| {"estimated_cost_usd": 0.001379000442233333, "event": "train", "grad_norm": 2.4492197036743164, "learning_rate": 1.4634146341463416e-06, "loss": 4.732727408409119, "ncp_loss": 1.3257142901420593, "ntp_loss": 2.0803881883621216, "step": 1, "tokens": 4096, "tokens_per_second": 759.0683247789995, "vq_loss": 1.3266249597072601} |
| {"estimated_cost_usd": 0.0032966898417222217, "event": "train", "grad_norm": 2.2670326232910156, "learning_rate": 8.048780487804879e-06, "loss": 4.751682639122009, "ncp_loss": 1.3053224384784698, "ntp_loss": 2.135641485452652, "step": 10, "tokens": 40960, "tokens_per_second": 3175.171477486401, "vq_loss": 1.3107188642024994} |
| {"estimated_cost_usd": 0.0054161960665, "event": "train", "grad_norm": 1.8863328695297241, "learning_rate": 1.5365853658536586e-05, "loss": 4.725244164466858, "ncp_loss": 1.3087759017944336, "ntp_loss": 2.1074967086315155, "step": 20, "tokens": 81920, "tokens_per_second": 3865.2794053372572, "vq_loss": 1.3089716136455536} |
| {"estimated_cost_usd": 0.007519445111322222, "event": "train", "grad_norm": 1.772733211517334, "learning_rate": 2.2682926829268295e-05, "loss": 4.656316518783569, "ncp_loss": 1.321251004934311, "ntp_loss": 2.009916454553604, "step": 30, "tokens": 122880, "tokens_per_second": 4176.1946794960795, "vq_loss": 1.3251491487026215} |
| {"estimated_cost_usd": 0.00968076818912222, "event": "train", "grad_norm": 1.417633056640625, "learning_rate": 3e-05, "loss": 4.613968253135681, "ncp_loss": 1.3476618230342865, "ntp_loss": 1.9152945578098297, "step": 40, "tokens": 163840, "tokens_per_second": 4325.0929476102565, "vq_loss": 1.351011872291565} |
| {"estimated_cost_usd": 0.011830828920811111, "event": "train", "grad_norm": 1.3075425624847412, "learning_rate": 2.999967182532756e-05, "loss": 4.52185332775116, "ncp_loss": 1.3464830219745636, "ntp_loss": 1.8288958966732025, "step": 50, "tokens": 204800, "tokens_per_second": 4423.84706330362, "vq_loss": 1.3464744091033936} |
| {"estimated_cost_usd": 0.013948621386199999, "event": "train", "grad_norm": 1.3439078330993652, "learning_rate": 2.9998537414845345e-05, "loss": 4.548559308052063, "ncp_loss": 1.354234218597412, "ntp_loss": 1.8380162119865417, "step": 60, "tokens": 245760, "tokens_per_second": 4502.619405489741, "vq_loss": 1.356308937072754} |
| {"estimated_cost_usd": 0.016073710462055555, "event": "train", "grad_norm": 1.2278417348861694, "learning_rate": 2.999659278508841e-05, "loss": 4.548083782196045, "ncp_loss": 1.3393913805484772, "ntp_loss": 1.8682179152965546, "step": 70, "tokens": 286720, "tokens_per_second": 4558.554732080108, "vq_loss": 1.3404744863510132} |
| {"estimated_cost_usd": 0.018186227976855554, "event": "train", "grad_norm": 1.3235681056976318, "learning_rate": 2.999383805277877e-05, "loss": 4.477233052253723, "ncp_loss": 1.327929139137268, "ntp_loss": 1.817845344543457, "step": 80, "tokens": 327680, "tokens_per_second": 4604.607648766723, "vq_loss": 1.3314585387706757} |
| {"estimated_cost_usd": 0.0202879887939, "event": "train", "grad_norm": 1.2423406839370728, "learning_rate": 2.999027338326302e-05, "loss": 4.456571578979492, "ncp_loss": 1.3444677591323853, "ntp_loss": 1.7666885554790497, "step": 90, "tokens": 368640, "tokens_per_second": 4643.535687890639, "vq_loss": 1.3454154133796692} |
| {"estimated_cost_usd": 0.02244906579291111, "event": "train", "grad_norm": 1.3579622507095337, "learning_rate": 2.998589899050242e-05, "loss": 4.5962233543396, "ncp_loss": 1.3446076214313507, "ntp_loss": 1.9055194556713104, "step": 100, "tokens": 409600, "tokens_per_second": 4662.802297484007, "vq_loss": 1.346096158027649} |
| {"estimated_cost_usd": 0.024870874542455554, "event": "train", "grad_norm": 1.3824291229248047, "learning_rate": 2.998071513706002e-05, "loss": 4.460774183273315, "ncp_loss": 1.3363004922866821, "ntp_loss": 1.785142958164215, "step": 110, "tokens": 450560, "tokens_per_second": 4629.63660222552, "vq_loss": 1.3393307030200958} |
| {"estimated_cost_usd": 0.027329548369477773, "event": "train", "grad_norm": 1.3511443138122559, "learning_rate": 2.9974722134084943e-05, "loss": 4.5454957485198975, "ncp_loss": 1.32761150598526, "ntp_loss": 1.8864036798477173, "step": 120, "tokens": 491520, "tokens_per_second": 4596.148643530141, "vq_loss": 1.3314803838729858} |
| {"estimated_cost_usd": 0.029731484192633335, "event": "train", "grad_norm": 1.2922022342681885, "learning_rate": 2.996792034129368e-05, "loss": 4.45792019367218, "ncp_loss": 1.3251806199550629, "ntp_loss": 1.804277777671814, "step": 130, "tokens": 532480, "tokens_per_second": 4576.906465232529, "vq_loss": 1.3284618258476257} |
| {"estimated_cost_usd": 0.032124104549400005, "event": "train", "grad_norm": 1.2152472734451294, "learning_rate": 2.9960310166948502e-05, "loss": 4.3962849378585815, "ncp_loss": 1.315126121044159, "ntp_loss": 1.7640931904315948, "step": 140, "tokens": 573440, "tokens_per_second": 4561.863430385171, "vq_loss": 1.3170656561851501} |
| {"estimated_cost_usd": 0.034429418580055555, "event": "train", "grad_norm": 1.3058998584747314, "learning_rate": 2.9951892067832975e-05, "loss": 4.396389722824097, "ncp_loss": 1.2990922331809998, "ntp_loss": 1.7943488359451294, "step": 150, "tokens": 614400, "tokens_per_second": 4560.441035861372, "vq_loss": 1.3029487133026123} |
| {"estimated_cost_usd": 0.03671470111363333, "event": "train", "grad_norm": 1.4507685899734497, "learning_rate": 2.994266654922452e-05, "loss": 4.413148522377014, "ncp_loss": 1.3056308031082153, "ntp_loss": 1.7985936999320984, "step": 160, "tokens": 655360, "tokens_per_second": 4561.684660608552, "vq_loss": 1.3089240193367004} |
| {"estimated_cost_usd": 0.0389222161042, "event": "train", "grad_norm": 1.378397822380066, "learning_rate": 2.9932634164864082e-05, "loss": 4.484859943389893, "ncp_loss": 1.3417249619960785, "ntp_loss": 1.7994524240493774, "step": 170, "tokens": 696320, "tokens_per_second": 4571.899091461097, "vq_loss": 1.3436825275421143} |
| {"estimated_cost_usd": 0.04109852768272222, "event": "train", "grad_norm": 1.3366121053695679, "learning_rate": 2.992179551692292e-05, "loss": 4.378557443618774, "ncp_loss": 1.3260003328323364, "ntp_loss": 1.7236586809158325, "step": 180, "tokens": 737280, "tokens_per_second": 4584.495129717503, "vq_loss": 1.3288982808589935} |
| {"estimated_cost_usd": 0.0432692703037, "event": "train", "grad_norm": 1.2051481008529663, "learning_rate": 2.9910151255966434e-05, "loss": 4.325296878814697, "ncp_loss": 1.2874716818332672, "ntp_loss": 1.7440879344940186, "step": 190, "tokens": 778240, "tokens_per_second": 4596.41575093881, "vq_loss": 1.2937373220920563} |
| {"estimated_cost_usd": 0.045387406645666664, "event": "train", "grad_norm": 1.233715534210205, "learning_rate": 2.9897702080915145e-05, "loss": 4.220903515815735, "ncp_loss": 1.28626748919487, "ntp_loss": 1.6469368636608124, "step": 200, "tokens": 819200, "tokens_per_second": 4612.537410332493, "vq_loss": 1.2876991927623749} |
| {"estimated_cost_usd": 0.04749956784012222, "event": "train", "grad_norm": 1.2234219312667847, "learning_rate": 2.9884448739002713e-05, "loss": 4.484064936637878, "ncp_loss": 1.323411911725998, "ntp_loss": 1.8318975865840912, "step": 210, "tokens": 860160, "tokens_per_second": 4627.803507740315, "vq_loss": 1.328755408525467} |
| {"estimated_cost_usd": 0.04961957493257778, "event": "train", "grad_norm": 1.246140718460083, "learning_rate": 2.9870392025731105e-05, "loss": 4.353778600692749, "ncp_loss": 1.3316521346569061, "ntp_loss": 1.6886476278305054, "step": 220, "tokens": 901120, "tokens_per_second": 4641.0357713690855, "vq_loss": 1.3334788084030151} |
| {"estimated_cost_usd": 0.05173607622141111, "event": "train", "grad_norm": 1.3180299997329712, "learning_rate": 2.985553278482284e-05, "loss": 4.3462711572647095, "ncp_loss": 1.2960798740386963, "ntp_loss": 1.750965803861618, "step": 230, "tokens": 942080, "tokens_per_second": 4653.498977143945, "vq_loss": 1.2992254495620728} |
| {"estimated_cost_usd": 0.05387012377503333, "event": "train", "grad_norm": 1.157309889793396, "learning_rate": 2.9839871908170355e-05, "loss": 4.393207669258118, "ncp_loss": 1.3115686774253845, "ntp_loss": 1.7673848867416382, "step": 240, "tokens": 983040, "tokens_per_second": 4663.463079878136, "vq_loss": 1.3142541348934174} |
| {"estimated_cost_usd": 0.055972929267922224, "event": "train", "grad_norm": 1.2626032829284668, "learning_rate": 2.982341033578246e-05, "loss": 4.355481266975403, "ncp_loss": 1.3028724491596222, "ntp_loss": 1.7477734982967377, "step": 250, "tokens": 1024000, "tokens_per_second": 4675.275929124213, "vq_loss": 1.3048352301120758} |
| {"estimated_cost_usd": 0.05807054870598888, "event": "train", "grad_norm": 1.266190528869629, "learning_rate": 2.9806149055727934e-05, "loss": 4.3419400453567505, "ncp_loss": 1.3232267200946808, "ntp_loss": 1.6921466290950775, "step": 260, "tokens": 1064960, "tokens_per_second": 4686.651848639698, "vq_loss": 1.3265666961669922} |
| {"estimated_cost_usd": 0.06014172766273333, "event": "train", "grad_norm": 1.2778618335723877, "learning_rate": 2.9788089104076182e-05, "loss": 4.232905864715576, "ncp_loss": 1.3069315254688263, "ntp_loss": 1.6157488226890564, "step": 270, "tokens": 1105920, "tokens_per_second": 4699.299654059111, "vq_loss": 1.3102255165576935} |
| {"estimated_cost_usd": 0.06218711632847777, "event": "train", "grad_norm": 1.39857017993927, "learning_rate": 2.976923156483509e-05, "loss": 4.111989736557007, "ncp_loss": 1.2836772501468658, "ntp_loss": 1.5443606674671173, "step": 280, "tokens": 1146880, "tokens_per_second": 4713.059116737628, "vq_loss": 1.2839517891407013} |
| {"estimated_cost_usd": 0.06421593892068889, "event": "train", "grad_norm": 1.2797125577926636, "learning_rate": 2.9749577569885936e-05, "loss": 4.093312978744507, "ncp_loss": 1.2695043087005615, "ntp_loss": 1.5471955239772797, "step": 290, "tokens": 1187840, "tokens_per_second": 4727.161452642272, "vq_loss": 1.276613175868988} |
| {"estimated_cost_usd": 0.06628567901302222, "event": "train", "grad_norm": 1.2456797361373901, "learning_rate": 2.972912829891545e-05, "loss": 4.213607013225555, "ncp_loss": 1.2909695208072662, "ntp_loss": 1.6302827298641205, "step": 300, "tokens": 1228800, "tokens_per_second": 4737.473785325095, "vq_loss": 1.2923547625541687} |
| {"estimated_cost_usd": 0.06851163197454445, "event": "train", "grad_norm": 1.267857313156128, "learning_rate": 2.9707884979345023e-05, "loss": 4.304669380187988, "ncp_loss": 1.276394098997116, "ntp_loss": 1.7488526701927185, "step": 310, "tokens": 1269760, "tokens_per_second": 4736.337653477417, "vq_loss": 1.2794226706027985} |
| {"estimated_cost_usd": 0.0706833217667, "event": "train", "grad_norm": 1.3272513151168823, "learning_rate": 2.9685848886257014e-05, "loss": 4.332229375839233, "ncp_loss": 1.3147471845149994, "ntp_loss": 1.6987119913101196, "step": 320, "tokens": 1310720, "tokens_per_second": 4738.908265847565, "vq_loss": 1.3187702894210815} |
| {"estimated_cost_usd": 0.07282531832374443, "event": "train", "grad_norm": 1.244828701019287, "learning_rate": 2.9663021342318226e-05, "loss": 4.320633411407471, "ncp_loss": 1.3036129772663116, "ntp_loss": 1.7122487425804138, "step": 330, "tokens": 1351680, "tokens_per_second": 4743.258818282532, "vq_loss": 1.3047715425491333} |
| {"estimated_cost_usd": 0.07501736549358888, "event": "train", "grad_norm": 1.2188670635223389, "learning_rate": 2.963940371770053e-05, "loss": 4.18202805519104, "ncp_loss": 1.289859026670456, "ntp_loss": 1.6010874211788177, "step": 340, "tokens": 1392640, "tokens_per_second": 4744.19338172179, "vq_loss": 1.291081577539444} |
| {"estimated_cost_usd": 0.07711064416158887, "event": "train", "grad_norm": 1.2273483276367188, "learning_rate": 2.9614997429998578e-05, "loss": 4.259208917617798, "ncp_loss": 1.2916564047336578, "ntp_loss": 1.6725585758686066, "step": 350, "tokens": 1433600, "tokens_per_second": 4751.152690109953, "vq_loss": 1.2949938774108887} |
| {"estimated_cost_usd": 0.07918908660573334, "event": "train", "grad_norm": 1.344735026359558, "learning_rate": 2.9589803944144777e-05, "loss": 4.223984718322754, "ncp_loss": 1.2728883922100067, "ntp_loss": 1.6719811856746674, "step": 360, "tokens": 1474560, "tokens_per_second": 4758.635515979258, "vq_loss": 1.2791151702404022} |
| {"estimated_cost_usd": 0.08124521789016666, "event": "train", "grad_norm": 1.2258611917495728, "learning_rate": 2.956382477232131e-05, "loss": 4.203184962272644, "ncp_loss": 1.270603358745575, "ntp_loss": 1.6604134440422058, "step": 370, "tokens": 1515520, "tokens_per_second": 4767.044333355545, "vq_loss": 1.2721681892871857} |
| {"estimated_cost_usd": 0.08328792595395555, "event": "train", "grad_norm": 1.2510343790054321, "learning_rate": 2.953706147386939e-05, "loss": 4.0973732471466064, "ncp_loss": 1.2523600161075592, "ntp_loss": 1.5896792709827423, "step": 380, "tokens": 1556480, "tokens_per_second": 4775.80761623252, "vq_loss": 1.2553338408470154} |
| {"estimated_cost_usd": 0.08543994736204444, "event": "train", "grad_norm": 1.2276841402053833, "learning_rate": 2.950951565519567e-05, "loss": 4.23621267080307, "ncp_loss": 1.267632246017456, "ntp_loss": 1.6971645653247833, "step": 390, "tokens": 1597440, "tokens_per_second": 4778.030409321384, "vq_loss": 1.2714157700538635} |
| {"estimated_cost_usd": 0.08761032338678888, "event": "train", "grad_norm": 1.258723497390747, "learning_rate": 2.948118896967581e-05, "loss": 4.341402173042297, "ncp_loss": 1.2890766859054565, "ntp_loss": 1.759465217590332, "step": 400, "tokens": 1638400, "tokens_per_second": 4779.142526089112, "vq_loss": 1.2928601205348969} |
| {"estimated_cost_usd": 0.08975913195861111, "event": "train", "grad_norm": 1.3652234077453613, "learning_rate": 2.9452083117555246e-05, "loss": 4.1284661293029785, "ncp_loss": 1.2476384937763214, "ntp_loss": 1.6313170790672302, "step": 410, "tokens": 1679360, "tokens_per_second": 4781.349467324088, "vq_loss": 1.249510496854782} |
| {"estimated_cost_usd": 0.09184416961569998, "event": "train", "grad_norm": 1.2177047729492188, "learning_rate": 2.9422199845847126e-05, "loss": 4.130444645881653, "ncp_loss": 1.25074103474617, "ntp_loss": 1.6269094944000244, "step": 420, "tokens": 1720320, "tokens_per_second": 4786.774546200274, "vq_loss": 1.2527941465377808} |
| {"estimated_cost_usd": 0.09400590512719999, "event": "train", "grad_norm": 1.2929503917694092, "learning_rate": 2.939154094822746e-05, "loss": 4.272367358207703, "ncp_loss": 1.2587842643260956, "ntp_loss": 1.7507393062114716, "step": 430, "tokens": 1761280, "tokens_per_second": 4788.049094148384, "vq_loss": 1.2628435492515564} |
| {"estimated_cost_usd": 0.09613180937058888, "event": "train", "grad_norm": 1.2165906429290771, "learning_rate": 2.936010826492746e-05, "loss": 4.115151643753052, "ncp_loss": 1.2577183544635773, "ntp_loss": 1.5955350697040558, "step": 440, "tokens": 1802240, "tokens_per_second": 4791.051447590402, "vq_loss": 1.2618982195854187} |
| {"estimated_cost_usd": 0.0982779089817111, "event": "train", "grad_norm": 1.3350259065628052, "learning_rate": 2.9327903682623072e-05, "loss": 4.135257005691528, "ncp_loss": 1.2225989699363708, "ntp_loss": 1.6859628558158875, "step": 450, "tokens": 1843200, "tokens_per_second": 4792.938768036442, "vq_loss": 1.2266952097415924} |
| {"estimated_cost_usd": 0.10042087109076667, "event": "train", "grad_norm": 1.232912302017212, "learning_rate": 2.929492913432173e-05, "loss": 4.105266571044922, "ncp_loss": 1.2244935631752014, "ntp_loss": 1.6514820158481598, "step": 460, "tokens": 1884160, "tokens_per_second": 4794.895227709575, "vq_loss": 1.2292910814285278} |
| {"estimated_cost_usd": 0.10253000358363333, "event": "train", "grad_norm": 1.3349467515945435, "learning_rate": 2.926118659924637e-05, "loss": 4.084441542625427, "ncp_loss": 1.2336347997188568, "ntp_loss": 1.6153377890586853, "step": 470, "tokens": 1925120, "tokens_per_second": 4798.352617922313, "vq_loss": 1.235468864440918} |
| {"estimated_cost_usd": 0.10461093625617778, "event": "train", "grad_norm": 1.2108197212219238, "learning_rate": 2.922667810271657e-05, "loss": 4.2264333963394165, "ncp_loss": 1.2764757871627808, "ntp_loss": 1.6717050969600677, "step": 480, "tokens": 1966080, "tokens_per_second": 4802.965011576359, "vq_loss": 1.2782524526119232} |
