 9.960578392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8652482269503546,
"grad_norm": 0.22883817553520203,
"loss": 1.1884,
"loss_ce": 1.0983341932296753,
"loss_region": 0.06179222837090492,
"loss_total": 1.1601264476776123,
"lr": 0.0011210281047079624,
"router/selected_tokens_s0": 488.625,
"router/selected_tokens_s1": 16.875,
"step": 3050,
"tokens_trained": 9.993343832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8680851063829788,
"grad_norm": 1.4661550521850586,
"loss": 1.1803,
"loss_ce": 1.1707799434661865,
"loss_region": 0.059745948761701584,
"loss_total": 1.2305258512496948,
"lr": 0.0011206212127241114,
"router/selected_tokens_s0": 356.0,
"router/selected_tokens_s1": 11.625,
"step": 3060,
"tokens_trained": 10.026108952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8709219858156029,
"grad_norm": 1.0446758270263672,
"loss": 1.1806,
"loss_ce": 1.1076890230178833,
"loss_region": 0.05960114300251007,
"loss_total": 1.167290210723877,
"lr": 0.0011202143207402603,
"router/selected_tokens_s0": 411.1875,
"router/selected_tokens_s1": 12.5,
"step": 3070,
"tokens_trained": 10.058874392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.873758865248227,
"grad_norm": 3.738612413406372,
"loss": 1.1938,
"loss_ce": 1.1079699993133545,
"loss_region": 0.06472290307283401,
"loss_total": 1.172692894935608,
"lr": 0.0011198074287564093,
"router/selected_tokens_s0": 560.8125,
"router/selected_tokens_s1": 22.5,
"step": 3080,
"tokens_trained": 10.091635328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8765957446808511,
"grad_norm": 0.6973010897636414,
"loss": 1.1884,
"loss_ce": 1.148849368095398,
"loss_region": 0.06155673786997795,
"loss_total": 1.2104060649871826,
"lr": 0.0011194005367725583,
"router/selected_tokens_s0": 433.1875,
"router/selected_tokens_s1": 15.25,
"step": 3090,
"tokens_trained": 10.124400768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8794326241134752,
"grad_norm": 1.7843979597091675,
"loss": 1.1861,
"loss_ce": 1.1582818031311035,
"loss_region": 0.05559933930635452,
"loss_total": 1.2138811349868774,
"lr": 0.0011189936447887072,
"router/selected_tokens_s0": 460.5625,
"router/selected_tokens_s1": 9.125,
"step": 3100,
"tokens_trained": 10.157166208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8822695035460993,
"grad_norm": 3.1261589527130127,
"loss": 1.182,
"loss_ce": 1.1174323558807373,
"loss_region": 0.05768623203039169,
"loss_total": 1.1751185655593872,
"lr": 0.0011185867528048562,
"router/selected_tokens_s0": 536.625,
"router/selected_tokens_s1": 13.0625,
"step": 3110,
"tokens_trained": 10.189931648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8851063829787233,
"grad_norm": 1.7496775388717651,
"loss": 1.1924,
"loss_ce": 1.1259160041809082,
"loss_region": 0.056387342512607574,
"loss_total": 1.1823033094406128,
"lr": 0.0011181798608210052,
"router/selected_tokens_s0": 313.0625,
"router/selected_tokens_s1": 7.125,
"step": 3120,
"tokens_trained": 10.22269608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8879432624113475,
"grad_norm": 2.1885197162628174,
"loss": 1.1868,
"loss_ce": 1.0467259883880615,
"loss_region": 0.06346448510885239,
"loss_total": 1.110190510749817,
"lr": 0.0011177729688371541,
"router/selected_tokens_s0": 419.4375,
"router/selected_tokens_s1": 17.1875,
"step": 3130,
"tokens_trained": 10.25546152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8907801418439716,
"grad_norm": 2.0042295455932617,
"loss": 1.1805,
"loss_ce": 1.1999831199645996,
"loss_region": 0.06402087956666946,
"loss_total": 1.2640039920806885,
"lr": 0.001117366076853303,
"router/selected_tokens_s0": 401.5,
"router/selected_tokens_s1": 16.25,
"step": 3140,
"tokens_trained": 10.28822616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8936170212765957,
"grad_norm": 1.7117962837219238,
"loss": 1.1863,
"loss_ce": 1.0752744674682617,
"loss_region": 0.055134840309619904,
"loss_total": 1.1304093599319458,
"lr": 0.001116959184869452,
"router/selected_tokens_s0": 383.25,
"router/selected_tokens_s1": 7.5,
"step": 3150,
"tokens_trained": 10.3209916
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8964539007092198,
"grad_norm": 2.2417776584625244,
"loss": 1.1847,
"loss_ce": 1.133635401725769,
"loss_region": 0.05906910449266434,
"loss_total": 1.1927045583724976,
"lr": 0.001116552292885601,
"router/selected_tokens_s0": 470.125,
"router/selected_tokens_s1": 13.5,
"step": 3160,
"tokens_trained": 10.35375624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8992907801418439,
"grad_norm": 1.591855525970459,
"loss": 1.1846,
"loss_ce": 1.0943703651428223,
"loss_region": 0.05788113921880722,
"loss_total": 1.1522514820098877,
"lr": 0.00111614540090175,
"router/selected_tokens_s0": 473.875,
"router/selected_tokens_s1": 11.6875,
"step": 3170,
"tokens_trained": 10.38652168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.902127659574468,
"grad_norm": 1.1587814092636108,
"loss": 1.1926,
"loss_ce": 1.195311427116394,
"loss_region": 0.06113569065928459,
"loss_total": 1.2564470767974854,
"lr": 0.001115738508917899,
"router/selected_tokens_s0": 375.3125,
"router/selected_tokens_s1": 13.3125,
"step": 3180,
"tokens_trained": 10.41928712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9049645390070922,
"grad_norm": 0.9598585367202759,
"loss": 1.1911,
"loss_ce": 1.082224726676941,
"loss_region": 0.057053092867136,
"loss_total": 1.1392778158187866,
"lr": 0.001115331616934048,
"router/selected_tokens_s0": 362.1875,
"router/selected_tokens_s1": 8.8125,
"step": 3190,
"tokens_trained": 10.45205256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9078014184397163,
"grad_norm": 3.3285744190216064,
"loss": 1.1946,
"loss_ce": 1.1597694158554077,
"loss_region": 0.055617451667785645,
"loss_total": 1.2153868675231934,
"lr": 0.0011149247249501969,
"router/selected_tokens_s0": 449.625,
"router/selected_tokens_s1": 8.875,
"step": 3200,
"tokens_trained": 10.4848172
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9106382978723404,
"grad_norm": 2.8464155197143555,
"loss": 1.1819,
"loss_ce": 1.1424304246902466,
"loss_region": 0.07084633409976959,
"loss_total": 1.213276743888855,
"lr": 0.001114517832966346,
"router/selected_tokens_s0": 359.3125,
"router/selected_tokens_s1": 19.8125,
"step": 3210,
"tokens_trained": 10.51758264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9134751773049645,
"grad_norm": 2.721564769744873,
"loss": 1.1914,
"loss_ce": 1.173911690711975,
"loss_region": 0.057439640164375305,
"loss_total": 1.231351375579834,
"lr": 0.001114110940982495,
"router/selected_tokens_s0": 363.3125,
"router/selected_tokens_s1": 9.125,
"step": 3220,
"tokens_trained": 10.55034808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9163120567375886,
"grad_norm": 1.964784026145935,
"loss": 1.1948,
"loss_ce": 1.1454870700836182,
"loss_region": 0.06161702051758766,
"loss_total": 1.2071040868759155,
"lr": 0.001113704048998644,
"router/selected_tokens_s0": 264.3125,
"router/selected_tokens_s1": 9.5625,
"step": 3230,
"tokens_trained": 10.58311352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9191489361702128,
"grad_norm": 1.3745988607406616,
"loss": 1.1871,
"loss_ce": 1.1452701091766357,
"loss_region": 0.06286661326885223,
"loss_total": 1.2081366777420044,
"lr": 0.0011132971570147927,
"router/selected_tokens_s0": 394.5625,
"router/selected_tokens_s1": 15.125,
"step": 3240,
"tokens_trained": 10.61587896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9219858156028369,
"grad_norm": 2.1371731758117676,
"loss": 1.1914,
"loss_ce": 1.1208454370498657,
"loss_region": 0.060756195336580276,
"loss_total": 1.181601643562317,
"lr": 0.0011128902650309417,
"router/selected_tokens_s0": 399.25,
"router/selected_tokens_s1": 13.25,
"step": 3250,
"tokens_trained": 10.6486444
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.924822695035461,
"grad_norm": 0.8851431608200073,
"loss": 1.1752,
"loss_ce": 1.127838373184204,
"loss_region": 0.059403836727142334,
"loss_total": 1.1872422695159912,
"lr": 0.0011124833730470907,
"router/selected_tokens_s0": 485.4375,
"router/selected_tokens_s1": 14.3125,
"step": 3260,
"tokens_trained": 10.68140984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9276595744680851,
"grad_norm": 1.363264560699463,
"loss": 1.1837,
"loss_ce": 1.0901366472244263,
"loss_region": 0.05801825225353241,
"loss_total": 1.148154854774475,
"lr": 0.0011120764810632396,
"router/selected_tokens_s0": 623.9375,
"router/selected_tokens_s1": 14.0625,
"step": 3270,
"tokens_trained": 10.714171944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9304964539007092,
"grad_norm": 2.8988099098205566,
"loss": 1.1867,
"loss_ce": 1.0907230377197266,
"loss_region": 0.06304143369197845,
"loss_total": 1.1537644863128662,
"lr": 0.0011116695890793888,
"router/selected_tokens_s0": 524.875,
"router/selected_tokens_s1": 19.875,
"step": 3280,
"tokens_trained": 10.746937384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9333333333333333,
"grad_norm": 1.667448878288269,
"loss": 1.1761,
"loss_ce": 1.166186809539795,
"loss_region": 0.06140407547354698,
"loss_total": 1.2275909185409546,
"lr": 0.0011112626970955378,
"router/selected_tokens_s0": 421.0,
"router/selected_tokens_s1": 14.8125,
"step": 3290,
"tokens_trained": 10.779702824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9361702127659575,
"grad_norm": 2.053053379058838,
"loss": 1.1802,
"loss_ce": 1.2236586809158325,
"loss_region": 0.062042418867349625,
"loss_total": 1.2857011556625366,
"lr": 0.0011108558051116867,
"router/selected_tokens_s0": 396.5625,
"router/selected_tokens_s1": 14.5,
"step": 3300,
"tokens_trained": 10.812468264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9390070921985816,
"grad_norm": 2.3373043537139893,
"loss": 1.1879,
"loss_ce": 1.0431127548217773,
"loss_region": 0.05739426985383034,
"loss_total": 1.1005070209503174,
"lr": 0.0011104489131278357,
"router/selected_tokens_s0": 408.5625,
"router/selected_tokens_s1": 10.125,
"step": 3310,
"tokens_trained": 10.845230648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9418439716312057,
"grad_norm": 2.5947089195251465,
"loss": 1.1842,
"loss_ce": 1.0695154666900635,
"loss_region": 0.05876738205552101,
"loss_total": 1.128282904624939,
"lr": 0.0011100420211439847,
"router/selected_tokens_s0": 479.875,
"router/selected_tokens_s1": 13.125,
"step": 3320,
"tokens_trained": 10.877996088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9446808510638298,
"grad_norm": 1.015472412109375,
"loss": 1.1902,
"loss_ce": 1.1727052927017212,
"loss_region": 0.06721828877925873,
"loss_total": 1.2399235963821411,
"lr": 0.0011096351291601336,
"router/selected_tokens_s0": 426.25,
"router/selected_tokens_s1": 21.0625,
"step": 3330,
"tokens_trained": 10.910761528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9475177304964539,
"grad_norm": 3.790830135345459,
"loss": 1.1912,
"loss_ce": 1.1549181938171387,
"loss_region": 0.06554245948791504,
"loss_total": 1.2204606533050537,
"lr": 0.0011092282371762826,
"router/selected_tokens_s0": 472.25,
"router/selected_tokens_s1": 20.9375,
"step": 3340,
"tokens_trained": 10.943526968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.950354609929078,
"grad_norm": 2.207831382751465,
"loss": 1.1935,
"loss_ce": 1.1465940475463867,
"loss_region": 0.05767892673611641,
"loss_total": 1.204272985458374,
"lr": 0.0011088213451924316,
"router/selected_tokens_s0": 309.375,
"router/selected_tokens_s1": 8.25,
"step": 3350,
"tokens_trained": 10.976292408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9531914893617022,
"grad_norm": 1.879736304283142,
"loss": 1.1895,
"loss_ce": 1.075555682182312,
"loss_region": 0.061205778270959854,
"loss_total": 1.1367614269256592,
"lr": 0.0011084144532085805,
"router/selected_tokens_s0": 389.4375,
"router/selected_tokens_s1": 13.375,
"step": 3360,
"tokens_trained": 11.009057848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9560283687943263,
"grad_norm": 2.642979145050049,
"loss": 1.1893,
"loss_ce": 1.0544582605361938,
"loss_region": 0.06224330514669418,
"loss_total": 1.116701602935791,
"lr": 0.0011080075612247295,
"router/selected_tokens_s0": 490.5625,
"router/selected_tokens_s1": 17.0625,
"step": 3370,
"tokens_trained": 11.041823288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9588652482269504,
"grad_norm": 1.8629803657531738,
"loss": 1.1888,
"loss_ce": 1.0984424352645874,
"loss_region": 0.060682639479637146,
"loss_total": 1.1591250896453857,
"lr": 0.0011076006692408785,
"router/selected_tokens_s0": 426.3125,
"router/selected_tokens_s1": 14.25,
"step": 3380,
"tokens_trained": 11.074587928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9617021276595744,
"grad_norm": 2.3181028366088867,
"loss": 1.1818,
"loss_ce": 1.116972804069519,
"loss_region": 0.0578857958316803,
"loss_total": 1.174858570098877,
"lr": 0.0011071937772570274,
"router/selected_tokens_s0": 447.1875,
"router/selected_tokens_s1": 11.5,
"step": 3390,
"tokens_trained": 11.107353368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9645390070921985,
"grad_norm": 1.6701099872589111,
"loss": 1.1952,
"loss_ce": 1.1640697717666626,
"loss_region": 0.05918049067258835,
"loss_total": 1.2232502698898315,
"lr": 0.0011067868852731764,
"router/selected_tokens_s0": 487.875,
"router/selected_tokens_s1": 13.5,
"step": 3400,
"tokens_trained": 11.140118808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9673758865248226,
"grad_norm": 2.3079371452331543,
"loss": 1.1839,
"loss_ce": 1.1166282892227173,
"loss_region": 0.06041375920176506,
"loss_total": 1.177042007446289,
"lr": 0.0011063799932893254,
"router/selected_tokens_s0": 495.375,
"router/selected_tokens_s1": 16.0,
"step": 3410,
"tokens_trained": 11.172884248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9702127659574468,
"grad_norm": 0.47914406657218933,
"loss": 1.188,
"loss_ce": 1.1150635480880737,
"loss_region": 0.058126792311668396,
"loss_total": 1.1731903553009033,
"lr": 0.0011059731013054743,
"router/selected_tokens_s0": 524.125,
"router/selected_tokens_s1": 12.9375,
"step": 3420,
"tokens_trained": 11.205649688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9730496453900709,
"grad_norm": 4.547239780426025,
"loss": 1.1843,
"loss_ce": 1.2131940126419067,
"loss_region": 0.0646928995847702,
"loss_total": 1.2778868675231934,
"lr": 0.0011055662093216233,
"router/selected_tokens_s0": 486.5,
"router/selected_tokens_s1": 20.4375,
"step": 3430,
"tokens_trained": 11.238415128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.975886524822695,
"grad_norm": 3.8095717430114746,
"loss": 1.2016,
"loss_ce": 1.221601128578186,
"loss_region": 0.058637771755456924,
"loss_total": 1.2802388668060303,
"lr": 0.0011051593173377723,
"router/selected_tokens_s0": 254.4375,
"router/selected_tokens_s1": 7.75,
