HNet_BPT3_12.8K-100B / checkpoint-9000 /trainer_state.json
andyjzhao's picture
Upload folder using huggingface_hub
dfd0379 verified
{
"best_global_step": 9000,
"best_metric": 2.7250221948753346,
"best_model_checkpoint": "/gpfs/scratch/guoh/DNAFM/output/gencode_human_12.8k_12800/HNet_BPT3_12.8K-100B/checkpoint-9000",
"epoch": 2.5525849230551025,
"eval_steps": 500,
"global_step": 9000,
"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": 0.0028366782497695198,
"grad_norm": 1632.1500244140625,
"loss": 88.4255,
"loss_ce": 61.45643997192383,
"loss_region": 0.09446925669908524,
"loss_total": 61.55091094970703,
"lr": 2.20454076850486e-05,
"router/selected_tokens_s0": 685.5,
"router/selected_tokens_s1": 127.125,
"step": 10,
"tokens_trained": 0.03276544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.0056733564995390395,
"grad_norm": 470.2360534667969,
"loss": 43.9906,
"loss_ce": 31.559911727905273,
"loss_region": 0.1008022278547287,
"loss_total": 31.66071319580078,
"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": 0.00851003474930856,
"grad_norm": 349.49151611328125,
"loss": 13.8617,
"loss_ce": 5.999421119689941,
"loss_region": 0.10440575331449509,
"loss_total": 6.103826999664307,
"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": 0.011346712999078079,
"grad_norm": 394.0719909667969,
"loss": 5.4272,
"loss_ce": 6.045137882232666,
"loss_region": 0.10674509406089783,
"loss_total": 6.151883125305176,
"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": 0.014183391248847599,
"grad_norm": 460.50262451171875,
"loss": 4.7094,
"loss_ce": 6.701486110687256,
"loss_region": 0.10931951552629471,
"loss_total": 6.810805797576904,
"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": 0.01702006949861712,
"grad_norm": 626.8062133789062,
"loss": 9.494,
"loss_ce": 10.466922760009766,
"loss_region": 0.11075878143310547,
"loss_total": 10.577681541442871,
"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": 0.01985674774838664,
"grad_norm": 448.8774108886719,
"loss": 12.7236,
"loss_ce": 14.8423433303833,
"loss_region": 0.11327756941318512,
"loss_total": 14.955620765686035,
"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": 0.022693425998156158,
"grad_norm": 386.830322265625,
"loss": 14.3151,
"loss_ce": 13.370331764221191,
"loss_region": 0.11444944888353348,
"loss_total": 13.484781265258789,
"lr": 0.00019350968967987104,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 80,
"tokens_trained": 0.26212192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.025530104247925678,
"grad_norm": 376.66900634765625,
"loss": 10.4163,
"loss_ce": 5.837803363800049,
"loss_region": 0.11401050537824631,
"loss_total": 5.951813697814941,
"lr": 0.0002180045871077028,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 90,
"tokens_trained": 0.29488736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.028366782497695198,
"grad_norm": 294.97216796875,
"loss": 8.8793,
"loss_ce": 6.233154773712158,
"loss_region": 0.11450602859258652,
"loss_total": 6.347661018371582,
"lr": 0.00024249948453553463,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 100,
"tokens_trained": 0.3276528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.031203460747464717,
"grad_norm": 497.3160095214844,
"loss": 11.7289,
"loss_ce": 20.51309585571289,
"loss_region": 0.11433509737253189,
"loss_total": 20.627431869506836,
"lr": 0.00026699438196336637,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 110,
"tokens_trained": 0.36041744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.03404013899723424,
"grad_norm": 493.2754821777344,
"loss": 20.8633,
"loss_ce": 18.29560661315918,
"loss_region": 0.10929017513990402,
"loss_total": 18.404897689819336,
"lr": 0.00029148927939119814,
"router/selected_tokens_s0": 1.0,
"router/selected_tokens_s1": 1.0,
"step": 120,
"tokens_trained": 0.39318128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.03687681724700376,
"grad_norm": 451.9964599609375,
"loss": 15.6879,
"loss_ce": 20.399511337280273,
"loss_region": 0.1114715188741684,
"loss_total": 20.510982513427734,
"lr": 0.00031598417681902996,
"router/selected_tokens_s0": 2386.25,
"router/selected_tokens_s1": 1.0,
"step": 130,
"tokens_trained": 0.42594672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.03971349549677328,
"grad_norm": 207.16168212890625,
"loss": 7.2589,
"loss_ce": 6.26461124420166,
"loss_region": 0.11115273833274841,
"loss_total": 6.375763893127441,
"lr": 0.00034047907424686173,
"router/selected_tokens_s0": 2255.5,
"router/selected_tokens_s1": 1.0,
"step": 140,
"tokens_trained": 0.458709112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.042550173746542796,
"grad_norm": 216.46034240722656,
"loss": 9.9827,
"loss_ce": 2.39017653465271,
"loss_region": 0.1067117229104042,
"loss_total": 2.4968881607055664,
"lr": 0.0003649739716746935,
"router/selected_tokens_s0": 3026.125,
"router/selected_tokens_s1": 1.0,
"step": 150,
"tokens_trained": 0.491469992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.045386851996312316,
"grad_norm": 278.6517028808594,
"loss": 8.6499,
"loss_ce": 5.831767559051514,
"loss_region": 0.10348913073539734,
"loss_total": 5.935256481170654,
"lr": 0.00038946886910252526,
"router/selected_tokens_s0": 4061.0,
"router/selected_tokens_s1": 1.0,
"step": 160,
"tokens_trained": 0.524234632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.048223530246081836,
"grad_norm": 270.7173156738281,
"loss": 6.2812,
"loss_ce": 9.848775863647461,
"loss_region": 0.11538821458816528,
"loss_total": 9.964163780212402,
"lr": 0.0004139637665303571,
"router/selected_tokens_s0": 1436.0,
"router/selected_tokens_s1": 1.0,
"step": 170,
"tokens_trained": 0.556999272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.051060208495851356,
"grad_norm": 225.5234375,
"loss": 7.4079,
"loss_ce": 4.911764144897461,
"loss_region": 0.11397740244865417,
"loss_total": 5.0257415771484375,
"lr": 0.0004384586639581888,
"router/selected_tokens_s0": 1610.375,
"router/selected_tokens_s1": 1.0,
"step": 180,
"tokens_trained": 0.589762952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.053896886745620876,
"grad_norm": 236.20843505859375,
"loss": 7.1161,
"loss_ce": 8.928335189819336,
"loss_region": 0.11002947390079498,
"loss_total": 9.03836441040039,
"lr": 0.0004629535613860206,
"router/selected_tokens_s0": 1923.375,
"router/selected_tokens_s1": 1.0,
"step": 190,
"tokens_trained": 0.622527592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.056733564995390395,
"grad_norm": 108.58197021484375,
"loss": 5.231,
"loss_ce": 5.8081512451171875,
"loss_region": 0.11359135806560516,
"loss_total": 5.9217424392700195,
"lr": 0.00048744845881385244,
"router/selected_tokens_s0": 1059.625,
"router/selected_tokens_s1": 1.0,
"step": 200,
"tokens_trained": 0.655293032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.059570243245159915,
"grad_norm": 195.470458984375,
"loss": 7.8328,
"loss_ce": 10.872328758239746,
"loss_region": 0.10074600577354431,
"loss_total": 10.973074913024902,
"lr": 0.0005119433562416841,
"router/selected_tokens_s0": 2660.875,
"router/selected_tokens_s1": 1.0,
"step": 210,
"tokens_trained": 0.688057672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.062406921494929435,
"grad_norm": 141.9326629638672,
"loss": 5.994,
"loss_ce": 4.301753044128418,
"loss_region": 0.09836956113576889,
"loss_total": 4.40012264251709,
"lr": 0.0005364382536695159,
"router/selected_tokens_s0": 2709.625,
"router/selected_tokens_s1": 1.0,
"step": 220,
"tokens_trained": 0.720823112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.06524359974469895,
"grad_norm": 128.35894775390625,
"loss": 3.2054,
"loss_ce": 3.196018695831299,
"loss_region": 0.09772488474845886,
"loss_total": 3.29374361038208,
"lr": 0.0005609331510973477,
"router/selected_tokens_s0": 1876.125,
"router/selected_tokens_s1": 1.0,
"step": 230,
"tokens_trained": 0.753588552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.06808027799446847,
"grad_norm": 76.50245666503906,
"loss": 3.7556,
"loss_ce": 1.953817367553711,
"loss_region": 0.08583591133356094,
"loss_total": 2.0396533012390137,
"lr": 0.0005854280485251795,
"router/selected_tokens_s0": 4237.5,
"router/selected_tokens_s1": 1.0,
"step": 240,
"tokens_trained": 0.786353992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.070916956244238,
"grad_norm": 98.34822082519531,
"loss": 3.5987,
"loss_ce": 2.239224433898926,
"loss_region": 0.08410990983247757,
"loss_total": 2.3233344554901123,
"lr": 0.0006099229459530113,
"router/selected_tokens_s0": 2309.125,
"router/selected_tokens_s1": 1.0,
"step": 250,
"tokens_trained": 0.819119432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.07375363449400751,
"grad_norm": 127.2884292602539,
"loss": 5.4797,
"loss_ce": 6.326235294342041,
"loss_region": 0.06658253818750381,
"loss_total": 6.392817974090576,
"lr": 0.0006344178433808431,
"router/selected_tokens_s0": 6774.375,
"router/selected_tokens_s1": 6774.375,
"step": 260,
"tokens_trained": 0.851884072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.07659031274377703,
"grad_norm": 91.72901916503906,
"loss": 3.183,
"loss_ce": 2.804473876953125,
"loss_region": 0.06812562048435211,
"loss_total": 2.8725996017456055,
"lr": 0.0006589127408086749,
"router/selected_tokens_s0": 5535.25,
"router/selected_tokens_s1": 5535.25,
"step": 270,
"tokens_trained": 0.884649512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.07942699099354655,
"grad_norm": 80.58329772949219,
"loss": 2.5646,
"loss_ce": 2.606522798538208,
"loss_region": 0.06925090402364731,
"loss_total": 2.6757736206054688,
"lr": 0.0006834076382365066,
"router/selected_tokens_s0": 3777.75,
"router/selected_tokens_s1": 3777.75,
"step": 280,
"tokens_trained": 0.917414936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.08226366924331607,
"grad_norm": 85.70040130615234,
"loss": 3.1077,
"loss_ce": 2.233630895614624,
"loss_region": 0.06535117328166962,
"loss_total": 2.2989821434020996,
"lr": 0.0007079025356643384,
"router/selected_tokens_s0": 3477.125,
"router/selected_tokens_s1": 3193.375,
"step": 290,
"tokens_trained": 0.950180376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.08510034749308559,
"grad_norm": 102.1810073852539,
"loss": 3.1872,
"loss_ce": 2.971275568008423,
"loss_region": 0.06759099662303925,
"loss_total": 3.0388665199279785,
"lr": 0.0007323974330921702,
"router/selected_tokens_s0": 3964.5,
"router/selected_tokens_s1": 3964.5,
"step": 300,
"tokens_trained": 0.982945816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.08793702574285511,
"grad_norm": 67.37890625,
"loss": 3.2037,
"loss_ce": 2.0559582710266113,
"loss_region": 0.06636148691177368,
"loss_total": 2.1223196983337402,
"lr": 0.000756892330520002,
"router/selected_tokens_s0": 5813.875,
"router/selected_tokens_s1": 5813.875,
"step": 310,
"tokens_trained": 1.015711256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.09077370399262463,
"grad_norm": 61.368873596191406,
"loss": 3.5341,
"loss_ce": 3.0156445503234863,
"loss_region": 0.06766507029533386,
"loss_total": 3.0833096504211426,
"lr": 0.0007813872279478337,
"router/selected_tokens_s0": 4320.5,
"router/selected_tokens_s1": 4320.5,
"step": 320,
"tokens_trained": 1.048476696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.09361038224239415,
"grad_norm": 54.85828399658203,
"loss": 3.4888,
"loss_ce": 3.9015138149261475,
"loss_region": 0.05761323869228363,
"loss_total": 3.9591269493103027,
"lr": 0.0008058821253756655,
"router/selected_tokens_s0": 8438.375,
"router/selected_tokens_s1": 7710.25,
"step": 330,
"tokens_trained": 1.081242136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.09644706049216367,
"grad_norm": 86.64398193359375,
"loss": 2.7011,
"loss_ce": 3.5396924018859863,
"loss_region": 0.0677424967288971,
"loss_total": 3.6074349880218506,
"lr": 0.0008303770228034974,
"router/selected_tokens_s0": 9649.25,
"router/selected_tokens_s1": 5.875,
"step": 340,
"tokens_trained": 1.114007576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.09928373874193319,
"grad_norm": 87.52863311767578,
"loss": 3.3207,
"loss_ce": 4.275536060333252,
"loss_region": 0.07108451426029205,
"loss_total": 4.346620559692383,
"lr": 0.0008548719202313291,
"router/selected_tokens_s0": 5297.875,
"router/selected_tokens_s1": 1.5,
"step": 350,
"tokens_trained": 1.146773016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.10212041699170271,
"grad_norm": 59.0909423828125,
"loss": 2.8189,
"loss_ce": 2.441368341445923,
"loss_region": 0.06068379059433937,
"loss_total": 2.502052068710327,
"lr": 0.0008793668176591608,
"router/selected_tokens_s0": 5374.625,
"router/selected_tokens_s1": 4637.25,
"step": 360,
"tokens_trained": 1.179538456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.10495709524147223,
"grad_norm": 60.50209045410156,
"loss": 2.0942,
"loss_ce": 2.445530414581299,
"loss_region": 0.06311789900064468,
"loss_total": 2.50864839553833,
"lr": 0.0009038617150869926,
"router/selected_tokens_s0": 7771.875,
"router/selected_tokens_s1": 2119.625,
"step": 370,
"tokens_trained": 1.212303896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.10779377349124175,
"grad_norm": 63.17313003540039,
"loss": 2.5238,
"loss_ce": 2.970167398452759,
"loss_region": 0.06014455109834671,
"loss_total": 3.0303120613098145,
"lr": 0.0009283566125148244,
"router/selected_tokens_s0": 6445.875,
"router/selected_tokens_s1": 6445.875,
"step": 380,
"tokens_trained": 1.245068536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11063045174101127,
"grad_norm": 79.03811645507812,
"loss": 2.8523,
"loss_ce": 2.7662765979766846,
"loss_region": 0.06919371336698532,
"loss_total": 2.835470199584961,
"lr": 0.0009528515099426562,
"router/selected_tokens_s0": 3670.875,
"router/selected_tokens_s1": 690.625,
"step": 390,
"tokens_trained": 1.277833176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11346712999078079,
"grad_norm": 39.57363510131836,
"loss": 2.0454,
"loss_ce": 1.830534815788269,
"loss_region": 0.06083514541387558,
"loss_total": 1.8913699388504028,
"lr": 0.000977346407370488,
"router/selected_tokens_s0": 9311.375,
"router/selected_tokens_s1": 3812.875,
"step": 400,
"tokens_trained": 1.310598616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11630380824055031,
"grad_norm": 79.65859985351562,
"loss": 2.3664,
"loss_ce": 2.813112735748291,
"loss_region": 0.06279323250055313,
"loss_total": 2.875905990600586,
"lr": 0.0010018413047983197,
"router/selected_tokens_s0": 6855.25,
"router/selected_tokens_s1": 2318.875,
"step": 410,
"tokens_trained": 1.343364056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.11914048649031983,
"grad_norm": 71.34756469726562,
"loss": 2.9128,
"loss_ce": 3.0529584884643555,
"loss_region": 0.06804051250219345,
"loss_total": 3.1209990978240967,
"lr": 0.0010263362022261515,
"router/selected_tokens_s0": 2438.25,
"router/selected_tokens_s1": 1069.0,
"step": 420,
"tokens_trained": 1.376129496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.12197716474008935,
"grad_norm": 69.63412475585938,
"loss": 2.6515,
"loss_ce": 2.2142796516418457,
"loss_region": 0.056970782577991486,
"loss_total": 2.2712504863739014,
"lr": 0.0010508310996539833,
"router/selected_tokens_s0": 11183.125,
"router/selected_tokens_s1": 11031.5,
"step": 430,
"tokens_trained": 1.408889864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.12481384298985887,
"grad_norm": 45.879173278808594,
"loss": 2.0195,
"loss_ce": 1.895429015159607,
"loss_region": 0.06761395186185837,
"loss_total": 1.963042974472046,
"lr": 0.0010753259970818151,
"router/selected_tokens_s0": 1293.875,
"router/selected_tokens_s1": 873.25,
"step": 440,
"tokens_trained": 1.441655304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1276505212396284,
"grad_norm": 35.60654067993164,
"loss": 1.8072,
"loss_ce": 1.6901588439941406,
"loss_region": 0.061801426112651825,
"loss_total": 1.751960277557373,
"lr": 0.001099820894509647,
"router/selected_tokens_s0": 6973.125,
"router/selected_tokens_s1": 2913.125,
"step": 450,
"tokens_trained": 1.474420744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1304871994893979,
"grad_norm": 49.47394943237305,
"loss": 1.8686,
"loss_ce": 2.0007646083831787,
"loss_region": 0.06083563342690468,
"loss_total": 2.0616002082824707,
"lr": 0.0011243157919374788,
"router/selected_tokens_s0": 8894.125,
"router/selected_tokens_s1": 3425.875,
"step": 460,
"tokens_trained": 1.507186184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13332387773916743,
"grad_norm": 36.48300552368164,
"loss": 1.8564,
"loss_ce": 1.7348560094833374,
"loss_region": 0.06224008649587631,
"loss_total": 1.7970961332321167,
"lr": 0.0011488106893653104,
"router/selected_tokens_s0": 4828.125,
"router/selected_tokens_s1": 2957.625,
"step": 470,
"tokens_trained": 1.539950832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13616055598893695,
"grad_norm": 59.48313903808594,
"loss": 2.1381,
"loss_ce": 2.6884067058563232,
"loss_region": 0.05959445983171463,
"loss_total": 2.7480010986328125,
"lr": 0.0011733055867931422,
"router/selected_tokens_s0": 8242.5,
"router/selected_tokens_s1": 4600.25,
"step": 480,
"tokens_trained": 1.572715472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.13899723423870647,
"grad_norm": 13.365839004516602,
"loss": 1.9219,
"loss_ce": 1.376577377319336,
"loss_region": 0.06748919934034348,
"loss_total": 1.4440665245056152,
"lr": 0.001197800484220974,
"router/selected_tokens_s0": 1833.25,
"router/selected_tokens_s1": 820.125,
"step": 490,
"tokens_trained": 1.605480912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.141833912488476,
"grad_norm": 35.323246002197266,
"loss": 1.8414,
"loss_ce": 2.028839111328125,
"loss_region": 0.06109331175684929,
"loss_total": 2.089932441711426,
"lr": 0.0012222953816488059,
"router/selected_tokens_s0": 10474.625,
"router/selected_tokens_s1": 3541.375,
"step": 500,
"tokens_trained": 1.638244216
},
{
"epoch": 0.141833912488476,
"eval_ppl": 5.586714635791497,
"eval_runtime": 1.0612,
"step": 500,
"tokens_trained": 1.638244216
},
{
"epoch": 0.141833912488476,
"eval_F": 0.1523211448811105,
"eval_F_cds": 0.1718298886393841,
"eval_F_dig": 0.16399718728025628,
"eval_F_exon": 0.1541913028892523,
"eval_F_intron": 0.15165489305779373,
"eval_F_nig": 0.15221594667480792,
"eval_F_promoter": 0.1501688968516134,
"eval_F_utr": 0.15336648715504136,
"eval_G": 0.372060118832526,
"eval_G_cds": 0.3656581890724531,
"eval_G_dig": 0.3759247548636612,
"eval_G_exon": 0.37130833411959574,
"eval_G_intron": 0.3726392825038316,
"eval_G_nig": 0.3703948690443253,
"eval_G_promoter": 0.37331512304800496,
"eval_G_utr": 0.37175619902922,
"eval_avg_bp_per_token": 6.565076705407635,
"eval_bp_per_token/cds": 5.819709294572609,
"eval_bp_per_token/dig": 6.097665555026203,
"eval_bp_per_token/exon": 6.485450095186293,
"eval_bp_per_token/intron": 6.593918467364669,
"eval_bp_per_token/nig": 6.5696139060671905,
"eval_bp_per_token/promoter": 6.6591685826135585,
"eval_bp_per_token/utr": 6.520329301075269,
"eval_ppl_cds": 6.264007437664035,
"eval_ppl_dig": 5.376989468471789,
"eval_ppl_exon": 5.6381595387903625,
"eval_ppl_intron": 5.4896203277448326,
"eval_ppl_nig": 5.436721243945483,
"eval_ppl_promoter": 6.014557891578177,
"eval_ppl_utr": 5.561276789916418,
"step": 500,
"tokens_trained": 1.638244216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1446705907382455,
"grad_norm": 24.587987899780273,
"loss": 2.1546,
"loss_ce": 1.7202653884887695,
"loss_region": 0.06705278903245926,
"loss_total": 1.787318229675293,
"lr": 0.0012243786686061229,
"router/selected_tokens_s0": 2551.0,
"router/selected_tokens_s1": 1029.625,
"step": 510,
"tokens_trained": 1.671005424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.14750726898801503,
"grad_norm": 31.121719360351562,
"loss": 1.9491,
"loss_ce": 1.5548391342163086,
"loss_region": 0.06364650279283524,
"loss_total": 1.618485689163208,
"lr": 0.0012239717766222718,
"router/selected_tokens_s0": 11385.75,
"router/selected_tokens_s1": 1565.75,
"step": 520,
"tokens_trained": 1.703770864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.15034394723778455,
"grad_norm": 36.0692024230957,
"loss": 1.6872,
"loss_ce": 1.6581867933273315,
"loss_region": 0.05713363736867905,
"loss_total": 1.7153204679489136,
"lr": 0.001223564884638421,
"router/selected_tokens_s0": 8757.75,
"router/selected_tokens_s1": 8757.75,
"step": 530,
"tokens_trained": 1.736536304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.15318062548755407,
"grad_norm": 24.032297134399414,
"loss": 1.6695,
"loss_ce": 1.7199375629425049,
"loss_region": 0.061875585466623306,
"loss_total": 1.781813144683838,
"lr": 0.00122315799265457,
"router/selected_tokens_s0": 4319.5,
"router/selected_tokens_s1": 3071.25,
"step": 540,
"tokens_trained": 1.769301744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1560173037373236,
"grad_norm": 29.07722282409668,
"loss": 1.7629,
"loss_ce": 1.444469928741455,
"loss_region": 0.06348070502281189,
"loss_total": 1.5079506635665894,
"lr": 0.001222751100670719,
"router/selected_tokens_s0": 9708.375,
"router/selected_tokens_s1": 1077.875,
"step": 550,
"tokens_trained": 1.802067184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1588539819870931,
"grad_norm": 46.87091064453125,
"loss": 1.6825,
"loss_ce": 1.963318943977356,
"loss_region": 0.06386174261569977,
"loss_total": 2.0271806716918945,
"lr": 0.001222344208686868,
"router/selected_tokens_s0": 5445.5,
"router/selected_tokens_s1": 1900.75,
"step": 560,
"tokens_trained": 1.834832624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.16169066023686263,
"grad_norm": 32.49260330200195,
"loss": 1.6009,
"loss_ce": 1.5414655208587646,
"loss_region": 0.06434743851423264,
"loss_total": 1.605812907218933,
"lr": 0.0012219373167030169,
"router/selected_tokens_s0": 8551.125,
"router/selected_tokens_s1": 655.75,
"step": 570,
"tokens_trained": 1.867598064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.16452733848663215,
"grad_norm": 16.306018829345703,
"loss": 1.4792,
"loss_ce": 1.3217185735702515,
"loss_region": 0.06380423158407211,
"loss_total": 1.3855228424072266,
"lr": 0.0012215304247191658,
"router/selected_tokens_s0": 7361.875,
"router/selected_tokens_s1": 1414.875,
"step": 580,
"tokens_trained": 1.900363504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.16736401673640167,
"grad_norm": 11.52273178100586,
"loss": 1.444,
"loss_ce": 1.2657556533813477,
"loss_region": 0.05732131749391556,
"loss_total": 1.3230769634246826,
"lr": 0.0012211235327353148,
"router/selected_tokens_s0": 7275.0,
"router/selected_tokens_s1": 6492.625,
"step": 590,
"tokens_trained": 1.933128944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17020069498617119,
"grad_norm": 9.447604179382324,
"loss": 1.4029,
"loss_ce": 1.2989217042922974,
"loss_region": 0.05687510594725609,
"loss_total": 1.3557968139648438,
"lr": 0.0012207166407514638,
"router/selected_tokens_s0": 8629.875,
"router/selected_tokens_s1": 7220.0,
"step": 600,
"tokens_trained": 1.96589048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1730373732359407,
"grad_norm": 15.3342924118042,
"loss": 1.5934,
"loss_ce": 1.3760124444961548,
"loss_region": 0.05879288166761398,
"loss_total": 1.4348052740097046,
"lr": 0.0012203097487676127,
"router/selected_tokens_s0": 12745.375,
"router/selected_tokens_s1": 8453.75,
"step": 610,
"tokens_trained": 1.99865592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17587405148571023,
"grad_norm": 13.668978691101074,
"loss": 1.4177,
"loss_ce": 1.3025627136230469,
"loss_region": 0.05752723664045334,
"loss_total": 1.360089898109436,
"lr": 0.0012199028567837617,
"router/selected_tokens_s0": 6367.875,
"router/selected_tokens_s1": 6018.25,
"step": 620,
"tokens_trained": 2.03142136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.17871072973547975,
"grad_norm": 10.949312210083008,
"loss": 1.3518,
"loss_ce": 1.2872226238250732,
"loss_region": 0.05511040613055229,
"loss_total": 1.3423330783843994,
"lr": 0.0012194959647999107,
"router/selected_tokens_s0": 10267.0,
"router/selected_tokens_s1": 9664.25,
"step": 630,
"tokens_trained": 2.0641868
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.18154740798524927,
"grad_norm": 37.183555603027344,
"loss": 1.3917,
"loss_ce": 1.5382307767868042,
"loss_region": 0.062242139130830765,
"loss_total": 1.6004729270935059,
"lr": 0.0012190890728160596,
"router/selected_tokens_s0": 4478.0,
"router/selected_tokens_s1": 2642.125,
"step": 640,
"tokens_trained": 2.09695224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.18438408623501878,
"grad_norm": 49.40961837768555,
"loss": 1.5734,
"loss_ce": 1.797605037689209,
"loss_region": 0.06264789402484894,
"loss_total": 1.8602529764175415,
"lr": 0.0012186821808322086,
"router/selected_tokens_s0": 9251.875,
"router/selected_tokens_s1": 1637.625,
"step": 650,
"tokens_trained": 2.12971768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.1872207644847883,
"grad_norm": 24.992237091064453,
"loss": 1.5306,
"loss_ce": 1.3852466344833374,
"loss_region": 0.06734807044267654,
"loss_total": 1.4525947570800781,
"lr": 0.0012182752888483576,
"router/selected_tokens_s0": 5227.5,
"router/selected_tokens_s1": 45.625,
"step": 660,
"tokens_trained": 2.16248312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.19005744273455782,
"grad_norm": 13.878795623779297,
"loss": 1.4926,
"loss_ce": 1.2988413572311401,
"loss_region": 0.06691248714923859,
"loss_total": 1.3657538890838623,
"lr": 0.0012178683968645065,
"router/selected_tokens_s0": 5859.75,
"router/selected_tokens_s1": 19.75,
"step": 670,
"tokens_trained": 2.19524856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.19289412098432734,
"grad_norm": 32.076271057128906,
"loss": 1.4449,
"loss_ce": 1.4827113151550293,
"loss_region": 0.06534749269485474,
"loss_total": 1.5480587482452393,
"lr": 0.0012174615048806555,
"router/selected_tokens_s0": 4726.125,
"router/selected_tokens_s1": 1088.125,
"step": 680,
"tokens_trained": 2.228014
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.19573079923409686,
"grad_norm": 10.969571113586426,
"loss": 1.3951,
"loss_ce": 1.2787609100341797,
"loss_region": 0.05903833732008934,
"loss_total": 1.3377991914749146,
"lr": 0.0012170546128968045,
"router/selected_tokens_s0": 9336.625,
"router/selected_tokens_s1": 5102.375,
"step": 690,
"tokens_trained": 2.26077944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.19856747748386638,
"grad_norm": 17.22534942626953,
"loss": 1.4386,
"loss_ce": 1.2547720670700073,
"loss_region": 0.060146868228912354,
"loss_total": 1.3149189949035645,
"lr": 0.0012166477209129534,
"router/selected_tokens_s0": 9219.125,
"router/selected_tokens_s1": 4007.875,
"step": 700,
"tokens_trained": 2.29354488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2014041557336359,
"grad_norm": 43.11760711669922,
"loss": 1.4423,
"loss_ce": 1.7917805910110474,
"loss_region": 0.05554146692156792,
"loss_total": 1.8473221063613892,
"lr": 0.0012162408289291026,
"router/selected_tokens_s0": 8606.125,
"router/selected_tokens_s1": 8472.0,
"step": 710,
"tokens_trained": 2.32631032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20424083398340542,
"grad_norm": 31.703508377075195,
"loss": 1.5672,
"loss_ce": 1.4175491333007812,
"loss_region": 0.05690694972872734,
"loss_total": 1.4744560718536377,
"lr": 0.0012158339369452516,
"router/selected_tokens_s0": 9807.125,
"router/selected_tokens_s1": 7348.125,
"step": 720,
"tokens_trained": 2.35907576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20707751223317494,
"grad_norm": 16.408870697021484,
"loss": 1.3753,
"loss_ce": 1.2296346426010132,
"loss_region": 0.062433354556560516,
"loss_total": 1.2920680046081543,
"lr": 0.0012154270449614005,
"router/selected_tokens_s0": 7699.0,
"router/selected_tokens_s1": 2266.625,
"step": 730,
"tokens_trained": 2.3918396
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.20991419048294446,
"grad_norm": 8.016473770141602,
"loss": 1.3183,
"loss_ce": 1.194352388381958,
"loss_region": 0.05566234141588211,
"loss_total": 1.2500147819519043,
"lr": 0.0012150201529775495,
"router/selected_tokens_s0": 8457.5,
"router/selected_tokens_s1": 8438.25,
"step": 740,
"tokens_trained": 2.424600048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.21275086873271398,
"grad_norm": 8.739754676818848,
"loss": 1.295,
"loss_ce": 1.2655029296875,
"loss_region": 0.06317088007926941,
"loss_total": 1.3286738395690918,
"lr": 0.0012146132609936982,
"router/selected_tokens_s0": 8715.875,
"router/selected_tokens_s1": 1289.125,
"step": 750,
"tokens_trained": 2.457364688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2155875469824835,
"grad_norm": 18.954246520996094,
"loss": 1.3007,
"loss_ce": 1.2969638109207153,
"loss_region": 0.0547361820936203,
"loss_total": 1.351699948310852,
"lr": 0.0012142063690098472,
"router/selected_tokens_s0": 9943.625,
"router/selected_tokens_s1": 9932.125,
"step": 760,
"tokens_trained": 2.490130128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.21842422523225302,
"grad_norm": 6.552379608154297,
"loss": 1.3183,
"loss_ce": 1.2186139822006226,
"loss_region": 0.05473633110523224,
"loss_total": 1.2733503580093384,
"lr": 0.0012137994770259962,
"router/selected_tokens_s0": 9790.875,
"router/selected_tokens_s1": 9770.5,
"step": 770,
"tokens_trained": 2.522895568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22126090348202254,
"grad_norm": 26.2993106842041,
"loss": 1.3727,
"loss_ce": 1.42295503616333,
"loss_region": 0.06471094489097595,
"loss_total": 1.4876660108566284,
"lr": 0.0012133925850421454,
"router/selected_tokens_s0": 5200.125,
"router/selected_tokens_s1": 1332.0,
"step": 780,
"tokens_trained": 2.555659392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22409758173179206,
"grad_norm": 11.26626205444336,
"loss": 1.407,
"loss_ce": 1.2448495626449585,
"loss_region": 0.05585968494415283,
"loss_total": 1.3007092475891113,
"lr": 0.0012129856930582943,
"router/selected_tokens_s0": 9143.375,
"router/selected_tokens_s1": 8323.125,
"step": 790,
"tokens_trained": 2.588422136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.22693425998156158,
"grad_norm": 7.997785568237305,
"loss": 1.3067,
"loss_ce": 1.2697006464004517,
"loss_region": 0.06230790168046951,
"loss_total": 1.3320086002349854,
"lr": 0.0012125788010744433,
"router/selected_tokens_s0": 7774.375,
"router/selected_tokens_s1": 2329.625,
"step": 800,
"tokens_trained": 2.621187576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2297709382313311,
"grad_norm": 6.670467376708984,
"loss": 1.2878,
"loss_ce": 1.2548019886016846,
"loss_region": 0.061417948454618454,
"loss_total": 1.3162199258804321,
"lr": 0.0012121719090905923,
"router/selected_tokens_s0": 9487.75,
"router/selected_tokens_s1": 2631.625,
"step": 810,
"tokens_trained": 2.653953016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.23260761648110062,
"grad_norm": 16.567520141601562,
"loss": 1.3082,
"loss_ce": 1.3074324131011963,
"loss_region": 0.05492587015032768,
"loss_total": 1.3623583316802979,
"lr": 0.0012117650171067412,
"router/selected_tokens_s0": 9648.0,
"router/selected_tokens_s1": 9643.5,
"step": 820,
"tokens_trained": 2.686718456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.23544429473087014,
"grad_norm": 3.946514844894409,
"loss": 1.2958,
"loss_ce": 1.1369494199752808,
"loss_region": 0.06178716570138931,
"loss_total": 1.198736548423767,
"lr": 0.0012113581251228902,
"router/selected_tokens_s0": 9761.0,
"router/selected_tokens_s1": 2224.75,
"step": 830,
"tokens_trained": 2.71948036
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.23828097298063966,
"grad_norm": 9.472439765930176,
"loss": 1.3045,
"loss_ce": 1.3183592557907104,
"loss_region": 0.06152363494038582,
"loss_total": 1.3798829317092896,
"lr": 0.0012109512331390391,
"router/selected_tokens_s0": 10037.5,
"router/selected_tokens_s1": 2320.0,
"step": 840,
"tokens_trained": 2.7522458
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24111765123040918,
"grad_norm": 11.188100814819336,
"loss": 1.2803,
"loss_ce": 1.2120747566223145,
"loss_region": 0.05707934871315956,
"loss_total": 1.2691540718078613,
"lr": 0.0012105443411551881,
"router/selected_tokens_s0": 7336.75,
"router/selected_tokens_s1": 6639.875,
"step": 850,
"tokens_trained": 2.78501124
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2439543294801787,
"grad_norm": 3.799870014190674,
"loss": 1.2797,
"loss_ce": 1.1893348693847656,
"loss_region": 0.06335902214050293,
"loss_total": 1.2526938915252686,
"lr": 0.001210137449171337,
"router/selected_tokens_s0": 6500.25,
"router/selected_tokens_s1": 1867.125,
"step": 860,
"tokens_trained": 2.81777668
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24679100772994822,
"grad_norm": 5.527514457702637,
"loss": 1.2928,
"loss_ce": 1.2499254941940308,
"loss_region": 0.062063559889793396,
"loss_total": 1.3119890689849854,
"lr": 0.001209730557187486,
"router/selected_tokens_s0": 6788.875,
"router/selected_tokens_s1": 2726.0,
"step": 870,
"tokens_trained": 2.85054212
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.24962768597971774,
"grad_norm": 12.200733184814453,
"loss": 1.3112,
"loss_ce": 1.310202717781067,
"loss_region": 0.06234995648264885,
"loss_total": 1.3725526332855225,
"lr": 0.001209323665203635,
"router/selected_tokens_s0": 7554.625,
"router/selected_tokens_s1": 2368.0,
"step": 880,
"tokens_trained": 2.88330756
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.25246436422948726,
"grad_norm": 12.507109642028809,
"loss": 1.3048,
"loss_ce": 1.2949899435043335,
"loss_region": 0.05900288373231888,
"loss_total": 1.3539928197860718,
"lr": 0.001208916773219784,
"router/selected_tokens_s0": 8159.375,
"router/selected_tokens_s1": 5136.375,
"step": 890,
"tokens_trained": 2.916073
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2553010424792568,
"grad_norm": 8.910531997680664,
"loss": 1.3012,
"loss_ce": 1.2440317869186401,
"loss_region": 0.06203978508710861,
"loss_total": 1.3060715198516846,
"lr": 0.001208509881235933,
"router/selected_tokens_s0": 7256.375,
"router/selected_tokens_s1": 2613.75,
"step": 900,
"tokens_trained": 2.94883828
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2581377207290263,
"grad_norm": 13.657557487487793,
"loss": 1.2896,
"loss_ce": 1.2510647773742676,
"loss_region": 0.05596454069018364,
"loss_total": 1.307029366493225,
"lr": 0.001208102989252082,
"router/selected_tokens_s0": 8780.875,
"router/selected_tokens_s1": 8493.25,
"step": 910,
"tokens_trained": 2.981597288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2609743989787958,
"grad_norm": 11.587185859680176,
"loss": 1.3346,
"loss_ce": 1.319909930229187,
"loss_region": 0.05452951416373253,
"loss_total": 1.3744394779205322,
"lr": 0.0012076960972682309,
"router/selected_tokens_s0": 12476.125,
"router/selected_tokens_s1": 11398.75,
"step": 920,
"tokens_trained": 3.014362456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.26381107722856534,
"grad_norm": 6.298766136169434,
"loss": 1.28,
"loss_ce": 1.1877198219299316,
"loss_region": 0.05859007313847542,
"loss_total": 1.2463098764419556,
"lr": 0.0012072892052843798,
"router/selected_tokens_s0": 8980.625,
"router/selected_tokens_s1": 5598.875,
"step": 930,
"tokens_trained": 3.047127096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.26664775547833486,
"grad_norm": 10.869803428649902,
"loss": 1.3065,
"loss_ce": 1.2654238939285278,
"loss_region": 0.057959433645009995,
"loss_total": 1.3233833312988281,
"lr": 0.0012068823133005288,
"router/selected_tokens_s0": 9552.375,
"router/selected_tokens_s1": 6223.0,
"step": 940,
"tokens_trained": 3.079892536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2694844337281044,
"grad_norm": 12.055986404418945,
"loss": 1.3382,
"loss_ce": 1.270828127861023,
"loss_region": 0.06640933454036713,
"loss_total": 1.3372374773025513,
"lr": 0.0012064754213166778,
"router/selected_tokens_s0": 4240.5,
"router/selected_tokens_s1": 659.375,
"step": 950,
"tokens_trained": 3.11265336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2723211119778739,
"grad_norm": 5.883482456207275,
"loss": 1.2889,
"loss_ce": 1.268551230430603,
"loss_region": 0.06191962957382202,
"loss_total": 1.3304708003997803,
"lr": 0.001206068529332827,
"router/selected_tokens_s0": 6975.625,
"router/selected_tokens_s1": 2819.0,
"step": 960,
"tokens_trained": 3.1454188
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2751577902276434,
"grad_norm": 9.4501371383667,
"loss": 1.2741,
"loss_ce": 1.213870882987976,
"loss_region": 0.062040336430072784,
"loss_total": 1.2759112119674683,
"lr": 0.001205661637348976,
"router/selected_tokens_s0": 6684.75,
"router/selected_tokens_s1": 2734.375,
"step": 970,
"tokens_trained": 3.17818424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.27799446847741294,
"grad_norm": 4.556408405303955,
"loss": 1.2736,
"loss_ce": 1.223037600517273,
"loss_region": 0.060666751116514206,
"loss_total": 1.283704400062561,
"lr": 0.0012052547453651249,
"router/selected_tokens_s0": 7010.5,
"router/selected_tokens_s1": 3735.625,
"step": 980,
"tokens_trained": 3.21094968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.28083114672718246,
"grad_norm": 3.892756700515747,
"loss": 1.2613,
"loss_ce": 1.2192856073379517,
"loss_region": 0.059792179614305496,
"loss_total": 1.2790777683258057,
"lr": 0.0012048478533812738,
"router/selected_tokens_s0": 6889.75,
"router/selected_tokens_s1": 4386.25,
"step": 990,
"tokens_trained": 3.24371512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.283667824976952,
"grad_norm": 2.7137346267700195,
"loss": 1.2637,
"loss_ce": 1.2060933113098145,
"loss_region": 0.056109219789505005,
"loss_total": 1.262202501296997,
"lr": 0.0012044409613974226,
"router/selected_tokens_s0": 8637.25,
"router/selected_tokens_s1": 8186.375,
"step": 1000,
"tokens_trained": 3.27648056
},
{
"epoch": 0.283667824976952,
"eval_ppl": 3.347568264113319,
"eval_runtime": 1.1031,
"step": 1000,
"tokens_trained": 3.27648056
},
{
"epoch": 0.283667824976952,
"eval_F": 0.38812667656327315,
"eval_F_cds": 0.42947160991705235,
"eval_F_dig": 0.25877021642315806,
"eval_F_exon": 0.38583469618819977,
"eval_F_intron": 0.38635905509328233,
"eval_F_nig": 0.38592072457131227,
"eval_F_promoter": 0.39958568949106993,
"eval_F_utr": 0.38073642711742123,
"eval_G": 0.29773473589855654,
"eval_G_cds": 0.295751199031323,
"eval_G_dig": 0.24374554408547544,
"eval_G_exon": 0.2947081099037615,
"eval_G_intron": 0.29904633539385567,
"eval_G_nig": 0.2965493859974463,
"eval_G_promoter": 0.2989992781350895,
"eval_G_utr": 0.29223971887964134,
"eval_avg_bp_per_token": 2.5764784035321986,
"eval_bp_per_token/cds": 2.3284426185776024,
"eval_bp_per_token/dig": 3.8644323671497585,
"eval_bp_per_token/exon": 2.5917835017932833,
"eval_bp_per_token/intron": 2.5882659842372804,
"eval_bp_per_token/nig": 2.591205748566155,
"eval_bp_per_token/promoter": 2.5025921255429453,
"eval_bp_per_token/utr": 2.6264889009204113,
"eval_ppl_cds": 3.903673949165709,
"eval_ppl_dig": 2.2362627784464695,
"eval_ppl_exon": 3.620784098443495,
"eval_ppl_intron": 3.3564639530661875,
"eval_ppl_nig": 3.33227950140761,
"eval_ppl_promoter": 3.551608871404792,
"eval_ppl_utr": 3.539918557582459,
"step": 1000,
"tokens_trained": 3.27648056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2865045032267215,
"grad_norm": 4.771963596343994,
"loss": 1.2563,
"loss_ce": 1.224116325378418,
"loss_region": 0.06507018953561783,
"loss_total": 1.2891864776611328,
"lr": 0.0012040340694135716,
"router/selected_tokens_s0": 5890.875,
"router/selected_tokens_s1": 891.375,
"step": 1010,
"tokens_trained": 3.309246
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.289341181476491,
"grad_norm": 7.340773105621338,
"loss": 1.2573,
"loss_ce": 1.214971899986267,
"loss_region": 0.062319301068782806,
"loss_total": 1.277291178703308,
"lr": 0.0012036271774297205,
"router/selected_tokens_s0": 7923.625,
"router/selected_tokens_s1": 2285.625,
"step": 1020,
"tokens_trained": 3.34201144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.29217785972626054,
"grad_norm": 6.7468695640563965,
"loss": 1.266,
"loss_ce": 1.1905633211135864,
"loss_region": 0.06161874532699585,
"loss_total": 1.2521820068359375,
"lr": 0.0012032202854458697,
"router/selected_tokens_s0": 7226.75,
"router/selected_tokens_s1": 2999.375,
"step": 1030,
"tokens_trained": 3.37477688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.29501453797603006,
"grad_norm": 14.67007064819336,
"loss": 1.2801,
"loss_ce": 1.2074471712112427,
"loss_region": 0.0633462518453598,
"loss_total": 1.2707934379577637,
"lr": 0.0012028133934620187,
"router/selected_tokens_s0": 7503.625,
"router/selected_tokens_s1": 1578.5,
"step": 1040,
"tokens_trained": 3.40754232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.2978512162257996,
"grad_norm": 13.262823104858398,
"loss": 1.2987,
"loss_ce": 1.2933048009872437,
"loss_region": 0.05701930820941925,
"loss_total": 1.3503241539001465,
"lr": 0.0012024065014781676,
"router/selected_tokens_s0": 7261.0,
"router/selected_tokens_s1": 6672.0,
"step": 1050,
"tokens_trained": 3.44030696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3006878944755691,
"grad_norm": 9.318674087524414,
"loss": 1.2813,
"loss_ce": 1.2383909225463867,
"loss_region": 0.057740017771720886,
"loss_total": 1.296130895614624,
"lr": 0.0012019996094943166,
"router/selected_tokens_s0": 7121.25,
"router/selected_tokens_s1": 6015.625,
"step": 1060,
"tokens_trained": 3.4730724
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3035245727253386,
"grad_norm": 5.476803302764893,
"loss": 1.2668,
"loss_ce": 1.1896486282348633,
"loss_region": 0.06287642568349838,
"loss_total": 1.2525250911712646,
"lr": 0.0012015927175104656,
"router/selected_tokens_s0": 7913.25,
"router/selected_tokens_s1": 1923.375,
"step": 1070,
"tokens_trained": 3.50583784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.30636125097510813,
"grad_norm": 3.5230581760406494,
"loss": 1.2474,
"loss_ce": 1.2183582782745361,
"loss_region": 0.058486904948949814,
"loss_total": 1.2768452167510986,
"lr": 0.0012011858255266145,
"router/selected_tokens_s0": 7827.0,
"router/selected_tokens_s1": 5555.25,
"step": 1080,
"tokens_trained": 3.53860328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.30919792922487765,
"grad_norm": 2.5523219108581543,
"loss": 1.2465,
"loss_ce": 1.1812347173690796,
"loss_region": 0.05868714675307274,
"loss_total": 1.2399218082427979,
"lr": 0.0012007789335427635,
"router/selected_tokens_s0": 6969.25,
"router/selected_tokens_s1": 5216.25,
"step": 1090,
"tokens_trained": 3.57136872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3120346074746472,
"grad_norm": 3.7527999877929688,
"loss": 1.2463,
"loss_ce": 1.141882300376892,
"loss_region": 0.06176374852657318,
"loss_total": 1.2036460638046265,
"lr": 0.0012003720415589125,
"router/selected_tokens_s0": 7818.0,
"router/selected_tokens_s1": 2807.0,
"step": 1100,
"tokens_trained": 3.60413416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3148712857244167,
"grad_norm": 4.556453227996826,
"loss": 1.2456,
"loss_ce": 1.186132788658142,
"loss_region": 0.057535041123628616,
"loss_total": 1.2436678409576416,
"lr": 0.0011999651495750614,
"router/selected_tokens_s0": 7479.125,
"router/selected_tokens_s1": 6318.5,
"step": 1110,
"tokens_trained": 3.6368996
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3177079639741862,
"grad_norm": 5.769139289855957,
"loss": 1.2386,
"loss_ce": 1.205984115600586,
"loss_region": 0.0598924346268177,
"loss_total": 1.2658765316009521,
"lr": 0.0011995582575912104,
"router/selected_tokens_s0": 6577.125,
"router/selected_tokens_s1": 4283.625,
"step": 1120,
"tokens_trained": 3.669661712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.32054464222395573,
"grad_norm": 5.950888633728027,
"loss": 1.2417,
"loss_ce": 1.1921892166137695,
"loss_region": 0.05988103523850441,
"loss_total": 1.2520703077316284,
"lr": 0.0011991513656073594,
"router/selected_tokens_s0": 5852.625,
"router/selected_tokens_s1": 4155.75,
"step": 1130,
"tokens_trained": 3.702426352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.32338132047372525,
"grad_norm": 9.715873718261719,
"loss": 1.2429,
"loss_ce": 1.213543176651001,
"loss_region": 0.060164351016283035,
"loss_total": 1.2737075090408325,
"lr": 0.0011987444736235083,
"router/selected_tokens_s0": 6526.5,
"router/selected_tokens_s1": 4105.125,
"step": 1140,
"tokens_trained": 3.735191792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3262179987234948,
"grad_norm": 3.8173344135284424,
"loss": 1.2484,
"loss_ce": 1.1513862609863281,
"loss_region": 0.06401993334293365,
"loss_total": 1.2154061794281006,
"lr": 0.0011983375816396573,
"router/selected_tokens_s0": 5951.125,
"router/selected_tokens_s1": 1578.5,
"step": 1150,
"tokens_trained": 3.767957232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3290546769732643,
"grad_norm": 4.6551833152771,
"loss": 1.2419,
"loss_ce": 1.2406567335128784,
"loss_region": 0.06077444925904274,
"loss_total": 1.3014311790466309,
"lr": 0.0011979306896558062,