| {"estimated_cost_usd": 0.10667801679283333, "event": "train", "grad_norm": 1.2358858585357666, "learning_rate": 2.919140571602704e-05, "loss": 4.1517369747161865, "ncp_loss": 1.252111166715622, "ntp_loss": 1.6445783972740173, "step": 490, "tokens": 2007040, "tokens_per_second": 4808.021724084767, "vq_loss": 1.2550475001335144} |
| {"estimated_cost_usd": 0.10873432099791111, "event": "train", "grad_norm": 1.1466139554977417, "learning_rate": 2.915537155632326e-05, "loss": 4.093167185783386, "ncp_loss": 1.2276672422885895, "ntp_loss": 1.6330280005931854, "step": 500, "tokens": 2048000, "tokens_per_second": 4813.363186291772, "vq_loss": 1.232472002506256} |
| {"estimated_cost_usd": 0.11079628103715555, "event": "train", "grad_norm": 1.2436197996139526, "learning_rate": 2.9118577786474425e-05, "loss": 4.124748110771179, "ncp_loss": 1.2268067002296448, "ntp_loss": 1.6687479615211487, "step": 510, "tokens": 2088960, "tokens_per_second": 4818.260399501209, "vq_loss": 1.229193389415741} |
| {"estimated_cost_usd": 0.11281348715378889, "event": "train", "grad_norm": 1.359126091003418, "learning_rate": 2.9081026614943625e-05, "loss": 4.048569738864899, "ncp_loss": 1.225799709558487, "ntp_loss": 1.5930202901363373, "step": 520, "tokens": 2129920, "tokens_per_second": 4824.891975432637, "vq_loss": 1.229749858379364} |
| {"estimated_cost_usd": 0.11490596553985555, "event": "train", "grad_norm": 1.337890863418579, "learning_rate": 2.9042720295655258e-05, "loss": 3.936640977859497, "ncp_loss": 1.1892670392990112, "ntp_loss": 1.5556455552577972, "step": 530, "tokens": 2170880, "tokens_per_second": 4828.12569249955, "vq_loss": 1.1917282044887543} |
| {"estimated_cost_usd": 0.1170125006036222, "event": "train", "grad_norm": 1.3347692489624023, "learning_rate": 2.9003661127859777e-05, "loss": 3.965855836868286, "ncp_loss": 1.2075303494930267, "ntp_loss": 1.5464983582496643, "step": 540, "tokens": 2211840, "tokens_per_second": 4830.663365743867, "vq_loss": 1.2118272185325623} |
| {"estimated_cost_usd": 0.11915251152875554, "event": "train", "grad_norm": 1.1906802654266357, "learning_rate": 2.8963851455995672e-05, "loss": 4.034745573997498, "ncp_loss": 1.2242150902748108, "ntp_loss": 1.5820457935333252, "step": 550, "tokens": 2252800, "tokens_per_second": 4831.75342398566, "vq_loss": 1.2284847497940063} |
| {"estimated_cost_usd": 0.12135868763182223, "event": "train", "grad_norm": 1.2355703115463257, "learning_rate": 2.8923293669548735e-05, "loss": 3.9800286889076233, "ncp_loss": 1.2167077958583832, "ntp_loss": 1.5448665618896484, "step": 560, "tokens": 2293760, "tokens_per_second": 4830.170155510188, "vq_loss": 1.2184543907642365} |
| {"estimated_cost_usd": 0.1235114007138, "event": "train", "grad_norm": 1.2951940298080444, "learning_rate": 2.888199020290866e-05, "loss": 4.005223214626312, "ncp_loss": 1.1932731568813324, "ntp_loss": 1.6161125898361206, "step": 570, "tokens": 2334720, "tokens_per_second": 4830.733545393292, "vq_loss": 1.1958376169204712} |
| {"estimated_cost_usd": 0.12564227978563333, "event": "train", "grad_norm": 1.3025509119033813, "learning_rate": 2.8839943535222907e-05, "loss": 3.8492720127105713, "ncp_loss": 1.174770325422287, "ntp_loss": 1.4969565868377686, "step": 580, "tokens": 2375680, "tokens_per_second": 4832.117208140979, "vq_loss": 1.177545189857483} |
| {"estimated_cost_usd": 0.1277557785778, "event": "train", "grad_norm": 1.2502669095993042, "learning_rate": 2.8797156190247915e-05, "loss": 3.9837382435798645, "ncp_loss": 1.2072685062885284, "ntp_loss": 1.5642071962356567, "step": 590, "tokens": 2416640, "tokens_per_second": 4834.112277760366, "vq_loss": 1.2122623920440674} |
| {"estimated_cost_usd": 0.12980787529065554, "event": "train", "grad_norm": 1.30978262424469, "learning_rate": 2.8753630736197586e-05, "loss": 3.9279762506484985, "ncp_loss": 1.196665346622467, "ntp_loss": 1.5311444103717804, "step": 600, "tokens": 2457600, "tokens_per_second": 4838.329969788396, "vq_loss": 1.2001665532588959} |
| {"estimated_cost_usd": 0.13180719381560002, "event": "train", "grad_norm": 1.2578792572021484, "learning_rate": 2.870936978558918e-05, "loss": 3.914194941520691, "ncp_loss": 1.1874699592590332, "ntp_loss": 1.5330425202846527, "step": 610, "tokens": 2498560, "tokens_per_second": 4844.3553830771025, "vq_loss": 1.1936824917793274} |
| {"estimated_cost_usd": 0.1338092591871, "event": "train", "grad_norm": 1.3705276250839233, "learning_rate": 2.8664375995086454e-05, "loss": 4.015088677406311, "ncp_loss": 1.1990845203399658, "ntp_loss": 1.6131640374660492, "step": 620, "tokens": 2539520, "tokens_per_second": 4850.101169284484, "vq_loss": 1.2028400897979736} |
| {"estimated_cost_usd": 0.13587464510803335, "event": "train", "grad_norm": 1.2752107381820679, "learning_rate": 2.8618652065340247e-05, "loss": 4.0228389501571655, "ncp_loss": 1.2187730073928833, "ntp_loss": 1.581907331943512, "step": 630, "tokens": 2580480, "tokens_per_second": 4853.414700554834, "vq_loss": 1.2221587002277374} |
| {"estimated_cost_usd": 0.13793441044255556, "event": "train", "grad_norm": 1.232136845588684, "learning_rate": 2.8572200740826356e-05, "loss": 3.957483172416687, "ncp_loss": 1.2000586688518524, "ntp_loss": 1.5541316270828247, "step": 640, "tokens": 2621440, "tokens_per_second": 4856.826903498118, "vq_loss": 1.2032928466796875} |
| {"estimated_cost_usd": 0.13993851707248892, "event": "train", "grad_norm": 1.3240067958831787, "learning_rate": 2.8525024809680808e-05, "loss": 4.050741016864777, "ncp_loss": 1.222690224647522, "ntp_loss": 1.602678120136261, "step": 650, "tokens": 2662400, "tokens_per_second": 4862.071753687835, "vq_loss": 1.2253727614879608} |
| {"estimated_cost_usd": 0.1419481242980889, "event": "train", "grad_norm": 1.2253563404083252, "learning_rate": 2.84771271035325e-05, "loss": 3.937649726867676, "ncp_loss": 1.1873109936714172, "ntp_loss": 1.5609338283538818, "step": 660, "tokens": 2703360, "tokens_per_second": 4866.979892005294, "vq_loss": 1.189404845237732} |
| {"estimated_cost_usd": 0.14394932776452224, "event": "train", "grad_norm": 1.23581862449646, "learning_rate": 2.842851049733326e-05, "loss": 3.8888415694236755, "ncp_loss": 1.1768845617771149, "ntp_loss": 1.5344268679618835, "step": 670, "tokens": 2744320, "tokens_per_second": 4872.035410748692, "vq_loss": 1.1775301098823547} |
| {"estimated_cost_usd": 0.14599512596826666, "event": "train", "grad_norm": 1.2753815650939941, "learning_rate": 2.837917790918526e-05, "loss": 3.978572189807892, "ncp_loss": 1.1736313700675964, "ntp_loss": 1.6269892156124115, "step": 680, "tokens": 2785280, "tokens_per_second": 4875.462609159243, "vq_loss": 1.177951693534851} |
| {"estimated_cost_usd": 0.14803620920472224, "event": "train", "grad_norm": 1.2360087633132935, "learning_rate": 2.832913230016588e-05, "loss": 3.906827986240387, "ncp_loss": 1.1840895414352417, "ntp_loss": 1.5375270247459412, "step": 690, "tokens": 2826240, "tokens_per_second": 4878.950475788689, "vq_loss": 1.1852113604545593} |
| {"estimated_cost_usd": 0.1501196017934556, "event": "train", "grad_norm": 1.2848765850067139, "learning_rate": 2.827837667414998e-05, "loss": 3.885526955127716, "ncp_loss": 1.16778963804245, "ntp_loss": 1.5467499494552612, "step": 700, "tokens": 2867200, "tokens_per_second": 4880.967442859497, "vq_loss": 1.1709874272346497} |
| {"estimated_cost_usd": 0.1521802843299, "event": "train", "grad_norm": 1.2910648584365845, "learning_rate": 2.8226914077629564e-05, "loss": 3.8597898483276367, "ncp_loss": 1.1819577515125275, "ntp_loss": 1.4938843846321106, "step": 710, "tokens": 2908160, "tokens_per_second": 4883.657878002946, "vq_loss": 1.1839478611946106} |
| {"estimated_cost_usd": 0.1542006156361889, "event": "train", "grad_norm": 1.2451316118240356, "learning_rate": 2.8174747599530965e-05, "loss": 3.902570128440857, "ncp_loss": 1.1733572781085968, "ntp_loss": 1.5508557558059692, "step": 720, "tokens": 2949120, "tokens_per_second": 4887.555065137657, "vq_loss": 1.1783570647239685} |
| {"estimated_cost_usd": 0.15620090920652227, "event": "train", "grad_norm": 1.2985961437225342, "learning_rate": 2.8121880371029428e-05, "loss": 3.9782209992408752, "ncp_loss": 1.1668046712875366, "ntp_loss": 1.642030954360962, "step": 730, "tokens": 2990080, "tokens_per_second": 4891.978922768325, "vq_loss": 1.1693852543830872} |
| {"estimated_cost_usd": 0.15821197837371112, "event": "train", "grad_norm": 1.2399241924285889, "learning_rate": 2.806831556536113e-05, "loss": 3.943186342716217, "ncp_loss": 1.1921539902687073, "ntp_loss": 1.5578822791576385, "step": 740, "tokens": 3031040, "tokens_per_second": 4895.957430488843, "vq_loss": 1.1931501030921936} |
| {"estimated_cost_usd": 0.16022800865291112, "event": "train", "grad_norm": 1.2640974521636963, "learning_rate": 2.801405639763279e-05, "loss": 3.965986669063568, "ncp_loss": 1.179174154996872, "ntp_loss": 1.6056373417377472, "step": 750, "tokens": 3072000, "tokens_per_second": 4899.6843514874645, "vq_loss": 1.1811752915382385} |
| {"estimated_cost_usd": 0.1622782388391, "event": "train", "grad_norm": 1.2100476026535034, "learning_rate": 2.7959106124628594e-05, "loss": 3.943954348564148, "ncp_loss": 1.1741312146186829, "ntp_loss": 1.593891441822052, "step": 760, "tokens": 3112960, "tokens_per_second": 4902.285284294956, "vq_loss": 1.1759317517280579} |
| {"estimated_cost_usd": 0.16430003981574448, "event": "train", "grad_norm": 1.2906981706619263, "learning_rate": 2.790346804461481e-05, "loss": 3.8672794699668884, "ncp_loss": 1.1726371049880981, "ntp_loss": 1.521160751581192, "step": 770, "tokens": 3153920, "tokens_per_second": 4905.670008854986, "vq_loss": 1.1734815835952759} |
| {"estimated_cost_usd": 0.16631781147017782, "event": "train", "grad_norm": 1.2255206108093262, "learning_rate": 2.784714549714173e-05, "loss": 3.8336262106895447, "ncp_loss": 1.176802635192871, "ntp_loss": 1.4767634272575378, "step": 780, "tokens": 3194880, "tokens_per_second": 4909.091372211407, "vq_loss": 1.1800602078437805} |
| {"estimated_cost_usd": 0.1683363059318111, "event": "train", "grad_norm": 1.2175796031951904, "learning_rate": 2.7790141862843297e-05, "loss": 3.759239375591278, "ncp_loss": 1.1449094414710999, "ntp_loss": 1.4679630398750305, "step": 790, "tokens": 3235840, "tokens_per_second": 4912.409621391244, "vq_loss": 1.1463668048381805} |
| {"estimated_cost_usd": 0.17039281664238892, "event": "train", "grad_norm": 1.3902579545974731, "learning_rate": 2.7732460563234138e-05, "loss": 3.86604642868042, "ncp_loss": 1.1536720097064972, "ntp_loss": 1.555623173713684, "step": 800, "tokens": 3276800, "tokens_per_second": 4914.552508407341, "vq_loss": 1.1567511856555939} |
| {"estimated_cost_usd": 0.1724035677275, "event": "train", "grad_norm": 1.3439730405807495, "learning_rate": 2.767410506050421e-05, "loss": 3.6488449573516846, "ncp_loss": 1.1372626721858978, "ntp_loss": 1.3709507584571838, "step": 810, "tokens": 3317760, "tokens_per_second": 4917.949269705027, "vq_loss": 1.140631526708603} |
| {"estimated_cost_usd": 0.17445742010804444, "event": "train", "grad_norm": 1.2218561172485352, "learning_rate": 2.7615078857310997e-05, "loss": 3.796009361743927, "ncp_loss": 1.14175346493721, "ntp_loss": 1.5108243227005005, "step": 820, "tokens": 3358720, "tokens_per_second": 4920.051867234832, "vq_loss": 1.1434316039085388} |
| {"estimated_cost_usd": 0.17646274633929998, "event": "train", "grad_norm": 1.2781987190246582, "learning_rate": 2.7555385496569273e-05, "loss": 3.711674392223358, "ncp_loss": 1.1170617043972015, "ntp_loss": 1.4745323657989502, "step": 830, "tokens": 3399680, "tokens_per_second": 4923.459082069263, "vq_loss": 1.1200803220272064} |
| {"estimated_cost_usd": 0.17850194457906665, "event": "train", "grad_norm": 1.2924796342849731, "learning_rate": 2.7495028561238424e-05, "loss": 3.74922114610672, "ncp_loss": 1.1219233870506287, "ntp_loss": 1.5021108090877533, "step": 840, "tokens": 3440640, "tokens_per_second": 4925.854834467619, "vq_loss": 1.1251868903636932} |
| {"estimated_cost_usd": 0.18060446244494446, "event": "train", "grad_norm": 1.232277750968933, "learning_rate": 2.7434011674107422e-05, "loss": 3.7636698484420776, "ncp_loss": 1.1342803537845612, "ntp_loss": 1.4930239915847778, "step": 850, "tokens": 3481600, "tokens_per_second": 4926.468649651731, "vq_loss": 1.1363655924797058} |
| {"estimated_cost_usd": 0.18262649205232223, "event": "train", "grad_norm": 1.2006860971450806, "learning_rate": 2.737233849757734e-05, "loss": 3.75118088722229, "ncp_loss": 1.128879576921463, "ntp_loss": 1.4926238059997559, "step": 860, "tokens": 3522560, "tokens_per_second": 4929.239825292537, "vq_loss": 1.1296775043010712} |
| {"estimated_cost_usd": 0.18471654515841113, "event": "train", "grad_norm": 1.2406078577041626, "learning_rate": 2.731001273344156e-05, "loss": 3.769082188606262, "ncp_loss": 1.1365255415439606, "ntp_loss": 1.492260754108429, "step": 870, "tokens": 3563520, "tokens_per_second": 4930.134074088194, "vq_loss": 1.1402958929538727} |
| {"estimated_cost_usd": 0.1867795246034, "event": "train", "grad_norm": 1.197744607925415, "learning_rate": 2.724703812266355e-05, "loss": 3.7942341566085815, "ncp_loss": 1.1550905406475067, "ntp_loss": 1.4839560091495514, "step": 880, "tokens": 3604480, "tokens_per_second": 4931.723061426622, "vq_loss": 1.1551876366138458} |
| {"estimated_cost_usd": 0.1890454926270778, "event": "train", "grad_norm": 1.2807033061981201, "learning_rate": 2.718341844515234e-05, "loss": 3.7570916414260864, "ncp_loss": 1.1161057949066162, "ntp_loss": 1.5234566926956177, "step": 890, "tokens": 3645440, "tokens_per_second": 4927.980199359726, "vq_loss": 1.117529183626175} |
| {"estimated_cost_usd": 0.19144577231530002, "event": "train", "grad_norm": 1.238788366317749, "learning_rate": 2.711915751953564e-05, "loss": 3.698392868041992, "ncp_loss": 1.105242758989334, "ntp_loss": 1.4841240644454956, "step": 900, "tokens": 3686400, "tokens_per_second": 4920.871266085987, "vq_loss": 1.1090260744094849} |
| {"estimated_cost_usd": 0.1938030565719778, "event": "train", "grad_norm": 1.280046820640564, "learning_rate": 2.7054259202930633e-05, "loss": 3.857237935066223, "ncp_loss": 1.1204325258731842, "ntp_loss": 1.6144200265407562, "step": 910, "tokens": 3727360, "tokens_per_second": 4915.028547043491, "vq_loss": 1.1223854422569275} |
| {"estimated_cost_usd": 0.19622087908930003, "event": "train", "grad_norm": 1.2935981750488281, "learning_rate": 2.6988727390712438e-05, "loss": 3.754499137401581, "ncp_loss": 1.1104685366153717, "ntp_loss": 1.5312455296516418, "step": 920, "tokens": 3768320, "tokens_per_second": 4907.811623210818, "vq_loss": 1.1127850711345673} |
| {"estimated_cost_usd": 0.19869594600430002, "event": "train", "grad_norm": 1.2315070629119873, "learning_rate": 2.6922566016280355e-05, "loss": 3.715157449245453, "ncp_loss": 1.1228306591510773, "ntp_loss": 1.4665200412273407, "step": 930, "tokens": 3809280, "tokens_per_second": 4899.358473300706, "vq_loss": 1.1258067786693573} |
| {"estimated_cost_usd": 0.201135655017, "event": "train", "grad_norm": 1.3591570854187012, "learning_rate": 2.6855779050821706e-05, "loss": 3.716896176338196, "ncp_loss": 1.1010234951972961, "ntp_loss": 1.513298124074936, "step": 940, "tokens": 3850240, "tokens_per_second": 4891.973141902954, "vq_loss": 1.1025745570659637} |
| {"estimated_cost_usd": 0.20361092308463336, "event": "train", "grad_norm": 1.4625614881515503, "learning_rate": 2.6788370503073522e-05, "loss": 3.681637167930603, "ncp_loss": 1.1227095127105713, "ntp_loss": 1.4347331523895264, "step": 950, "tokens": 3891200, "tokens_per_second": 4883.91174065075, "vq_loss": 1.1241944134235382} |
| {"estimated_cost_usd": 0.2060508516118889, "event": "train", "grad_norm": 1.180348515510559, "learning_rate": 2.67203444190819e-05, "loss": 3.7230054140090942, "ncp_loss": 1.1104866862297058, "ntp_loss": 1.500829041004181, "step": 960, "tokens": 3932160, "tokens_per_second": 4876.880272381037, "vq_loss": 1.11168971657753} |
| {"estimated_cost_usd": 0.2085068768268889, "event": "train", "grad_norm": 1.3195892572402954, "learning_rate": 2.6651704881959157e-05, "loss": 3.686444103717804, "ncp_loss": 1.104638934135437, "ntp_loss": 1.4738691747188568, "step": 970, "tokens": 3973120, "tokens_per_second": 4869.6374159969655, "vq_loss": 1.1079360246658325} |