"step": 3440,
"tokens_trained": 11.27117724
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9787234042553191,
"grad_norm": 1.4747904539108276,
"loss": 1.1841,
"loss_ce": 1.0546537637710571,
"loss_region": 0.06348768621683121,
"loss_total": 1.1181414127349854,
"lr": 0.0011047524253539212,
"router/selected_tokens_s0": 416.625,
"router/selected_tokens_s1": 16.9375,
"step": 3450,
"tokens_trained": 11.30394268
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9815602836879432,
"grad_norm": 3.052072525024414,
"loss": 1.1922,
"loss_ce": 1.1165164709091187,
"loss_region": 0.06090632081031799,
"loss_total": 1.1774227619171143,
"lr": 0.0011043455333700704,
"router/selected_tokens_s0": 375.1875,
"router/selected_tokens_s1": 12.25,
"step": 3460,
"tokens_trained": 11.33670812
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9843971631205674,
"grad_norm": 0.5006700158119202,
"loss": 1.1902,
"loss_ce": 1.1183781623840332,
"loss_region": 0.055539172142744064,
"loss_total": 1.173917293548584,
"lr": 0.0011039386413862194,
"router/selected_tokens_s0": 613.75,
"router/selected_tokens_s1": 9.875,
"step": 3470,
"tokens_trained": 11.369471136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9872340425531915,
"grad_norm": 0.7260355949401855,
"loss": 1.18,
"loss_ce": 1.0984702110290527,
"loss_region": 0.06133873388171196,
"loss_total": 1.1598089933395386,
"lr": 0.0011035317494023683,
"router/selected_tokens_s0": 591.1875,
"router/selected_tokens_s1": 18.8125,
"step": 3480,
"tokens_trained": 11.402236576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9900709219858156,
"grad_norm": 1.2982653379440308,
"loss": 1.1858,
"loss_ce": 1.0897129774093628,
"loss_region": 0.05735067278146744,
"loss_total": 1.1470636129379272,
"lr": 0.001103124857418517,
"router/selected_tokens_s0": 467.0625,
"router/selected_tokens_s1": 11.0,
"step": 3490,
"tokens_trained": 11.435000416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9929078014184397,
"grad_norm": 2.721036672592163,
"loss": 1.1799,
"loss_ce": 1.0403258800506592,
"loss_region": 0.060663700103759766,
"loss_total": 1.100989580154419,
"lr": 0.001102717965434666,
"router/selected_tokens_s0": 470.125,
"router/selected_tokens_s1": 15.25,
"step": 3500,
"tokens_trained": 11.467765856
},
{
"epoch": 0.9929078014184397,
"eval_ppl": 3.0734159224478197,
"eval_runtime": 2.0438,
"step": 3500,
"tokens_trained": 11.467765856
},
{
"epoch": 0.9929078014184397,
"eval_F": 0.0010450035158996796,
"eval_F_cds": 0.0007456652591860569,
"eval_F_dig": 0.0008203765919212438,
"eval_F_exon": 0.0008154278957883149,
"eval_F_intron": 0.0010699422514866485,
"eval_F_nig": 0.0011481930661093125,
"eval_F_promoter": 0.0008896047838628851,
"eval_F_utr": 0.001065859455772162,
"eval_G": 0.014131649526876887,
"eval_G_cds": 0.012825789882984457,
"eval_G_dig": 0.026729230555121494,
"eval_G_exon": 0.013125177313097132,
"eval_G_intron": 0.014041850972301874,
"eval_G_nig": 0.015474153168448888,
"eval_G_promoter": 0.012678847285718421,
"eval_G_utr": 0.012453943213672845,
"eval_avg_bp_per_token": 956.9345794392524,
"eval_bp_per_token/cds": 1341.0843373493976,
"eval_bp_per_token/dig": 1218.952380952381,
"eval_bp_per_token/exon": 1226.35,
"eval_bp_per_token/intron": 934.6298817628091,
"eval_bp_per_token/nig": 870.9336691855583,
"eval_bp_per_token/promoter": 1124.094674556213,
"eval_bp_per_token/utr": 938.21,
"eval_ppl_cds": 3.75262282223572,
"eval_ppl_dig": 1.1259622508284348,
"eval_ppl_exon": 3.3195279800467707,
"eval_ppl_intron": 3.0972300222467624,
"eval_ppl_nig": 2.9334187719602456,
"eval_ppl_promoter": 3.3346561893814193,
"eval_ppl_utr": 3.428849009891916,
"step": 3500,
"tokens_trained": 11.467765856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9957446808510638,
"grad_norm": 2.2520830631256104,
"loss": 1.1819,
"loss_ce": 1.1254873275756836,
"loss_region": 0.05975877493619919,
"loss_total": 1.1852461099624634,
"lr": 0.001102311073450815,
"router/selected_tokens_s0": 381.6875,
"router/selected_tokens_s1": 11.8125,
"step": 3510,
"tokens_trained": 11.500531296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9985815602836879,
"grad_norm": 1.1383335590362549,
"loss": 1.1876,
"loss_ce": 1.1634926795959473,
"loss_region": 0.05750522017478943,
"loss_total": 1.220997929573059,
"lr": 0.001101904181466964,
"router/selected_tokens_s0": 403.125,
"router/selected_tokens_s1": 9.9375,
"step": 3520,
"tokens_trained": 11.533296736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.001418439716312,
"grad_norm": 1.6436549425125122,
"loss": 1.1797,
"loss_ce": 1.1281497478485107,
"loss_region": 0.06324146687984467,
"loss_total": 1.1913912296295166,
"lr": 0.0011014972894831132,
"router/selected_tokens_s0": 401.75,
"router/selected_tokens_s1": 16.0625,
"step": 3530,
"tokens_trained": 11.566062176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.004255319148936,
"grad_norm": 2.5775251388549805,
"loss": 1.179,
"loss_ce": 1.1454085111618042,
"loss_region": 0.056651920080184937,
"loss_total": 1.2020604610443115,
"lr": 0.0011010903974992621,
"router/selected_tokens_s0": 416.875,
"router/selected_tokens_s1": 9.5,
"step": 3540,
"tokens_trained": 11.598827616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0070921985815602,
"grad_norm": 4.208657741546631,
"loss": 1.2065,
"loss_ce": 1.154625415802002,
"loss_region": 0.06376195698976517,
"loss_total": 1.2183873653411865,
"lr": 0.001100683505515411,
"router/selected_tokens_s0": 392.1875,
"router/selected_tokens_s1": 16.1875,
"step": 3550,
"tokens_trained": 11.631593056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0099290780141843,
"grad_norm": 0.942011833190918,
"loss": 1.1958,
"loss_ce": 1.183512568473816,
"loss_region": 0.05952717736363411,
"loss_total": 1.2430397272109985,
"lr": 0.00110027661353156,
"router/selected_tokens_s0": 374.625,
"router/selected_tokens_s1": 11.1875,
"step": 3560,
"tokens_trained": 11.664358496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0127659574468084,
"grad_norm": 1.8631629943847656,
"loss": 1.1879,
"loss_ce": 1.0455646514892578,
"loss_region": 0.0647355318069458,
"loss_total": 1.1103001832962036,
"lr": 0.001099869721547709,
"router/selected_tokens_s0": 387.1875,
"router/selected_tokens_s1": 16.875,
"step": 3570,
"tokens_trained": 11.697123936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0156028368794325,
"grad_norm": 1.5745539665222168,
"loss": 1.1884,
"loss_ce": 1.1641039848327637,
"loss_region": 0.05902648717164993,
"loss_total": 1.223130464553833,
"lr": 0.001099462829563858,
"router/selected_tokens_s0": 415.3125,
"router/selected_tokens_s1": 12.3125,
"step": 3580,
"tokens_trained": 11.729887776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0184397163120567,
"grad_norm": 1.9251041412353516,
"loss": 1.1883,
"loss_ce": 1.0914249420166016,
"loss_region": 0.06119132786989212,
"loss_total": 1.152616262435913,
"lr": 0.001099055937580007,
"router/selected_tokens_s0": 443.0,
"router/selected_tokens_s1": 15.0,
"step": 3590,
"tokens_trained": 11.762653216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0212765957446808,
"grad_norm": 2.675755262374878,
"loss": 1.1864,
"loss_ce": 1.139623761177063,
"loss_region": 0.062219422310590744,
"loss_total": 1.2018431425094604,
"lr": 0.001098649045596156,
"router/selected_tokens_s0": 408.25,
"router/selected_tokens_s1": 15.5,
"step": 3600,
"tokens_trained": 11.795417056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0241134751773049,
"grad_norm": 0.8826751708984375,
"loss": 1.1881,
"loss_ce": 1.1148252487182617,
"loss_region": 0.057967670261859894,
"loss_total": 1.172792911529541,
"lr": 0.0010982421536123049,
"router/selected_tokens_s0": 486.75,
"router/selected_tokens_s1": 12.25,
"step": 3610,
"tokens_trained": 11.828182496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.026950354609929,
"grad_norm": 2.168684244155884,
"loss": 1.1835,
"loss_ce": 1.1765309572219849,
"loss_region": 0.06523355096578598,
"loss_total": 1.2417645454406738,
"lr": 0.0010978352616284538,
"router/selected_tokens_s0": 513.4375,
"router/selected_tokens_s1": 22.125,
"step": 3620,
"tokens_trained": 11.860946336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0297872340425531,
"grad_norm": 2.1988205909729004,
"loss": 1.1775,
"loss_ce": 1.1069942712783813,
"loss_region": 0.05631319805979729,
"loss_total": 1.1633074283599854,
"lr": 0.0010974283696446028,
"router/selected_tokens_s0": 459.0,
"router/selected_tokens_s1": 8.875,
"step": 3630,
"tokens_trained": 11.893711776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0326241134751772,
"grad_norm": 2.237173557281494,
"loss": 1.1737,
"loss_ce": 1.0201938152313232,
"loss_region": 0.0641506239771843,
"loss_total": 1.0843443870544434,
"lr": 0.0010970214776607518,
"router/selected_tokens_s0": 433.3125,
"router/selected_tokens_s1": 17.875,
"step": 3640,
"tokens_trained": 11.926477216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0354609929078014,
"grad_norm": 1.5898455381393433,
"loss": 1.1757,
"loss_ce": 1.146393895149231,
"loss_region": 0.05984107777476311,
"loss_total": 1.2062349319458008,
"lr": 0.0010966145856769007,
"router/selected_tokens_s0": 498.0,
"router/selected_tokens_s1": 14.5,
"step": 3650,
"tokens_trained": 11.959242656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0382978723404255,
"grad_norm": 1.6782652139663696,
"loss": 1.1872,
"loss_ce": 1.065536618232727,
"loss_region": 0.06172078102827072,
"loss_total": 1.1272573471069336,
"lr": 0.0010962076936930497,
"router/selected_tokens_s0": 456.875,
"router/selected_tokens_s1": 16.1875,
"step": 3660,
"tokens_trained": 11.992008096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0411347517730496,
"grad_norm": 2.0294923782348633,
"loss": 1.189,
"loss_ce": 1.1464074850082397,
"loss_region": 0.0617014616727829,
"loss_total": 1.208108901977539,
"lr": 0.0010958008017091987,
"router/selected_tokens_s0": 320.9375,
"router/selected_tokens_s1": 11.9375,
"step": 3670,
"tokens_trained": 12.024773536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0439716312056737,
"grad_norm": 1.3117985725402832,
"loss": 1.1906,
"loss_ce": 1.0983753204345703,
"loss_region": 0.05521257221698761,
"loss_total": 1.1535879373550415,
"lr": 0.0010953939097253476,
"router/selected_tokens_s0": 352.6875,
"router/selected_tokens_s1": 7.375,
"step": 3680,
"tokens_trained": 12.057538976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0468085106382978,
"grad_norm": 2.1483266353607178,
"loss": 1.1763,
"loss_ce": 1.1546844244003296,
"loss_region": 0.056960638612508774,
"loss_total": 1.2116450071334839,
"lr": 0.0010949870177414966,
"router/selected_tokens_s0": 412.0,
"router/selected_tokens_s1": 9.75,
"step": 3690,
"tokens_trained": 12.090304416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.049645390070922,
"grad_norm": 0.35853058099746704,
"loss": 1.1845,
"loss_ce": 1.103888988494873,
"loss_region": 0.060773998498916626,
"loss_total": 1.1646629571914673,
"lr": 0.0010945801257576456,
"router/selected_tokens_s0": 467.375,
"router/selected_tokens_s1": 15.25,
"step": 3700,
"tokens_trained": 12.123069856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.052482269503546,
"grad_norm": 1.2375736236572266,
"loss": 1.1833,
"loss_ce": 1.1234687566757202,
"loss_region": 0.06205715984106064,
"loss_total": 1.185525894165039,
"lr": 0.0010941732337737947,
"router/selected_tokens_s0": 533.0625,
"router/selected_tokens_s1": 18.875,
"step": 3710,
"tokens_trained": 12.155835296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0553191489361702,
"grad_norm": 2.2981228828430176,
"loss": 1.1837,
"loss_ce": 1.1076805591583252,
"loss_region": 0.06259025633335114,
"loss_total": 1.1702708005905151,
"lr": 0.0010937663417899437,
"router/selected_tokens_s0": 405.0,
"router/selected_tokens_s1": 15.5625,
"step": 3720,
"tokens_trained": 12.188600576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0581560283687943,
"grad_norm": 3.0473289489746094,
"loss": 1.1866,
"loss_ce": 1.1796292066574097,
"loss_region": 0.059974055737257004,
"loss_total": 1.2396032810211182,
"lr": 0.0010933594498060927,
"router/selected_tokens_s0": 430.0625,
"router/selected_tokens_s1": 13.6875,
"step": 3730,
"tokens_trained": 12.221366016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0609929078014184,
"grad_norm": 1.4829760789871216,
"loss": 1.1815,
"loss_ce": 1.1546300649642944,
"loss_region": 0.0575762614607811,
"loss_total": 1.2122063636779785,
"lr": 0.0010929525578222414,
"router/selected_tokens_s0": 386.875,
"router/selected_tokens_s1": 9.75,
"step": 3740,
"tokens_trained": 12.254131456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0638297872340425,
"grad_norm": 1.9733688831329346,
"loss": 1.1836,
"loss_ce": 1.102645754814148,
"loss_region": 0.059846386313438416,
"loss_total": 1.1624921560287476,
"lr": 0.0010925456658383904,
"router/selected_tokens_s0": 407.25,
"router/selected_tokens_s1": 12.5,
"step": 3750,
"tokens_trained": 12.286896896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0666666666666667,
"grad_norm": 1.8906550407409668,
"loss": 1.1801,
"loss_ce": 1.1507176160812378,
"loss_region": 0.05901917442679405,
"loss_total": 1.2097368240356445,
"lr": 0.0010921387738545394,
"router/selected_tokens_s0": 405.875,
"router/selected_tokens_s1": 11.8125,
"step": 3760,
"tokens_trained": 12.319662336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0695035460992908,
"grad_norm": 1.3158189058303833,
"loss": 1.1746,
"loss_ce": 1.0708504915237427,
"loss_region": 0.057457201182842255,
"loss_total": 1.1283077001571655,
"lr": 0.0010917318818706883,
"router/selected_tokens_s0": 435.625,
"router/selected_tokens_s1": 10.5625,
"step": 3770,
"tokens_trained": 12.352427776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0723404255319149,
"grad_norm": 2.073458194732666,
"loss": 1.1798,
"loss_ce": 1.141626238822937,
"loss_region": 0.06303444504737854,
"loss_total": 1.2046606540679932,
"lr": 0.0010913249898868375,
"router/selected_tokens_s0": 410.75,
"router/selected_tokens_s1": 16.1875,
"step": 3780,
"tokens_trained": 12.385193216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.075177304964539,
"grad_norm": 0.6519181132316589,
"loss": 1.1842,
"loss_ce": 1.1240960359573364,
"loss_region": 0.05678265169262886,
"loss_total": 1.1808786392211914,
"lr": 0.0010909180979029865,
"router/selected_tokens_s0": 423.125,
"router/selected_tokens_s1": 9.125,
"step": 3790,
"tokens_trained": 12.417958656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0780141843971631,
"grad_norm": 1.093948245048523,
"loss": 1.1766,
"loss_ce": 1.0316849946975708,
"loss_region": 0.06699247658252716,
"loss_total": 1.0986775159835815,
"lr": 0.0010905112059191354,
"router/selected_tokens_s0": 436.625,
"router/selected_tokens_s1": 21.375,
"step": 3800,