"router/selected_tokens_s0": 7148.375,
"router/selected_tokens_s1": 3660.125,
"step": 1160,
"tokens_trained": 3.800722672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3318913552230338,
"grad_norm": 8.04861831665039,
"loss": 1.2343,
"loss_ce": 1.1574338674545288,
"loss_region": 0.060126934200525284,
"loss_total": 1.2175607681274414,
"lr": 0.0011975237976719552,
"router/selected_tokens_s0": 7432.375,
"router/selected_tokens_s1": 4170.875,
"step": 1170,
"tokens_trained": 3.833488112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.33472803347280333,
"grad_norm": 1.6629078388214111,
"loss": 1.2338,
"loss_ce": 1.1838352680206299,
"loss_region": 0.06075272709131241,
"loss_total": 1.244588017463684,
"lr": 0.0011971169056881042,
"router/selected_tokens_s0": 7034.375,
"router/selected_tokens_s1": 3672.375,
"step": 1180,
"tokens_trained": 3.866252752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.33756471172257285,
"grad_norm": 2.558566093444824,
"loss": 1.2326,
"loss_ce": 1.1726329326629639,
"loss_region": 0.05713306739926338,
"loss_total": 1.2297660112380981,
"lr": 0.0011967100137042531,
"router/selected_tokens_s0": 7075.5,
"router/selected_tokens_s1": 6530.625,
"step": 1190,
"tokens_trained": 3.899018184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.34040138997234237,
"grad_norm": 5.142763137817383,
"loss": 1.2306,
"loss_ce": 1.1462597846984863,
"loss_region": 0.06102370843291283,
"loss_total": 1.2072834968566895,
"lr": 0.0011963031217204021,
"router/selected_tokens_s0": 7709.875,
"router/selected_tokens_s1": 3417.375,
"step": 1200,
"tokens_trained": 3.931783624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3432380682221119,
"grad_norm": 2.3559539318084717,
"loss": 1.227,
"loss_ce": 1.1722111701965332,
"loss_region": 0.05798247084021568,
"loss_total": 1.2301936149597168,
"lr": 0.0011958962297365513,
"router/selected_tokens_s0": 7702.75,
"router/selected_tokens_s1": 5993.375,
"step": 1210,
"tokens_trained": 3.964549064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3460747464718814,
"grad_norm": 5.716832160949707,
"loss": 1.2248,
"loss_ce": 1.1278504133224487,
"loss_region": 0.06037168204784393,
"loss_total": 1.188222050666809,
"lr": 0.0011954893377527003,
"router/selected_tokens_s0": 6809.375,
"router/selected_tokens_s1": 3940.0,
"step": 1220,
"tokens_trained": 3.997311912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.34891142472165093,
"grad_norm": 8.192803382873535,
"loss": 1.2482,
"loss_ce": 1.208156704902649,
"loss_region": 0.0598159022629261,
"loss_total": 1.2679725885391235,
"lr": 0.0011950824457688492,
"router/selected_tokens_s0": 7796.0,
"router/selected_tokens_s1": 4444.75,
"step": 1230,
"tokens_trained": 4.030077352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.35174810297142045,
"grad_norm": 4.9980010986328125,
"loss": 1.2321,
"loss_ce": 1.1176339387893677,
"loss_region": 0.05978400260210037,
"loss_total": 1.1774179935455322,
"lr": 0.0011946755537849982,
"router/selected_tokens_s0": 7440.75,
"router/selected_tokens_s1": 4458.25,
"step": 1240,
"tokens_trained": 4.062842792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.35458478122118997,
"grad_norm": 1.7752015590667725,
"loss": 1.2207,
"loss_ce": 1.184716820716858,
"loss_region": 0.05878889188170433,
"loss_total": 1.2435057163238525,
"lr": 0.001194268661801147,
"router/selected_tokens_s0": 7180.375,
"router/selected_tokens_s1": 5210.5,
"step": 1250,
"tokens_trained": 4.095608232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3574214594709595,
"grad_norm": 3.125553607940674,
"loss": 1.2205,
"loss_ce": 1.1985727548599243,
"loss_region": 0.06049454212188721,
"loss_total": 1.2590672969818115,
"lr": 0.001193861769817296,
"router/selected_tokens_s0": 7793.875,
"router/selected_tokens_s1": 3874.875,
"step": 1260,
"tokens_trained": 4.128373672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.360258137720729,
"grad_norm": 3.002474546432495,
"loss": 1.2223,
"loss_ce": 1.215548038482666,
"loss_region": 0.06029829755425453,
"loss_total": 1.2758463621139526,
"lr": 0.0011934548778334449,
"router/selected_tokens_s0": 7393.25,
"router/selected_tokens_s1": 4025.25,
"step": 1270,
"tokens_trained": 4.161136768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36309481597049853,
"grad_norm": 3.3697590827941895,
"loss": 1.2242,
"loss_ce": 1.167251467704773,
"loss_region": 0.061523206532001495,
"loss_total": 1.2287746667861938,
"lr": 0.001193047985849594,
"router/selected_tokens_s0": 7325.625,
"router/selected_tokens_s1": 3059.375,
"step": 1280,
"tokens_trained": 4.193902208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36593149422026805,
"grad_norm": 2.45526123046875,
"loss": 1.2241,
"loss_ce": 1.2129099369049072,
"loss_region": 0.059980034828186035,
"loss_total": 1.2728899717330933,
"lr": 0.001192641093865743,
"router/selected_tokens_s0": 7482.25,
"router/selected_tokens_s1": 4287.625,
"step": 1290,
"tokens_trained": 4.226667648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.36876817247003757,
"grad_norm": 2.280808448791504,
"loss": 1.2237,
"loss_ce": 1.1102901697158813,
"loss_region": 0.05960178002715111,
"loss_total": 1.1698919534683228,
"lr": 0.001192234201881892,
"router/selected_tokens_s0": 7548.625,
"router/selected_tokens_s1": 4616.25,
"step": 1300,
"tokens_trained": 4.259424272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3716048507198071,
"grad_norm": 1.7201220989227295,
"loss": 1.2133,
"loss_ce": 1.0806467533111572,
"loss_region": 0.06031251698732376,
"loss_total": 1.1409592628479004,
"lr": 0.001191827309898041,
"router/selected_tokens_s0": 7452.0,
"router/selected_tokens_s1": 4023.25,
"step": 1310,
"tokens_trained": 4.292189712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3744415289695766,
"grad_norm": 1.477432131767273,
"loss": 1.2134,
"loss_ce": 1.1256206035614014,
"loss_region": 0.058301862329244614,
"loss_total": 1.1839224100112915,
"lr": 0.00119142041791419,
"router/selected_tokens_s0": 7398.875,
"router/selected_tokens_s1": 5646.875,
"step": 1320,
"tokens_trained": 4.32495164
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.37727820721934613,
"grad_norm": 2.436877727508545,
"loss": 1.2179,
"loss_ce": 1.0498384237289429,
"loss_region": 0.05817071720957756,
"loss_total": 1.1080090999603271,
"lr": 0.0011910135259303389,
"router/selected_tokens_s0": 7537.0,
"router/selected_tokens_s1": 5800.375,
"step": 1330,
"tokens_trained": 4.35771708
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.38011488546911565,
"grad_norm": 4.487268447875977,
"loss": 1.2305,
"loss_ce": 1.2367991209030151,
"loss_region": 0.06230239197611809,
"loss_total": 1.29910147190094,
"lr": 0.0011906066339464878,
"router/selected_tokens_s0": 7214.25,
"router/selected_tokens_s1": 2476.375,
"step": 1340,
"tokens_trained": 4.39048252
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.38295156371888517,
"grad_norm": 3.622452735900879,
"loss": 1.214,
"loss_ce": 1.0572057962417603,
"loss_region": 0.059732843190431595,
"loss_total": 1.116938591003418,
"lr": 0.0011901997419626368,
"router/selected_tokens_s0": 7352.625,
"router/selected_tokens_s1": 4475.625,
"step": 1350,
"tokens_trained": 4.42324796
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3857882419686547,
"grad_norm": 2.1303977966308594,
"loss": 1.213,
"loss_ce": 1.159555435180664,
"loss_region": 0.060326918959617615,
"loss_total": 1.2198823690414429,
"lr": 0.0011897928499787858,
"router/selected_tokens_s0": 7290.625,
"router/selected_tokens_s1": 3996.0,
"step": 1360,
"tokens_trained": 4.4560134
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3886249202184242,
"grad_norm": 1.6034486293792725,
"loss": 1.2153,
"loss_ce": 1.1271262168884277,
"loss_region": 0.06016794219613075,
"loss_total": 1.1872941255569458,
"lr": 0.0011893859579949347,
"router/selected_tokens_s0": 7241.375,
"router/selected_tokens_s1": 4116.75,
"step": 1370,
"tokens_trained": 4.48877884
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3914615984681937,
"grad_norm": 0.8884724974632263,
"loss": 1.2086,
"loss_ce": 1.1884993314743042,
"loss_region": 0.05992608517408371,
"loss_total": 1.2484253644943237,
"lr": 0.0011889790660110837,
"router/selected_tokens_s0": 7768.375,
"router/selected_tokens_s1": 4367.875,
"step": 1380,
"tokens_trained": 4.52154428
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.39429827671796325,
"grad_norm": 1.7758926153182983,
"loss": 1.2076,
"loss_ce": 1.1677520275115967,
"loss_region": 0.05958346277475357,
"loss_total": 1.2273354530334473,
"lr": 0.0011885721740272327,
"router/selected_tokens_s0": 7557.875,
"router/selected_tokens_s1": 4631.375,
"step": 1390,
"tokens_trained": 4.55430972
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.39713495496773277,
"grad_norm": 1.3425244092941284,
"loss": 1.2121,
"loss_ce": 0.9700872302055359,
"loss_region": 0.05964002013206482,
"loss_total": 1.0297272205352783,
"lr": 0.0011881652820433816,
"router/selected_tokens_s0": 7196.75,
"router/selected_tokens_s1": 4533.0,
"step": 1400,
"tokens_trained": 4.58707516
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.3999716332175023,
"grad_norm": 1.086186408996582,
"loss": 1.2112,
"loss_ce": 1.13883638381958,
"loss_region": 0.05995158478617668,
"loss_total": 1.1987879276275635,
"lr": 0.0011877583900595306,
"router/selected_tokens_s0": 7518.25,
"router/selected_tokens_s1": 4321.125,
"step": 1410,
"tokens_trained": 4.6198406
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4028083114672718,
"grad_norm": 1.7367637157440186,
"loss": 1.2049,
"loss_ce": 1.155705213546753,
"loss_region": 0.06088727340102196,
"loss_total": 1.2165924310684204,
"lr": 0.0011873514980756796,
"router/selected_tokens_s0": 6863.0,
"router/selected_tokens_s1": 3570.375,
"step": 1420,
"tokens_trained": 4.652606024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4056449897170413,
"grad_norm": 5.4363789558410645,
"loss": 1.238,
"loss_ce": 1.1930514574050903,
"loss_region": 0.05885593220591545,
"loss_total": 1.2519073486328125,
"lr": 0.0011869446060918285,
"router/selected_tokens_s0": 7346.125,
"router/selected_tokens_s1": 5190.25,
"step": 1430,
"tokens_trained": 4.685371464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.40848166796681085,
"grad_norm": 3.524890899658203,
"loss": 1.223,
"loss_ce": 1.184119701385498,
"loss_region": 0.05786283686757088,
"loss_total": 1.2419825792312622,
"lr": 0.0011865377141079775,
"router/selected_tokens_s0": 7959.5,
"router/selected_tokens_s1": 6231.5,
"step": 1440,
"tokens_trained": 4.718136904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.41131834621658037,
"grad_norm": 2.0465176105499268,
"loss": 1.2131,
"loss_ce": 1.2069507837295532,
"loss_region": 0.061854004859924316,
"loss_total": 1.2688047885894775,
"lr": 0.0011861308221241265,
"router/selected_tokens_s0": 7283.625,
"router/selected_tokens_s1": 2811.625,
"step": 1450,
"tokens_trained": 4.750902344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4141550244663499,
"grad_norm": 1.2570910453796387,
"loss": 1.2008,
"loss_ce": 1.2179498672485352,
"loss_region": 0.062061723321676254,
"loss_total": 1.280011534690857,
"lr": 0.0011857239301402756,
"router/selected_tokens_s0": 7247.25,
"router/selected_tokens_s1": 2646.375,
"step": 1460,
"tokens_trained": 4.783666984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4169917027161194,
"grad_norm": 1.7545820474624634,
"loss": 1.2037,
"loss_ce": 1.206125020980835,
"loss_region": 0.06104295700788498,
"loss_total": 1.2671679258346558,
"lr": 0.0011853170381564246,
"router/selected_tokens_s0": 7784.375,
"router/selected_tokens_s1": 3447.5,
"step": 1470,
"tokens_trained": 4.816432424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4198283809658889,
"grad_norm": 0.8268412947654724,
"loss": 1.1988,
"loss_ce": 1.0823899507522583,
"loss_region": 0.06159386783838272,
"loss_total": 1.1439838409423828,
"lr": 0.0011849101461725736,
"router/selected_tokens_s0": 7545.125,
"router/selected_tokens_s1": 2985.0,
"step": 1480,
"tokens_trained": 4.849197864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.42266505921565845,
"grad_norm": 1.3997455835342407,
"loss": 1.2004,
"loss_ce": 1.211706280708313,
"loss_region": 0.061140816658735275,
"loss_total": 1.272847056388855,
"lr": 0.0011845032541887225,
"router/selected_tokens_s0": 7438.125,
"router/selected_tokens_s1": 3359.0,
"step": 1490,
"tokens_trained": 4.881963248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.42550173746542796,
"grad_norm": 1.2946134805679321,
"loss": 1.208,
"loss_ce": 1.131969928741455,
"loss_region": 0.06115822494029999,
"loss_total": 1.1931281089782715,
"lr": 0.0011840963622048713,
"router/selected_tokens_s0": 7596.125,
"router/selected_tokens_s1": 3365.25,
"step": 1500,
"tokens_trained": 4.914728608
},
{
"epoch": 0.42550173746542796,
"eval_ppl": 3.1621453960135706,
"eval_runtime": 1.0551,
"step": 1500,
"tokens_trained": 4.914728608
},
{
"epoch": 0.42550173746542796,
"eval_F": 0.3383701851707165,
"eval_F_cds": 0.32189175564822875,
"eval_F_dig": 0.30971169622626765,
"eval_F_exon": 0.34561999412924055,
"eval_F_intron": 0.34410581946232166,
"eval_F_nig": 0.3375343459013891,
"eval_F_promoter": 0.31860851389433215,
"eval_F_utr": 0.3465690947975985,
"eval_G": 0.2924601907782509,
"eval_G_cds": 0.2914013539852665,
"eval_G_dig": 0.2889913884873818,
"eval_G_exon": 0.2899214097947331,
"eval_G_intron": 0.2925929726588761,
"eval_G_nig": 0.29211948150012085,
"eval_G_promoter": 0.29322862355481216,
"eval_G_utr": 0.29183338191527736,
"eval_avg_bp_per_token": 2.955343123672301,
"eval_bp_per_token/cds": 3.106634396355353,
"eval_bp_per_token/dig": 3.2288092835519677,
"eval_bp_per_token/exon": 2.893351128366901,
"eval_bp_per_token/intron": 2.9060827903536706,
"eval_bp_per_token/nig": 2.962661465841318,
"eval_bp_per_token/promoter": 3.1386480787253985,
"eval_bp_per_token/utr": 2.88542750929368,
"eval_ppl_cds": 3.7980160314314775,
"eval_ppl_dig": 1.3756820840176516,
"eval_ppl_exon": 3.52970478822946,
"eval_ppl_intron": 3.1966549688737778,
"eval_ppl_nig": 3.043349946903372,
"eval_ppl_promoter": 3.4552084267408065,
"eval_ppl_utr": 3.438440616943856,
"step": 1500,
"tokens_trained": 4.914728608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4283384157151975,
"grad_norm": 1.6150286197662354,
"loss": 1.2087,
"loss_ce": 1.2292938232421875,
"loss_region": 0.06086890026926994,
"loss_total": 1.2901626825332642,
"lr": 0.0011836894702210202,
"router/selected_tokens_s0": 7728.625,
"router/selected_tokens_s1": 3601.125,
"step": 1510,
"tokens_trained": 4.947494048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.431175093964967,
"grad_norm": 5.560505390167236,
"loss": 1.2111,
"loss_ce": 1.2069859504699707,
"loss_region": 0.0635954886674881,
"loss_total": 1.2705814838409424,
"lr": 0.0011832825782371692,
"router/selected_tokens_s0": 6884.125,
"router/selected_tokens_s1": 1571.875,
"step": 1520,
"tokens_trained": 4.980259488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4340117722147365,
"grad_norm": 2.3368101119995117,
"loss": 1.2138,
"loss_ce": 1.1481984853744507,
"loss_region": 0.05834292247891426,
"loss_total": 1.2065414190292358,
"lr": 0.0011828756862533184,
"router/selected_tokens_s0": 7559.875,
"router/selected_tokens_s1": 5684.875,
"step": 1530,
"tokens_trained": 5.013024928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.43684845046450604,
"grad_norm": 1.1860406398773193,
"loss": 1.2027,
"loss_ce": 1.1155500411987305,
"loss_region": 0.058888982981443405,
"loss_total": 1.1744390726089478,
"lr": 0.0011824687942694674,
"router/selected_tokens_s0": 7458.25,
"router/selected_tokens_s1": 5186.0,
"step": 1540,
"tokens_trained": 5.04578704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.43968512871427556,
"grad_norm": 1.4350230693817139,
"loss": 1.202,
"loss_ce": 1.1809712648391724,
"loss_region": 0.06128743663430214,
"loss_total": 1.2422586679458618,
"lr": 0.0011820619022856163,
"router/selected_tokens_s0": 7819.25,
"router/selected_tokens_s1": 3293.5,
"step": 1550,
"tokens_trained": 5.078551904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4425218069640451,
"grad_norm": 0.8890047073364258,
"loss": 1.2026,
"loss_ce": 1.07762610912323,
"loss_region": 0.06053788587450981,
"loss_total": 1.1381640434265137,
"lr": 0.0011816550103017653,
"router/selected_tokens_s0": 7270.375,
"router/selected_tokens_s1": 3828.25,
"step": 1560,
"tokens_trained": 5.111317344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4453584852138146,
"grad_norm": 0.7954491376876831,
"loss": 1.2054,
"loss_ce": 1.219533085823059,
"loss_region": 0.06046753376722336,
"loss_total": 1.2800005674362183,
"lr": 0.0011812481183179143,
"router/selected_tokens_s0": 7368.375,
"router/selected_tokens_s1": 3893.25,
"step": 1570,
"tokens_trained": 5.144082784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4481951634635841,
"grad_norm": 1.1368037462234497,
"loss": 1.199,
"loss_ce": 1.144284725189209,
"loss_region": 0.060155730694532394,
"loss_total": 1.2044404745101929,
"lr": 0.0011808412263340632,
"router/selected_tokens_s0": 7437.125,
"router/selected_tokens_s1": 4154.25,
"step": 1580,
"tokens_trained": 5.176848224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.45103184171335364,
"grad_norm": 2.1435985565185547,
"loss": 1.2037,
"loss_ce": 1.131495714187622,
"loss_region": 0.05997314676642418,
"loss_total": 1.1914688348770142,
"lr": 0.0011804343343502122,
"router/selected_tokens_s0": 7080.125,
"router/selected_tokens_s1": 4246.5,
"step": 1590,
"tokens_trained": 5.209613664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.45386851996312316,
"grad_norm": 4.92233419418335,
"loss": 1.2057,
"loss_ce": 1.214929223060608,
"loss_region": 0.06080314517021179,
"loss_total": 1.275732398033142,
"lr": 0.0011800274423663611,
"router/selected_tokens_s0": 7388.875,
"router/selected_tokens_s1": 3633.0,
"step": 1600,
"tokens_trained": 5.242378304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4567051982128927,
"grad_norm": 5.72175931930542,
"loss": 1.2192,
"loss_ce": 1.1509543657302856,
"loss_region": 0.05994424968957901,
"loss_total": 1.2108986377716064,
"lr": 0.0011796205503825101,
"router/selected_tokens_s0": 7110.75,
"router/selected_tokens_s1": 4277.75,
"step": 1610,
"tokens_trained": 5.275142944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4595418764626622,
"grad_norm": 0.9513784050941467,
"loss": 1.211,
"loss_ce": 1.1676510572433472,
"loss_region": 0.058869313448667526,
"loss_total": 1.2265204191207886,
"lr": 0.001179213658398659,
"router/selected_tokens_s0": 8026.375,
"router/selected_tokens_s1": 5480.0,
"step": 1620,
"tokens_trained": 5.307906784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4623785547124317,
"grad_norm": 1.5998790264129639,
"loss": 1.2047,
"loss_ce": 1.0538767576217651,
"loss_region": 0.05941499024629593,
"loss_total": 1.1132917404174805,
"lr": 0.001178806766414808,
"router/selected_tokens_s0": 7281.5,
"router/selected_tokens_s1": 4720.625,
"step": 1630,
"tokens_trained": 5.340672224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.46521523296220124,
"grad_norm": 0.5995892286300659,
"loss": 1.2167,
"loss_ce": 1.1786582469940186,
"loss_region": 0.059631455689668655,
"loss_total": 1.238289713859558,
"lr": 0.001178399874430957,
"router/selected_tokens_s0": 7377.5,
"router/selected_tokens_s1": 4563.125,
"step": 1640,
"tokens_trained": 5.373436896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.46805191121197076,
"grad_norm": 1.8776949644088745,
"loss": 1.2252,
"loss_ce": 1.2116706371307373,
"loss_region": 0.058519087731838226,
"loss_total": 1.2701897621154785,
"lr": 0.001177992982447106,
"router/selected_tokens_s0": 7360.625,
"router/selected_tokens_s1": 5456.625,
"step": 1650,
"tokens_trained": 5.406202336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4708885894617403,
"grad_norm": 0.9382694363594055,
"loss": 1.2314,
"loss_ce": 1.1839154958724976,
"loss_region": 0.05979941412806511,
"loss_total": 1.2437149286270142,
"lr": 0.001177586090463255,
"router/selected_tokens_s0": 7499.125,
"router/selected_tokens_s1": 4458.75,
"step": 1660,
"tokens_trained": 5.438967776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4737252677115098,
"grad_norm": 1.2017229795455933,
"loss": 1.2312,
"loss_ce": 1.1372504234313965,
"loss_region": 0.059748563915491104,
"loss_total": 1.196998953819275,
"lr": 0.001177179198479404,
"router/selected_tokens_s0": 7295.375,
"router/selected_tokens_s1": 4452.5,
"step": 1670,
"tokens_trained": 5.471733216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4765619459612793,
"grad_norm": 1.8002878427505493,
"loss": 1.2231,
"loss_ce": 1.1727172136306763,
"loss_region": 0.060064543038606644,
"loss_total": 1.2327817678451538,
"lr": 0.0011767723064955529,
"router/selected_tokens_s0": 7462.25,
"router/selected_tokens_s1": 4250.375,
"step": 1680,
"tokens_trained": 5.504498656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.47939862421104884,
"grad_norm": 1.8060473203659058,
"loss": 1.2174,
"loss_ce": 1.152571201324463,
"loss_region": 0.0597725547850132,
"loss_total": 1.2123438119888306,
"lr": 0.0011763654145117018,
"router/selected_tokens_s0": 7397.25,
"router/selected_tokens_s1": 4450.125,
"step": 1690,
"tokens_trained": 5.537264096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.48223530246081836,
"grad_norm": 0.5139926671981812,
"loss": 1.2158,
"loss_ce": 1.1350646018981934,
"loss_region": 0.05997651070356369,
"loss_total": 1.1950410604476929,
"lr": 0.0011759585225278508,
"router/selected_tokens_s0": 7432.5,
"router/selected_tokens_s1": 4295.5,
"step": 1700,
"tokens_trained": 5.570029536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4850719807105879,
"grad_norm": 1.5214523077011108,
"loss": 1.2131,
"loss_ce": 1.0787264108657837,
"loss_region": 0.059902340173721313,
"loss_total": 1.1386287212371826,
"lr": 0.001175551630544,
"router/selected_tokens_s0": 7345.875,
"router/selected_tokens_s1": 4338.75,
"step": 1710,
"tokens_trained": 5.602794976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4879086589603574,
"grad_norm": 0.5068179368972778,
"loss": 1.2096,
"loss_ce": 1.1360502243041992,
"loss_region": 0.060493726283311844,
"loss_total": 1.1965439319610596,
"lr": 0.001175144738560149,
"router/selected_tokens_s0": 7206.5,
"router/selected_tokens_s1": 3846.125,
"step": 1720,
"tokens_trained": 5.635560416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4907453372101269,
"grad_norm": 0.4137960970401764,
"loss": 1.2064,
"loss_ce": 1.2108829021453857,
"loss_region": 0.05981894209980965,
"loss_total": 1.2707018852233887,
"lr": 0.001174737846576298,
"router/selected_tokens_s0": 7653.0,
"router/selected_tokens_s1": 4487.625,
"step": 1730,
"tokens_trained": 5.668325856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.49358201545989644,
"grad_norm": 0.8189796805381775,
"loss": 1.2067,
"loss_ce": 1.1404913663864136,
"loss_region": 0.05990920960903168,
"loss_total": 1.2004005908966064,
"lr": 0.0011743309545924469,
"router/selected_tokens_s0": 7451.125,
"router/selected_tokens_s1": 4361.125,
"step": 1740,
"tokens_trained": 5.701091296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.49641869370966596,
"grad_norm": 0.8574137687683105,
"loss": 1.2035,
"loss_ce": 1.1549724340438843,
"loss_region": 0.05982809513807297,
"loss_total": 1.214800477027893,
"lr": 0.0011739240626085956,
"router/selected_tokens_s0": 7422.875,
"router/selected_tokens_s1": 4414.75,
"step": 1750,
"tokens_trained": 5.733856736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.4992553719594355,
"grad_norm": 1.5001907348632812,
"loss": 1.2017,
"loss_ce": 1.1385822296142578,
"loss_region": 0.06083447486162186,
"loss_total": 1.1994167566299438,
"lr": 0.0011735171706247446,
"router/selected_tokens_s0": 7473.375,
"router/selected_tokens_s1": 3602.625,
"step": 1760,
"tokens_trained": 5.766622176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.502092050209205,
"grad_norm": 1.8692625761032104,
"loss": 1.202,
"loss_ce": 1.2150356769561768,
"loss_region": 0.060022830963134766,
"loss_total": 1.2750585079193115,
"lr": 0.0011731102786408936,
"router/selected_tokens_s0": 7648.0,
"router/selected_tokens_s1": 4317.5,
"step": 1770,
"tokens_trained": 5.799387616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5049287284589745,
"grad_norm": 1.3365726470947266,
"loss": 1.2043,
"loss_ce": 1.0311381816864014,
"loss_region": 0.060505885630846024,
"loss_total": 1.091644048690796,
"lr": 0.0011727033866570427,
"router/selected_tokens_s0": 7286.75,
"router/selected_tokens_s1": 3841.0,
"step": 1780,
"tokens_trained": 5.832153056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.507765406708744,
"grad_norm": 0.8497097492218018,
"loss": 1.1973,
"loss_ce": 1.0274080038070679,
"loss_region": 0.05991562083363533,
"loss_total": 1.0873236656188965,
"lr": 0.0011722964946731917,
"router/selected_tokens_s0": 7360.125,
"router/selected_tokens_s1": 4338.75,
"step": 1790,
"tokens_trained": 5.864918496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5106020849585136,
"grad_norm": 1.7930278778076172,
"loss": 1.1965,
"loss_ce": 1.0668989419937134,
"loss_region": 0.06032132729887962,
"loss_total": 1.1272202730178833,
"lr": 0.0011718896026893407,
"router/selected_tokens_s0": 7489.25,
"router/selected_tokens_s1": 4029.0,
"step": 1800,
"tokens_trained": 5.897683936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5134387632082831,
"grad_norm": 0.5829694271087646,
"loss": 1.1941,
"loss_ce": 1.115596890449524,
"loss_region": 0.05983370915055275,
"loss_total": 1.1754306554794312,
"lr": 0.0011714827107054896,
"router/selected_tokens_s0": 7556.25,
"router/selected_tokens_s1": 4460.375,
"step": 1810,
"tokens_trained": 5.930449376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5162754414580526,
"grad_norm": 0.7106938362121582,
"loss": 1.1921,
"loss_ce": 1.0678681135177612,
"loss_region": 0.060275427997112274,
"loss_total": 1.128143548965454,
"lr": 0.0011710758187216386,
"router/selected_tokens_s0": 7005.0,
"router/selected_tokens_s1": 4000.75,
"step": 1820,
"tokens_trained": 5.96321104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5191121197078221,
"grad_norm": 0.64195317029953,
"loss": 1.1967,
"loss_ce": 1.1604429483413696,
"loss_region": 0.05958753824234009,
"loss_total": 1.2200305461883545,
"lr": 0.0011706689267377876,
"router/selected_tokens_s0": 7597.75,
"router/selected_tokens_s1": 4673.875,
"step": 1830,
"tokens_trained": 5.99597648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5219487979575916,
"grad_norm": 0.7763417959213257,
"loss": 1.1938,
"loss_ce": 1.138045072555542,
"loss_region": 0.05993033945560455,
"loss_total": 1.1979753971099854,
"lr": 0.0011702620347539365,
"router/selected_tokens_s0": 7406.0,
"router/selected_tokens_s1": 4328.75,
"step": 1840,
"tokens_trained": 6.028741744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5247854762073612,
"grad_norm": 1.4419437646865845,
"loss": 1.1946,
"loss_ce": 1.0854356288909912,
"loss_region": 0.06058506295084953,
"loss_total": 1.1460206508636475,
"lr": 0.0011698551427700855,
"router/selected_tokens_s0": 7468.625,
"router/selected_tokens_s1": 3814.0,
"step": 1850,
"tokens_trained": 6.061507184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5276221544571307,
"grad_norm": 0.4786941111087799,
"loss": 1.198,
"loss_ce": 1.0818524360656738,
"loss_region": 0.05998766049742699,
"loss_total": 1.1418401002883911,
"lr": 0.0011694482507862345,
"router/selected_tokens_s0": 7472.625,
"router/selected_tokens_s1": 4303.875,
"step": 1860,
"tokens_trained": 6.094268624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5304588327069002,
"grad_norm": 0.6779845356941223,
"loss": 1.186,
"loss_ce": 1.0940133333206177,
"loss_region": 0.060079120099544525,
"loss_total": 1.1540924310684204,
"lr": 0.0011690413588023834,
"router/selected_tokens_s0": 7563.625,
"router/selected_tokens_s1": 4256.5,
"step": 1870,
"tokens_trained": 6.127034064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5332955109566697,
"grad_norm": 0.5507255792617798,
"loss": 1.1942,
"loss_ce": 1.1586185693740845,
"loss_region": 0.05944622680544853,
"loss_total": 1.218064785003662,
"lr": 0.0011686344668185324,
"router/selected_tokens_s0": 7539.625,
"router/selected_tokens_s1": 4774.75,
"step": 1880,
"tokens_trained": 6.159799504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5361321892064392,
"grad_norm": 1.0612168312072754,
"loss": 1.1953,
"loss_ce": 1.124820351600647,
"loss_region": 0.05970805883407593,
"loss_total": 1.1845283508300781,
"lr": 0.0011682275748346814,
"router/selected_tokens_s0": 7456.0,
"router/selected_tokens_s1": 4528.375,
"step": 1890,
"tokens_trained": 6.192561072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5389688674562088,
"grad_norm": 0.27030009031295776,
"loss": 1.1816,
"loss_ce": 1.1418118476867676,
"loss_region": 0.05972041189670563,
"loss_total": 1.201532244682312,
"lr": 0.0011678206828508303,
"router/selected_tokens_s0": 7315.625,
"router/selected_tokens_s1": 4474.25,
"step": 1900,
"tokens_trained": 6.225326512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5418055457059783,
"grad_norm": 0.7955554127693176,
"loss": 1.1932,
"loss_ce": 1.1275066137313843,
"loss_region": 0.06015876308083534,
"loss_total": 1.187665343284607,
"lr": 0.0011674137908669793,
"router/selected_tokens_s0": 7343.0,
"router/selected_tokens_s1": 4132.5,
"step": 1910,
"tokens_trained": 6.258091952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5446422239557478,
"grad_norm": 1.206097960472107,
"loss": 1.191,
"loss_ce": 1.1694256067276,
"loss_region": 0.06038440391421318,
"loss_total": 1.2298099994659424,
"lr": 0.0011670068988831283,
"router/selected_tokens_s0": 7146.5,
"router/selected_tokens_s1": 3922.625,
"step": 1920,
"tokens_trained": 6.290857392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5474789022055173,
"grad_norm": 1.862305760383606,
"loss": 1.1893,
"loss_ce": 1.143494963645935,
"loss_region": 0.06012733653187752,
"loss_total": 1.2036223411560059,
"lr": 0.0011666000068992772,
"router/selected_tokens_s0": 7706.5,
"router/selected_tokens_s1": 4280.75,
"step": 1930,
"tokens_trained": 6.323622832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5503155804552868,
"grad_norm": 1.6529579162597656,
"loss": 1.1967,
"loss_ce": 1.1993005275726318,
"loss_region": 0.059735652059316635,
"loss_total": 1.2590361833572388,
"lr": 0.0011661931149154262,
"router/selected_tokens_s0": 7429.25,
"router/selected_tokens_s1": 4494.0,
"step": 1940,
"tokens_trained": 6.356388272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5531522587050564,
"grad_norm": 0.6790427565574646,
"loss": 1.1897,
"loss_ce": 1.2285912036895752,
"loss_region": 0.06015128269791603,
"loss_total": 1.2887425422668457,
"lr": 0.0011657862229315751,
"router/selected_tokens_s0": 7461.875,
"router/selected_tokens_s1": 4166.625,
"step": 1950,
"tokens_trained": 6.389153712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5559889369548259,
"grad_norm": 0.7350674867630005,
"loss": 1.1879,
"loss_ce": 1.1737867593765259,
"loss_region": 0.060010842978954315,
"loss_total": 1.233797550201416,
"lr": 0.0011653793309477243,
"router/selected_tokens_s0": 7463.25,
"router/selected_tokens_s1": 4283.625,
"step": 1960,
"tokens_trained": 6.421919152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5588256152045954,
"grad_norm": 2.1251847743988037,
"loss": 1.1929,
"loss_ce": 1.1881052255630493,
"loss_region": 0.05957598611712456,
"loss_total": 1.2476812601089478,
"lr": 0.0011649724389638733,
"router/selected_tokens_s0": 7391.5,
"router/selected_tokens_s1": 4616.25,
"step": 1970,
"tokens_trained": 6.454684592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5616622934543649,
"grad_norm": 2.2398009300231934,
"loss": 1.1965,
"loss_ce": 1.1543619632720947,
"loss_region": 0.06045198440551758,
"loss_total": 1.2148139476776123,
"lr": 0.0011645655469800223,
"router/selected_tokens_s0": 7461.125,
"router/selected_tokens_s1": 3922.625,
"step": 1980,
"tokens_trained": 6.487450032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5644989717041344,
"grad_norm": 0.9572720527648926,
"loss": 1.1905,
"loss_ce": 1.1940102577209473,
"loss_region": 0.05966882035136223,
"loss_total": 1.2536790370941162,
"lr": 0.0011641586549961712,
"router/selected_tokens_s0": 7304.375,
"router/selected_tokens_s1": 4512.875,
"step": 1990,
"tokens_trained": 6.520215472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.567335649953904,
"grad_norm": 1.0482014417648315,
"loss": 1.1875,
"loss_ce": 1.1852117776870728,
"loss_region": 0.05964534357190132,
"loss_total": 1.2448570728302002,
"lr": 0.00116375176301232,
"router/selected_tokens_s0": 7341.375,
"router/selected_tokens_s1": 4539.25,
"step": 2000,
"tokens_trained": 6.552980912
},
{
"epoch": 0.567335649953904,
"eval_ppl": 3.0970225704644703,
"eval_runtime": 1.034,
"step": 2000,
"tokens_trained": 6.552980912
},
{
"epoch": 0.567335649953904,
"eval_F": 0.3193354949605438,
"eval_F_cds": 0.30131524678062416,
"eval_F_dig": 0.3408078756152824,
"eval_F_exon": 0.3181112928250933,
"eval_F_intron": 0.31980747812788923,
"eval_F_nig": 0.32217091538187553,
"eval_F_promoter": 0.31566914879719316,
"eval_F_utr": 0.3197454198768327,
"eval_G": 0.28967377288386786,
"eval_G_cds": 0.28399038089741535,
"eval_G_dig": 0.2875696160344558,
"eval_G_exon": 0.28512627374512517,
"eval_G_intron": 0.2903097508538823,
"eval_G_nig": 0.2919082544550291,
"eval_G_promoter": 0.28639406205967843,
"eval_G_utr": 0.28500934665605915,
"eval_avg_bp_per_token": 3.131502810621028,
"eval_bp_per_token/cds": 3.318783269961977,
"eval_bp_per_token/dig": 2.9342044933516735,
"eval_bp_per_token/exon": 3.1435539151067755,
"eval_bp_per_token/intron": 3.126881228212261,
"eval_bp_per_token/nig": 3.1039425108088365,
"eval_bp_per_token/promoter": 3.167873717816075,
"eval_bp_per_token/utr": 3.1274881134660326,
"eval_ppl_cds": 3.7688088011455108,
"eval_ppl_dig": 1.213764587451198,
"eval_ppl_exon": 3.475874625951551,
"eval_ppl_intron": 3.1372681996036618,
"eval_ppl_nig": 2.9655860866121753,
"eval_ppl_promoter": 3.4064425195757795,
"eval_ppl_utr": 3.401034912667057,
"step": 2000,
"tokens_trained": 6.552980912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5701723282036735,
"grad_norm": 0.4732998311519623,
"loss": 1.1901,
"loss_ce": 1.140292763710022,
"loss_region": 0.05972037836909294,
"loss_total": 1.2000131607055664,
"lr": 0.001163344871028469,
"router/selected_tokens_s0": 7414.375,
"router/selected_tokens_s1": 4512.625,
"step": 2010,
"tokens_trained": 6.585746352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.573009006453443,
"grad_norm": 0.9064376354217529,
"loss": 1.1917,
"loss_ce": 1.187543511390686,
"loss_region": 0.05966633930802345,
"loss_total": 1.247209906578064,
"lr": 0.001162937979044618,
"router/selected_tokens_s0": 7509.25,
"router/selected_tokens_s1": 4591.375,
"step": 2020,
"tokens_trained": 6.618511792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5758456847032125,
"grad_norm": 1.8362021446228027,
"loss": 1.1878,
"loss_ce": 1.1521724462509155,
"loss_region": 0.06033769249916077,
"loss_total": 1.212510108947754,
"lr": 0.001162531087060767,
"router/selected_tokens_s0": 7567.5,
"router/selected_tokens_s1": 4059.25,
"step": 2030,
"tokens_trained": 6.651277232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.578682362952982,
"grad_norm": 0.5258932113647461,
"loss": 1.1861,
"loss_ce": 1.1424130201339722,
"loss_region": 0.05959177017211914,
"loss_total": 1.2020047903060913,
"lr": 0.001162124195076916,
"router/selected_tokens_s0": 7294.75,
"router/selected_tokens_s1": 4573.5,
"step": 2040,
"tokens_trained": 6.684041872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5815190412027516,
"grad_norm": 0.8636136651039124,
"loss": 1.1844,
"loss_ce": 1.2008599042892456,
"loss_region": 0.06002184376120567,
"loss_total": 1.260881781578064,
"lr": 0.001161717303093065,
"router/selected_tokens_s0": 7491.875,
"router/selected_tokens_s1": 4283.5,
"step": 2050,
"tokens_trained": 6.716806512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5843557194525211,
"grad_norm": 1.8349488973617554,
"loss": 1.188,
"loss_ce": 1.151695966720581,
"loss_region": 0.060406751930713654,
"loss_total": 1.2121027708053589,
"lr": 0.001161310411109214,
"router/selected_tokens_s0": 7363.75,
"router/selected_tokens_s1": 3931.875,
"step": 2060,
"tokens_trained": 6.749571952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5871923977022906,
"grad_norm": 1.5168817043304443,
"loss": 1.1871,
"loss_ce": 1.1098576784133911,
"loss_region": 0.05994623526930809,
"loss_total": 1.1698038578033447,
"lr": 0.001160903519125363,
"router/selected_tokens_s0": 7911.125,
"router/selected_tokens_s1": 4589.875,
"step": 2070,
"tokens_trained": 6.782337392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5900290759520601,
"grad_norm": 0.41119372844696045,
"loss": 1.1909,
"loss_ce": 1.1331144571304321,
"loss_region": 0.060201916843652725,
"loss_total": 1.1933163404464722,
"lr": 0.001160496627141512,
"router/selected_tokens_s0": 7271.25,
"router/selected_tokens_s1": 4090.125,
"step": 2080,
"tokens_trained": 6.815102832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5928657542018296,
"grad_norm": 0.7637854814529419,
"loss": 1.1825,
"loss_ce": 1.1243622303009033,
"loss_region": 0.06005639582872391,
"loss_total": 1.1844186782836914,
"lr": 0.0011600897351576609,
"router/selected_tokens_s0": 7414.5,
"router/selected_tokens_s1": 4234.5,
"step": 2090,
"tokens_trained": 6.847868272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5957024324515992,
"grad_norm": 0.7214458584785461,
"loss": 1.1846,
"loss_ce": 1.2273354530334473,
"loss_region": 0.059937622398138046,
"loss_total": 1.2872730493545532,
"lr": 0.0011596828431738098,
"router/selected_tokens_s0": 7353.5,
"router/selected_tokens_s1": 4309.875,
"step": 2100,
"tokens_trained": 6.880633712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.5985391107013687,
"grad_norm": 0.761725664138794,
"loss": 1.1841,
"loss_ce": 1.1755341291427612,
"loss_region": 0.06007400527596474,
"loss_total": 1.2356081008911133,
"lr": 0.0011592759511899588,
"router/selected_tokens_s0": 7109.5,
"router/selected_tokens_s1": 4157.375,
"step": 2110,
"tokens_trained": 6.913397016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6013757889511382,
"grad_norm": 1.6571940183639526,
"loss": 1.1874,
"loss_ce": 1.0919430255889893,
"loss_region": 0.060075193643569946,
"loss_total": 1.1520181894302368,
"lr": 0.0011588690592061078,
"router/selected_tokens_s0": 7679.625,
"router/selected_tokens_s1": 4325.75,
"step": 2120,
"tokens_trained": 6.946162296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6042124672009077,
"grad_norm": 1.00299870967865,
"loss": 1.1899,
"loss_ce": 0.9806433320045471,
"loss_region": 0.0603158213198185,
"loss_total": 1.040959119796753,
"lr": 0.0011584621672222567,
"router/selected_tokens_s0": 7512.25,
"router/selected_tokens_s1": 4050.5,
"step": 2130,
"tokens_trained": 6.978927736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6070491454506772,
"grad_norm": 0.7420610189437866,
"loss": 1.1868,
"loss_ce": 1.0650607347488403,
"loss_region": 0.060088276863098145,
"loss_total": 1.1251490116119385,
"lr": 0.0011580552752384057,
"router/selected_tokens_s0": 7468.875,
"router/selected_tokens_s1": 4230.25,
"step": 2140,
"tokens_trained": 7.011693176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6098858237004467,
"grad_norm": 0.422925740480423,
"loss": 1.1866,
"loss_ce": 1.140285849571228,
"loss_region": 0.059929173439741135,
"loss_total": 1.2002149820327759,
"lr": 0.0011576483832545547,
"router/selected_tokens_s0": 7197.0,
"router/selected_tokens_s1": 4285.5,
"step": 2150,
"tokens_trained": 7.044458616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6127225019502163,
"grad_norm": 1.301650881767273,
"loss": 1.1857,
"loss_ce": 1.1306639909744263,
"loss_region": 0.0599885918200016,
"loss_total": 1.19065260887146,
"lr": 0.0011572414912707036,
"router/selected_tokens_s0": 7413.875,
"router/selected_tokens_s1": 4286.25,
"step": 2160,
"tokens_trained": 7.077224056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6155591801999858,
"grad_norm": 1.5111349821090698,
"loss": 1.1789,
"loss_ce": 1.1107418537139893,
"loss_region": 0.05998992919921875,
"loss_total": 1.170731782913208,
"lr": 0.0011568345992868526,
"router/selected_tokens_s0": 7362.75,
"router/selected_tokens_s1": 4271.625,
"step": 2170,
"tokens_trained": 7.109989496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6183958584497553,
"grad_norm": 1.040898323059082,
"loss": 1.1843,
"loss_ce": 1.1505948305130005,
"loss_region": 0.05984164774417877,
"loss_total": 1.210436463356018,
"lr": 0.0011564277073030016,
"router/selected_tokens_s0": 7593.875,
"router/selected_tokens_s1": 4479.0,
"step": 2180,
"tokens_trained": 7.142754936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6212325366995248,
"grad_norm": 0.5109982490539551,
"loss": 1.1831,
"loss_ce": 1.1635215282440186,
"loss_region": 0.05977338179945946,
"loss_total": 1.2232948541641235,
"lr": 0.0011560208153191505,
"router/selected_tokens_s0": 7465.25,
"router/selected_tokens_s1": 4481.5,
"step": 2190,
"tokens_trained": 7.175520376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6240692149492943,
"grad_norm": 0.8081886768341064,
"loss": 1.1829,
"loss_ce": 1.1379996538162231,
"loss_region": 0.05986666679382324,
"loss_total": 1.1978663206100464,
"lr": 0.0011556139233352995,
"router/selected_tokens_s0": 7448.875,
"router/selected_tokens_s1": 4400.625,
"step": 2200,
"tokens_trained": 7.208285816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6269058931990639,
"grad_norm": 0.6905659437179565,
"loss": 1.181,
"loss_ce": 1.1509792804718018,
"loss_region": 0.05997806414961815,
"loss_total": 1.2109572887420654,
"lr": 0.0011552070313514487,
"router/selected_tokens_s0": 7552.125,
"router/selected_tokens_s1": 4350.75,
"step": 2210,
"tokens_trained": 7.241051256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6297425714488334,
"grad_norm": 1.281117558479309,
"loss": 1.1859,
"loss_ce": 1.0983253717422485,
"loss_region": 0.05995757132768631,
"loss_total": 1.158282995223999,
"lr": 0.0011548001393675976,
"router/selected_tokens_s0": 7399.875,
"router/selected_tokens_s1": 4318.0,
"step": 2220,
"tokens_trained": 7.273816696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6325792496986029,
"grad_norm": 0.9121662378311157,
"loss": 1.1886,
"loss_ce": 1.1557446718215942,
"loss_region": 0.05996396020054817,
"loss_total": 1.215708613395691,
"lr": 0.0011543932473837466,
"router/selected_tokens_s0": 7308.5,
"router/selected_tokens_s1": 4276.75,
"step": 2230,
"tokens_trained": 7.306582136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6354159279483724,
"grad_norm": 0.6554101705551147,
"loss": 1.1782,
"loss_ce": 1.0497093200683594,
"loss_region": 0.05988743156194687,
"loss_total": 1.1095967292785645,
"lr": 0.0011539863553998956,
"router/selected_tokens_s0": 7355.0,
"router/selected_tokens_s1": 4360.0,
"step": 2240,
"tokens_trained": 7.339347576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.638252606198142,
"grad_norm": 0.8508551120758057,
"loss": 1.1777,
"loss_ce": 1.1053940057754517,
"loss_region": 0.05997467786073685,
"loss_total": 1.165368676185608,
"lr": 0.0011535794634160443,
"router/selected_tokens_s0": 7460.125,
"router/selected_tokens_s1": 4319.25,
"step": 2250,
"tokens_trained": 7.372113016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6410892844479115,
"grad_norm": 0.4902251958847046,
"loss": 1.1781,
"loss_ce": 1.034322738647461,
"loss_region": 0.06009990721940994,
"loss_total": 1.094422698020935,
"lr": 0.0011531725714321933,
"router/selected_tokens_s0": 7439.0,
"router/selected_tokens_s1": 4203.25,
"step": 2260,
"tokens_trained": 7.404878456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.643925962697681,
"grad_norm": 1.0787978172302246,
"loss": 1.1791,
"loss_ce": 1.157869577407837,
"loss_region": 0.060018230229616165,
"loss_total": 1.2178877592086792,
"lr": 0.0011527656794483422,
"router/selected_tokens_s0": 7333.5,
"router/selected_tokens_s1": 4239.25,
"step": 2270,
"tokens_trained": 7.437643896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6467626409474505,
"grad_norm": 0.501467227935791,
"loss": 1.1763,
"loss_ce": 1.006744623184204,
"loss_region": 0.06016156077384949,
"loss_total": 1.066906213760376,
"lr": 0.0011523587874644914,
"router/selected_tokens_s0": 7145.375,
"router/selected_tokens_s1": 4089.875,
"step": 2280,
"tokens_trained": 7.470409336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.64959931919722,
"grad_norm": 0.2689010500907898,
"loss": 1.183,
"loss_ce": 1.1373342275619507,
"loss_region": 0.06009635701775551,
"loss_total": 1.1974306106567383,
"lr": 0.0011519518954806404,
"router/selected_tokens_s0": 7760.375,
"router/selected_tokens_s1": 4351.25,
"step": 2290,
"tokens_trained": 7.503173472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6524359974469895,
"grad_norm": 0.6574118733406067,