| {"estimated_cost_usd": 0.21097628672884444, "event": "train", "grad_norm": 1.2157219648361206, "learning_rate": 2.6582456011638766e-05, "loss": 3.736134171485901, "ncp_loss": 1.1110413074493408, "ntp_loss": 1.511466145515442, "step": 980, "tokens": 4014080, "tokens_per_second": 4862.254712838281, "vq_loss": 1.1136267483234406} |
| {"estimated_cost_usd": 0.21346102866693334, "event": "train", "grad_norm": 1.2310750484466553, "learning_rate": 2.6512601964628036e-05, "loss": 3.6331737637519836, "ncp_loss": 1.115503877401352, "ntp_loss": 1.4007582068443298, "step": 990, "tokens": 4055040, "tokens_per_second": 4854.694116633986, "vq_loss": 1.1169116497039795} |
| {"estimated_cost_usd": 0.21592388262154447, "event": "train", "grad_norm": 1.3679139614105225, "learning_rate": 2.644214693375864e-05, "loss": 3.8165704011917114, "ncp_loss": 1.114872008562088, "ntp_loss": 1.5838407278060913, "step": 1000, "tokens": 4096000, "tokens_per_second": 4847.798876376412, "vq_loss": 1.1178575456142426} |
| {"estimated_cost_usd": 0.21835005882984446, "event": "train", "grad_norm": 1.4468833208084106, "learning_rate": 2.6371095147934964e-05, "loss": 3.6652318835258484, "ncp_loss": 1.0970568656921387, "ntp_loss": 1.4686591923236847, "step": 1010, "tokens": 4136960, "tokens_per_second": 4841.872343780693, "vq_loss": 1.0995157659053802} |
| {"estimated_cost_usd": 0.22074082298157782, "event": "train", "grad_norm": 1.2425404787063599, "learning_rate": 2.6299450871880263e-05, "loss": 3.6846262216567993, "ncp_loss": 1.0957728326320648, "ntp_loss": 1.4893491864204407, "step": 1020, "tokens": 4177920, "tokens_per_second": 4836.851889221108, "vq_loss": 1.0995041728019714} |
| {"codebook_perplexity": 1.6184775829315186, "codebook_usage": 0.3072916567325592, "event": "eval", "loss": 3.922361359000206, "ncp_loss": 1.1248576939105988, "ntp_loss": 1.6719476506114006, "step": 1024, "tokens": 4194304, "vq_loss": 1.1255560219287872} |
| {"estimated_cost_usd": 0.2235353057860111, "event": "train", "grad_norm": 1.1919090747833252, "learning_rate": 2.6227218405880676e-05, "loss": 3.6657499074935913, "ncp_loss": 1.109115481376648, "ntp_loss": 1.4453617632389069, "step": 1030, "tokens": 4218880, "tokens_per_second": 4823.212236792411, "vq_loss": 1.1112726628780365} |
| {"estimated_cost_usd": 0.2255702769981222, "event": "train", "grad_norm": 1.3321053981781006, "learning_rate": 2.6154402085527123e-05, "loss": 3.609175205230713, "ncp_loss": 1.1060375571250916, "ntp_loss": 1.3963464796543121, "step": 1040, "tokens": 4259840, "tokens_per_second": 4826.10471674351, "vq_loss": 1.1067911982536316} |
| {"estimated_cost_usd": 0.22762731180995557, "event": "train", "grad_norm": 1.2570587396621704, "learning_rate": 2.6081006281455055e-05, "loss": 3.601173460483551, "ncp_loss": 1.1023948788642883, "ntp_loss": 1.395376056432724, "step": 1050, "tokens": 4300800, "tokens_per_second": 4828.477411581254, "vq_loss": 1.1034025251865387} |
| {"estimated_cost_usd": 0.23046665381950002, "event": "train", "grad_norm": 1.273529052734375, "learning_rate": 2.6007035399082144e-05, "loss": 3.684360682964325, "ncp_loss": 1.0873070657253265, "ntp_loss": 1.5086902678012848, "step": 1060, "tokens": 4341760, "tokens_per_second": 4814.409679232336, "vq_loss": 1.0883632600307465} |
| {"estimated_cost_usd": 0.23281136799683336, "event": "train", "grad_norm": 1.4312963485717773, "learning_rate": 2.593249387834382e-05, "loss": 3.5726680159568787, "ncp_loss": 1.0786129236221313, "ntp_loss": 1.4133538007736206, "step": 1070, "tokens": 4382720, "tokens_per_second": 4810.883824451729, "vq_loss": 1.080701321363449} |
| {"estimated_cost_usd": 0.23487354034677774, "event": "train", "grad_norm": 1.2234575748443604, "learning_rate": 2.5857386193426817e-05, "loss": 3.5946754217147827, "ncp_loss": 1.0827355682849884, "ntp_loss": 1.4279965162277222, "step": 1080, "tokens": 4423680, "tokens_per_second": 4813.211391674367, "vq_loss": 1.083943396806717} |
| {"estimated_cost_usd": 0.23696429063806665, "event": "train", "grad_norm": 1.194201111793518, "learning_rate": 2.5781716852500573e-05, "loss": 3.6197510361671448, "ncp_loss": 1.0711933374404907, "ntp_loss": 1.475104659795761, "step": 1090, "tokens": 4464640, "tokens_per_second": 4814.917692802223, "vq_loss": 1.0734530985355377} |
| {"estimated_cost_usd": 0.23913957824994447, "event": "train", "grad_norm": 1.3199129104614258, "learning_rate": 2.5705490397446686e-05, "loss": 3.550203263759613, "ncp_loss": 1.047328770160675, "ntp_loss": 1.452486664056778, "step": 1100, "tokens": 4505600, "tokens_per_second": 4814.89145183511, "vq_loss": 1.0503877103328705} |
| {"estimated_cost_usd": 0.24124984160246668, "event": "train", "grad_norm": 1.2567616701126099, "learning_rate": 2.562871140358626e-05, "loss": 3.542230010032654, "ncp_loss": 1.0714515149593353, "ntp_loss": 1.3971223831176758, "step": 1110, "tokens": 4546560, "tokens_per_second": 4816.163438487359, "vq_loss": 1.0736561119556427} |
| {"estimated_cost_usd": 0.2432721037298778, "event": "train", "grad_norm": 1.2391833066940308, "learning_rate": 2.5551384479405283e-05, "loss": 3.5006000995635986, "ncp_loss": 1.0381624698638916, "ntp_loss": 1.423780471086502, "step": 1120, "tokens": 4587520, "tokens_per_second": 4819.156016030442, "vq_loss": 1.038657158613205} |
| {"estimated_cost_usd": 0.24535655901623335, "event": "train", "grad_norm": 1.2745219469070435, "learning_rate": 2.5473514266278056e-05, "loss": 3.57944393157959, "ncp_loss": 1.0617583990097046, "ntp_loss": 1.4544433951377869, "step": 1130, "tokens": 4628480, "tokens_per_second": 4820.876941380315, "vq_loss": 1.0632421374320984} |
| {"estimated_cost_usd": 0.24739182761093337, "event": "train", "grad_norm": 1.3695473670959473, "learning_rate": 2.5395105438188545e-05, "loss": 3.476417124271393, "ncp_loss": 1.0496933460235596, "ntp_loss": 1.3769977688789368, "step": 1140, "tokens": 4669440, "tokens_per_second": 4823.527700397634, "vq_loss": 1.0497260689735413} |
| {"estimated_cost_usd": 0.2493683815937778, "event": "train", "grad_norm": 1.255088448524475, "learning_rate": 2.5316162701449887e-05, "loss": 3.674796462059021, "ncp_loss": 1.0688958764076233, "ntp_loss": 1.5351977348327637, "step": 1150, "tokens": 4710400, "tokens_per_second": 4827.27152975566, "vq_loss": 1.0707029402256012} |
| {"estimated_cost_usd": 0.2514334450761778, "event": "train", "grad_norm": 1.1995580196380615, "learning_rate": 2.5236690794421865e-05, "loss": 3.580032527446747, "ncp_loss": 1.0746717751026154, "ntp_loss": 1.4316364228725433, "step": 1160, "tokens": 4751360, "tokens_per_second": 4829.255885495116, "vq_loss": 1.0737243294715881} |
| {"estimated_cost_usd": 0.25344173065661113, "event": "train", "grad_norm": 1.3200668096542358, "learning_rate": 2.515669448722652e-05, "loss": 3.377484381198883, "ncp_loss": 1.0397162735462189, "ntp_loss": 1.296636700630188, "step": 1170, "tokens": 4792320, "tokens_per_second": 4832.29023423674, "vq_loss": 1.0411314368247986} |
| {"estimated_cost_usd": 0.25546603411707774, "event": "train", "grad_norm": 1.421371340751648, "learning_rate": 2.5076178581461835e-05, "loss": 3.5903682112693787, "ncp_loss": 1.0641663670539856, "ntp_loss": 1.460739254951477, "step": 1180, "tokens": 4833280, "tokens_per_second": 4834.973697479828, "vq_loss": 1.0654626190662384} |
| {"estimated_cost_usd": 0.2574856475601444, "event": "train", "grad_norm": 1.3168216943740845, "learning_rate": 2.4995147909913525e-05, "loss": 3.6008212566375732, "ncp_loss": 1.05776447057724, "ntp_loss": 1.4840171039104462, "step": 1190, "tokens": 4874240, "tokens_per_second": 4837.703083315159, "vq_loss": 1.0590396523475647} |
| {"estimated_cost_usd": 0.2596022676861444, "event": "train", "grad_norm": 1.3439891338348389, "learning_rate": 2.4913607336264966e-05, "loss": 3.515022575855255, "ncp_loss": 1.059683233499527, "ntp_loss": 1.395839810371399, "step": 1200, "tokens": 4915200, "tokens_per_second": 4838.581256868227, "vq_loss": 1.0594994723796844} |
| {"estimated_cost_usd": 0.26167024447223336, "event": "train", "grad_norm": 1.3432868719100952, "learning_rate": 2.4831561754805236e-05, "loss": 3.5203935503959656, "ncp_loss": 1.0443346798419952, "ntp_loss": 1.4286814033985138, "step": 1210, "tokens": 4956160, "tokens_per_second": 4840.344857615717, "vq_loss": 1.0473774671554565} |
| {"estimated_cost_usd": 0.2637243354550334, "event": "train", "grad_norm": 1.4477314949035645, "learning_rate": 2.47490160901354e-05, "loss": 3.51560777425766, "ncp_loss": 1.0651470720767975, "ntp_loss": 1.3848087787628174, "step": 1220, "tokens": 4997120, "tokens_per_second": 4842.335750223253, "vq_loss": 1.0656518042087555} |
| {"estimated_cost_usd": 0.2657445761216445, "event": "train", "grad_norm": 1.267012357711792, "learning_rate": 2.4665975296872856e-05, "loss": 3.4868582487106323, "ncp_loss": 1.0416741967201233, "ntp_loss": 1.4011718928813934, "step": 1230, "tokens": 5038080, "tokens_per_second": 4844.912931521042, "vq_loss": 1.0440120697021484} |
| {"estimated_cost_usd": 0.26776456625155554, "event": "train", "grad_norm": 1.247028112411499, "learning_rate": 2.4582444359354006e-05, "loss": 3.47781503200531, "ncp_loss": 1.0342988967895508, "ntp_loss": 1.407554566860199, "step": 1240, "tokens": 5079040, "tokens_per_second": 4847.455759585025, "vq_loss": 1.0359615981578827} |
| {"estimated_cost_usd": 0.26979648704828896, "event": "train", "grad_norm": 1.2307907342910767, "learning_rate": 2.4498428291335047e-05, "loss": 3.5742964148521423, "ncp_loss": 1.0487164855003357, "ntp_loss": 1.4735535383224487, "step": 1250, "tokens": 5120000, "tokens_per_second": 4849.746039170092, "vq_loss": 1.0520264208316803} |
| {"estimated_cost_usd": 0.2718598665297222, "event": "train", "grad_norm": 1.3093037605285645, "learning_rate": 2.4413932135691047e-05, "loss": 3.5570074915885925, "ncp_loss": 1.0674160718917847, "ntp_loss": 1.4193912148475647, "step": 1260, "tokens": 5160960, "tokens_per_second": 4851.4406220964, "vq_loss": 1.0702001750469208} |
| {"estimated_cost_usd": 0.27394975864501114, "event": "train", "grad_norm": 1.298625111579895, "learning_rate": 2.432896096411323e-05, "loss": 3.492428421974182, "ncp_loss": 1.0470606982707977, "ntp_loss": 1.396180659532547, "step": 1270, "tokens": 5201920, "tokens_per_second": 4852.639995489789, "vq_loss": 1.0491870641708374} |
| {"estimated_cost_usd": 0.27603382998367776, "event": "train", "grad_norm": 1.278141975402832, "learning_rate": 2.4243519876804608e-05, "loss": 3.398134171962738, "ncp_loss": 1.0387124121189117, "ntp_loss": 1.3198252320289612, "step": 1280, "tokens": 5242880, "tokens_per_second": 4853.923561435705, "vq_loss": 1.0395965278148651} |
| {"estimated_cost_usd": 0.27813634969696666, "event": "train", "grad_norm": 1.2695516347885132, "learning_rate": 2.4157614002173807e-05, "loss": 3.425596058368683, "ncp_loss": 1.048560917377472, "ntp_loss": 1.3273634016513824, "step": 1290, "tokens": 5283840, "tokens_per_second": 4854.865853161058, "vq_loss": 1.0496717989444733} |
| {"estimated_cost_usd": 0.2803426210923555, "event": "train", "grad_norm": 1.2555822134017944, "learning_rate": 2.4071248496527267e-05, "loss": 3.4118138551712036, "ncp_loss": 1.028389722108841, "ntp_loss": 1.3533171117305756, "step": 1300, "tokens": 5324800, "tokens_per_second": 4853.996930327367, "vq_loss": 1.0301070809364319} |
| {"estimated_cost_usd": 0.2823853441838334, "event": "train", "grad_norm": 1.2822494506835938, "learning_rate": 2.3984428543759753e-05, "loss": 3.521212935447693, "ncp_loss": 1.0371734499931335, "ntp_loss": 1.4446752071380615, "step": 1310, "tokens": 5365760, "tokens_per_second": 4855.952357375501, "vq_loss": 1.0393643975257874} |
| {"estimated_cost_usd": 0.2843930184932666, "event": "train", "grad_norm": 1.2573087215423584, "learning_rate": 2.389715935504318e-05, "loss": 3.3966387510299683, "ncp_loss": 1.0252160429954529, "ntp_loss": 1.3451298773288727, "step": 1320, "tokens": 5406720, "tokens_per_second": 4858.478385488381, "vq_loss": 1.0262928009033203} |
| {"estimated_cost_usd": 0.28638956116635556, "event": "train", "grad_norm": 1.2398685216903687, "learning_rate": 2.380944616851385e-05, "loss": 3.3738715052604675, "ncp_loss": 1.0150648653507233, "ntp_loss": 1.3418467044830322, "step": 1330, "tokens": 5447680, "tokens_per_second": 4861.157938924346, "vq_loss": 1.0169599205255508} |
| {"estimated_cost_usd": 0.2883644861294778, "event": "train", "grad_norm": 1.3757095336914062, "learning_rate": 2.372129424895802e-05, "loss": 3.388369560241699, "ncp_loss": 0.9928022623062134, "ntp_loss": 1.401574820280075, "step": 1340, "tokens": 5488640, "tokens_per_second": 4864.165013075303, "vq_loss": 0.9939924776554108} |
| {"estimated_cost_usd": 0.2903503127148889, "event": "train", "grad_norm": 1.3726223707199097, "learning_rate": 2.3632708887495928e-05, "loss": 3.4550845623016357, "ncp_loss": 1.0250872373580933, "ntp_loss": 1.4039731323719025, "step": 1350, "tokens": 5529600, "tokens_per_second": 4866.948434760671, "vq_loss": 1.0260241329669952} |
| {"estimated_cost_usd": 0.29233342218558894, "event": "train", "grad_norm": 1.1976627111434937, "learning_rate": 2.3543695401264162e-05, "loss": 3.434700608253479, "ncp_loss": 1.019545555114746, "ntp_loss": 1.3932407200336456, "step": 1360, "tokens": 5570560, "tokens_per_second": 4869.73930285599, "vq_loss": 1.0219143331050873} |
| {"estimated_cost_usd": 0.2943228963415111, "event": "train", "grad_norm": 1.4967658519744873, "learning_rate": 2.3454259133096548e-05, "loss": 3.396520495414734, "ncp_loss": 1.0052334070205688, "ntp_loss": 1.3834744691848755, "step": 1370, "tokens": 5611520, "tokens_per_second": 4872.387194257346, "vq_loss": 1.0078125596046448} |
| {"estimated_cost_usd": 0.29633256077143333, "event": "train", "grad_norm": 1.3894292116165161, "learning_rate": 2.336440545120344e-05, "loss": 3.4277435541152954, "ncp_loss": 1.0056287497282028, "ntp_loss": 1.415659785270691, "step": 1380, "tokens": 5652480, "tokens_per_second": 4874.667376768134, "vq_loss": 1.006455048918724} |
| {"estimated_cost_usd": 0.2983012758050889, "event": "train", "grad_norm": 1.3498700857162476, "learning_rate": 2.327413974884951e-05, "loss": 3.4378585815429688, "ncp_loss": 1.010861873626709, "ntp_loss": 1.416307508945465, "step": 1390, "tokens": 5693440, "tokens_per_second": 4877.586320391462, "vq_loss": 1.0106893181800842} |
| {"estimated_cost_usd": 0.3004522504686111, "event": "train", "grad_norm": 1.4672638177871704, "learning_rate": 2.3183467444030035e-05, "loss": 3.3841533064842224, "ncp_loss": 1.0011349320411682, "ntp_loss": 1.3793440163135529, "step": 1400, "tokens": 5734400, "tokens_per_second": 4877.506410726243, "vq_loss": 1.003674328327179} |
| {"estimated_cost_usd": 0.3025299408063667, "event": "train", "grad_norm": 1.3843499422073364, "learning_rate": 2.3092393979145683e-05, "loss": 3.4478772282600403, "ncp_loss": 0.9963300824165344, "ntp_loss": 1.4555063247680664, "step": 1410, "tokens": 5775360, "tokens_per_second": 4878.609136667218, "vq_loss": 0.9960408955812454} |
| {"estimated_cost_usd": 0.3046296438083, "event": "train", "grad_norm": 1.2692525386810303, "learning_rate": 2.3000924820675844e-05, "loss": 3.4094821214675903, "ncp_loss": 1.004793792963028, "ntp_loss": 1.397715449333191, "step": 1420, "tokens": 5816320, "tokens_per_second": 4879.34421058595, "vq_loss": 1.0069729536771774} |
| {"estimated_cost_usd": 0.30671672812371115, "event": "train", "grad_norm": 1.3484814167022705, "learning_rate": 2.2909065458850532e-05, "loss": 3.3293882608413696, "ncp_loss": 0.9902133345603943, "ntp_loss": 1.3462661504745483, "step": 1430, "tokens": 5857280, "tokens_per_second": 4880.269992449517, "vq_loss": 0.992908701300621} |
| {"estimated_cost_usd": 0.30885792846419996, "event": "train", "grad_norm": 1.366557240486145, "learning_rate": 2.281682140732084e-05, "loss": 3.3335360288619995, "ncp_loss": 0.9897025525569916, "ntp_loss": 1.352079600095749, "step": 1440, "tokens": 5898240, "tokens_per_second": 4880.328011960735, "vq_loss": 0.9917538911104202} |
| {"estimated_cost_usd": 0.3109958932929778, "event": "train", "grad_norm": 1.3051563501358032, "learning_rate": 2.272419820282799e-05, "loss": 3.359206736087799, "ncp_loss": 1.0026670843362808, "ntp_loss": 1.3523353934288025, "step": 1450, "tokens": 5939200, "tokens_per_second": 4880.436006676448, "vq_loss": 1.0042042434215546} |