"tokens_trained": 12.450724096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0808510638297872,
"grad_norm": 2.533555746078491,
"loss": 1.1842,
"loss_ce": 1.0861109495162964,
"loss_region": 0.06075740605592728,
"loss_total": 1.146868348121643,
"lr": 0.0010901043139352844,
"router/selected_tokens_s0": 415.3125,
"router/selected_tokens_s1": 14.0,
"step": 3810,
"tokens_trained": 12.483489536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0836879432624114,
"grad_norm": 0.5290806293487549,
"loss": 1.1715,
"loss_ce": 1.1869332790374756,
"loss_region": 0.05955567955970764,
"loss_total": 1.2464889287948608,
"lr": 0.0010896974219514334,
"router/selected_tokens_s0": 391.4375,
"router/selected_tokens_s1": 11.875,
"step": 3820,
"tokens_trained": 12.516254976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0865248226950355,
"grad_norm": 1.6873115301132202,
"loss": 1.1825,
"loss_ce": 1.1999320983886719,
"loss_region": 0.06173175573348999,
"loss_total": 1.2616639137268066,
"lr": 0.0010892905299675823,
"router/selected_tokens_s0": 436.875,
"router/selected_tokens_s1": 15.5625,
"step": 3830,
"tokens_trained": 12.549020416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0893617021276596,
"grad_norm": 2.160799264907837,
"loss": 1.187,
"loss_ce": 1.1249465942382812,
"loss_region": 0.06040271744132042,
"loss_total": 1.1853493452072144,
"lr": 0.0010888836379837313,
"router/selected_tokens_s0": 313.25,
"router/selected_tokens_s1": 10.625,
"step": 3840,
"tokens_trained": 12.581785856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0921985815602837,
"grad_norm": 2.2160236835479736,
"loss": 1.1818,
"loss_ce": 1.1184971332550049,
"loss_region": 0.06124234199523926,
"loss_total": 1.1797394752502441,
"lr": 0.0010884767459998803,
"router/selected_tokens_s0": 381.25,
"router/selected_tokens_s1": 13.5,
"step": 3850,
"tokens_trained": 12.614549696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0950354609929078,
"grad_norm": 1.383900761604309,
"loss": 1.1753,
"loss_ce": 1.0543675422668457,
"loss_region": 0.058981068432331085,
"loss_total": 1.1133486032485962,
"lr": 0.0010880698540160292,
"router/selected_tokens_s0": 414.375,
"router/selected_tokens_s1": 11.875,
"step": 3860,
"tokens_trained": 12.647315136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.097872340425532,
"grad_norm": 1.4804929494857788,
"loss": 1.1723,
"loss_ce": 1.0903220176696777,
"loss_region": 0.06363452225923538,
"loss_total": 1.1539565324783325,
"lr": 0.0010876629620321782,
"router/selected_tokens_s0": 428.8125,
"router/selected_tokens_s1": 17.25,
"step": 3870,
"tokens_trained": 12.680079808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.100709219858156,
"grad_norm": 2.7304487228393555,
"loss": 1.1821,
"loss_ce": 1.077646017074585,
"loss_region": 0.057004958391189575,
"loss_total": 1.1346509456634521,
"lr": 0.0010872560700483272,
"router/selected_tokens_s0": 478.5,
"router/selected_tokens_s1": 10.75,
"step": 3880,
"tokens_trained": 12.712844448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1035460992907802,
"grad_norm": 1.97611665725708,
"loss": 1.203,
"loss_ce": 1.1368480920791626,
"loss_region": 0.05987485125660896,
"loss_total": 1.1967229843139648,
"lr": 0.0010868491780644761,
"router/selected_tokens_s0": 415.875,
"router/selected_tokens_s1": 13.1875,
"step": 3890,
"tokens_trained": 12.745609888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1063829787234043,
"grad_norm": 2.3967514038085938,
"loss": 1.1847,
"loss_ce": 1.129238486289978,
"loss_region": 0.06246556341648102,
"loss_total": 1.1917040348052979,
"lr": 0.001086442286080625,
"router/selected_tokens_s0": 472.0,
"router/selected_tokens_s1": 17.5625,
"step": 3900,
"tokens_trained": 12.778375328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1092198581560284,
"grad_norm": 1.5276507139205933,
"loss": 1.1882,
"loss_ce": 1.107843279838562,
"loss_region": 0.05788169056177139,
"loss_total": 1.1657249927520752,
"lr": 0.001086035394096774,
"router/selected_tokens_s0": 390.875,
"router/selected_tokens_s1": 10.25,
"step": 3910,
"tokens_trained": 12.811139968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1120567375886525,
"grad_norm": 1.167576789855957,
"loss": 1.1841,
"loss_ce": 1.1291859149932861,
"loss_region": 0.0615556500852108,
"loss_total": 1.1907415390014648,
"lr": 0.001085628502112923,
"router/selected_tokens_s0": 397.6875,
"router/selected_tokens_s1": 14.1875,
"step": 3920,
"tokens_trained": 12.843905408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1148936170212767,
"grad_norm": 1.0138903856277466,
"loss": 1.1774,
"loss_ce": 1.0464414358139038,
"loss_region": 0.060723938047885895,
"loss_total": 1.1071653366088867,
"lr": 0.001085221610129072,
"router/selected_tokens_s0": 419.4375,
"router/selected_tokens_s1": 14.0625,
"step": 3930,
"tokens_trained": 12.876670848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1177304964539008,
"grad_norm": 2.0475807189941406,
"loss": 1.1815,
"loss_ce": 1.0976098775863647,
"loss_region": 0.05905111879110336,
"loss_total": 1.156661033630371,
"lr": 0.001084814718145221,
"router/selected_tokens_s0": 430.875,
"router/selected_tokens_s1": 12.4375,
"step": 3940,
"tokens_trained": 12.909436288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1205673758865249,
"grad_norm": 1.7863166332244873,
"loss": 1.1712,
"loss_ce": 1.1482179164886475,
"loss_region": 0.06282122433185577,
"loss_total": 1.2110391855239868,
"lr": 0.00108440782616137,
"router/selected_tokens_s0": 410.0625,
"router/selected_tokens_s1": 15.9375,
"step": 3950,
"tokens_trained": 12.942201728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.123404255319149,
"grad_norm": 1.1568286418914795,
"loss": 1.17,
"loss_ce": 1.0623869895935059,
"loss_region": 0.059787455946207047,
"loss_total": 1.1221745014190674,
"lr": 0.001084000934177519,
"router/selected_tokens_s0": 492.125,
"router/selected_tokens_s1": 14.3125,
"step": 3960,
"tokens_trained": 12.974967168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1262411347517731,
"grad_norm": 1.1083351373672485,
"loss": 1.1777,
"loss_ce": 1.0901384353637695,
"loss_region": 0.06682166457176208,
"loss_total": 1.156960129737854,
"lr": 0.001083594042193668,
"router/selected_tokens_s0": 427.9375,
"router/selected_tokens_s1": 21.625,
"step": 3970,
"tokens_trained": 13.007732608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1290780141843972,
"grad_norm": 2.0190722942352295,
"loss": 1.1741,
"loss_ce": 1.1439288854599,
"loss_region": 0.057421792298555374,
"loss_total": 1.2013506889343262,
"lr": 0.001083187150209817,
"router/selected_tokens_s0": 421.875,
"router/selected_tokens_s1": 10.1875,
"step": 3980,
"tokens_trained": 13.040497248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1319148936170214,
"grad_norm": 1.738838791847229,
"loss": 1.1762,
"loss_ce": 1.0594556331634521,
"loss_region": 0.06316748261451721,
"loss_total": 1.122623085975647,
"lr": 0.0010827802582259658,
"router/selected_tokens_s0": 399.0,
"router/selected_tokens_s1": 16.0,
"step": 3990,
"tokens_trained": 13.073261888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1347517730496455,
"grad_norm": 1.5448288917541504,
"loss": 1.1853,
"loss_ce": 1.097516655921936,
"loss_region": 0.06060180068016052,
"loss_total": 1.158118486404419,
"lr": 0.0010823733662421147,
"router/selected_tokens_s0": 466.25,
"router/selected_tokens_s1": 14.875,
"step": 4000,
"tokens_trained": 13.106027328
},
{
"epoch": 1.1347517730496455,
"eval_ppl": 3.0780662311338154,
"eval_runtime": 2.0365,
"step": 4000,
"tokens_trained": 13.106027328
},
{
"epoch": 1.1347517730496455,
"eval_F": 0.001075576556592397,
"eval_F_cds": 0.0008444883658251729,
"eval_F_dig": 0.000664114383936245,
"eval_F_exon": 0.0010192848697353936,
"eval_F_intron": 0.00112246181023035,
"eval_F_nig": 0.001104810456558583,
"eval_F_promoter": 0.0009211883856568336,
"eval_F_utr": 0.0011298110231184916,
"eval_G": 0.013302638605348116,
"eval_G_cds": 0.011082541157577935,
"eval_G_dig": 0.021607370448863194,
"eval_G_exon": 0.01194230253054457,
"eval_G_intron": 0.013434109888838712,
"eval_G_nig": 0.013912727565888544,
"eval_G_promoter": 0.012317198595385109,
"eval_G_utr": 0.012318524937114292,
"eval_avg_bp_per_token": 929.733912356889,
"eval_bp_per_token/cds": 1184.1489361702127,
"eval_bp_per_token/dig": 1505.764705882353,
"eval_bp_per_token/exon": 981.08,
"eval_bp_per_token/intron": 890.8989071038251,
"eval_bp_per_token/nig": 905.1326352530541,
"eval_bp_per_token/promoter": 1085.5542857142857,
"eval_bp_per_token/utr": 885.1037735849056,
"eval_ppl_cds": 3.7825145100068065,
"eval_ppl_dig": 1.1088177473934662,
"eval_ppl_exon": 3.3321747505821633,
"eval_ppl_intron": 3.100516205807046,
"eval_ppl_nig": 2.9327303159960234,
"eval_ppl_promoter": 3.351815098328506,
"eval_ppl_utr": 3.4471430144116186,
"step": 4000,
"tokens_trained": 13.106027328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1375886524822696,
"grad_norm": 2.2905516624450684,
"loss": 1.1719,
"loss_ce": 1.1303597688674927,
"loss_region": 0.05621382221579552,
"loss_total": 1.1865736246109009,
"lr": 0.0010819664742582637,
"router/selected_tokens_s0": 454.5625,
"router/selected_tokens_s1": 9.625,
"step": 4010,
"tokens_trained": 13.138791968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1404255319148937,
"grad_norm": 1.3957611322402954,
"loss": 1.1742,
"loss_ce": 1.1473259925842285,
"loss_region": 0.062191255390644073,
"loss_total": 1.209517240524292,
"lr": 0.0010815595822744127,
"router/selected_tokens_s0": 383.125,
"router/selected_tokens_s1": 14.5,
"step": 4020,
"tokens_trained": 13.171557408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1432624113475178,
"grad_norm": 1.3832191228866577,
"loss": 1.1765,
"loss_ce": 1.0680574178695679,
"loss_region": 0.055804431438446045,
"loss_total": 1.1238617897033691,
"lr": 0.0010811526902905618,
"router/selected_tokens_s0": 423.1875,
"router/selected_tokens_s1": 8.625,
"step": 4030,
"tokens_trained": 13.204322848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1460992907801417,
"grad_norm": 0.8278810977935791,
"loss": 1.1763,
"loss_ce": 1.0880036354064941,
"loss_region": 0.06598131358623505,
"loss_total": 1.1539849042892456,
"lr": 0.0010807457983067108,
"router/selected_tokens_s0": 444.8125,
"router/selected_tokens_s1": 20.625,
"step": 4040,
"tokens_trained": 13.237088288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.148936170212766,
"grad_norm": 1.973814606666565,
"loss": 1.1785,
"loss_ce": 1.1111335754394531,
"loss_region": 0.056068602949380875,
"loss_total": 1.1672022342681885,
"lr": 0.0010803389063228598,
"router/selected_tokens_s0": 414.625,
"router/selected_tokens_s1": 8.5,
"step": 4050,
"tokens_trained": 13.269853704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.15177304964539,
"grad_norm": 1.9284107685089111,
"loss": 1.1835,
"loss_ce": 1.1678242683410645,
"loss_region": 0.06446538865566254,
"loss_total": 1.2322896718978882,
"lr": 0.0010799320143390087,
"router/selected_tokens_s0": 467.0625,
"router/selected_tokens_s1": 19.75,
"step": 4060,
"tokens_trained": 13.302619144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1546099290780143,
"grad_norm": 1.5813398361206055,
"loss": 1.177,
"loss_ce": 1.117352843284607,
"loss_region": 0.059066567569971085,
"loss_total": 1.1764193773269653,
"lr": 0.0010795251223551577,
"router/selected_tokens_s0": 399.375,
"router/selected_tokens_s1": 11.625,
"step": 4070,
"tokens_trained": 13.335384584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1574468085106382,
"grad_norm": 2.2116472721099854,
"loss": 1.1738,
"loss_ce": 1.0900934934616089,
"loss_region": 0.058406438678503036,
"loss_total": 1.1484999656677246,
"lr": 0.0010791182303713067,
"router/selected_tokens_s0": 458.0,
"router/selected_tokens_s1": 12.1875,
"step": 4080,
"tokens_trained": 13.368150024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1602836879432625,
"grad_norm": 0.8941004872322083,
"loss": 1.1785,
"loss_ce": 1.1180888414382935,
"loss_region": 0.061131663620471954,
"loss_total": 1.1792205572128296,
"lr": 0.0010787113383874556,
"router/selected_tokens_s0": 414.125,
"router/selected_tokens_s1": 14.4375,
"step": 4090,
"tokens_trained": 13.400914384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1631205673758864,
"grad_norm": 1.9441637992858887,
"loss": 1.1763,
"loss_ce": 1.132266879081726,
"loss_region": 0.05915014073252678,
"loss_total": 1.1914169788360596,
"lr": 0.0010783044464036046,
"router/selected_tokens_s0": 474.25,
"router/selected_tokens_s1": 13.75,
"step": 4100,
"tokens_trained": 13.433677248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1659574468085105,
"grad_norm": 0.49526798725128174,
"loss": 1.1742,
"loss_ce": 1.1343379020690918,
"loss_region": 0.059441614896059036,
"loss_total": 1.193779468536377,
"lr": 0.0010778975544197536,
"router/selected_tokens_s0": 354.125,
"router/selected_tokens_s1": 11.0625,
"step": 4110,
"tokens_trained": 13.466442688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1687943262411347,
"grad_norm": 1.8044946193695068,
"loss": 1.1762,
"loss_ce": 1.1329114437103271,
"loss_region": 0.05853970721364021,
"loss_total": 1.1914511919021606,
"lr": 0.0010774906624359025,
"router/selected_tokens_s0": 421.9375,
"router/selected_tokens_s1": 11.8125,
"step": 4120,
"tokens_trained": 13.499207928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1716312056737588,
"grad_norm": 1.7056463956832886,
"loss": 1.1762,
"loss_ce": 1.137860655784607,
"loss_region": 0.06000075116753578,
"loss_total": 1.1978614330291748,
"lr": 0.0010770837704520515,
"router/selected_tokens_s0": 380.0,
"router/selected_tokens_s1": 12.125,
"step": 4130,
"tokens_trained": 13.531973368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.174468085106383,
"grad_norm": 2.1075713634490967,
"loss": 1.1836,
"loss_ce": 1.1564133167266846,
"loss_region": 0.05947628244757652,
"loss_total": 1.215889573097229,
"lr": 0.0010766768784682005,
"router/selected_tokens_s0": 438.875,
"router/selected_tokens_s1": 13.3125,
"step": 4140,
"tokens_trained": 13.564734752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.177304964539007,
"grad_norm": 3.1112468242645264,
"loss": 1.1813,
"loss_ce": 1.1807456016540527,
"loss_region": 0.05970983952283859,
"loss_total": 1.2404553890228271,
"lr": 0.0010762699864843494,
"router/selected_tokens_s0": 345.625,
"router/selected_tokens_s1": 10.9375,
"step": 4150,
"tokens_trained": 13.597500192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1801418439716311,
"grad_norm": 2.5510308742523193,
"loss": 1.1811,
"loss_ce": 1.061288595199585,
"loss_region": 0.06100037693977356,
"loss_total": 1.1222889423370361,
"lr": 0.0010758630945004984,
"router/selected_tokens_s0": 363.625,
"router/selected_tokens_s1": 12.125,
"step": 4160,