"loss": 1.1784,
"loss_ce": 1.1269201040267944,
"loss_region": 0.05999438464641571,
"loss_total": 1.1869144439697266,
"lr": 0.0011515450034967894,
"router/selected_tokens_s0": 7411.875,
"router/selected_tokens_s1": 4283.125,
"step": 2300,
"tokens_trained": 7.535938912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6552726756967591,
"grad_norm": 1.2753338813781738,
"loss": 1.1849,
"loss_ce": 1.122605562210083,
"loss_region": 0.059686850756406784,
"loss_total": 1.1822924613952637,
"lr": 0.0011511381115129383,
"router/selected_tokens_s0": 7782.0,
"router/selected_tokens_s1": 4731.875,
"step": 2310,
"tokens_trained": 7.568704352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6581093539465286,
"grad_norm": 0.6676866412162781,
"loss": 1.1793,
"loss_ce": 1.0851284265518188,
"loss_region": 0.06009310483932495,
"loss_total": 1.145221471786499,
"lr": 0.0011507312195290873,
"router/selected_tokens_s0": 7423.375,
"router/selected_tokens_s1": 4202.0,
"step": 2320,
"tokens_trained": 7.601469792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6609460321962981,
"grad_norm": 0.2944624423980713,
"loss": 1.1781,
"loss_ce": 1.1351754665374756,
"loss_region": 0.05992001295089722,
"loss_total": 1.1950955390930176,
"lr": 0.0011503243275452363,
"router/selected_tokens_s0": 7475.375,
"router/selected_tokens_s1": 4371.625,
"step": 2330,
"tokens_trained": 7.634233608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6637827104460676,
"grad_norm": 0.7615077495574951,
"loss": 1.1739,
"loss_ce": 1.1925767660140991,
"loss_region": 0.06029242277145386,
"loss_total": 1.2528691291809082,
"lr": 0.0011499174355613852,
"router/selected_tokens_s0": 7301.0,
"router/selected_tokens_s1": 4010.0,
"step": 2340,
"tokens_trained": 7.666998248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6666193886958371,
"grad_norm": 0.6357439160346985,
"loss": 1.1739,
"loss_ce": 1.0707632303237915,
"loss_region": 0.059961337596178055,
"loss_total": 1.130724549293518,
"lr": 0.0011495105435775342,
"router/selected_tokens_s0": 7490.25,
"router/selected_tokens_s1": 4340.25,
"step": 2350,
"tokens_trained": 7.699763688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6694560669456067,
"grad_norm": 0.5703539848327637,
"loss": 1.1754,
"loss_ce": 1.1037662029266357,
"loss_region": 0.05993586778640747,
"loss_total": 1.1637020111083984,
"lr": 0.0011491036515936831,
"router/selected_tokens_s0": 7448.25,
"router/selected_tokens_s1": 4343.25,
"step": 2360,
"tokens_trained": 7.732529128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6722927451953762,
"grad_norm": 0.24826520681381226,
"loss": 1.1704,
"loss_ce": 1.148972988128662,
"loss_region": 0.0599345862865448,
"loss_total": 1.2089076042175293,
"lr": 0.0011486967596098321,
"router/selected_tokens_s0": 7434.875,
"router/selected_tokens_s1": 4339.125,
"step": 2370,
"tokens_trained": 7.765294568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6751294234451457,
"grad_norm": 0.8287674188613892,
"loss": 1.1755,
"loss_ce": 1.1266905069351196,
"loss_region": 0.06008046492934227,
"loss_total": 1.1867709159851074,
"lr": 0.001148289867625981,
"router/selected_tokens_s0": 7483.75,
"router/selected_tokens_s1": 4241.0,
"step": 2380,
"tokens_trained": 7.798060008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6779661016949152,
"grad_norm": 0.5604900121688843,
"loss": 1.1775,
"loss_ce": 1.123670220375061,
"loss_region": 0.05985580384731293,
"loss_total": 1.1835260391235352,
"lr": 0.00114788297564213,
"router/selected_tokens_s0": 7468.375,
"router/selected_tokens_s1": 4420.75,
"step": 2390,
"tokens_trained": 7.830825448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6808027799446847,
"grad_norm": 1.3453503847122192,
"loss": 1.1807,
"loss_ce": 1.152555227279663,
"loss_region": 0.06042764335870743,
"loss_total": 1.2129828929901123,
"lr": 0.001147476083658279,
"router/selected_tokens_s0": 7370.375,
"router/selected_tokens_s1": 3917.0,
"step": 2400,
"tokens_trained": 7.863590888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6836394581944543,
"grad_norm": 0.28487667441368103,
"loss": 1.178,
"loss_ce": 1.0731216669082642,
"loss_region": 0.059980422258377075,
"loss_total": 1.1331020593643188,
"lr": 0.001147069191674428,
"router/selected_tokens_s0": 7738.75,
"router/selected_tokens_s1": 4453.125,
"step": 2410,
"tokens_trained": 7.896356328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6864761364442238,
"grad_norm": 0.657503604888916,
"loss": 1.1744,
"loss_ce": 0.9968506097793579,
"loss_region": 0.060376450419425964,
"loss_total": 1.0572270154953003,
"lr": 0.001146662299690577,
"router/selected_tokens_s0": 7406.125,
"router/selected_tokens_s1": 3959.25,
"step": 2420,
"tokens_trained": 7.929121768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6893128146939933,
"grad_norm": 0.4880315959453583,
"loss": 1.1715,
"loss_ce": 1.1423887014389038,
"loss_region": 0.05990506336092949,
"loss_total": 1.2022937536239624,
"lr": 0.001146255407706726,
"router/selected_tokens_s0": 7357.75,
"router/selected_tokens_s1": 4339.75,
"step": 2430,
"tokens_trained": 7.961887208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6921494929437628,
"grad_norm": 0.814704179763794,
"loss": 1.177,
"loss_ce": 1.1437619924545288,
"loss_region": 0.06004530191421509,
"loss_total": 1.2038073539733887,
"lr": 0.0011458485157228749,
"router/selected_tokens_s0": 7665.375,
"router/selected_tokens_s1": 4347.5,
"step": 2440,
"tokens_trained": 7.994651848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6949861711935323,
"grad_norm": 0.8780333399772644,
"loss": 1.1746,
"loss_ce": 1.0909539461135864,
"loss_region": 0.05988944694399834,
"loss_total": 1.1508433818817139,
"lr": 0.0011454416237390238,
"router/selected_tokens_s0": 7393.75,
"router/selected_tokens_s1": 4379.75,
"step": 2450,
"tokens_trained": 8.027417288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.6978228494433019,
"grad_norm": 0.4150752127170563,
"loss": 1.1708,
"loss_ce": 1.1503171920776367,
"loss_region": 0.06001152843236923,
"loss_total": 1.2103286981582642,
"lr": 0.001145034731755173,
"router/selected_tokens_s0": 7436.25,
"router/selected_tokens_s1": 4275.125,
"step": 2460,
"tokens_trained": 8.060182704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7006595276930714,
"grad_norm": 0.3488692045211792,
"loss": 1.1695,
"loss_ce": 1.1709470748901367,
"loss_region": 0.06026313453912735,
"loss_total": 1.2312102317810059,
"lr": 0.001144627839771322,
"router/selected_tokens_s0": 7478.625,
"router/selected_tokens_s1": 4083.125,
"step": 2470,
"tokens_trained": 8.092948144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7034962059428409,
"grad_norm": 0.5676023960113525,
"loss": 1.1762,
"loss_ce": 1.111052393913269,
"loss_region": 0.05988939851522446,
"loss_total": 1.1709418296813965,
"lr": 0.001144220947787471,
"router/selected_tokens_s0": 7557.625,
"router/selected_tokens_s1": 4431.625,
"step": 2480,
"tokens_trained": 8.125713584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7063328841926104,
"grad_norm": 0.9211216568946838,
"loss": 1.1722,
"loss_ce": 1.1372982263565063,
"loss_region": 0.05975315347313881,
"loss_total": 1.1970514059066772,
"lr": 0.00114381405580362,
"router/selected_tokens_s0": 7306.625,
"router/selected_tokens_s1": 4463.875,
"step": 2490,
"tokens_trained": 8.158479016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7091695624423799,
"grad_norm": 0.38418033719062805,
"loss": 1.172,
"loss_ce": 1.0843875408172607,
"loss_region": 0.060160085558891296,
"loss_total": 1.1445475816726685,
"lr": 0.0011434071638197687,
"router/selected_tokens_s0": 7460.25,
"router/selected_tokens_s1": 4160.0,
"step": 2500,
"tokens_trained": 8.191244456
},
{
"epoch": 0.7091695624423799,
"eval_ppl": 3.0502517341523907,
"eval_runtime": 1.0296,
"step": 2500,
"tokens_trained": 8.191244456
},
{
"epoch": 0.7091695624423799,
"eval_F": 0.324281193843269,
"eval_F_cds": 0.33014069016085423,
"eval_F_dig": 0.3424486287991249,
"eval_F_exon": 0.32918186774017694,
"eval_F_intron": 0.32455070534671615,
"eval_F_nig": 0.32592670330229484,
"eval_F_promoter": 0.31897710094619564,
"eval_F_utr": 0.31848282614857376,
"eval_G": 0.2886181369760333,
"eval_G_cds": 0.2838436794687457,
"eval_G_dig": 0.30049420975271507,
"eval_G_exon": 0.2874631111879901,
"eval_G_intron": 0.2892678897551585,
"eval_G_nig": 0.29121496986385664,
"eval_G_promoter": 0.28373180247233265,
"eval_G_utr": 0.2818582472815584,
"eval_avg_bp_per_token": 3.0837434269571555,
"eval_bp_per_token/cds": 3.029011660188784,
"eval_bp_per_token/dig": 2.920146018708647,
"eval_bp_per_token/exon": 3.0378343949044586,
"eval_bp_per_token/intron": 3.081182642729752,
"eval_bp_per_token/nig": 3.0681745001805107,
"eval_bp_per_token/promoter": 3.1350212821975516,
"eval_bp_per_token/utr": 3.1398867313915857,
"eval_ppl_cds": 3.7501344975557402,
"eval_ppl_dig": 1.1912519609990055,
"eval_ppl_exon": 3.4368045839019854,
"eval_ppl_intron": 3.093198175869257,
"eval_ppl_nig": 2.911204542550375,
"eval_ppl_promoter": 3.3724010489561747,
"eval_ppl_utr": 3.3630147084441506,
"step": 2500,
"tokens_trained": 8.191244456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7120062406921495,
"grad_norm": 0.2484031319618225,
"loss": 1.1708,
"loss_ce": 1.0516343116760254,
"loss_region": 0.05984216183423996,
"loss_total": 1.1114764213562012,
"lr": 0.0011430002718359176,
"router/selected_tokens_s0": 7426.5,
"router/selected_tokens_s1": 4435.875,
"step": 2510,
"tokens_trained": 8.224009896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.714842918941919,
"grad_norm": 0.5577887296676636,
"loss": 1.1686,
"loss_ce": 1.1628156900405884,
"loss_region": 0.06016436591744423,
"loss_total": 1.22298002243042,
"lr": 0.0011425933798520666,
"router/selected_tokens_s0": 7422.25,
"router/selected_tokens_s1": 4144.75,
"step": 2520,
"tokens_trained": 8.256775336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7176795971916885,
"grad_norm": 1.2296240329742432,
"loss": 1.1737,
"loss_ce": 1.143703818321228,
"loss_region": 0.05981975421309471,
"loss_total": 1.2035235166549683,
"lr": 0.0011421864878682158,
"router/selected_tokens_s0": 7441.875,
"router/selected_tokens_s1": 4451.5,
"step": 2530,
"tokens_trained": 8.289540776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.720516275441458,
"grad_norm": 0.6363380551338196,
"loss": 1.1719,
"loss_ce": 1.0045700073242188,
"loss_region": 0.0602262057363987,
"loss_total": 1.0647962093353271,
"lr": 0.0011417795958843647,
"router/selected_tokens_s0": 7545.375,
"router/selected_tokens_s1": 4129.25,
"step": 2540,
"tokens_trained": 8.322306216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7233529536912275,
"grad_norm": 0.5893341302871704,
"loss": 1.1715,
"loss_ce": 1.094207763671875,
"loss_region": 0.05962364003062248,
"loss_total": 1.1538313627243042,
"lr": 0.0011413727039005137,
"router/selected_tokens_s0": 7538.5,
"router/selected_tokens_s1": 4675.25,
"step": 2550,
"tokens_trained": 8.355071656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7261896319409971,
"grad_norm": 0.721533477306366,
"loss": 1.1675,
"loss_ce": 1.1756376028060913,
"loss_region": 0.059939730912446976,
"loss_total": 1.2355773448944092,
"lr": 0.0011409658119166627,
"router/selected_tokens_s0": 7450.0,
"router/selected_tokens_s1": 4343.875,
"step": 2560,
"tokens_trained": 8.387835072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7290263101907666,
"grad_norm": 0.6618571281433105,
"loss": 1.1697,
"loss_ce": 1.139210820198059,
"loss_region": 0.06019924208521843,
"loss_total": 1.199410080909729,
"lr": 0.0011405589199328116,
"router/selected_tokens_s0": 7507.375,
"router/selected_tokens_s1": 4144.875,
"step": 2570,
"tokens_trained": 8.420600512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7318629884405361,
"grad_norm": 0.7483921051025391,
"loss": 1.1723,
"loss_ce": 1.0926769971847534,
"loss_region": 0.06003560498356819,
"loss_total": 1.1527125835418701,
"lr": 0.0011401520279489606,
"router/selected_tokens_s0": 7537.875,
"router/selected_tokens_s1": 4298.0,
"step": 2580,
"tokens_trained": 8.453365928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7346996666903056,
"grad_norm": 0.42239630222320557,
"loss": 1.1731,
"loss_ce": 1.0441555976867676,
"loss_region": 0.059957705438137054,
"loss_total": 1.1041133403778076,
"lr": 0.0011397451359651096,
"router/selected_tokens_s0": 7481.375,
"router/selected_tokens_s1": 4350.75,
"step": 2590,
"tokens_trained": 8.486131368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7375363449400751,
"grad_norm": 0.41389554738998413,
"loss": 1.1702,
"loss_ce": 1.0931426286697388,
"loss_region": 0.05995481461286545,
"loss_total": 1.15309739112854,
"lr": 0.0011393382439812585,
"router/selected_tokens_s0": 7410.25,
"router/selected_tokens_s1": 4320.125,
"step": 2600,
"tokens_trained": 8.518896808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7403730231898447,
"grad_norm": 0.9596730470657349,
"loss": 1.1648,
"loss_ce": 1.0973268747329712,
"loss_region": 0.060223136097192764,
"loss_total": 1.1575499773025513,
"lr": 0.0011389313519974075,
"router/selected_tokens_s0": 7651.375,
"router/selected_tokens_s1": 4185.375,
"step": 2610,
"tokens_trained": 8.551662248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7432097014396142,
"grad_norm": 0.45995089411735535,
"loss": 1.1699,
"loss_ce": 1.129144310951233,
"loss_region": 0.05994933471083641,
"loss_total": 1.1890935897827148,
"lr": 0.0011385244600135565,
"router/selected_tokens_s0": 7339.375,
"router/selected_tokens_s1": 4301.25,
"step": 2620,
"tokens_trained": 8.584426888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7460463796893837,
"grad_norm": 1.477419376373291,
"loss": 1.1667,
"loss_ce": 1.1206713914871216,
"loss_region": 0.060068678110837936,
"loss_total": 1.1807401180267334,
"lr": 0.0011381175680297054,
"router/selected_tokens_s0": 7434.375,
"router/selected_tokens_s1": 4225.5,
"step": 2630,
"tokens_trained": 8.617192328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7488830579391532,
"grad_norm": 0.9513674974441528,
"loss": 1.1693,
"loss_ce": 1.1470342874526978,
"loss_region": 0.05986784026026726,
"loss_total": 1.2069021463394165,
"lr": 0.0011377106760458544,
"router/selected_tokens_s0": 7393.125,
"router/selected_tokens_s1": 4392.625,
"step": 2640,
"tokens_trained": 8.649951656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7517197361889227,
"grad_norm": 0.6216477155685425,
"loss": 1.1689,
"loss_ce": 0.9593722820281982,
"loss_region": 0.059885814785957336,
"loss_total": 1.0192581415176392,
"lr": 0.0011373037840620034,
"router/selected_tokens_s0": 7577.0,
"router/selected_tokens_s1": 4453.25,
"step": 2650,
"tokens_trained": 8.682717096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7545564144386923,
"grad_norm": 0.35981065034866333,
"loss": 1.1644,
"loss_ce": 1.1608963012695312,
"loss_region": 0.05997583642601967,
"loss_total": 1.220872163772583,
"lr": 0.0011368968920781523,
"router/selected_tokens_s0": 7422.75,
"router/selected_tokens_s1": 4303.25,
"step": 2660,
"tokens_trained": 8.715482536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7573930926884618,
"grad_norm": 0.053441207855939865,
"loss": 1.1648,
"loss_ce": 1.0992127656936646,
"loss_region": 0.05997667461633682,
"loss_total": 1.1591894626617432,
"lr": 0.0011364900000943013,
"router/selected_tokens_s0": 7271.625,
"router/selected_tokens_s1": 4261.375,
"step": 2670,
"tokens_trained": 8.748247976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7602297709382313,
"grad_norm": 0.7620555758476257,
"loss": 1.1704,
"loss_ce": 1.111451506614685,
"loss_region": 0.05993987247347832,
"loss_total": 1.1713913679122925,
"lr": 0.0011360831081104503,
"router/selected_tokens_s0": 7619.375,
"router/selected_tokens_s1": 4424.125,
"step": 2680,
"tokens_trained": 8.781013416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7630664491880008,
"grad_norm": 0.8613774180412292,
"loss": 1.1739,
"loss_ce": 1.1915504932403564,
"loss_region": 0.06020931154489517,
"loss_total": 1.2517597675323486,
"lr": 0.0011356762161265992,
"router/selected_tokens_s0": 7298.0,
"router/selected_tokens_s1": 4064.875,
"step": 2690,
"tokens_trained": 8.813778696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7659031274377703,
"grad_norm": 0.5968960523605347,
"loss": 1.1583,
"loss_ce": 1.1074433326721191,
"loss_region": 0.060063157230615616,
"loss_total": 1.167506456375122,
"lr": 0.0011352693241427482,
"router/selected_tokens_s0": 7549.875,
"router/selected_tokens_s1": 4278.625,
"step": 2700,
"tokens_trained": 8.846544136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7687398056875399,
"grad_norm": 0.6496450901031494,
"loss": 1.1657,
"loss_ce": 1.1257076263427734,
"loss_region": 0.05991235002875328,
"loss_total": 1.1856199502944946,
"lr": 0.0011348624321588974,
"router/selected_tokens_s0": 7512.375,
"router/selected_tokens_s1": 4401.125,
"step": 2710,
"tokens_trained": 8.879309576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7715764839373094,
"grad_norm": 0.8424694538116455,
"loss": 1.1617,
"loss_ce": 1.1279290914535522,
"loss_region": 0.060039110481739044,
"loss_total": 1.1879682540893555,
"lr": 0.0011344555401750463,
"router/selected_tokens_s0": 7467.5,
"router/selected_tokens_s1": 4261.25,
"step": 2720,
"tokens_trained": 8.912075016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7744131621870789,
"grad_norm": 0.7486598491668701,
"loss": 1.1733,
"loss_ce": 1.1374742984771729,
"loss_region": 0.0601111575961113,
"loss_total": 1.1975854635238647,
"lr": 0.0011340486481911953,
"router/selected_tokens_s0": 7572.375,
"router/selected_tokens_s1": 4257.125,
"step": 2730,
"tokens_trained": 8.944840456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7772498404368484,
"grad_norm": 0.5935088396072388,
"loss": 1.1695,
"loss_ce": 1.0936038494110107,
"loss_region": 0.059866975992918015,
"loss_total": 1.1534708738327026,
"lr": 0.001133641756207344,
"router/selected_tokens_s0": 7294.75,
"router/selected_tokens_s1": 4377.5,
"step": 2740,
"tokens_trained": 8.977605896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7800865186866179,
"grad_norm": 0.18403343856334686,
"loss": 1.1649,
"loss_ce": 1.1556285619735718,
"loss_region": 0.0601109080016613,
"loss_total": 1.2157394886016846,
"lr": 0.001133234864223493,
"router/selected_tokens_s0": 7394.0,
"router/selected_tokens_s1": 4183.875,
"step": 2750,
"tokens_trained": 9.010371336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7829231969363875,
"grad_norm": 0.18721617758274078,
"loss": 1.1593,
"loss_ce": 1.1401076316833496,
"loss_region": 0.05992697551846504,
"loss_total": 1.2000346183776855,
"lr": 0.001132827972239642,
"router/selected_tokens_s0": 7434.5,
"router/selected_tokens_s1": 4354.125,
"step": 2760,
"tokens_trained": 9.043136776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.785759875186157,
"grad_norm": 0.4251779317855835,
"loss": 1.1691,
"loss_ce": 1.1821259260177612,
"loss_region": 0.06003726273775101,
"loss_total": 1.2421631813049316,
"lr": 0.001132421080255791,
"router/selected_tokens_s0": 7411.75,
"router/selected_tokens_s1": 4242.0,
"step": 2770,
"tokens_trained": 9.075902216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7885965534359265,
"grad_norm": 0.7461664080619812,
"loss": 1.1679,
"loss_ce": 1.1305651664733887,
"loss_region": 0.06012176349759102,
"loss_total": 1.1906869411468506,
"lr": 0.0011320141882719401,
"router/selected_tokens_s0": 7582.125,
"router/selected_tokens_s1": 4240.125,
"step": 2780,
"tokens_trained": 9.108667656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.791433231685696,
"grad_norm": 0.46765202283859253,
"loss": 1.1629,
"loss_ce": 1.0436062812805176,
"loss_region": 0.06002155691385269,
"loss_total": 1.1036278009414673,
"lr": 0.001131607296288089,
"router/selected_tokens_s0": 7352.75,
"router/selected_tokens_s1": 4238.875,
"step": 2790,
"tokens_trained": 9.14143004
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7942699099354655,
"grad_norm": 0.15761826932430267,
"loss": 1.1619,
"loss_ce": 0.9722632765769958,
"loss_region": 0.05996977165341377,
"loss_total": 1.0322329998016357,
"lr": 0.001131200404304238,
"router/selected_tokens_s0": 7640.125,
"router/selected_tokens_s1": 4418.75,
"step": 2800,
"tokens_trained": 9.17419548
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.797106588185235,
"grad_norm": 0.6991495490074158,
"loss": 1.1656,
"loss_ce": 1.0889579057693481,
"loss_region": 0.05980755016207695,
"loss_total": 1.1487654447555542,
"lr": 0.001130793512320387,
"router/selected_tokens_s0": 7576.375,
"router/selected_tokens_s1": 4533.5,
"step": 2810,
"tokens_trained": 9.20696092
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.7999432664350046,
"grad_norm": 7.605064868927002,
"loss": 1.1754,
"loss_ce": 1.0953309535980225,
"loss_region": 0.06001967564225197,
"loss_total": 1.155350685119629,
"lr": 0.001130386620336536,
"router/selected_tokens_s0": 7465.375,
"router/selected_tokens_s1": 4280.0,
"step": 2820,
"tokens_trained": 9.23972636
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8027799446847741,
"grad_norm": 1.1716810464859009,
"loss": 1.1723,
"loss_ce": 1.0848501920700073,
"loss_region": 0.06025412306189537,
"loss_total": 1.1451042890548706,
"lr": 0.001129979728352685,
"router/selected_tokens_s0": 7606.25,
"router/selected_tokens_s1": 4139.5,
"step": 2830,
"tokens_trained": 9.2724918
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8056166229345436,
"grad_norm": 0.22220773994922638,
"loss": 1.1679,
"loss_ce": 1.0692635774612427,
"loss_region": 0.05984492972493172,
"loss_total": 1.1291085481643677,
"lr": 0.001129572836368834,
"router/selected_tokens_s0": 7514.375,
"router/selected_tokens_s1": 4475.875,
"step": 2840,
"tokens_trained": 9.30525692
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8084533011843131,
"grad_norm": 0.157245472073555,
"loss": 1.1629,
"loss_ce": 1.1122710704803467,
"loss_region": 0.06007363274693489,
"loss_total": 1.17234468460083,
"lr": 0.0011291659443849829,
"router/selected_tokens_s0": 7484.0,
"router/selected_tokens_s1": 4237.625,
"step": 2850,
"tokens_trained": 9.33802236
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8112899794340827,
"grad_norm": 0.20226812362670898,
"loss": 1.1579,
"loss_ce": 1.1239492893218994,
"loss_region": 0.06007097288966179,
"loss_total": 1.1840202808380127,
"lr": 0.0011287590524011318,
"router/selected_tokens_s0": 7343.75,
"router/selected_tokens_s1": 4189.625,
"step": 2860,
"tokens_trained": 9.3707878
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8141266576838522,
"grad_norm": 0.8050180077552795,
"loss": 1.1591,
"loss_ce": 1.0115890502929688,
"loss_region": 0.05998658388853073,
"loss_total": 1.07157564163208,
"lr": 0.0011283521604172808,
"router/selected_tokens_s0": 7345.0,
"router/selected_tokens_s1": 4284.0,
"step": 2870,
"tokens_trained": 9.403548272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8169633359336217,
"grad_norm": 0.23213136196136475,
"loss": 1.1609,
"loss_ce": 1.0894582271575928,
"loss_region": 0.059960782527923584,
"loss_total": 1.1494190692901611,
"lr": 0.0011279452684334298,
"router/selected_tokens_s0": 7514.125,
"router/selected_tokens_s1": 4359.625,
"step": 2880,
"tokens_trained": 9.436313712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8198000141833912,
"grad_norm": 0.15889334678649902,
"loss": 1.1619,
"loss_ce": 1.178969383239746,
"loss_region": 0.059914231300354004,
"loss_total": 1.2388836145401,
"lr": 0.0011275383764495787,
"router/selected_tokens_s0": 7517.75,
"router/selected_tokens_s1": 4405.625,
"step": 2890,
"tokens_trained": 9.469079152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8226366924331607,
"grad_norm": 1.0330082178115845,
"loss": 1.1673,
"loss_ce": 1.0116691589355469,
"loss_region": 0.05996264889836311,
"loss_total": 1.0716317892074585,
"lr": 0.0011271314844657277,
"router/selected_tokens_s0": 7586.25,
"router/selected_tokens_s1": 4396.125,
"step": 2900,
"tokens_trained": 9.50184356
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8254733706829303,
"grad_norm": 0.11898782849311829,
"loss": 1.1614,
"loss_ce": 1.0050482749938965,
"loss_region": 0.059950973838567734,
"loss_total": 1.0649992227554321,
"lr": 0.0011267245924818767,
"router/selected_tokens_s0": 7383.25,
"router/selected_tokens_s1": 4316.5,
"step": 2910,
"tokens_trained": 9.534608992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8283100489326998,
"grad_norm": 0.334542453289032,
"loss": 1.1596,
"loss_ce": 1.192863941192627,
"loss_region": 0.05996337905526161,
"loss_total": 1.2528272867202759,
"lr": 0.0011263177004980256,
"router/selected_tokens_s0": 7447.75,
"router/selected_tokens_s1": 4325.875,
"step": 2920,
"tokens_trained": 9.567373632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8311467271824693,
"grad_norm": 2.9175424575805664,
"loss": 1.1657,
"loss_ce": 1.1350030899047852,
"loss_region": 0.06023212894797325,
"loss_total": 1.195235252380371,
"lr": 0.0011259108085141746,
"router/selected_tokens_s0": 7292.75,
"router/selected_tokens_s1": 4036.5,
"step": 2930,
"tokens_trained": 9.600139072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8339834054322388,
"grad_norm": 0.56610107421875,
"loss": 1.1666,
"loss_ce": 1.0537909269332886,
"loss_region": 0.0598357617855072,
"loss_total": 1.1136267185211182,
"lr": 0.0011255039165303236,
"router/selected_tokens_s0": 7546.5,
"router/selected_tokens_s1": 4522.375,
"step": 2940,
"tokens_trained": 9.632904512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8368200836820083,
"grad_norm": 0.4306299090385437,
"loss": 1.1627,
"loss_ce": 0.9236807227134705,
"loss_region": 0.060068003833293915,
"loss_total": 0.983748733997345,
"lr": 0.0011250970245464725,
"router/selected_tokens_s0": 7534.5,
"router/selected_tokens_s1": 4282.375,
"step": 2950,
"tokens_trained": 9.665669952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8396567619317779,
"grad_norm": 0.26961612701416016,
"loss": 1.1591,
"loss_ce": 1.145656704902649,
"loss_region": 0.05994835123419762,
"loss_total": 1.2056050300598145,
"lr": 0.0011246901325626217,
"router/selected_tokens_s0": 7376.0,
"router/selected_tokens_s1": 4319.875,
"step": 2960,
"tokens_trained": 9.698432616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8424934401815474,
"grad_norm": 0.3499460220336914,
"loss": 1.1564,
"loss_ce": 1.1160905361175537,
"loss_region": 0.05992301553487778,
"loss_total": 1.1760135889053345,
"lr": 0.0011242832405787707,
"router/selected_tokens_s0": 7367.625,
"router/selected_tokens_s1": 4343.5,
"step": 2970,
"tokens_trained": 9.731196464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8453301184313169,
"grad_norm": 0.33717259764671326,
"loss": 1.1596,
"loss_ce": 1.1449989080429077,
"loss_region": 0.06000290438532829,
"loss_total": 1.2050018310546875,
"lr": 0.0011238763485949196,
"router/selected_tokens_s0": 7521.125,
"router/selected_tokens_s1": 4322.125,
"step": 2980,
"tokens_trained": 9.763955848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8481667966810864,
"grad_norm": 0.577868640422821,
"loss": 1.1567,
"loss_ce": 1.1596364974975586,
"loss_region": 0.059965357184410095,
"loss_total": 1.2196018695831299,
"lr": 0.0011234694566110684,
"router/selected_tokens_s0": 7441.375,
"router/selected_tokens_s1": 4320.875,
"step": 2990,
"tokens_trained": 9.796721288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8510034749308559,
"grad_norm": 0.31575798988342285,
"loss": 1.1571,
"loss_ce": 1.151265263557434,
"loss_region": 0.05999479070305824,
"loss_total": 1.2112600803375244,
"lr": 0.0011230625646272174,
"router/selected_tokens_s0": 7448.0,
"router/selected_tokens_s1": 4295.125,
"step": 3000,
"tokens_trained": 9.829486728
},
{
"epoch": 0.8510034749308559,
"eval_ppl": 3.0109347418579757,
"eval_runtime": 1.041,
"step": 3000,
"tokens_trained": 9.829486728
},
{
"epoch": 0.8510034749308559,
"eval_F": 0.3265157434174545,
"eval_F_cds": 0.32704733971861966,
"eval_F_dig": 0.32940073443237755,
"eval_F_exon": 0.3268335639703107,
"eval_F_intron": 0.3263412398381537,
"eval_F_nig": 0.33125031801760546,
"eval_F_promoter": 0.32055409364910514,
"eval_F_utr": 0.32332706331005695,
"eval_G": 0.2973011006414075,
"eval_G_cds": 0.2947680577912332,
"eval_G_dig": 0.29819865077349794,
"eval_G_exon": 0.2960844786555961,
"eval_G_intron": 0.29743575612920226,
"eval_G_nig": 0.30035083925839884,
"eval_G_promoter": 0.29358059830951516,
"eval_G_utr": 0.2933570700417429,
"eval_avg_bp_per_token": 3.062639459689046,
"eval_bp_per_token/cds": 3.0576613185735306,
"eval_bp_per_token/dig": 3.0358159392789372,
"eval_bp_per_token/exon": 3.0596612779060814,
"eval_bp_per_token/intron": 3.064277136704947,
"eval_bp_per_token/nig": 3.0188650262574286,
"eval_bp_per_token/promoter": 3.11959828251219,
"eval_bp_per_token/utr": 3.092843481032834,
"eval_ppl_cds": 3.7454664560279944,
"eval_ppl_dig": 1.1519394255345423,
"eval_ppl_exon": 3.40224242349742,
"eval_ppl_intron": 3.059094676849309,
"eval_ppl_nig": 2.858553832785096,
"eval_ppl_promoter": 3.339582435304094,
"eval_ppl_utr": 3.3378419038139535,
"step": 3000,
"tokens_trained": 9.829486728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8538401531806254,
"grad_norm": 1.484962821006775,
"loss": 1.1514,
"loss_ce": 1.1324831247329712,
"loss_region": 0.05994853004813194,
"loss_total": 1.1924316883087158,
"lr": 0.0011226556726433663,
"router/selected_tokens_s0": 7517.5,
"router/selected_tokens_s1": 4376.375,
"step": 3010,
"tokens_trained": 9.862252168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.856676831430395,
"grad_norm": 1.3830934762954712,
"loss": 1.1595,
"loss_ce": 1.1091521978378296,
"loss_region": 0.06006480008363724,
"loss_total": 1.1692169904708862,
"lr": 0.0011222487806595153,
"router/selected_tokens_s0": 7292.625,
"router/selected_tokens_s1": 4178.875,
"step": 3020,
"tokens_trained": 9.895016808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8595135096801645,
"grad_norm": 0.5553335547447205,
"loss": 1.1541,
"loss_ce": 0.938005268573761,
"loss_region": 0.060082145035266876,
"loss_total": 0.9980874061584473,
"lr": 0.0011218418886756645,
"router/selected_tokens_s0": 7320.125,
"router/selected_tokens_s1": 4164.75,
"step": 3030,
"tokens_trained": 9.927782248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.862350187929934,
"grad_norm": 0.16215354204177856,
"loss": 1.1601,
"loss_ce": 1.1301517486572266,
"loss_region": 0.05998187139630318,
"loss_total": 1.1901335716247559,
"lr": 0.0011214349966918134,
"router/selected_tokens_s0": 7467.875,
"router/selected_tokens_s1": 4321.375,
"step": 3040,
"tokens_trained": 9.960547688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8651868661797035,
"grad_norm": 0.33606576919555664,
"loss": 1.1614,
"loss_ce": 1.0460857152938843,
"loss_region": 0.060056839138269424,
"loss_total": 1.106142520904541,
"lr": 0.0011210281047079624,
"router/selected_tokens_s0": 7379.875,
"router/selected_tokens_s1": 4211.75,
"step": 3050,
"tokens_trained": 9.993313128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.868023544429473,
"grad_norm": 0.28386250138282776,
"loss": 1.1553,
"loss_ce": 1.0485560894012451,
"loss_region": 0.06009070575237274,
"loss_total": 1.1086467504501343,
"lr": 0.0011206212127241114,
"router/selected_tokens_s0": 7455.875,
"router/selected_tokens_s1": 4209.875,
"step": 3060,
"tokens_trained": 10.026078568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8708602226792426,
"grad_norm": 0.26301583647727966,
"loss": 1.1555,
"loss_ce": 1.0704364776611328,
"loss_region": 0.060045089572668076,
"loss_total": 1.1304816007614136,
"lr": 0.0011202143207402603,
"router/selected_tokens_s0": 7333.625,
"router/selected_tokens_s1": 4212.0,
"step": 3070,
"tokens_trained": 10.058844008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8736969009290121,
"grad_norm": 0.6406818628311157,
"loss": 1.1644,
"loss_ce": 1.0923793315887451,
"loss_region": 0.06021547690033913,
"loss_total": 1.152594804763794,
"lr": 0.0011198074287564093,
"router/selected_tokens_s0": 7350.0,
"router/selected_tokens_s1": 4048.75,
"step": 3080,
"tokens_trained": 10.091604144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8765335791787816,
"grad_norm": 0.3559488356113434,
"loss": 1.1612,
"loss_ce": 1.1637524366378784,
"loss_region": 0.05999548360705376,
"loss_total": 1.223747968673706,
"lr": 0.0011194005367725583,
"router/selected_tokens_s0": 7453.25,
"router/selected_tokens_s1": 4298.0,
"step": 3090,
"tokens_trained": 10.124368784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8793702574285511,
"grad_norm": 0.6486785411834717,
"loss": 1.1579,
"loss_ce": 1.0859977006912231,
"loss_region": 0.05990362912416458,
"loss_total": 1.1459013223648071,
"lr": 0.0011189936447887072,
"router/selected_tokens_s0": 7465.375,
"router/selected_tokens_s1": 4406.875,
"step": 3100,
"tokens_trained": 10.157134224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8822069356783206,
"grad_norm": 0.1741045117378235,
"loss": 1.1547,
"loss_ce": 1.1454678773880005,
"loss_region": 0.05989646539092064,
"loss_total": 1.2053643465042114,
"lr": 0.0011185867528048562,
"router/selected_tokens_s0": 7361.125,
"router/selected_tokens_s1": 4378.625,
"step": 3110,
"tokens_trained": 10.189899664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8850436139280902,
"grad_norm": 0.682843804359436,
"loss": 1.1585,
"loss_ce": 1.1063830852508545,
"loss_region": 0.060072798281908035,
"loss_total": 1.166455864906311,
"lr": 0.0011181798608210052,
"router/selected_tokens_s0": 7449.5,
"router/selected_tokens_s1": 4223.0,
"step": 3120,
"tokens_trained": 10.222665104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8878802921778597,
"grad_norm": 0.8256351351737976,
"loss": 1.159,
"loss_ce": 1.0325148105621338,
"loss_region": 0.06016336381435394,
"loss_total": 1.092678189277649,
"lr": 0.0011177729688371541,
"router/selected_tokens_s0": 7448.0,
"router/selected_tokens_s1": 4129.875,
"step": 3130,
"tokens_trained": 10.255429744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8907169704276292,
"grad_norm": 0.585247278213501,
"loss": 1.1541,
"loss_ce": 1.0111068487167358,
"loss_region": 0.059877362102270126,
"loss_total": 1.0709842443466187,
"lr": 0.001117366076853303,
"router/selected_tokens_s0": 7432.375,
"router/selected_tokens_s1": 4420.875,
"step": 3140,
"tokens_trained": 10.288194384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8935536486773987,
"grad_norm": 0.34178733825683594,
"loss": 1.1569,
"loss_ce": 1.1468701362609863,
"loss_region": 0.060133885592222214,
"loss_total": 1.2070040702819824,
"lr": 0.001116959184869452,
"router/selected_tokens_s0": 7415.125,
"router/selected_tokens_s1": 4145.0,
"step": 3150,
"tokens_trained": 10.320959664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8963903269271682,
"grad_norm": 0.3433026969432831,
"loss": 1.1526,
"loss_ce": 1.1024417877197266,
"loss_region": 0.060020167380571365,
"loss_total": 1.1624619960784912,
"lr": 0.001116552292885601,
"router/selected_tokens_s0": 7450.875,
"router/selected_tokens_s1": 4279.125,
"step": 3160,
"tokens_trained": 10.353725104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.8992270051769378,
"grad_norm": 0.9464390277862549,
"loss": 1.1564,
"loss_ce": 1.0875449180603027,
"loss_region": 0.0599987767636776,
"loss_total": 1.1475436687469482,
"lr": 0.00111614540090175,
"router/selected_tokens_s0": 7436.0,
"router/selected_tokens_s1": 4293.75,
"step": 3170,
"tokens_trained": 10.386490544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9020636834267073,
"grad_norm": 0.18355347216129303,
"loss": 1.1626,
"loss_ce": 1.0882506370544434,
"loss_region": 0.05997658893465996,
"loss_total": 1.1482272148132324,
"lr": 0.001115738508917899,
"router/selected_tokens_s0": 7366.125,
"router/selected_tokens_s1": 4289.25,
"step": 3180,
"tokens_trained": 10.419255984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9049003616764768,
"grad_norm": 0.21294108033180237,
"loss": 1.1586,
"loss_ce": 1.096394658088684,
"loss_region": 0.06007112190127373,
"loss_total": 1.156465768814087,
"lr": 0.001115331616934048,
"router/selected_tokens_s0": 7388.875,
"router/selected_tokens_s1": 4189.5,
"step": 3190,
"tokens_trained": 10.452021424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9077370399262463,
"grad_norm": 0.6308612823486328,
"loss": 1.1545,
"loss_ce": 1.1357101202011108,
"loss_region": 0.059982795268297195,
"loss_total": 1.1956928968429565,
"lr": 0.0011149247249501969,
"router/selected_tokens_s0": 7421.625,
"router/selected_tokens_s1": 4299.75,
"step": 3200,
"tokens_trained": 10.484786064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9105737181760158,
"grad_norm": 0.5103173851966858,
"loss": 1.151,
"loss_ce": 1.0303833484649658,
"loss_region": 0.05991167947649956,
"loss_total": 1.0902950763702393,
"lr": 0.001114517832966346,
"router/selected_tokens_s0": 7488.75,
"router/selected_tokens_s1": 4412.0,
"step": 3210,
"tokens_trained": 10.517551504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9134103964257854,
"grad_norm": 0.2153053730726242,
"loss": 1.1559,
"loss_ce": 1.0447967052459717,
"loss_region": 0.06009405478835106,
"loss_total": 1.1048907041549683,
"lr": 0.001114110940982495,
"router/selected_tokens_s0": 7537.0,
"router/selected_tokens_s1": 4243.25,
"step": 3220,
"tokens_trained": 10.550316944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9162470746755549,
"grad_norm": 0.7214828133583069,
"loss": 1.1549,
"loss_ce": 1.139117956161499,
"loss_region": 0.05997217446565628,
"loss_total": 1.1990901231765747,
"lr": 0.001113704048998644,
"router/selected_tokens_s0": 7427.25,
"router/selected_tokens_s1": 4315.375,
"step": 3230,
"tokens_trained": 10.583082384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9190837529253244,
"grad_norm": 0.5311968922615051,
"loss": 1.154,
"loss_ce": 1.153262972831726,
"loss_region": 0.06014882028102875,
"loss_total": 1.213411808013916,
"lr": 0.0011132971570147927,
"router/selected_tokens_s0": 7319.625,
"router/selected_tokens_s1": 4102.75,
"step": 3240,
"tokens_trained": 10.615847824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9219204311750939,
"grad_norm": 0.3367522656917572,
"loss": 1.1555,
"loss_ce": 1.0961225032806396,
"loss_region": 0.06004282087087631,
"loss_total": 1.156165361404419,
"lr": 0.0011128902650309417,
"router/selected_tokens_s0": 7466.875,
"router/selected_tokens_s1": 4262.0,
"step": 3250,
"tokens_trained": 10.648613248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9247571094248634,
"grad_norm": 0.5154868364334106,
"loss": 1.1425,
"loss_ce": 0.9198837280273438,
"loss_region": 0.059922680258750916,
"loss_total": 0.9798064231872559,
"lr": 0.0011124833730470907,
"router/selected_tokens_s0": 7582.125,
"router/selected_tokens_s1": 4459.25,
"step": 3260,
"tokens_trained": 10.681378688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.927593787674633,
"grad_norm": 0.47784504294395447,
"loss": 1.1497,
"loss_ce": 0.9742546677589417,
"loss_region": 0.06002604961395264,
"loss_total": 1.034280776977539,
"lr": 0.0011120764810632396,
"router/selected_tokens_s0": 7462.0,
"router/selected_tokens_s1": 4289.5,
"step": 3270,
"tokens_trained": 10.714144128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9304304659244025,
"grad_norm": 0.5129175186157227,
"loss": 1.1509,
"loss_ce": 1.052802324295044,
"loss_region": 0.059992704540491104,
"loss_total": 1.1127949953079224,
"lr": 0.0011116695890793888,
"router/selected_tokens_s0": 7418.875,
"router/selected_tokens_s1": 4290.0,
"step": 3280,
"tokens_trained": 10.746909568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.933267144174172,
"grad_norm": 0.6715986132621765,
"loss": 1.144,
"loss_ce": 1.0578795671463013,
"loss_region": 0.05989795923233032,
"loss_total": 1.1177775859832764,
"lr": 0.0011112626970955378,
"router/selected_tokens_s0": 7524.75,
"router/selected_tokens_s1": 4455.625,
"step": 3290,
"tokens_trained": 10.779675008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9361038224239415,
"grad_norm": 1.6286574602127075,
"loss": 1.1526,
"loss_ce": 1.1762213706970215,
"loss_region": 0.060009438544511795,
"loss_total": 1.2362308502197266,
"lr": 0.0011108558051116867,
"router/selected_tokens_s0": 7364.875,
"router/selected_tokens_s1": 4253.375,
"step": 3300,
"tokens_trained": 10.812440448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.938940500673711,
"grad_norm": 0.5151171088218689,
"loss": 1.1554,
"loss_ce": 1.0672016143798828,
"loss_region": 0.06006050854921341,
"loss_total": 1.1272621154785156,
"lr": 0.0011104489131278357,
"router/selected_tokens_s0": 7480.25,
"router/selected_tokens_s1": 4240.75,
"step": 3310,
"tokens_trained": 10.845202832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9417771789234806,
"grad_norm": 0.2817917466163635,
"loss": 1.1505,
"loss_ce": 1.1648095846176147,
"loss_region": 0.0600048191845417,
"loss_total": 1.2248144149780273,
"lr": 0.0011100420211439847,
"router/selected_tokens_s0": 7581.625,
"router/selected_tokens_s1": 4353.375,
"step": 3320,
"tokens_trained": 10.877968272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9446138571732501,
"grad_norm": 0.11748674511909485,
"loss": 1.1557,
"loss_ce": 1.0878210067749023,
"loss_region": 0.05999528616666794,
"loss_total": 1.1478163003921509,
"lr": 0.0011096351291601336,
"router/selected_tokens_s0": 7491.625,
"router/selected_tokens_s1": 4317.25,
"step": 3330,
"tokens_trained": 10.910733712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9474505354230196,
"grad_norm": 0.659820556640625,
"loss": 1.1515,
"loss_ce": 1.0421631336212158,
"loss_region": 0.059975143522024155,
"loss_total": 1.1021382808685303,
"lr": 0.0011092282371762826,
"router/selected_tokens_s0": 7401.375,
"router/selected_tokens_s1": 4302.875,
"step": 3340,
"tokens_trained": 10.943499152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9502872136727891,
"grad_norm": 0.2588161528110504,
"loss": 1.1543,
"loss_ce": 1.165223240852356,
"loss_region": 0.0600115992128849,
"loss_total": 1.225234866142273,
"lr": 0.0011088213451924316,
"router/selected_tokens_s0": 7404.625,
"router/selected_tokens_s1": 4262.75,
"step": 3350,
"tokens_trained": 10.976264592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9531238919225586,
"grad_norm": 0.48925071954727173,
"loss": 1.1488,
"loss_ce": 1.0838979482650757,
"loss_region": 0.059988539665937424,
"loss_total": 1.1438864469528198,
"lr": 0.0011084144532085805,
"router/selected_tokens_s0": 7438.25,
"router/selected_tokens_s1": 4303.625,
"step": 3360,
"tokens_trained": 11.009030032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9559605701723282,
"grad_norm": 0.2473180890083313,
"loss": 1.1499,
"loss_ce": 0.9721645712852478,
"loss_region": 0.0599365159869194,
"loss_total": 1.032101035118103,
"lr": 0.0011080075612247295,
"router/selected_tokens_s0": 7439.5,
"router/selected_tokens_s1": 4369.0,
"step": 3370,
"tokens_trained": 11.041794728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9587972484220977,
"grad_norm": 0.18463283777236938,
"loss": 1.1535,
"loss_ce": 1.084818720817566,
"loss_region": 0.06001410260796547,
"loss_total": 1.1448328495025635,
"lr": 0.0011076006692408785,
"router/selected_tokens_s0": 7494.375,
"router/selected_tokens_s1": 4295.625,
"step": 3380,
"tokens_trained": 11.074559368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9616339266718672,
"grad_norm": 0.31234511733055115,
"loss": 1.1475,
"loss_ce": 1.0884270668029785,
"loss_region": 0.0599556639790535,
"loss_total": 1.1483827829360962,
"lr": 0.0011071937772570274,
"router/selected_tokens_s0": 7453.75,
"router/selected_tokens_s1": 4346.75,
"step": 3390,
"tokens_trained": 11.107324808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9644706049216367,
"grad_norm": 0.6354888677597046,
"loss": 1.1591,
"loss_ce": 1.06814706325531,
"loss_region": 0.059949424117803574,
"loss_total": 1.1280964612960815,
"lr": 0.0011067868852731764,
"router/selected_tokens_s0": 7476.375,
"router/selected_tokens_s1": 4367.5,
"step": 3400,
"tokens_trained": 11.140090248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9673072831714062,
"grad_norm": 0.21459953486919403,
"loss": 1.1508,
"loss_ce": 1.0278993844985962,
"loss_region": 0.060014039278030396,
"loss_total": 1.0879133939743042,
"lr": 0.0011063799932893254,
"router/selected_tokens_s0": 7518.125,
"router/selected_tokens_s1": 4318.875,
"step": 3410,
"tokens_trained": 11.172855688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9701439614211758,
"grad_norm": 1.008099913597107,
"loss": 1.1504,
"loss_ce": 1.0413086414337158,
"loss_region": 0.06001026928424835,
"loss_total": 1.1013189554214478,
"lr": 0.0011059731013054743,
"router/selected_tokens_s0": 7393.875,
"router/selected_tokens_s1": 4257.5,
"step": 3420,
"tokens_trained": 11.205621096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9729806396709453,
"grad_norm": 0.49454066157341003,
"loss": 1.1453,
"loss_ce": 0.9835691452026367,
"loss_region": 0.05995873734354973,
"loss_total": 1.0435278415679932,
"lr": 0.0011055662093216233,