| {"estimated_cost_usd": 0.3130941062825889, "event": "train", "grad_norm": 1.2775709629058838, "learning_rate": 2.2631201404870995e-05, "loss": 3.3702322244644165, "ncp_loss": 1.002993866801262, "ntp_loss": 1.3627035319805145, "step": 1460, "tokens": 5980160, "tokens_per_second": 4881.162182375126, "vq_loss": 1.0045348405838013} |
| {"estimated_cost_usd": 0.3152525456155333, "event": "train", "grad_norm": 1.6008234024047852, "learning_rate": 2.2537836595372996e-05, "loss": 3.26063334941864, "ncp_loss": 0.9704724997282028, "ntp_loss": 1.3187669217586517, "step": 1470, "tokens": 6021120, "tokens_per_second": 4880.946048071655, "vq_loss": 0.9713939726352692} |
| {"estimated_cost_usd": 0.31751054538836665, "event": "train", "grad_norm": 1.3033127784729004, "learning_rate": 2.2444109378346177e-05, "loss": 3.404597818851471, "ncp_loss": 1.003970518708229, "ntp_loss": 1.39757838845253, "step": 1480, "tokens": 6062080, "tokens_per_second": 4879.202422481126, "vq_loss": 1.003048837184906} |
| {"estimated_cost_usd": 0.3196660907705889, "event": "train", "grad_norm": 1.364354133605957, "learning_rate": 2.235002537955542e-05, "loss": 3.317942798137665, "ncp_loss": 0.9852304011583328, "ntp_loss": 1.3470546901226044, "step": 1490, "tokens": 6103040, "tokens_per_second": 4879.046676543135, "vq_loss": 0.985657662153244} |
| {"estimated_cost_usd": 0.3218026079878001, "event": "train", "grad_norm": 1.2858554124832153, "learning_rate": 2.225559024618064e-05, "loss": 3.267240345478058, "ncp_loss": 0.9832972139120102, "ntp_loss": 1.3008479177951813, "step": 1500, "tokens": 6144000, "tokens_per_second": 4879.1815055546695, "vq_loss": 0.9830951243638992} |
| {"estimated_cost_usd": 0.32403114023704443, "event": "train", "grad_norm": 1.2494703531265259, "learning_rate": 2.2160809646477803e-05, "loss": 3.2662616968154907, "ncp_loss": 0.982033833861351, "ntp_loss": 1.3007746934890747, "step": 1510, "tokens": 6184960, "tokens_per_second": 4877.928978469794, "vq_loss": 0.983453169465065} |
| {"estimated_cost_usd": 0.3263199003949, "event": "train", "grad_norm": 1.4008564949035645, "learning_rate": 2.206568926943872e-05, "loss": 3.5101542472839355, "ncp_loss": 1.0140612721443176, "ntp_loss": 1.4783266186714172, "step": 1520, "tokens": 6225920, "tokens_per_second": 4875.793485224142, "vq_loss": 1.0177663713693619} |
| {"estimated_cost_usd": 0.32853175968628884, "event": "train", "grad_norm": 1.286969780921936, "learning_rate": 2.197023482444955e-05, "loss": 3.394566833972931, "ncp_loss": 0.996055394411087, "ntp_loss": 1.4018424451351166, "step": 1530, "tokens": 6266880, "tokens_per_second": 4874.828544824062, "vq_loss": 0.9966689497232437} |
| {"estimated_cost_usd": 0.3306384226796334, "event": "train", "grad_norm": 1.354886770248413, "learning_rate": 2.187445204094816e-05, "loss": 3.412529468536377, "ncp_loss": 1.0126723647117615, "ntp_loss": 1.3874491155147552, "step": 1540, "tokens": 6307840, "tokens_per_second": 4875.427188683027, "vq_loss": 1.0124080032110214} |
| {"estimated_cost_usd": 0.3327729247577222, "event": "train", "grad_norm": 1.4529293775558472, "learning_rate": 2.1778346668080168e-05, "loss": 3.3291197419166565, "ncp_loss": 0.9981753826141357, "ntp_loss": 1.3335197269916534, "step": 1550, "tokens": 6348800, "tokens_per_second": 4875.610334862318, "vq_loss": 0.9974246025085449} |
| {"estimated_cost_usd": 0.33498747360266673, "event": "train", "grad_norm": 1.3822879791259766, "learning_rate": 2.1681924474353913e-05, "loss": 3.2304060459136963, "ncp_loss": 0.9675352722406387, "ntp_loss": 1.294412612915039, "step": 1560, "tokens": 6389760, "tokens_per_second": 4874.626054237234, "vq_loss": 0.9684582650661469} |
| {"estimated_cost_usd": 0.3371997609815556, "event": "train", "grad_norm": 1.3753561973571777, "learning_rate": 2.1585191247294176e-05, "loss": 3.312950551509857, "ncp_loss": 0.9768686443567276, "ntp_loss": 1.3585489392280579, "step": 1570, "tokens": 6430720, "tokens_per_second": 4873.687387673192, "vq_loss": 0.9775329977273941} |
| {"estimated_cost_usd": 0.33928225588335553, "event": "train", "grad_norm": 1.3749841451644897, "learning_rate": 2.1488152793094815e-05, "loss": 3.3829947113990784, "ncp_loss": 0.9880613386631012, "ntp_loss": 1.4075727760791779, "step": 1580, "tokens": 6471680, "tokens_per_second": 4874.625032988391, "vq_loss": 0.9873606413602829} |
| {"estimated_cost_usd": 0.34145014214915553, "event": "train", "grad_norm": 1.2915397882461548, "learning_rate": 2.1390814936270267e-05, "loss": 3.135443925857544, "ncp_loss": 0.9541568905115128, "ntp_loss": 1.2273735702037811, "step": 1590, "tokens": 6512640, "tokens_per_second": 4874.331938647428, "vq_loss": 0.9539135098457336} |
| {"estimated_cost_usd": 0.34360007039241114, "event": "train", "grad_norm": 1.3971836566925049, "learning_rate": 2.1293183519305937e-05, "loss": 3.183899700641632, "ncp_loss": 0.9660051912069321, "ntp_loss": 1.252341777086258, "step": 1600, "tokens": 6553600, "tokens_per_second": 4874.297281069123, "vq_loss": 0.9655527621507645} |
| {"estimated_cost_usd": 0.34574542592900004, "event": "train", "grad_norm": 1.2950992584228516, "learning_rate": 2.1195264402307485e-05, "loss": 3.2189818620681763, "ncp_loss": 0.9537747204303741, "ntp_loss": 1.3104156255722046, "step": 1610, "tokens": 6594560, "tokens_per_second": 4874.327519781915, "vq_loss": 0.9547914415597916} |
| {"estimated_cost_usd": 0.3478550732387889, "event": "train", "grad_norm": 1.299423098564148, "learning_rate": 2.1097063462649173e-05, "loss": 3.178436517715454, "ncp_loss": 0.9572744518518448, "ntp_loss": 1.2635923624038696, "step": 1620, "tokens": 6635520, "tokens_per_second": 4874.857750992001, "vq_loss": 0.9575697481632233} |
| {"estimated_cost_usd": 0.3503995924917222, "event": "train", "grad_norm": 1.3579617738723755, "learning_rate": 2.099858659462098e-05, "loss": 3.234764277935028, "ncp_loss": 0.9722202718257904, "ntp_loss": 1.290931522846222, "step": 1630, "tokens": 6676480, "tokens_per_second": 4869.330878562203, "vq_loss": 0.9716125130653381} |
| {"estimated_cost_usd": 0.35280766286823334, "event": "train", "grad_norm": 1.3795801401138306, "learning_rate": 2.0899839709074898e-05, "loss": 3.2904969453811646, "ncp_loss": 0.9561741352081299, "ntp_loss": 1.378486156463623, "step": 1640, "tokens": 6717440, "tokens_per_second": 4865.764811214593, "vq_loss": 0.955836683511734} |
| {"estimated_cost_usd": 0.3549859478963333, "event": "train", "grad_norm": 1.3093829154968262, "learning_rate": 2.0800828733070094e-05, "loss": 3.2635015845298767, "ncp_loss": 0.979845330119133, "ntp_loss": 1.305198758840561, "step": 1650, "tokens": 6758400, "tokens_per_second": 4865.394466743923, "vq_loss": 0.9784575998783112} |
| {"estimated_cost_usd": 0.3573745194067, "event": "train", "grad_norm": 1.3859554529190063, "learning_rate": 2.0701559609517163e-05, "loss": 3.2405956983566284, "ncp_loss": 0.9717316329479218, "ntp_loss": 1.297725647687912, "step": 1660, "tokens": 6799360, "tokens_per_second": 4862.1659571783275, "vq_loss": 0.9711383879184723} |
| {"estimated_cost_usd": 0.3596130896499556, "event": "train", "grad_norm": 1.411043405532837, "learning_rate": 2.060203829682145e-05, "loss": 3.2117209434509277, "ncp_loss": 0.9499792605638504, "ntp_loss": 1.3132662773132324, "step": 1670, "tokens": 6840320, "tokens_per_second": 4861.007088143944, "vq_loss": 0.9484753906726837} |
| {"estimated_cost_usd": 0.36187723221244444, "event": "train", "grad_norm": 1.3452366590499878, "learning_rate": 2.050227076852537e-05, "loss": 3.212020993232727, "ncp_loss": 0.9444178491830826, "ntp_loss": 1.323441058397293, "step": 1680, "tokens": 6881280, "tokens_per_second": 4859.519131894309, "vq_loss": 0.9441620707511902} |
| {"estimated_cost_usd": 0.3642785053097667, "event": "train", "grad_norm": 1.2966382503509521, "learning_rate": 2.040226301294987e-05, "loss": 3.24935245513916, "ncp_loss": 0.958745464682579, "ntp_loss": 1.3313212990760803, "step": 1690, "tokens": 6922240, "tokens_per_second": 4856.220894462585, "vq_loss": 0.959285631775856} |
| {"estimated_cost_usd": 0.36648042799267777, "event": "train", "grad_norm": 1.2338885068893433, "learning_rate": 2.0302021032835002e-05, "loss": 3.299479126930237, "ncp_loss": 0.9635418355464935, "ntp_loss": 1.3738036453723907, "step": 1700, "tokens": 6963200, "tokens_per_second": 4855.6056709254835, "vq_loss": 0.9621336460113525} |
| {"estimated_cost_usd": 0.36885724927837776, "event": "train", "grad_norm": 1.308516025543213, "learning_rate": 2.0201550844979617e-05, "loss": 3.1790414452552795, "ncp_loss": 0.9370278865098953, "ntp_loss": 1.3066526651382446, "step": 1710, "tokens": 7004160, "tokens_per_second": 4852.695733923661, "vq_loss": 0.9353608787059784} |
| {"estimated_cost_usd": 0.3709930038074111, "event": "train", "grad_norm": 1.2877916097640991, "learning_rate": 2.0100858479880226e-05, "loss": 3.241492211818695, "ncp_loss": 0.9521827399730682, "ntp_loss": 1.3366462290287018, "step": 1720, "tokens": 7045120, "tokens_per_second": 4852.974414822616, "vq_loss": 0.9526631683111191} |
| {"estimated_cost_usd": 0.37314586873360006, "event": "train", "grad_norm": 1.3463399410247803, "learning_rate": 1.999994998136902e-05, "loss": 3.2046971321105957, "ncp_loss": 0.9419393688440323, "ntp_loss": 1.3222526609897614, "step": 1730, "tokens": 7086080, "tokens_per_second": 4853.027362347558, "vq_loss": 0.9405050873756409} |
| {"estimated_cost_usd": 0.37524911862942223, "event": "train", "grad_norm": 1.4271997213363647, "learning_rate": 1.9898831406251125e-05, "loss": 3.2698864936828613, "ncp_loss": 0.9705441445112228, "ntp_loss": 1.3311183750629425, "step": 1740, "tokens": 7127040, "tokens_per_second": 4853.7213713361125, "vq_loss": 0.968223974108696} |
| {"estimated_cost_usd": 0.37743767675421114, "event": "train", "grad_norm": 1.2922101020812988, "learning_rate": 1.979750882394102e-05, "loss": 3.2279701232910156, "ncp_loss": 0.9610984325408936, "ntp_loss": 1.3061010539531708, "step": 1750, "tokens": 7168000, "tokens_per_second": 4853.310453728529, "vq_loss": 0.9607706218957901} |
| {"estimated_cost_usd": 0.3795316464354889, "event": "train", "grad_norm": 1.4353079795837402, "learning_rate": 1.9695988316098272e-05, "loss": 3.2398349046707153, "ncp_loss": 0.9629019498825073, "ntp_loss": 1.3140891194343567, "step": 1760, "tokens": 7208960, "tokens_per_second": 4854.113734863271, "vq_loss": 0.9628438800573349} |
| {"estimated_cost_usd": 0.3816056999071889, "event": "train", "grad_norm": 1.3160635232925415, "learning_rate": 1.9594275976262485e-05, "loss": 3.284681260585785, "ncp_loss": 0.9549332410097122, "ntp_loss": 1.3755750954151154, "step": 1770, "tokens": 7249920, "tokens_per_second": 4855.161581139763, "vq_loss": 0.9541729688644409} |
| {"estimated_cost_usd": 0.38365666322655556, "event": "train", "grad_norm": 1.291337013244629, "learning_rate": 1.949237790948753e-05, "loss": 3.168791711330414, "ncp_loss": 0.9310670644044876, "ntp_loss": 1.3066404163837433, "step": 1780, "tokens": 7290880, "tokens_per_second": 4856.490366201782, "vq_loss": 0.9310841709375381} |
| {"estimated_cost_usd": 0.3857806435871555, "event": "train", "grad_norm": 1.3803551197052002, "learning_rate": 1.9390300231975124e-05, "loss": 3.1929527521133423, "ncp_loss": 0.9324051886796951, "ntp_loss": 1.3268996179103851, "step": 1790, "tokens": 7331840, "tokens_per_second": 4856.8855788668925, "vq_loss": 0.933648020029068} |
| {"estimated_cost_usd": 0.38798377330316663, "event": "train", "grad_norm": 1.3003060817718506, "learning_rate": 1.928804907070773e-05, "loss": 3.11271208524704, "ncp_loss": 0.9323108047246933, "ntp_loss": 1.2491265535354614, "step": 1800, "tokens": 7372800, "tokens_per_second": 4856.285570808489, "vq_loss": 0.931274801492691} |
| {"estimated_cost_usd": 0.39019411717694447, "event": "train", "grad_norm": 1.4042109251022339, "learning_rate": 1.9185630563080758e-05, "loss": 3.1930251121520996, "ncp_loss": 0.9503099173307419, "ntp_loss": 1.294996291399002, "step": 1810, "tokens": 7413760, "tokens_per_second": 4855.602563316924, "vq_loss": 0.9477188587188721} |
| {"estimated_cost_usd": 0.3923592024695222, "event": "train", "grad_norm": 1.3111851215362549, "learning_rate": 1.908305085653422e-05, "loss": 3.168425142765045, "ncp_loss": 0.9396859705448151, "ntp_loss": 1.2908244729042053, "step": 1820, "tokens": 7454720, "tokens_per_second": 4855.48726554743, "vq_loss": 0.9379146993160248} |
| {"estimated_cost_usd": 0.39459237953375553, "event": "train", "grad_norm": 1.3712363243103027, "learning_rate": 1.8980316108183728e-05, "loss": 3.1474176049232483, "ncp_loss": 0.922835037112236, "ntp_loss": 1.302643746137619, "step": 1830, "tokens": 7495680, "tokens_per_second": 4854.535378838453, "vq_loss": 0.9219388216733932} |
| {"estimated_cost_usd": 0.3968067559934444, "event": "train", "grad_norm": 1.3666298389434814, "learning_rate": 1.8877432484450923e-05, "loss": 3.1068923473358154, "ncp_loss": 0.9160504788160324, "ntp_loss": 1.2755824327468872, "step": 1840, "tokens": 7536640, "tokens_per_second": 4853.824167888013, "vq_loss": 0.9152594059705734} |
| {"estimated_cost_usd": 0.3990054484664, "event": "train", "grad_norm": 1.371802806854248, "learning_rate": 1.877440616069337e-05, "loss": 3.0968435406684875, "ncp_loss": 0.9371460676193237, "ntp_loss": 1.223653644323349, "step": 1850, "tokens": 7577600, "tokens_per_second": 4853.311615720579, "vq_loss": 0.9360437989234924} |
| {"estimated_cost_usd": 0.4010259841841667, "event": "train", "grad_norm": 1.3195630311965942, "learning_rate": 1.8671243320833857e-05, "loss": 3.1958808302879333, "ncp_loss": 0.930509477853775, "ntp_loss": 1.335853785276413, "step": 1860, "tokens": 7618560, "tokens_per_second": 4854.9605514818995, "vq_loss": 0.9295175820589066} |
| {"estimated_cost_usd": 0.4031644118989333, "event": "train", "grad_norm": 1.3066632747650146, "learning_rate": 1.8567950156989272e-05, "loss": 3.128267526626587, "ncp_loss": 0.9214961677789688, "ntp_loss": 1.285728245973587, "step": 1870, "tokens": 7659520, "tokens_per_second": 4855.172805727667, "vq_loss": 0.9210431575775146} |
| {"estimated_cost_usd": 0.40524152230702226, "event": "train", "grad_norm": 1.31593656539917, "learning_rate": 1.8464532869098877e-05, "loss": 3.078608751296997, "ncp_loss": 0.9113724827766418, "ntp_loss": 1.2568271458148956, "step": 1880, "tokens": 7700480, "tokens_per_second": 4856.117490728179, "vq_loss": 0.9104091227054596} |
| {"estimated_cost_usd": 0.4073522209125667, "event": "train", "grad_norm": 1.4145770072937012, "learning_rate": 1.836099766455223e-05, "loss": 3.1362640857696533, "ncp_loss": 0.9165553599596024, "ntp_loss": 1.3049492537975311, "step": 1890, "tokens": 7741440, "tokens_per_second": 4856.6520530266935, "vq_loss": 0.9147594124078751} |
| {"estimated_cost_usd": 0.40951149574248885, "event": "train", "grad_norm": 1.4049077033996582, "learning_rate": 1.825735075781654e-05, "loss": 3.037455677986145, "ncp_loss": 0.8917864114046097, "ntp_loss": 1.2557165026664734, "step": 1900, "tokens": 7782400, "tokens_per_second": 4856.604945728276, "vq_loss": 0.8899527341127396} |
| {"estimated_cost_usd": 0.41178163605331114, "event": "train", "grad_norm": 1.276283860206604, "learning_rate": 1.8153598370063707e-05, "loss": 3.083295166492462, "ncp_loss": 0.9206663370132446, "ntp_loss": 1.2434233129024506, "step": 1910, "tokens": 7823360, "tokens_per_second": 4855.250783578586, "vq_loss": 0.9192055761814117} |
| {"estimated_cost_usd": 0.4140704368738889, "event": "train", "grad_norm": 1.3720862865447998, "learning_rate": 1.80497467287969e-05, "loss": 3.151830792427063, "ncp_loss": 0.9200097173452377, "ntp_loss": 1.310449630022049, "step": 1920, "tokens": 7864320, "tokens_per_second": 4853.692723971915, "vq_loss": 0.9213714450597763} |
| {"estimated_cost_usd": 0.4162235057122, "event": "train", "grad_norm": 1.339871883392334, "learning_rate": 1.794580206747672e-05, "loss": 3.1861042976379395, "ncp_loss": 0.9322685301303864, "ntp_loss": 1.3226846754550934, "step": 1930, "tokens": 7905280, "tokens_per_second": 4853.734098379169, "vq_loss": 0.9311511367559433} |