"tokens_trained": 13.630265632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1829787234042553,
"grad_norm": 3.261460065841675,
"loss": 1.1814,
"loss_ce": 1.1258513927459717,
"loss_region": 0.06240670382976532,
"loss_total": 1.1882580518722534,
"lr": 0.0010754562025166474,
"router/selected_tokens_s0": 375.375,
"router/selected_tokens_s1": 14.1875,
"step": 4170,
"tokens_trained": 13.663031072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1858156028368794,
"grad_norm": 1.1999715566635132,
"loss": 1.177,
"loss_ce": 1.1389847993850708,
"loss_region": 0.05969350412487984,
"loss_total": 1.1986782550811768,
"lr": 0.0010750493105327963,
"router/selected_tokens_s0": 353.3125,
"router/selected_tokens_s1": 11.1875,
"step": 4180,
"tokens_trained": 13.695793424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1886524822695035,
"grad_norm": 2.061321973800659,
"loss": 1.1722,
"loss_ce": 1.1006853580474854,
"loss_region": 0.06308386474847794,
"loss_total": 1.163769245147705,
"lr": 0.0010746424185489453,
"router/selected_tokens_s0": 404.5,
"router/selected_tokens_s1": 16.3125,
"step": 4190,
"tokens_trained": 13.728557088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1914893617021276,
"grad_norm": 1.17081618309021,
"loss": 1.1768,
"loss_ce": 1.092057466506958,
"loss_region": 0.058908574283123016,
"loss_total": 1.1509660482406616,
"lr": 0.0010742355265650943,
"router/selected_tokens_s0": 392.625,
"router/selected_tokens_s1": 11.3125,
"step": 4200,
"tokens_trained": 13.761322528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1943262411347517,
"grad_norm": 0.3326140344142914,
"loss": 1.1747,
"loss_ce": 1.0654566287994385,
"loss_region": 0.05828992277383804,
"loss_total": 1.1237465143203735,
"lr": 0.0010738286345812434,
"router/selected_tokens_s0": 444.125,
"router/selected_tokens_s1": 11.75,
"step": 4210,
"tokens_trained": 13.794087968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1971631205673758,
"grad_norm": 1.0290011167526245,
"loss": 1.1824,
"loss_ce": 1.140906572341919,
"loss_region": 0.0639735609292984,
"loss_total": 1.2048801183700562,
"lr": 0.0010734217425973924,
"router/selected_tokens_s0": 438.6875,
"router/selected_tokens_s1": 18.1875,
"step": 4220,
"tokens_trained": 13.826853408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2,
"grad_norm": 0.9843527674674988,
"loss": 1.1796,
"loss_ce": 1.0733304023742676,
"loss_region": 0.058738574385643005,
"loss_total": 1.1320689916610718,
"lr": 0.0010730148506135414,
"router/selected_tokens_s0": 441.9375,
"router/selected_tokens_s1": 12.1875,
"step": 4230,
"tokens_trained": 13.859618048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.202836879432624,
"grad_norm": 1.3148319721221924,
"loss": 1.1696,
"loss_ce": 1.1151381731033325,
"loss_region": 0.062236238270998,
"loss_total": 1.1773743629455566,
"lr": 0.0010726079586296901,
"router/selected_tokens_s0": 469.8125,
"router/selected_tokens_s1": 17.3125,
"step": 4240,
"tokens_trained": 13.892383488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2056737588652482,
"grad_norm": 1.3859351873397827,
"loss": 1.1717,
"loss_ce": 1.1349636316299438,
"loss_region": 0.05773340165615082,
"loss_total": 1.1926970481872559,
"lr": 0.001072201066645839,
"router/selected_tokens_s0": 418.625,
"router/selected_tokens_s1": 10.6875,
"step": 4250,
"tokens_trained": 13.925146528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2085106382978723,
"grad_norm": 2.72090744972229,
"loss": 1.1765,
"loss_ce": 1.072594165802002,
"loss_region": 0.06244191154837608,
"loss_total": 1.1350361108779907,
"lr": 0.001071794174661988,
"router/selected_tokens_s0": 477.4375,
"router/selected_tokens_s1": 17.25,
"step": 4260,
"tokens_trained": 13.957911968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2113475177304964,
"grad_norm": 1.4798249006271362,
"loss": 1.1734,
"loss_ce": 1.1144499778747559,
"loss_region": 0.056226495653390884,
"loss_total": 1.1706764698028564,
"lr": 0.0010713872826781372,
"router/selected_tokens_s0": 426.6875,
"router/selected_tokens_s1": 9.1875,
"step": 4270,
"tokens_trained": 13.990673272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2141843971631205,
"grad_norm": 1.357850432395935,
"loss": 1.1693,
"loss_ce": 1.077507495880127,
"loss_region": 0.06390528380870819,
"loss_total": 1.1414127349853516,
"lr": 0.0010709803906942862,
"router/selected_tokens_s0": 412.6875,
"router/selected_tokens_s1": 17.3125,
"step": 4280,
"tokens_trained": 14.023438712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2170212765957447,
"grad_norm": 1.3726602792739868,
"loss": 1.176,
"loss_ce": 1.0596121549606323,
"loss_region": 0.05795986205339432,
"loss_total": 1.1175720691680908,
"lr": 0.0010705734987104352,
"router/selected_tokens_s0": 445.5625,
"router/selected_tokens_s1": 11.25,
"step": 4290,
"tokens_trained": 14.056204152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2198581560283688,
"grad_norm": 1.4125066995620728,
"loss": 1.1771,
"loss_ce": 1.0902185440063477,
"loss_region": 0.06225195899605751,
"loss_total": 1.1524704694747925,
"lr": 0.0010701666067265841,
"router/selected_tokens_s0": 385.0,
"router/selected_tokens_s1": 14.9375,
"step": 4300,
"tokens_trained": 14.088969592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.222695035460993,
"grad_norm": 1.2627815008163452,
"loss": 1.1721,
"loss_ce": 1.0882596969604492,
"loss_region": 0.05787515267729759,
"loss_total": 1.146134853363037,
"lr": 0.001069759714742733,
"router/selected_tokens_s0": 488.75,
"router/selected_tokens_s1": 11.875,
"step": 4310,
"tokens_trained": 14.121735032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.225531914893617,
"grad_norm": 1.7309290170669556,
"loss": 1.1713,
"loss_ce": 1.1801739931106567,
"loss_region": 0.062443725764751434,
"loss_total": 1.2426177263259888,
"lr": 0.001069352822758882,
"router/selected_tokens_s0": 420.9375,
"router/selected_tokens_s1": 16.125,
"step": 4320,
"tokens_trained": 14.154499672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2283687943262411,
"grad_norm": 1.483018398284912,
"loss": 1.1751,
"loss_ce": 1.1250663995742798,
"loss_region": 0.05841255187988281,
"loss_total": 1.1834789514541626,
"lr": 0.001068945930775031,
"router/selected_tokens_s0": 421.3125,
"router/selected_tokens_s1": 11.3125,
"step": 4330,
"tokens_trained": 14.187265112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2312056737588652,
"grad_norm": 1.1965560913085938,
"loss": 1.1727,
"loss_ce": 1.117280125617981,
"loss_region": 0.0637601837515831,
"loss_total": 1.1810402870178223,
"lr": 0.00106853903879118,
"router/selected_tokens_s0": 447.1875,
"router/selected_tokens_s1": 18.4375,
"step": 4340,
"tokens_trained": 14.220030552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2340425531914894,
"grad_norm": 1.5123695135116577,
"loss": 1.1695,
"loss_ce": 1.0661840438842773,
"loss_region": 0.060901377350091934,
"loss_total": 1.1270854473114014,
"lr": 0.001068132146807329,
"router/selected_tokens_s0": 424.75,
"router/selected_tokens_s1": 13.6875,
"step": 4350,
"tokens_trained": 14.252795992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2368794326241135,
"grad_norm": 1.7330703735351562,
"loss": 1.1654,
"loss_ce": 1.0469716787338257,
"loss_region": 0.055631160736083984,
"loss_total": 1.1026028394699097,
"lr": 0.001067725254823478,
"router/selected_tokens_s0": 447.125,
"router/selected_tokens_s1": 8.3125,
"step": 4360,
"tokens_trained": 14.285561432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2397163120567376,
"grad_norm": 2.1848738193511963,
"loss": 1.1806,
"loss_ce": 1.1433590650558472,
"loss_region": 0.06835979223251343,
"loss_total": 1.2117187976837158,
"lr": 0.0010673183628396269,
"router/selected_tokens_s0": 320.9375,
"router/selected_tokens_s1": 17.3125,
"step": 4370,
"tokens_trained": 14.318326792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2425531914893617,
"grad_norm": 1.8598670959472656,
"loss": 1.1732,
"loss_ce": 1.0439656972885132,
"loss_region": 0.05709763243794441,
"loss_total": 1.1010633707046509,
"lr": 0.0010669114708557758,
"router/selected_tokens_s0": 429.8125,
"router/selected_tokens_s1": 9.5625,
"step": 4380,
"tokens_trained": 14.351092216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2453900709219858,
"grad_norm": 0.9603729248046875,
"loss": 1.1674,
"loss_ce": 1.1185280084609985,
"loss_region": 0.06183166801929474,
"loss_total": 1.1803597211837769,
"lr": 0.0010665045788719248,
"router/selected_tokens_s0": 396.75,
"router/selected_tokens_s1": 14.6875,
"step": 4390,
"tokens_trained": 14.383857656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.24822695035461,
"grad_norm": 1.593279242515564,
"loss": 1.1763,
"loss_ce": 1.1112045049667358,
"loss_region": 0.06215018033981323,
"loss_total": 1.1733546257019043,
"lr": 0.0010660976868880738,
"router/selected_tokens_s0": 461.6875,
"router/selected_tokens_s1": 17.125,
"step": 4400,
"tokens_trained": 14.416623096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.251063829787234,
"grad_norm": 1.1648064851760864,
"loss": 1.1733,
"loss_ce": 0.9768592715263367,
"loss_region": 0.05571449548006058,
"loss_total": 1.0325738191604614,
"lr": 0.0010656907949042227,
"router/selected_tokens_s0": 511.875,
"router/selected_tokens_s1": 9.375,
"step": 4410,
"tokens_trained": 14.449387936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2539007092198582,
"grad_norm": 1.1375138759613037,
"loss": 1.177,
"loss_ce": 1.064677357673645,
"loss_region": 0.06464707851409912,
"loss_total": 1.1293244361877441,
"lr": 0.0010652839029203717,
"router/selected_tokens_s0": 384.4375,
"router/selected_tokens_s1": 17.125,
"step": 4420,
"tokens_trained": 14.48214904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2567375886524823,
"grad_norm": 1.069541096687317,
"loss": 1.1701,
"loss_ce": 1.1224985122680664,
"loss_region": 0.05752616375684738,
"loss_total": 1.1800246238708496,
"lr": 0.0010648770109365207,
"router/selected_tokens_s0": 443.1875,
"router/selected_tokens_s1": 11.25,
"step": 4430,
"tokens_trained": 14.51491448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2595744680851064,
"grad_norm": 1.6241931915283203,
"loss": 1.1755,
"loss_ce": 1.1491807699203491,
"loss_region": 0.0633014589548111,
"loss_total": 1.212482213973999,
"lr": 0.0010644701189526696,
"router/selected_tokens_s0": 413.1875,
"router/selected_tokens_s1": 16.5,
"step": 4440,
"tokens_trained": 14.54767992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2624113475177305,
"grad_norm": 1.3303278684616089,
"loss": 1.1711,
"loss_ce": 1.0399068593978882,
"loss_region": 0.05873655900359154,
"loss_total": 1.09864342212677,
"lr": 0.0010640632269688186,
"router/selected_tokens_s0": 471.9375,
"router/selected_tokens_s1": 12.75,
"step": 4450,
"tokens_trained": 14.58044536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2652482269503547,
"grad_norm": 1.3606629371643066,
"loss": 1.1715,
"loss_ce": 1.1313279867172241,
"loss_region": 0.061985936015844345,
"loss_total": 1.1933139562606812,
"lr": 0.0010636563349849678,
"router/selected_tokens_s0": 465.3125,
"router/selected_tokens_s1": 17.0,
"step": 4460,
"tokens_trained": 14.613210784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2680851063829788,
"grad_norm": 1.165449619293213,
"loss": 1.1774,
"loss_ce": 1.077015995979309,
"loss_region": 0.05757826194167137,
"loss_total": 1.134594202041626,
"lr": 0.0010632494430011167,
"router/selected_tokens_s0": 444.125,
"router/selected_tokens_s1": 10.8125,
"step": 4470,
"tokens_trained": 14.645976224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.270921985815603,
"grad_norm": 1.4742231369018555,
"loss": 1.1779,
"loss_ce": 1.1043974161148071,
"loss_region": 0.06537966430187225,
"loss_total": 1.1697770357131958,
"lr": 0.0010628425510172657,
"router/selected_tokens_s0": 465.375,
"router/selected_tokens_s1": 20.875,
"step": 4480,
"tokens_trained": 14.678741664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.273758865248227,
"grad_norm": 1.670129656791687,
"loss": 1.1805,
"loss_ce": 1.1499029397964478,
"loss_region": 0.057785190641880035,
"loss_total": 1.2076880931854248,
"lr": 0.0010624356590334145,
"router/selected_tokens_s0": 392.4375,
"router/selected_tokens_s1": 10.1875,
"step": 4490,
"tokens_trained": 14.711504648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2765957446808511,
"grad_norm": 0.8384753465652466,
"loss": 1.1612,
"loss_ce": 1.1587680578231812,
"loss_region": 0.058904800564050674,
"loss_total": 1.2176728248596191,
"lr": 0.0010620287670495634,
"router/selected_tokens_s0": 401.875,
"router/selected_tokens_s1": 11.625,
"step": 4500,
"tokens_trained": 14.744270088
},
{
"epoch": 1.2765957446808511,
"eval_ppl": 3.0410384974007107,
"eval_runtime": 2.0139,
"step": 4500,
"tokens_trained": 14.744270088
},
{
"epoch": 1.2765957446808511,
"eval_F": 0.0011583785418018391,
"eval_F_cds": 0.0011679094420986435,
"eval_F_dig": 0.0010157043519024925,
"eval_F_exon": 0.001141599054103641,
"eval_F_intron": 0.001173064596757128,
"eval_F_nig": 0.0012291739372706748,
"eval_F_promoter": 0.0010383109089760595,
"eval_F_utr": 0.0009805906993103888,
"eval_G": 0.014433089722771523,
"eval_G_cds": 0.012305126167909443,
"eval_G_dig": 0.021026957062075163,
"eval_G_exon": 0.01361236362817847,
"eval_G_intron": 0.01457564882380148,
"eval_G_nig": 0.015167288991204899,
"eval_G_promoter": 0.013283806400581402,
"eval_G_utr": 0.013029840400869741,
"eval_avg_bp_per_token": 863.2756598240469,
"eval_bp_per_token/cds": 856.2307692307693,
"eval_bp_per_token/dig": 984.5384615384615,
"eval_bp_per_token/exon": 875.9642857142857,
"eval_bp_per_token/intron": 852.4679738562091,
"eval_bp_per_token/nig": 813.5545098039215,
"eval_bp_per_token/promoter": 963.1026615969582,
"eval_bp_per_token/utr": 1019.7934782608696,
"eval_ppl_cds": 3.7443685934757203,
"eval_ppl_dig": 1.100676930462353,
"eval_ppl_exon": 3.289243520065538,
"eval_ppl_intron": 3.063192321562982,
"eval_ppl_nig": 2.893788578025708,
"eval_ppl_promoter": 3.3166590776504705,
"eval_ppl_utr": 3.4129745459503487,
"step": 4500,
"tokens_trained": 14.744270088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2794326241134752,
"grad_norm": 2.825514554977417,
"loss": 1.1776,
"loss_ce": 1.1078251600265503,
"loss_region": 0.06376127153635025,
"loss_total": 1.1715863943099976,
"lr": 0.0010616218750657124,
"router/selected_tokens_s0": 426.1875,
"router/selected_tokens_s1": 17.6875,
"step": 4510,
"tokens_trained": 14.777033928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2822695035460994,
"grad_norm": 3.562530279159546,
"loss": 1.1776,
"loss_ce": 1.1453254222869873,
"loss_region": 0.05877625197172165,
"loss_total": 1.2041016817092896,
"lr": 0.0010612149830818616,
"router/selected_tokens_s0": 604.375,
"router/selected_tokens_s1": 14.875,
"step": 4520,