"router/selected_tokens_s0": 7526.625,
"router/selected_tokens_s1": 4386.375,
"step": 3430,
"tokens_trained": 11.238384136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9758173179207148,
"grad_norm": 0.2803723216056824,
"loss": 1.1535,
"loss_ce": 1.0913236141204834,
"loss_region": 0.05994022637605667,
"loss_total": 1.1512638330459595,
"lr": 0.0011051593173377723,
"router/selected_tokens_s0": 7456.0,
"router/selected_tokens_s1": 4370.25,
"step": 3440,
"tokens_trained": 11.271149576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9786539961704843,
"grad_norm": 0.4610815644264221,
"loss": 1.1521,
"loss_ce": 1.0604761838912964,
"loss_region": 0.060004524886608124,
"loss_total": 1.1204806566238403,
"lr": 0.0011047524253539212,
"router/selected_tokens_s0": 7462.5,
"router/selected_tokens_s1": 4301.75,
"step": 3450,
"tokens_trained": 11.303915016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9814906744202538,
"grad_norm": 0.37205979228019714,
"loss": 1.1458,
"loss_ce": 1.0331106185913086,
"loss_region": 0.060014817863702774,
"loss_total": 1.0931254625320435,
"lr": 0.0011043455333700704,
"router/selected_tokens_s0": 7482.0,
"router/selected_tokens_s1": 4290.0,
"step": 3460,
"tokens_trained": 11.336680456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9843273526700234,
"grad_norm": 0.24320276081562042,
"loss": 1.1473,
"loss_ce": 0.9818251729011536,
"loss_region": 0.059945087879896164,
"loss_total": 1.0417702198028564,
"lr": 0.0011039386413862194,
"router/selected_tokens_s0": 7398.375,
"router/selected_tokens_s1": 4348.875,
"step": 3470,
"tokens_trained": 11.369444288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9871640309197929,
"grad_norm": 0.47212696075439453,
"loss": 1.141,
"loss_ce": 1.1068347692489624,
"loss_region": 0.05994030460715294,
"loss_total": 1.166775107383728,
"lr": 0.0011035317494023683,
"router/selected_tokens_s0": 7398.125,
"router/selected_tokens_s1": 4349.25,
"step": 3480,
"tokens_trained": 11.402209728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9900007091695624,
"grad_norm": 1.9513204097747803,
"loss": 1.153,
"loss_ce": 1.111778736114502,
"loss_region": 0.06009702384471893,
"loss_total": 1.1718757152557373,
"lr": 0.001103124857418517,
"router/selected_tokens_s0": 7419.125,
"router/selected_tokens_s1": 4178.625,
"step": 3490,
"tokens_trained": 11.434975168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9928373874193319,
"grad_norm": 0.6990298628807068,
"loss": 1.1454,
"loss_ce": 1.1152887344360352,
"loss_region": 0.05999855324625969,
"loss_total": 1.1752872467041016,
"lr": 0.001102717965434666,
"router/selected_tokens_s0": 7405.5,
"router/selected_tokens_s1": 4282.875,
"step": 3500,
"tokens_trained": 11.467740608
},
{
"epoch": 0.9928373874193319,
"eval_ppl": 2.990368541747783,
"eval_runtime": 1.0282,
"step": 3500,
"tokens_trained": 11.467740608
},
{
"epoch": 0.9928373874193319,
"eval_F": 0.34124931635284006,
"eval_F_cds": 0.3399935841620457,
"eval_F_dig": 0.3237752949449176,
"eval_F_exon": 0.3411330565689605,
"eval_F_intron": 0.3419830788859948,
"eval_F_nig": 0.3420374751946268,
"eval_F_promoter": 0.3388947987234757,
"eval_F_utr": 0.3383235847354995,
"eval_G": 0.3070386282009337,
"eval_G_cds": 0.30430517226811327,
"eval_G_dig": 0.2977837318833503,
"eval_G_exon": 0.3072212306579444,
"eval_G_intron": 0.3076679212901026,
"eval_G_nig": 0.3092953701307529,
"eval_G_promoter": 0.3028028836396338,
"eval_G_utr": 0.3037611886096009,
"eval_avg_bp_per_token": 2.9304088010715144,
"eval_bp_per_token/cds": 2.9412319719638766,
"eval_bp_per_token/dig": 3.088561776061776,
"eval_bp_per_token/exon": 2.9314074984634297,
"eval_bp_per_token/intron": 2.9241212847649845,
"eval_bp_per_token/nig": 2.923656243898357,
"eval_bp_per_token/promoter": 2.9507682141087064,
"eval_bp_per_token/utr": 2.9557501904036556,
"eval_ppl_cds": 3.7629390152362947,
"eval_ppl_dig": 1.147684685044179,
"eval_ppl_exon": 3.390840392014607,
"eval_ppl_intron": 3.042627072402514,
"eval_ppl_nig": 2.824713259021816,
"eval_ppl_promoter": 3.3304855964307176,
"eval_ppl_utr": 3.3256724056579388,
"step": 3500,
"tokens_trained": 11.467740608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.9956740656691014,
"grad_norm": 0.5327582359313965,
"loss": 1.1501,
"loss_ce": 1.1076359748840332,
"loss_region": 0.0600367896258831,
"loss_total": 1.1676727533340454,
"lr": 0.001102311073450815,
"router/selected_tokens_s0": 7424.625,
"router/selected_tokens_s1": 4241.0,
"step": 3510,
"tokens_trained": 11.500506048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 0.998510743918871,
"grad_norm": 0.41065487265586853,
"loss": 1.1514,
"loss_ce": 1.0242090225219727,
"loss_region": 0.059992894530296326,
"loss_total": 1.0842019319534302,
"lr": 0.001101904181466964,
"router/selected_tokens_s0": 7490.25,
"router/selected_tokens_s1": 4330.75,
"step": 3520,
"tokens_trained": 11.533271488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0011346712999079,
"grad_norm": 0.1535387933254242,
"loss": 1.1414,
"loss_ce": 1.102476954460144,
"loss_region": 0.060031864792108536,
"loss_total": 1.1625088453292847,
"lr": 0.0011014972894831132,
"router/selected_tokens_s0": 7425.125,
"router/selected_tokens_s1": 4247.0,
"step": 3530,
"tokens_trained": 11.56357952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0039713495496774,
"grad_norm": 0.1981125921010971,
"loss": 1.1437,
"loss_ce": 1.0602258443832397,
"loss_region": 0.05993477255105972,
"loss_total": 1.1201605796813965,
"lr": 0.0011010903974992621,
"router/selected_tokens_s0": 7320.25,
"router/selected_tokens_s1": 4332.875,
"step": 3540,
"tokens_trained": 11.59634496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.006808027799447,
"grad_norm": 0.5812313556671143,
"loss": 1.156,
"loss_ce": 1.0328749418258667,
"loss_region": 0.059998273849487305,
"loss_total": 1.092873215675354,
"lr": 0.001100683505515411,
"router/selected_tokens_s0": 7472.125,
"router/selected_tokens_s1": 4304.625,
"step": 3550,
"tokens_trained": 11.6291104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0096447060492164,
"grad_norm": 0.4127905070781708,
"loss": 1.1601,
"loss_ce": 1.1510852575302124,
"loss_region": 0.059947848320007324,
"loss_total": 1.2110331058502197,
"lr": 0.00110027661353156,
"router/selected_tokens_s0": 7431.625,
"router/selected_tokens_s1": 4357.5,
"step": 3560,
"tokens_trained": 11.66187584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.012481384298986,
"grad_norm": 0.3352585434913635,
"loss": 1.1578,
"loss_ce": 1.0219836235046387,
"loss_region": 0.059950411319732666,
"loss_total": 1.0819339752197266,
"lr": 0.001099869721547709,
"router/selected_tokens_s0": 7476.0,
"router/selected_tokens_s1": 4375.875,
"step": 3570,
"tokens_trained": 11.69464128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0153180625487555,
"grad_norm": 0.35328951478004456,
"loss": 1.1552,
"loss_ce": 1.1077344417572021,
"loss_region": 0.06004289910197258,
"loss_total": 1.1677772998809814,
"lr": 0.001099462829563858,
"router/selected_tokens_s0": 7441.5,
"router/selected_tokens_s1": 4242.75,
"step": 3580,
"tokens_trained": 11.72740592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.018154740798525,
"grad_norm": 0.19262564182281494,
"loss": 1.1517,
"loss_ce": 1.1469261646270752,
"loss_region": 0.060008659958839417,
"loss_total": 1.2069348096847534,
"lr": 0.001099055937580007,
"router/selected_tokens_s0": 7375.125,
"router/selected_tokens_s1": 4253.875,
"step": 3590,
"tokens_trained": 11.76017136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0209914190482945,
"grad_norm": 0.20067667961120605,
"loss": 1.1528,
"loss_ce": 1.0741374492645264,
"loss_region": 0.060044094920158386,
"loss_total": 1.1341814994812012,
"lr": 0.001098649045596156,
"router/selected_tokens_s0": 7434.25,
"router/selected_tokens_s1": 4234.375,
"step": 3600,
"tokens_trained": 11.7929352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.023828097298064,
"grad_norm": 0.30228880047798157,
"loss": 1.1506,
"loss_ce": 1.1023025512695312,
"loss_region": 0.06002019718289375,
"loss_total": 1.162322759628296,
"lr": 0.0010982421536123049,
"router/selected_tokens_s0": 7451.25,
"router/selected_tokens_s1": 4271.25,
"step": 3610,
"tokens_trained": 11.82570064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0266647755478335,
"grad_norm": 0.8743928670883179,
"loss": 1.148,
"loss_ce": 1.005650520324707,
"loss_region": 0.060022272169589996,
"loss_total": 1.065672755241394,
"lr": 0.0010978352616284538,
"router/selected_tokens_s0": 7474.625,
"router/selected_tokens_s1": 4284.5,
"step": 3620,
"tokens_trained": 11.85846448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.029501453797603,
"grad_norm": 0.827194094657898,
"loss": 1.1452,
"loss_ce": 1.1064406633377075,
"loss_region": 0.05999286100268364,
"loss_total": 1.166433572769165,
"lr": 0.0010974283696446028,
"router/selected_tokens_s0": 7428.625,
"router/selected_tokens_s1": 4296.75,
"step": 3630,
"tokens_trained": 11.89122992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0323381320473726,
"grad_norm": 0.27454066276550293,
"loss": 1.139,
"loss_ce": 1.0833203792572021,
"loss_region": 0.059953462332487106,
"loss_total": 1.1432738304138184,
"lr": 0.0010970214776607518,
"router/selected_tokens_s0": 7458.875,
"router/selected_tokens_s1": 4362.125,
"step": 3640,
"tokens_trained": 11.92399536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.035174810297142,
"grad_norm": 0.07617896795272827,
"loss": 1.1378,
"loss_ce": 1.1439638137817383,
"loss_region": 0.059945326298475266,
"loss_total": 1.203909158706665,
"lr": 0.0010966145856769007,
"router/selected_tokens_s0": 7424.625,
"router/selected_tokens_s1": 4355.875,
"step": 3650,
"tokens_trained": 11.9567608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0380114885469116,
"grad_norm": 0.6363743543624878,
"loss": 1.1485,
"loss_ce": 1.079978585243225,
"loss_region": 0.06003373861312866,
"loss_total": 1.140012264251709,
"lr": 0.0010962076936930497,
"router/selected_tokens_s0": 7431.375,
"router/selected_tokens_s1": 4242.875,
"step": 3660,
"tokens_trained": 11.98952624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0408481667966811,
"grad_norm": 0.41256821155548096,
"loss": 1.1433,
"loss_ce": 1.13809072971344,
"loss_region": 0.06003982573747635,
"loss_total": 1.1981306076049805,
"lr": 0.0010958008017091987,
"router/selected_tokens_s0": 7385.375,
"router/selected_tokens_s1": 4224.125,
"step": 3670,
"tokens_trained": 12.02229168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0436848450464506,
"grad_norm": 0.22508053481578827,
"loss": 1.1512,
"loss_ce": 1.103158712387085,
"loss_region": 0.06010059267282486,
"loss_total": 1.1632592678070068,
"lr": 0.0010953939097253476,
"router/selected_tokens_s0": 7469.0,
"router/selected_tokens_s1": 4187.25,
"step": 3680,
"tokens_trained": 12.05505712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0465215232962202,
"grad_norm": 0.33240363001823425,
"loss": 1.1358,
"loss_ce": 1.138681173324585,
"loss_region": 0.059974271804094315,
"loss_total": 1.1986554861068726,
"lr": 0.0010949870177414966,
"router/selected_tokens_s0": 7456.125,
"router/selected_tokens_s1": 4332.125,
"step": 3690,
"tokens_trained": 12.08782256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0493582015459897,
"grad_norm": 0.372721791267395,
"loss": 1.1436,
"loss_ce": 1.081639051437378,
"loss_region": 0.05995466560125351,
"loss_total": 1.1415936946868896,
"lr": 0.0010945801257576456,
"router/selected_tokens_s0": 7384.875,
"router/selected_tokens_s1": 4328.0,
"step": 3700,
"tokens_trained": 12.1205864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0521948797957592,
"grad_norm": 0.7060279250144958,
"loss": 1.1442,
"loss_ce": 1.137622594833374,
"loss_region": 0.06001655012369156,
"loss_total": 1.1976391077041626,
"lr": 0.0010941732337737947,
"router/selected_tokens_s0": 7376.0,
"router/selected_tokens_s1": 4245.0,
"step": 3710,
"tokens_trained": 12.15335184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0550315580455287,
"grad_norm": 0.4556179940700531,
"loss": 1.1469,
"loss_ce": 1.1033775806427002,
"loss_region": 0.05993418022990227,
"loss_total": 1.1633117198944092,
"lr": 0.0010937663417899437,
"router/selected_tokens_s0": 7439.25,
"router/selected_tokens_s1": 4378.875,
"step": 3720,
"tokens_trained": 12.18611712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0578682362952982,
"grad_norm": 0.30534932017326355,
"loss": 1.1422,
"loss_ce": 1.0742703676223755,
"loss_region": 0.06001539155840874,
"loss_total": 1.134285807609558,
"lr": 0.0010933594498060927,
"router/selected_tokens_s0": 7455.875,
"router/selected_tokens_s1": 4283.875,
"step": 3730,
"tokens_trained": 12.21888256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0607049145450678,
"grad_norm": 0.44344577193260193,
"loss": 1.1423,
"loss_ce": 1.1271259784698486,
"loss_region": 0.059946540743112564,
"loss_total": 1.187072515487671,
"lr": 0.0010929525578222414,
"router/selected_tokens_s0": 7390.625,
"router/selected_tokens_s1": 4344.75,
"step": 3740,
"tokens_trained": 12.251648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0635415927948373,
"grad_norm": 0.5021528005599976,
"loss": 1.1466,
"loss_ce": 1.1103929281234741,
"loss_region": 0.06003858521580696,
"loss_total": 1.1704314947128296,
"lr": 0.0010925456658383904,
"router/selected_tokens_s0": 7478.625,
"router/selected_tokens_s1": 4263.0,
"step": 3750,
"tokens_trained": 12.284409608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0663782710446068,
"grad_norm": 0.21326135098934174,
"loss": 1.1457,
"loss_ce": 1.101629614830017,
"loss_region": 0.05999373272061348,
"loss_total": 1.1616233587265015,
"lr": 0.0010921387738545394,
"router/selected_tokens_s0": 7429.5,
"router/selected_tokens_s1": 4293.75,
"step": 3760,
"tokens_trained": 12.317175048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0692149492943763,
"grad_norm": 0.12464369833469391,
"loss": 1.1357,
"loss_ce": 1.0160081386566162,
"loss_region": 0.05996187403798103,
"loss_total": 1.0759700536727905,
"lr": 0.0010917318818706883,
"router/selected_tokens_s0": 7375.25,
"router/selected_tokens_s1": 4324.25,
"step": 3770,
"tokens_trained": 12.349940488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0720516275441458,
"grad_norm": 0.6811399459838867,
"loss": 1.1444,
"loss_ce": 1.106014609336853,
"loss_region": 0.06000228598713875,
"loss_total": 1.166016936302185,
"lr": 0.0010913249898868375,
"router/selected_tokens_s0": 7413.0,
"router/selected_tokens_s1": 4280.0,
"step": 3780,
"tokens_trained": 12.382705928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0748883057939154,
"grad_norm": 0.5335866808891296,
"loss": 1.1425,
"loss_ce": 1.0999557971954346,
"loss_region": 0.059975773096084595,
"loss_total": 1.1599315404891968,
"lr": 0.0010909180979029865,
"router/selected_tokens_s0": 7386.125,
"router/selected_tokens_s1": 4300.625,
"step": 3790,
"tokens_trained": 12.415470568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0777249840436849,
"grad_norm": 0.4129198491573334,
"loss": 1.1451,
"loss_ce": 1.1344683170318604,
"loss_region": 0.05997394025325775,
"loss_total": 1.1944422721862793,
"lr": 0.0010905112059191354,
"router/selected_tokens_s0": 7444.875,
"router/selected_tokens_s1": 4331.875,
"step": 3800,
"tokens_trained": 12.448236008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0805616622934544,
"grad_norm": 0.16327404975891113,
"loss": 1.1442,
"loss_ce": 1.1254371404647827,
"loss_region": 0.0599752776324749,
"loss_total": 1.1854124069213867,
"lr": 0.0010901043139352844,
"router/selected_tokens_s0": 7459.75,
"router/selected_tokens_s1": 4331.375,
"step": 3810,
"tokens_trained": 12.481001448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.083398340543224,
"grad_norm": 0.7598224878311157,
"loss": 1.1348,
"loss_ce": 1.0765974521636963,
"loss_region": 0.05999346822500229,
"loss_total": 1.1365909576416016,
"lr": 0.0010896974219514334,
"router/selected_tokens_s0": 7440.25,
"router/selected_tokens_s1": 4309.625,
"step": 3820,
"tokens_trained": 12.513766888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0862350187929934,
"grad_norm": 0.5273082852363586,
"loss": 1.1429,
"loss_ce": 1.1588966846466064,
"loss_region": 0.059993255883455276,
"loss_total": 1.2188899517059326,
"lr": 0.0010892905299675823,
"router/selected_tokens_s0": 7423.5,
"router/selected_tokens_s1": 4291.375,
"step": 3830,
"tokens_trained": 12.546532328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.089071697042763,
"grad_norm": 0.20225034654140472,
"loss": 1.1464,
"loss_ce": 1.0285930633544922,
"loss_region": 0.06002606824040413,
"loss_total": 1.0886191129684448,
"lr": 0.0010888836379837313,
"router/selected_tokens_s0": 7424.75,
"router/selected_tokens_s1": 4250.125,
"step": 3840,
"tokens_trained": 12.57929404
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0919083752925325,
"grad_norm": 0.1807214766740799,
"loss": 1.1429,
"loss_ce": 1.0824134349822998,
"loss_region": 0.05998450517654419,
"loss_total": 1.1423978805541992,
"lr": 0.0010884767459998803,
"router/selected_tokens_s0": 7402.125,
"router/selected_tokens_s1": 4295.5,
"step": 3850,
"tokens_trained": 12.61205788
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.094745053542302,
"grad_norm": 0.8687542080879211,
"loss": 1.1394,
"loss_ce": 1.0904909372329712,
"loss_region": 0.06012667715549469,
"loss_total": 1.1506175994873047,
"lr": 0.0010880698540160292,
"router/selected_tokens_s0": 7367.875,
"router/selected_tokens_s1": 4109.25,
"step": 3860,
"tokens_trained": 12.64482332
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.0975817317920715,
"grad_norm": 0.31520599126815796,
"loss": 1.1336,
"loss_ce": 1.1574056148529053,
"loss_region": 0.060040898621082306,
"loss_total": 1.2174465656280518,
"lr": 0.0010876629620321782,
"router/selected_tokens_s0": 7445.5,
"router/selected_tokens_s1": 4242.875,
"step": 3870,
"tokens_trained": 12.677587992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.100418410041841,
"grad_norm": 0.16909047961235046,
"loss": 1.1397,
"loss_ce": 1.0726521015167236,
"loss_region": 0.060116663575172424,
"loss_total": 1.1327687501907349,
"lr": 0.0010872560700483272,
"router/selected_tokens_s0": 7365.125,
"router/selected_tokens_s1": 4121.625,
"step": 3880,
"tokens_trained": 12.710352632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1032550882916106,
"grad_norm": 0.4796403646469116,
"loss": 1.1426,
"loss_ce": 1.043395757675171,
"loss_region": 0.060001593083143234,
"loss_total": 1.1033973693847656,
"lr": 0.0010868491780644761,
"router/selected_tokens_s0": 7446.25,
"router/selected_tokens_s1": 4295.125,
"step": 3890,
"tokens_trained": 12.743118072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.10609176654138,
"grad_norm": 0.3688628375530243,
"loss": 1.1334,
"loss_ce": 1.0408189296722412,
"loss_region": 0.05999990180134773,
"loss_total": 1.1008188724517822,
"lr": 0.001086442286080625,
"router/selected_tokens_s0": 7405.875,
"router/selected_tokens_s1": 4278.0,
"step": 3900,
"tokens_trained": 12.775882712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1089284447911496,
"grad_norm": 0.1674785166978836,
"loss": 1.1453,
"loss_ce": 1.1500557661056519,
"loss_region": 0.06002119183540344,
"loss_total": 1.210076928138733,
"lr": 0.001086035394096774,
"router/selected_tokens_s0": 7402.0,
"router/selected_tokens_s1": 4250.0,
"step": 3910,
"tokens_trained": 12.808648152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1117651230409191,
"grad_norm": 0.18490345776081085,
"loss": 1.1435,
"loss_ce": 1.1302103996276855,
"loss_region": 0.059938620775938034,
"loss_total": 1.1901490688323975,
"lr": 0.001085628502112923,
"router/selected_tokens_s0": 7380.0,
"router/selected_tokens_s1": 4363.375,
"step": 3920,
"tokens_trained": 12.841413592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1146018012906886,
"grad_norm": 0.23284821212291718,
"loss": 1.1423,
"loss_ce": 1.0065786838531494,
"loss_region": 0.059997957199811935,
"loss_total": 1.066576600074768,
"lr": 0.001085221610129072,
"router/selected_tokens_s0": 7459.875,
"router/selected_tokens_s1": 4311.375,
"step": 3930,
"tokens_trained": 12.874179032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1174384795404582,
"grad_norm": 0.23733806610107422,
"loss": 1.1395,
"loss_ce": 1.0488975048065186,
"loss_region": 0.060037050396203995,
"loss_total": 1.1089345216751099,
"lr": 0.001084814718145221,
"router/selected_tokens_s0": 7396.625,
"router/selected_tokens_s1": 4231.75,
"step": 3940,
"tokens_trained": 12.906944472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1202751577902277,
"grad_norm": 0.33361032605171204,
"loss": 1.1355,
"loss_ce": 1.0286937952041626,
"loss_region": 0.060001228004693985,
"loss_total": 1.0886950492858887,
"lr": 0.00108440782616137,
"router/selected_tokens_s0": 7383.375,
"router/selected_tokens_s1": 4268.5,
"step": 3950,
"tokens_trained": 12.939709912
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1231118360399972,
"grad_norm": 0.46005359292030334,
"loss": 1.1301,
"loss_ce": 1.105696678161621,
"loss_region": 0.059990961104631424,
"loss_total": 1.1656876802444458,
"lr": 0.001084000934177519,
"router/selected_tokens_s0": 7330.25,
"router/selected_tokens_s1": 4260.25,
"step": 3960,
"tokens_trained": 12.972475352
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1259485142897667,
"grad_norm": 0.09066780656576157,
"loss": 1.1408,
"loss_ce": 1.1488341093063354,
"loss_region": 0.059959400445222855,
"loss_total": 1.2087935209274292,
"lr": 0.001083594042193668,
"router/selected_tokens_s0": 7336.875,
"router/selected_tokens_s1": 4313.5,
"step": 3970,
"tokens_trained": 13.005240792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1287851925395362,
"grad_norm": 0.9433469772338867,
"loss": 1.1324,
"loss_ce": 1.1015199422836304,
"loss_region": 0.05999411270022392,
"loss_total": 1.1615140438079834,
"lr": 0.001083187150209817,
"router/selected_tokens_s0": 7323.5,
"router/selected_tokens_s1": 4254.75,
"step": 3980,
"tokens_trained": 13.038005432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1316218707893058,
"grad_norm": 0.2512190639972687,
"loss": 1.1389,
"loss_ce": 1.0987569093704224,
"loss_region": 0.05999063700437546,
"loss_total": 1.1587475538253784,
"lr": 0.0010827802582259658,
"router/selected_tokens_s0": 7455.125,
"router/selected_tokens_s1": 4317.25,
"step": 3990,
"tokens_trained": 13.070770872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1344585490390753,
"grad_norm": 0.3653326630592346,
"loss": 1.1399,
"loss_ce": 1.072330355644226,
"loss_region": 0.06002863124012947,
"loss_total": 1.1323590278625488,
"lr": 0.0010823733662421147,
"router/selected_tokens_s0": 7473.0,
"router/selected_tokens_s1": 4271.5,
"step": 4000,
"tokens_trained": 13.103536312
},
{
"epoch": 1.1344585490390753,
"eval_ppl": 2.9523484878038198,
"eval_runtime": 1.0573,
"step": 4000,
"tokens_trained": 13.103536312
},
{
"epoch": 1.1344585490390753,
"eval_F": 0.33808435554861055,
"eval_F_cds": 0.33309655836121166,
"eval_F_dig": 0.32549417923275253,
"eval_F_exon": 0.33622677904977566,
"eval_F_intron": 0.3384065143924063,
"eval_F_nig": 0.33901630794280774,
"eval_F_promoter": 0.33740178788048447,
"eval_F_utr": 0.33783400757556237,
"eval_G": 0.3120454166035921,
"eval_G_cds": 0.30918100324801795,
"eval_G_dig": 0.3016167339733573,
"eval_G_exon": 0.31355957051725586,
"eval_G_intron": 0.3124654773125766,
"eval_G_nig": 0.31342695299580536,
"eval_G_promoter": 0.30978970781894444,
"eval_G_utr": 0.30942776240691594,
"eval_avg_bp_per_token": 2.957841685331156,
"eval_bp_per_token/cds": 3.0021324895095276,
"eval_bp_per_token/dig": 3.07225156024964,
"eval_bp_per_token/exon": 2.974183088051883,
"eval_bp_per_token/intron": 2.955025856388891,
"eval_bp_per_token/nig": 2.94971060851946,
"eval_bp_per_token/promoter": 2.963825432822612,
"eval_bp_per_token/utr": 2.9600335596064373,
"eval_ppl_cds": 3.7308104955454358,
"eval_ppl_dig": 1.1529258628275645,
"eval_ppl_exon": 3.3675201309937965,
"eval_ppl_intron": 3.0130073290188872,
"eval_ppl_nig": 2.7720357615980986,
"eval_ppl_promoter": 3.30537569832896,
"eval_ppl_utr": 3.2970389002777467,
"step": 4000,
"tokens_trained": 13.103536312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1372952272888448,
"grad_norm": 0.24893344938755035,
"loss": 1.1333,
"loss_ce": 1.0987017154693604,
"loss_region": 0.05996103584766388,
"loss_total": 1.1586627960205078,
"lr": 0.0010819664742582637,
"router/selected_tokens_s0": 7486.375,
"router/selected_tokens_s1": 4381.25,
"step": 4010,
"tokens_trained": 13.136300952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1401319055386143,
"grad_norm": 0.5850163102149963,
"loss": 1.1354,
"loss_ce": 1.0224004983901978,
"loss_region": 0.059973448514938354,
"loss_total": 1.0823739767074585,
"lr": 0.0010815595822744127,
"router/selected_tokens_s0": 7335.75,
"router/selected_tokens_s1": 4307.875,
"step": 4020,
"tokens_trained": 13.169065592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1429685837883838,
"grad_norm": 0.35301917791366577,
"loss": 1.1386,
"loss_ce": 1.0751712322235107,
"loss_region": 0.059972189366817474,
"loss_total": 1.1351433992385864,
"lr": 0.0010811526902905618,
"router/selected_tokens_s0": 7411.125,
"router/selected_tokens_s1": 4328.75,
"step": 4030,
"tokens_trained": 13.201831032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1458052620381534,
"grad_norm": 0.5564679503440857,
"loss": 1.1356,
"loss_ce": 1.0059022903442383,
"loss_region": 0.05994752421975136,
"loss_total": 1.065849781036377,
"lr": 0.0010807457983067108,
"router/selected_tokens_s0": 7381.0,
"router/selected_tokens_s1": 4361.5,
"step": 4040,
"tokens_trained": 13.234596472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1486419402879229,
"grad_norm": 0.18776975572109222,
"loss": 1.1368,
"loss_ce": 1.1155309677124023,
"loss_region": 0.06004191190004349,
"loss_total": 1.1755728721618652,
"lr": 0.0010803389063228598,
"router/selected_tokens_s0": 7473.375,
"router/selected_tokens_s1": 4257.875,
"step": 4050,
"tokens_trained": 13.267361888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1514786185376924,
"grad_norm": 0.17018158733844757,
"loss": 1.1406,
"loss_ce": 1.113221287727356,
"loss_region": 0.06000470370054245,
"loss_total": 1.173225998878479,
"lr": 0.0010799320143390087,
"router/selected_tokens_s0": 7405.875,
"router/selected_tokens_s1": 4272.375,
"step": 4060,
"tokens_trained": 13.300127328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.154315296787462,
"grad_norm": 0.42208781838417053,
"loss": 1.1383,
"loss_ce": 1.0297209024429321,
"loss_region": 0.060001879930496216,
"loss_total": 1.089722752571106,
"lr": 0.0010795251223551577,
"router/selected_tokens_s0": 7452.25,
"router/selected_tokens_s1": 4312.75,
"step": 4070,
"tokens_trained": 13.332892768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1571519750372314,
"grad_norm": 0.35124096274375916,
"loss": 1.1331,
"loss_ce": 1.1511611938476562,
"loss_region": 0.05999987572431564,
"loss_total": 1.2111610174179077,
"lr": 0.0010791182303713067,
"router/selected_tokens_s0": 7421.25,
"router/selected_tokens_s1": 4286.75,
"step": 4080,
"tokens_trained": 13.365658208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.159988653287001,
"grad_norm": 0.2931098937988281,
"loss": 1.1368,
"loss_ce": 1.0053439140319824,
"loss_region": 0.060056962072849274,
"loss_total": 1.0654008388519287,
"lr": 0.0010787113383874556,
"router/selected_tokens_s0": 7453.75,
"router/selected_tokens_s1": 4215.25,
"step": 4090,
"tokens_trained": 13.398422568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1628253315367705,
"grad_norm": 0.40350601077079773,
"loss": 1.1383,
"loss_ce": 1.1511709690093994,
"loss_region": 0.05996457114815712,
"loss_total": 1.2111355066299438,
"lr": 0.0010783044464036046,
"router/selected_tokens_s0": 7475.75,
"router/selected_tokens_s1": 4380.375,
"step": 4100,
"tokens_trained": 13.431185432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.16566200978654,
"grad_norm": 0.2456795573234558,
"loss": 1.1353,
"loss_ce": 1.1185240745544434,
"loss_region": 0.06002639979124069,
"loss_total": 1.1785504817962646,
"lr": 0.0010778975544197536,
"router/selected_tokens_s0": 7406.5,
"router/selected_tokens_s1": 4244.625,
"step": 4110,
"tokens_trained": 13.463950872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1684986880363095,
"grad_norm": 0.4379357397556305,
"loss": 1.1306,
"loss_ce": 0.9611161947250366,
"loss_region": 0.06001690775156021,
"loss_total": 1.0211330652236938,
"lr": 0.0010774906624359025,
"router/selected_tokens_s0": 7336.125,
"router/selected_tokens_s1": 4239.0,
"step": 4120,
"tokens_trained": 13.496713976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.171335366286079,
"grad_norm": 0.6094051599502563,
"loss": 1.1339,
"loss_ce": 1.146083950996399,
"loss_region": 0.060058578848838806,
"loss_total": 1.206142544746399,
"lr": 0.0010770837704520515,
"router/selected_tokens_s0": 7396.25,
"router/selected_tokens_s1": 4185.5,
"step": 4130,
"tokens_trained": 13.529479416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1741720445358486,
"grad_norm": 0.2225402295589447,
"loss": 1.1436,
"loss_ce": 0.917146623134613,
"loss_region": 0.060047075152397156,
"loss_total": 0.9771937131881714,
"lr": 0.0010766768784682005,
"router/selected_tokens_s0": 7424.25,
"router/selected_tokens_s1": 4215.5,
"step": 4140,
"tokens_trained": 13.562244856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.177008722785618,
"grad_norm": 0.13494586944580078,
"loss": 1.1371,
"loss_ce": 1.123674988746643,
"loss_region": 0.06002392992377281,
"loss_total": 1.1836988925933838,
"lr": 0.0010762699864843494,
"router/selected_tokens_s0": 7392.875,
"router/selected_tokens_s1": 4235.0,
"step": 4150,
"tokens_trained": 13.595010296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1798454010353876,
"grad_norm": 0.40003934502601624,
"loss": 1.1226,
"loss_ce": 0.9939314126968384,
"loss_region": 0.059998590499162674,
"loss_total": 1.0539300441741943,
"lr": 0.0010758630945004984,
"router/selected_tokens_s0": 7431.625,
"router/selected_tokens_s1": 4292.125,
"step": 4160,
"tokens_trained": 13.627775736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1826820792851571,
"grad_norm": 0.4521540105342865,
"loss": 1.1314,
"loss_ce": 1.0949397087097168,
"loss_region": 0.05998746678233147,
"loss_total": 1.154927134513855,
"lr": 0.0010754562025166474,
"router/selected_tokens_s0": 7429.5,
"router/selected_tokens_s1": 4307.875,
"step": 4170,
"tokens_trained": 13.660541176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1855187575349266,
"grad_norm": 0.20438899099826813,
"loss": 1.1314,
"loss_ce": 1.1041476726531982,
"loss_region": 0.0599747933447361,
"loss_total": 1.164122462272644,
"lr": 0.0010750493105327963,
"router/selected_tokens_s0": 7337.25,
"router/selected_tokens_s1": 4301.25,
"step": 4180,
"tokens_trained": 13.693306616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1883554357846962,
"grad_norm": 0.7250345349311829,
"loss": 1.1298,
"loss_ce": 1.0269466638565063,
"loss_region": 0.060086045414209366,
"loss_total": 1.087032675743103,
"lr": 0.0010746424185489453,
"router/selected_tokens_s0": 7419.875,
"router/selected_tokens_s1": 4171.125,
"step": 4190,
"tokens_trained": 13.726072056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1911921140344657,
"grad_norm": 0.21629612147808075,
"loss": 1.1353,
"loss_ce": 1.0419249534606934,
"loss_region": 0.060025639832019806,
"loss_total": 1.1019506454467773,
"lr": 0.0010742355265650943,
"router/selected_tokens_s0": 7399.125,
"router/selected_tokens_s1": 4234.125,
"step": 4200,
"tokens_trained": 13.758837496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1940287922842352,
"grad_norm": 0.1624452769756317,
"loss": 1.1332,
"loss_ce": 1.0706652402877808,
"loss_region": 0.059998173266649246,
"loss_total": 1.1306633949279785,
"lr": 0.0010738286345812434,
"router/selected_tokens_s0": 7412.125,
"router/selected_tokens_s1": 4284.5,
"step": 4210,
"tokens_trained": 13.791602936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1968654705340047,
"grad_norm": 0.5419676899909973,
"loss": 1.143,
"loss_ce": 1.0858913660049438,
"loss_region": 0.05999434366822243,
"loss_total": 1.145885705947876,
"lr": 0.0010734217425973924,
"router/selected_tokens_s0": 7422.5,
"router/selected_tokens_s1": 4295.875,
"step": 4220,
"tokens_trained": 13.824368376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.1997021487837742,
"grad_norm": 0.2358941286802292,
"loss": 1.1329,
"loss_ce": 1.081803321838379,
"loss_region": 0.060014963150024414,
"loss_total": 1.1418182849884033,
"lr": 0.0010730148506135414,
"router/selected_tokens_s0": 7424.625,
"router/selected_tokens_s1": 4259.25,
"step": 4230,
"tokens_trained": 13.857133016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2025388270335438,
"grad_norm": 0.510456383228302,
"loss": 1.1278,
"loss_ce": 1.110556721687317,
"loss_region": 0.06000852584838867,
"loss_total": 1.1705652475357056,
"lr": 0.0010726079586296901,
"router/selected_tokens_s0": 7484.0,
"router/selected_tokens_s1": 4306.625,
"step": 4240,
"tokens_trained": 13.889896856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2053755052833133,
"grad_norm": 0.18302984535694122,
"loss": 1.1313,
"loss_ce": 1.0691109895706177,
"loss_region": 0.05997291952371597,
"loss_total": 1.1290838718414307,
"lr": 0.001072201066645839,
"router/selected_tokens_s0": 7450.0,
"router/selected_tokens_s1": 4361.5,
"step": 4250,
"tokens_trained": 13.922662296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2082121835330828,
"grad_norm": 0.5035632848739624,
"loss": 1.1307,
"loss_ce": 1.0827662944793701,
"loss_region": 0.06004443019628525,
"loss_total": 1.1428107023239136,
"lr": 0.001071794174661988,
"router/selected_tokens_s0": 7423.75,
"router/selected_tokens_s1": 4217.75,
"step": 4260,
"tokens_trained": 13.955427736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2110488617828523,
"grad_norm": 0.3019254505634308,
"loss": 1.1301,
"loss_ce": 1.080075740814209,
"loss_region": 0.06004132702946663,
"loss_total": 1.1401170492172241,
"lr": 0.0010713872826781372,
"router/selected_tokens_s0": 7457.625,
"router/selected_tokens_s1": 4234.875,
"step": 4270,
"tokens_trained": 13.988193176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2138855400326218,
"grad_norm": 0.22490078210830688,
"loss": 1.1268,
"loss_ce": 1.1394598484039307,
"loss_region": 0.05999091640114784,
"loss_total": 1.1994507312774658,
"lr": 0.0010709803906942862,
"router/selected_tokens_s0": 7419.125,
"router/selected_tokens_s1": 4300.875,
"step": 4280,
"tokens_trained": 14.020958616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2167222182823914,
"grad_norm": 0.2757962644100189,
"loss": 1.1311,
"loss_ce": 1.060826063156128,
"loss_region": 0.059974100440740585,
"loss_total": 1.1208001375198364,
"lr": 0.0010705734987104352,
"router/selected_tokens_s0": 7454.125,
"router/selected_tokens_s1": 4350.75,
"step": 4290,
"tokens_trained": 14.053724056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2195588965321609,
"grad_norm": 0.3286055028438568,
"loss": 1.1351,
"loss_ce": 1.116142749786377,
"loss_region": 0.05997960641980171,
"loss_total": 1.1761223077774048,
"lr": 0.0010701666067265841,
"router/selected_tokens_s0": 7509.0,
"router/selected_tokens_s1": 4382.875,
"step": 4300,
"tokens_trained": 14.086488728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2223955747819304,
"grad_norm": 0.5284584760665894,
"loss": 1.1263,
"loss_ce": 1.0240802764892578,
"loss_region": 0.06002355366945267,
"loss_total": 1.0841038227081299,
"lr": 0.001069759714742733,
"router/selected_tokens_s0": 7453.75,
"router/selected_tokens_s1": 4262.0,
"step": 4310,
"tokens_trained": 14.119254168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2252322530317,
"grad_norm": 0.052983351051807404,
"loss": 1.1243,
"loss_ce": 1.0505942106246948,
"loss_region": 0.06003909558057785,
"loss_total": 1.1106332540512085,
"lr": 0.001069352822758882,
"router/selected_tokens_s0": 7451.5,
"router/selected_tokens_s1": 4236.625,
"step": 4320,
"tokens_trained": 14.152019608
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2280689312814694,
"grad_norm": 0.44211697578430176,
"loss": 1.1298,
"loss_ce": 1.0448384284973145,
"loss_region": 0.060010477900505066,
"loss_total": 1.104848861694336,
"lr": 0.001068945930775031,
"router/selected_tokens_s0": 7421.625,
"router/selected_tokens_s1": 4270.125,
"step": 4330,
"tokens_trained": 14.184785048
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.230905609531239,
"grad_norm": 0.24782565236091614,
"loss": 1.1294,
"loss_ce": 1.0347596406936646,
"loss_region": 0.05996475741267204,
"loss_total": 1.094724416732788,
"lr": 0.00106853903879118,
"router/selected_tokens_s0": 7470.625,
"router/selected_tokens_s1": 4404.375,
"step": 4340,
"tokens_trained": 14.217550488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2337422877810085,
"grad_norm": 0.11738014966249466,
"loss": 1.1239,
"loss_ce": 1.104210376739502,
"loss_region": 0.06001203507184982,
"loss_total": 1.1642223596572876,
"lr": 0.001068132146807329,
"router/selected_tokens_s0": 7455.25,
"router/selected_tokens_s1": 4282.0,
"step": 4350,
"tokens_trained": 14.250315928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.236578966030778,
"grad_norm": 0.30317816138267517,
"loss": 1.1244,
"loss_ce": 1.1028004884719849,
"loss_region": 0.06001470610499382,
"loss_total": 1.1628152132034302,
"lr": 0.001067725254823478,
"router/selected_tokens_s0": 7429.75,
"router/selected_tokens_s1": 4263.25,
"step": 4360,
"tokens_trained": 14.283081368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2394156442805475,
"grad_norm": 0.200590580701828,
"loss": 1.1274,
"loss_ce": 1.0992459058761597,
"loss_region": 0.06001310050487518,
"loss_total": 1.1592589616775513,
"lr": 0.0010673183628396269,
"router/selected_tokens_s0": 7432.875,
"router/selected_tokens_s1": 4263.125,
"step": 4370,
"tokens_trained": 14.315846808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.242252322530317,
"grad_norm": 0.4970727860927582,
"loss": 1.1246,
"loss_ce": 1.1652504205703735,
"loss_region": 0.060001764446496964,
"loss_total": 1.2252521514892578,
"lr": 0.0010669114708557758,
"router/selected_tokens_s0": 7388.75,
"router/selected_tokens_s1": 4263.125,
"step": 4380,
"tokens_trained": 14.348612232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2450890007800866,
"grad_norm": 0.17079408466815948,
"loss": 1.1275,
"loss_ce": 1.1308954954147339,
"loss_region": 0.059982020407915115,
"loss_total": 1.1908775568008423,
"lr": 0.0010665045788719248,
"router/selected_tokens_s0": 7438.875,
"router/selected_tokens_s1": 4336.625,
"step": 4390,
"tokens_trained": 14.381377672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.247925679029856,
"grad_norm": 0.1912943720817566,
"loss": 1.1282,
"loss_ce": 1.0140893459320068,
"loss_region": 0.05996926501393318,
"loss_total": 1.0740586519241333,
"lr": 0.0010660976868880738,
"router/selected_tokens_s0": 7448.375,
"router/selected_tokens_s1": 4391.875,
"step": 4400,
"tokens_trained": 14.414143112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2507623572796256,
"grad_norm": 0.5349684953689575,
"loss": 1.1317,
"loss_ce": 1.0418589115142822,
"loss_region": 0.059975508600473404,
"loss_total": 1.1018344163894653,
"lr": 0.0010656907949042227,
"router/selected_tokens_s0": 7420.25,
"router/selected_tokens_s1": 4350.875,
"step": 4410,
"tokens_trained": 14.446908552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2535990355293951,
"grad_norm": 0.10011377930641174,
"loss": 1.1295,
"loss_ce": 1.14780592918396,
"loss_region": 0.0599743016064167,
"loss_total": 1.2077802419662476,
"lr": 0.0010652839029203717,
"router/selected_tokens_s0": 7343.375,
"router/selected_tokens_s1": 4315.875,
"step": 4420,
"tokens_trained": 14.479673992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2564357137791646,
"grad_norm": 0.13616910576820374,
"loss": 1.127,
"loss_ce": 1.0690678358078003,
"loss_region": 0.06000702828168869,
"loss_total": 1.1290748119354248,
"lr": 0.0010648770109365207,
"router/selected_tokens_s0": 7325.125,
"router/selected_tokens_s1": 4238.75,
"step": 4430,
"tokens_trained": 14.512439432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2592723920289342,
"grad_norm": 0.21678487956523895,
"loss": 1.1266,
"loss_ce": 1.1105207204818726,
"loss_region": 0.06007102504372597,
"loss_total": 1.1705917119979858,
"lr": 0.0010644701189526696,
"router/selected_tokens_s0": 7417.75,
"router/selected_tokens_s1": 4169.25,
"step": 4440,
"tokens_trained": 14.545204872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2621090702787037,
"grad_norm": 0.5876789093017578,
"loss": 1.127,
"loss_ce": 0.9410568475723267,
"loss_region": 0.06004181131720543,
"loss_total": 1.0010986328125,
"lr": 0.0010640632269688186,
"router/selected_tokens_s0": 7412.75,
"router/selected_tokens_s1": 4238.875,
"step": 4450,
"tokens_trained": 14.577970312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2649457485284732,
"grad_norm": 0.3269062936306,
"loss": 1.1279,
"loss_ce": 1.0947961807250977,
"loss_region": 0.0600116066634655,
"loss_total": 1.1548078060150146,
"lr": 0.0010636563349849678,
"router/selected_tokens_s0": 7457.625,
"router/selected_tokens_s1": 4283.0,
"step": 4460,
"tokens_trained": 14.610735752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2677824267782427,
"grad_norm": 0.1908155232667923,
"loss": 1.1287,
"loss_ce": 1.098473072052002,
"loss_region": 0.060026198625564575,
"loss_total": 1.1584992408752441,
"lr": 0.0010632494430011167,
"router/selected_tokens_s0": 7424.75,
"router/selected_tokens_s1": 4236.25,
"step": 4470,
"tokens_trained": 14.643501192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2706191050280122,
"grad_norm": 0.10397963970899582,
"loss": 1.1321,
"loss_ce": 1.036777138710022,
"loss_region": 0.060002975165843964,
"loss_total": 1.0967800617218018,
"lr": 0.0010628425510172657,
"router/selected_tokens_s0": 7400.5,
"router/selected_tokens_s1": 4276.0,
"step": 4480,
"tokens_trained": 14.676266632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2734557832777817,
"grad_norm": 0.21262697875499725,
"loss": 1.1309,
"loss_ce": 0.9618175029754639,
"loss_region": 0.0600084513425827,
"loss_total": 1.021825909614563,
"lr": 0.0010624356590334145,
"router/selected_tokens_s0": 7394.5,
"router/selected_tokens_s1": 4267.75,
"step": 4490,
"tokens_trained": 14.709032072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2762924615275513,
"grad_norm": 0.2513585686683655,
"loss": 1.117,
"loss_ce": 1.0686031579971313,
"loss_region": 0.060012537986040115,
"loss_total": 1.1286157369613647,
"lr": 0.0010620287670495634,
"router/selected_tokens_s0": 7436.625,
"router/selected_tokens_s1": 4269.125,
"step": 4500,
"tokens_trained": 14.741797512
},
{
"epoch": 1.2762924615275513,
"eval_ppl": 2.917957803788485,
"eval_runtime": 1.0395,
"step": 4500,
"tokens_trained": 14.741797512
},
{
"epoch": 1.2762924615275513,
"eval_F": 0.33461598562387684,
"eval_F_cds": 0.33259245680766236,
"eval_F_dig": 0.3207281818892101,
"eval_F_exon": 0.33861701681553236,
"eval_F_intron": 0.33541328126143716,
"eval_F_nig": 0.33607782526840685,
"eval_F_promoter": 0.3298154265345352,
"eval_F_utr": 0.33543765621376487,
"eval_G": 0.31760316662922883,
"eval_G_cds": 0.313791894490972,
"eval_G_dig": 0.29314698658098287,
"eval_G_exon": 0.32055345667169877,
"eval_G_intron": 0.3188114075381784,
"eval_G_nig": 0.31865636741806275,
"eval_G_promoter": 0.3128496054748008,
"eval_G_utr": 0.31821468602643715,
"eval_avg_bp_per_token": 2.988500379429105,
"eval_bp_per_token/cds": 3.006682741991044,
"eval_bp_per_token/dig": 3.117904993909866,
"eval_bp_per_token/exon": 2.9531888544891642,
"eval_bp_per_token/intron": 2.981396551261046,
"eval_bp_per_token/nig": 2.9755012821847293,
"eval_bp_per_token/promoter": 3.0319988682982033,
"eval_bp_per_token/utr": 2.981179904747273,
"eval_ppl_cds": 3.7123510478966413,
"eval_ppl_dig": 1.1330739061422115,
"eval_ppl_exon": 3.337367507183785,
"eval_ppl_intron": 2.9854555129266296,
"eval_ppl_nig": 2.7241976865988637,
"eval_ppl_promoter": 3.2884822422677225,
"eval_ppl_utr": 3.2793148726546266,
"step": 4500,
"tokens_trained": 14.741797512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2791291397773208,
"grad_norm": 0.24554239213466644,
"loss": 1.1286,
"loss_ce": 1.1632256507873535,
"loss_region": 0.05998421087861061,
"loss_total": 1.2232098579406738,
"lr": 0.0010616218750657124,
"router/selected_tokens_s0": 7387.5,
"router/selected_tokens_s1": 4308.375,
"step": 4510,
"tokens_trained": 14.774562152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2819658180270903,
"grad_norm": 0.07869572937488556,
"loss": 1.1184,
"loss_ce": 1.1050900220870972,
"loss_region": 0.059989046305418015,
"loss_total": 1.165079116821289,
"lr": 0.0010612149830818616,
"router/selected_tokens_s0": 7434.875,
"router/selected_tokens_s1": 4323.0,
"step": 4520,
"tokens_trained": 14.807327592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2848024962768598,