| {"estimated_cost_usd": 0.4183882040305445, "event": "train", "grad_norm": 1.3378937244415283, "learning_rate": 1.7841770625147134e-05, "loss": 3.1257102489471436, "ncp_loss": 0.9169317036867142, "ntp_loss": 1.2905575037002563, "step": 1940, "tokens": 7946240, "tokens_per_second": 4853.64013185593, "vq_loss": 0.9182210713624954} |
| {"estimated_cost_usd": 0.42066014266945556, "event": "train", "grad_norm": 1.3470690250396729, "learning_rate": 1.7737658646060902e-05, "loss": 3.057657241821289, "ncp_loss": 0.9068938195705414, "ntp_loss": 1.2462100684642792, "step": 1950, "tokens": 7987200, "tokens_per_second": 4852.309801400028, "vq_loss": 0.9045533686876297} |
| {"estimated_cost_usd": 0.42284058750028886, "event": "train", "grad_norm": 1.4388017654418945, "learning_rate": 1.7633472379304854e-05, "loss": 2.982353150844574, "ncp_loss": 0.9115265309810638, "ntp_loss": 1.1615605354309082, "step": 1960, "tokens": 8028160, "tokens_per_second": 4852.0434166871155, "vq_loss": 0.9092660546302795} |
| {"estimated_cost_usd": 0.4249520269757, "event": "train", "grad_norm": 1.384407639503479, "learning_rate": 1.752921807842475e-05, "loss": 3.15858656167984, "ncp_loss": 0.9149389714002609, "ntp_loss": 1.3310454189777374, "step": 1970, "tokens": 8069120, "tokens_per_second": 4852.567615973183, "vq_loss": 0.9126021713018417} |
| {"estimated_cost_usd": 0.4271237972420444, "event": "train", "grad_norm": 1.413645625114441, "learning_rate": 1.7424902001049937e-05, "loss": 3.169084906578064, "ncp_loss": 0.9181087464094162, "ntp_loss": 1.3334346115589142, "step": 1980, "tokens": 8110080, "tokens_per_second": 4852.401138458467, "vq_loss": 0.9175415635108948} |
| {"estimated_cost_usd": 0.4292043537915, "event": "train", "grad_norm": 1.3709352016448975, "learning_rate": 1.7320530408517794e-05, "loss": 3.0522353649139404, "ncp_loss": 0.931732103228569, "ntp_loss": 1.190187782049179, "step": 1990, "tokens": 8151040, "tokens_per_second": 4853.267533645434, "vq_loss": 0.9303155541419983} |
| {"estimated_cost_usd": 0.43128212070264443, "event": "train", "grad_norm": 1.26165771484375, "learning_rate": 1.721610956549783e-05, "loss": 3.098519802093506, "ncp_loss": 0.9151458889245987, "ntp_loss": 1.2701185941696167, "step": 2000, "tokens": 8192000, "tokens_per_second": 4854.1569673706035, "vq_loss": 0.9132552891969681} |
| {"estimated_cost_usd": 0.43337167888374445, "event": "train", "grad_norm": 1.4783521890640259, "learning_rate": 1.711164573961573e-05, "loss": 3.0685930848121643, "ncp_loss": 0.9209269732236862, "ntp_loss": 1.2271886765956879, "step": 2010, "tokens": 8232960, "tokens_per_second": 4854.905775305811, "vq_loss": 0.9204773604869843} |
| {"estimated_cost_usd": 0.4354701975116667, "event": "train", "grad_norm": 1.4391601085662842, "learning_rate": 1.7007145201077116e-05, "loss": 3.087134599685669, "ncp_loss": 0.9160249829292297, "ntp_loss": 1.2576551139354706, "step": 2020, "tokens": 8273920, "tokens_per_second": 4855.5474847749465, "vq_loss": 0.913454458117485} |
| {"estimated_cost_usd": 0.43749387173506665, "event": "train", "grad_norm": 1.3683924674987793, "learning_rate": 1.69026142222912e-05, "loss": 3.09087598323822, "ncp_loss": 0.887452706694603, "ntp_loss": 1.3186506032943726, "step": 2030, "tokens": 8314880, "tokens_per_second": 4857.013812217609, "vq_loss": 0.8847726881504059} |
| {"estimated_cost_usd": 0.4397296017821778, "event": "train", "grad_norm": 1.3947163820266724, "learning_rate": 1.6798059077494335e-05, "loss": 3.1452133655548096, "ncp_loss": 0.9126100987195969, "ntp_loss": 1.3210683465003967, "step": 2040, "tokens": 8355840, "tokens_per_second": 4856.123683006233, "vq_loss": 0.9115349352359772} |
| {"codebook_perplexity": 2.216791868209839, "codebook_usage": 0.34375, "event": "eval", "loss": 3.5729056894779205, "ncp_loss": 0.9268169179558754, "ntp_loss": 1.721991129219532, "step": 2048, "tokens": 8388608, "vq_loss": 0.9240976236760616} |
| {"estimated_cost_usd": 0.4435138762080223, "event": "train", "grad_norm": 1.386175513267517, "learning_rate": 1.6693486042373332e-05, "loss": 3.0003966093063354, "ncp_loss": 0.9126189798116684, "ntp_loss": 1.1773194670677185, "step": 2050, "tokens": 8396800, "tokens_per_second": 4838.290308379025, "vq_loss": 0.9104581475257874} |
| {"estimated_cost_usd": 0.4456458780079889, "event": "train", "grad_norm": 1.3425894975662231, "learning_rate": 1.658890139368887e-05, "loss": 3.095194101333618, "ncp_loss": 0.8983852863311768, "ntp_loss": 1.299962043762207, "step": 2060, "tokens": 8437760, "tokens_per_second": 4838.632086272296, "vq_loss": 0.896846741437912} |
| {"estimated_cost_usd": 0.44769911789929995, "event": "train", "grad_norm": 1.377930998802185, "learning_rate": 1.648431140889869e-05, "loss": 3.0556896328926086, "ncp_loss": 0.889567106962204, "ntp_loss": 1.2795508205890656, "step": 2070, "tokens": 8478720, "tokens_per_second": 4839.821910230723, "vq_loss": 0.8865716904401779} |
| {"estimated_cost_usd": 0.44992716550072226, "event": "train", "grad_norm": 1.4951443672180176, "learning_rate": 1.6379722365780816e-05, "loss": 3.138780951499939, "ncp_loss": 0.8961555659770966, "ntp_loss": 1.348217397928238, "step": 2080, "tokens": 8519680, "tokens_per_second": 4839.120023198645, "vq_loss": 0.8944079577922821} |
| {"estimated_cost_usd": 0.4520483215566445, "event": "train", "grad_norm": 1.3489733934402466, "learning_rate": 1.6275140542056758e-05, "loss": 3.0470522046089172, "ncp_loss": 0.8959478586912155, "ntp_loss": 1.2564918994903564, "step": 2090, "tokens": 8560640, "tokens_per_second": 4839.569149549372, "vq_loss": 0.8946124464273453} |
| {"estimated_cost_usd": 0.4541040398760778, "event": "train", "grad_norm": 1.3209563493728638, "learning_rate": 1.617057221501471e-05, "loss": 3.0807685256004333, "ncp_loss": 0.892971932888031, "ntp_loss": 1.2950071096420288, "step": 2100, "tokens": 8601600, "tokens_per_second": 4840.711541052438, "vq_loss": 0.8927895426750183} |
| {"estimated_cost_usd": 0.4562121265078333, "event": "train", "grad_norm": 1.4624593257904053, "learning_rate": 1.6066023661132723e-05, "loss": 3.011155128479004, "ncp_loss": 0.8872200101613998, "ntp_loss": 1.23847496509552, "step": 2110, "tokens": 8642560, "tokens_per_second": 4841.287843724817, "vq_loss": 0.8854601234197617} |
| {"estimated_cost_usd": 0.4582775700271556, "event": "train", "grad_norm": 1.3264025449752808, "learning_rate": 1.596150115570204e-05, "loss": 2.946670949459076, "ncp_loss": 0.8854451775550842, "ntp_loss": 1.1775248050689697, "step": 2120, "tokens": 8683520, "tokens_per_second": 4842.309383909586, "vq_loss": 0.8837009221315384} |
| {"estimated_cost_usd": 0.46033764133783334, "event": "train", "grad_norm": 1.367457628250122, "learning_rate": 1.5857010972450393e-05, "loss": 2.918885886669159, "ncp_loss": 0.8906982690095901, "ntp_loss": 1.1415200531482697, "step": 2130, "tokens": 8724480, "tokens_per_second": 4843.378279589956, "vq_loss": 0.8866675794124603} |
| {"estimated_cost_usd": 0.4624153414868778, "event": "train", "grad_norm": 1.4318757057189941, "learning_rate": 1.5752559383165454e-05, "loss": 3.0475507974624634, "ncp_loss": 0.8939562737941742, "ntp_loss": 1.2639152109622955, "step": 2140, "tokens": 8765440, "tokens_per_second": 4844.252964631486, "vq_loss": 0.8896793276071548} |
| {"estimated_cost_usd": 0.46447571086631106, "event": "train", "grad_norm": 1.3914622068405151, "learning_rate": 1.564815265731837e-05, "loss": 3.012372136116028, "ncp_loss": 0.8897845894098282, "ntp_loss": 1.2346305549144745, "step": 2150, "tokens": 8806400, "tokens_per_second": 4845.300608393293, "vq_loss": 0.8879570215940475} |
| {"estimated_cost_usd": 0.4665554655261334, "event": "train", "grad_norm": 1.4723454713821411, "learning_rate": 1.5543797061687465e-05, "loss": 2.993844151496887, "ncp_loss": 0.901213213801384, "ntp_loss": 1.1943232417106628, "step": 2160, "tokens": 8847360, "tokens_per_second": 4846.137634354546, "vq_loss": 0.8983076363801956} |
| {"estimated_cost_usd": 0.46860598923883334, "event": "train", "grad_norm": 1.3584117889404297, "learning_rate": 1.54394988599821e-05, "loss": 2.9574140310287476, "ncp_loss": 0.9065636843442917, "ntp_loss": 1.1472621858119965, "step": 2170, "tokens": 8888320, "tokens_per_second": 4847.26957767897, "vq_loss": 0.9035881161689758} |
| {"estimated_cost_usd": 0.4706733185493666, "event": "train", "grad_norm": 1.4101145267486572, "learning_rate": 1.533526431246667e-05, "loss": 3.0203333497047424, "ncp_loss": 0.8882939517498016, "ntp_loss": 1.2451023757457733, "step": 2180, "tokens": 8929280, "tokens_per_second": 4848.218543902379, "vq_loss": 0.8869369924068451} |
| {"estimated_cost_usd": 0.4727264039979778, "event": "train", "grad_norm": 1.4040710926055908, "learning_rate": 1.5231099675584884e-05, "loss": 2.9993978142738342, "ncp_loss": 0.8697793185710907, "ntp_loss": 1.2609108090400696, "step": 2190, "tokens": 8970240, "tokens_per_second": 4849.305321808241, "vq_loss": 0.8687076717615128} |
| {"estimated_cost_usd": 0.4747601198982, "event": "train", "grad_norm": 1.3678574562072754, "learning_rate": 1.5127011201584234e-05, "loss": 2.893627405166626, "ncp_loss": 0.8747712224721909, "ntp_loss": 1.1459282040596008, "step": 2200, "tokens": 9011200, "tokens_per_second": 4850.580589448017, "vq_loss": 0.8729279190301895} |
| {"estimated_cost_usd": 0.4768785432970334, "event": "train", "grad_norm": 1.495620846748352, "learning_rate": 1.5023005138140681e-05, "loss": 3.0948259830474854, "ncp_loss": 0.9060954451560974, "ntp_loss": 1.283700406551361, "step": 2210, "tokens": 9052160, "tokens_per_second": 4850.983149260448, "vq_loss": 0.9050301164388657} |
| {"estimated_cost_usd": 0.4790290140203333, "event": "train", "grad_norm": 1.5155699253082275, "learning_rate": 1.4919087727983703e-05, "loss": 2.966345727443695, "ncp_loss": 0.8819701820611954, "ntp_loss": 1.204626441001892, "step": 2220, "tokens": 9093120, "tokens_per_second": 4851.057587995485, "vq_loss": 0.8797491490840912} |
| {"estimated_cost_usd": 0.4811531972184444, "event": "train", "grad_norm": 1.3465029001235962, "learning_rate": 1.4815265208521557e-05, "loss": 2.9265297651290894, "ncp_loss": 0.8834014385938644, "ntp_loss": 1.1612969934940338, "step": 2230, "tokens": 9134080, "tokens_per_second": 4851.396400113971, "vq_loss": 0.8818312436342239} |
| {"estimated_cost_usd": 0.4831993509413667, "event": "train", "grad_norm": 1.3803868293762207, "learning_rate": 1.4711543811466887e-05, "loss": 3.0531144738197327, "ncp_loss": 0.8886392116546631, "ntp_loss": 1.2786604762077332, "step": 2240, "tokens": 9175040, "tokens_per_second": 4852.515716083741, "vq_loss": 0.8858148604631424} |
| {"estimated_cost_usd": 0.4852405522087111, "event": "train", "grad_norm": 1.4083244800567627, "learning_rate": 1.4607929762462703e-05, "loss": 2.9047972559928894, "ncp_loss": 0.8828899711370468, "ntp_loss": 1.1396312415599823, "step": 2250, "tokens": 9216000, "tokens_per_second": 4853.675129334582, "vq_loss": 0.8822760730981827} |
| {"estimated_cost_usd": 0.48735502016414445, "event": "train", "grad_norm": 1.3501378297805786, "learning_rate": 1.4504429280708691e-05, "loss": 3.0485774874687195, "ncp_loss": 0.8748954683542252, "ntp_loss": 1.3021376430988312, "step": 2260, "tokens": 9256960, "tokens_per_second": 4854.094977330454, "vq_loss": 0.8715443015098572} |
| {"estimated_cost_usd": 0.4894783918036778, "event": "train", "grad_norm": 1.482041358947754, "learning_rate": 1.440104857858793e-05, "loss": 2.9917810559272766, "ncp_loss": 0.8755857795476913, "ntp_loss": 1.244093656539917, "step": 2270, "tokens": 9297920, "tokens_per_second": 4854.422893634378, "vq_loss": 0.8721017092466354} |
| {"estimated_cost_usd": 0.4915371001852111, "event": "train", "grad_norm": 1.5038447380065918, "learning_rate": 1.4297793861293966e-05, "loss": 3.0441675186157227, "ncp_loss": 0.8694597780704498, "ntp_loss": 1.3030766546726227, "step": 2280, "tokens": 9338880, "tokens_per_second": 4855.386634635301, "vq_loss": 0.871630996465683} |
| {"estimated_cost_usd": 0.49363385153632217, "event": "train", "grad_norm": 1.4198001623153687, "learning_rate": 1.4194671326458416e-05, "loss": 2.9859650135040283, "ncp_loss": 0.8762255609035492, "ntp_loss": 1.234002709388733, "step": 2290, "tokens": 9379840, "tokens_per_second": 4855.9680718044165, "vq_loss": 0.8757367879152298} |
| {"estimated_cost_usd": 0.4957522421568334, "event": "train", "grad_norm": 1.422979474067688, "learning_rate": 1.4091687163778942e-05, "loss": 2.9388132095336914, "ncp_loss": 0.873275876045227, "ntp_loss": 1.1957252621650696, "step": 2300, "tokens": 9420800, "tokens_per_second": 4856.332605382636, "vq_loss": 0.8698121160268784} |
| {"estimated_cost_usd": 0.49787050459118887, "event": "train", "grad_norm": 1.3890283107757568, "learning_rate": 1.3988847554647707e-05, "loss": 2.957785964012146, "ncp_loss": 0.8958559930324554, "ntp_loss": 1.1695477366447449, "step": 2310, "tokens": 9461760, "tokens_per_second": 4856.695287299263, "vq_loss": 0.8923821449279785} |
| {"estimated_cost_usd": 0.49990706823513337, "event": "train", "grad_norm": 1.3942558765411377, "learning_rate": 1.3886158671780402e-05, "loss": 3.004215180873871, "ncp_loss": 0.8770425617694855, "ntp_loss": 1.2507676482200623, "step": 2320, "tokens": 9502720, "tokens_per_second": 4857.848674679363, "vq_loss": 0.8764049708843231} |
| {"estimated_cost_usd": 0.5021170080842666, "event": "train", "grad_norm": 1.3990421295166016, "learning_rate": 1.3783626678845695e-05, "loss": 2.957097589969635, "ncp_loss": 0.8688305169343948, "ntp_loss": 1.220785528421402, "step": 2330, "tokens": 9543680, "tokens_per_second": 4857.314938901919, "vq_loss": 0.8674815595149994} |
| {"estimated_cost_usd": 0.5042884598197778, "event": "train", "grad_norm": 1.4946736097335815, "learning_rate": 1.3681257730095295e-05, "loss": 2.8287470936775208, "ncp_loss": 0.8648127019405365, "ntp_loss": 1.1027088910341263, "step": 2340, "tokens": 9584640, "tokens_per_second": 4857.156558520826, "vq_loss": 0.8612255305051804} |
| {"estimated_cost_usd": 0.5063865423487889, "event": "train", "grad_norm": 1.5582492351531982, "learning_rate": 1.3579057969994544e-05, "loss": 2.924481987953186, "ncp_loss": 0.8612096458673477, "ntp_loss": 1.204342782497406, "step": 2350, "tokens": 9625600, "tokens_per_second": 4857.703255986694, "vq_loss": 0.8589295148849487} |
| {"estimated_cost_usd": 0.5085160265393667, "event": "train", "grad_norm": 1.5036078691482544, "learning_rate": 1.3477033532853635e-05, "loss": 2.9210087060928345, "ncp_loss": 0.8575181812047958, "ntp_loss": 1.2093437016010284, "step": 2360, "tokens": 9666560, "tokens_per_second": 4857.945437674165, "vq_loss": 0.8541467934846878} |
| {"estimated_cost_usd": 0.5107111516604445, "event": "train", "grad_norm": 1.3924431800842285, "learning_rate": 1.3375190542459388e-05, "loss": 2.8783710598945618, "ncp_loss": 0.8687876462936401, "ntp_loss": 1.1435201615095139, "step": 2370, "tokens": 9707520, "tokens_per_second": 4857.561184244668, "vq_loss": 0.8660631775856018} |
| {"estimated_cost_usd": 0.5127668293754223, "event": "train", "grad_norm": 1.5280189514160156, "learning_rate": 1.3273535111707669e-05, "loss": 2.781075596809387, "ncp_loss": 0.843139573931694, "ntp_loss": 1.0987917184829712, "step": 2380, "tokens": 9748480, "tokens_per_second": 4858.501134437136, "vq_loss": 0.8391442745923996} |
| {"estimated_cost_usd": 0.5148952565215222, "event": "train", "grad_norm": 1.3991601467132568, "learning_rate": 1.3172073342236532e-05, "loss": 2.899665415287018, "ncp_loss": 0.8666919320821762, "ntp_loss": 1.1702224910259247, "step": 2390, "tokens": 9789440, "tokens_per_second": 4858.74698997777, "vq_loss": 0.8627510666847229} |
| {"estimated_cost_usd": 0.5170002933164777, "event": "train", "grad_norm": 1.4094661474227905, "learning_rate": 1.3070811324059939e-05, "loss": 2.943657100200653, "ncp_loss": 0.8567293435335159, "ntp_loss": 1.2336839139461517, "step": 2400, "tokens": 9830400, "tokens_per_second": 4859.210653862243, "vq_loss": 0.8532438278198242} |
| {"estimated_cost_usd": 0.5191066101585445, "event": "train", "grad_norm": 1.4481171369552612, "learning_rate": 1.2969755135202216e-05, "loss": 2.8787827491760254, "ncp_loss": 0.8653837442398071, "ntp_loss": 1.1504112780094147, "step": 2410, "tokens": 9871360, "tokens_per_second": 4859.658574022814, "vq_loss": 0.8629876971244812} |