"tokens_trained": 14.809799368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2851063829787235,
"grad_norm": 2.0739846229553223,
"loss": 1.1816,
"loss_ce": 1.167551040649414,
"loss_region": 0.05897127464413643,
"loss_total": 1.2265223264694214,
"lr": 0.0010608080910980105,
"router/selected_tokens_s0": 447.875,
"router/selected_tokens_s1": 12.9375,
"step": 4530,
"tokens_trained": 14.842564808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2879432624113476,
"grad_norm": 0.5496819019317627,
"loss": 1.1826,
"loss_ce": 1.048570156097412,
"loss_region": 0.05806339904665947,
"loss_total": 1.1066335439682007,
"lr": 0.0010604011991141595,
"router/selected_tokens_s0": 413.375,
"router/selected_tokens_s1": 11.3125,
"step": 4540,
"tokens_trained": 14.875330248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2907801418439715,
"grad_norm": 1.5685514211654663,
"loss": 1.1784,
"loss_ce": 1.1430702209472656,
"loss_region": 0.06285207718610764,
"loss_total": 1.205922245979309,
"lr": 0.0010599943071303085,
"router/selected_tokens_s0": 393.6875,
"router/selected_tokens_s1": 15.0,
"step": 4550,
"tokens_trained": 14.908095688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2936170212765958,
"grad_norm": 0.891741156578064,
"loss": 1.1716,
"loss_ce": 1.1201016902923584,
"loss_region": 0.05721219629049301,
"loss_total": 1.1773139238357544,
"lr": 0.0010595874151464574,
"router/selected_tokens_s0": 409.0625,
"router/selected_tokens_s1": 9.5625,
"step": 4560,
"tokens_trained": 14.940861128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2964539007092197,
"grad_norm": 1.012353777885437,
"loss": 1.1584,
"loss_ce": 1.009028673171997,
"loss_region": 0.06006960570812225,
"loss_total": 1.0690982341766357,
"lr": 0.0010591805231626064,
"router/selected_tokens_s0": 539.6875,
"router/selected_tokens_s1": 16.875,
"step": 4570,
"tokens_trained": 14.973625768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.299290780141844,
"grad_norm": 1.1502134799957275,
"loss": 1.1743,
"loss_ce": 1.073366641998291,
"loss_region": 0.06413622200489044,
"loss_total": 1.137502908706665,
"lr": 0.0010587736311787554,
"router/selected_tokens_s0": 393.625,
"router/selected_tokens_s1": 16.5625,
"step": 4580,
"tokens_trained": 15.006387136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.302127659574468,
"grad_norm": 1.2014880180358887,
"loss": 1.1678,
"loss_ce": 1.125981330871582,
"loss_region": 0.05629488825798035,
"loss_total": 1.1822762489318848,
"lr": 0.0010583667391949043,
"router/selected_tokens_s0": 466.1875,
"router/selected_tokens_s1": 9.3125,
"step": 4590,
"tokens_trained": 15.039152576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3049645390070923,
"grad_norm": 4.010960578918457,
"loss": 1.1722,
"loss_ce": 1.1003656387329102,
"loss_region": 0.05642012134194374,
"loss_total": 1.1567857265472412,
"lr": 0.0010579598472110533,
"router/selected_tokens_s0": 410.9375,
"router/selected_tokens_s1": 9.5625,
"step": 4600,
"tokens_trained": 15.071918016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3078014184397162,
"grad_norm": 2.229997158050537,
"loss": 1.1824,
"loss_ce": 1.129849910736084,
"loss_region": 0.06458568572998047,
"loss_total": 1.1944355964660645,
"lr": 0.0010575529552272023,
"router/selected_tokens_s0": 429.875,
"router/selected_tokens_s1": 18.375,
"step": 4610,
"tokens_trained": 15.104683456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3106382978723405,
"grad_norm": 2.0674681663513184,
"loss": 1.1844,
"loss_ce": 1.132249116897583,
"loss_region": 0.05796496197581291,
"loss_total": 1.1902140378952026,
"lr": 0.0010571460632433512,
"router/selected_tokens_s0": 403.8125,
"router/selected_tokens_s1": 10.25,
"step": 4620,
"tokens_trained": 15.137448096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3134751773049644,
"grad_norm": 1.2590811252593994,
"loss": 1.169,
"loss_ce": 1.0923088788986206,
"loss_region": 0.05617872625589371,
"loss_total": 1.1484875679016113,
"lr": 0.0010567391712595002,
"router/selected_tokens_s0": 477.125,
"router/selected_tokens_s1": 9.9375,
"step": 4630,
"tokens_trained": 15.170210824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3163120567375888,
"grad_norm": 1.314387559890747,
"loss": 1.1735,
"loss_ce": 1.1269707679748535,
"loss_region": 0.06321462988853455,
"loss_total": 1.1901854276657104,
"lr": 0.0010563322792756492,
"router/selected_tokens_s0": 412.375,
"router/selected_tokens_s1": 16.125,
"step": 4640,
"tokens_trained": 15.202976264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3191489361702127,
"grad_norm": 0.959001898765564,
"loss": 1.1731,
"loss_ce": 1.067009687423706,
"loss_region": 0.0584431029856205,
"loss_total": 1.1254527568817139,
"lr": 0.0010559253872917981,
"router/selected_tokens_s0": 434.125,
"router/selected_tokens_s1": 12.0625,
"step": 4650,
"tokens_trained": 15.235741704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.321985815602837,
"grad_norm": 0.6913428902626038,
"loss": 1.1645,
"loss_ce": 1.1260396242141724,
"loss_region": 0.05686100572347641,
"loss_total": 1.1829006671905518,
"lr": 0.001055518495307947,
"router/selected_tokens_s0": 452.375,
"router/selected_tokens_s1": 10.5625,
"step": 4660,
"tokens_trained": 15.268507144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.324822695035461,
"grad_norm": 1.705417275428772,
"loss": 1.1765,
"loss_ce": 1.1382602453231812,
"loss_region": 0.06457319855690002,
"loss_total": 1.2028334140777588,
"lr": 0.001055111603324096,
"router/selected_tokens_s0": 441.875,
"router/selected_tokens_s1": 19.3125,
"step": 4670,
"tokens_trained": 15.30127256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.327659574468085,
"grad_norm": 1.1720391511917114,
"loss": 1.17,
"loss_ce": 1.123241901397705,
"loss_region": 0.059922970831394196,
"loss_total": 1.1831648349761963,
"lr": 0.001054704711340245,
"router/selected_tokens_s0": 393.6875,
"router/selected_tokens_s1": 12.4375,
"step": 4680,
"tokens_trained": 15.334037984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3304964539007091,
"grad_norm": 1.7748150825500488,
"loss": 1.1743,
"loss_ce": 1.072164535522461,
"loss_region": 0.056693922728300095,
"loss_total": 1.1288584470748901,
"lr": 0.001054297819356394,
"router/selected_tokens_s0": 450.8125,
"router/selected_tokens_s1": 9.75,
"step": 4690,
"tokens_trained": 15.366803424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3333333333333333,
"grad_norm": 1.1712427139282227,
"loss": 1.1671,
"loss_ce": 1.1227179765701294,
"loss_region": 0.06404247134923935,
"loss_total": 1.186760425567627,
"lr": 0.0010538909273725432,
"router/selected_tokens_s0": 434.25,
"router/selected_tokens_s1": 17.875,
"step": 4700,
"tokens_trained": 15.399568864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3361702127659574,
"grad_norm": 1.1698198318481445,
"loss": 1.1689,
"loss_ce": 1.1782885789871216,
"loss_region": 0.059104278683662415,
"loss_total": 1.2373929023742676,
"lr": 0.0010534840353886921,
"router/selected_tokens_s0": 410.875,
"router/selected_tokens_s1": 12.3125,
"step": 4710,
"tokens_trained": 15.432334288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3390070921985815,
"grad_norm": 1.4182919263839722,
"loss": 1.1701,
"loss_ce": 0.9779119491577148,
"loss_region": 0.06040428206324577,
"loss_total": 1.038316249847412,
"lr": 0.001053077143404841,
"router/selected_tokens_s0": 482.375,
"router/selected_tokens_s1": 15.25,
"step": 4720,
"tokens_trained": 15.465099728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3418439716312056,
"grad_norm": 1.4712938070297241,
"loss": 1.1652,
"loss_ce": 1.099825143814087,
"loss_region": 0.06161494553089142,
"loss_total": 1.161440134048462,
"lr": 0.0010526702514209898,
"router/selected_tokens_s0": 408.625,
"router/selected_tokens_s1": 14.6875,
"step": 4730,
"tokens_trained": 15.497864368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3446808510638297,
"grad_norm": 1.376592755317688,
"loss": 1.1666,
"loss_ce": 1.1483793258666992,
"loss_region": 0.05899408087134361,
"loss_total": 1.2073733806610107,
"lr": 0.0010522633594371388,
"router/selected_tokens_s0": 450.25,
"router/selected_tokens_s1": 13.0,
"step": 4740,
"tokens_trained": 15.530629808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3475177304964538,
"grad_norm": 0.9113925695419312,
"loss": 1.1698,
"loss_ce": 1.167178988456726,
"loss_region": 0.06208512559533119,
"loss_total": 1.2292641401290894,
"lr": 0.0010518564674532878,
"router/selected_tokens_s0": 386.75,
"router/selected_tokens_s1": 14.5,
"step": 4750,
"tokens_trained": 15.563395248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.350354609929078,
"grad_norm": 1.6873319149017334,
"loss": 1.175,
"loss_ce": 1.144089937210083,
"loss_region": 0.05694330856204033,
"loss_total": 1.2010332345962524,
"lr": 0.0010514495754694367,
"router/selected_tokens_s0": 456.3125,
"router/selected_tokens_s1": 10.8125,
"step": 4760,
"tokens_trained": 15.596158264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.353191489361702,
"grad_norm": 0.7729793190956116,
"loss": 1.1667,
"loss_ce": 1.1456177234649658,
"loss_region": 0.06607680022716522,
"loss_total": 1.2116944789886475,
"lr": 0.001051042683485586,
"router/selected_tokens_s0": 388.75,
"router/selected_tokens_s1": 18.6875,
"step": 4770,
"tokens_trained": 15.628923704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3560283687943262,
"grad_norm": 2.3347153663635254,
"loss": 1.1724,
"loss_ce": 1.1867260932922363,
"loss_region": 0.05604035034775734,
"loss_total": 1.2427664995193481,
"lr": 0.0010506357915017349,
"router/selected_tokens_s0": 406.3125,
"router/selected_tokens_s1": 8.125,
"step": 4780,
"tokens_trained": 15.661689144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3588652482269503,
"grad_norm": 0.8608954548835754,
"loss": 1.1681,
"loss_ce": 1.1013946533203125,
"loss_region": 0.059269458055496216,
"loss_total": 1.1606640815734863,
"lr": 0.0010502288995178838,
"router/selected_tokens_s0": 420.75,
"router/selected_tokens_s1": 12.5,
"step": 4790,
"tokens_trained": 15.694454584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3617021276595744,
"grad_norm": 1.589377760887146,
"loss": 1.1774,
"loss_ce": 1.1131365299224854,
"loss_region": 0.06720637530088425,
"loss_total": 1.1803429126739502,
"lr": 0.0010498220075340328,
"router/selected_tokens_s0": 428.625,
"router/selected_tokens_s1": 21.5,
"step": 4800,
"tokens_trained": 15.727220024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3645390070921986,
"grad_norm": 1.1269258260726929,
"loss": 1.1722,
"loss_ce": 1.1789302825927734,
"loss_region": 0.0603567399084568,
"loss_total": 1.23928701877594,
"lr": 0.0010494151155501818,
"router/selected_tokens_s0": 408.0,
"router/selected_tokens_s1": 13.0625,
"step": 4810,
"tokens_trained": 15.759985464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3673758865248227,
"grad_norm": 0.5982851982116699,
"loss": 1.1615,
"loss_ce": 1.1606470346450806,
"loss_region": 0.057830557227134705,
"loss_total": 1.2184776067733765,
"lr": 0.0010490082235663307,
"router/selected_tokens_s0": 335.8125,
"router/selected_tokens_s1": 8.375,
"step": 4820,
"tokens_trained": 15.792750904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3702127659574468,
"grad_norm": 0.7754488587379456,
"loss": 1.1694,
"loss_ce": 1.076349139213562,
"loss_region": 0.05904084071516991,
"loss_total": 1.1353899240493774,
"lr": 0.0010486013315824797,
"router/selected_tokens_s0": 440.625,
"router/selected_tokens_s1": 13.1875,
"step": 4830,
"tokens_trained": 15.825515544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.373049645390071,
"grad_norm": 0.8074977993965149,
"loss": 1.1673,
"loss_ce": 1.1052080392837524,
"loss_region": 0.05970120057463646,
"loss_total": 1.1649092435836792,
"lr": 0.0010481944395986287,
"router/selected_tokens_s0": 442.0,
"router/selected_tokens_s1": 13.6875,
"step": 4840,
"tokens_trained": 15.858280984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.375886524822695,
"grad_norm": 1.8432601690292358,
"loss": 1.163,
"loss_ce": 1.1196966171264648,
"loss_region": 0.05893434211611748,
"loss_total": 1.1786309480667114,
"lr": 0.0010477875476147776,
"router/selected_tokens_s0": 467.8125,
"router/selected_tokens_s1": 13.25,
"step": 4850,
"tokens_trained": 15.891045624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3787234042553191,
"grad_norm": 0.80079185962677,
"loss": 1.1646,
"loss_ce": 1.0457513332366943,
"loss_region": 0.06003762036561966,
"loss_total": 1.1057889461517334,
"lr": 0.0010473806556309266,
"router/selected_tokens_s0": 355.25,
"router/selected_tokens_s1": 11.25,
"step": 4860,
"tokens_trained": 15.923810264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3815602836879433,
"grad_norm": 1.3119624853134155,
"loss": 1.1626,
"loss_ce": 1.0813933610916138,
"loss_region": 0.061243828386068344,
"loss_total": 1.1426371335983276,
"lr": 0.0010469737636470756,
"router/selected_tokens_s0": 470.3125,
"router/selected_tokens_s1": 16.0,
"step": 4870,
"tokens_trained": 15.956575704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3843971631205674,
"grad_norm": 1.396918773651123,
"loss": 1.1716,
"loss_ce": 1.0860676765441895,
"loss_region": 0.05864456295967102,
"loss_total": 1.144712209701538,
"lr": 0.0010465668716632245,
"router/selected_tokens_s0": 451.875,
"router/selected_tokens_s1": 12.375,
"step": 4880,
"tokens_trained": 15.989339352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3872340425531915,
"grad_norm": 1.2318918704986572,
"loss": 1.1647,
"loss_ce": 1.11076819896698,
"loss_region": 0.0610792338848114,
"loss_total": 1.1718474626541138,
"lr": 0.0010461599796793735,
"router/selected_tokens_s0": 357.1875,
"router/selected_tokens_s1": 12.25,
"step": 4890,
"tokens_trained": 16.022103992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3900709219858156,
"grad_norm": 1.2649383544921875,
"loss": 1.1718,
"loss_ce": 1.0666271448135376,
"loss_region": 0.058861564844846725,
"loss_total": 1.1254887580871582,
"lr": 0.0010457530876955225,
"router/selected_tokens_s0": 418.8125,
"router/selected_tokens_s1": 12.0625,
"step": 4900,
"tokens_trained": 16.054869432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3929078014184397,
"grad_norm": 1.6673067808151245,
"loss": 1.163,
"loss_ce": 1.1077296733856201,
"loss_region": 0.06258165091276169,
"loss_total": 1.1703113317489624,
"lr": 0.0010453461957116714,
"router/selected_tokens_s0": 439.5,
"router/selected_tokens_s1": 16.8125,
"step": 4910,
"tokens_trained": 16.087634872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3957446808510638,
"grad_norm": 1.2215776443481445,
"loss": 1.1713,
"loss_ce": 1.0790401697158813,
"loss_region": 0.05825230851769447,
"loss_total": 1.137292504310608,
"lr": 0.0010449393037278204,
"router/selected_tokens_s0": 470.5625,
"router/selected_tokens_s1": 12.375,