"grad_norm": 0.17654132843017578,
"loss": 1.1229,
"loss_ce": 1.0468547344207764,
"loss_region": 0.05998006463050842,
"loss_total": 1.1068347692489624,
"lr": 0.0010608080910980105,
"router/selected_tokens_s0": 7451.375,
"router/selected_tokens_s1": 4358.75,
"step": 4530,
"tokens_trained": 14.840092232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2876391745266293,
"grad_norm": 0.5160551071166992,
"loss": 1.1315,
"loss_ce": 1.0896406173706055,
"loss_region": 0.060032665729522705,
"loss_total": 1.1496732234954834,
"lr": 0.0010604011991141595,
"router/selected_tokens_s0": 7418.5,
"router/selected_tokens_s1": 4231.5,
"step": 4540,
"tokens_trained": 14.872854344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2904758527763989,
"grad_norm": 0.27445802092552185,
"loss": 1.1303,
"loss_ce": 1.1501026153564453,
"loss_region": 0.059976108372211456,
"loss_total": 1.2100787162780762,
"lr": 0.0010599943071303085,
"router/selected_tokens_s0": 7381.0,
"router/selected_tokens_s1": 4362.0,
"step": 4550,
"tokens_trained": 14.905619784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2933125310261684,
"grad_norm": 0.10401671379804611,
"loss": 1.1242,
"loss_ce": 1.12882399559021,
"loss_region": 0.059980615973472595,
"loss_total": 1.1888046264648438,
"lr": 0.0010595874151464574,
"router/selected_tokens_s0": 7415.25,
"router/selected_tokens_s1": 4340.5,
"step": 4560,
"tokens_trained": 14.938385224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.296149209275938,
"grad_norm": 0.22361941635608673,
"loss": 1.1184,
"loss_ce": 1.0420340299606323,
"loss_region": 0.05997908487915993,
"loss_total": 1.102013111114502,
"lr": 0.0010591805231626064,
"router/selected_tokens_s0": 7414.625,
"router/selected_tokens_s1": 4339.875,
"step": 4570,
"tokens_trained": 14.971149864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.2989858875257074,
"grad_norm": 0.13880027830600739,
"loss": 1.1182,
"loss_ce": 1.1432592868804932,
"loss_region": 0.05998491123318672,
"loss_total": 1.2032442092895508,
"lr": 0.0010587736311787554,
"router/selected_tokens_s0": 7413.375,
"router/selected_tokens_s1": 4324.25,
"step": 4580,
"tokens_trained": 15.003915304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.301822565775477,
"grad_norm": 0.34181830286979675,
"loss": 1.1229,
"loss_ce": 1.0234683752059937,
"loss_region": 0.05998027324676514,
"loss_total": 1.0834486484527588,
"lr": 0.0010583667391949043,
"router/selected_tokens_s0": 7370.75,
"router/selected_tokens_s1": 4327.625,
"step": 4590,
"tokens_trained": 15.036680744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3046592440252465,
"grad_norm": 0.44472306966781616,
"loss": 1.1253,
"loss_ce": 1.101945400238037,
"loss_region": 0.05997232720255852,
"loss_total": 1.1619176864624023,
"lr": 0.0010579598472110533,
"router/selected_tokens_s0": 7432.125,
"router/selected_tokens_s1": 4372.75,
"step": 4600,
"tokens_trained": 15.069442824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.307495922275016,
"grad_norm": 0.16355791687965393,
"loss": 1.1188,
"loss_ce": 1.1986117362976074,
"loss_region": 0.06000068411231041,
"loss_total": 1.2586123943328857,
"lr": 0.0010575529552272023,
"router/selected_tokens_s0": 7469.875,
"router/selected_tokens_s1": 4313.25,
"step": 4610,
"tokens_trained": 15.102208264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3103326005247855,
"grad_norm": 0.22206738591194153,
"loss": 1.1225,
"loss_ce": 1.048006296157837,
"loss_region": 0.05998196825385094,
"loss_total": 1.1079882383346558,
"lr": 0.0010571460632433512,
"router/selected_tokens_s0": 7401.875,
"router/selected_tokens_s1": 4326.5,
"step": 4620,
"tokens_trained": 15.134972904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.313169278774555,
"grad_norm": 0.4577283263206482,
"loss": 1.1217,
"loss_ce": 0.9944411516189575,
"loss_region": 0.06000739336013794,
"loss_total": 1.0544486045837402,
"lr": 0.0010567391712595002,
"router/selected_tokens_s0": 7405.25,
"router/selected_tokens_s1": 4267.875,
"step": 4630,
"tokens_trained": 15.167735632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3160059570243245,
"grad_norm": 0.11892636120319366,
"loss": 1.1252,
"loss_ce": 1.0683937072753906,
"loss_region": 0.059995830059051514,
"loss_total": 1.128389596939087,
"lr": 0.0010563322792756492,
"router/selected_tokens_s0": 7362.75,
"router/selected_tokens_s1": 4270.875,
"step": 4640,
"tokens_trained": 15.200501072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.318842635274094,
"grad_norm": 0.22857649624347687,
"loss": 1.1228,
"loss_ce": 1.0523583889007568,
"loss_region": 0.05998574197292328,
"loss_total": 1.1123441457748413,
"lr": 0.0010559253872917981,
"router/selected_tokens_s0": 7456.75,
"router/selected_tokens_s1": 4359.25,
"step": 4650,
"tokens_trained": 15.233266512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3216793135238636,
"grad_norm": 0.23737908899784088,
"loss": 1.1186,
"loss_ce": 1.13929283618927,
"loss_region": 0.0599866583943367,
"loss_total": 1.199279546737671,
"lr": 0.001055518495307947,
"router/selected_tokens_s0": 7427.75,
"router/selected_tokens_s1": 4333.625,
"step": 4660,
"tokens_trained": 15.266028416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.324515991773633,
"grad_norm": 0.37915486097335815,
"loss": 1.1254,
"loss_ce": 1.09169602394104,
"loss_region": 0.06004900857806206,
"loss_total": 1.151745080947876,
"lr": 0.001055111603324096,
"router/selected_tokens_s0": 7402.75,
"router/selected_tokens_s1": 4227.625,
"step": 4670,
"tokens_trained": 15.298793832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3273526700234026,
"grad_norm": 0.3147301971912384,
"loss": 1.1198,
"loss_ce": 1.1839306354522705,
"loss_region": 0.060013432055711746,
"loss_total": 1.2439440488815308,
"lr": 0.001054704711340245,
"router/selected_tokens_s0": 7460.5,
"router/selected_tokens_s1": 4279.875,
"step": 4680,
"tokens_trained": 15.331559256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3301893482731721,
"grad_norm": 0.20523282885551453,
"loss": 1.1242,
"loss_ce": 1.0608105659484863,
"loss_region": 0.0599835105240345,
"loss_total": 1.1207940578460693,
"lr": 0.001054297819356394,
"router/selected_tokens_s0": 7370.25,
"router/selected_tokens_s1": 4307.375,
"step": 4690,
"tokens_trained": 15.364323896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3330260265229417,
"grad_norm": 0.4551692008972168,
"loss": 1.122,
"loss_ce": 1.038015604019165,
"loss_region": 0.0599852129817009,
"loss_total": 1.0980007648468018,
"lr": 0.0010538909273725432,
"router/selected_tokens_s0": 7438.0,
"router/selected_tokens_s1": 4342.25,
"step": 4700,
"tokens_trained": 15.397089336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3358627047727112,
"grad_norm": 0.17796026170253754,
"loss": 1.116,
"loss_ce": 1.0065257549285889,
"loss_region": 0.05998144671320915,
"loss_total": 1.0665072202682495,
"lr": 0.0010534840353886921,
"router/selected_tokens_s0": 7439.875,
"router/selected_tokens_s1": 4383.0,
"step": 4710,
"tokens_trained": 15.42985476
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3386993830224807,
"grad_norm": 0.22296547889709473,
"loss": 1.123,
"loss_ce": 1.0840928554534912,
"loss_region": 0.060023073107004166,
"loss_total": 1.144115924835205,
"lr": 0.001053077143404841,
"router/selected_tokens_s0": 7459.125,
"router/selected_tokens_s1": 4259.125,
"step": 4720,
"tokens_trained": 15.4626202
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3415360612722502,
"grad_norm": 0.13965415954589844,
"loss": 1.1186,
"loss_ce": 0.9718788862228394,
"loss_region": 0.06004929542541504,
"loss_total": 1.0319281816482544,
"lr": 0.0010526702514209898,
"router/selected_tokens_s0": 7428.875,
"router/selected_tokens_s1": 4207.0,
"step": 4730,
"tokens_trained": 15.49538484
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3443727395220197,
"grad_norm": 0.06705205887556076,
"loss": 1.1143,
"loss_ce": 1.0242143869400024,
"loss_region": 0.06001764535903931,
"loss_total": 1.0842320919036865,
"lr": 0.0010522633594371388,
"router/selected_tokens_s0": 7395.625,
"router/selected_tokens_s1": 4246.125,
"step": 4740,
"tokens_trained": 15.52815028
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3472094177717893,
"grad_norm": 0.22649919986724854,
"loss": 1.1177,
"loss_ce": 1.1338170766830444,
"loss_region": 0.06001260131597519,
"loss_total": 1.1938296556472778,
"lr": 0.0010518564674532878,
"router/selected_tokens_s0": 7391.125,
"router/selected_tokens_s1": 4239.0,
"step": 4750,
"tokens_trained": 15.56091572
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3500460960215588,
"grad_norm": 0.31113359332084656,
"loss": 1.123,
"loss_ce": 0.9169719815254211,
"loss_region": 0.06001540645956993,
"loss_total": 0.976987361907959,
"lr": 0.0010514495754694367,
"router/selected_tokens_s0": 7328.375,
"router/selected_tokens_s1": 4216.875,
"step": 4760,
"tokens_trained": 15.593678736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3528827742713283,
"grad_norm": 0.1546049863100052,
"loss": 1.1181,
"loss_ce": 1.0581512451171875,
"loss_region": 0.05999620631337166,
"loss_total": 1.1181474924087524,
"lr": 0.001051042683485586,
"router/selected_tokens_s0": 7396.625,
"router/selected_tokens_s1": 4291.375,
"step": 4770,
"tokens_trained": 15.626444176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3557194525210978,
"grad_norm": 0.2984902858734131,
"loss": 1.1199,
"loss_ce": 1.0760042667388916,
"loss_region": 0.060034509748220444,
"loss_total": 1.1360387802124023,
"lr": 0.0010506357915017349,
"router/selected_tokens_s0": 7484.25,
"router/selected_tokens_s1": 4248.375,
"step": 4780,
"tokens_trained": 15.659209616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3585561307708673,
"grad_norm": 0.15915615856647491,
"loss": 1.1209,
"loss_ce": 1.1233313083648682,
"loss_region": 0.060023460537195206,
"loss_total": 1.1833547353744507,
"lr": 0.0010502288995178838,
"router/selected_tokens_s0": 7426.25,
"router/selected_tokens_s1": 4239.625,
"step": 4790,
"tokens_trained": 15.691975056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3613928090206369,
"grad_norm": 0.4409286379814148,
"loss": 1.1238,
"loss_ce": 1.1545687913894653,
"loss_region": 0.06003446504473686,
"loss_total": 1.214603304862976,
"lr": 0.0010498220075340328,
"router/selected_tokens_s0": 7428.375,
"router/selected_tokens_s1": 4222.25,
"step": 4800,
"tokens_trained": 15.724740496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3642294872704064,
"grad_norm": 0.14395779371261597,
"loss": 1.1167,
"loss_ce": 1.1078091859817505,
"loss_region": 0.06001976132392883,
"loss_total": 1.167828917503357,
"lr": 0.0010494151155501818,
"router/selected_tokens_s0": 7381.5,
"router/selected_tokens_s1": 4220.125,
"step": 4810,
"tokens_trained": 15.757505936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.367066165520176,
"grad_norm": 0.07509951293468475,
"loss": 1.1117,
"loss_ce": 1.0311144590377808,
"loss_region": 0.05999474227428436,
"loss_total": 1.0911091566085815,
"lr": 0.0010490082235663307,
"router/selected_tokens_s0": 7421.625,
"router/selected_tokens_s1": 4303.625,
"step": 4820,
"tokens_trained": 15.790271376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3699028437699454,
"grad_norm": 0.33459046483039856,
"loss": 1.123,
"loss_ce": 1.0805909633636475,
"loss_region": 0.059987638145685196,
"loss_total": 1.1405786275863647,
"lr": 0.0010486013315824797,
"router/selected_tokens_s0": 7454.625,
"router/selected_tokens_s1": 4340.875,
"step": 4830,
"tokens_trained": 15.823036016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.372739522019715,
"grad_norm": 0.3175514340400696,
"loss": 1.116,
"loss_ce": 0.9817476868629456,
"loss_region": 0.06001373007893562,
"loss_total": 1.0417613983154297,
"lr": 0.0010481944395986287,
"router/selected_tokens_s0": 7536.375,
"router/selected_tokens_s1": 4333.25,
"step": 4840,
"tokens_trained": 15.855801456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3755762002694845,
"grad_norm": 0.18610598146915436,
"loss": 1.1122,
"loss_ce": 0.9771859049797058,
"loss_region": 0.059994395822286606,
"loss_total": 1.0371803045272827,
"lr": 0.0010477875476147776,
"router/selected_tokens_s0": 7416.5,
"router/selected_tokens_s1": 4305.75,
"step": 4850,
"tokens_trained": 15.888566096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.378412878519254,
"grad_norm": 0.2766318619251251,
"loss": 1.1136,
"loss_ce": 1.0846664905548096,
"loss_region": 0.059982847422361374,
"loss_total": 1.1446493864059448,
"lr": 0.0010473806556309266,
"router/selected_tokens_s0": 7447.5,
"router/selected_tokens_s1": 4378.25,
"step": 4860,
"tokens_trained": 15.921331536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3812495567690235,
"grad_norm": 0.236831933259964,
"loss": 1.1133,
"loss_ce": 1.09515380859375,
"loss_region": 0.06001046299934387,
"loss_total": 1.1551642417907715,
"lr": 0.0010469737636470756,
"router/selected_tokens_s0": 7429.125,
"router/selected_tokens_s1": 4270.375,
"step": 4870,
"tokens_trained": 15.954096176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.384086235018793,
"grad_norm": 0.38822853565216064,
"loss": 1.1163,
"loss_ce": 1.102951169013977,
"loss_region": 0.06000502035021782,
"loss_total": 1.1629562377929688,
"lr": 0.0010465668716632245,
"router/selected_tokens_s0": 7433.625,
"router/selected_tokens_s1": 4280.0,
"step": 4880,
"tokens_trained": 15.9868564
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3869229132685625,
"grad_norm": 0.14238017797470093,
"loss": 1.1136,
"loss_ce": 1.0466766357421875,
"loss_region": 0.06005201116204262,
"loss_total": 1.1067286729812622,
"lr": 0.0010461599796793735,
"router/selected_tokens_s0": 7479.375,
"router/selected_tokens_s1": 4220.5,
"step": 4890,
"tokens_trained": 16.019621784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.389759591518332,
"grad_norm": 0.24368639290332794,
"loss": 1.1171,
"loss_ce": 1.1112743616104126,
"loss_region": 0.059988003224134445,
"loss_total": 1.1712623834609985,
"lr": 0.0010457530876955225,
"router/selected_tokens_s0": 7440.125,
"router/selected_tokens_s1": 4345.0,
"step": 4900,
"tokens_trained": 16.052387224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3925962697681016,
"grad_norm": 0.16130021214485168,
"loss": 1.113,
"loss_ce": 0.9168754816055298,
"loss_region": 0.05999680235981941,
"loss_total": 0.9768722653388977,
"lr": 0.0010453461957116714,
"router/selected_tokens_s0": 7493.375,
"router/selected_tokens_s1": 4340.75,
"step": 4910,
"tokens_trained": 16.085152664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.395432948017871,
"grad_norm": 0.4398319125175476,
"loss": 1.1189,
"loss_ce": 0.9984895586967468,
"loss_region": 0.05999951437115669,
"loss_total": 1.0584890842437744,
"lr": 0.0010449393037278204,
"router/selected_tokens_s0": 7526.375,
"router/selected_tokens_s1": 4367.125,
"step": 4920,
"tokens_trained": 16.117918104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.3982696262676406,
"grad_norm": 0.20883530378341675,
"loss": 1.1163,
"loss_ce": 0.99969083070755,
"loss_region": 0.0599936805665493,
"loss_total": 1.0596845149993896,
"lr": 0.0010445324117439694,
"router/selected_tokens_s0": 7413.75,
"router/selected_tokens_s1": 4302.0,
"step": 4930,
"tokens_trained": 16.150683544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4011063045174101,
"grad_norm": 0.6086301207542419,
"loss": 1.1135,
"loss_ce": 1.027841567993164,
"loss_region": 0.05998702719807625,
"loss_total": 1.0878286361694336,
"lr": 0.0010441255197601183,
"router/selected_tokens_s0": 7387.25,
"router/selected_tokens_s1": 4316.875,
"step": 4940,
"tokens_trained": 16.183448184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4039429827671797,
"grad_norm": 0.047434039413928986,
"loss": 1.1168,
"loss_ce": 1.03725266456604,
"loss_region": 0.06001438945531845,
"loss_total": 1.0972670316696167,
"lr": 0.0010437186277762675,
"router/selected_tokens_s0": 7409.0,
"router/selected_tokens_s1": 4250.125,
"step": 4950,
"tokens_trained": 16.216210576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4067796610169492,
"grad_norm": 0.12742455303668976,
"loss": 1.1131,
"loss_ce": 1.1178278923034668,
"loss_region": 0.060008853673934937,
"loss_total": 1.1778367757797241,
"lr": 0.0010433117357924165,
"router/selected_tokens_s0": 7387.75,
"router/selected_tokens_s1": 4253.0,
"step": 4960,
"tokens_trained": 16.248975216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4096163392667187,
"grad_norm": 0.46089595556259155,
"loss": 1.1148,
"loss_ce": 1.0517332553863525,
"loss_region": 0.0600130595266819,
"loss_total": 1.1117463111877441,
"lr": 0.0010429048438085654,
"router/selected_tokens_s0": 7444.375,
"router/selected_tokens_s1": 4266.125,
"step": 4970,
"tokens_trained": 16.281739056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4124530175164882,
"grad_norm": 0.16032390296459198,
"loss": 1.1141,
"loss_ce": 1.0725197792053223,
"loss_region": 0.060011573135852814,
"loss_total": 1.1325314044952393,
"lr": 0.0010424979518247142,
"router/selected_tokens_s0": 7395.875,
"router/selected_tokens_s1": 4244.375,
"step": 4980,
"tokens_trained": 16.314504496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4152896957662577,
"grad_norm": 0.2698926627635956,
"loss": 1.114,
"loss_ce": 0.9691027998924255,
"loss_region": 0.06001393124461174,
"loss_total": 1.0291167497634888,
"lr": 0.0010420910598408631,
"router/selected_tokens_s0": 7416.875,
"router/selected_tokens_s1": 4247.125,
"step": 4990,
"tokens_trained": 16.347269936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4181263740160273,
"grad_norm": 0.29608723521232605,
"loss": 1.1139,
"loss_ce": 1.0969948768615723,
"loss_region": 0.06001259386539459,
"loss_total": 1.1570074558258057,
"lr": 0.0010416841678570121,
"router/selected_tokens_s0": 7368.25,
"router/selected_tokens_s1": 4259.5,
"step": 5000,
"tokens_trained": 16.380034576
},
{
"epoch": 1.4181263740160273,
"eval_ppl": 2.8878776092072367,
"eval_runtime": 1.0117,
"step": 5000,
"tokens_trained": 16.380034576
},
{
"epoch": 1.4181263740160273,
"eval_F": 0.3334707138578535,
"eval_F_cds": 0.3258558269556849,
"eval_F_dig": 0.3043987811547777,
"eval_F_exon": 0.3379041388853944,
"eval_F_intron": 0.33496283233277363,
"eval_F_nig": 0.33443367424820636,
"eval_F_promoter": 0.32823376817274136,
"eval_F_utr": 0.33587569893581387,
"eval_G": 0.32152487499023363,
"eval_G_cds": 0.31537235847921724,
"eval_G_dig": 0.28879102493358855,
"eval_G_exon": 0.32521681186312745,
"eval_G_intron": 0.3229452310232905,
"eval_G_nig": 0.3225945309816726,
"eval_G_promoter": 0.3164494893582153,
"eval_G_utr": 0.3238339528202221,
"eval_avg_bp_per_token": 2.998764084651415,
"eval_bp_per_token/cds": 3.0688418535967936,
"eval_bp_per_token/dig": 3.2851642710472277,
"eval_bp_per_token/exon": 2.9594192107222637,
"eval_bp_per_token/intron": 2.985405852451521,
"eval_bp_per_token/nig": 2.9901295144633995,
"eval_bp_per_token/promoter": 3.04660914557007,
"eval_bp_per_token/utr": 2.9772919064058305,
"eval_ppl_cds": 3.709566657145957,
"eval_ppl_dig": 1.123842032296959,
"eval_ppl_exon": 3.3107114360355596,
"eval_ppl_intron": 2.957223274787988,
"eval_ppl_nig": 2.6887659433495315,
"eval_ppl_promoter": 3.2651215439300434,
"eval_ppl_utr": 3.2607755780543872,
"step": 5000,
"tokens_trained": 16.380034576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4209630522657968,
"grad_norm": 0.13509275019168854,
"loss": 1.1122,
"loss_ce": 1.0823110342025757,
"loss_region": 0.06001218780875206,
"loss_total": 1.1423232555389404,
"lr": 0.001041277275873161,
"router/selected_tokens_s0": 7402.875,
"router/selected_tokens_s1": 4253.0,
"step": 5010,
"tokens_trained": 16.412800016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4237997305155663,
"grad_norm": 0.46688932180404663,
"loss": 1.1176,
"loss_ce": 1.067285418510437,
"loss_region": 0.0600067637860775,
"loss_total": 1.1272921562194824,
"lr": 0.0010408703838893103,
"router/selected_tokens_s0": 7453.125,
"router/selected_tokens_s1": 4284.0,
"step": 5020,
"tokens_trained": 16.445565456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4266364087653358,
"grad_norm": 0.27795660495758057,
"loss": 1.1091,
"loss_ce": 1.0628243684768677,
"loss_region": 0.059996675699949265,
"loss_total": 1.1228210926055908,
"lr": 0.0010404634919054592,
"router/selected_tokens_s0": 7427.25,
"router/selected_tokens_s1": 4300.875,
"step": 5030,
"tokens_trained": 16.478329936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4294730870151053,
"grad_norm": 0.14971427619457245,
"loss": 1.1043,
"loss_ce": 1.1450423002243042,
"loss_region": 0.059983156621456146,
"loss_total": 1.2050254344940186,
"lr": 0.0010400565999216082,
"router/selected_tokens_s0": 7437.25,
"router/selected_tokens_s1": 4375.0,
"step": 5040,
"tokens_trained": 16.511090344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4323097652648749,
"grad_norm": 0.15365780889987946,
"loss": 1.1052,
"loss_ce": 1.002153754234314,
"loss_region": 0.059985172003507614,
"loss_total": 1.0621389150619507,
"lr": 0.0010396497079377572,
"router/selected_tokens_s0": 7341.625,
"router/selected_tokens_s1": 4392.375,
"step": 5050,
"tokens_trained": 16.543855784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4351464435146444,
"grad_norm": 0.30252763628959656,
"loss": 1.1175,
"loss_ce": 1.1226723194122314,
"loss_region": 0.059989143162965775,
"loss_total": 1.1826614141464233,
"lr": 0.0010392428159539061,
"router/selected_tokens_s0": 7409.625,
"router/selected_tokens_s1": 4329.875,
"step": 5060,
"tokens_trained": 16.576621224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.437983121764414,
"grad_norm": 0.13629955053329468,
"loss": 1.1122,
"loss_ce": 0.9620881676673889,
"loss_region": 0.06000163033604622,
"loss_total": 1.0220898389816284,
"lr": 0.001038835923970055,
"router/selected_tokens_s0": 7431.25,
"router/selected_tokens_s1": 4287.375,
"step": 5070,
"tokens_trained": 16.609386664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4408198000141834,
"grad_norm": 0.35703352093696594,
"loss": 1.1165,
"loss_ce": 0.8642436861991882,
"loss_region": 0.06000054255127907,
"loss_total": 0.924244225025177,
"lr": 0.001038429031986204,
"router/selected_tokens_s0": 7412.125,
"router/selected_tokens_s1": 4284.0,
"step": 5080,
"tokens_trained": 16.642152104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.443656478263953,
"grad_norm": 0.0827016830444336,
"loss": 1.1121,
"loss_ce": 1.0974977016448975,
"loss_region": 0.060001373291015625,
"loss_total": 1.157499074935913,
"lr": 0.001038022140002353,
"router/selected_tokens_s0": 7450.625,
"router/selected_tokens_s1": 4308.0,
"step": 5090,
"tokens_trained": 16.674914848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4464931565137225,
"grad_norm": 0.1692710518836975,
"loss": 1.1067,
"loss_ce": 1.1373043060302734,
"loss_region": 0.06000300124287605,
"loss_total": 1.1973073482513428,
"lr": 0.001037615248018502,
"router/selected_tokens_s0": 7456.625,
"router/selected_tokens_s1": 4291.75,
"step": 5100,
"tokens_trained": 16.707680128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.449329834763492,
"grad_norm": 0.2739175856113434,
"loss": 1.1093,
"loss_ce": 1.1393697261810303,
"loss_region": 0.059991370886564255,
"loss_total": 1.1993610858917236,
"lr": 0.001037208356034651,
"router/selected_tokens_s0": 7455.125,
"router/selected_tokens_s1": 4355.375,
"step": 5110,
"tokens_trained": 16.740445568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4521665130132615,
"grad_norm": 0.30162233114242554,
"loss": 1.1123,
"loss_ce": 1.1314183473587036,
"loss_region": 0.059990085661411285,
"loss_total": 1.191408395767212,
"lr": 0.0010368014640508,
"router/selected_tokens_s0": 7427.5,
"router/selected_tokens_s1": 4322.125,
"step": 5120,
"tokens_trained": 16.773211008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.455003191263031,
"grad_norm": 0.0802861824631691,
"loss": 1.1163,
"loss_ce": 1.0108295679092407,
"loss_region": 0.06001696363091469,
"loss_total": 1.0708465576171875,
"lr": 0.0010363945720669489,
"router/selected_tokens_s0": 7423.125,
"router/selected_tokens_s1": 4250.75,
"step": 5130,
"tokens_trained": 16.805971784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4578398695128005,
"grad_norm": 0.1599212884902954,
"loss": 1.112,
"loss_ce": 1.0099071264266968,
"loss_region": 0.05999860167503357,
"loss_total": 1.0699057579040527,
"lr": 0.0010359876800830978,
"router/selected_tokens_s0": 7411.0,
"router/selected_tokens_s1": 4282.875,
"step": 5140,
"tokens_trained": 16.838737224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.46067654776257,
"grad_norm": 0.1863497495651245,
"loss": 1.1069,
"loss_ce": 1.0711653232574463,
"loss_region": 0.05999632179737091,
"loss_total": 1.1311616897583008,
"lr": 0.0010355807880992468,
"router/selected_tokens_s0": 7435.375,
"router/selected_tokens_s1": 4302.75,
"step": 5150,
"tokens_trained": 16.871502664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4635132260123396,
"grad_norm": 0.22350755333900452,
"loss": 1.1053,
"loss_ce": 1.1011829376220703,
"loss_region": 0.05999854579567909,
"loss_total": 1.1611814498901367,
"lr": 0.0010351738961153958,
"router/selected_tokens_s0": 7417.875,
"router/selected_tokens_s1": 4287.25,
"step": 5160,
"tokens_trained": 16.904268104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.466349904262109,
"grad_norm": 0.10094260424375534,
"loss": 1.1102,
"loss_ce": 1.0678144693374634,
"loss_region": 0.059994544833898544,
"loss_total": 1.1278090476989746,
"lr": 0.0010347670041315447,
"router/selected_tokens_s0": 7475.125,
"router/selected_tokens_s1": 4293.0,
"step": 5170,
"tokens_trained": 16.937030128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4691865825118786,
"grad_norm": 0.16106005012989044,
"loss": 1.1087,
"loss_ce": 1.0874272584915161,
"loss_region": 0.05999764800071716,
"loss_total": 1.1474249362945557,
"lr": 0.0010343601121476937,
"router/selected_tokens_s0": 7448.125,
"router/selected_tokens_s1": 4309.875,
"step": 5180,
"tokens_trained": 16.969795184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4720232607616481,
"grad_norm": 0.2280910164117813,
"loss": 1.1116,
"loss_ce": 1.0265172719955444,
"loss_region": 0.05999668687582016,
"loss_total": 1.0865139961242676,
"lr": 0.0010339532201638427,
"router/selected_tokens_s0": 7427.25,
"router/selected_tokens_s1": 4310.875,
"step": 5190,
"tokens_trained": 17.002560624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4748599390114177,
"grad_norm": 0.20116379857063293,
"loss": 1.1153,
"loss_ce": 1.101824164390564,
"loss_region": 0.05999062955379486,
"loss_total": 1.16181480884552,
"lr": 0.0010335463281799918,
"router/selected_tokens_s0": 7408.5,
"router/selected_tokens_s1": 4336.5,
"step": 5200,
"tokens_trained": 17.035326064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4776966172611872,
"grad_norm": 0.18408538401126862,
"loss": 1.1055,
"loss_ce": 0.9988734126091003,
"loss_region": 0.06001979857683182,
"loss_total": 1.0588932037353516,
"lr": 0.0010331394361961408,
"router/selected_tokens_s0": 7452.5,
"router/selected_tokens_s1": 4255.625,
"step": 5210,
"tokens_trained": 17.068091504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4805332955109567,
"grad_norm": 0.23415856063365936,
"loss": 1.1015,
"loss_ce": 1.020708680152893,
"loss_region": 0.06000715121626854,
"loss_total": 1.0807157754898071,
"lr": 0.0010327325442122898,
"router/selected_tokens_s0": 7493.25,
"router/selected_tokens_s1": 4307.375,
"step": 5220,
"tokens_trained": 17.100856944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4833699737607262,
"grad_norm": 0.06807141751050949,
"loss": 1.1108,
"loss_ce": 1.0629068613052368,
"loss_region": 0.0599919855594635,
"loss_total": 1.122898817062378,
"lr": 0.0010323256522284385,
"router/selected_tokens_s0": 7458.75,
"router/selected_tokens_s1": 4347.375,
"step": 5230,
"tokens_trained": 17.133622384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4862066520104957,
"grad_norm": 0.1424221247434616,
"loss": 1.1025,
"loss_ce": 1.0725303888320923,
"loss_region": 0.05999269708991051,
"loss_total": 1.1325230598449707,
"lr": 0.0010319187602445875,
"router/selected_tokens_s0": 7437.625,
"router/selected_tokens_s1": 4324.625,
"step": 5240,
"tokens_trained": 17.166385424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4890433302602653,
"grad_norm": 0.3532690703868866,
"loss": 1.1109,
"loss_ce": 0.8595598340034485,
"loss_region": 0.06000366061925888,
"loss_total": 0.9195634722709656,
"lr": 0.0010315118682607365,
"router/selected_tokens_s0": 7354.625,
"router/selected_tokens_s1": 4278.875,
"step": 5250,
"tokens_trained": 17.199150864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4918800085100348,
"grad_norm": 0.22460265457630157,
"loss": 1.1129,
"loss_ce": 1.0128638744354248,
"loss_region": 0.06000963971018791,
"loss_total": 1.0728734731674194,
"lr": 0.0010311049762768854,
"router/selected_tokens_s0": 7375.25,
"router/selected_tokens_s1": 4243.25,
"step": 5260,
"tokens_trained": 17.231916304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4947166867598043,
"grad_norm": 0.1373329609632492,
"loss": 1.1099,
"loss_ce": 1.0595307350158691,
"loss_region": 0.05999409779906273,
"loss_total": 1.1195248365402222,
"lr": 0.0010306980842930346,
"router/selected_tokens_s0": 7399.875,
"router/selected_tokens_s1": 4312.75,
"step": 5270,
"tokens_trained": 17.264676432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.4975533650095738,
"grad_norm": 0.21981820464134216,
"loss": 1.1031,
"loss_ce": 0.9644787311553955,
"loss_region": 0.06000012904405594,
"loss_total": 1.0244789123535156,
"lr": 0.0010302911923091836,
"router/selected_tokens_s0": 7390.625,
"router/selected_tokens_s1": 4275.375,
"step": 5280,
"tokens_trained": 17.297440272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5003900432593433,
"grad_norm": 0.2568603754043579,
"loss": 1.1132,
"loss_ce": 1.0996148586273193,
"loss_region": 0.05999647080898285,
"loss_total": 1.1596113443374634,
"lr": 0.0010298843003253325,
"router/selected_tokens_s0": 7425.0,
"router/selected_tokens_s1": 4308.75,
"step": 5290,
"tokens_trained": 17.330205712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5032267215091129,
"grad_norm": 0.15437553822994232,
"loss": 1.1087,
"loss_ce": 1.082763910293579,
"loss_region": 0.060007624328136444,
"loss_total": 1.1427714824676514,
"lr": 0.0010294774083414815,
"router/selected_tokens_s0": 7454.5,
"router/selected_tokens_s1": 4281.75,
"step": 5300,
"tokens_trained": 17.362971152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5060633997588824,
"grad_norm": 0.1503092348575592,
"loss": 1.1118,
"loss_ce": 1.1156936883926392,
"loss_region": 0.060016077011823654,
"loss_total": 1.1757097244262695,
"lr": 0.0010290705163576305,
"router/selected_tokens_s0": 7488.25,
"router/selected_tokens_s1": 4275.375,
"step": 5310,
"tokens_trained": 17.395736592
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.508900078008652,
"grad_norm": 0.2845729887485504,
"loss": 1.1114,
"loss_ce": 1.0718103647232056,
"loss_region": 0.06000002846121788,
"loss_total": 1.1318104267120361,
"lr": 0.0010286636243737794,
"router/selected_tokens_s0": 7451.375,
"router/selected_tokens_s1": 4305.5,
"step": 5320,
"tokens_trained": 17.428502032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5117367562584214,
"grad_norm": 0.2394387274980545,
"loss": 1.1064,
"loss_ce": 1.067128300666809,
"loss_region": 0.06001432612538338,
"loss_total": 1.1271426677703857,
"lr": 0.0010282567323899284,
"router/selected_tokens_s0": 7442.375,
"router/selected_tokens_s1": 4261.125,
"step": 5330,
"tokens_trained": 17.461262816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.514573434508191,
"grad_norm": 0.17551490664482117,
"loss": 1.1077,
"loss_ce": 0.9975200891494751,
"loss_region": 0.06000635772943497,
"loss_total": 1.0575264692306519,
"lr": 0.0010278498404060774,
"router/selected_tokens_s0": 7472.0,
"router/selected_tokens_s1": 4289.375,
"step": 5340,
"tokens_trained": 17.494028256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5174101127579604,
"grad_norm": 0.14462608098983765,
"loss": 1.1143,
"loss_ce": 1.0838935375213623,
"loss_region": 0.06000163033604622,
"loss_total": 1.143895149230957,
"lr": 0.0010274429484222263,
"router/selected_tokens_s0": 7453.5,
"router/selected_tokens_s1": 4294.125,
"step": 5350,
"tokens_trained": 17.526793696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.52024679100773,
"grad_norm": 0.11604762822389603,
"loss": 1.1096,
"loss_ce": 0.9876978993415833,
"loss_region": 0.05999482050538063,
"loss_total": 1.0476927757263184,
"lr": 0.0010270360564383753,
"router/selected_tokens_s0": 7393.625,
"router/selected_tokens_s1": 4336.25,
"step": 5360,
"tokens_trained": 17.559559136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5230834692574995,
"grad_norm": 0.19762036204338074,
"loss": 1.1052,
"loss_ce": 1.0647521018981934,
"loss_region": 0.05999292433261871,
"loss_total": 1.1247450113296509,
"lr": 0.0010266291644545243,
"router/selected_tokens_s0": 7445.5,
"router/selected_tokens_s1": 4347.625,
"step": 5370,
"tokens_trained": 17.59232456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.525920147507269,
"grad_norm": 0.12396788597106934,
"loss": 1.1071,
"loss_ce": 0.9899451732635498,
"loss_region": 0.0599982813000679,
"loss_total": 1.049943447113037,
"lr": 0.0010262222724706732,
"router/selected_tokens_s0": 7417.0,
"router/selected_tokens_s1": 4315.375,
"step": 5380,
"tokens_trained": 17.6250892
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5287568257570385,
"grad_norm": 0.26794371008872986,
"loss": 1.1092,
"loss_ce": 1.0269250869750977,
"loss_region": 0.059988874942064285,
"loss_total": 1.0869139432907104,
"lr": 0.0010258153804868222,
"router/selected_tokens_s0": 7418.625,
"router/selected_tokens_s1": 4356.25,
"step": 5390,
"tokens_trained": 17.65785464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.531593504006808,
"grad_norm": 0.13411357998847961,
"loss": 1.1132,
"loss_ce": 1.1071951389312744,
"loss_region": 0.05999772250652313,
"loss_total": 1.167192816734314,
"lr": 0.0010254084885029712,
"router/selected_tokens_s0": 7403.5,
"router/selected_tokens_s1": 4374.0,
"step": 5400,
"tokens_trained": 17.69062008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5344301822565776,
"grad_norm": 0.10997501015663147,
"loss": 1.1052,
"loss_ce": 1.0851551294326782,
"loss_region": 0.05999771133065224,
"loss_total": 1.1451528072357178,
"lr": 0.0010250015965191201,
"router/selected_tokens_s0": 7394.0,
"router/selected_tokens_s1": 4301.125,
"step": 5410,
"tokens_trained": 17.72338552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.537266860506347,
"grad_norm": 0.1932307481765747,
"loss": 1.1071,
"loss_ce": 1.1663951873779297,
"loss_region": 0.06001700833439827,
"loss_total": 1.2264121770858765,
"lr": 0.001024594704535269,
"router/selected_tokens_s0": 7470.125,
"router/selected_tokens_s1": 4251.375,
"step": 5420,
"tokens_trained": 17.75615016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5401035387561166,
"grad_norm": 0.18134096264839172,
"loss": 1.1095,
"loss_ce": 1.0441800355911255,
"loss_region": 0.060025617480278015,
"loss_total": 1.10420560836792,
"lr": 0.001024187812551418,
"router/selected_tokens_s0": 7487.75,
"router/selected_tokens_s1": 4252.375,
"step": 5430,
"tokens_trained": 17.78891464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5429402170058861,
"grad_norm": 0.11615798622369766,
"loss": 1.1043,
"loss_ce": 1.0413671731948853,
"loss_region": 0.06000577658414841,
"loss_total": 1.1013729572296143,
"lr": 0.001023780920567567,
"router/selected_tokens_s0": 7445.75,
"router/selected_tokens_s1": 4278.125,
"step": 5440,
"tokens_trained": 17.821677712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5457768952556556,
"grad_norm": 0.1413813829421997,
"loss": 1.1027,
"loss_ce": 1.124322772026062,
"loss_region": 0.05999701842665672,
"loss_total": 1.1843197345733643,
"lr": 0.0010233740285837162,
"router/selected_tokens_s0": 7456.5,
"router/selected_tokens_s1": 4312.0,
"step": 5450,
"tokens_trained": 17.854443152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5486135735054252,
"grad_norm": 0.2357422411441803,
"loss": 1.1088,
"loss_ce": 1.029032826423645,
"loss_region": 0.06000213697552681,
"loss_total": 1.089034914970398,
"lr": 0.0010229671365998652,
"router/selected_tokens_s0": 7351.875,
"router/selected_tokens_s1": 4269.75,
"step": 5460,
"tokens_trained": 17.88720588
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5514502517551947,
"grad_norm": 0.3043672740459442,
"loss": 1.1069,
"loss_ce": 1.0109539031982422,
"loss_region": 0.06000383198261261,
"loss_total": 1.0709577798843384,
"lr": 0.0010225602446160141,
"router/selected_tokens_s0": 7402.125,
"router/selected_tokens_s1": 4259.875,
"step": 5470,
"tokens_trained": 17.91997132
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5542869300049642,
"grad_norm": 0.21447394788265228,
"loss": 1.0999,
"loss_ce": 0.898987352848053,
"loss_region": 0.059998832643032074,
"loss_total": 0.9589861631393433,
"lr": 0.0010221533526321629,
"router/selected_tokens_s0": 7391.75,
"router/selected_tokens_s1": 4311.25,
"step": 5480,
"tokens_trained": 17.952736472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5571236082547337,
"grad_norm": 0.12158813327550888,
"loss": 1.1054,
"loss_ce": 1.0969467163085938,
"loss_region": 0.06000404804944992,
"loss_total": 1.1569507122039795,
"lr": 0.0010217464606483118,
"router/selected_tokens_s0": 7385.25,
"router/selected_tokens_s1": 4268.75,
"step": 5490,
"tokens_trained": 17.985498936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5599602865045032,
"grad_norm": 0.16777564585208893,
"loss": 1.1088,
"loss_ce": 1.074271559715271,
"loss_region": 0.05999928340315819,
"loss_total": 1.1342707872390747,
"lr": 0.0010213395686644608,
"router/selected_tokens_s0": 7404.625,
"router/selected_tokens_s1": 4339.0,
"step": 5500,
"tokens_trained": 18.018264376
},
{
"epoch": 1.5599602865045032,
"eval_ppl": 2.8623211345020083,
"eval_runtime": 1.0594,
"step": 5500,
"tokens_trained": 18.018264376
},
{
"epoch": 1.5599602865045032,
"eval_F": 0.3352866109331458,
"eval_F_cds": 0.332042527840154,
"eval_F_dig": 0.3194780842253301,
"eval_F_exon": 0.3372331949511469,
"eval_F_intron": 0.33585922570081406,
"eval_F_nig": 0.3355467358672976,
"eval_F_promoter": 0.3334546404643264,
"eval_F_utr": 0.3378597747945064,
"eval_G": 0.3283424776227635,
"eval_G_cds": 0.3256197978724623,
"eval_G_dig": 0.2966016937358387,
"eval_G_exon": 0.33176564072524845,
"eval_G_intron": 0.3290947716744763,
"eval_G_nig": 0.32887621721238486,
"eval_G_promoter": 0.32587681763864007,
"eval_G_utr": 0.33184780954482207,
"eval_avg_bp_per_token": 2.9825229144011187,
"eval_bp_per_token/cds": 3.0116624111517494,
"eval_bp_per_token/dig": 3.1301051601858645,
"eval_bp_per_token/exon": 2.965307137527978,
"eval_bp_per_token/intron": 2.9774379367229518,
"eval_bp_per_token/nig": 2.980210781712033,
"eval_bp_per_token/promoter": 2.998908632992864,
"eval_bp_per_token/utr": 2.9598078096400244,
"eval_ppl_cds": 3.5822509806281193,
"eval_ppl_dig": 1.121855248822277,
"eval_ppl_exon": 3.2827148915254987,
"eval_ppl_intron": 2.9368199473955423,
"eval_ppl_nig": 2.662848735088766,
"eval_ppl_promoter": 3.249090164143398,
"eval_ppl_utr": 3.2504448948002427,
"step": 5500,
"tokens_trained": 18.018264376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5627969647542728,
"grad_norm": 0.23786824941635132,
"loss": 1.1033,
"loss_ce": 1.0256643295288086,
"loss_region": 0.059994738548994064,
"loss_total": 1.0856590270996094,
"lr": 0.0010209326766806098,
"router/selected_tokens_s0": 7439.875,
"router/selected_tokens_s1": 4329.375,
"step": 5510,
"tokens_trained": 18.051029816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5656336430040423,
"grad_norm": 0.06368014961481094,
"loss": 1.1021,
"loss_ce": 1.013634204864502,
"loss_region": 0.05999471992254257,
"loss_total": 1.0736289024353027,
"lr": 0.001020525784696759,
"router/selected_tokens_s0": 7432.125,
"router/selected_tokens_s1": 4334.125,
"step": 5520,
"tokens_trained": 18.083794456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5684703212538118,
"grad_norm": 0.20794622600078583,
"loss": 1.0995,
"loss_ce": 0.9896392226219177,
"loss_region": 0.06000121310353279,
"loss_total": 1.049640417098999,
"lr": 0.001020118892712908,
"router/selected_tokens_s0": 7468.0,
"router/selected_tokens_s1": 4308.75,
"step": 5530,
"tokens_trained": 18.116559896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5713069995035813,
"grad_norm": 0.10307029634714127,
"loss": 1.1022,
"loss_ce": 1.1249936819076538,
"loss_region": 0.059996627271175385,
"loss_total": 1.1849902868270874,
"lr": 0.0010197120007290569,
"router/selected_tokens_s0": 7442.5,
"router/selected_tokens_s1": 4306.125,
"step": 5540,
"tokens_trained": 18.149325336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5741436777533508,
"grad_norm": 0.10810263454914093,
"loss": 1.1039,
"loss_ce": 1.0132877826690674,
"loss_region": 0.0599999763071537,
"loss_total": 1.0732877254486084,
"lr": 0.0010193051087452058,
"router/selected_tokens_s0": 7422.25,
"router/selected_tokens_s1": 4291.875,
"step": 5550,
"tokens_trained": 18.182090776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5769803560031204,
"grad_norm": 0.1716887205839157,
"loss": 1.1052,
"loss_ce": 0.8134817481040955,
"loss_region": 0.06000108644366264,
"loss_total": 0.8734828233718872,
"lr": 0.0010188982167613548,
"router/selected_tokens_s0": 7408.875,
"router/selected_tokens_s1": 4308.625,
"step": 5560,
"tokens_trained": 18.214852704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5798170342528899,
"grad_norm": 0.14704060554504395,
"loss": 1.1105,
"loss_ce": 1.1164242029190063,
"loss_region": 0.05999663099646568,
"loss_total": 1.17642080783844,
"lr": 0.0010184913247775038,
"router/selected_tokens_s0": 7460.25,
"router/selected_tokens_s1": 4319.5,
"step": 5570,
"tokens_trained": 18.247618144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5826537125026594,
"grad_norm": 0.20581626892089844,
"loss": 1.1033,
"loss_ce": 0.9779660701751709,
"loss_region": 0.06000097095966339,
"loss_total": 1.0379670858383179,
"lr": 0.0010180844327936527,
"router/selected_tokens_s0": 7422.875,
"router/selected_tokens_s1": 4289.0,
"step": 5580,
"tokens_trained": 18.280383584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.585490390752429,
"grad_norm": 0.14134176075458527,
"loss": 1.0991,
"loss_ce": 0.9097084999084473,
"loss_region": 0.05999951437115669,
"loss_total": 0.9697080254554749,
"lr": 0.0010176775408098017,
"router/selected_tokens_s0": 7425.875,
"router/selected_tokens_s1": 4281.125,
"step": 5590,
"tokens_trained": 18.313149024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5883270690021984,
"grad_norm": 0.19416779279708862,
"loss": 1.099,
"loss_ce": 1.0267307758331299,
"loss_region": 0.06000243127346039,
"loss_total": 1.0867332220077515,
"lr": 0.0010172706488259507,
"router/selected_tokens_s0": 7437.625,
"router/selected_tokens_s1": 4288.375,
"step": 5600,
"tokens_trained": 18.345914464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.591163747251968,
"grad_norm": 0.28280109167099,
"loss": 1.1031,
"loss_ce": 1.0410712957382202,
"loss_region": 0.06000087037682533,
"loss_total": 1.1010721921920776,
"lr": 0.0010168637568420996,
"router/selected_tokens_s0": 7408.0,
"router/selected_tokens_s1": 4275.625,
"step": 5610,
"tokens_trained": 18.378679104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5940004255017375,
"grad_norm": 0.26848140358924866,
"loss": 1.0972,
"loss_ce": 0.9527778029441833,
"loss_region": 0.059995293617248535,
"loss_total": 1.012773036956787,
"lr": 0.0010164568648582486,
"router/selected_tokens_s0": 7462.0,
"router/selected_tokens_s1": 4331.25,
"step": 5620,
"tokens_trained": 18.411444544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.596837103751507,
"grad_norm": 0.22628232836723328,
"loss": 1.1009,
"loss_ce": 1.0201693773269653,
"loss_region": 0.060002438724040985,
"loss_total": 1.080171823501587,
"lr": 0.0010160499728743976,
"router/selected_tokens_s0": 7481.0,
"router/selected_tokens_s1": 4304.5,
"step": 5630,
"tokens_trained": 18.444209984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.5996737820012765,
"grad_norm": 0.260987251996994,
"loss": 1.0964,
"loss_ce": 0.984906017780304,
"loss_region": 0.06002039834856987,
"loss_total": 1.044926404953003,
"lr": 0.0010156430808905465,
"router/selected_tokens_s0": 7382.0,
"router/selected_tokens_s1": 4233.75,
"step": 5640,
"tokens_trained": 18.476975424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.602510460251046,
"grad_norm": 0.26559290289878845,
"loss": 1.1014,
"loss_ce": 1.1597309112548828,
"loss_region": 0.06001560389995575,
"loss_total": 1.219746470451355,
"lr": 0.0010152361889066955,
"router/selected_tokens_s0": 7370.0,
"router/selected_tokens_s1": 4235.625,
"step": 5650,
"tokens_trained": 18.509739264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6053471385008156,