| {"estimated_cost_usd": 0.5211791803510445, "event": "train", "grad_norm": 1.458057165145874, "learning_rate": 1.2868910841333263e-05, "loss": 2.924189805984497, "ncp_loss": 0.8546620607376099, "ntp_loss": 1.218427300453186, "step": 2420, "tokens": 9912320, "tokens_per_second": 4860.417568365302, "vq_loss": 0.8511004596948624} |
| {"estimated_cost_usd": 0.5232636858234, "event": "train", "grad_norm": 1.4278463125228882, "learning_rate": 1.2768284495404457e-05, "loss": 3.005406081676483, "ncp_loss": 0.8648358434438705, "ntp_loss": 1.2780366241931915, "step": 2430, "tokens": 9953280, "tokens_per_second": 4861.059670130565, "vq_loss": 0.8625335544347763} |
| {"estimated_cost_usd": 0.5253544250033888, "event": "train", "grad_norm": 1.3680659532546997, "learning_rate": 1.2667882137285345e-05, "loss": 3.0495075583457947, "ncp_loss": 0.8618465662002563, "ntp_loss": 1.3281349837779999, "step": 2440, "tokens": 9994240, "tokens_per_second": 4861.638988838973, "vq_loss": 0.8595258891582489} |
| {"estimated_cost_usd": 0.5275448198833889, "event": "train", "grad_norm": 1.4418269395828247, "learning_rate": 1.2567709793401106e-05, "loss": 3.027544140815735, "ncp_loss": 0.8682086765766144, "ntp_loss": 1.294343739748001, "step": 2450, "tokens": 10035200, "tokens_per_second": 4861.2952197653885, "vq_loss": 0.8649917244911194} |
| {"estimated_cost_usd": 0.5296455766799, "event": "train", "grad_norm": 1.3137733936309814, "learning_rate": 1.2467773476370832e-05, "loss": 2.962594211101532, "ncp_loss": 0.8652152121067047, "ntp_loss": 1.234784722328186, "step": 2460, "tokens": 10076160, "tokens_per_second": 4861.776969437284, "vq_loss": 0.8625943660736084} |
| {"estimated_cost_usd": 0.5316388631576332, "event": "train", "grad_norm": 1.592400074005127, "learning_rate": 1.2368079184646647e-05, "loss": 2.9078630208969116, "ncp_loss": 0.8639370203018188, "ntp_loss": 1.1826268434524536, "step": 2470, "tokens": 10117120, "tokens_per_second": 4863.2378131009855, "vq_loss": 0.861299142241478} |
| {"estimated_cost_usd": 0.5336169460792778, "event": "train", "grad_norm": 1.4462000131607056, "learning_rate": 1.2268632902153627e-05, "loss": 2.9126482605934143, "ncp_loss": 0.8520192056894302, "ntp_loss": 1.210649698972702, "step": 2480, "tokens": 10158080, "tokens_per_second": 4864.826345661266, "vq_loss": 0.849979355931282} |
| {"estimated_cost_usd": 0.535599058996011, "event": "train", "grad_norm": 1.4563510417938232, "learning_rate": 1.216944059793068e-05, "loss": 2.879419267177582, "ncp_loss": 0.8735454678535461, "ntp_loss": 1.135177418589592, "step": 2490, "tokens": 10199040, "tokens_per_second": 4866.366528386199, "vq_loss": 0.8706963062286377} |
| {"estimated_cost_usd": 0.5375898436449111, "event": "train", "grad_norm": 1.4946863651275635, "learning_rate": 1.207050822577223e-05, "loss": 2.903420627117157, "ncp_loss": 0.8494613617658615, "ntp_loss": 1.2069115340709686, "step": 2500, "tokens": 10240000, "tokens_per_second": 4867.816830664302, "vq_loss": 0.8470477610826492} |
| {"estimated_cost_usd": 0.5396453226869111, "event": "train", "grad_norm": 1.3950600624084473, "learning_rate": 1.1971841723870855e-05, "loss": 2.9589011669158936, "ncp_loss": 0.8611708134412766, "ntp_loss": 1.2387627363204956, "step": 2510, "tokens": 10280960, "tokens_per_second": 4868.672689244769, "vq_loss": 0.8589677214622498} |
| {"estimated_cost_usd": 0.5416580241681889, "event": "train", "grad_norm": 1.416367530822754, "learning_rate": 1.1873447014460886e-05, "loss": 2.9134625792503357, "ncp_loss": 0.8698757886886597, "ntp_loss": 1.1765626072883606, "step": 2520, "tokens": 10321920, "tokens_per_second": 4869.906624296469, "vq_loss": 0.8670242428779602} |
| {"estimated_cost_usd": 0.5436694709588333, "event": "train", "grad_norm": 1.4656766653060913, "learning_rate": 1.1775330003462916e-05, "loss": 2.9371326565742493, "ncp_loss": 0.8737063705921173, "ntp_loss": 1.1960726082324982, "step": 2530, "tokens": 10362880, "tokens_per_second": 4871.142664834466, "vq_loss": 0.8673537075519562} |
| {"estimated_cost_usd": 0.5456812236456444, "event": "train", "grad_norm": 1.4069706201553345, "learning_rate": 1.1677496580129317e-05, "loss": 2.930539071559906, "ncp_loss": 0.845559373497963, "ntp_loss": 1.243670254945755, "step": 2540, "tokens": 10403840, "tokens_per_second": 4872.3668616416635, "vq_loss": 0.8413094133138657} |
| {"estimated_cost_usd": 0.5477108844611, "event": "train", "grad_norm": 1.3789764642715454, "learning_rate": 1.1579952616690748e-05, "loss": 2.9172300696372986, "ncp_loss": 0.8440687507390976, "ntp_loss": 1.230836570262909, "step": 2550, "tokens": 10444800, "tokens_per_second": 4873.422716974037, "vq_loss": 0.8423247188329697} |
| {"estimated_cost_usd": 0.5497212345389111, "event": "train", "grad_norm": 1.3635423183441162, "learning_rate": 1.1482703968003695e-05, "loss": 3.0398390889167786, "ncp_loss": 0.8553875088691711, "ntp_loss": 1.3322560489177704, "step": 2560, "tokens": 10485760, "tokens_per_second": 4874.642007361906, "vq_loss": 0.8521955609321594} |
| {"estimated_cost_usd": 0.5517286864056332, "event": "train", "grad_norm": 1.4354417324066162, "learning_rate": 1.1385756471199046e-05, "loss": 2.8240047693252563, "ncp_loss": 0.8399436324834824, "ntp_loss": 1.1479457318782806, "step": 2570, "tokens": 10526720, "tokens_per_second": 4875.878024946413, "vq_loss": 0.8361153900623322} |
| {"estimated_cost_usd": 0.5537385459422555, "event": "train", "grad_norm": 1.4413107633590698, "learning_rate": 1.1289115945331711e-05, "loss": 2.884438157081604, "ncp_loss": 0.8536589592695236, "ntp_loss": 1.1811316311359406, "step": 2580, "tokens": 10567680, "tokens_per_second": 4877.083874914061, "vq_loss": 0.8496475666761398} |
| {"estimated_cost_usd": 0.5557387691558444, "event": "train", "grad_norm": 1.4032732248306274, "learning_rate": 1.1192788191031372e-05, "loss": 2.8896318674087524, "ncp_loss": 0.8405941426753998, "ntp_loss": 1.2118710279464722, "step": 2590, "tokens": 10608640, "tokens_per_second": 4878.3655907378725, "vq_loss": 0.8371667712926865} |
| {"estimated_cost_usd": 0.5577741946797999, "event": "train", "grad_norm": 1.439794659614563, "learning_rate": 1.1096778990154309e-05, "loss": 2.832208037376404, "ncp_loss": 0.8505644798278809, "ntp_loss": 1.1334141194820404, "step": 2600, "tokens": 10649600, "tokens_per_second": 4879.330149016317, "vq_loss": 0.8482294380664825} |
| {"estimated_cost_usd": 0.5598015842483223, "event": "train", "grad_norm": 1.5377362966537476, "learning_rate": 1.1001094105436334e-05, "loss": 2.8559893369674683, "ncp_loss": 0.8233509808778763, "ntp_loss": 1.212910145521164, "step": 2610, "tokens": 10690560, "tokens_per_second": 4880.35774973459, "vq_loss": 0.8197281658649445} |
| {"estimated_cost_usd": 0.561823258630411, "event": "train", "grad_norm": 1.464074969291687, "learning_rate": 1.0905739280146928e-05, "loss": 2.803025782108307, "ncp_loss": 0.845609650015831, "ntp_loss": 1.115767478942871, "step": 2620, "tokens": 10731520, "tokens_per_second": 4881.42759030857, "vq_loss": 0.8416487276554108} |
| {"estimated_cost_usd": 0.5638200652205778, "event": "train", "grad_norm": 1.490684151649475, "learning_rate": 1.0810720237744497e-05, "loss": 2.827532470226288, "ncp_loss": 0.8346540331840515, "ntp_loss": 1.1610781848430634, "step": 2630, "tokens": 10772480, "tokens_per_second": 4882.70510563347, "vq_loss": 0.8318001925945282} |
| {"estimated_cost_usd": 0.5658453566705778, "event": "train", "grad_norm": 1.5168988704681396, "learning_rate": 1.0716042681532823e-05, "loss": 2.8265199065208435, "ncp_loss": 0.8483017981052399, "ntp_loss": 1.1331072449684143, "step": 2640, "tokens": 10813440, "tokens_per_second": 4883.727743082772, "vq_loss": 0.8451108783483505} |
| {"estimated_cost_usd": 0.5678550680787665, "event": "train", "grad_norm": 1.4225177764892578, "learning_rate": 1.0621712294318767e-05, "loss": 2.937989115715027, "ncp_loss": 0.8524457067251205, "ntp_loss": 1.2386627793312073, "step": 2650, "tokens": 10854400, "tokens_per_second": 4884.87710712385, "vq_loss": 0.8468806445598602} |
| {"estimated_cost_usd": 0.5698586804246444, "event": "train", "grad_norm": 1.4580308198928833, "learning_rate": 1.0527734738071144e-05, "loss": 2.938201665878296, "ncp_loss": 0.851549819111824, "ntp_loss": 1.2391871213912964, "step": 2660, "tokens": 10895360, "tokens_per_second": 4886.070658260282, "vq_loss": 0.8474647104740143} |
| {"estimated_cost_usd": 0.5718810751143444, "event": "train", "grad_norm": 1.4362958669662476, "learning_rate": 1.0434115653580886e-05, "loss": 2.854145050048828, "ncp_loss": 0.8371146321296692, "ntp_loss": 1.1811955273151398, "step": 2670, "tokens": 10936320, "tokens_per_second": 4887.095333194094, "vq_loss": 0.8358348309993744} |
| {"estimated_cost_usd": 0.5739098936112776, "event": "train", "grad_norm": 1.4719057083129883, "learning_rate": 1.034086066012247e-05, "loss": 2.890119969844818, "ncp_loss": 0.8340090364217758, "ntp_loss": 1.2252540290355682, "step": 2680, "tokens": 10977280, "tokens_per_second": 4888.058073431622, "vq_loss": 0.8308568745851517} |
| {"estimated_cost_usd": 0.5759123861206332, "event": "train", "grad_norm": 1.4984855651855469, "learning_rate": 1.0247975355116617e-05, "loss": 2.7937268018722534, "ncp_loss": 0.8515682518482208, "ntp_loss": 1.092770904302597, "step": 2690, "tokens": 11018240, "tokens_per_second": 4889.237516511131, "vq_loss": 0.8493875414133072} |
| {"estimated_cost_usd": 0.5779118060929554, "event": "train", "grad_norm": 1.5758388042449951, "learning_rate": 1.0155465313794357e-05, "loss": 2.8217203617095947, "ncp_loss": 0.8510964512825012, "ntp_loss": 1.121936947107315, "step": 2700, "tokens": 11059200, "tokens_per_second": 4890.434786420346, "vq_loss": 0.8486869633197784} |
| {"estimated_cost_usd": 0.5798983091546223, "event": "train", "grad_norm": 1.3615825176239014, "learning_rate": 1.0063336088862337e-05, "loss": 2.8073025345802307, "ncp_loss": 0.839846059679985, "ntp_loss": 1.1315629333257675, "step": 2710, "tokens": 11100160, "tokens_per_second": 4891.732758612312, "vq_loss": 0.8358935415744781} |
| {"estimated_cost_usd": 0.5819368693263444, "event": "train", "grad_norm": 1.6002275943756104, "learning_rate": 9.971593210169574e-06, "loss": 2.8655338287353516, "ncp_loss": 0.8350136876106262, "ntp_loss": 1.197737216949463, "step": 2720, "tokens": 11141120, "tokens_per_second": 4892.5841636516825, "vq_loss": 0.8327829837799072} |
| {"estimated_cost_usd": 0.5840992116304887, "event": "train", "grad_norm": 1.479616403579712, "learning_rate": 9.880242184375524e-06, "loss": 2.8725239634513855, "ncp_loss": 0.8401286005973816, "ntp_loss": 1.1964538395404816, "step": 2730, "tokens": 11182080, "tokens_per_second": 4892.392610306176, "vq_loss": 0.8359415680170059} |
| {"estimated_cost_usd": 0.5861956560583556, "event": "train", "grad_norm": 1.406265377998352, "learning_rate": 9.789288494619545e-06, "loss": 2.8327385783195496, "ncp_loss": 0.833938255906105, "ntp_loss": 1.168732926249504, "step": 2740, "tokens": 11223040, "tokens_per_second": 4892.752432707729, "vq_loss": 0.8300673812627792} |
| {"estimated_cost_usd": 0.5883631006755999, "event": "train", "grad_norm": 1.463039517402649, "learning_rate": 9.698737600191804e-06, "loss": 2.866764187812805, "ncp_loss": 0.8293488621711731, "ntp_loss": 1.2122209966182709, "step": 2750, "tokens": 11264000, "tokens_per_second": 4892.519218952365, "vq_loss": 0.8251943737268448} |
| {"estimated_cost_usd": 0.5905487612925889, "event": "train", "grad_norm": 1.5515508651733398, "learning_rate": 9.608594936205588e-06, "loss": 2.7519878149032593, "ncp_loss": 0.8301757723093033, "ntp_loss": 1.0932117104530334, "step": 2760, "tokens": 11304960, "tokens_per_second": 4892.136810192967, "vq_loss": 0.828600287437439} |
| {"estimated_cost_usd": 0.5926220887179222, "event": "train", "grad_norm": 1.434829592704773, "learning_rate": 9.518865913271065e-06, "loss": 2.8107200860977173, "ncp_loss": 0.8351944983005524, "ntp_loss": 1.1432644128799438, "step": 2770, "tokens": 11345920, "tokens_per_second": 4892.684468042174, "vq_loss": 0.8322611451148987} |
| {"estimated_cost_usd": 0.594782293675511, "event": "train", "grad_norm": 1.3786687850952148, "learning_rate": 9.429555917170535e-06, "loss": 2.786289691925049, "ncp_loss": 0.846234068274498, "ntp_loss": 1.0973027497529984, "step": 2780, "tokens": 11386880, "tokens_per_second": 4892.513572423208, "vq_loss": 0.8427528589963913} |
| {"estimated_cost_usd": 0.5969264940268777, "event": "train", "grad_norm": 1.5323760509490967, "learning_rate": 9.34067030853515e-06, "loss": 2.9256179332733154, "ncp_loss": 0.8447887003421783, "ntp_loss": 1.240630865097046, "step": 2790, "tokens": 11427840, "tokens_per_second": 4892.47508566524, "vq_loss": 0.8401983976364136} |
| {"estimated_cost_usd": 0.5990504263688444, "event": "train", "grad_norm": 1.4452179670333862, "learning_rate": 9.252214422523181e-06, "loss": 2.8950467705726624, "ncp_loss": 0.8315692991018295, "ntp_loss": 1.2343993484973907, "step": 2800, "tokens": 11468800, "tokens_per_second": 4892.602402975249, "vq_loss": 0.8290781527757645} |
| {"estimated_cost_usd": 0.6011770893531, "event": "train", "grad_norm": 1.3944013118743896, "learning_rate": 9.16419356849975e-06, "loss": 2.9021041989326477, "ncp_loss": 0.8395830243825912, "ntp_loss": 1.225549042224884, "step": 2810, "tokens": 11509760, "tokens_per_second": 4892.706597113012, "vq_loss": 0.8369722217321396} |
| {"estimated_cost_usd": 0.603560835874911, "event": "train", "grad_norm": 1.4276716709136963, "learning_rate": 9.076613029718164e-06, "loss": 2.834649980068207, "ncp_loss": 0.8255891352891922, "ntp_loss": 1.1859638094902039, "step": 2820, "tokens": 11550720, "tokens_per_second": 4890.725990177471, "vq_loss": 0.823096975684166} |
| {"estimated_cost_usd": 0.6056988995602443, "event": "train", "grad_norm": 1.448679804801941, "learning_rate": 8.989478063002811e-06, "loss": 2.770165979862213, "ncp_loss": 0.8226745575666428, "ntp_loss": 1.1275648176670074, "step": 2830, "tokens": 11591680, "tokens_per_second": 4890.743939559663, "vq_loss": 0.8199265599250793} |
| {"estimated_cost_usd": 0.6078447270195222, "event": "train", "grad_norm": 1.438356637954712, "learning_rate": 8.902793898433615e-06, "loss": 2.9104966521263123, "ncp_loss": 0.8509770780801773, "ntp_loss": 1.2134118974208832, "step": 2840, "tokens": 11632640, "tokens_per_second": 4890.699294792601, "vq_loss": 0.8461076617240906} |
| {"estimated_cost_usd": 0.6100452709416222, "event": "train", "grad_norm": 1.372109293937683, "learning_rate": 8.816565739032115e-06, "loss": 2.8956193327903748, "ncp_loss": 0.8265251070261002, "ntp_loss": 1.2464424669742584, "step": 2850, "tokens": 11673600, "tokens_per_second": 4890.2163092398, "vq_loss": 0.822651818394661} |
| {"estimated_cost_usd": 0.612282533170022, "event": "train", "grad_norm": 1.5182287693023682, "learning_rate": 8.730798760449167e-06, "loss": 2.8754685521125793, "ncp_loss": 0.8437790721654892, "ntp_loss": 1.191437691450119, "step": 2860, "tokens": 11714560, "tokens_per_second": 4889.44356029437, "vq_loss": 0.8402518182992935} |
| {"estimated_cost_usd": 0.614545187117311, "event": "train", "grad_norm": 1.544616460800171, "learning_rate": 8.645498110654299e-06, "loss": 2.8720650672912598, "ncp_loss": 0.8370656818151474, "ntp_loss": 1.2007762789726257, "step": 2870, "tokens": 11755520, "tokens_per_second": 4888.474448130325, "vq_loss": 0.8342231214046478} |
| {"estimated_cost_usd": 0.6169082779082443, "event": "train", "grad_norm": 1.459849238395691, "learning_rate": 8.560668909626695e-06, "loss": 2.8320552110671997, "ncp_loss": 0.8250718414783478, "ntp_loss": 1.18673837184906, "step": 2880, "tokens": 11796480, "tokens_per_second": 4886.716725899379, "vq_loss": 0.8202449679374695} |
| {"estimated_cost_usd": 0.6191793331209888, "event": "train", "grad_norm": 1.572809100151062, "learning_rate": 8.476316249047887e-06, "loss": 2.873945653438568, "ncp_loss": 0.8333158791065216, "ntp_loss": 1.2128281593322754, "step": 2890, "tokens": 11837440, "tokens_per_second": 4885.69852664065, "vq_loss": 0.8278016149997711} |
| {"estimated_cost_usd": 0.6214640705141887, "event": "train", "grad_norm": 1.5425288677215576, "learning_rate": 8.392445191996153e-06, "loss": 2.866956889629364, "ncp_loss": 0.8358407765626907, "ntp_loss": 1.1979272961616516, "step": 2900, "tokens": 11878400, "tokens_per_second": 4884.5802277829425, "vq_loss": 0.8331888169050217} |