"step": 4920,
"tokens_trained": 16.120400312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.398581560283688,
"grad_norm": 0.9133660793304443,
"loss": 1.1672,
"loss_ce": 1.1354037523269653,
"loss_region": 0.062443241477012634,
"loss_total": 1.1978470087051392,
"lr": 0.0010445324117439694,
"router/selected_tokens_s0": 455.5625,
"router/selected_tokens_s1": 17.1875,
"step": 4930,
"tokens_trained": 16.153164952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.401418439716312,
"grad_norm": 0.7142453789710999,
"loss": 1.1637,
"loss_ce": 1.0729459524154663,
"loss_region": 0.05855097249150276,
"loss_total": 1.1314969062805176,
"lr": 0.0010441255197601183,
"router/selected_tokens_s0": 483.25,
"router/selected_tokens_s1": 13.0,
"step": 4940,
"tokens_trained": 16.185929592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4042553191489362,
"grad_norm": 1.346866488456726,
"loss": 1.1688,
"loss_ce": 1.1217612028121948,
"loss_region": 0.061914537101984024,
"loss_total": 1.183675765991211,
"lr": 0.0010437186277762675,
"router/selected_tokens_s0": 419.25,
"router/selected_tokens_s1": 15.4375,
"step": 4950,
"tokens_trained": 16.218695032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4070921985815603,
"grad_norm": 0.8455023765563965,
"loss": 1.1644,
"loss_ce": 0.9533401727676392,
"loss_region": 0.057561516761779785,
"loss_total": 1.010901689529419,
"lr": 0.0010433117357924165,
"router/selected_tokens_s0": 444.9375,
"router/selected_tokens_s1": 10.75,
"step": 4960,
"tokens_trained": 16.251457848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4099290780141844,
"grad_norm": 0.719833254814148,
"loss": 1.1677,
"loss_ce": 0.9225043654441833,
"loss_region": 0.061203230172395706,
"loss_total": 0.98370760679245,
"lr": 0.0010429048438085654,
"router/selected_tokens_s0": 442.375,
"router/selected_tokens_s1": 15.0,
"step": 4970,
"tokens_trained": 16.284222488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4127659574468086,
"grad_norm": 1.3556922674179077,
"loss": 1.1647,
"loss_ce": 1.0813281536102295,
"loss_region": 0.05944563448429108,
"loss_total": 1.1407737731933594,
"lr": 0.0010424979518247142,
"router/selected_tokens_s0": 478.5,
"router/selected_tokens_s1": 14.125,
"step": 4980,
"tokens_trained": 16.316987928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4156028368794327,
"grad_norm": 1.9594775438308716,
"loss": 1.1697,
"loss_ce": 1.1046741008758545,
"loss_region": 0.061166729778051376,
"loss_total": 1.1658408641815186,
"lr": 0.0010420910598408631,
"router/selected_tokens_s0": 412.1875,
"router/selected_tokens_s1": 14.25,
"step": 4990,
"tokens_trained": 16.349753368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4184397163120568,
"grad_norm": 1.9190337657928467,
"loss": 1.1659,
"loss_ce": 0.9583069682121277,
"loss_region": 0.05831551179289818,
"loss_total": 1.0166224241256714,
"lr": 0.0010416841678570121,
"router/selected_tokens_s0": 430.125,
"router/selected_tokens_s1": 12.3125,
"step": 5000,
"tokens_trained": 16.382518808
},
{
"epoch": 1.4184397163120568,
"eval_ppl": 3.0297582706547788,
"eval_runtime": 2.0152,
"step": 5000,
"tokens_trained": 16.382518808
},
{
"epoch": 1.4184397163120568,
"eval_F": 0.0008749409770464404,
"eval_F_cds": 0.0007276974216153086,
"eval_F_dig": 0.0004297210719587468,
"eval_F_exon": 0.0008561992905777307,
"eval_F_intron": 0.0009058665497180045,
"eval_F_nig": 0.0008965739307150804,
"eval_F_promoter": 0.0007803781609921462,
"eval_F_utr": 0.0008526875646177295,
"eval_G": 0.015531097207779055,
"eval_G_cds": 0.013802124275671549,
"eval_G_dig": 0.0182552103679975,
"eval_G_exon": 0.01449494753231133,
"eval_G_intron": 0.01584569984851749,
"eval_G_nig": 0.016464907279915203,
"eval_G_promoter": 0.013578435037466047,
"eval_G_utr": 0.014395785092090257,
"eval_avg_bp_per_token": 1142.934239262315,
"eval_bp_per_token/cds": 1374.1975308641975,
"eval_bp_per_token/dig": 2327.090909090909,
"eval_bp_per_token/exon": 1167.952380952381,
"eval_bp_per_token/intron": 1103.9153618281846,
"eval_bp_per_token/nig": 1115.3569892473117,
"eval_bp_per_token/promoter": 1281.4300168634063,
"eval_bp_per_token/utr": 1172.7625,
"eval_ppl_cds": 3.742546850083132,
"eval_ppl_dig": 1.1138565762627513,
"eval_ppl_exon": 3.2794754104779216,
"eval_ppl_intron": 3.05261384850238,
"eval_ppl_nig": 2.8751225098839135,
"eval_ppl_promoter": 3.309446838442905,
"eval_ppl_utr": 3.411906653203143,
"step": 5000,
"tokens_trained": 16.382518808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.421276595744681,
"grad_norm": 1.2634458541870117,
"loss": 1.1716,
"loss_ce": 1.0555835962295532,
"loss_region": 0.0644194483757019,
"loss_total": 1.1200029850006104,
"lr": 0.001041277275873161,
"router/selected_tokens_s0": 485.5625,
"router/selected_tokens_s1": 20.5,
"step": 5010,
"tokens_trained": 16.415284248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.424113475177305,
"grad_norm": 1.134238839149475,
"loss": 1.1675,
"loss_ce": 1.0413823127746582,
"loss_region": 0.05861315503716469,
"loss_total": 1.099995493888855,
"lr": 0.0010408703838893103,
"router/selected_tokens_s0": 453.25,
"router/selected_tokens_s1": 11.875,
"step": 5020,
"tokens_trained": 16.448049688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4269503546099291,
"grad_norm": 0.6608848571777344,
"loss": 1.16,
"loss_ce": 1.0865141153335571,
"loss_region": 0.06405461579561234,
"loss_total": 1.1505687236785889,
"lr": 0.0010404634919054592,
"router/selected_tokens_s0": 415.3125,
"router/selected_tokens_s1": 17.6875,
"step": 5030,
"tokens_trained": 16.480814968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4297872340425533,
"grad_norm": 1.7596572637557983,
"loss": 1.1605,
"loss_ce": 1.080395221710205,
"loss_region": 0.05989512428641319,
"loss_total": 1.140290379524231,
"lr": 0.0010400565999216082,
"router/selected_tokens_s0": 458.25,
"router/selected_tokens_s1": 14.125,
"step": 5040,
"tokens_trained": 16.513576176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4326241134751774,
"grad_norm": 1.449523687362671,
"loss": 1.1587,
"loss_ce": 1.1526217460632324,
"loss_region": 0.05976712331175804,
"loss_total": 1.2123888731002808,
"lr": 0.0010396497079377572,
"router/selected_tokens_s0": 470.0625,
"router/selected_tokens_s1": 14.4375,
"step": 5050,
"tokens_trained": 16.546341616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4354609929078015,
"grad_norm": 1.0609499216079712,
"loss": 1.17,
"loss_ce": 1.1456844806671143,
"loss_region": 0.060984060168266296,
"loss_total": 1.206668496131897,
"lr": 0.0010392428159539061,
"router/selected_tokens_s0": 421.9375,
"router/selected_tokens_s1": 14.5,
"step": 5060,
"tokens_trained": 16.579105456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4382978723404256,
"grad_norm": 1.4889984130859375,
"loss": 1.1639,
"loss_ce": 1.1069124937057495,
"loss_region": 0.0588313490152359,
"loss_total": 1.1657438278198242,
"lr": 0.001038835923970055,
"router/selected_tokens_s0": 412.625,
"router/selected_tokens_s1": 12.0,
"step": 5070,
"tokens_trained": 16.611870896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4411347517730497,
"grad_norm": 0.7745299935340881,
"loss": 1.1727,
"loss_ce": 1.1384263038635254,
"loss_region": 0.06151129677891731,
"loss_total": 1.1999375820159912,
"lr": 0.001038429031986204,
"router/selected_tokens_s0": 441.625,
"router/selected_tokens_s1": 15.9375,
"step": 5080,
"tokens_trained": 16.644635536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4439716312056738,
"grad_norm": 0.3887619376182556,
"loss": 1.1641,
"loss_ce": 1.0129387378692627,
"loss_region": 0.057277847081422806,
"loss_total": 1.0702165365219116,
"lr": 0.001038022140002353,
"router/selected_tokens_s0": 449.75,
"router/selected_tokens_s1": 10.625,
"step": 5090,
"tokens_trained": 16.67739828
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4468085106382977,
"grad_norm": 0.9931978583335876,
"loss": 1.1593,
"loss_ce": 1.1114816665649414,
"loss_region": 0.0629933550953865,
"loss_total": 1.174475073814392,
"lr": 0.001037615248018502,
"router/selected_tokens_s0": 430.25,
"router/selected_tokens_s1": 16.6875,
"step": 5100,
"tokens_trained": 16.71016372
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.449645390070922,
"grad_norm": 1.7544564008712769,
"loss": 1.1669,
"loss_ce": 1.1303014755249023,
"loss_region": 0.05773321911692619,
"loss_total": 1.1880346536636353,
"lr": 0.001037208356034651,
"router/selected_tokens_s0": 436.8125,
"router/selected_tokens_s1": 10.875,
"step": 5110,
"tokens_trained": 16.74292916
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.452482269503546,
"grad_norm": 0.46224844455718994,
"loss": 1.1623,
"loss_ce": 1.22366201877594,
"loss_region": 0.06073080375790596,
"loss_total": 1.2843928337097168,
"lr": 0.0010368014640508,
"router/selected_tokens_s0": 371.875,
"router/selected_tokens_s1": 12.625,
"step": 5120,
"tokens_trained": 16.775691312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4553191489361703,
"grad_norm": 0.4505470097064972,
"loss": 1.1699,
"loss_ce": 1.0685856342315674,
"loss_region": 0.06006813421845436,
"loss_total": 1.1286537647247314,
"lr": 0.0010363945720669489,
"router/selected_tokens_s0": 453.3125,
"router/selected_tokens_s1": 14.3125,
"step": 5130,
"tokens_trained": 16.808456752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4581560283687942,
"grad_norm": 0.443447470664978,
"loss": 1.1616,
"loss_ce": 1.0702182054519653,
"loss_region": 0.057352010160684586,
"loss_total": 1.1275702714920044,
"lr": 0.0010359876800830978,
"router/selected_tokens_s0": 478.625,
"router/selected_tokens_s1": 11.5625,
"step": 5140,
"tokens_trained": 16.841222192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4609929078014185,
"grad_norm": 1.0394787788391113,
"loss": 1.1641,
"loss_ce": 1.0516167879104614,
"loss_region": 0.06636694073677063,
"loss_total": 1.1179836988449097,
"lr": 0.0010355807880992468,
"router/selected_tokens_s0": 492.0625,
"router/selected_tokens_s1": 23.3125,
"step": 5150,
"tokens_trained": 16.873987632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4638297872340424,
"grad_norm": 0.7827674150466919,
"loss": 1.1617,
"loss_ce": 1.1885493993759155,
"loss_region": 0.057987358421087265,
"loss_total": 1.2465367317199707,
"lr": 0.0010351738961153958,
"router/selected_tokens_s0": 357.6875,
"router/selected_tokens_s1": 8.625,
"step": 5160,
"tokens_trained": 16.906753072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4666666666666668,
"grad_norm": 0.9744030237197876,
"loss": 1.1617,
"loss_ce": 1.0603646039962769,
"loss_region": 0.05650093033909798,
"loss_total": 1.1168655157089233,
"lr": 0.0010347670041315447,
"router/selected_tokens_s0": 504.5625,
"router/selected_tokens_s1": 10.3125,
"step": 5170,
"tokens_trained": 16.939515096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4695035460992907,
"grad_norm": 0.2740679383277893,
"loss": 1.1609,
"loss_ce": 1.0844225883483887,
"loss_region": 0.06521714478731155,
"loss_total": 1.1496397256851196,
"lr": 0.0010343601121476937,
"router/selected_tokens_s0": 428.0,
"router/selected_tokens_s1": 19.0625,
"step": 5180,
"tokens_trained": 16.972279352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.472340425531915,
"grad_norm": 1.3795894384384155,
"loss": 1.1686,
"loss_ce": 1.124297857284546,
"loss_region": 0.05923352763056755,
"loss_total": 1.183531403541565,
"lr": 0.0010339532201638427,
"router/selected_tokens_s0": 442.0,
"router/selected_tokens_s1": 13.0,
"step": 5190,
"tokens_trained": 17.005044792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.475177304964539,
"grad_norm": 0.8263188004493713,
"loss": 1.1675,
"loss_ce": 1.0006603002548218,
"loss_region": 0.06344455480575562,
"loss_total": 1.0641047954559326,
"lr": 0.0010335463281799918,
"router/selected_tokens_s0": 427.125,
"router/selected_tokens_s1": 17.3125,
"step": 5200,
"tokens_trained": 17.037810232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4780141843971633,
"grad_norm": 0.5774252414703369,
"loss": 1.1614,
"loss_ce": 1.1466084718704224,
"loss_region": 0.05995073914527893,
"loss_total": 1.206559181213379,
"lr": 0.0010331394361961408,
"router/selected_tokens_s0": 391.25,
"router/selected_tokens_s1": 12.3125,
"step": 5210,
"tokens_trained": 17.070575672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4808510638297872,
"grad_norm": 1.3741319179534912,
"loss": 1.1559,
"loss_ce": 1.1331387758255005,
"loss_region": 0.059787504374980927,
"loss_total": 1.192926287651062,
"lr": 0.0010327325442122898,
"router/selected_tokens_s0": 431.9375,
"router/selected_tokens_s1": 13.5625,
"step": 5220,
"tokens_trained": 17.103341112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4836879432624113,
"grad_norm": 0.9346311092376709,
"loss": 1.1677,
"loss_ce": 1.1160879135131836,
"loss_region": 0.05967224761843681,
"loss_total": 1.1757601499557495,
"lr": 0.0010323256522284385,
"router/selected_tokens_s0": 423.9375,
"router/selected_tokens_s1": 13.0625,
"step": 5230,
"tokens_trained": 17.136106552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4865248226950354,
"grad_norm": 0.9840303659439087,
"loss": 1.1563,
"loss_ce": 1.1366236209869385,
"loss_region": 0.057842716574668884,
"loss_total": 1.1944663524627686,
"lr": 0.0010319187602445875,
"router/selected_tokens_s0": 437.0625,
"router/selected_tokens_s1": 11.1875,
"step": 5240,
"tokens_trained": 17.168867192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4893617021276595,
"grad_norm": 0.6291745901107788,
"loss": 1.1678,
"loss_ce": 1.1215194463729858,
"loss_region": 0.061599425971508026,
"loss_total": 1.1831188201904297,
"lr": 0.0010315118682607365,
"router/selected_tokens_s0": 442.25,
"router/selected_tokens_s1": 15.9375,
"step": 5250,
"tokens_trained": 17.201632632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4921985815602836,
"grad_norm": 0.9545523524284363,
"loss": 1.1654,
"loss_ce": 1.0638751983642578,
"loss_region": 0.056087564677000046,
"loss_total": 1.1199628114700317,
"lr": 0.0010311049762768854,
"router/selected_tokens_s0": 481.5625,
"router/selected_tokens_s1": 9.5625,
"step": 5260,
"tokens_trained": 17.234398072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4950354609929077,
"grad_norm": 1.1328867673873901,
"loss": 1.1627,
"loss_ce": 1.1201285123825073,
"loss_region": 0.06611510366201401,
"loss_total": 1.1862436532974243,
"lr": 0.0010306980842930346,
"router/selected_tokens_s0": 423.25,
"router/selected_tokens_s1": 20.3125,
"step": 5270,
"tokens_trained": 17.26716272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4978723404255319,
"grad_norm": 1.4490420818328857,
"loss": 1.1635,
"loss_ce": 1.0298516750335693,
"loss_region": 0.05839422717690468,
"loss_total": 1.0882458686828613,
"lr": 0.0010302911923091836,
"router/selected_tokens_s0": 565.0625,
"router/selected_tokens_s1": 13.6875,