"grad_norm": 0.20504187047481537,
"loss": 1.1017,
"loss_ce": 0.9569210410118103,
"loss_region": 0.05999953672289848,
"loss_total": 1.016920566558838,
"lr": 0.0010148292969228445,
"router/selected_tokens_s0": 7356.125,
"router/selected_tokens_s1": 4291.5,
"step": 5660,
"tokens_trained": 18.542503904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.608183816750585,
"grad_norm": 0.150313138961792,
"loss": 1.0987,
"loss_ce": 1.0686254501342773,
"loss_region": 0.059998732060194016,
"loss_total": 1.1286242008209229,
"lr": 0.0010144224049389934,
"router/selected_tokens_s0": 7439.125,
"router/selected_tokens_s1": 4303.25,
"step": 5670,
"tokens_trained": 18.575269344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6110204950003546,
"grad_norm": 0.11161628365516663,
"loss": 1.0954,
"loss_ce": 0.9945487976074219,
"loss_region": 0.06000113487243652,
"loss_total": 1.0545499324798584,
"lr": 0.0010140155129551424,
"router/selected_tokens_s0": 7482.25,
"router/selected_tokens_s1": 4331.75,
"step": 5680,
"tokens_trained": 18.608031832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6138571732501241,
"grad_norm": 0.17794479429721832,
"loss": 1.0983,
"loss_ce": 1.112082600593567,
"loss_region": 0.05999523028731346,
"loss_total": 1.1720777750015259,
"lr": 0.0010136086209712914,
"router/selected_tokens_s0": 7418.125,
"router/selected_tokens_s1": 4316.625,
"step": 5690,
"tokens_trained": 18.640797272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6166938514998936,
"grad_norm": 0.16560673713684082,
"loss": 1.1002,
"loss_ce": 0.9786914587020874,
"loss_region": 0.06000278890132904,
"loss_total": 1.0386942625045776,
"lr": 0.0010132017289874405,
"router/selected_tokens_s0": 7344.625,
"router/selected_tokens_s1": 4255.5,
"step": 5700,
"tokens_trained": 18.673562712
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6195305297496632,
"grad_norm": 0.10915427654981613,
"loss": 1.0996,
"loss_ce": 1.0432522296905518,
"loss_region": 0.06000416725873947,
"loss_total": 1.103256344795227,
"lr": 0.0010127948370035895,
"router/selected_tokens_s0": 7388.625,
"router/selected_tokens_s1": 4249.625,
"step": 5710,
"tokens_trained": 18.706328152
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6223672079994327,
"grad_norm": 0.16476505994796753,
"loss": 1.104,
"loss_ce": 1.1305444240570068,
"loss_region": 0.05999914929270744,
"loss_total": 1.190543532371521,
"lr": 0.0010123879450197385,
"router/selected_tokens_s0": 7396.75,
"router/selected_tokens_s1": 4338.125,
"step": 5720,
"tokens_trained": 18.739093568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6252038862492022,
"grad_norm": 0.10708323866128922,
"loss": 1.1039,
"loss_ce": 1.016690731048584,
"loss_region": 0.05999882519245148,
"loss_total": 1.076689600944519,
"lr": 0.0010119810530358872,
"router/selected_tokens_s0": 7452.875,
"router/selected_tokens_s1": 4316.375,
"step": 5730,
"tokens_trained": 18.771858208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6280405644989717,
"grad_norm": 0.21779781579971313,
"loss": 1.1069,
"loss_ce": 1.1287535429000854,
"loss_region": 0.05999905243515968,
"loss_total": 1.1887526512145996,
"lr": 0.0010115741610520362,
"router/selected_tokens_s0": 7480.125,
"router/selected_tokens_s1": 4319.5,
"step": 5740,
"tokens_trained": 18.804619848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6308772427487412,
"grad_norm": 0.23356978595256805,
"loss": 1.0974,
"loss_ce": 1.1192667484283447,
"loss_region": 0.06000344455242157,
"loss_total": 1.1792701482772827,
"lr": 0.0010111672690681851,
"router/selected_tokens_s0": 7453.625,
"router/selected_tokens_s1": 4299.375,
"step": 5750,
"tokens_trained": 18.837385288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6337139209985108,
"grad_norm": 0.06789640337228775,
"loss": 1.0989,
"loss_ce": 1.0962039232254028,
"loss_region": 0.06000284478068352,
"loss_total": 1.156206727027893,
"lr": 0.0010107603770843341,
"router/selected_tokens_s0": 7391.125,
"router/selected_tokens_s1": 4261.5,
"step": 5760,
"tokens_trained": 18.870150648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6365505992482803,
"grad_norm": 0.1432223916053772,
"loss": 1.0971,
"loss_ce": 1.0244016647338867,
"loss_region": 0.060005053877830505,
"loss_total": 1.0844067335128784,
"lr": 0.0010103534851004833,
"router/selected_tokens_s0": 7423.875,
"router/selected_tokens_s1": 4263.25,
"step": 5770,
"tokens_trained": 18.902916088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6393872774980498,
"grad_norm": 0.26096969842910767,
"loss": 1.1026,
"loss_ce": 1.0609381198883057,
"loss_region": 0.0600053071975708,
"loss_total": 1.1209434270858765,
"lr": 0.0010099465931166323,
"router/selected_tokens_s0": 7478.75,
"router/selected_tokens_s1": 4297.625,
"step": 5780,
"tokens_trained": 18.935681528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6422239557478193,
"grad_norm": 0.12078365683555603,
"loss": 1.0929,
"loss_ce": 0.9542346000671387,
"loss_region": 0.06000049039721489,
"loss_total": 1.0142351388931274,
"lr": 0.0010095397011327812,
"router/selected_tokens_s0": 7443.0,
"router/selected_tokens_s1": 4298.875,
"step": 5790,
"tokens_trained": 18.968446968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6450606339975888,
"grad_norm": 0.19275307655334473,
"loss": 1.0965,
"loss_ce": 0.9804484248161316,
"loss_region": 0.060001272708177567,
"loss_total": 1.0404497385025024,
"lr": 0.0010091328091489302,
"router/selected_tokens_s0": 7427.5,
"router/selected_tokens_s1": 4289.875,
"step": 5800,
"tokens_trained": 19.001210808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6478973122473584,
"grad_norm": 0.18818101286888123,
"loss": 1.0954,
"loss_ce": 1.0286747217178345,
"loss_region": 0.060000162571668625,
"loss_total": 1.0886749029159546,
"lr": 0.0010087259171650792,
"router/selected_tokens_s0": 7470.625,
"router/selected_tokens_s1": 4308.375,
"step": 5810,
"tokens_trained": 19.033976248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6507339904971279,
"grad_norm": 0.10521817207336426,
"loss": 1.0971,
"loss_ce": 1.0690152645111084,
"loss_region": 0.059997450560331345,
"loss_total": 1.1290127038955688,
"lr": 0.0010083190251812281,
"router/selected_tokens_s0": 7459.625,
"router/selected_tokens_s1": 4354.125,
"step": 5820,
"tokens_trained": 19.066741688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6535706687468974,
"grad_norm": 0.14187674224376678,
"loss": 1.0965,
"loss_ce": 1.1216542720794678,
"loss_region": 0.059998299926519394,
"loss_total": 1.181652545928955,
"lr": 0.001007912133197377,
"router/selected_tokens_s0": 7462.75,
"router/selected_tokens_s1": 4328.25,
"step": 5830,
"tokens_trained": 19.099507128
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.656407346996667,
"grad_norm": 0.22437113523483276,
"loss": 1.0949,
"loss_ce": 1.0522420406341553,
"loss_region": 0.06000174209475517,
"loss_total": 1.1122437715530396,
"lr": 0.001007505241213526,
"router/selected_tokens_s0": 7470.0,
"router/selected_tokens_s1": 4301.625,
"step": 5840,
"tokens_trained": 19.132272568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6592440252464364,
"grad_norm": 0.16007539629936218,
"loss": 1.0967,
"loss_ce": 1.0500563383102417,
"loss_region": 0.060007136315107346,
"loss_total": 1.1100634336471558,
"lr": 0.001007098349229675,
"router/selected_tokens_s0": 7476.625,
"router/selected_tokens_s1": 4285.75,
"step": 5850,
"tokens_trained": 19.165038008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.662080703496206,
"grad_norm": 0.3188250958919525,
"loss": 1.0938,
"loss_ce": 0.9961692690849304,
"loss_region": 0.06000681594014168,
"loss_total": 1.0561760663986206,
"lr": 0.001006691457245824,
"router/selected_tokens_s0": 7489.375,
"router/selected_tokens_s1": 4298.25,
"step": 5860,
"tokens_trained": 19.197803448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6649173817459755,
"grad_norm": 0.12829625606536865,
"loss": 1.0978,
"loss_ce": 1.124149203300476,
"loss_region": 0.060012202709913254,
"loss_total": 1.1841614246368408,
"lr": 0.001006284565261973,
"router/selected_tokens_s0": 7500.125,
"router/selected_tokens_s1": 4290.875,
"step": 5870,
"tokens_trained": 19.230568888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.667754059995745,
"grad_norm": 0.12101241201162338,
"loss": 1.0936,
"loss_ce": 1.0956649780273438,
"loss_region": 0.06001261621713638,
"loss_total": 1.1556775569915771,
"lr": 0.001005877673278122,
"router/selected_tokens_s0": 7488.875,
"router/selected_tokens_s1": 4266.125,
"step": 5880,
"tokens_trained": 19.263333528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6705907382455145,
"grad_norm": 0.17701566219329834,
"loss": 1.0922,
"loss_ce": 1.0158523321151733,
"loss_region": 0.060010313987731934,
"loss_total": 1.0758626461029053,
"lr": 0.0010054707812942709,
"router/selected_tokens_s0": 7456.25,
"router/selected_tokens_s1": 4267.875,
"step": 5890,
"tokens_trained": 19.296098168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.673427416495284,
"grad_norm": 0.19043512642383575,
"loss": 1.0986,
"loss_ce": 1.003629207611084,
"loss_region": 0.060002945363521576,
"loss_total": 1.0636321306228638,
"lr": 0.0010050638893104198,
"router/selected_tokens_s0": 7441.375,
"router/selected_tokens_s1": 4296.5,
"step": 5900,
"tokens_trained": 19.328862688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6762640947450536,
"grad_norm": 0.17591844499111176,
"loss": 1.0986,
"loss_ce": 1.1180049180984497,
"loss_region": 0.059997666627168655,
"loss_total": 1.1780025959014893,
"lr": 0.0010046569973265688,
"router/selected_tokens_s0": 7446.375,
"router/selected_tokens_s1": 4344.25,
"step": 5910,
"tokens_trained": 19.361627328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.679100772994823,
"grad_norm": 0.1346396952867508,
"loss": 1.0925,
"loss_ce": 0.998043954372406,
"loss_region": 0.05999904125928879,
"loss_total": 1.0580430030822754,
"lr": 0.0010042501053427178,
"router/selected_tokens_s0": 7426.125,
"router/selected_tokens_s1": 4302.25,
"step": 5920,
"tokens_trained": 19.394392768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6819374512445926,
"grad_norm": 0.17575864493846893,
"loss": 1.0988,
"loss_ce": 1.1197152137756348,
"loss_region": 0.060000572353601456,
"loss_total": 1.1797157526016235,
"lr": 0.0010038432133588667,
"router/selected_tokens_s0": 7466.625,
"router/selected_tokens_s1": 4301.625,
"step": 5930,
"tokens_trained": 19.427158208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6847741294943621,
"grad_norm": 0.2070358544588089,
"loss": 1.0926,
"loss_ce": 1.0191881656646729,
"loss_region": 0.06000307574868202,
"loss_total": 1.0791912078857422,
"lr": 0.0010034363213750157,
"router/selected_tokens_s0": 7439.0,
"router/selected_tokens_s1": 4286.375,
"step": 5940,
"tokens_trained": 19.459922848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6876108077441316,
"grad_norm": 0.09869208186864853,
"loss": 1.0965,
"loss_ce": 1.076581358909607,
"loss_region": 0.060005977749824524,
"loss_total": 1.136587381362915,
"lr": 0.0010030294293911649,
"router/selected_tokens_s0": 7388.0,
"router/selected_tokens_s1": 4243.875,
"step": 5950,
"tokens_trained": 19.492688288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6904474859939012,
"grad_norm": 0.13199345767498016,
"loss": 1.0979,
"loss_ce": 1.0537714958190918,
"loss_region": 0.06000440567731857,
"loss_total": 1.1137758493423462,
"lr": 0.0010026225374073139,
"router/selected_tokens_s0": 7365.375,
"router/selected_tokens_s1": 4246.0,
"step": 5960,
"tokens_trained": 19.525453728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6932841642436707,
"grad_norm": 0.09942718595266342,
"loss": 1.0993,
"loss_ce": 0.9943310618400574,
"loss_region": 0.05999838560819626,
"loss_total": 1.0543293952941895,
"lr": 0.0010022156454234628,
"router/selected_tokens_s0": 7437.0,
"router/selected_tokens_s1": 4312.875,
"step": 5970,
"tokens_trained": 19.558219168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6961208424934402,
"grad_norm": 0.1292436569929123,
"loss": 1.0892,
"loss_ce": 1.0568798780441284,
"loss_region": 0.05999910086393356,
"loss_total": 1.1168789863586426,
"lr": 0.0010018087534396116,
"router/selected_tokens_s0": 7451.625,
"router/selected_tokens_s1": 4347.25,
"step": 5980,
"tokens_trained": 19.590983808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.6989575207432097,
"grad_norm": 0.12750542163848877,
"loss": 1.0923,
"loss_ce": 1.069689393043518,
"loss_region": 0.059999238699674606,
"loss_total": 1.1296886205673218,
"lr": 0.0010014018614557605,
"router/selected_tokens_s0": 7408.125,
"router/selected_tokens_s1": 4289.875,
"step": 5990,
"tokens_trained": 19.623749248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7017941989929792,
"grad_norm": 0.14449970424175262,
"loss": 1.0972,
"loss_ce": 1.070797324180603,
"loss_region": 0.06000017747282982,
"loss_total": 1.1307975053787231,
"lr": 0.0010009949694719095,
"router/selected_tokens_s0": 7418.375,
"router/selected_tokens_s1": 4301.5,
"step": 6000,
"tokens_trained": 19.65651468
},
{
"epoch": 1.7017941989929792,
"eval_ppl": 2.8376622214251768,
"eval_runtime": 1.0214,
"step": 6000,
"tokens_trained": 19.65651468
},
{
"epoch": 1.7017941989929792,
"eval_F": 0.33497148214704275,
"eval_F_cds": 0.33165299482150223,
"eval_F_dig": 0.31479021798578016,
"eval_F_exon": 0.33605904306621376,
"eval_F_intron": 0.3353029212739146,
"eval_F_nig": 0.3358393120643159,
"eval_F_promoter": 0.333664595114122,
"eval_F_utr": 0.33729289597773715,
"eval_G": 0.3311586550239114,
"eval_G_cds": 0.3296152860203474,
"eval_G_dig": 0.29498825591843114,
"eval_G_exon": 0.3339356431102445,
"eval_G_intron": 0.3316809731709803,
"eval_G_nig": 0.3319550251551926,
"eval_G_promoter": 0.3294627592210916,
"eval_G_utr": 0.33407873737406274,
"eval_avg_bp_per_token": 2.9853287616915076,
"eval_bp_per_token/cds": 3.015199668370872,
"eval_bp_per_token/dig": 3.1767187887813355,
"eval_bp_per_token/exon": 2.975667581731969,
"eval_bp_per_token/intron": 2.982377833753149,
"eval_bp_per_token/nig": 2.977614484299837,
"eval_bp_per_token/promoter": 2.9970216038593303,
"eval_bp_per_token/utr": 2.9647822765469822,
"eval_ppl_cds": 3.545879467798099,
"eval_ppl_dig": 1.1176450122381292,
"eval_ppl_exon": 3.264747422456715,
"eval_ppl_intron": 2.9216169428282455,
"eval_ppl_nig": 2.628432349810158,
"eval_ppl_promoter": 3.22240321944314,
"eval_ppl_utr": 3.223965449989413,
"step": 6000,
"tokens_trained": 19.65651468
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7046308772427488,
"grad_norm": 0.34348469972610474,
"loss": 1.0964,
"loss_ce": 1.1062127351760864,
"loss_region": 0.05999796837568283,
"loss_total": 1.166210651397705,
"lr": 0.0010005880774880585,
"router/selected_tokens_s0": 7427.375,
"router/selected_tokens_s1": 4319.5,
"step": 6010,
"tokens_trained": 19.68928012
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7074675554925183,
"grad_norm": 0.10299943387508392,
"loss": 1.0924,
"loss_ce": 1.0347900390625,
"loss_region": 0.059998273849487305,
"loss_total": 1.0947883129119873,
"lr": 0.0010001811855042076,
"router/selected_tokens_s0": 7407.0,
"router/selected_tokens_s1": 4302.875,
"step": 6020,
"tokens_trained": 19.722045536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7103042337422878,
"grad_norm": 0.08903520554304123,
"loss": 1.0907,
"loss_ce": 1.0642378330230713,
"loss_region": 0.06000013276934624,
"loss_total": 1.1242380142211914,
"lr": 0.0009997742935203566,
"router/selected_tokens_s0": 7402.625,
"router/selected_tokens_s1": 4288.0,
"step": 6030,
"tokens_trained": 19.754810976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7131409119920573,
"grad_norm": 0.15829990804195404,
"loss": 1.0956,
"loss_ce": 1.1073267459869385,
"loss_region": 0.059999532997608185,
"loss_total": 1.1673263311386108,
"lr": 0.0009993674015365056,
"router/selected_tokens_s0": 7419.875,
"router/selected_tokens_s1": 4291.25,
"step": 6040,
"tokens_trained": 19.787576416
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7159775902418268,
"grad_norm": 0.19429846107959747,
"loss": 1.0899,
"loss_ce": 0.995491623878479,
"loss_region": 0.06000322476029396,
"loss_total": 1.0554949045181274,
"lr": 0.0009989605095526545,
"router/selected_tokens_s0": 7405.25,
"router/selected_tokens_s1": 4325.25,
"step": 6050,
"tokens_trained": 19.820338544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7188142684915964,
"grad_norm": 0.06903360784053802,
"loss": 1.0944,
"loss_ce": 1.1205158233642578,
"loss_region": 0.06000121310353279,
"loss_total": 1.1805170774459839,
"lr": 0.0009985536175688035,
"router/selected_tokens_s0": 7457.0,
"router/selected_tokens_s1": 4315.125,
"step": 6060,
"tokens_trained": 19.853099816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7216509467413659,
"grad_norm": 0.25323474407196045,
"loss": 1.0937,
"loss_ce": 1.0416542291641235,
"loss_region": 0.0600033737719059,
"loss_total": 1.1016576290130615,
"lr": 0.0009981467255849525,
"router/selected_tokens_s0": 7445.375,
"router/selected_tokens_s1": 4345.5,
"step": 6070,
"tokens_trained": 19.885862632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7244876249911354,
"grad_norm": 0.137556791305542,
"loss": 1.0979,
"loss_ce": 0.9344243407249451,
"loss_region": 0.06000184267759323,
"loss_total": 0.9944261908531189,
"lr": 0.0009977398336011014,
"router/selected_tokens_s0": 7469.125,
"router/selected_tokens_s1": 4310.875,
"step": 6080,
"tokens_trained": 19.918628072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.727324303240905,
"grad_norm": 0.20417067408561707,
"loss": 1.0935,
"loss_ce": 1.066884160041809,
"loss_region": 0.06000082194805145,
"loss_total": 1.126884937286377,
"lr": 0.0009973329416172504,
"router/selected_tokens_s0": 7440.375,
"router/selected_tokens_s1": 4329.125,
"step": 6090,
"tokens_trained": 19.951393512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7301609814906744,
"grad_norm": 0.14983755350112915,
"loss": 1.0902,
"loss_ce": 1.0103222131729126,
"loss_region": 0.06000688672065735,
"loss_total": 1.0703290700912476,
"lr": 0.0009969260496333994,
"router/selected_tokens_s0": 7381.125,
"router/selected_tokens_s1": 4263.5,
"step": 6100,
"tokens_trained": 19.984154824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.732997659740444,
"grad_norm": 0.13496913015842438,
"loss": 1.0922,
"loss_ce": 1.0360006093978882,
"loss_region": 0.06000128760933876,
"loss_total": 1.0960018634796143,
"lr": 0.0009965191576495483,
"router/selected_tokens_s0": 7387.75,
"router/selected_tokens_s1": 4317.625,
"step": 6110,
"tokens_trained": 20.016919464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7358343379902135,
"grad_norm": 0.10311873257160187,
"loss": 1.085,
"loss_ce": 1.073644995689392,
"loss_region": 0.0599980466067791,
"loss_total": 1.1336430311203003,
"lr": 0.0009961122656656973,
"router/selected_tokens_s0": 7395.875,
"router/selected_tokens_s1": 4310.0,
"step": 6120,
"tokens_trained": 20.049684904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.738671016239983,
"grad_norm": 0.17320473492145538,
"loss": 1.0961,
"loss_ce": 1.0533865690231323,
"loss_region": 0.060003116726875305,
"loss_total": 1.1133897304534912,
"lr": 0.0009957053736818463,
"router/selected_tokens_s0": 7374.125,
"router/selected_tokens_s1": 4297.125,
"step": 6130,
"tokens_trained": 20.082450344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7415076944897525,
"grad_norm": 0.25150588154792786,
"loss": 1.091,
"loss_ce": 1.1272531747817993,
"loss_region": 0.06000062823295593,
"loss_total": 1.1872538328170776,
"lr": 0.0009952984816979952,
"router/selected_tokens_s0": 7418.125,
"router/selected_tokens_s1": 4277.875,
"step": 6140,
"tokens_trained": 20.115215784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.744344372739522,
"grad_norm": 0.14748281240463257,
"loss": 1.0968,
"loss_ce": 1.0051281452178955,
"loss_region": 0.0599982924759388,
"loss_total": 1.0651264190673828,
"lr": 0.0009948915897141442,
"router/selected_tokens_s0": 7441.25,
"router/selected_tokens_s1": 4307.0,
"step": 6150,
"tokens_trained": 20.147981224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7471810509892916,
"grad_norm": 0.23062776029109955,
"loss": 1.0922,
"loss_ce": 0.9553651213645935,
"loss_region": 0.06000138446688652,
"loss_total": 1.015366554260254,
"lr": 0.0009944846977302932,
"router/selected_tokens_s0": 7438.125,
"router/selected_tokens_s1": 4299.0,
"step": 6160,
"tokens_trained": 20.180746664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.750017729239061,
"grad_norm": 0.12702351808547974,
"loss": 1.0923,
"loss_ce": 0.978821873664856,
"loss_region": 0.060008883476257324,
"loss_total": 1.0388307571411133,
"lr": 0.0009940778057464421,
"router/selected_tokens_s0": 7447.75,
"router/selected_tokens_s1": 4285.75,
"step": 6170,
"tokens_trained": 20.213511184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7528544074888306,
"grad_norm": 0.16335810720920563,
"loss": 1.0928,
"loss_ce": 0.9987698793411255,
"loss_region": 0.06001174449920654,
"loss_total": 1.058781623840332,
"lr": 0.000993670913762591,
"router/selected_tokens_s0": 7450.625,
"router/selected_tokens_s1": 4250.875,
"step": 6180,
"tokens_trained": 20.246275824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7556910857386,
"grad_norm": 0.13845063745975494,
"loss": 1.0897,
"loss_ce": 1.0286316871643066,
"loss_region": 0.060003817081451416,
"loss_total": 1.0886354446411133,
"lr": 0.00099326402177874,
"router/selected_tokens_s0": 7433.75,
"router/selected_tokens_s1": 4268.75,
"step": 6190,
"tokens_trained": 20.279039664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7585277639883696,
"grad_norm": 0.12126460671424866,
"loss": 1.0927,
"loss_ce": 0.813042163848877,
"loss_region": 0.060008224099874496,
"loss_total": 0.8730503916740417,
"lr": 0.0009928571297948892,
"router/selected_tokens_s0": 7334.0,
"router/selected_tokens_s1": 4220.125,
"step": 6200,
"tokens_trained": 20.311804304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7613644422381391,
"grad_norm": 0.2719525098800659,
"loss": 1.096,
"loss_ce": 0.9927342534065247,
"loss_region": 0.06000946834683418,
"loss_total": 1.052743673324585,
"lr": 0.0009924502378110382,
"router/selected_tokens_s0": 7441.5,
"router/selected_tokens_s1": 4231.375,
"step": 6210,
"tokens_trained": 20.344569744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7642011204879087,
"grad_norm": 0.11398852616548538,
"loss": 1.0905,
"loss_ce": 1.0965769290924072,
"loss_region": 0.06000201404094696,
"loss_total": 1.1565788984298706,
"lr": 0.0009920433458271872,
"router/selected_tokens_s0": 7465.75,
"router/selected_tokens_s1": 4339.5,
"step": 6220,
"tokens_trained": 20.377335184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7670377987376782,
"grad_norm": 0.09571532905101776,
"loss": 1.087,
"loss_ce": 1.0089653730392456,
"loss_region": 0.060008108615875244,
"loss_total": 1.0689735412597656,
"lr": 0.000991636453843336,
"router/selected_tokens_s0": 7477.5,
"router/selected_tokens_s1": 4277.75,
"step": 6230,
"tokens_trained": 20.410099824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7698744769874477,
"grad_norm": 0.16976556181907654,
"loss": 1.0848,
"loss_ce": 0.9082801938056946,
"loss_region": 0.06001298874616623,
"loss_total": 0.9682931900024414,
"lr": 0.0009912295618594849,
"router/selected_tokens_s0": 7406.5,
"router/selected_tokens_s1": 4263.375,
"step": 6240,
"tokens_trained": 20.442865264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7727111552372172,
"grad_norm": 0.12344443053007126,
"loss": 1.0826,
"loss_ce": 1.0324137210845947,
"loss_region": 0.05999824032187462,
"loss_total": 1.092411994934082,
"lr": 0.0009908226698756338,
"router/selected_tokens_s0": 7416.75,
"router/selected_tokens_s1": 4288.875,
"step": 6250,
"tokens_trained": 20.475630704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7755478334869867,
"grad_norm": 0.1562611311674118,
"loss": 1.0947,
"loss_ce": 0.9874376058578491,
"loss_region": 0.060002829879522324,
"loss_total": 1.0474404096603394,
"lr": 0.0009904157778917828,
"router/selected_tokens_s0": 7420.375,
"router/selected_tokens_s1": 4293.25,
"step": 6260,
"tokens_trained": 20.508396144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7783845117367563,
"grad_norm": 0.12798430025577545,
"loss": 1.0816,
"loss_ce": 1.040648341178894,
"loss_region": 0.060009755194187164,
"loss_total": 1.1006580591201782,
"lr": 0.000990008885907932,
"router/selected_tokens_s0": 7448.75,
"router/selected_tokens_s1": 4249.125,
"step": 6270,
"tokens_trained": 20.541161584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7812211899865258,
"grad_norm": 0.18397857248783112,
"loss": 1.0944,
"loss_ce": 1.0447720289230347,
"loss_region": 0.059998903423547745,
"loss_total": 1.1047708988189697,
"lr": 0.000989601993924081,
"router/selected_tokens_s0": 7452.875,
"router/selected_tokens_s1": 4298.0,
"step": 6280,
"tokens_trained": 20.573927024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7840578682362953,
"grad_norm": 0.21940062940120697,
"loss": 1.0907,
"loss_ce": 1.0577622652053833,
"loss_region": 0.05999821051955223,
"loss_total": 1.117760419845581,
"lr": 0.00098919510194023,
"router/selected_tokens_s0": 7429.375,
"router/selected_tokens_s1": 4307.75,
"step": 6290,
"tokens_trained": 20.606692464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7868945464860648,
"grad_norm": 0.10880064219236374,
"loss": 1.0928,
"loss_ce": 1.0223802328109741,
"loss_region": 0.060006335377693176,
"loss_total": 1.0823866128921509,
"lr": 0.0009887882099563789,
"router/selected_tokens_s0": 7338.0,
"router/selected_tokens_s1": 4266.0,
"step": 6300,
"tokens_trained": 20.639457104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7897312247358343,
"grad_norm": 0.312143474817276,
"loss": 1.0911,
"loss_ce": 1.0233956575393677,
"loss_region": 0.05999905988574028,
"loss_total": 1.0833947658538818,
"lr": 0.0009883813179725278,
"router/selected_tokens_s0": 7434.375,
"router/selected_tokens_s1": 4351.375,
"step": 6310,
"tokens_trained": 20.672222544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7925679029856039,
"grad_norm": 0.10863707214593887,
"loss": 1.0938,
"loss_ce": 1.0155285596847534,
"loss_region": 0.06000586226582527,
"loss_total": 1.075534462928772,
"lr": 0.0009879744259886768,
"router/selected_tokens_s0": 7493.0,
"router/selected_tokens_s1": 4304.25,
"step": 6320,
"tokens_trained": 20.704987984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.7954045812353734,
"grad_norm": 0.08422418683767319,
"loss": 1.0861,
"loss_ce": 1.0128514766693115,
"loss_region": 0.06000527739524841,
"loss_total": 1.0728567838668823,
"lr": 0.0009875675340048258,
"router/selected_tokens_s0": 7379.5,
"router/selected_tokens_s1": 4237.25,
"step": 6330,
"tokens_trained": 20.737753424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.798241259485143,
"grad_norm": 0.12360615283250809,
"loss": 1.0856,
"loss_ce": 1.1110481023788452,
"loss_region": 0.05999955162405968,
"loss_total": 1.1710476875305176,
"lr": 0.0009871606420209747,
"router/selected_tokens_s0": 7395.5,
"router/selected_tokens_s1": 4270.875,
"step": 6340,
"tokens_trained": 20.770518864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8010779377349124,
"grad_norm": 0.16334226727485657,
"loss": 1.0918,
"loss_ce": 0.9591702818870544,
"loss_region": 0.06000158563256264,
"loss_total": 1.0191718339920044,
"lr": 0.0009867537500371237,
"router/selected_tokens_s0": 7417.375,
"router/selected_tokens_s1": 4286.75,
"step": 6350,
"tokens_trained": 20.803284304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.803914615984682,
"grad_norm": 0.09888935089111328,
"loss": 1.087,
"loss_ce": 0.9803853631019592,
"loss_region": 0.059998247772455215,
"loss_total": 1.0403835773468018,
"lr": 0.0009863468580532727,
"router/selected_tokens_s0": 7420.0,
"router/selected_tokens_s1": 4307.25,
"step": 6360,
"tokens_trained": 20.836048936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8067512942344515,
"grad_norm": 0.12638556957244873,
"loss": 1.0933,
"loss_ce": 1.0328595638275146,
"loss_region": 0.05999911203980446,
"loss_total": 1.0928586721420288,
"lr": 0.0009859399660694216,
"router/selected_tokens_s0": 7449.875,
"router/selected_tokens_s1": 4304.125,
"step": 6370,
"tokens_trained": 20.868814376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.809587972484221,
"grad_norm": 0.08907432109117508,
"loss": 1.0935,
"loss_ce": 1.134492039680481,
"loss_region": 0.06000338867306709,
"loss_total": 1.194495439529419,
"lr": 0.0009855330740855706,
"router/selected_tokens_s0": 7486.375,
"router/selected_tokens_s1": 4320.375,
"step": 6380,
"tokens_trained": 20.901579816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8124246507339905,
"grad_norm": 0.24893128871917725,
"loss": 1.0895,
"loss_ce": 1.0298666954040527,
"loss_region": 0.059999607503414154,
"loss_total": 1.089866280555725,
"lr": 0.0009851261821017196,
"router/selected_tokens_s0": 7462.0,
"router/selected_tokens_s1": 4304.125,
"step": 6390,
"tokens_trained": 20.934345256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.81526132898376,
"grad_norm": 0.11238834261894226,
"loss": 1.0971,
"loss_ce": 1.033632516860962,
"loss_region": 0.060001298785209656,
"loss_total": 1.093633770942688,
"lr": 0.0009847192901178685,
"router/selected_tokens_s0": 7403.625,
"router/selected_tokens_s1": 4291.5,
"step": 6400,
"tokens_trained": 20.967109088
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8180980072335295,
"grad_norm": 0.2275191992521286,
"loss": 1.0873,
"loss_ce": 1.0130294561386108,
"loss_region": 0.05999968945980072,
"loss_total": 1.0730291604995728,
"lr": 0.0009843123981340175,
"router/selected_tokens_s0": 7404.0,
"router/selected_tokens_s1": 4286.625,
"step": 6410,
"tokens_trained": 20.999874528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.820934685483299,
"grad_norm": 0.09575220942497253,
"loss": 1.0859,
"loss_ce": 1.015393853187561,
"loss_region": 0.05999882519245148,
"loss_total": 1.075392723083496,
"lr": 0.0009839055061501665,
"router/selected_tokens_s0": 7406.375,
"router/selected_tokens_s1": 4295.375,
"step": 6420,
"tokens_trained": 21.032639968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8237713637330686,
"grad_norm": 0.08018634468317032,
"loss": 1.0928,
"loss_ce": 0.9829267859458923,
"loss_region": 0.05999834090471268,
"loss_total": 1.0429251194000244,
"lr": 0.0009834986141663154,
"router/selected_tokens_s0": 7425.0,
"router/selected_tokens_s1": 4291.25,
"step": 6430,
"tokens_trained": 21.065405408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.826608041982838,
"grad_norm": 0.1278838813304901,
"loss": 1.0901,
"loss_ce": 1.0687657594680786,
"loss_region": 0.06000075116753578,
"loss_total": 1.1287665367126465,
"lr": 0.0009830917221824644,
"router/selected_tokens_s0": 7419.0,
"router/selected_tokens_s1": 4281.75,
"step": 6440,
"tokens_trained": 21.098170848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8294447202326076,
"grad_norm": 0.11121010035276413,
"loss": 1.0815,
"loss_ce": 1.0862224102020264,
"loss_region": 0.06000552698969841,
"loss_total": 1.1462279558181763,
"lr": 0.0009826848301986136,
"router/selected_tokens_s0": 7489.25,
"router/selected_tokens_s1": 4284.5,
"step": 6450,
"tokens_trained": 21.13093628
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8322813984823771,
"grad_norm": 0.16781003773212433,
"loss": 1.092,
"loss_ce": 1.0084702968597412,
"loss_region": 0.0600038543343544,
"loss_total": 1.0684741735458374,
"lr": 0.0009822779382147625,
"router/selected_tokens_s0": 7421.125,
"router/selected_tokens_s1": 4249.125,
"step": 6460,
"tokens_trained": 21.163697856
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8351180767321467,
"grad_norm": 0.1009034812450409,
"loss": 1.0869,
"loss_ce": 0.990406334400177,
"loss_region": 0.059993598610162735,
"loss_total": 1.050399899482727,
"lr": 0.0009818710462309115,
"router/selected_tokens_s0": 7413.125,
"router/selected_tokens_s1": 4293.25,
"step": 6470,
"tokens_trained": 21.196463296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8379547549819162,
"grad_norm": 0.12884724140167236,
"loss": 1.0912,
"loss_ce": 1.0650509595870972,
"loss_region": 0.060001127421855927,
"loss_total": 1.1250520944595337,
"lr": 0.0009814641542470603,
"router/selected_tokens_s0": 7395.875,
"router/selected_tokens_s1": 4298.375,
"step": 6480,
"tokens_trained": 21.229228736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8407914332316857,
"grad_norm": 0.19979813694953918,
"loss": 1.0833,
"loss_ce": 1.0048813819885254,
"loss_region": 0.06000029295682907,
"loss_total": 1.064881682395935,
"lr": 0.0009810572622632092,
"router/selected_tokens_s0": 7402.125,
"router/selected_tokens_s1": 4293.0,
"step": 6490,
"tokens_trained": 21.261994176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8436281114814552,
"grad_norm": 0.16422773897647858,
"loss": 1.091,
"loss_ce": 1.0990355014801025,
"loss_region": 0.059999119490385056,
"loss_total": 1.1590346097946167,
"lr": 0.0009806503702793582,
"router/selected_tokens_s0": 7458.25,
"router/selected_tokens_s1": 4287.25,
"step": 6500,
"tokens_trained": 21.294759616
},
{
"epoch": 1.8436281114814552,
"eval_ppl": 2.8148460739009615,
"eval_runtime": 1.0215,
"step": 6500,
"tokens_trained": 21.294759616
},
{
"epoch": 1.8436281114814552,
"eval_F": 0.33702047034924604,
"eval_F_cds": 0.33144677145868656,
"eval_F_dig": 0.3183842487694351,
"eval_F_exon": 0.33819767685662766,
"eval_F_intron": 0.33763849896903503,
"eval_F_nig": 0.33872373174578946,
"eval_F_promoter": 0.333771905268462,
"eval_F_utr": 0.3387100930196604,
"eval_G": 0.33543778520904954,
"eval_G_cds": 0.3324244975453691,
"eval_G_dig": 0.30429180868622546,
"eval_G_exon": 0.3373760326246488,
"eval_G_intron": 0.3360761604092272,
"eval_G_nig": 0.33625805801952946,
"eval_G_promoter": 0.33342863306109216,
"eval_G_utr": 0.3377500124809967,
"eval_avg_bp_per_token": 2.9671788154699463,
"eval_bp_per_token/cds": 3.017075699965434,
"eval_bp_per_token/dig": 3.1408588957055215,
"eval_bp_per_token/exon": 2.956850588964662,
"eval_bp_per_token/intron": 2.961747558567693,
"eval_bp_per_token/nig": 2.9522584521786484,
"eval_bp_per_token/promoter": 2.996058039084123,
"eval_bp_per_token/utr": 2.9523773297831877,
"eval_ppl_cds": 3.428821805678024,
"eval_ppl_dig": 1.11498108266459,
"eval_ppl_exon": 3.261777228188115,
"eval_ppl_intron": 2.903715208272621,
"eval_ppl_nig": 2.597753309797117,
"eval_ppl_promoter": 3.1453687602347755,
"eval_ppl_utr": 3.148085691800301,
"step": 6500,
"tokens_trained": 21.294759616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8464647897312247,
"grad_norm": 0.0870455726981163,
"loss": 1.0815,
"loss_ce": 0.9556036591529846,
"loss_region": 0.060003068298101425,
"loss_total": 1.0156067609786987,
"lr": 0.0009802434782955071,
"router/selected_tokens_s0": 7424.0,
"router/selected_tokens_s1": 4282.875,
"step": 6510,
"tokens_trained": 21.327524256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8493014679809943,
"grad_norm": 0.17482812702655792,
"loss": 1.0878,
"loss_ce": 1.05632483959198,
"loss_region": 0.06000639125704765,
"loss_total": 1.1163312196731567,
"lr": 0.0009798365863116563,
"router/selected_tokens_s0": 7390.0,
"router/selected_tokens_s1": 4326.0,
"step": 6520,
"tokens_trained": 21.360289696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8521381462307638,
"grad_norm": 0.07318949699401855,
"loss": 1.0845,
"loss_ce": 1.0725730657577515,
"loss_region": 0.05999938026070595,
"loss_total": 1.1325724124908447,
"lr": 0.0009794296943278053,
"router/selected_tokens_s0": 7435.375,
"router/selected_tokens_s1": 4311.375,
"step": 6530,
"tokens_trained": 21.393055136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8549748244805333,
"grad_norm": 0.1223776638507843,
"loss": 1.0863,
"loss_ce": 1.1225980520248413,
"loss_region": 0.060001373291015625,
"loss_total": 1.182599425315857,
"lr": 0.0009790228023439543,
"router/selected_tokens_s0": 7443.875,
"router/selected_tokens_s1": 4267.875,
"step": 6540,
"tokens_trained": 21.425820576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8578115027303028,
"grad_norm": 0.14479322731494904,
"loss": 1.0845,
"loss_ce": 1.024285078048706,
"loss_region": 0.06000075861811638,
"loss_total": 1.084285855293274,
"lr": 0.0009786159103601032,
"router/selected_tokens_s0": 7439.625,
"router/selected_tokens_s1": 4291.375,
"step": 6550,
"tokens_trained": 21.458586016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8606481809800723,
"grad_norm": 0.1520773023366928,
"loss": 1.0901,
"loss_ce": 0.9158788919448853,
"loss_region": 0.06000827997922897,
"loss_total": 0.9758871793746948,
"lr": 0.0009782090183762522,
"router/selected_tokens_s0": 7440.5,
"router/selected_tokens_s1": 4345.0,
"step": 6560,
"tokens_trained": 21.491351456
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8634848592298419,
"grad_norm": 0.12373050302267075,
"loss": 1.0838,
"loss_ce": 1.0457063913345337,
"loss_region": 0.059999339282512665,
"loss_total": 1.105705738067627,
"lr": 0.0009778021263924012,
"router/selected_tokens_s0": 7416.75,
"router/selected_tokens_s1": 4279.75,
"step": 6570,
"tokens_trained": 21.524116896
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8663215374796114,
"grad_norm": 0.0876341238617897,
"loss": 1.0833,
"loss_ce": 0.98248291015625,
"loss_region": 0.06000464782118797,
"loss_total": 1.0424875020980835,
"lr": 0.0009773952344085501,
"router/selected_tokens_s0": 7340.375,
"router/selected_tokens_s1": 4247.375,
"step": 6580,
"tokens_trained": 21.556882336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.869158215729381,
"grad_norm": 0.10975274443626404,
"loss": 1.0856,
"loss_ce": 1.0620837211608887,
"loss_region": 0.06000051274895668,
"loss_total": 1.1220842599868774,
"lr": 0.000976988342424699,
"router/selected_tokens_s0": 7448.0,
"router/selected_tokens_s1": 4340.25,
"step": 6590,
"tokens_trained": 21.589647776
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8719948939791504,
"grad_norm": 0.08602806180715561,
"loss": 1.0801,
"loss_ce": 0.9247351884841919,
"loss_region": 0.06001641973853111,
"loss_total": 0.9847515821456909,
"lr": 0.000976581450440848,
"router/selected_tokens_s0": 7384.875,
"router/selected_tokens_s1": 4269.75,
"step": 6600,
"tokens_trained": 21.622413216
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.87483157222892,
"grad_norm": 0.1520455777645111,
"loss": 1.087,
"loss_ce": 0.9793323278427124,
"loss_region": 0.06001337245106697,
"loss_total": 1.0393457412719727,
"lr": 0.0009761745584569969,
"router/selected_tokens_s0": 7422.75,
"router/selected_tokens_s1": 4372.5,
"step": 6610,
"tokens_trained": 21.655178656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8776682504786895,
"grad_norm": 0.18168233335018158,
"loss": 1.0884,
"loss_ce": 0.9781649112701416,
"loss_region": 0.0600033737719059,
"loss_total": 1.0381683111190796,
"lr": 0.000975767666473146,
"router/selected_tokens_s0": 7411.75,
"router/selected_tokens_s1": 4281.125,
"step": 6620,
"tokens_trained": 21.687944096
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.880504928728459,
"grad_norm": 0.08537963032722473,
"loss": 1.0892,
"loss_ce": 1.0330227613449097,
"loss_region": 0.05999727547168732,
"loss_total": 1.0930200815200806,
"lr": 0.000975360774489295,
"router/selected_tokens_s0": 7448.25,
"router/selected_tokens_s1": 4309.875,
"step": 6630,
"tokens_trained": 21.720707792
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8833416069782285,
"grad_norm": 0.07447545975446701,
"loss": 1.0896,
"loss_ce": 1.0348316431045532,
"loss_region": 0.06000027805566788,
"loss_total": 1.094831943511963,
"lr": 0.0009749538825054439,
"router/selected_tokens_s0": 7475.875,
"router/selected_tokens_s1": 4340.75,
"step": 6640,
"tokens_trained": 21.753473232
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.886178285227998,
"grad_norm": 0.052135758101940155,
"loss": 1.0821,
"loss_ce": 1.043008804321289,
"loss_region": 0.05999908968806267,
"loss_total": 1.1030079126358032,
"lr": 0.0009745469905215929,
"router/selected_tokens_s0": 7413.75,
"router/selected_tokens_s1": 4280.75,
"step": 6650,
"tokens_trained": 21.786238672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8890149634777675,
"grad_norm": 0.140451118350029,
"loss": 1.0833,
"loss_ce": 1.083349585533142,
"loss_region": 0.06000323221087456,
"loss_total": 1.1433528661727905,
"lr": 0.0009741400985377418,
"router/selected_tokens_s0": 7392.625,
"router/selected_tokens_s1": 4293.625,
"step": 6660,
"tokens_trained": 21.819004112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.891851641727537,
"grad_norm": 0.10239919275045395,
"loss": 1.0823,
"loss_ce": 0.984279453754425,
"loss_region": 0.05999943986535072,
"loss_total": 1.044278860092163,
"lr": 0.0009737332065538909,
"router/selected_tokens_s0": 7461.5,
"router/selected_tokens_s1": 4314.625,
"step": 6670,
"tokens_trained": 21.851769552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.8946883199773066,
"grad_norm": 0.11570015549659729,
"loss": 1.0758,
"loss_ce": 1.0949254035949707,
"loss_region": 0.06000664457678795,
"loss_total": 1.1549320220947266,
"lr": 0.0009733263145700399,
"router/selected_tokens_s0": 7371.75,
"router/selected_tokens_s1": 4303.875,
"step": 6680,
"tokens_trained": 21.884534992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.897524998227076,
"grad_norm": 0.07118403166532516,
"loss": 1.0803,
"loss_ce": 0.9520093202590942,
"loss_region": 0.060000941157341,
"loss_total": 1.0120102167129517,
"lr": 0.0009729194225861888,
"router/selected_tokens_s0": 7413.75,
"router/selected_tokens_s1": 4268.75,
"step": 6690,
"tokens_trained": 21.917300432
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9003616764768456,
"grad_norm": 0.08157458156347275,
"loss": 1.0771,
"loss_ce": 1.1682521104812622,
"loss_region": 0.06000512093305588,
"loss_total": 1.228257179260254,
"lr": 0.0009725125306023378,
"router/selected_tokens_s0": 7389.625,
"router/selected_tokens_s1": 4302.75,
"step": 6700,
"tokens_trained": 21.950065872
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9031983547266151,
"grad_norm": 0.13799847662448883,
"loss": 1.0839,
"loss_ce": 1.0058233737945557,
"loss_region": 0.06000097095966339,
"loss_total": 1.0658243894577026,
"lr": 0.0009721056386184868,
"router/selected_tokens_s0": 7442.75,
"router/selected_tokens_s1": 4334.125,
"step": 6710,
"tokens_trained": 21.982831312
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9060350329763847,
"grad_norm": 0.07417915761470795,
"loss": 1.0874,
"loss_ce": 0.9934352040290833,
"loss_region": 0.060005929321050644,
"loss_total": 1.0534411668777466,
"lr": 0.0009716987466346357,
"router/selected_tokens_s0": 7397.5,
"router/selected_tokens_s1": 4303.125,
"step": 6720,
"tokens_trained": 22.015596752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9088717112261542,
"grad_norm": 0.12218568474054337,
"loss": 1.0765,
"loss_ce": 1.054198145866394,
"loss_region": 0.05999940261244774,
"loss_total": 1.1141974925994873,
"lr": 0.0009712918546507846,
"router/selected_tokens_s0": 7443.5,
"router/selected_tokens_s1": 4270.25,
"step": 6730,
"tokens_trained": 22.048362192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9117083894759237,
"grad_norm": 0.08367050439119339,
"loss": 1.075,
"loss_ce": 1.1362199783325195,
"loss_region": 0.05999961495399475,
"loss_total": 1.196219563484192,
"lr": 0.0009708849626669337,
"router/selected_tokens_s0": 7419.125,
"router/selected_tokens_s1": 4273.75,
"step": 6740,
"tokens_trained": 22.081127632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9145450677256932,
"grad_norm": 0.07572333514690399,
"loss": 1.0818,
"loss_ce": 1.1262247562408447,
"loss_region": 0.0599992461502552,
"loss_total": 1.1862239837646484,
"lr": 0.0009704780706830826,
"router/selected_tokens_s0": 7456.625,
"router/selected_tokens_s1": 4306.5,
"step": 6750,
"tokens_trained": 22.113893072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9173817459754627,
"grad_norm": 0.1779952049255371,
"loss": 1.0841,
"loss_ce": 0.9176620244979858,
"loss_region": 0.06000371649861336,
"loss_total": 0.9776657223701477,
"lr": 0.0009700711786992316,
"router/selected_tokens_s0": 7432.5,
"router/selected_tokens_s1": 4260.125,
"step": 6760,
"tokens_trained": 22.146655448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9202184242252323,
"grad_norm": 0.14154663681983948,
"loss": 1.0845,
"loss_ce": 0.9990371465682983,
"loss_region": 0.06000208854675293,
"loss_total": 1.0590392351150513,
"lr": 0.0009696642867153806,
"router/selected_tokens_s0": 7448.0,
"router/selected_tokens_s1": 4277.75,
"step": 6770,
"tokens_trained": 22.179420888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9230551024750018,
"grad_norm": 0.12332601845264435,
"loss": 1.0903,
"loss_ce": 1.0889134407043457,
"loss_region": 0.06000123545527458,
"loss_total": 1.1489146947860718,
"lr": 0.0009692573947315295,
"router/selected_tokens_s0": 7410.625,
"router/selected_tokens_s1": 4298.125,
"step": 6780,
"tokens_trained": 22.212186328
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9258917807247713,