| {"estimated_cost_usd": 0.6237666918512778, "event": "train", "grad_norm": 1.4339513778686523, "learning_rate": 8.309060772642596e-06, "loss": 2.7579122185707092, "ncp_loss": 0.8242822885513306, "ntp_loss": 1.1137436628341675, "step": 2910, "tokens": 11919360, "tokens_per_second": 4883.330107970764, "vq_loss": 0.8198862373828888} |
| {"estimated_cost_usd": 0.6260003936666444, "event": "train", "grad_norm": 1.5737966299057007, "learning_rate": 8.226167995948982e-06, "loss": 2.8617185950279236, "ncp_loss": 0.8271270245313644, "ntp_loss": 1.2141018211841583, "step": 2920, "tokens": 11960320, "tokens_per_second": 4882.626677467991, "vq_loss": 0.8204898089170456} |
| {"estimated_cost_usd": 0.6281891218943221, "event": "train", "grad_norm": 1.467522382736206, "learning_rate": 8.143771837367358e-06, "loss": 2.738552153110504, "ncp_loss": 0.8238667696714401, "ntp_loss": 1.09525465965271, "step": 2930, "tokens": 12001280, "tokens_per_second": 4882.277758215823, "vq_loss": 0.8194306939840317} |
| {"estimated_cost_usd": 0.6303826522199333, "event": "train", "grad_norm": 1.4690940380096436, "learning_rate": 8.061877242541366e-06, "loss": 2.6565127968788147, "ncp_loss": 0.8058986067771912, "ntp_loss": 1.0489852577447891, "step": 2940, "tokens": 12042240, "tokens_per_second": 4881.894072585682, "vq_loss": 0.8016288727521896} |
| {"estimated_cost_usd": 0.6325557464442222, "event": "train", "grad_norm": 1.4478440284729004, "learning_rate": 7.980489127009422e-06, "loss": 2.808457612991333, "ncp_loss": 0.8347622603178024, "ntp_loss": 1.1427941918373108, "step": 2950, "tokens": 12083200, "tokens_per_second": 4881.670755893098, "vq_loss": 0.8309011608362198} |
| {"estimated_cost_usd": 0.6347075841502888, "event": "train", "grad_norm": 1.4966562986373901, "learning_rate": 7.899612375909657e-06, "loss": 2.7120361924171448, "ncp_loss": 0.803942933678627, "ntp_loss": 1.1057987660169601, "step": 2960, "tokens": 12124160, "tokens_per_second": 4881.612449286241, "vq_loss": 0.8022944629192352} |
| {"estimated_cost_usd": 0.6369433992820666, "event": "train", "grad_norm": 1.4988206624984741, "learning_rate": 7.819251843686727e-06, "loss": 2.7860040068626404, "ncp_loss": 0.821291908621788, "ntp_loss": 1.1486530900001526, "step": 2970, "tokens": 12165120, "tokens_per_second": 4880.910931024906, "vq_loss": 0.8160589635372162} |
| {"estimated_cost_usd": 0.6392196326483666, "event": "train", "grad_norm": 1.4642903804779053, "learning_rate": 7.739412353800392e-06, "loss": 2.8095234036445618, "ncp_loss": 0.8300954550504684, "ntp_loss": 1.1517457365989685, "step": 2980, "tokens": 12206080, "tokens_per_second": 4879.90574168033, "vq_loss": 0.8276822865009308} |
| {"estimated_cost_usd": 0.6414590616198778, "event": "train", "grad_norm": 1.5597060918807983, "learning_rate": 7.660098698436024e-06, "loss": 2.754862070083618, "ncp_loss": 0.8070948570966721, "ntp_loss": 1.143689602613449, "step": 2990, "tokens": 12247040, "tokens_per_second": 4879.187618314135, "vq_loss": 0.804077610373497} |
| {"estimated_cost_usd": 0.6437824643161444, "event": "train", "grad_norm": 1.4263041019439697, "learning_rate": 7.581315638216972e-06, "loss": 2.6551403403282166, "ncp_loss": 0.8163608908653259, "ntp_loss": 1.0270568281412125, "step": 3000, "tokens": 12288000, "tokens_per_second": 4877.838152989153, "vq_loss": 0.8117225766181946} |
| {"estimated_cost_usd": 0.6461231334328776, "event": "train", "grad_norm": 1.467634677886963, "learning_rate": 7.503067901918801e-06, "loss": 2.86636084318161, "ncp_loss": 0.8338451683521271, "ntp_loss": 1.203496515750885, "step": 3010, "tokens": 12328960, "tokens_per_second": 4876.368077834092, "vq_loss": 0.8290191888809204} |
| {"estimated_cost_usd": 0.6483701993675777, "event": "train", "grad_norm": 1.4393540620803833, "learning_rate": 7.4253601861854675e-06, "loss": 2.8197575211524963, "ncp_loss": 0.8144945204257965, "ntp_loss": 1.191937506198883, "step": 3020, "tokens": 12369920, "tokens_per_second": 4875.612390670059, "vq_loss": 0.8133255541324615} |
| {"estimated_cost_usd": 0.6505773227997556, "event": "train", "grad_norm": 1.5196269750595093, "learning_rate": 7.3481971552474016e-06, "loss": 2.747621178627014, "ncp_loss": 0.8007507771253586, "ntp_loss": 1.148940920829773, "step": 3030, "tokens": 12410880, "tokens_per_second": 4875.161217861197, "vq_loss": 0.7979294508695602} |
| {"estimated_cost_usd": 0.6527714820434999, "event": "train", "grad_norm": 1.5625007152557373, "learning_rate": 7.271583440641576e-06, "loss": 2.837472975254059, "ncp_loss": 0.8141249716281891, "ntp_loss": 1.2143778502941132, "step": 3040, "tokens": 12451840, "tokens_per_second": 4874.809908863075, "vq_loss": 0.8089702278375626} |
| {"estimated_cost_usd": 0.6550589794591889, "event": "train", "grad_norm": 1.4961364269256592, "learning_rate": 7.195523640933472e-06, "loss": 2.6998652815818787, "ncp_loss": 0.8157413750886917, "ntp_loss": 1.0709592998027802, "step": 3050, "tokens": 12492800, "tokens_per_second": 4873.766400515922, "vq_loss": 0.8131646066904068} |
| {"estimated_cost_usd": 0.657245019543211, "event": "train", "grad_norm": 1.533850073814392, "learning_rate": 7.120022321441082e-06, "loss": 2.836397647857666, "ncp_loss": 0.8154711276292801, "ntp_loss": 1.2103134989738464, "step": 3060, "tokens": 12533760, "tokens_per_second": 4873.482346395189, "vq_loss": 0.8106129616498947} |
| {"estimated_cost_usd": 0.6594998762055555, "event": "train", "grad_norm": 1.4933112859725952, "learning_rate": 7.0450840139608945e-06, "loss": 2.8360917568206787, "ncp_loss": 0.8259681761264801, "ntp_loss": 1.1871113777160645, "step": 3070, "tokens": 12574720, "tokens_per_second": 4872.691673643236, "vq_loss": 0.8230120986700058} |
| {"codebook_perplexity": 2.3485846519470215, "codebook_usage": 0.3142361044883728, "event": "eval", "loss": 3.464422821998596, "ncp_loss": 0.8307736553251743, "ntp_loss": 1.80772864818573, "step": 3072, "tokens": 12582912, "vq_loss": 0.8259205296635628} |
| {"estimated_cost_usd": 0.6623663790832555, "event": "train", "grad_norm": 1.620055913925171, "learning_rate": 6.970713216495845e-06, "loss": 2.667180120944977, "ncp_loss": 0.8119617104530334, "ntp_loss": 1.047950103878975, "step": 3080, "tokens": 12615680, "tokens_per_second": 4867.407545010482, "vq_loss": 0.8072683066129684} |
| {"estimated_cost_usd": 0.6646591106357777, "event": "train", "grad_norm": 1.55989408493042, "learning_rate": 6.8969143929853895e-06, "loss": 2.841669201850891, "ncp_loss": 0.8152209222316742, "ntp_loss": 1.2159052789211273, "step": 3090, "tokens": 12656640, "tokens_per_second": 4866.366254383754, "vq_loss": 0.8105429708957672} |
| {"estimated_cost_usd": 0.6668565519680221, "event": "train", "grad_norm": 1.516377568244934, "learning_rate": 6.823691973037514e-06, "loss": 2.85527366399765, "ncp_loss": 0.8298588395118713, "ntp_loss": 1.1986151039600372, "step": 3100, "tokens": 12697600, "tokens_per_second": 4866.027352727918, "vq_loss": 0.8267997056245804} |
| {"estimated_cost_usd": 0.6692038001031443, "event": "train", "grad_norm": 1.5180660486221313, "learning_rate": 6.7510503516628995e-06, "loss": 2.757284104824066, "ncp_loss": 0.8187423944473267, "ntp_loss": 1.1233327388763428, "step": 3110, "tokens": 12738560, "tokens_per_second": 4864.601452167519, "vq_loss": 0.8152089416980743} |
| {"estimated_cost_usd": 0.6715590476495109, "event": "train", "grad_norm": 1.5500913858413696, "learning_rate": 6.678993889011084e-06, "loss": 2.7486246824264526, "ncp_loss": 0.8021566569805145, "ntp_loss": 1.1480889320373535, "step": 3120, "tokens": 12779520, "tokens_per_second": 4863.127590587992, "vq_loss": 0.7983791083097458} |
| {"estimated_cost_usd": 0.6737077527313, "event": "train", "grad_norm": 1.4642893075942993, "learning_rate": 6.607526910108783e-06, "loss": 2.7214320302009583, "ncp_loss": 0.795840248465538, "ntp_loss": 1.1332747340202332, "step": 3130, "tokens": 12820480, "tokens_per_second": 4863.154499270871, "vq_loss": 0.792317122220993} |
| {"estimated_cost_usd": 0.6759110892461889, "event": "train", "grad_norm": 1.4761862754821777, "learning_rate": 6.536653704600284e-06, "loss": 2.746337115764618, "ncp_loss": 0.8126169741153717, "ntp_loss": 1.127975881099701, "step": 3140, "tokens": 12861440, "tokens_per_second": 4862.788163617893, "vq_loss": 0.8057443499565125} |
| {"estimated_cost_usd": 0.6781385025582111, "event": "train", "grad_norm": 1.4970848560333252, "learning_rate": 6.466378526489943e-06, "loss": 2.747775614261627, "ncp_loss": 0.808898851275444, "ntp_loss": 1.1331592500209808, "step": 3150, "tokens": 12902400, "tokens_per_second": 4862.25157185639, "vq_loss": 0.8057175576686859} |
| {"estimated_cost_usd": 0.6803188516093778, "event": "train", "grad_norm": 1.4700812101364136, "learning_rate": 6.396705593886895e-06, "loss": 2.6903494000434875, "ncp_loss": 0.8248207867145538, "ntp_loss": 1.0463350415229797, "step": 3160, "tokens": 12943360, "tokens_per_second": 4862.054825808035, "vq_loss": 0.8191935569047928} |
| {"estimated_cost_usd": 0.6824443835755332, "event": "train", "grad_norm": 1.4886997938156128, "learning_rate": 6.327639088751837e-06, "loss": 2.774125099182129, "ncp_loss": 0.8109614700078964, "ntp_loss": 1.157344400882721, "step": 3170, "tokens": 12984320, "tokens_per_second": 4862.249863829159, "vq_loss": 0.8058192729949951} |
| {"estimated_cost_usd": 0.6846687567168889, "event": "train", "grad_norm": 1.5075109004974365, "learning_rate": 6.2591831566460215e-06, "loss": 2.7482938170433044, "ncp_loss": 0.8126508593559265, "ntp_loss": 1.1275453865528107, "step": 3180, "tokens": 13025280, "tokens_per_second": 4861.741731327576, "vq_loss": 0.8080975562334061} |
| {"estimated_cost_usd": 0.6868563164037554, "event": "train", "grad_norm": 1.5023605823516846, "learning_rate": 6.191341906482431e-06, "loss": 2.7658446431159973, "ncp_loss": 0.809713289141655, "ntp_loss": 1.1520277857780457, "step": 3190, "tokens": 13066240, "tokens_per_second": 4861.497437637839, "vq_loss": 0.8041035532951355} |
| {"estimated_cost_usd": 0.689077125421411, "event": "train", "grad_norm": 1.4507489204406738, "learning_rate": 6.124119410279149e-06, "loss": 2.7745911478996277, "ncp_loss": 0.805499255657196, "ntp_loss": 1.1670068204402924, "step": 3200, "tokens": 13107200, "tokens_per_second": 4861.020129973535, "vq_loss": 0.8020851463079453} |
| {"estimated_cost_usd": 0.6912142239183888, "event": "train", "grad_norm": 1.4432424306869507, "learning_rate": 6.057519702914963e-06, "loss": 2.6939945220947266, "ncp_loss": 0.8241136372089386, "ntp_loss": 1.0499893128871918, "step": 3210, "tokens": 13148160, "tokens_per_second": 4861.134532627986, "vq_loss": 0.819891631603241} |
| {"estimated_cost_usd": 0.6934206454580334, "event": "train", "grad_norm": 1.4949779510498047, "learning_rate": 5.991546781887144e-06, "loss": 2.7309908270835876, "ncp_loss": 0.791834682226181, "ntp_loss": 1.1532334387302399, "step": 3220, "tokens": 13189120, "tokens_per_second": 4860.762238572372, "vq_loss": 0.7859227806329727} |
| {"estimated_cost_usd": 0.6956404069299554, "event": "train", "grad_norm": 1.594862699508667, "learning_rate": 5.926204607071532e-06, "loss": 2.7388065457344055, "ncp_loss": 0.8069416135549545, "ntp_loss": 1.125858634710312, "step": 3230, "tokens": 13230080, "tokens_per_second": 4860.299101033793, "vq_loss": 0.8060063272714615} |
| {"estimated_cost_usd": 0.6978650132373889, "event": "train", "grad_norm": 1.443652868270874, "learning_rate": 5.861497100484868e-06, "loss": 2.721050977706909, "ncp_loss": 0.7995985299348831, "ntp_loss": 1.1242045164108276, "step": 3240, "tokens": 13271040, "tokens_per_second": 4859.805171012831, "vq_loss": 0.7972479164600372} |
| {"estimated_cost_usd": 0.7000189844045444, "event": "train", "grad_norm": 1.5373722314834595, "learning_rate": 5.7974281460493236e-06, "loss": 2.8327548503875732, "ncp_loss": 0.8246928751468658, "ntp_loss": 1.1885049045085907, "step": 3250, "tokens": 13312000, "tokens_per_second": 4859.804707224267, "vq_loss": 0.8195570856332779} |
| {"estimated_cost_usd": 0.7022569352171666, "event": "train", "grad_norm": 1.5239982604980469, "learning_rate": 5.734001589359455e-06, "loss": 2.672277092933655, "ncp_loss": 0.7947129458189011, "ntp_loss": 1.0886557400226593, "step": 3260, "tokens": 13352960, "tokens_per_second": 4859.22308486117, "vq_loss": 0.7889084815979004} |
| {"estimated_cost_usd": 0.7045127781736888, "event": "train", "grad_norm": 1.481123924255371, "learning_rate": 5.671221237451319e-06, "loss": 2.817827880382538, "ncp_loss": 0.8392038643360138, "ntp_loss": 1.1442378759384155, "step": 3270, "tokens": 13393920, "tokens_per_second": 4858.521765268529, "vq_loss": 0.8343862593173981} |
| {"estimated_cost_usd": 0.706727990327389, "event": "train", "grad_norm": 1.525189757347107, "learning_rate": 5.609090858574001e-06, "loss": 2.7391907572746277, "ncp_loss": 0.814922034740448, "ntp_loss": 1.113208383321762, "step": 3280, "tokens": 13434880, "tokens_per_second": 4858.104205879455, "vq_loss": 0.8110603541135788} |
| {"estimated_cost_usd": 0.7088913951344222, "event": "train", "grad_norm": 1.499280333518982, "learning_rate": 5.547614181963415e-06, "loss": 2.722165524959564, "ncp_loss": 0.8105057030916214, "ntp_loss": 1.1045306324958801, "step": 3290, "tokens": 13475840, "tokens_per_second": 4858.044266604124, "vq_loss": 0.8071292042732239} |
| {"estimated_cost_usd": 0.7111569358518334, "event": "train", "grad_norm": 1.540619969367981, "learning_rate": 5.486794897618463e-06, "loss": 2.7153952717781067, "ncp_loss": 0.8100508898496628, "ntp_loss": 1.1011437624692917, "step": 3300, "tokens": 13516800, "tokens_per_second": 4857.286991366729, "vq_loss": 0.8042005598545074} |
| {"estimated_cost_usd": 0.7133724610603221, "event": "train", "grad_norm": 1.5002648830413818, "learning_rate": 5.426636656079576e-06, "loss": 2.7866994738578796, "ncp_loss": 0.8109727948904037, "ntp_loss": 1.1687894314527512, "step": 3310, "tokens": 13557760, "tokens_per_second": 4856.875023937757, "vq_loss": 0.8069372624158859} |
| {"estimated_cost_usd": 0.7156016521363888, "event": "train", "grad_norm": 1.5129847526550293, "learning_rate": 5.367143068209558e-06, "loss": 2.734138250350952, "ncp_loss": 0.8174180388450623, "ntp_loss": 1.1053312718868256, "step": 3320, "tokens": 13598720, "tokens_per_second": 4856.372863407098, "vq_loss": 0.8113889098167419} |
| {"estimated_cost_usd": 0.717775872695211, "event": "train", "grad_norm": 1.4307767152786255, "learning_rate": 5.3083177049768995e-06, "loss": 2.7425793409347534, "ncp_loss": 0.802473247051239, "ntp_loss": 1.1413269639015198, "step": 3330, "tokens": 13639680, "tokens_per_second": 4856.245706492464, "vq_loss": 0.7987790703773499} |
| {"estimated_cost_usd": 0.7199667021121666, "event": "train", "grad_norm": 1.6058399677276611, "learning_rate": 5.250164097241395e-06, "loss": 2.7571550011634827, "ncp_loss": 0.8243758827447891, "ntp_loss": 1.1088447123765945, "step": 3340, "tokens": 13680640, "tokens_per_second": 4856.007292141232, "vq_loss": 0.8239343613386154} |
| {"estimated_cost_usd": 0.7221285798881222, "event": "train", "grad_norm": 1.4720966815948486, "learning_rate": 5.192685735542234e-06, "loss": 2.7112139463424683, "ncp_loss": 0.817892462015152, "ntp_loss": 1.08078271150589, "step": 3350, "tokens": 13721600, "tokens_per_second": 4855.965002319097, "vq_loss": 0.81253881752491} |
| {"estimated_cost_usd": 0.7242474523683444, "event": "train", "grad_norm": 1.6170531511306763, "learning_rate": 5.135886069888497e-06, "loss": 2.654174506664276, "ncp_loss": 0.8042348921298981, "ntp_loss": 1.0494596809148788, "step": 3360, "tokens": 13762560, "tokens_per_second": 4856.211306184766, "vq_loss": 0.8004799485206604} |
| {"estimated_cost_usd": 0.7263863395091333, "event": "train", "grad_norm": 1.525567650794983, "learning_rate": 5.0797685095520445e-06, "loss": 2.7157047986984253, "ncp_loss": 0.7907727062702179, "ntp_loss": 1.1375163197517395, "step": 3370, "tokens": 13803520, "tokens_per_second": 4856.322359539456, "vq_loss": 0.7874157279729843} |
| {"estimated_cost_usd": 0.7284628629137778, "event": "train", "grad_norm": 1.5033044815063477, "learning_rate": 5.024336422862924e-06, "loss": 2.716120481491089, "ncp_loss": 0.8044426590204239, "ntp_loss": 1.1125613749027252, "step": 3380, "tokens": 13844480, "tokens_per_second": 4856.848520219686, "vq_loss": 0.799116387963295} |