"step": 5280,
"tokens_trained": 17.29992816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.500709219858156,
"grad_norm": 0.5782109498977661,
"loss": 1.167,
"loss_ce": 1.129813313484192,
"loss_region": 0.05724978446960449,
"loss_total": 1.1870630979537964,
"lr": 0.0010298843003253325,
"router/selected_tokens_s0": 409.9375,
"router/selected_tokens_s1": 10.0,
"step": 5290,
"tokens_trained": 17.3326928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.50354609929078,
"grad_norm": 1.1590781211853027,
"loss": 1.1645,
"loss_ce": 1.1144260168075562,
"loss_region": 0.06544779241085052,
"loss_total": 1.1798738241195679,
"lr": 0.0010294774083414815,
"router/selected_tokens_s0": 403.5625,
"router/selected_tokens_s1": 18.1875,
"step": 5300,
"tokens_trained": 17.36545824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5063829787234042,
"grad_norm": 1.357226848602295,
"loss": 1.1685,
"loss_ce": 1.1005100011825562,
"loss_region": 0.05805032700300217,
"loss_total": 1.1585602760314941,
"lr": 0.0010290705163576305,
"router/selected_tokens_s0": 439.5,
"router/selected_tokens_s1": 10.875,
"step": 5310,
"tokens_trained": 17.39822368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5092198581560283,
"grad_norm": 0.7000742554664612,
"loss": 1.1605,
"loss_ce": 1.1245887279510498,
"loss_region": 0.054603416472673416,
"loss_total": 1.1791921854019165,
"lr": 0.0010286636243737794,
"router/selected_tokens_s0": 480.5,
"router/selected_tokens_s1": 7.9375,
"step": 5320,
"tokens_trained": 17.43098912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5120567375886524,
"grad_norm": 1.1702980995178223,
"loss": 1.1649,
"loss_ce": 1.088313341140747,
"loss_region": 0.06897804886102676,
"loss_total": 1.1572914123535156,
"lr": 0.0010282567323899284,
"router/selected_tokens_s0": 401.875,
"router/selected_tokens_s1": 21.875,
"step": 5330,
"tokens_trained": 17.46375296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5148936170212766,
"grad_norm": 1.2126129865646362,
"loss": 1.1653,
"loss_ce": 1.1331862211227417,
"loss_region": 0.06121586263179779,
"loss_total": 1.1944020986557007,
"lr": 0.0010278498404060774,
"router/selected_tokens_s0": 462.125,
"router/selected_tokens_s1": 16.0625,
"step": 5340,
"tokens_trained": 17.4965184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5177304964539007,
"grad_norm": 0.9559081792831421,
"loss": 1.1667,
"loss_ce": 1.076651930809021,
"loss_region": 0.05728324502706528,
"loss_total": 1.1339352130889893,
"lr": 0.0010274429484222263,
"router/selected_tokens_s0": 429.375,
"router/selected_tokens_s1": 10.25,
"step": 5350,
"tokens_trained": 17.52928304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5205673758865248,
"grad_norm": 1.1095921993255615,
"loss": 1.163,
"loss_ce": 1.112319827079773,
"loss_region": 0.06240734085440636,
"loss_total": 1.174727201461792,
"lr": 0.0010270360564383753,
"router/selected_tokens_s0": 468.75,
"router/selected_tokens_s1": 17.25,
"step": 5360,
"tokens_trained": 17.56204848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.523404255319149,
"grad_norm": 0.711679995059967,
"loss": 1.1636,
"loss_ce": 1.0815953016281128,
"loss_region": 0.05967709422111511,
"loss_total": 1.1412724256515503,
"lr": 0.0010266291644545243,
"router/selected_tokens_s0": 441.1875,
"router/selected_tokens_s1": 13.375,
"step": 5370,
"tokens_trained": 17.59481392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.526241134751773,
"grad_norm": 1.6682300567626953,
"loss": 1.16,
"loss_ce": 1.119455099105835,
"loss_region": 0.05931823328137398,
"loss_total": 1.178773283958435,
"lr": 0.0010262222724706732,
"router/selected_tokens_s0": 456.625,
"router/selected_tokens_s1": 13.75,
"step": 5380,
"tokens_trained": 17.62757936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5290780141843971,
"grad_norm": 0.7429375052452087,
"loss": 1.1681,
"loss_ce": 1.1057552099227905,
"loss_region": 0.06057373434305191,
"loss_total": 1.1663289070129395,
"lr": 0.0010258153804868222,
"router/selected_tokens_s0": 455.625,
"router/selected_tokens_s1": 14.6875,
"step": 5390,
"tokens_trained": 17.6603448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5319148936170213,
"grad_norm": 1.3467381000518799,
"loss": 1.163,
"loss_ce": 1.1104803085327148,
"loss_region": 0.05636877194046974,
"loss_total": 1.166849136352539,
"lr": 0.0010254084885029712,
"router/selected_tokens_s0": 436.8125,
"router/selected_tokens_s1": 9.375,
"step": 5400,
"tokens_trained": 17.69310944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5347517730496454,
"grad_norm": 0.7579314708709717,
"loss": 1.1633,
"loss_ce": 1.1696826219558716,
"loss_region": 0.06521567702293396,
"loss_total": 1.234898328781128,
"lr": 0.0010250015965191201,
"router/selected_tokens_s0": 378.1875,
"router/selected_tokens_s1": 17.0,
"step": 5410,
"tokens_trained": 17.72587488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5375886524822695,
"grad_norm": 1.506962776184082,
"loss": 1.1663,
"loss_ce": 1.0815457105636597,
"loss_region": 0.0584101639688015,
"loss_total": 1.1399558782577515,
"lr": 0.001024594704535269,
"router/selected_tokens_s0": 421.25,
"router/selected_tokens_s1": 11.375,
"step": 5420,
"tokens_trained": 17.75863776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5404255319148936,
"grad_norm": 1.0177658796310425,
"loss": 1.1602,
"loss_ce": 1.1353583335876465,
"loss_region": 0.05683788284659386,
"loss_total": 1.192196249961853,
"lr": 0.001024187812551418,
"router/selected_tokens_s0": 431.375,
"router/selected_tokens_s1": 10.0625,
"step": 5430,
"tokens_trained": 17.7914032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5432624113475177,
"grad_norm": 1.3501242399215698,
"loss": 1.1612,
"loss_ce": 1.0791661739349365,
"loss_region": 0.06427235901355743,
"loss_total": 1.1434385776519775,
"lr": 0.001023780920567567,
"router/selected_tokens_s0": 431.6875,
"router/selected_tokens_s1": 18.8125,
"step": 5440,
"tokens_trained": 17.824165472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5460992907801419,
"grad_norm": 0.5377880930900574,
"loss": 1.1609,
"loss_ce": 1.1013327836990356,
"loss_region": 0.05677126348018646,
"loss_total": 1.1581040620803833,
"lr": 0.0010233740285837162,
"router/selected_tokens_s0": 467.1875,
"router/selected_tokens_s1": 10.125,
"step": 5450,
"tokens_trained": 17.856930912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.548936170212766,
"grad_norm": 0.5063560605049133,
"loss": 1.1603,
"loss_ce": 1.0957387685775757,
"loss_region": 0.057693321257829666,
"loss_total": 1.1534321308135986,
"lr": 0.0010229671365998652,
"router/selected_tokens_s0": 456.125,
"router/selected_tokens_s1": 11.6875,
"step": 5460,
"tokens_trained": 17.88969364
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.55177304964539,
"grad_norm": 1.4588333368301392,
"loss": 1.1709,
"loss_ce": 1.1442478895187378,
"loss_region": 0.06362947821617126,
"loss_total": 1.2078773975372314,
"lr": 0.0010225602446160141,
"router/selected_tokens_s0": 434.8125,
"router/selected_tokens_s1": 18.0625,
"step": 5470,
"tokens_trained": 17.92245908
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5546099290780142,
"grad_norm": 1.0143531560897827,
"loss": 1.1552,
"loss_ce": 1.123971700668335,
"loss_region": 0.05629895254969597,
"loss_total": 1.1802706718444824,
"lr": 0.0010221533526321629,
"router/selected_tokens_s0": 445.1875,
"router/selected_tokens_s1": 9.5625,
"step": 5480,
"tokens_trained": 17.95522452
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5574468085106383,
"grad_norm": 0.7020089030265808,
"loss": 1.1643,
"loss_ce": 1.1418280601501465,
"loss_region": 0.06544672697782516,
"loss_total": 1.2072747945785522,
"lr": 0.0010217464606483118,
"router/selected_tokens_s0": 442.6875,
"router/selected_tokens_s1": 20.5625,
"step": 5490,
"tokens_trained": 17.98798996
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5602836879432624,
"grad_norm": 0.9480003714561462,
"loss": 1.1674,
"loss_ce": 1.1325876712799072,
"loss_region": 0.057331230491399765,
"loss_total": 1.189918875694275,
"lr": 0.0010213395686644608,
"router/selected_tokens_s0": 416.5625,
"router/selected_tokens_s1": 9.375,
"step": 5500,
"tokens_trained": 18.0207554
},
{
"epoch": 1.5602836879432624,
"eval_ppl": 3.016075433537383,
"eval_runtime": 2.0117,
"step": 5500,
"tokens_trained": 18.0207554
},
{
"epoch": 1.5602836879432624,
"eval_F": 0.000746067118015334,
"eval_F_cds": 0.0009792471476057856,
"eval_F_dig": 0.0005859832799437456,
"eval_F_exon": 0.0006795232464902625,
"eval_F_intron": 0.0007563583167979783,
"eval_F_nig": 0.0008204133495037994,
"eval_F_promoter": 0.0005987724506769419,
"eval_F_utr": 0.0006501742680210188,
"eval_G": 0.012171905510010335,
"eval_G_cds": 0.010553139177746832,
"eval_G_dig": 0.017514414578287365,
"eval_G_exon": 0.011079122200364224,
"eval_G_intron": 0.012297019961888818,
"eval_G_nig": 0.013013662524390667,
"eval_G_promoter": 0.0109304193923973,
"eval_G_utr": 0.01076197459790452,
"eval_avg_bp_per_token": 1340.3619806488332,
"eval_bp_per_token/cds": 1021.1926605504588,
"eval_bp_per_token/dig": 1706.5333333333333,
"eval_bp_per_token/exon": 1471.62,
"eval_bp_per_token/intron": 1322.1246832235174,
"eval_bp_per_token/nig": 1218.8977673325498,
"eval_bp_per_token/promoter": 1670.0835164835164,
"eval_bp_per_token/utr": 1538.049180327869,
"eval_ppl_cds": 3.7454442422362386,
"eval_ppl_dig": 1.1207937865323054,
"eval_ppl_exon": 3.2698117991844704,
"eval_ppl_intron": 3.037524573763349,
"eval_ppl_nig": 2.8559054717599377,
"eval_ppl_promoter": 3.304611442870541,
"eval_ppl_utr": 3.4102085366729313,
"step": 5500,
"tokens_trained": 18.0207554
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5631205673758866,
"grad_norm": 1.2048259973526,
"loss": 1.1553,
"loss_ce": 1.1304912567138672,
"loss_region": 0.05862328037619591,
"loss_total": 1.1891145706176758,
"lr": 0.0010209326766806098,
"router/selected_tokens_s0": 446.1875,
"router/selected_tokens_s1": 12.5625,
"step": 5510,
"tokens_trained": 18.05352084
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5659574468085107,
"grad_norm": 0.827768087387085,
"loss": 1.1641,
"loss_ce": 1.0551944971084595,
"loss_region": 0.0649186372756958,
"loss_total": 1.1201131343841553,
"lr": 0.001020525784696759,
"router/selected_tokens_s0": 453.125,
"router/selected_tokens_s1": 20.1875,
"step": 5520,
"tokens_trained": 18.08628548
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5687943262411348,
"grad_norm": 0.8574738502502441,
"loss": 1.1586,
"loss_ce": 1.1029974222183228,
"loss_region": 0.05974757671356201,
"loss_total": 1.1627449989318848,
"lr": 0.001020118892712908,
"router/selected_tokens_s0": 400.1875,
"router/selected_tokens_s1": 12.0,
"step": 5530,
"tokens_trained": 18.11905092
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.571631205673759,
"grad_norm": 0.4658717215061188,
"loss": 1.1563,
"loss_ce": 1.116166591644287,
"loss_region": 0.05434912443161011,
"loss_total": 1.170515775680542,
"lr": 0.0010197120007290569,
"router/selected_tokens_s0": 510.4375,
"router/selected_tokens_s1": 7.8125,
"step": 5540,
"tokens_trained": 18.15181636
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.574468085106383,
"grad_norm": 0.6120085716247559,
"loss": 1.1627,
"loss_ce": 1.064978003501892,
"loss_region": 0.06429442018270493,
"loss_total": 1.1292724609375,
"lr": 0.0010193051087452058,
"router/selected_tokens_s0": 464.5625,
"router/selected_tokens_s1": 19.75,
"step": 5550,
"tokens_trained": 18.1845818
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5773049645390071,
"grad_norm": 1.1164491176605225,
"loss": 1.162,
"loss_ce": 1.0743745565414429,
"loss_region": 0.059213023632764816,
"loss_total": 1.1335875988006592,
"lr": 0.0010188982167613548,
"router/selected_tokens_s0": 455.0625,
"router/selected_tokens_s1": 13.4375,
"step": 5560,
"tokens_trained": 18.2173404
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.580141843971631,
"grad_norm": 0.7541922926902771,
"loss": 1.1649,
"loss_ce": 0.9796167612075806,
"loss_region": 0.060397908091545105,
"loss_total": 1.040014624595642,
"lr": 0.0010184913247775038,
"router/selected_tokens_s0": 482.5625,
"router/selected_tokens_s1": 16.5625,
"step": 5570,
"tokens_trained": 18.25010584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5829787234042554,
"grad_norm": 0.6305317878723145,
"loss": 1.1622,
"loss_ce": 1.0828227996826172,
"loss_region": 0.06084812805056572,
"loss_total": 1.143670916557312,
"lr": 0.0010180844327936527,
"router/selected_tokens_s0": 499.9375,
"router/selected_tokens_s1": 16.375,
"step": 5580,
"tokens_trained": 18.28287128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5858156028368793,
"grad_norm": 1.2468684911727905,
"loss": 1.1579,
"loss_ce": 1.1797648668289185,
"loss_region": 0.06281707435846329,
"loss_total": 1.2425819635391235,
"lr": 0.0010176775408098017,
"router/selected_tokens_s0": 443.6875,
"router/selected_tokens_s1": 17.4375,
"step": 5590,
"tokens_trained": 18.31563672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5886524822695036,
"grad_norm": 0.6272963285446167,
"loss": 1.1579,
"loss_ce": 1.1127893924713135,
"loss_region": 0.05846928060054779,
"loss_total": 1.1712586879730225,
"lr": 0.0010172706488259507,
"router/selected_tokens_s0": 441.0,
"router/selected_tokens_s1": 12.1875,
"step": 5600,
"tokens_trained": 18.34840216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5914893617021275,
"grad_norm": 0.9740651249885559,
"loss": 1.1603,
"loss_ce": 1.0885473489761353,
"loss_region": 0.06197122111916542,
"loss_total": 1.150518536567688,
"lr": 0.0010168637568420996,
"router/selected_tokens_s0": 472.875,
"router/selected_tokens_s1": 17.3125,
"step": 5610,
"tokens_trained": 18.38116752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5943262411347519,
"grad_norm": 0.9614301919937134,
"loss": 1.1543,
"loss_ce": 1.0123392343521118,
"loss_region": 0.05750362575054169,
"loss_total": 1.06984281539917,
"lr": 0.0010164568648582486,
"router/selected_tokens_s0": 494.625,
"router/selected_tokens_s1": 11.9375,
"step": 5620,
"tokens_trained": 18.41393296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5971631205673757,
"grad_norm": 0.8865266442298889,
"loss": 1.1602,
"loss_ce": 1.1279913187026978,
"loss_region": 0.06505395472049713,
"loss_total": 1.1930452585220337,
"lr": 0.0010160499728743976,
"router/selected_tokens_s0": 424.8125,
"router/selected_tokens_s1": 19.4375,
"step": 5630,
"tokens_trained": 18.4466984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6,
"grad_norm": 0.6749231219291687,
"loss": 1.1557,
"loss_ce": 1.1030737161636353,
"loss_region": 0.0562567301094532,
"loss_total": 1.1593304872512817,
"lr": 0.0010156430808905465,
"router/selected_tokens_s0": 428.25,
"router/selected_tokens_s1": 8.75,
"step": 5640,