"grad_norm": 0.049108777195215225,
"loss": 1.0793,
"loss_ce": 1.0911067724227905,
"loss_region": 0.06000058352947235,
"loss_total": 1.1511073112487793,
"lr": 0.0009688505027476785,
"router/selected_tokens_s0": 7404.375,
"router/selected_tokens_s1": 4292.625,
"step": 6790,
"tokens_trained": 22.244951768
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9287284589745408,
"grad_norm": 0.08588030934333801,
"loss": 1.0822,
"loss_ce": 1.0566279888153076,
"loss_region": 0.06000346690416336,
"loss_total": 1.1166315078735352,
"lr": 0.0009684436107638276,
"router/selected_tokens_s0": 7381.625,
"router/selected_tokens_s1": 4274.5,
"step": 6800,
"tokens_trained": 22.277717208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9315651372243103,
"grad_norm": 0.09908344596624374,
"loss": 1.0782,
"loss_ce": 1.0376368761062622,
"loss_region": 0.05999937653541565,
"loss_total": 1.0976362228393555,
"lr": 0.0009680367187799765,
"router/selected_tokens_s0": 7475.125,
"router/selected_tokens_s1": 4332.375,
"step": 6810,
"tokens_trained": 22.310482648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9344018154740799,
"grad_norm": 0.09425711631774902,
"loss": 1.0808,
"loss_ce": 1.1275286674499512,
"loss_region": 0.05999993532896042,
"loss_total": 1.1875286102294922,
"lr": 0.0009676298267961255,
"router/selected_tokens_s0": 7449.5,
"router/selected_tokens_s1": 4272.5,
"step": 6820,
"tokens_trained": 22.343246488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9372384937238494,
"grad_norm": 0.08792036026716232,
"loss": 1.0818,
"loss_ce": 1.053713321685791,
"loss_region": 0.06000383198261261,
"loss_total": 1.1137171983718872,
"lr": 0.0009672229348122745,
"router/selected_tokens_s0": 7464.25,
"router/selected_tokens_s1": 4300.625,
"step": 6830,
"tokens_trained": 22.376011928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.940075171973619,
"grad_norm": 0.14521412551403046,
"loss": 1.0828,
"loss_ce": 0.9131529927253723,
"loss_region": 0.0600009560585022,
"loss_total": 0.9731539487838745,
"lr": 0.0009668160428284234,
"router/selected_tokens_s0": 7414.875,
"router/selected_tokens_s1": 4263.25,
"step": 6840,
"tokens_trained": 22.408777368
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9429118502233884,
"grad_norm": 0.11343439668416977,
"loss": 1.0838,
"loss_ce": 1.1041600704193115,
"loss_region": 0.06000589206814766,
"loss_total": 1.16416597366333,
"lr": 0.0009664091508445723,
"router/selected_tokens_s0": 7446.625,
"router/selected_tokens_s1": 4249.5,
"step": 6850,
"tokens_trained": 22.441542808
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.945748528473158,
"grad_norm": 0.121289923787117,
"loss": 1.0837,
"loss_ce": 0.8764686584472656,
"loss_region": 0.05999890714883804,
"loss_total": 0.9364675879478455,
"lr": 0.0009660022588607213,
"router/selected_tokens_s0": 7444.0,
"router/selected_tokens_s1": 4321.375,
"step": 6860,
"tokens_trained": 22.474308248
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9485852067229275,
"grad_norm": 0.06294595450162888,
"loss": 1.074,
"loss_ce": 0.9599717855453491,
"loss_region": 0.06000233069062233,
"loss_total": 1.0199741125106812,
"lr": 0.0009655953668768703,
"router/selected_tokens_s0": 7448.625,
"router/selected_tokens_s1": 4300.625,
"step": 6870,
"tokens_trained": 22.507073688
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.951421884972697,
"grad_norm": 0.06342046707868576,
"loss": 1.0798,
"loss_ce": 1.0366178750991821,
"loss_region": 0.06000163033604622,
"loss_total": 1.0966194868087769,
"lr": 0.0009651884748930193,
"router/selected_tokens_s0": 7455.25,
"router/selected_tokens_s1": 4314.5,
"step": 6880,
"tokens_trained": 22.539837536
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9542585632224665,
"grad_norm": 0.06787163019180298,
"loss": 1.0851,
"loss_ce": 0.9529252052307129,
"loss_region": 0.06001782417297363,
"loss_total": 1.0129430294036865,
"lr": 0.0009647815829091683,
"router/selected_tokens_s0": 7417.75,
"router/selected_tokens_s1": 4262.875,
"step": 6890,
"tokens_trained": 22.572602976
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.957095241472236,
"grad_norm": 0.10369361191987991,
"loss": 1.0824,
"loss_ce": 1.1339085102081299,
"loss_region": 0.059998538345098495,
"loss_total": 1.1939070224761963,
"lr": 0.0009643746909253172,
"router/selected_tokens_s0": 7439.625,
"router/selected_tokens_s1": 4269.0,
"step": 6900,
"tokens_trained": 22.605367616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9599319197220055,
"grad_norm": 0.09577842801809311,
"loss": 1.0758,
"loss_ce": 0.8998700976371765,
"loss_region": 0.06000450626015663,
"loss_total": 0.9598746299743652,
"lr": 0.0009639677989414662,
"router/selected_tokens_s0": 7404.875,
"router/selected_tokens_s1": 4287.75,
"step": 6910,
"tokens_trained": 22.638133056
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.962768597971775,
"grad_norm": 0.09918491542339325,
"loss": 1.0767,
"loss_ce": 0.9360069632530212,
"loss_region": 0.06000268831849098,
"loss_total": 0.9960096478462219,
"lr": 0.0009635609069576153,
"router/selected_tokens_s0": 7433.75,
"router/selected_tokens_s1": 4320.625,
"step": 6920,
"tokens_trained": 22.670898496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9656052762215446,
"grad_norm": 0.09037332236766815,
"loss": 1.0824,
"loss_ce": 1.1245343685150146,
"loss_region": 0.06000065803527832,
"loss_total": 1.184535026550293,
"lr": 0.0009631540149737642,
"router/selected_tokens_s0": 7447.0,
"router/selected_tokens_s1": 4299.375,
"step": 6930,
"tokens_trained": 22.703663936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.968441954471314,
"grad_norm": 0.0935681015253067,
"loss": 1.0775,
"loss_ce": 1.1298129558563232,
"loss_region": 0.060005635023117065,
"loss_total": 1.1898186206817627,
"lr": 0.0009627471229899132,
"router/selected_tokens_s0": 7427.5,
"router/selected_tokens_s1": 4319.75,
"step": 6940,
"tokens_trained": 22.736429376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9712786327210836,
"grad_norm": 0.07654014229774475,
"loss": 1.0788,
"loss_ce": 1.045467734336853,
"loss_region": 0.0600028894841671,
"loss_total": 1.1054706573486328,
"lr": 0.0009623402310060622,
"router/selected_tokens_s0": 7431.375,
"router/selected_tokens_s1": 4300.25,
"step": 6950,
"tokens_trained": 22.769194816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9741153109708531,
"grad_norm": 0.2214384526014328,
"loss": 1.0807,
"loss_ce": 1.138108253479004,
"loss_region": 0.06000784412026405,
"loss_total": 1.1981160640716553,
"lr": 0.0009619333390222111,
"router/selected_tokens_s0": 7450.875,
"router/selected_tokens_s1": 4360.125,
"step": 6960,
"tokens_trained": 22.801960256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9769519892206227,
"grad_norm": 0.10386006534099579,
"loss": 1.0887,
"loss_ce": 0.9496551752090454,
"loss_region": 0.05999850109219551,
"loss_total": 1.0096536874771118,
"lr": 0.00096152644703836,
"router/selected_tokens_s0": 7437.125,
"router/selected_tokens_s1": 4279.5,
"step": 6970,
"tokens_trained": 22.834725696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9797886674703922,
"grad_norm": 0.07160235196352005,
"loss": 1.0747,
"loss_ce": 1.0140540599822998,
"loss_region": 0.06000373139977455,
"loss_total": 1.0740578174591064,
"lr": 0.0009611195550545089,
"router/selected_tokens_s0": 7451.25,
"router/selected_tokens_s1": 4298.75,
"step": 6980,
"tokens_trained": 22.867491136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9826253457201617,
"grad_norm": 0.16528116166591644,
"loss": 1.0852,
"loss_ce": 0.9280127286911011,
"loss_region": 0.060000862926244736,
"loss_total": 0.9880135655403137,
"lr": 0.000960712663070658,
"router/selected_tokens_s0": 7405.625,
"router/selected_tokens_s1": 4259.5,
"step": 6990,
"tokens_trained": 22.900255448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9854620239699312,
"grad_norm": 0.08820237964391708,
"loss": 1.0759,
"loss_ce": 1.0279951095581055,
"loss_region": 0.059999141842126846,
"loss_total": 1.0879942178726196,
"lr": 0.000960305771086807,
"router/selected_tokens_s0": 7447.625,
"router/selected_tokens_s1": 4283.875,
"step": 7000,
"tokens_trained": 22.933020888
},
{
"epoch": 1.9854620239699312,
"eval_ppl": 2.794549019742632,
"eval_runtime": 1.0319,
"step": 7000,
"tokens_trained": 22.933020888
},
{
"epoch": 1.9854620239699312,
"eval_F": 0.3364006302575722,
"eval_F_cds": 0.3297511571422025,
"eval_F_dig": 0.3325259785920775,
"eval_F_exon": 0.33740093093470874,
"eval_F_intron": 0.3370067443465844,
"eval_F_nig": 0.33774423752098914,
"eval_F_promoter": 0.3332120262023403,
"eval_F_utr": 0.33739596485351336,
"eval_G": 0.33825298851472774,
"eval_G_cds": 0.33560851824217497,
"eval_G_dig": 0.3102000156262208,
"eval_G_exon": 0.3403066620015096,
"eval_G_intron": 0.33883673270951786,
"eval_G_nig": 0.3388791193714859,
"eval_G_promoter": 0.33646450986378607,
"eval_G_utr": 0.3406638219388544,
"eval_avg_bp_per_token": 2.972646035871957,
"eval_bp_per_token/cds": 3.032589813077618,
"eval_bp_per_token/dig": 3.0072838345864663,
"eval_bp_per_token/exon": 2.963832960477256,
"eval_bp_per_token/intron": 2.9672996661799154,
"eval_bp_per_token/nig": 2.9608203158102877,
"eval_bp_per_token/promoter": 3.0010921616399227,
"eval_bp_per_token/utr": 2.96387658469528,
"eval_ppl_cds": 3.4120921617320685,
"eval_ppl_dig": 1.11111283111052,
"eval_ppl_exon": 3.2512919962069096,
"eval_ppl_intron": 2.89221028657143,
"eval_ppl_nig": 2.586823069198443,
"eval_ppl_promoter": 3.0910928401544187,
"eval_ppl_utr": 3.108658160865457,
"step": 7000,
"tokens_trained": 22.933020888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9882987022197007,
"grad_norm": 0.1708163172006607,
"loss": 1.0825,
"loss_ce": 1.1052597761154175,
"loss_region": 0.05999952182173729,
"loss_total": 1.1652592420578003,
"lr": 0.000959898879102956,
"router/selected_tokens_s0": 7447.25,
"router/selected_tokens_s1": 4298.5,
"step": 7010,
"tokens_trained": 22.965785528
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9911353804694703,
"grad_norm": 0.1802079677581787,
"loss": 1.0845,
"loss_ce": 1.109366774559021,
"loss_region": 0.05999884009361267,
"loss_total": 1.169365644454956,
"lr": 0.0009594919871191049,
"router/selected_tokens_s0": 7416.0,
"router/selected_tokens_s1": 4261.25,
"step": 7020,
"tokens_trained": 22.998550968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9939720587192398,
"grad_norm": 0.08593832701444626,
"loss": 1.0785,
"loss_ce": 0.929319441318512,
"loss_region": 0.06000542640686035,
"loss_total": 0.9893248677253723,
"lr": 0.0009590850951352539,
"router/selected_tokens_s0": 7443.0,
"router/selected_tokens_s1": 4242.375,
"step": 7030,
"tokens_trained": 23.031316408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9968087369690093,
"grad_norm": 0.09409149736166,
"loss": 1.0841,
"loss_ce": 0.970834493637085,
"loss_region": 0.06000007688999176,
"loss_total": 1.0308345556259155,
"lr": 0.0009586782031514028,
"router/selected_tokens_s0": 7411.25,
"router/selected_tokens_s1": 4277.625,
"step": 7040,
"tokens_trained": 23.064081848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 1.9996454152187788,
"grad_norm": 0.1600276380777359,
"loss": 1.0808,
"loss_ce": 0.9412515759468079,
"loss_region": 0.060001179575920105,
"loss_total": 1.0012527704238892,
"lr": 0.0009582713111675519,
"router/selected_tokens_s0": 7405.25,
"router/selected_tokens_s1": 4291.625,
"step": 7050,
"tokens_trained": 23.096847288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0022693425998157,
"grad_norm": 0.09644526243209839,
"loss": 1.0706,
"loss_ce": 0.971865713596344,
"loss_region": 0.060010332614183426,
"loss_total": 1.0318760871887207,
"lr": 0.0009578644191837009,
"router/selected_tokens_s0": 7413.25,
"router/selected_tokens_s1": 4330.5,
"step": 7060,
"tokens_trained": 23.12715532
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0051060208495852,
"grad_norm": 0.08329671621322632,
"loss": 1.076,
"loss_ce": 0.9211774468421936,
"loss_region": 0.06000356748700142,
"loss_total": 0.9811810255050659,
"lr": 0.0009574575271998498,
"router/selected_tokens_s0": 7464.0,
"router/selected_tokens_s1": 4346.5,
"step": 7070,
"tokens_trained": 23.15992076
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0079426990993547,
"grad_norm": 0.10517358034849167,
"loss": 1.0705,
"loss_ce": 1.066274881362915,
"loss_region": 0.0600065216422081,
"loss_total": 1.1262813806533813,
"lr": 0.0009570506352159988,
"router/selected_tokens_s0": 7373.875,
"router/selected_tokens_s1": 4275.75,
"step": 7080,
"tokens_trained": 23.1926862
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0107793773491243,
"grad_norm": 0.18958993256092072,
"loss": 1.0769,
"loss_ce": 1.0623862743377686,
"loss_region": 0.06000087037682533,
"loss_total": 1.122387170791626,
"lr": 0.0009566437432321478,
"router/selected_tokens_s0": 7403.25,
"router/selected_tokens_s1": 4238.125,
"step": 7090,
"tokens_trained": 23.22545164
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.013616055598894,
"grad_norm": 0.09266994893550873,
"loss": 1.0779,
"loss_ce": 1.0237703323364258,
"loss_region": 0.06000027060508728,
"loss_total": 1.0837706327438354,
"lr": 0.0009562368512482966,
"router/selected_tokens_s0": 7413.625,
"router/selected_tokens_s1": 4262.75,
"step": 7100,
"tokens_trained": 23.25821708
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0164527338486633,
"grad_norm": 0.08144967257976532,
"loss": 1.0765,
"loss_ce": 0.977138340473175,
"loss_region": 0.06000202149152756,
"loss_total": 1.0371403694152832,
"lr": 0.0009558299592644456,
"router/selected_tokens_s0": 7403.25,
"router/selected_tokens_s1": 4263.125,
"step": 7110,
"tokens_trained": 23.29098252
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.019289412098433,
"grad_norm": 0.09503156691789627,
"loss": 1.074,
"loss_ce": 1.0922651290893555,
"loss_region": 0.060002658516168594,
"loss_total": 1.1522678136825562,
"lr": 0.0009554230672805947,
"router/selected_tokens_s0": 7420.375,
"router/selected_tokens_s1": 4300.75,
"step": 7120,
"tokens_trained": 23.32374796
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0221260903482023,
"grad_norm": 0.15637706220149994,
"loss": 1.0697,
"loss_ce": 0.9792024493217468,
"loss_region": 0.05999979004263878,
"loss_total": 1.0392022132873535,
"lr": 0.0009550161752967436,
"router/selected_tokens_s0": 7453.625,
"router/selected_tokens_s1": 4296.0,
"step": 7130,
"tokens_trained": 23.3565134
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.024962768597972,
"grad_norm": 0.10303203016519547,
"loss": 1.0773,
"loss_ce": 1.0813617706298828,
"loss_region": 0.05999702960252762,
"loss_total": 1.1413588523864746,
"lr": 0.0009546092833128926,
"router/selected_tokens_s0": 7435.125,
"router/selected_tokens_s1": 4272.375,
"step": 7140,
"tokens_trained": 23.38927804
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0277994468477414,
"grad_norm": 0.09615137428045273,
"loss": 1.0687,
"loss_ce": 0.9444698095321655,
"loss_region": 0.06000514701008797,
"loss_total": 1.0044749975204468,
"lr": 0.0009542023913290416,
"router/selected_tokens_s0": 7447.625,
"router/selected_tokens_s1": 4315.75,
"step": 7150,
"tokens_trained": 23.42204348
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.030636125097511,
"grad_norm": 0.14985762536525726,
"loss": 1.0683,
"loss_ce": 1.0583648681640625,
"loss_region": 0.06000368297100067,
"loss_total": 1.1183685064315796,
"lr": 0.0009537954993451905,
"router/selected_tokens_s0": 7450.5,
"router/selected_tokens_s1": 4309.0,
"step": 7160,
"tokens_trained": 23.45480892
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0334728033472804,
"grad_norm": 0.08965207636356354,
"loss": 1.0702,
"loss_ce": 1.0723220109939575,
"loss_region": 0.06000346690416336,
"loss_total": 1.132325530052185,
"lr": 0.0009533886073613396,
"router/selected_tokens_s0": 7471.375,
"router/selected_tokens_s1": 4292.875,
"step": 7170,
"tokens_trained": 23.48757436
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.03630948159705,
"grad_norm": 0.07297336310148239,
"loss": 1.0677,
"loss_ce": 0.9436392784118652,
"loss_region": 0.060007572174072266,
"loss_total": 1.0036468505859375,
"lr": 0.0009529817153774886,
"router/selected_tokens_s0": 7418.5,
"router/selected_tokens_s1": 4244.0,
"step": 7180,
"tokens_trained": 23.520339
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0391461598468195,
"grad_norm": 0.12650638818740845,
"loss": 1.0704,
"loss_ce": 0.9642244577407837,
"loss_region": 0.06000884622335434,
"loss_total": 1.024233341217041,
"lr": 0.0009525748233936375,
"router/selected_tokens_s0": 7376.25,
"router/selected_tokens_s1": 4291.25,
"step": 7190,
"tokens_trained": 23.55310444
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.041982838096589,
"grad_norm": 0.1184626966714859,
"loss": 1.0826,
"loss_ce": 1.0093343257904053,
"loss_region": 0.06000237911939621,
"loss_total": 1.0693366527557373,
"lr": 0.0009521679314097865,
"router/selected_tokens_s0": 7418.125,
"router/selected_tokens_s1": 4302.625,
"step": 7200,
"tokens_trained": 23.58586988
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0448195163463585,
"grad_norm": 0.05724379047751427,
"loss": 1.0768,
"loss_ce": 1.079675316810608,
"loss_region": 0.060005199164152145,
"loss_total": 1.1396805047988892,
"lr": 0.0009517610394259355,
"router/selected_tokens_s0": 7453.625,
"router/selected_tokens_s1": 4327.25,
"step": 7210,
"tokens_trained": 23.61863532
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.047656194596128,
"grad_norm": 0.1011098176240921,
"loss": 1.0779,
"loss_ce": 1.0079035758972168,
"loss_region": 0.059999871999025345,
"loss_total": 1.0679033994674683,
"lr": 0.0009513541474420843,
"router/selected_tokens_s0": 7451.5,
"router/selected_tokens_s1": 4284.625,
"step": 7220,
"tokens_trained": 23.65140076
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0504928728458975,
"grad_norm": 0.10729926079511642,
"loss": 1.0713,
"loss_ce": 1.114392876625061,
"loss_region": 0.05999760329723358,
"loss_total": 1.174390435218811,
"lr": 0.0009509472554582333,
"router/selected_tokens_s0": 7431.25,
"router/selected_tokens_s1": 4259.875,
"step": 7230,
"tokens_trained": 23.6841662
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.053329551095667,
"grad_norm": 0.08418073505163193,
"loss": 1.0771,
"loss_ce": 0.9541222453117371,
"loss_region": 0.06000092998147011,
"loss_total": 1.0141232013702393,
"lr": 0.0009505403634743824,
"router/selected_tokens_s0": 7403.625,
"router/selected_tokens_s1": 4292.75,
"step": 7240,
"tokens_trained": 23.71693004
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0561662293454366,
"grad_norm": 0.11302497237920761,
"loss": 1.0722,
"loss_ce": 1.072424054145813,
"loss_region": 0.06000204384326935,
"loss_total": 1.132426142692566,
"lr": 0.0009501334714905313,
"router/selected_tokens_s0": 7415.625,
"router/selected_tokens_s1": 4278.375,
"step": 7250,
"tokens_trained": 23.74969548
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.059002907595206,
"grad_norm": 0.11750608682632446,
"loss": 1.069,
"loss_ce": 1.016484022140503,
"loss_region": 0.06000182405114174,
"loss_total": 1.0764858722686768,
"lr": 0.0009497265795066803,
"router/selected_tokens_s0": 7384.25,
"router/selected_tokens_s1": 4272.125,
"step": 7260,
"tokens_trained": 23.78246092
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0618395858449756,
"grad_norm": 0.1328291893005371,
"loss": 1.0696,
"loss_ce": 1.08993661403656,
"loss_region": 0.060007493942976,
"loss_total": 1.1499440670013428,
"lr": 0.0009493196875228293,
"router/selected_tokens_s0": 7411.125,
"router/selected_tokens_s1": 4311.625,
"step": 7270,
"tokens_trained": 23.81522636
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.064676264094745,
"grad_norm": 0.04345889016985893,
"loss": 1.0711,
"loss_ce": 1.0987412929534912,
"loss_region": 0.05999920889735222,
"loss_total": 1.158740520477295,
"lr": 0.0009489127955389782,
"router/selected_tokens_s0": 7362.375,
"router/selected_tokens_s1": 4233.375,
"step": 7280,
"tokens_trained": 23.8479918
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0675129423445147,
"grad_norm": 0.11810455471277237,
"loss": 1.0728,
"loss_ce": 0.9469420313835144,
"loss_region": 0.059997860342264175,
"loss_total": 1.0069398880004883,
"lr": 0.0009485059035551272,
"router/selected_tokens_s0": 7399.125,
"router/selected_tokens_s1": 4261.125,
"step": 7290,
"tokens_trained": 23.88075724
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.070349620594284,
"grad_norm": 0.047945018857717514,
"loss": 1.08,
"loss_ce": 1.002561092376709,
"loss_region": 0.06000149995088577,
"loss_total": 1.0625625848770142,
"lr": 0.0009480990115712763,
"router/selected_tokens_s0": 7451.75,
"router/selected_tokens_s1": 4322.375,
"step": 7300,
"tokens_trained": 23.91352268
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0731862988440537,
"grad_norm": 0.15315809845924377,
"loss": 1.0738,
"loss_ce": 1.0678074359893799,
"loss_region": 0.06000760942697525,
"loss_total": 1.1278150081634521,
"lr": 0.0009476921195874252,
"router/selected_tokens_s0": 7464.0,
"router/selected_tokens_s1": 4323.625,
"step": 7310,
"tokens_trained": 23.94628812
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.076022977093823,
"grad_norm": 0.08653237670660019,
"loss": 1.0697,
"loss_ce": 1.124541163444519,
"loss_region": 0.06001746654510498,
"loss_total": 1.184558629989624,
"lr": 0.0009472852276035742,
"router/selected_tokens_s0": 7398.125,
"router/selected_tokens_s1": 4335.625,
"step": 7320,
"tokens_trained": 23.97905276
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0788596553435927,
"grad_norm": 0.08466868847608566,
"loss": 1.0691,
"loss_ce": 0.8798490166664124,
"loss_region": 0.06001843884587288,
"loss_total": 0.9398674368858337,
"lr": 0.0009468783356197232,
"router/selected_tokens_s0": 7391.25,
"router/selected_tokens_s1": 4293.375,
"step": 7330,
"tokens_trained": 24.0118182
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0816963335933623,
"grad_norm": 0.136433944106102,
"loss": 1.0758,
"loss_ce": 1.1402568817138672,
"loss_region": 0.060009267181158066,
"loss_total": 1.2002661228179932,
"lr": 0.0009464714436358721,
"router/selected_tokens_s0": 7420.0,
"router/selected_tokens_s1": 4331.875,
"step": 7340,
"tokens_trained": 24.04458364
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0845330118431318,
"grad_norm": 0.20771656930446625,
"loss": 1.0594,
"loss_ce": 0.8919783234596252,
"loss_region": 0.06003022566437721,
"loss_total": 0.9520085453987122,
"lr": 0.000946064551652021,
"router/selected_tokens_s0": 7372.25,
"router/selected_tokens_s1": 4267.25,
"step": 7350,
"tokens_trained": 24.07734908
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0873696900929013,
"grad_norm": 0.07634517550468445,
"loss": 1.0697,
"loss_ce": 0.8688952326774597,
"loss_region": 0.06001392379403114,
"loss_total": 0.928909182548523,
"lr": 0.0009456576596681699,
"router/selected_tokens_s0": 7393.25,
"router/selected_tokens_s1": 4316.75,
"step": 7360,
"tokens_trained": 24.110113704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.090206368342671,
"grad_norm": 0.07431330531835556,
"loss": 1.0645,
"loss_ce": 0.980828583240509,
"loss_region": 0.06001806631684303,
"loss_total": 1.0408467054367065,
"lr": 0.000945250767684319,
"router/selected_tokens_s0": 7389.875,
"router/selected_tokens_s1": 4340.125,
"step": 7370,
"tokens_trained": 24.142879144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0930430465924403,
"grad_norm": 0.1355743110179901,
"loss": 1.0741,
"loss_ce": 1.0412564277648926,
"loss_region": 0.060002874583005905,
"loss_total": 1.1012593507766724,
"lr": 0.000944843875700468,
"router/selected_tokens_s0": 7403.75,
"router/selected_tokens_s1": 4279.875,
"step": 7380,
"tokens_trained": 24.175643784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.09587972484221,
"grad_norm": 0.09457384049892426,
"loss": 1.0677,
"loss_ce": 1.0146124362945557,
"loss_region": 0.060000814497470856,
"loss_total": 1.0746132135391235,
"lr": 0.000944436983716617,
"router/selected_tokens_s0": 7456.375,
"router/selected_tokens_s1": 4266.25,
"step": 7390,
"tokens_trained": 24.208409224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.0987164030919794,
"grad_norm": 0.08905760198831558,
"loss": 1.0615,
"loss_ce": 0.9676433801651001,
"loss_region": 0.0599987618625164,
"loss_total": 1.0276421308517456,
"lr": 0.0009440300917327659,
"router/selected_tokens_s0": 7453.625,
"router/selected_tokens_s1": 4254.625,
"step": 7400,
"tokens_trained": 24.241174664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.101553081341749,
"grad_norm": 0.09464745968580246,
"loss": 1.0739,
"loss_ce": 1.0466071367263794,
"loss_region": 0.05999983474612236,
"loss_total": 1.1066069602966309,
"lr": 0.0009436231997489149,
"router/selected_tokens_s0": 7391.0,
"router/selected_tokens_s1": 4242.75,
"step": 7410,
"tokens_trained": 24.273940104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1043897595915184,
"grad_norm": 0.09178861975669861,
"loss": 1.0623,
"loss_ce": 1.0746018886566162,
"loss_region": 0.060001909732818604,
"loss_total": 1.13460373878479,
"lr": 0.000943216307765064,
"router/selected_tokens_s0": 7428.125,
"router/selected_tokens_s1": 4302.25,
"step": 7420,
"tokens_trained": 24.306705544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.107226437841288,
"grad_norm": 0.08409807831048965,
"loss": 1.0672,
"loss_ce": 0.9870949983596802,
"loss_region": 0.06000875309109688,
"loss_total": 1.047103762626648,
"lr": 0.0009428094157812129,
"router/selected_tokens_s0": 7369.625,
"router/selected_tokens_s1": 4281.375,
"step": 7430,
"tokens_trained": 24.339470184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1100631160910575,
"grad_norm": 0.09397881478071213,
"loss": 1.0726,
"loss_ce": 1.0716584920883179,
"loss_region": 0.060008931905031204,
"loss_total": 1.1316673755645752,
"lr": 0.0009424025237973619,
"router/selected_tokens_s0": 7366.625,
"router/selected_tokens_s1": 4281.5,
"step": 7440,
"tokens_trained": 24.372235624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.112899794340827,
"grad_norm": 0.10131512582302094,
"loss": 1.0648,
"loss_ce": 1.0101292133331299,
"loss_region": 0.059999801218509674,
"loss_total": 1.0701290369033813,
"lr": 0.0009419956318135108,
"router/selected_tokens_s0": 7475.125,
"router/selected_tokens_s1": 4291.375,
"step": 7450,
"tokens_trained": 24.404997
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1157364725905965,
"grad_norm": 0.07813931256532669,
"loss": 1.0679,
"loss_ce": 1.0638779401779175,
"loss_region": 0.060002557933330536,
"loss_total": 1.1238805055618286,
"lr": 0.0009415887398296598,
"router/selected_tokens_s0": 7411.375,
"router/selected_tokens_s1": 4283.375,
"step": 7460,
"tokens_trained": 24.43776244
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.118573150840366,
"grad_norm": 0.15742971003055573,
"loss": 1.0728,
"loss_ce": 0.940522313117981,
"loss_region": 0.060000792145729065,
"loss_total": 1.0005230903625488,
"lr": 0.0009411818478458087,
"router/selected_tokens_s0": 7412.125,
"router/selected_tokens_s1": 4288.625,
"step": 7470,
"tokens_trained": 24.47052788
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1214098290901355,
"grad_norm": 0.10386386513710022,
"loss": 1.0647,
"loss_ce": 0.9601840972900391,
"loss_region": 0.060003604739904404,
"loss_total": 1.0201877355575562,
"lr": 0.0009407749558619576,
"router/selected_tokens_s0": 7382.5,
"router/selected_tokens_s1": 4285.375,
"step": 7480,
"tokens_trained": 24.50329252
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.124246507339905,
"grad_norm": 0.05695318058133125,
"loss": 1.0725,
"loss_ce": 1.0721138715744019,
"loss_region": 0.06000151485204697,
"loss_total": 1.132115364074707,
"lr": 0.0009403680638781067,
"router/selected_tokens_s0": 7455.5,
"router/selected_tokens_s1": 4300.25,
"step": 7490,
"tokens_trained": 24.53605796
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1270831855896746,
"grad_norm": 0.08580978959798813,
"loss": 1.0692,
"loss_ce": 1.0266975164413452,
"loss_region": 0.0600011944770813,
"loss_total": 1.0866987705230713,
"lr": 0.0009399611718942557,
"router/selected_tokens_s0": 7451.875,
"router/selected_tokens_s1": 4288.625,
"step": 7500,
"tokens_trained": 24.5688234
},
{
"epoch": 2.1270831855896746,
"eval_ppl": 2.7742442040790527,
"eval_runtime": 1.0454,
"step": 7500,
"tokens_trained": 24.5688234
},
{
"epoch": 2.1270831855896746,
"eval_F": 0.33731541526681774,
"eval_F_cds": 0.3319508730122359,
"eval_F_dig": 0.32635362137667007,
"eval_F_exon": 0.33907829077032753,
"eval_F_intron": 0.33807881279680363,
"eval_F_nig": 0.3386028850557167,
"eval_F_promoter": 0.3338978780583394,
"eval_F_utr": 0.3368548532556881,
"eval_G": 0.34280952226899236,
"eval_G_cds": 0.3411604825913111,
"eval_G_dig": 0.30843382539651537,
"eval_G_exon": 0.34520221031471465,
"eval_G_intron": 0.34351362208587694,
"eval_G_nig": 0.3433470244881507,
"eval_G_promoter": 0.3409342019623761,
"eval_G_utr": 0.34442165879692854,
"eval_avg_bp_per_token": 2.964584346698168,
"eval_bp_per_token/cds": 3.0124939601021605,
"eval_bp_per_token/dig": 3.0641608810150824,
"eval_bp_per_token/exon": 2.9491714073707644,
"eval_bp_per_token/intron": 2.957890178705261,
"eval_bp_per_token/nig": 2.953312107294807,
"eval_bp_per_token/promoter": 2.994927688115699,
"eval_bp_per_token/utr": 2.968637650118565,
"eval_ppl_cds": 3.3837930340528177,
"eval_ppl_dig": 1.108579965306159,
"eval_ppl_exon": 3.2416552682993873,
"eval_ppl_intron": 2.881913272039216,
"eval_ppl_nig": 2.5730585876659235,
"eval_ppl_promoter": 3.0510066204208863,
"eval_ppl_utr": 3.063097120424939,
"step": 7500,
"tokens_trained": 24.5688234
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.129919863839444,
"grad_norm": 0.09488757699728012,
"loss": 1.0692,
"loss_ce": 1.02474844455719,
"loss_region": 0.0600028894841671,
"loss_total": 1.0847513675689697,
"lr": 0.0009395542799104046,
"router/selected_tokens_s0": 7394.25,
"router/selected_tokens_s1": 4274.875,
"step": 7510,
"tokens_trained": 24.60158804
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1327565420892136,
"grad_norm": 0.09648344665765762,
"loss": 1.065,
"loss_ce": 1.0811760425567627,
"loss_region": 0.06000041216611862,
"loss_total": 1.141176462173462,
"lr": 0.0009391473879265536,
"router/selected_tokens_s0": 7421.875,
"router/selected_tokens_s1": 4280.375,
"step": 7520,
"tokens_trained": 24.634352656
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.135593220338983,
"grad_norm": 0.07925688475370407,
"loss": 1.0667,
"loss_ce": 0.9782887101173401,
"loss_region": 0.06000470370054245,
"loss_total": 1.0382933616638184,
"lr": 0.0009387404959427026,
"router/selected_tokens_s0": 7414.375,
"router/selected_tokens_s1": 4294.75,
"step": 7530,
"tokens_trained": 24.66711596
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1384298985887527,
"grad_norm": 0.12421741336584091,
"loss": 1.0701,
"loss_ce": 1.038988471031189,
"loss_region": 0.05999799445271492,
"loss_total": 1.0989865064620972,
"lr": 0.0009383336039588515,
"router/selected_tokens_s0": 7395.625,
"router/selected_tokens_s1": 4239.375,
"step": 7540,
"tokens_trained": 24.6998814
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.141266576838522,
"grad_norm": 0.06676165759563446,
"loss": 1.0715,
"loss_ce": 1.0221954584121704,
"loss_region": 0.06001207232475281,
"loss_total": 1.0822075605392456,
"lr": 0.0009379267119750006,
"router/selected_tokens_s0": 7363.75,
"router/selected_tokens_s1": 4287.875,
"step": 7550,
"tokens_trained": 24.732646072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1441032550882917,
"grad_norm": 0.057106681168079376,
"loss": 1.0681,
"loss_ce": 1.0698057413101196,
"loss_region": 0.06000233814120293,
"loss_total": 1.1298080682754517,
"lr": 0.0009375198199911496,
"router/selected_tokens_s0": 7417.0,
"router/selected_tokens_s1": 4300.75,
"step": 7560,
"tokens_trained": 24.765403184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.146939933338061,
"grad_norm": 0.0772121250629425,
"loss": 1.0689,
"loss_ce": 1.0054962635040283,
"loss_region": 0.05999879539012909,
"loss_total": 1.0654950141906738,
"lr": 0.0009371129280072985,
"router/selected_tokens_s0": 7428.0,
"router/selected_tokens_s1": 4283.75,
"step": 7570,
"tokens_trained": 24.798168624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1497766115878307,
"grad_norm": 0.08018133044242859,
"loss": 1.0726,
"loss_ce": 0.999915599822998,
"loss_region": 0.060004789382219315,
"loss_total": 1.0599204301834106,
"lr": 0.0009367060360234475,
"router/selected_tokens_s0": 7452.875,
"router/selected_tokens_s1": 4282.125,
"step": 7580,
"tokens_trained": 24.830934064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1526132898376003,
"grad_norm": 0.08076012879610062,
"loss": 1.0553,
"loss_ce": 1.1044143438339233,
"loss_region": 0.05999838933348656,
"loss_total": 1.1644127368927002,
"lr": 0.0009362991440395965,
"router/selected_tokens_s0": 7389.875,
"router/selected_tokens_s1": 4254.375,
"step": 7590,
"tokens_trained": 24.863699504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1554499680873698,
"grad_norm": 0.10798979550600052,
"loss": 1.0623,
"loss_ce": 1.0324264764785767,
"loss_region": 0.06000140681862831,
"loss_total": 1.0924278497695923,
"lr": 0.0009358922520557453,
"router/selected_tokens_s0": 7404.25,
"router/selected_tokens_s1": 4272.75,
"step": 7600,
"tokens_trained": 24.896464928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1582866463371393,
"grad_norm": 0.06346011161804199,
"loss": 1.0697,
"loss_ce": 1.1126902103424072,
"loss_region": 0.05999580770730972,
"loss_total": 1.172685980796814,
"lr": 0.0009354853600718943,
"router/selected_tokens_s0": 7429.625,
"router/selected_tokens_s1": 4238.875,
"step": 7610,
"tokens_trained": 24.929227968
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.161123324586909,
"grad_norm": 0.07517693191766739,
"loss": 1.0654,
"loss_ce": 1.0678085088729858,
"loss_region": 0.060007259249687195,
"loss_total": 1.1278157234191895,
"lr": 0.0009350784680880434,
"router/selected_tokens_s0": 7375.375,
"router/selected_tokens_s1": 4282.875,
"step": 7620,
"tokens_trained": 24.961993408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1639600028366783,
"grad_norm": 0.1385023593902588,
"loss": 1.0686,
"loss_ce": 1.038794994354248,
"loss_region": 0.060001399368047714,
"loss_total": 1.0987963676452637,
"lr": 0.0009346715761041923,
"router/selected_tokens_s0": 7449.75,
"router/selected_tokens_s1": 4309.625,
"step": 7630,
"tokens_trained": 24.994758848
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.166796681086448,
"grad_norm": 0.12499692291021347,
"loss": 1.0615,
"loss_ce": 1.134606957435608,
"loss_region": 0.06000205874443054,
"loss_total": 1.1946090459823608,
"lr": 0.0009342646841203413,
"router/selected_tokens_s0": 7430.75,
"router/selected_tokens_s1": 4298.375,
"step": 7640,
"tokens_trained": 25.027524288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1696333593362174,
"grad_norm": 0.16676566004753113,
"loss": 1.0724,
"loss_ce": 0.8759081959724426,
"loss_region": 0.060003675520420074,
"loss_total": 0.9359118938446045,
"lr": 0.0009338577921364903,
"router/selected_tokens_s0": 7386.0,
"router/selected_tokens_s1": 4263.125,
"step": 7650,
"tokens_trained": 25.06028972
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.172470037585987,
"grad_norm": 0.1451634168624878,
"loss": 1.0642,
"loss_ce": 0.8085017204284668,
"loss_region": 0.06006048619747162,
"loss_total": 0.8685622215270996,
"lr": 0.0009334509001526392,
"router/selected_tokens_s0": 7334.75,
"router/selected_tokens_s1": 4194.0,
"step": 7660,
"tokens_trained": 25.09305516
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1753067158357564,
"grad_norm": 0.07147655636072159,
"loss": 1.0642,
"loss_ce": 1.1068609952926636,
"loss_region": 0.06000683829188347,
"loss_total": 1.1668678522109985,
"lr": 0.0009330440081687883,
"router/selected_tokens_s0": 7382.125,
"router/selected_tokens_s1": 4288.125,
"step": 7670,
"tokens_trained": 25.125817728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.178143394085526,
"grad_norm": 0.07307510077953339,
"loss": 1.068,
"loss_ce": 1.133186936378479,
"loss_region": 0.06001383066177368,
"loss_total": 1.1932008266448975,
"lr": 0.0009326371161849373,
"router/selected_tokens_s0": 7364.75,
"router/selected_tokens_s1": 4293.875,
"step": 7680,
"tokens_trained": 25.158583168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1809800723352954,
"grad_norm": 0.09967056661844254,
"loss": 1.0636,
"loss_ce": 1.1033625602722168,
"loss_region": 0.059995364397764206,
"loss_total": 1.1633579730987549,
"lr": 0.0009322302242010862,
"router/selected_tokens_s0": 7423.375,
"router/selected_tokens_s1": 4245.5,
"step": 7690,
"tokens_trained": 25.191341672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.183816750585065,
"grad_norm": 0.10262995958328247,
"loss": 1.0618,
"loss_ce": 0.9780526161193848,
"loss_region": 0.06000777333974838,
"loss_total": 1.0380604267120361,
"lr": 0.0009318233322172352,
"router/selected_tokens_s0": 7457.625,
"router/selected_tokens_s1": 4322.5,
"step": 7700,
"tokens_trained": 25.224107112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1866534288348345,
"grad_norm": 0.08990202844142914,
"loss": 1.0692,
"loss_ce": 1.038571834564209,
"loss_region": 0.06000371649861336,
"loss_total": 1.0985755920410156,
"lr": 0.0009314164402333842,
"router/selected_tokens_s0": 7422.0,
"router/selected_tokens_s1": 4297.0,
"step": 7710,
"tokens_trained": 25.256872552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.189490107084604,
"grad_norm": 0.07706000655889511,
"loss": 1.0667,
"loss_ce": 1.0372638702392578,
"loss_region": 0.05999591574072838,
"loss_total": 1.097259759902954,
"lr": 0.000931009548249533,
"router/selected_tokens_s0": 7437.625,
"router/selected_tokens_s1": 4269.25,
"step": 7720,
"tokens_trained": 25.289637992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1923267853343735,
"grad_norm": 0.08618722856044769,
"loss": 1.0628,
"loss_ce": 1.068077564239502,
"loss_region": 0.060001399368047714,
"loss_total": 1.1280789375305176,
"lr": 0.000930602656265682,
"router/selected_tokens_s0": 7391.75,
"router/selected_tokens_s1": 4263.75,
"step": 7730,
"tokens_trained": 25.322402632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.195163463584143,
"grad_norm": 0.14893005788326263,
"loss": 1.0646,
"loss_ce": 0.9990720152854919,
"loss_region": 0.060002293437719345,
"loss_total": 1.0590742826461792,
"lr": 0.000930195764281831,
"router/selected_tokens_s0": 7351.75,
"router/selected_tokens_s1": 4226.0,
"step": 7740,
"tokens_trained": 25.355165584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.1980001418339126,
"grad_norm": 0.10031340271234512,
"loss": 1.0704,
"loss_ce": 0.943006694316864,
"loss_region": 0.060008347034454346,
"loss_total": 1.0030150413513184,
"lr": 0.00092978887229798,
"router/selected_tokens_s0": 7386.125,
"router/selected_tokens_s1": 4292.125,
"step": 7750,
"tokens_trained": 25.387931024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.200836820083682,
"grad_norm": 0.06115954741835594,
"loss": 1.0593,
"loss_ce": 0.9749414324760437,
"loss_region": 0.05999942868947983,
"loss_total": 1.0349408388137817,
"lr": 0.000929381980314129,
"router/selected_tokens_s0": 7455.25,
"router/selected_tokens_s1": 4303.625,
"step": 7760,
"tokens_trained": 25.420695664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2036734983334516,
"grad_norm": 0.07545716315507889,
"loss": 1.0643,
"loss_ce": 0.9750471115112305,
"loss_region": 0.06000591441988945,
"loss_total": 1.035053014755249,
"lr": 0.000928975088330278,
"router/selected_tokens_s0": 7427.5,
"router/selected_tokens_s1": 4313.75,
"step": 7770,
"tokens_trained": 25.453461104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.206510176583221,
"grad_norm": 0.09267102926969528,
"loss": 1.0633,
"loss_ce": 1.0577032566070557,
"loss_region": 0.060004863888025284,
"loss_total": 1.1177080869674683,
"lr": 0.0009285681963464269,
"router/selected_tokens_s0": 7395.5,
"router/selected_tokens_s1": 4290.375,
"step": 7780,
"tokens_trained": 25.486226544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2093468548329906,
"grad_norm": 0.09359267354011536,
"loss": 1.0679,
"loss_ce": 0.8935257792472839,
"loss_region": 0.06000054255127907,
"loss_total": 0.9535263180732727,
"lr": 0.0009281613043625759,
"router/selected_tokens_s0": 7415.875,
"router/selected_tokens_s1": 4261.25,
"step": 7790,
"tokens_trained": 25.518991984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.21218353308276,
"grad_norm": 0.14112727344036102,
"loss": 1.0657,
"loss_ce": 0.8202201128005981,
"loss_region": 0.059999506920576096,
"loss_total": 0.8802196383476257,
"lr": 0.000927754412378725,
"router/selected_tokens_s0": 7408.75,
"router/selected_tokens_s1": 4247.25,
"step": 7800,
"tokens_trained": 25.551757424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2150202113325297,
"grad_norm": 0.09152037650346756,
"loss": 1.0671,
"loss_ce": 1.0103726387023926,
"loss_region": 0.05999613553285599,
"loss_total": 1.070368766784668,
"lr": 0.0009273475203948739,
"router/selected_tokens_s0": 7446.0,
"router/selected_tokens_s1": 4284.875,
"step": 7810,
"tokens_trained": 25.584522064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.217856889582299,
"grad_norm": 0.07887820154428482,
"loss": 1.0709,
"loss_ce": 1.094946265220642,
"loss_region": 0.0599982887506485,
"loss_total": 1.1549445390701294,
"lr": 0.0009269406284110229,
"router/selected_tokens_s0": 7361.75,
"router/selected_tokens_s1": 4215.75,
"step": 7820,
"tokens_trained": 25.617287344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2206935678320687,
"grad_norm": 0.07482978701591492,
"loss": 1.0653,
"loss_ce": 1.0106014013290405,
"loss_region": 0.059999577701091766,
"loss_total": 1.070600986480713,
"lr": 0.0009265337364271718,
"router/selected_tokens_s0": 7424.25,
"router/selected_tokens_s1": 4287.25,
"step": 7830,
"tokens_trained": 25.650052784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2235302460818382,
"grad_norm": 0.060630913823843,
"loss": 1.0643,
"loss_ce": 0.8532955646514893,
"loss_region": 0.060004934668540955,
"loss_total": 0.9133005142211914,
"lr": 0.0009261268444433207,
"router/selected_tokens_s0": 7419.125,
"router/selected_tokens_s1": 4301.125,
"step": 7840,
"tokens_trained": 25.682818224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2263669243316078,
"grad_norm": 0.1081499457359314,
"loss": 1.0658,
"loss_ce": 1.054540991783142,
"loss_region": 0.06000063568353653,
"loss_total": 1.1145416498184204,
"lr": 0.0009257199524594697,
"router/selected_tokens_s0": 7393.875,
"router/selected_tokens_s1": 4270.0,
"step": 7850,
"tokens_trained": 25.715583664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2292036025813773,
"grad_norm": 0.11165347695350647,
"loss": 1.0675,
"loss_ce": 0.9684391617774963,
"loss_region": 0.0600094199180603,
"loss_total": 1.0284485816955566,
"lr": 0.0009253130604756186,
"router/selected_tokens_s0": 7381.125,
"router/selected_tokens_s1": 4288.25,
"step": 7860,
"tokens_trained": 25.748349104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.232040280831147,
"grad_norm": 0.11471514403820038,
"loss": 1.0618,
"loss_ce": 0.9423663020133972,
"loss_region": 0.06000564247369766,
"loss_total": 1.002371907234192,
"lr": 0.0009249061684917677,
"router/selected_tokens_s0": 7354.375,
"router/selected_tokens_s1": 4260.625,
"step": 7870,
"tokens_trained": 25.781114544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2348769590809163,
"grad_norm": 0.08616702258586884,
"loss": 1.0568,
"loss_ce": 1.0355966091156006,
"loss_region": 0.06000853329896927,
"loss_total": 1.0956051349639893,
"lr": 0.0009244992765079167,
"router/selected_tokens_s0": 7475.5,
"router/selected_tokens_s1": 4341.5,
"step": 7880,
"tokens_trained": 25.813879984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.237713637330686,
"grad_norm": 0.09955234080553055,
"loss": 1.0637,
"loss_ce": 0.9721653461456299,
"loss_region": 0.06001753732562065,
"loss_total": 1.0321829319000244,
"lr": 0.0009240923845240656,
"router/selected_tokens_s0": 7451.625,
"router/selected_tokens_s1": 4340.875,
"step": 7890,
"tokens_trained": 25.846645424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2405503155804554,
"grad_norm": 0.07359630614519119,
"loss": 1.0617,
"loss_ce": 0.9473441243171692,
"loss_region": 0.0600101463496685,
"loss_total": 1.0073542594909668,
"lr": 0.0009236854925402146,
"router/selected_tokens_s0": 7386.25,
"router/selected_tokens_s1": 4292.875,
"step": 7900,
"tokens_trained": 25.879410864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.243386993830225,
"grad_norm": 0.09445139020681381,
"loss": 1.064,
"loss_ce": 1.011965036392212,
"loss_region": 0.06000087782740593,
"loss_total": 1.0719659328460693,
"lr": 0.0009232786005563636,
"router/selected_tokens_s0": 7392.125,
"router/selected_tokens_s1": 4271.25,
"step": 7910,
"tokens_trained": 25.912176304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2462236720799944,