"tokens_trained": 18.47946384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.602836879432624,
"grad_norm": 1.4124048948287964,
"loss": 1.1577,
"loss_ce": 1.0829676389694214,
"loss_region": 0.061727654188871384,
"loss_total": 1.1446952819824219,
"lr": 0.0010152361889066955,
"router/selected_tokens_s0": 464.625,
"router/selected_tokens_s1": 16.6875,
"step": 5650,
"tokens_trained": 18.51222928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6056737588652483,
"grad_norm": 1.0576155185699463,
"loss": 1.1663,
"loss_ce": 1.144495964050293,
"loss_region": 0.06459303945302963,
"loss_total": 1.2090890407562256,
"lr": 0.0010148292969228445,
"router/selected_tokens_s0": 389.9375,
"router/selected_tokens_s1": 17.9375,
"step": 5660,
"tokens_trained": 18.54499392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6085106382978722,
"grad_norm": 0.6192797422409058,
"loss": 1.159,
"loss_ce": 1.1436125040054321,
"loss_region": 0.056959912180900574,
"loss_total": 1.2005723714828491,
"lr": 0.0010144224049389934,
"router/selected_tokens_s0": 447.125,
"router/selected_tokens_s1": 9.8125,
"step": 5670,
"tokens_trained": 18.57775936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6113475177304966,
"grad_norm": 0.9440255165100098,
"loss": 1.1491,
"loss_ce": 1.0525715351104736,
"loss_region": 0.05895181745290756,
"loss_total": 1.1115233898162842,
"lr": 0.0010140155129551424,
"router/selected_tokens_s0": 494.875,
"router/selected_tokens_s1": 14.3125,
"step": 5680,
"tokens_trained": 18.6105248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6141843971631205,
"grad_norm": 0.8564097881317139,
"loss": 1.1583,
"loss_ce": 1.1537847518920898,
"loss_region": 0.06267160922288895,
"loss_total": 1.216456413269043,
"lr": 0.0010136086209712914,
"router/selected_tokens_s0": 426.3125,
"router/selected_tokens_s1": 16.625,
"step": 5690,
"tokens_trained": 18.64329024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6170212765957448,
"grad_norm": 1.5163027048110962,
"loss": 1.1573,
"loss_ce": 1.1002916097640991,
"loss_region": 0.05866721272468567,
"loss_total": 1.1589587926864624,
"lr": 0.0010132017289874405,
"router/selected_tokens_s0": 478.5,
"router/selected_tokens_s1": 12.875,
"step": 5700,
"tokens_trained": 18.67605568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6198581560283687,
"grad_norm": 1.0508079528808594,
"loss": 1.1576,
"loss_ce": 1.0324606895446777,
"loss_region": 0.05855386331677437,
"loss_total": 1.0910145044326782,
"lr": 0.0010127948370035895,
"router/selected_tokens_s0": 445.6875,
"router/selected_tokens_s1": 12.5625,
"step": 5710,
"tokens_trained": 18.70882112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.622695035460993,
"grad_norm": 1.1140241622924805,
"loss": 1.1626,
"loss_ce": 1.1185026168823242,
"loss_region": 0.06571623682975769,
"loss_total": 1.1842188835144043,
"lr": 0.0010123879450197385,
"router/selected_tokens_s0": 455.25,
"router/selected_tokens_s1": 21.25,
"step": 5720,
"tokens_trained": 18.74158656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.625531914893617,
"grad_norm": 0.9186303615570068,
"loss": 1.1624,
"loss_ce": 1.1634204387664795,
"loss_region": 0.058083634823560715,
"loss_total": 1.2215040922164917,
"lr": 0.0010119810530358872,
"router/selected_tokens_s0": 412.5,
"router/selected_tokens_s1": 10.6875,
"step": 5730,
"tokens_trained": 18.774352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6283687943262413,
"grad_norm": 1.6307847499847412,
"loss": 1.1612,
"loss_ce": 1.114676833152771,
"loss_region": 0.05957353860139847,
"loss_total": 1.1742503643035889,
"lr": 0.0010115741610520362,
"router/selected_tokens_s0": 475.8125,
"router/selected_tokens_s1": 14.375,
"step": 5740,
"tokens_trained": 18.80711744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6312056737588652,
"grad_norm": 0.432007759809494,
"loss": 1.1634,
"loss_ce": 1.0877857208251953,
"loss_region": 0.06144358590245247,
"loss_total": 1.1492292881011963,
"lr": 0.0010111672690681851,
"router/selected_tokens_s0": 473.625,
"router/selected_tokens_s1": 16.75,
"step": 5750,
"tokens_trained": 18.83988288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6340425531914895,
"grad_norm": 0.32113170623779297,
"loss": 1.1568,
"loss_ce": 1.0600965023040771,
"loss_region": 0.05585326626896858,
"loss_total": 1.1159497499465942,
"lr": 0.0010107603770843341,
"router/selected_tokens_s0": 512.875,
"router/selected_tokens_s1": 10.0,
"step": 5760,
"tokens_trained": 18.87264832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6368794326241134,
"grad_norm": 0.5704630613327026,
"loss": 1.1561,
"loss_ce": 1.140356421470642,
"loss_region": 0.06394833326339722,
"loss_total": 1.2043046951293945,
"lr": 0.0010103534851004833,
"router/selected_tokens_s0": 443.4375,
"router/selected_tokens_s1": 18.6875,
"step": 5770,
"tokens_trained": 18.90541376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6397163120567377,
"grad_norm": 0.886239230632782,
"loss": 1.1629,
"loss_ce": 1.092922329902649,
"loss_region": 0.060600440949201584,
"loss_total": 1.1535227298736572,
"lr": 0.0010099465931166323,
"router/selected_tokens_s0": 464.0625,
"router/selected_tokens_s1": 15.5625,
"step": 5780,
"tokens_trained": 18.9381792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6425531914893616,
"grad_norm": 0.7641704082489014,
"loss": 1.1497,
"loss_ce": 0.9872031807899475,
"loss_region": 0.056345850229263306,
"loss_total": 1.0435490608215332,
"lr": 0.0010095397011327812,
"router/selected_tokens_s0": 468.5625,
"router/selected_tokens_s1": 9.625,
"step": 5790,
"tokens_trained": 18.97094464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.645390070921986,
"grad_norm": 0.7847086191177368,
"loss": 1.1551,
"loss_ce": 1.0804718732833862,
"loss_region": 0.059678997844457626,
"loss_total": 1.1401509046554565,
"lr": 0.0010091328091489302,
"router/selected_tokens_s0": 463.1875,
"router/selected_tokens_s1": 14.4375,
"step": 5800,
"tokens_trained": 19.00370848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6482269503546099,
"grad_norm": 0.5308611989021301,
"loss": 1.1598,
"loss_ce": 1.1176682710647583,
"loss_region": 0.06210538372397423,
"loss_total": 1.1797736883163452,
"lr": 0.0010087259171650792,
"router/selected_tokens_s0": 466.8125,
"router/selected_tokens_s1": 17.4375,
"step": 5810,
"tokens_trained": 19.03647392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6510638297872342,
"grad_norm": 0.9863501787185669,
"loss": 1.1553,
"loss_ce": 1.0464540719985962,
"loss_region": 0.05664392560720444,
"loss_total": 1.1030980348587036,
"lr": 0.0010083190251812281,
"router/selected_tokens_s0": 457.5625,
"router/selected_tokens_s1": 10.0625,
"step": 5820,
"tokens_trained": 19.06923936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.653900709219858,
"grad_norm": 0.6776580214500427,
"loss": 1.154,
"loss_ce": 1.0867358446121216,
"loss_region": 0.06509334594011307,
"loss_total": 1.1518292427062988,
"lr": 0.001007912133197377,
"router/selected_tokens_s0": 422.4375,
"router/selected_tokens_s1": 19.0,
"step": 5830,
"tokens_trained": 19.1020048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6567375886524822,
"grad_norm": 0.976962685585022,
"loss": 1.1597,
"loss_ce": 1.1119444370269775,
"loss_region": 0.0586853101849556,
"loss_total": 1.1706297397613525,
"lr": 0.001007505241213526,
"router/selected_tokens_s0": 402.0625,
"router/selected_tokens_s1": 11.0625,
"step": 5840,
"tokens_trained": 19.13477024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6595744680851063,
"grad_norm": 0.7124935984611511,
"loss": 1.1514,
"loss_ce": 1.1340878009796143,
"loss_region": 0.05913223326206207,
"loss_total": 1.1932200193405151,
"lr": 0.001007098349229675,
"router/selected_tokens_s0": 475.4375,
"router/selected_tokens_s1": 13.8125,
"step": 5850,
"tokens_trained": 19.16753568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6624113475177305,
"grad_norm": 0.6097173094749451,
"loss": 1.155,
"loss_ce": 1.017051339149475,
"loss_region": 0.06248475983738899,
"loss_total": 1.0795360803604126,
"lr": 0.001006691457245824,
"router/selected_tokens_s0": 446.25,
"router/selected_tokens_s1": 17.125,
"step": 5860,
"tokens_trained": 19.20030112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6652482269503546,
"grad_norm": 1.3263115882873535,
"loss": 1.1563,
"loss_ce": 1.0393388271331787,
"loss_region": 0.05702516809105873,
"loss_total": 1.0963640213012695,
"lr": 0.001006284565261973,
"router/selected_tokens_s0": 438.6875,
"router/selected_tokens_s1": 9.875,
"step": 5870,
"tokens_trained": 19.23306656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6680851063829787,
"grad_norm": 0.650032103061676,
"loss": 1.1522,
"loss_ce": 1.1351990699768066,
"loss_region": 0.05994255840778351,
"loss_total": 1.1951416730880737,
"lr": 0.001005877673278122,
"router/selected_tokens_s0": 459.4375,
"router/selected_tokens_s1": 14.375,
"step": 5880,
"tokens_trained": 19.265832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6709219858156028,
"grad_norm": 1.0562461614608765,
"loss": 1.1563,
"loss_ce": 1.1028565168380737,
"loss_region": 0.06198059767484665,
"loss_total": 1.164837121963501,
"lr": 0.0010054707812942709,
"router/selected_tokens_s0": 429.5625,
"router/selected_tokens_s1": 15.9375,
"step": 5890,
"tokens_trained": 19.29859664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.673758865248227,
"grad_norm": 0.6909924149513245,
"loss": 1.1567,
"loss_ce": 1.1044297218322754,
"loss_region": 0.05730178952217102,
"loss_total": 1.161731481552124,
"lr": 0.0010050638893104198,
"router/selected_tokens_s0": 439.75,
"router/selected_tokens_s1": 10.5,
"step": 5900,
"tokens_trained": 19.33136116
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.676595744680851,
"grad_norm": 0.5099886059761047,
"loss": 1.1534,
"loss_ce": 1.1194809675216675,
"loss_region": 0.06314481794834137,
"loss_total": 1.1826257705688477,
"lr": 0.0010046569973265688,
"router/selected_tokens_s0": 453.375,
"router/selected_tokens_s1": 18.0625,
"step": 5910,
"tokens_trained": 19.3641258
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6794326241134752,
"grad_norm": 0.703726053237915,
"loss": 1.1572,
"loss_ce": 1.098257303237915,
"loss_region": 0.059644293040037155,
"loss_total": 1.157901644706726,
"lr": 0.0010042501053427178,
"router/selected_tokens_s0": 455.5625,
"router/selected_tokens_s1": 13.6875,
"step": 5920,
"tokens_trained": 19.39688964
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6822695035460993,
"grad_norm": 0.728217363357544,
"loss": 1.1559,
"loss_ce": 1.0854500532150269,
"loss_region": 0.05772150680422783,
"loss_total": 1.1431715488433838,
"lr": 0.0010038432133588667,
"router/selected_tokens_s0": 494.6875,
"router/selected_tokens_s1": 12.125,
"step": 5930,
"tokens_trained": 19.42965508
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6851063829787234,
"grad_norm": 0.6884320378303528,
"loss": 1.1525,
"loss_ce": 1.1034066677093506,
"loss_region": 0.06277105957269669,
"loss_total": 1.166177749633789,
"lr": 0.0010034363213750157,
"router/selected_tokens_s0": 469.4375,
"router/selected_tokens_s1": 18.25,
"step": 5940,
"tokens_trained": 19.46241972
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6879432624113475,
"grad_norm": 0.7436274290084839,
"loss": 1.1584,
"loss_ce": 1.1485267877578735,
"loss_region": 0.06026006489992142,
"loss_total": 1.2087868452072144,
"lr": 0.0010030294293911649,
"router/selected_tokens_s0": 454.25,
"router/selected_tokens_s1": 14.6875,
"step": 5950,
"tokens_trained": 19.49518516
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6907801418439716,
"grad_norm": 0.6739595532417297,
"loss": 1.1518,
"loss_ce": 1.1541627645492554,
"loss_region": 0.05630716681480408,
"loss_total": 1.2104699611663818,
"lr": 0.0010026225374073139,
"router/selected_tokens_s0": 432.0,
"router/selected_tokens_s1": 9.125,
"step": 5960,
"tokens_trained": 19.5279506
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6936170212765957,
"grad_norm": 0.9516991972923279,
"loss": 1.1595,
"loss_ce": 1.1228985786437988,
"loss_region": 0.06748107820749283,
"loss_total": 1.1903796195983887,
"lr": 0.0010022156454234628,
"router/selected_tokens_s0": 403.3125,
"router/selected_tokens_s1": 20.9375,
"step": 5970,
"tokens_trained": 19.56071604
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6964539007092199,
"grad_norm": 0.7473562955856323,
"loss": 1.1562,
"loss_ce": 1.0967330932617188,
"loss_region": 0.059221576899290085,
"loss_total": 1.1559547185897827,
"lr": 0.0010018087534396116,
"router/selected_tokens_s0": 490.375,
"router/selected_tokens_s1": 14.1875,
"step": 5980,
"tokens_trained": 19.59348068
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.699290780141844,
"grad_norm": 1.1160359382629395,
"loss": 1.151,
"loss_ce": 1.089220404624939,
"loss_region": 0.05939415842294693,
"loss_total": 1.148614525794983,
"lr": 0.0010014018614557605,
"router/selected_tokens_s0": 511.4375,
"router/selected_tokens_s1": 14.9375,
"step": 5990,
"tokens_trained": 19.62624612
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.702127659574468,
"grad_norm": 1.0865445137023926,
"loss": 1.158,
"loss_ce": 1.0744832754135132,
"loss_region": 0.06320250779390335,
"loss_total": 1.137685775756836,
"lr": 0.0010009949694719095,
"router/selected_tokens_s0": 443.0625,
"router/selected_tokens_s1": 17.9375,
"step": 6000,
"tokens_trained": 19.659011552
},
{
"epoch": 1.702127659574468,
"eval_ppl": 2.998067346037042,
"eval_runtime": 2.067,
"step": 6000,
"tokens_trained": 19.659011552
},
{
"epoch": 1.702127659574468,
"eval_F": 0.0013543432401308525,
"eval_F_cds": 0.001446410924445243,
"eval_F_dig": 0.002304867567778733,
"eval_F_exon": 0.0012367323086122776,
"eval_F_intron": 0.0013766258061943945,
"eval_F_nig": 0.0013487171280326855,
"eval_F_promoter": 0.0012541321879013748,
"eval_F_utr": 0.0013323243197152024,
"eval_G": 0.013059948922586937,
"eval_G_cds": 0.012359187601069086,
"eval_G_dig": 0.02614904606805219,
"eval_G_exon": 0.012316438474266455,
"eval_G_intron": 0.013067059240385087,
"eval_G_nig": 0.013578898008810526,
"eval_G_promoter": 0.012155479142156476,
"eval_G_utr": 0.012293668761524606,
"eval_avg_bp_per_token": 738.3652610126979,
"eval_bp_per_token/cds": 691.3664596273292,
"eval_bp_per_token/dig": 433.864406779661,
"eval_bp_per_token/exon": 808.5824175824176,
"eval_bp_per_token/intron": 726.4138123085492,
"eval_bp_per_token/nig": 741.445318084346,
"eval_bp_per_token/promoter": 797.3641133263379,
"eval_bp_per_token/utr": 750.568,
"eval_ppl_cds": 3.7357774747386774,
"eval_ppl_dig": 1.0956703388366842,
"eval_ppl_exon": 3.2539563358776444,
"eval_ppl_intron": 3.019567682292059,
"eval_ppl_nig": 2.8358108842977168,
"eval_ppl_promoter": 3.2906528782913433,
"eval_ppl_utr": 3.398305967468575,
"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
}