"grad_norm": 0.05465928837656975,
"loss": 1.0572,
"loss_ce": 1.0671688318252563,
"loss_region": 0.05999647080898285,
"loss_total": 1.1271653175354004,
"lr": 0.0009228717085725126,
"router/selected_tokens_s0": 7432.375,
"router/selected_tokens_s1": 4276.375,
"step": 7920,
"tokens_trained": 25.944941744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.249060350329764,
"grad_norm": 0.060297515243291855,
"loss": 1.0578,
"loss_ce": 0.996216893196106,
"loss_region": 0.0600031316280365,
"loss_total": 1.0562200546264648,
"lr": 0.0009224648165886616,
"router/selected_tokens_s0": 7392.5,
"router/selected_tokens_s1": 4274.375,
"step": 7930,
"tokens_trained": 25.977707184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2518970285795334,
"grad_norm": 0.11160633713006973,
"loss": 1.0625,
"loss_ce": 1.0593509674072266,
"loss_region": 0.059995170682668686,
"loss_total": 1.1193461418151855,
"lr": 0.0009220579246048106,
"router/selected_tokens_s0": 7382.75,
"router/selected_tokens_s1": 4234.5,
"step": 7940,
"tokens_trained": 26.010471824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.254733706829303,
"grad_norm": 0.08213996887207031,
"loss": 1.0636,
"loss_ce": 0.9958966374397278,
"loss_region": 0.06001153588294983,
"loss_total": 1.055908203125,
"lr": 0.0009216510326209595,
"router/selected_tokens_s0": 7389.25,
"router/selected_tokens_s1": 4300.75,
"step": 7950,
"tokens_trained": 26.043237264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2575703850790725,
"grad_norm": 0.12535226345062256,
"loss": 1.0585,
"loss_ce": 1.0670008659362793,
"loss_region": 0.060003187507390976,
"loss_total": 1.1270040273666382,
"lr": 0.0009212441406371085,
"router/selected_tokens_s0": 7471.375,
"router/selected_tokens_s1": 4314.5,
"step": 7960,
"tokens_trained": 26.076002704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.260407063328842,
"grad_norm": 0.09521625936031342,
"loss": 1.0663,
"loss_ce": 0.9568244814872742,
"loss_region": 0.059986263513565063,
"loss_total": 1.0168107748031616,
"lr": 0.0009208372486532574,
"router/selected_tokens_s0": 7424.375,
"router/selected_tokens_s1": 4269.875,
"step": 7970,
"tokens_trained": 26.108768144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2632437415786115,
"grad_norm": 0.1134655624628067,
"loss": 1.063,
"loss_ce": 1.038812279701233,
"loss_region": 0.059999361634254456,
"loss_total": 1.0988116264343262,
"lr": 0.0009204303566694063,
"router/selected_tokens_s0": 7409.125,
"router/selected_tokens_s1": 4272.125,
"step": 7980,
"tokens_trained": 26.141533584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.266080419828381,
"grad_norm": 0.09075932949781418,
"loss": 1.0647,
"loss_ce": 0.9599190354347229,
"loss_region": 0.06002267077565193,
"loss_total": 1.0199416875839233,
"lr": 0.0009200234646855554,
"router/selected_tokens_s0": 7373.5,
"router/selected_tokens_s1": 4319.625,
"step": 7990,
"tokens_trained": 26.174299024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2689170980781506,
"grad_norm": 0.0673384889960289,
"loss": 1.054,
"loss_ce": 0.9738999009132385,
"loss_region": 0.059999220073223114,
"loss_total": 1.0338990688323975,
"lr": 0.0009196165727017044,
"router/selected_tokens_s0": 7463.375,
"router/selected_tokens_s1": 4269.375,
"step": 8000,
"tokens_trained": 26.207064464
},
{
"epoch": 2.2689170980781506,
"eval_ppl": 2.754127303226834,
"eval_runtime": 1.0212,
"step": 8000,
"tokens_trained": 26.207064464
},
{
"epoch": 2.2689170980781506,
"eval_F": 0.3358680365653567,
"eval_F_cds": 0.32883460886302185,
"eval_F_dig": 0.3228377216970076,
"eval_F_exon": 0.3363945150333375,
"eval_F_intron": 0.3369414292519282,
"eval_F_nig": 0.3380240930137892,
"eval_F_promoter": 0.3305992572271056,
"eval_F_utr": 0.3348192429591074,
"eval_G": 0.3438682406930392,
"eval_G_cds": 0.34103056366287066,
"eval_G_dig": 0.3056676485955934,
"eval_G_exon": 0.3462706262842286,
"eval_G_intron": 0.3448363649250059,
"eval_G_nig": 0.34470574228489287,
"eval_G_promoter": 0.3411262685489101,
"eval_G_utr": 0.3443868327900745,
"eval_avg_bp_per_token": 2.977359829253683,
"eval_bp_per_token/cds": 3.041042436067173,
"eval_bp_per_token/dig": 3.0975314617618586,
"eval_bp_per_token/exon": 2.9727000747943157,
"eval_bp_per_token/intron": 2.9678748684012635,
"eval_bp_per_token/nig": 2.958369005842451,
"eval_bp_per_token/promoter": 3.0248101837477774,
"eval_bp_per_token/utr": 2.9866861628443897,
"eval_ppl_cds": 3.318432024253968,
"eval_ppl_dig": 1.1105163039128156,
"eval_ppl_exon": 3.241143234233957,
"eval_ppl_intron": 2.8734801903701843,
"eval_ppl_nig": 2.573137410563195,
"eval_ppl_promoter": 2.988459127366735,
"eval_ppl_utr": 3.029647440548638,
"step": 8000,
"tokens_trained": 26.207064464
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.27175377632792,
"grad_norm": 0.12231134623289108,
"loss": 1.0562,
"loss_ce": 0.9975427985191345,
"loss_region": 0.05999762564897537,
"loss_total": 1.0575404167175293,
"lr": 0.0009192096807178533,
"router/selected_tokens_s0": 7380.125,
"router/selected_tokens_s1": 4252.25,
"step": 8010,
"tokens_trained": 26.239829904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2745904545776896,
"grad_norm": 0.08055052161216736,
"loss": 1.0577,
"loss_ce": 1.1121338605880737,
"loss_region": 0.060004789382219315,
"loss_total": 1.1721386909484863,
"lr": 0.0009188027887340023,
"router/selected_tokens_s0": 7379.375,
"router/selected_tokens_s1": 4277.375,
"step": 8020,
"tokens_trained": 26.272595344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.277427132827459,
"grad_norm": 0.09591927379369736,
"loss": 1.0528,
"loss_ce": 0.9205632209777832,
"loss_region": 0.0599990114569664,
"loss_total": 0.9805622100830078,
"lr": 0.0009183958967501513,
"router/selected_tokens_s0": 7414.0,
"router/selected_tokens_s1": 4271.375,
"step": 8030,
"tokens_trained": 26.305360784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2802638110772286,
"grad_norm": 0.11075546592473984,
"loss": 1.061,
"loss_ce": 1.0516383647918701,
"loss_region": 0.06000576540827751,
"loss_total": 1.1116441488265991,
"lr": 0.0009179890047663002,
"router/selected_tokens_s0": 7414.5,
"router/selected_tokens_s1": 4294.0,
"step": 8040,
"tokens_trained": 26.338126208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.283100489326998,
"grad_norm": 0.09984137862920761,
"loss": 1.0645,
"loss_ce": 0.9013442993164062,
"loss_region": 0.06000048667192459,
"loss_total": 0.9613447785377502,
"lr": 0.0009175821127824493,
"router/selected_tokens_s0": 7456.875,
"router/selected_tokens_s1": 4280.5,
"step": 8050,
"tokens_trained": 26.370891648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2859371675767677,
"grad_norm": 0.07570505142211914,
"loss": 1.062,
"loss_ce": 1.0161606073379517,
"loss_region": 0.05999864265322685,
"loss_total": 1.0761592388153076,
"lr": 0.0009171752207985983,
"router/selected_tokens_s0": 7415.0,
"router/selected_tokens_s1": 4264.75,
"step": 8060,
"tokens_trained": 26.403656288
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.288773845826537,
"grad_norm": 0.06136245280504227,
"loss": 1.0573,
"loss_ce": 0.9474148750305176,
"loss_region": 0.05999542027711868,
"loss_total": 1.0074102878570557,
"lr": 0.0009167683288147472,
"router/selected_tokens_s0": 7419.625,
"router/selected_tokens_s1": 4234.0,
"step": 8070,
"tokens_trained": 26.436421728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2916105240763067,
"grad_norm": 0.12230025231838226,
"loss": 1.059,
"loss_ce": 1.0230987071990967,
"loss_region": 0.059994686394929886,
"loss_total": 1.0830934047698975,
"lr": 0.0009163614368308962,
"router/selected_tokens_s0": 7427.0,
"router/selected_tokens_s1": 4254.375,
"step": 8080,
"tokens_trained": 26.469187168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2944472023260762,
"grad_norm": 0.10080068558454514,
"loss": 1.0537,
"loss_ce": 0.9321814775466919,
"loss_region": 0.0599973164498806,
"loss_total": 0.9921787977218628,
"lr": 0.000915954544847045,
"router/selected_tokens_s0": 7403.25,
"router/selected_tokens_s1": 4247.125,
"step": 8090,
"tokens_trained": 26.501951008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.2972838805758458,
"grad_norm": 0.073105588555336,
"loss": 1.0672,
"loss_ce": 1.0272918939590454,
"loss_region": 0.05999736115336418,
"loss_total": 1.0872892141342163,
"lr": 0.000915547652863194,
"router/selected_tokens_s0": 7454.5,
"router/selected_tokens_s1": 4261.5,
"step": 8100,
"tokens_trained": 26.534716448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3001205588256153,
"grad_norm": 0.06740695238113403,
"loss": 1.0552,
"loss_ce": 1.053105354309082,
"loss_region": 0.06000041216611862,
"loss_total": 1.1131057739257812,
"lr": 0.000915140760879343,
"router/selected_tokens_s0": 7447.25,
"router/selected_tokens_s1": 4282.625,
"step": 8110,
"tokens_trained": 26.5674814
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.302957237075385,
"grad_norm": 0.09442190825939178,
"loss": 1.0656,
"loss_ce": 1.0914051532745361,
"loss_region": 0.059995636343955994,
"loss_total": 1.1514008045196533,
"lr": 0.000914733868895492,
"router/selected_tokens_s0": 7415.0,
"router/selected_tokens_s1": 4259.375,
"step": 8120,
"tokens_trained": 26.60024684
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3057939153251543,
"grad_norm": 0.09779255837202072,
"loss": 1.0564,
"loss_ce": 1.083017349243164,
"loss_region": 0.059998348355293274,
"loss_total": 1.143015742301941,
"lr": 0.000914326976911641,
"router/selected_tokens_s0": 7457.125,
"router/selected_tokens_s1": 4291.125,
"step": 8130,
"tokens_trained": 26.633011272
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.308630593574924,
"grad_norm": 0.1056966781616211,
"loss": 1.0573,
"loss_ce": 0.931369423866272,
"loss_region": 0.05998814478516579,
"loss_total": 0.9913575649261475,
"lr": 0.00091392008492779,
"router/selected_tokens_s0": 7414.625,
"router/selected_tokens_s1": 4299.375,
"step": 8140,
"tokens_trained": 26.665774
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3114672718246934,
"grad_norm": 0.09716489166021347,
"loss": 1.0589,
"loss_ce": 1.0023393630981445,
"loss_region": 0.06001187860965729,
"loss_total": 1.0623512268066406,
"lr": 0.000913513192943939,
"router/selected_tokens_s0": 7344.875,
"router/selected_tokens_s1": 4269.5,
"step": 8150,
"tokens_trained": 26.69853944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.314303950074463,
"grad_norm": 0.11967064440250397,
"loss": 1.0593,
"loss_ce": 1.0250205993652344,
"loss_region": 0.06000397726893425,
"loss_total": 1.0850245952606201,
"lr": 0.0009131063009600879,
"router/selected_tokens_s0": 7420.125,
"router/selected_tokens_s1": 4292.375,
"step": 8160,
"tokens_trained": 26.73130488
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3171406283242324,
"grad_norm": 0.07524566352367401,
"loss": 1.0629,
"loss_ce": 0.9791299104690552,
"loss_region": 0.06000060588121414,
"loss_total": 1.0391305685043335,
"lr": 0.000912699408976237,
"router/selected_tokens_s0": 7456.625,
"router/selected_tokens_s1": 4279.25,
"step": 8170,
"tokens_trained": 26.76407032
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.319977306574002,
"grad_norm": 0.09677954018115997,
"loss": 1.0572,
"loss_ce": 1.0635145902633667,
"loss_region": 0.06001080572605133,
"loss_total": 1.1235253810882568,
"lr": 0.000912292516992386,
"router/selected_tokens_s0": 7425.125,
"router/selected_tokens_s1": 4309.75,
"step": 8180,
"tokens_trained": 26.79683576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3228139848237714,
"grad_norm": 0.08558879047632217,
"loss": 1.0633,
"loss_ce": 1.102909803390503,
"loss_region": 0.060004692524671555,
"loss_total": 1.162914514541626,
"lr": 0.0009118856250085349,
"router/selected_tokens_s0": 7407.25,
"router/selected_tokens_s1": 4298.25,
"step": 8190,
"tokens_trained": 26.8296012
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.325650663073541,
"grad_norm": 0.1450275331735611,
"loss": 1.0604,
"loss_ce": 1.0180364847183228,
"loss_region": 0.0600145123898983,
"loss_total": 1.078050971031189,
"lr": 0.0009114787330246839,
"router/selected_tokens_s0": 7394.875,
"router/selected_tokens_s1": 4304.875,
"step": 8200,
"tokens_trained": 26.86236568
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3284873413233105,
"grad_norm": 0.0971994549036026,
"loss": 1.0549,
"loss_ce": 0.9048692584037781,
"loss_region": 0.060006506741046906,
"loss_total": 0.9648757576942444,
"lr": 0.0009110718410408328,
"router/selected_tokens_s0": 7393.75,
"router/selected_tokens_s1": 4288.0,
"step": 8210,
"tokens_trained": 26.89513112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.33132401957308,
"grad_norm": 0.09337711334228516,
"loss": 1.0525,
"loss_ce": 0.9577232599258423,
"loss_region": 0.06000382453203201,
"loss_total": 1.0177271366119385,
"lr": 0.0009106649490569817,
"router/selected_tokens_s0": 7372.875,
"router/selected_tokens_s1": 4256.25,
"step": 8220,
"tokens_trained": 26.92789576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3341606978228495,
"grad_norm": 0.07152654230594635,
"loss": 1.0571,
"loss_ce": 0.9388102889060974,
"loss_region": 0.060004305094480515,
"loss_total": 0.998814582824707,
"lr": 0.0009102580570731307,
"router/selected_tokens_s0": 7412.875,
"router/selected_tokens_s1": 4286.625,
"step": 8230,
"tokens_trained": 26.9606612
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.336997376072619,
"grad_norm": 0.1019396185874939,
"loss": 1.057,
"loss_ce": 1.048132061958313,
"loss_region": 0.059996627271175385,
"loss_total": 1.1081286668777466,
"lr": 0.0009098511650892797,
"router/selected_tokens_s0": 7413.375,
"router/selected_tokens_s1": 4258.625,
"step": 8240,
"tokens_trained": 26.99342664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3398340543223886,
"grad_norm": 0.0851474180817604,
"loss": 1.0608,
"loss_ce": 0.8752225041389465,
"loss_region": 0.06000366061925888,
"loss_total": 0.9352261424064636,
"lr": 0.0009094442731054287,
"router/selected_tokens_s0": 7397.625,
"router/selected_tokens_s1": 4267.125,
"step": 8250,
"tokens_trained": 27.02619208
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.342670732572158,
"grad_norm": 0.1310846209526062,
"loss": 1.0627,
"loss_ce": 0.8542342185974121,
"loss_region": 0.06000632792711258,
"loss_total": 0.9142405390739441,
"lr": 0.0009090373811215777,
"router/selected_tokens_s0": 7411.625,
"router/selected_tokens_s1": 4283.0,
"step": 8260,
"tokens_trained": 27.05895752
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3455074108219276,
"grad_norm": 0.12587329745292664,
"loss": 1.0562,
"loss_ce": 0.9656789302825928,
"loss_region": 0.060002002865076065,
"loss_total": 1.0256808996200562,
"lr": 0.0009086304891377266,
"router/selected_tokens_s0": 7434.625,
"router/selected_tokens_s1": 4295.125,
"step": 8270,
"tokens_trained": 27.09172296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.348344089071697,
"grad_norm": 0.07155922055244446,
"loss": 1.0604,
"loss_ce": 0.9499186873435974,
"loss_region": 0.05999379605054855,
"loss_total": 1.0099124908447266,
"lr": 0.0009082235971538756,
"router/selected_tokens_s0": 7428.0,
"router/selected_tokens_s1": 4259.125,
"step": 8280,
"tokens_trained": 27.1244884
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3511807673214666,
"grad_norm": 0.09406653046607971,
"loss": 1.0513,
"loss_ce": 0.9733015894889832,
"loss_region": 0.06000078469514847,
"loss_total": 1.0333024263381958,
"lr": 0.0009078167051700246,
"router/selected_tokens_s0": 7426.125,
"router/selected_tokens_s1": 4277.625,
"step": 8290,
"tokens_trained": 27.15725384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.354017445571236,
"grad_norm": 0.08878457546234131,
"loss": 1.0544,
"loss_ce": 1.0448791980743408,
"loss_region": 0.0600077249109745,
"loss_total": 1.1048868894577026,
"lr": 0.0009074098131861736,
"router/selected_tokens_s0": 7380.625,
"router/selected_tokens_s1": 4254.75,
"step": 8300,
"tokens_trained": 27.19001928
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3568541238210057,
"grad_norm": 0.08128737658262253,
"loss": 1.0589,
"loss_ce": 1.0410749912261963,
"loss_region": 0.05999433994293213,
"loss_total": 1.1010693311691284,
"lr": 0.0009070029212023226,
"router/selected_tokens_s0": 7437.875,
"router/selected_tokens_s1": 4243.375,
"step": 8310,
"tokens_trained": 27.22278472
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.359690802070775,
"grad_norm": 0.14990991353988647,
"loss": 1.0583,
"loss_ce": 1.0307172536849976,
"loss_region": 0.06000310927629471,
"loss_total": 1.0907204151153564,
"lr": 0.0009065960292184716,
"router/selected_tokens_s0": 7408.875,
"router/selected_tokens_s1": 4284.125,
"step": 8320,
"tokens_trained": 27.25555016
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3625274803205447,
"grad_norm": 0.08982635289430618,
"loss": 1.054,
"loss_ce": 1.0846338272094727,
"loss_region": 0.06000533327460289,
"loss_total": 1.1446391344070435,
"lr": 0.0009061891372346205,
"router/selected_tokens_s0": 7436.625,
"router/selected_tokens_s1": 4314.375,
"step": 8330,
"tokens_trained": 27.2883156
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3653641585703142,
"grad_norm": 0.11252354085445404,
"loss": 1.0536,
"loss_ce": 0.9864820837974548,
"loss_region": 0.06000399589538574,
"loss_total": 1.0464861392974854,
"lr": 0.0009057822452507694,
"router/selected_tokens_s0": 7402.125,
"router/selected_tokens_s1": 4284.25,
"step": 8340,
"tokens_trained": 27.32108104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3682008368200838,
"grad_norm": 0.09558703005313873,
"loss": 1.0559,
"loss_ce": 1.0942038297653198,
"loss_region": 0.0599936842918396,
"loss_total": 1.1541974544525146,
"lr": 0.0009053753532669184,
"router/selected_tokens_s0": 7449.5,
"router/selected_tokens_s1": 4267.625,
"step": 8350,
"tokens_trained": 27.35384648
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3710375150698533,
"grad_norm": 0.08678382635116577,
"loss": 1.0571,
"loss_ce": 0.9340338110923767,
"loss_region": 0.06000067666172981,
"loss_total": 0.994034469127655,
"lr": 0.0009049684612830673,
"router/selected_tokens_s0": 7452.375,
"router/selected_tokens_s1": 4290.875,
"step": 8360,
"tokens_trained": 27.386609784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.373874193319623,
"grad_norm": 0.09878090023994446,
"loss": 1.0601,
"loss_ce": 0.9702523350715637,
"loss_region": 0.060000043362379074,
"loss_total": 1.0302523374557495,
"lr": 0.0009045615692992164,
"router/selected_tokens_s0": 7392.0,
"router/selected_tokens_s1": 4262.375,
"step": 8370,
"tokens_trained": 27.419375224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3767108715693923,
"grad_norm": 0.08482500910758972,
"loss": 1.0653,
"loss_ce": 0.9229720234870911,
"loss_region": 0.059997960925102234,
"loss_total": 0.9829699993133545,
"lr": 0.0009041546773153654,
"router/selected_tokens_s0": 7337.125,
"router/selected_tokens_s1": 4221.25,
"step": 8380,
"tokens_trained": 27.452140664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.379547549819162,
"grad_norm": 0.14045023918151855,
"loss": 1.0586,
"loss_ce": 1.0012965202331543,
"loss_region": 0.06000533327460289,
"loss_total": 1.061301827430725,
"lr": 0.0009037477853315143,
"router/selected_tokens_s0": 7421.125,
"router/selected_tokens_s1": 4302.25,
"step": 8390,
"tokens_trained": 27.484904504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3823842280689314,
"grad_norm": 0.07333158701658249,
"loss": 1.0632,
"loss_ce": 1.0295556783676147,
"loss_region": 0.060006577521562576,
"loss_total": 1.0895622968673706,
"lr": 0.0009033408933476633,
"router/selected_tokens_s0": 7440.5,
"router/selected_tokens_s1": 4315.375,
"step": 8400,
"tokens_trained": 27.517669944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.385220906318701,
"grad_norm": 0.08430515229701996,
"loss": 1.0553,
"loss_ce": 1.0218313932418823,
"loss_region": 0.05999813973903656,
"loss_total": 1.08182954788208,
"lr": 0.0009029340013638123,
"router/selected_tokens_s0": 7353.875,
"router/selected_tokens_s1": 4234.0,
"step": 8410,
"tokens_trained": 27.550435384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3880575845684704,
"grad_norm": 0.1045287624001503,
"loss": 1.0597,
"loss_ce": 0.8894641399383545,
"loss_region": 0.06000156328082085,
"loss_total": 0.9494656920433044,
"lr": 0.0009025271093799613,
"router/selected_tokens_s0": 7369.625,
"router/selected_tokens_s1": 4292.0,
"step": 8420,
"tokens_trained": 27.583198336
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.39089426281824,
"grad_norm": 0.10882244259119034,
"loss": 1.0545,
"loss_ce": 0.9567221999168396,
"loss_region": 0.05999777466058731,
"loss_total": 1.016719937324524,
"lr": 0.0009021202173961103,
"router/selected_tokens_s0": 7478.125,
"router/selected_tokens_s1": 4277.875,
"step": 8430,
"tokens_trained": 27.615963616
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3937309410680094,
"grad_norm": 0.08376454561948776,
"loss": 1.0607,
"loss_ce": 0.9995729923248291,
"loss_region": 0.05999734625220299,
"loss_total": 1.0595703125,
"lr": 0.0009017133254122593,
"router/selected_tokens_s0": 7459.125,
"router/selected_tokens_s1": 4281.75,
"step": 8440,
"tokens_trained": 27.648725192
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.396567619317779,
"grad_norm": 0.10345184803009033,
"loss": 1.0598,
"loss_ce": 0.9711935520172119,
"loss_region": 0.05999723821878433,
"loss_total": 1.0311907529830933,
"lr": 0.0009013064334284082,
"router/selected_tokens_s0": 7377.375,
"router/selected_tokens_s1": 4241.875,
"step": 8450,
"tokens_trained": 27.681490632
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.3994042975675485,
"grad_norm": 0.08357074856758118,
"loss": 1.0489,
"loss_ce": 0.9034456610679626,
"loss_region": 0.06000221520662308,
"loss_total": 0.9634478688240051,
"lr": 0.0009008995414445572,
"router/selected_tokens_s0": 7427.25,
"router/selected_tokens_s1": 4293.0,
"step": 8460,
"tokens_trained": 27.714256072
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.402240975817318,
"grad_norm": 0.09288746863603592,
"loss": 1.0598,
"loss_ce": 1.0702778100967407,
"loss_region": 0.05999256670475006,
"loss_total": 1.1302703619003296,
"lr": 0.000900492649460706,
"router/selected_tokens_s0": 7414.25,
"router/selected_tokens_s1": 4245.5,
"step": 8470,
"tokens_trained": 27.747021512
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4050776540670875,
"grad_norm": 0.11204234510660172,
"loss": 1.0492,
"loss_ce": 1.0531384944915771,
"loss_region": 0.05999329686164856,
"loss_total": 1.1131317615509033,
"lr": 0.000900085757476855,
"router/selected_tokens_s0": 7426.375,
"router/selected_tokens_s1": 4250.5,
"step": 8480,
"tokens_trained": 27.779786952
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.407914332316857,
"grad_norm": 0.07378879934549332,
"loss": 1.0592,
"loss_ce": 1.143384575843811,
"loss_region": 0.06000464782118797,
"loss_total": 1.2033891677856445,
"lr": 0.0008996788654930041,
"router/selected_tokens_s0": 7419.0,
"router/selected_tokens_s1": 4290.125,
"step": 8490,
"tokens_trained": 27.812552392
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4107510105666266,
"grad_norm": 0.07602507621049881,
"loss": 1.054,
"loss_ce": 0.9728952050209045,
"loss_region": 0.05999796837568283,
"loss_total": 1.032893180847168,
"lr": 0.0008992719735091531,
"router/selected_tokens_s0": 7366.375,
"router/selected_tokens_s1": 4244.625,
"step": 8500,
"tokens_trained": 27.845317832
},
{
"epoch": 2.4107510105666266,
"eval_ppl": 2.7353563129661476,
"eval_runtime": 1.0242,
"step": 8500,
"tokens_trained": 27.845317832
},
{
"epoch": 2.4107510105666266,
"eval_F": 0.3339355939266089,
"eval_F_cds": 0.32580999954172585,
"eval_F_dig": 0.31799359324947263,
"eval_F_exon": 0.3340042772675808,
"eval_F_intron": 0.33525900250336993,
"eval_F_nig": 0.33602694245153414,
"eval_F_promoter": 0.32815445197170745,
"eval_F_utr": 0.33298977041407923,
"eval_G": 0.34417926963084683,
"eval_G_cds": 0.34153050315636313,
"eval_G_dig": 0.30210047537893586,
"eval_G_exon": 0.34643828036545476,
"eval_G_intron": 0.34527678432674214,
"eval_G_nig": 0.34516020310790657,
"eval_G_promoter": 0.34088548592254075,
"eval_G_utr": 0.3447772665489964,
"eval_avg_bp_per_token": 2.9945894303791296,
"eval_bp_per_token/cds": 3.069273507278993,
"eval_bp_per_token/dig": 3.1447174447174446,
"eval_bp_per_token/exon": 2.9939736346516006,
"eval_bp_per_token/intron": 2.9827685238368753,
"eval_bp_per_token/nig": 2.9759518469095143,
"eval_bp_per_token/promoter": 3.0473455227912534,
"eval_bp_per_token/utr": 3.003095256519384,
"eval_ppl_cds": 3.2651534127504553,
"eval_ppl_dig": 1.1102873279172925,
"eval_ppl_exon": 3.2467158647548793,
"eval_ppl_intron": 2.863752192690005,
"eval_ppl_nig": 2.5461023597898556,
"eval_ppl_promoter": 2.9017922324048033,
"eval_ppl_utr": 2.9731277746153,
"step": 8500,
"tokens_trained": 27.845317832
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.413587688816396,
"grad_norm": 0.0890352874994278,
"loss": 1.056,
"loss_ce": 0.8717209696769714,
"loss_region": 0.059997204691171646,
"loss_total": 0.9317181706428528,
"lr": 0.000898865081525302,
"router/selected_tokens_s0": 7415.0,
"router/selected_tokens_s1": 4265.25,
"step": 8510,
"tokens_trained": 27.878081672
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4164243670661656,
"grad_norm": 0.10223552584648132,
"loss": 1.0517,
"loss_ce": 1.022995114326477,
"loss_region": 0.05999619513750076,
"loss_total": 1.082991361618042,
"lr": 0.000898458189541451,
"router/selected_tokens_s0": 7418.375,
"router/selected_tokens_s1": 4260.375,
"step": 8520,
"tokens_trained": 27.910847112
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.419261045315935,
"grad_norm": 0.07929608225822449,
"loss": 1.0561,
"loss_ce": 0.8792555332183838,
"loss_region": 0.059996481984853745,
"loss_total": 0.9392520189285278,
"lr": 0.0008980512975576,
"router/selected_tokens_s0": 7442.875,
"router/selected_tokens_s1": 4277.375,
"step": 8530,
"tokens_trained": 27.943612552
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4220977235657046,
"grad_norm": 0.08173707127571106,
"loss": 1.0565,
"loss_ce": 1.0021259784698486,
"loss_region": 0.0599919818341732,
"loss_total": 1.0621179342269897,
"lr": 0.0008976444055737489,
"router/selected_tokens_s0": 7401.75,
"router/selected_tokens_s1": 4235.75,
"step": 8540,
"tokens_trained": 27.976377992
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.424934401815474,
"grad_norm": 0.09709572046995163,
"loss": 1.0557,
"loss_ce": 0.890242338180542,
"loss_region": 0.059995055198669434,
"loss_total": 0.9502373933792114,
"lr": 0.000897237513589898,
"router/selected_tokens_s0": 7385.625,
"router/selected_tokens_s1": 4234.375,
"step": 8550,
"tokens_trained": 28.009141296
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4277710800652437,
"grad_norm": 0.103042833507061,
"loss": 1.0581,
"loss_ce": 1.0838439464569092,
"loss_region": 0.05999678373336792,
"loss_total": 1.1438407897949219,
"lr": 0.000896830621606047,
"router/selected_tokens_s0": 7459.25,
"router/selected_tokens_s1": 4277.625,
"step": 8560,
"tokens_trained": 28.041906736
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.430607758315013,
"grad_norm": 0.08488387614488602,
"loss": 1.0616,
"loss_ce": 1.0874125957489014,
"loss_region": 0.059994734823703766,
"loss_total": 1.1474072933197021,
"lr": 0.0008964237296221959,
"router/selected_tokens_s0": 7402.375,
"router/selected_tokens_s1": 4249.125,
"step": 8570,
"tokens_trained": 28.074672176
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4334444365647827,
"grad_norm": 0.07600562274456024,
"loss": 1.0523,
"loss_ce": 1.0529037714004517,
"loss_region": 0.059999555349349976,
"loss_total": 1.112903356552124,
"lr": 0.0008960168376383449,
"router/selected_tokens_s0": 7401.875,
"router/selected_tokens_s1": 4268.875,
"step": 8580,
"tokens_trained": 28.107436008
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4362811148145522,
"grad_norm": 0.07200396806001663,
"loss": 1.055,
"loss_ce": 0.9904854893684387,
"loss_region": 0.05999687686562538,
"loss_total": 1.0504823923110962,
"lr": 0.0008956099456544937,
"router/selected_tokens_s0": 7439.375,
"router/selected_tokens_s1": 4280.625,
"step": 8590,
"tokens_trained": 28.140201448
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4391177930643217,
"grad_norm": 0.1327984780073166,
"loss": 1.052,
"loss_ce": 1.0562522411346436,
"loss_region": 0.05999882519245148,
"loss_total": 1.1162511110305786,
"lr": 0.0008952030536706427,
"router/selected_tokens_s0": 7396.25,
"router/selected_tokens_s1": 4266.125,
"step": 8600,
"tokens_trained": 28.172966888
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4419544713140913,
"grad_norm": 0.10581366717815399,
"loss": 1.0577,
"loss_ce": 0.9608261585235596,
"loss_region": 0.05999242514371872,
"loss_total": 1.0208185911178589,
"lr": 0.0008947961616867917,
"router/selected_tokens_s0": 7394.25,
"router/selected_tokens_s1": 4226.0,
"step": 8610,
"tokens_trained": 28.205730728
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.444791149563861,
"grad_norm": 0.09172872453927994,
"loss": 1.0561,
"loss_ce": 1.1066234111785889,
"loss_region": 0.06000348925590515,
"loss_total": 1.1666269302368164,
"lr": 0.0008943892697029407,
"router/selected_tokens_s0": 7435.0,
"router/selected_tokens_s1": 4288.0,
"step": 8620,
"tokens_trained": 28.238496168
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4476278278136303,
"grad_norm": 0.11657129973173141,
"loss": 1.0539,
"loss_ce": 1.0094045400619507,
"loss_region": 0.05999579280614853,
"loss_total": 1.0694003105163574,
"lr": 0.0008939823777190897,
"router/selected_tokens_s0": 7382.375,
"router/selected_tokens_s1": 4243.5,
"step": 8630,
"tokens_trained": 28.271258408
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4504645060634,
"grad_norm": 0.1171703115105629,
"loss": 1.0581,
"loss_ce": 1.1134108304977417,
"loss_region": 0.0599915012717247,
"loss_total": 1.1734023094177246,
"lr": 0.0008935754857352387,
"router/selected_tokens_s0": 7397.0,
"router/selected_tokens_s1": 4215.625,
"step": 8640,
"tokens_trained": 28.304020264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4533011843131693,
"grad_norm": 0.0931129977107048,
"loss": 1.0551,
"loss_ce": 1.0483548641204834,
"loss_region": 0.05999862402677536,
"loss_total": 1.1083534955978394,
"lr": 0.0008931685937513876,
"router/selected_tokens_s0": 7403.0,
"router/selected_tokens_s1": 4250.625,
"step": 8650,
"tokens_trained": 28.336784904
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.456137862562939,
"grad_norm": 0.10282409936189651,
"loss": 1.0556,
"loss_ce": 1.0182043313980103,
"loss_region": 0.05999889597296715,
"loss_total": 1.0782032012939453,
"lr": 0.0008927617017675366,
"router/selected_tokens_s0": 7410.75,
"router/selected_tokens_s1": 4262.625,
"step": 8660,
"tokens_trained": 28.369550344
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4589745408127084,
"grad_norm": 0.08674661070108414,
"loss": 1.0529,
"loss_ce": 1.028585433959961,
"loss_region": 0.05999217554926872,
"loss_total": 1.0885776281356812,
"lr": 0.0008923548097836857,
"router/selected_tokens_s0": 7433.75,
"router/selected_tokens_s1": 4253.375,
"step": 8670,
"tokens_trained": 28.402315784
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.461811219062478,
"grad_norm": 0.10035062581300735,
"loss": 1.057,
"loss_ce": 0.9080606698989868,
"loss_region": 0.05999957025051117,
"loss_total": 0.9680602550506592,
"lr": 0.0008919479177998346,
"router/selected_tokens_s0": 7416.5,
"router/selected_tokens_s1": 4270.375,
"step": 8680,
"tokens_trained": 28.435081224
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4646478973122474,
"grad_norm": 0.06010536104440689,
"loss": 1.0518,
"loss_ce": 1.0172017812728882,
"loss_region": 0.06000963971018791,
"loss_total": 1.0772113800048828,
"lr": 0.0008915410258159836,
"router/selected_tokens_s0": 7396.125,
"router/selected_tokens_s1": 4298.625,
"step": 8690,
"tokens_trained": 28.467846664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.467484575562017,
"grad_norm": 0.1024271696805954,
"loss": 1.0586,
"loss_ce": 1.0059974193572998,
"loss_region": 0.05999946594238281,
"loss_total": 1.0659968852996826,
"lr": 0.0008911341338321326,
"router/selected_tokens_s0": 7422.75,
"router/selected_tokens_s1": 4281.125,
"step": 8700,
"tokens_trained": 28.500612104
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4703212538117865,
"grad_norm": 0.09084313362836838,
"loss": 1.0477,
"loss_ce": 1.0958322286605835,
"loss_region": 0.06000053510069847,
"loss_total": 1.1558327674865723,
"lr": 0.0008907272418482815,
"router/selected_tokens_s0": 7403.875,
"router/selected_tokens_s1": 4275.0,
"step": 8710,
"tokens_trained": 28.533377544
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.473157932061556,
"grad_norm": 0.09956429153680801,
"loss": 1.0578,
"loss_ce": 1.1075488328933716,
"loss_region": 0.059996794909238815,
"loss_total": 1.1675456762313843,
"lr": 0.0008903203498644304,
"router/selected_tokens_s0": 7410.125,
"router/selected_tokens_s1": 4261.375,
"step": 8720,
"tokens_trained": 28.566141984
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4759946103113255,
"grad_norm": 0.07981985062360764,
"loss": 1.0495,
"loss_ce": 1.1032137870788574,
"loss_region": 0.06000319495797157,
"loss_total": 1.1632169485092163,
"lr": 0.0008899134578805794,
"router/selected_tokens_s0": 7392.125,
"router/selected_tokens_s1": 4270.375,
"step": 8730,
"tokens_trained": 28.598907424
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.478831288561095,
"grad_norm": 0.08922786265611649,
"loss": 1.0549,
"loss_ce": 0.8978429436683655,
"loss_region": 0.060004547238349915,
"loss_total": 0.9578474760055542,
"lr": 0.0008895065658967284,
"router/selected_tokens_s0": 7302.125,
"router/selected_tokens_s1": 4239.125,
"step": 8740,
"tokens_trained": 28.631672864
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4816679668108645,
"grad_norm": 0.1105889230966568,
"loss": 1.0617,
"loss_ce": 1.044762134552002,
"loss_region": 0.060012366622686386,
"loss_total": 1.1047744750976562,
"lr": 0.0008890996739128774,
"router/selected_tokens_s0": 7422.625,
"router/selected_tokens_s1": 4317.125,
"step": 8750,
"tokens_trained": 28.664438304
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.484504645060634,
"grad_norm": 0.11524499952793121,
"loss": 1.0444,
"loss_ce": 1.0382664203643799,
"loss_region": 0.06000260263681412,
"loss_total": 1.098268985748291,
"lr": 0.0008886927819290264,
"router/selected_tokens_s0": 7386.0,
"router/selected_tokens_s1": 4268.75,
"step": 8760,
"tokens_trained": 28.697203744
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4873413233104036,
"grad_norm": 0.11217573285102844,
"loss": 1.0526,
"loss_ce": 0.9426054954528809,
"loss_region": 0.059998948127031326,
"loss_total": 1.0026044845581055,
"lr": 0.0008882858899451753,
"router/selected_tokens_s0": 7367.375,
"router/selected_tokens_s1": 4257.5,
"step": 8770,
"tokens_trained": 28.729969184
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.490178001560173,
"grad_norm": 0.09291733801364899,
"loss": 1.0554,
"loss_ce": 1.0549249649047852,
"loss_region": 0.06003744900226593,
"loss_total": 1.1149624586105347,
"lr": 0.0008878789979613243,
"router/selected_tokens_s0": 7397.75,
"router/selected_tokens_s1": 4349.25,
"step": 8780,
"tokens_trained": 28.762734624
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4930146798099426,
"grad_norm": 0.07984460145235062,
"loss": 1.0505,
"loss_ce": 1.01552414894104,
"loss_region": 0.05999819189310074,
"loss_total": 1.0755223035812378,
"lr": 0.0008874721059774733,
"router/selected_tokens_s0": 7407.125,
"router/selected_tokens_s1": 4255.75,
"step": 8790,
"tokens_trained": 28.795500064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.495851358059712,
"grad_norm": 0.14549370110034943,
"loss": 1.0546,
"loss_ce": 0.9735129475593567,
"loss_region": 0.05998510867357254,
"loss_total": 1.0334980487823486,
"lr": 0.0008870652139936223,
"router/selected_tokens_s0": 7398.625,
"router/selected_tokens_s1": 4285.625,
"step": 8800,
"tokens_trained": 28.828265504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.4986880363094817,
"grad_norm": 0.10017771273851395,
"loss": 1.0547,
"loss_ce": 0.7661262154579163,
"loss_region": 0.05999436974525452,
"loss_total": 0.8261206150054932,
"lr": 0.0008866583220097713,
"router/selected_tokens_s0": 7422.0,
"router/selected_tokens_s1": 4255.625,
"step": 8810,
"tokens_trained": 28.861030944
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.501524714559251,
"grad_norm": 0.0791676864027977,
"loss": 1.0558,
"loss_ce": 0.8253862857818604,
"loss_region": 0.05999884754419327,
"loss_total": 0.8853851556777954,
"lr": 0.0008862514300259203,
"router/selected_tokens_s0": 7395.5,
"router/selected_tokens_s1": 4261.0,
"step": 8820,
"tokens_trained": 28.893796384
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5043613928090207,
"grad_norm": 0.0699949711561203,
"loss": 1.0561,
"loss_ce": 1.0247315168380737,
"loss_region": 0.06000084429979324,
"loss_total": 1.0847324132919312,
"lr": 0.0008858445380420692,
"router/selected_tokens_s0": 7448.125,
"router/selected_tokens_s1": 4285.25,
"step": 8830,
"tokens_trained": 28.926561824
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5071980710587902,
"grad_norm": 0.1134558767080307,
"loss": 1.0605,
"loss_ce": 1.0843263864517212,
"loss_region": 0.06000571325421333,
"loss_total": 1.1443320512771606,
"lr": 0.0008854376460582181,
"router/selected_tokens_s0": 7421.875,
"router/selected_tokens_s1": 4288.625,
"step": 8840,
"tokens_trained": 28.959327264
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5100347493085597,
"grad_norm": 0.07717236131429672,
"loss": 1.0467,
"loss_ce": 0.9929010272026062,
"loss_region": 0.06002375856041908,
"loss_total": 1.0529247522354126,
"lr": 0.000885030754074367,
"router/selected_tokens_s0": 7356.125,
"router/selected_tokens_s1": 4301.625,
"step": 8850,
"tokens_trained": 28.992092704
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5128714275583293,
"grad_norm": 0.10177972167730331,
"loss": 1.0577,
"loss_ce": 1.1059026718139648,
"loss_region": 0.06001473218202591,
"loss_total": 1.1659173965454102,
"lr": 0.000884623862090516,
"router/selected_tokens_s0": 7414.25,
"router/selected_tokens_s1": 4308.75,
"step": 8860,
"tokens_trained": 29.024858144
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.515708105808099,
"grad_norm": 0.06407687813043594,
"loss": 1.0539,
"loss_ce": 1.0892680883407593,
"loss_region": 0.059991251677274704,
"loss_total": 1.149259328842163,
"lr": 0.0008842169701066651,
"router/selected_tokens_s0": 7435.0,
"router/selected_tokens_s1": 4263.0,
"step": 8870,
"tokens_trained": 29.057623584
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5185447840578683,
"grad_norm": 0.09954580664634705,
"loss": 1.0534,
"loss_ce": 0.8777329921722412,
"loss_region": 0.060006193816661835,
"loss_total": 0.9377391934394836,
"lr": 0.0008838100781228141,
"router/selected_tokens_s0": 7430.375,
"router/selected_tokens_s1": 4296.25,
"step": 8880,
"tokens_trained": 29.090389024
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.521381462307638,
"grad_norm": 0.10266491025686264,
"loss": 1.0446,
"loss_ce": 1.1141995191574097,
"loss_region": 0.060007236897945404,
"loss_total": 1.1742067337036133,
"lr": 0.000883403186138963,
"router/selected_tokens_s0": 7403.0,
"router/selected_tokens_s1": 4294.625,
"step": 8890,
"tokens_trained": 29.123153664
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5242181405574073,
"grad_norm": 0.09132856875658035,
"loss": 1.0464,
"loss_ce": 1.117302417755127,
"loss_region": 0.05999713018536568,
"loss_total": 1.1772994995117188,
"lr": 0.000882996294155112,
"router/selected_tokens_s0": 7382.375,
"router/selected_tokens_s1": 4240.25,
"step": 8900,
"tokens_trained": 29.155917496
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.527054818807177,
"grad_norm": 0.08423041552305222,
"loss": 1.0514,
"loss_ce": 1.1031696796417236,
"loss_region": 0.06001175567507744,
"loss_total": 1.1631814241409302,
"lr": 0.000882589402171261,
"router/selected_tokens_s0": 7401.75,
"router/selected_tokens_s1": 4303.25,
"step": 8910,
"tokens_trained": 29.188682936
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5298914970569464,
"grad_norm": 0.12287457287311554,
"loss": 1.0485,
"loss_ce": 0.8693131804466248,
"loss_region": 0.06000253185629845,
"loss_total": 0.9293156862258911,
"lr": 0.00088218251018741,
"router/selected_tokens_s0": 7403.0,
"router/selected_tokens_s1": 4264.625,
"step": 8920,
"tokens_trained": 29.221448376
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.532728175306716,
"grad_norm": 0.09478288888931274,
"loss": 1.0539,
"loss_ce": 1.0362886190414429,
"loss_region": 0.05999806895852089,
"loss_total": 1.096286654472351,
"lr": 0.000881775618203559,
"router/selected_tokens_s0": 7375.875,
"router/selected_tokens_s1": 4248.375,
"step": 8930,
"tokens_trained": 29.254213816
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5355648535564854,
"grad_norm": 0.06375641375780106,
"loss": 1.0485,
"loss_ce": 1.0071486234664917,
"loss_region": 0.06001626327633858,
"loss_total": 1.0671648979187012,
"lr": 0.000881368726219708,
"router/selected_tokens_s0": 7397.25,
"router/selected_tokens_s1": 4307.5,
"step": 8940,
"tokens_trained": 29.286979256
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.538401531806255,
"grad_norm": 0.12006037682294846,
"loss": 1.0391,
"loss_ce": 0.9393020272254944,
"loss_region": 0.060008224099874496,
"loss_total": 0.9993102550506592,
"lr": 0.0008809618342358569,
"router/selected_tokens_s0": 7438.875,
"router/selected_tokens_s1": 4308.375,
"step": 8950,
"tokens_trained": 29.319744696
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5412382100560245,
"grad_norm": 0.08267606049776077,
"loss": 1.0516,
"loss_ce": 1.027431607246399,
"loss_region": 0.05999532714486122,
"loss_total": 1.0874269008636475,
"lr": 0.0008805549422520058,
"router/selected_tokens_s0": 7441.0,
"router/selected_tokens_s1": 4274.125,
"step": 8960,
"tokens_trained": 29.352510136
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.544074888305794,
"grad_norm": 0.1047692596912384,
"loss": 1.0568,
"loss_ce": 0.9955906271934509,
"loss_region": 0.05999518185853958,
"loss_total": 1.0555858612060547,
"lr": 0.0008801480502681547,
"router/selected_tokens_s0": 7389.25,
"router/selected_tokens_s1": 4252.75,
"step": 8970,
"tokens_trained": 29.385275576
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5469115665555635,
"grad_norm": 0.07880797237157822,
"loss": 1.0427,
"loss_ce": 1.063873529434204,
"loss_region": 0.06000230833888054,
"loss_total": 1.1238758563995361,
"lr": 0.0008797411582843037,
"router/selected_tokens_s0": 7401.375,
"router/selected_tokens_s1": 4278.0,
"step": 8980,
"tokens_trained": 29.418036064
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.549748244805333,
"grad_norm": 0.09025935083627701,
"loss": 1.0523,
"loss_ce": 0.9206526875495911,
"loss_region": 0.06000004708766937,
"loss_total": 0.9806527495384216,
"lr": 0.0008793342663004528,
"router/selected_tokens_s0": 7416.0,
"router/selected_tokens_s1": 4278.75,
"step": 8990,
"tokens_trained": 29.450801504
},
{
"comp/rl_weight": 0.03,
"comp/strictness": 0.0,
"epoch": 2.5525849230551025,
"grad_norm": 0.09820877760648727,
"loss": 1.0528,
"loss_ce": 1.007702112197876,
"loss_region": 0.06000753864645958,
"loss_total": 1.0677096843719482,
"lr": 0.0008789273743166017,
"router/selected_tokens_s0": 7384.0,
"router/selected_tokens_s1": 4275.375,
"step": 9000,
"tokens_trained": 29.483566944
},
{
"epoch": 2.5525849230551025,
"eval_ppl": 2.7250221948753346,
"eval_runtime": 1.0167,
"step": 9000,
"tokens_trained": 29.483566944
},
{
"epoch": 2.5525849230551025,
"eval_F": 0.3320773758366539,
"eval_F_cds": 0.32461848677879107,
"eval_F_dig": 0.3169778888975701,
"eval_F_exon": 0.33236885142785255,
"eval_F_intron": 0.33329054068511027,
"eval_F_nig": 0.3344018724876609,
"eval_F_promoter": 0.3263581733012336,
"eval_F_utr": 0.3302584452060089,
"eval_G": 0.3439454638281474,
"eval_G_cds": 0.3421455034714266,
"eval_G_dig": 0.3039759270743808,
"eval_G_exon": 0.3462285284836667,
"eval_G_intron": 0.3449180219900721,
"eval_G_nig": 0.34477996088582213,
"eval_G_promoter": 0.34113107089701955,
"eval_G_utr": 0.3442766678637687,
"eval_avg_bp_per_token": 3.011346369142268,
"eval_bp_per_token/cds": 3.0805392814286723,
"eval_bp_per_token/dig": 3.154794182893764,
"eval_bp_per_token/exon": 3.0087055261165783,
"eval_bp_per_token/intron": 3.0003851832830457,
"eval_bp_per_token/nig": 2.990413877054169,
"eval_bp_per_token/promoter": 3.064118143218631,
"eval_bp_per_token/utr": 3.0279316532729967,
"eval_ppl_cds": 3.2245429468340667,
"eval_ppl_dig": 1.1062662889876407,
"eval_ppl_exon": 3.2440991246218105,
"eval_ppl_intron": 2.8497260833235316,
"eval_ppl_nig": 2.5493835432583385,
"eval_ppl_promoter": 2.8852114125443373,
"eval_ppl_utr": 3.007436285101054,
"step": 9000,
"tokens_trained": 29.483566944
}
],
"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": 8,
"trial_name": null,
"trial_params": null
}