| {"estimated_cost_usd": 0.7305533748023999, "event": "train", "grad_norm": 1.4360076189041138, "learning_rate": 4.969593137007157e-06, "loss": 2.7224515080451965, "ncp_loss": 0.800563707947731, "ntp_loss": 1.12485870718956, "step": 3390, "tokens": 13885440, "tokens_per_second": 4857.2786817843835, "vq_loss": 0.7970290631055832} |
| {"estimated_cost_usd": 0.7326305960980888, "event": "train", "grad_norm": 1.473126769065857, "learning_rate": 4.915541937827052e-06, "loss": 2.5532352924346924, "ncp_loss": 0.7883950024843216, "ntp_loss": 0.9804582446813583, "step": 3400, "tokens": 13926400, "tokens_per_second": 4857.7945117820245, "vq_loss": 0.7843820005655289} |
| {"estimated_cost_usd": 0.7347401498369777, "event": "train", "grad_norm": 1.4942710399627686, "learning_rate": 4.862186069623984e-06, "loss": 2.693382680416107, "ncp_loss": 0.804668977856636, "ntp_loss": 1.0868727564811707, "step": 3410, "tokens": 13967360, "tokens_per_second": 4858.093633832889, "vq_loss": 0.8018409013748169} |
| {"estimated_cost_usd": 0.7368389860335666, "event": "train", "grad_norm": 1.5140626430511475, "learning_rate": 4.809528734963636e-06, "loss": 2.7249763011932373, "ncp_loss": 0.8009402006864548, "ntp_loss": 1.1277239918708801, "step": 3420, "tokens": 14008320, "tokens_per_second": 4858.461709892367, "vq_loss": 0.79631207883358} |
| {"estimated_cost_usd": 0.7389261040656999, "event": "train", "grad_norm": 1.5388758182525635, "learning_rate": 4.757573094483809e-06, "loss": 2.739966034889221, "ncp_loss": 0.8018270283937454, "ntp_loss": 1.1404147744178772, "step": 3430, "tokens": 14049280, "tokens_per_second": 4858.904748121236, "vq_loss": 0.7977242171764374} |
| {"estimated_cost_usd": 0.7410269088399555, "event": "train", "grad_norm": 1.4685603380203247, "learning_rate": 4.706322266704682e-06, "loss": 2.6873207688331604, "ncp_loss": 0.8097256720066071, "ntp_loss": 1.0707371234893799, "step": 3440, "tokens": 14090240, "tokens_per_second": 4859.255538706501, "vq_loss": 0.8068580478429794} |
| {"estimated_cost_usd": 0.7431139378664333, "event": "train", "grad_norm": 1.4981310367584229, "learning_rate": 4.65577932784164e-06, "loss": 2.716478943824768, "ncp_loss": 0.809012845158577, "ntp_loss": 1.1021212935447693, "step": 3450, "tokens": 14131200, "tokens_per_second": 4859.694432639965, "vq_loss": 0.8053447604179382} |
| {"estimated_cost_usd": 0.7451442830251667, "event": "train", "grad_norm": 1.5894465446472168, "learning_rate": 4.60594731162064e-06, "loss": 2.6788265109062195, "ncp_loss": 0.8027673661708832, "ntp_loss": 1.076728954911232, "step": 3460, "tokens": 14172160, "tokens_per_second": 4860.500583213761, "vq_loss": 0.7993301451206207} |
| {"estimated_cost_usd": 0.7472934244966889, "event": "train", "grad_norm": 1.4348162412643433, "learning_rate": 4.556829209096099e-06, "loss": 2.6263566613197327, "ncp_loss": 0.8040558844804764, "ntp_loss": 1.0227430611848831, "step": 3470, "tokens": 14213120, "tokens_per_second": 4860.529557347753, "vq_loss": 0.7995577156543732} |
| {"estimated_cost_usd": 0.749393628461111, "event": "train", "grad_norm": 1.51047945022583, "learning_rate": 4.508427968471391e-06, "loss": 2.6460999846458435, "ncp_loss": 0.8109526187181473, "ntp_loss": 1.029130443930626, "step": 3480, "tokens": 14254080, "tokens_per_second": 4860.8757734085375, "vq_loss": 0.8060169219970703} |
| {"estimated_cost_usd": 0.7514745306701553, "event": "train", "grad_norm": 1.5694764852523804, "learning_rate": 4.460746494921846e-06, "loss": 2.626801609992981, "ncp_loss": 0.7948775440454483, "ntp_loss": 1.043025091290474, "step": 3490, "tokens": 14295040, "tokens_per_second": 4861.34491561681, "vq_loss": 0.7888989597558975} |
| {"estimated_cost_usd": 0.7535410168589556, "event": "train", "grad_norm": 1.5078295469284058, "learning_rate": 4.413787650420421e-06, "loss": 2.672273278236389, "ncp_loss": 0.7950214445590973, "ntp_loss": 1.0862166583538055, "step": 3500, "tokens": 14336000, "tokens_per_second": 4861.904478293567, "vq_loss": 0.7910352051258087} |
| {"estimated_cost_usd": 0.7556147046135333, "event": "train", "grad_norm": 1.6499868631362915, "learning_rate": 4.367554253565882e-06, "loss": 2.7016453742980957, "ncp_loss": 0.8074336796998978, "ntp_loss": 1.0913135707378387, "step": 3510, "tokens": 14376960, "tokens_per_second": 4862.414637469451, "vq_loss": 0.8028981387615204} |
| {"estimated_cost_usd": 0.757933145469711, "event": "train", "grad_norm": 1.514615535736084, "learning_rate": 4.322049079413634e-06, "loss": 2.6816028356552124, "ncp_loss": 0.8160014748573303, "ntp_loss": 1.055343747138977, "step": 3520, "tokens": 14417920, "tokens_per_second": 4861.351660867299, "vq_loss": 0.810257613658905} |
| {"estimated_cost_usd": 0.7600107429357668, "event": "train", "grad_norm": 1.7176491022109985, "learning_rate": 4.277274859309169e-06, "loss": 2.5726659297943115, "ncp_loss": 0.7969480454921722, "ntp_loss": 0.9820584505796432, "step": 3530, "tokens": 14458880, "tokens_per_second": 4861.835369376355, "vq_loss": 0.7936594039201736} |
| {"estimated_cost_usd": 0.7621023316225444, "event": "train", "grad_norm": 1.5297744274139404, "learning_rate": 4.233234280724093e-06, "loss": 2.773882210254669, "ncp_loss": 0.809502363204956, "ntp_loss": 1.1609726548194885, "step": 3540, "tokens": 14499840, "tokens_per_second": 4862.227174633474, "vq_loss": 0.8034071624279022} |
| {"estimated_cost_usd": 0.7641909721307332, "event": "train", "grad_norm": 1.6361260414123535, "learning_rate": 4.18992998709485e-06, "loss": 2.645514726638794, "ncp_loss": 0.8052729815244675, "ntp_loss": 1.0380865335464478, "step": 3550, "tokens": 14540800, "tokens_per_second": 4862.635594688122, "vq_loss": 0.8021552562713623} |
| {"estimated_cost_usd": 0.7663570366697776, "event": "train", "grad_norm": 1.606301188468933, "learning_rate": 4.147364577664025e-06, "loss": 2.5550439953804016, "ncp_loss": 0.795353427529335, "ntp_loss": 0.9693892747163773, "step": 3560, "tokens": 14581760, "tokens_per_second": 4862.550481654284, "vq_loss": 0.7903013080358505} |
| {"estimated_cost_usd": 0.7684668773663776, "event": "train", "grad_norm": 1.5529816150665283, "learning_rate": 4.1055406073243504e-06, "loss": 2.7248108983039856, "ncp_loss": 0.7982406169176102, "ntp_loss": 1.1321351826190948, "step": 3570, "tokens": 14622720, "tokens_per_second": 4862.821604153153, "vq_loss": 0.7944350689649582} |
| {"estimated_cost_usd": 0.7705255135041443, "event": "train", "grad_norm": 1.5001842975616455, "learning_rate": 4.064460586465363e-06, "loss": 2.7746636271476746, "ncp_loss": 0.8131037503480911, "ntp_loss": 1.1502515077590942, "step": 3580, "tokens": 14663680, "tokens_per_second": 4863.414414205161, "vq_loss": 0.811308354139328} |
| {"estimated_cost_usd": 0.772685392649611, "event": "train", "grad_norm": 1.4162572622299194, "learning_rate": 4.024126980822682e-06, "loss": 2.8167844414711, "ncp_loss": 0.8146073669195175, "ntp_loss": 1.1909773349761963, "step": 3590, "tokens": 14704640, "tokens_per_second": 4863.3667469219445, "vq_loss": 0.8111997693777084} |
| {"estimated_cost_usd": 0.774747732874, "event": "train", "grad_norm": 1.5311081409454346, "learning_rate": 3.984542211330056e-06, "loss": 2.780831217765808, "ncp_loss": 0.8159461468458176, "ntp_loss": 1.1532652378082275, "step": 3600, "tokens": 14745600, "tokens_per_second": 4863.931625873961, "vq_loss": 0.8116198480129242} |
| {"estimated_cost_usd": 0.7768567537560445, "event": "train", "grad_norm": 1.5570580959320068, "learning_rate": 3.9457086539740296e-06, "loss": 2.7566210627555847, "ncp_loss": 0.809578001499176, "ntp_loss": 1.141110509634018, "step": 3610, "tokens": 14786560, "tokens_per_second": 4864.2012021977025, "vq_loss": 0.8059325367212296} |
| {"estimated_cost_usd": 0.7789655581781888, "event": "train", "grad_norm": 1.4869965314865112, "learning_rate": 3.9076286396513225e-06, "loss": 2.7029738426208496, "ncp_loss": 0.8131864368915558, "ntp_loss": 1.0810653567314148, "step": 3620, "tokens": 14827520, "tokens_per_second": 4864.470670530361, "vq_loss": 0.8087220340967178} |
| {"estimated_cost_usd": 0.7811934326448111, "event": "train", "grad_norm": 1.567455530166626, "learning_rate": 3.870304454028948e-06, "loss": 2.570105791091919, "ncp_loss": 0.7985147535800934, "ntp_loss": 0.9770054370164871, "step": 3630, "tokens": 14868480, "tokens_per_second": 4863.997196958393, "vq_loss": 0.7945856750011444} |
| {"estimated_cost_usd": 0.7833533857971221, "event": "train", "grad_norm": 1.5795314311981201, "learning_rate": 3.83373833740699e-06, "loss": 2.6835891604423523, "ncp_loss": 0.7946197539567947, "ntp_loss": 1.0973732471466064, "step": 3640, "tokens": 14909440, "tokens_per_second": 4863.948112441056, "vq_loss": 0.7915961295366287} |
| {"estimated_cost_usd": 0.7854169229811221, "event": "train", "grad_norm": 1.6173275709152222, "learning_rate": 3.797932484584165e-06, "loss": 2.6970083117485046, "ncp_loss": 0.7975438088178635, "ntp_loss": 1.1053937673568726, "step": 3650, "tokens": 14950400, "tokens_per_second": 4864.496378911877, "vq_loss": 0.794070765376091} |
| {"estimated_cost_usd": 0.7876136859802443, "event": "train", "grad_norm": 1.50535249710083, "learning_rate": 3.7628890447260534e-06, "loss": 2.722587823867798, "ncp_loss": 0.7951602339744568, "ntp_loss": 1.1364797055721283, "step": 3660, "tokens": 14991360, "tokens_per_second": 4864.218844248764, "vq_loss": 0.7909478843212128} |
| {"estimated_cost_usd": 0.7897423885109666, "event": "train", "grad_norm": 1.5225703716278076, "learning_rate": 3.7286101212361294e-06, "loss": 2.684251606464386, "ncp_loss": 0.7908031344413757, "ntp_loss": 1.1063585877418518, "step": 3670, "tokens": 15032320, "tokens_per_second": 4864.3620309302205, "vq_loss": 0.7870899140834808} |
| {"estimated_cost_usd": 0.7917982056161665, "event": "train", "grad_norm": 1.6220667362213135, "learning_rate": 3.6950977716294895e-06, "loss": 2.6888335943222046, "ncp_loss": 0.7970280796289444, "ntp_loss": 1.098206490278244, "step": 3680, "tokens": 15073280, "tokens_per_second": 4864.95222788087, "vq_loss": 0.7935990542173386} |
| {"estimated_cost_usd": 0.7938892238786667, "event": "train", "grad_norm": 1.4779646396636963, "learning_rate": 3.6623540074093604e-06, "loss": 2.692849099636078, "ncp_loss": 0.8038583844900131, "ntp_loss": 1.091206207871437, "step": 3690, "tokens": 15114240, "tokens_per_second": 4865.323629320766, "vq_loss": 0.7977844923734665} |
| {"estimated_cost_usd": 0.7960809299592777, "event": "train", "grad_norm": 1.5657366514205933, "learning_rate": 3.6303807939463705e-06, "loss": 2.60578453540802, "ncp_loss": 0.7831545919179916, "ntp_loss": 1.0437589585781097, "step": 3700, "tokens": 15155200, "tokens_per_second": 4865.07766962044, "vq_loss": 0.7788709551095963} |
| {"estimated_cost_usd": 0.7982586389876444, "event": "train", "grad_norm": 1.4889988899230957, "learning_rate": 3.5991800503605663e-06, "loss": 2.6873392462730408, "ncp_loss": 0.7876530885696411, "ntp_loss": 1.1149886846542358, "step": 3710, "tokens": 15196160, "tokens_per_second": 4864.918362845579, "vq_loss": 0.784697487950325} |
| {"estimated_cost_usd": 0.8003821894271334, "event": "train", "grad_norm": 1.6236393451690674, "learning_rate": 3.5687536494062407e-06, "loss": 2.5905551314353943, "ncp_loss": 0.7914160341024399, "ntp_loss": 1.0100033432245255, "step": 3720, "tokens": 15237120, "tokens_per_second": 4865.089101312605, "vq_loss": 0.7891357690095901} |
| {"estimated_cost_usd": 0.8024974975720555, "event": "train", "grad_norm": 1.491723895072937, "learning_rate": 3.5391034173595085e-06, "loss": 2.7110219597816467, "ncp_loss": 0.7955743968486786, "ntp_loss": 1.1227077543735504, "step": 3730, "tokens": 15278080, "tokens_per_second": 4865.308906301792, "vq_loss": 0.7927398979663849} |
| {"estimated_cost_usd": 0.8046758431159667, "event": "train", "grad_norm": 1.520702600479126, "learning_rate": 3.5102311339087038e-06, "loss": 2.746619999408722, "ncp_loss": 0.8031388372182846, "ntp_loss": 1.1446058452129364, "step": 3740, "tokens": 15319040, "tokens_per_second": 4865.146395619562, "vq_loss": 0.7988752871751785} |
| {"estimated_cost_usd": 0.8068677996149556, "event": "train", "grad_norm": 1.5406372547149658, "learning_rate": 3.482138532047541e-06, "loss": 2.7666218876838684, "ncp_loss": 0.7975688874721527, "ntp_loss": 1.1740050613880157, "step": 3750, "tokens": 15360000, "tokens_per_second": 4864.902695592186, "vq_loss": 0.7950479835271835} |
| {"estimated_cost_usd": 0.8090109750735445, "event": "train", "grad_norm": 1.5567716360092163, "learning_rate": 3.4548272979711124e-06, "loss": 2.7936922907829285, "ncp_loss": 0.8038012236356735, "ntp_loss": 1.1912804245948792, "step": 3760, "tokens": 15400960, "tokens_per_second": 4864.953641118525, "vq_loss": 0.7986106872558594} |
| {"estimated_cost_usd": 0.8113508889671333, "event": "train", "grad_norm": 1.5873196125030518, "learning_rate": 3.4282990709746673e-06, "loss": 2.606522500514984, "ncp_loss": 0.7852796316146851, "ntp_loss": 1.0406424552202225, "step": 3770, "tokens": 15441920, "tokens_per_second": 4863.824638767731, "vq_loss": 0.7806004136800766} |
| {"estimated_cost_usd": 0.8135189195114223, "event": "train", "grad_norm": 1.5747501850128174, "learning_rate": 3.402555443355222e-06, "loss": 2.6569784283638, "ncp_loss": 0.7950679808855057, "ntp_loss": 1.0713687390089035, "step": 3780, "tokens": 15482880, "tokens_per_second": 4863.729539782935, "vq_loss": 0.7905416786670685} |
| {"estimated_cost_usd": 0.8156248077814555, "event": "train", "grad_norm": 1.451345443725586, "learning_rate": 3.3775979603159817e-06, "loss": 2.671610951423645, "ncp_loss": 0.7971207797527313, "ntp_loss": 1.0829872339963913, "step": 3790, "tokens": 15523840, "tokens_per_second": 4864.005505603205, "vq_loss": 0.7915030270814896} |
| {"estimated_cost_usd": 0.8177291982242777, "event": "train", "grad_norm": 1.7692314386367798, "learning_rate": 3.353428119873597e-06, "loss": 2.750085413455963, "ncp_loss": 0.7894090116024017, "ntp_loss": 1.175107717514038, "step": 3800, "tokens": 15564800, "tokens_per_second": 4864.288959901074, "vq_loss": 0.7855687439441681} |
| {"estimated_cost_usd": 0.8197483756772999, "event": "train", "grad_norm": 1.5114974975585938, "learning_rate": 3.3300473727682493e-06, "loss": 2.60783988237381, "ncp_loss": 0.7831820547580719, "ntp_loss": 1.0465168803930283, "step": 3810, "tokens": 15605760, "tokens_per_second": 4865.0766320476705, "vq_loss": 0.7781409174203873} |
| {"estimated_cost_usd": 0.8220387080668555, "event": "train", "grad_norm": 1.6712102890014648, "learning_rate": 3.3074571223765678e-06, "loss": 2.7286073565483093, "ncp_loss": 0.7785058319568634, "ntp_loss": 1.1742594242095947, "step": 3820, "tokens": 15646720, "tokens_per_second": 4864.25539695756, "vq_loss": 0.7758422046899796} |
| {"estimated_cost_usd": 0.8243333035276221, "event": "train", "grad_norm": 1.5245496034622192, "learning_rate": 3.2856587246274e-06, "loss": 2.6539719104766846, "ncp_loss": 0.7827900350093842, "ntp_loss": 1.093892127275467, "step": 3830, "tokens": 15687680, "tokens_per_second": 4863.41357388024, "vq_loss": 0.7772897332906723} |
| {"estimated_cost_usd": 0.826512495520089, "event": "train", "grad_norm": 1.6170716285705566, "learning_rate": 3.2646534879204277e-06, "loss": 2.5889166593551636, "ncp_loss": 0.7827244102954865, "ntp_loss": 1.0282370895147324, "step": 3840, "tokens": 15728640, "tokens_per_second": 4863.255371358915, "vq_loss": 0.7779551595449448} |
| {"estimated_cost_usd": 0.8285798256859667, "event": "train", "grad_norm": 1.4464718103408813, "learning_rate": 3.2444426730476248e-06, "loss": 2.681169807910919, "ncp_loss": 0.8021830320358276, "ntp_loss": 1.0794344395399094, "step": 3850, "tokens": 15769600, "tokens_per_second": 4863.754539947332, "vq_loss": 0.7995523512363434} |
| {"estimated_cost_usd": 0.8306372785803, "event": "train", "grad_norm": 1.5718473196029663, "learning_rate": 3.225027493117585e-06, "loss": 2.4935490489006042, "ncp_loss": 0.791942372918129, "ntp_loss": 0.9150974005460739, "step": 3860, "tokens": 15810560, "tokens_per_second": 4864.309065625256, "vq_loss": 0.7865092903375626} |
| {"estimated_cost_usd": 0.8327610309590221, "event": "train", "grad_norm": 1.7774218320846558, "learning_rate": 3.206409113482712e-06, "loss": 2.7689846754074097, "ncp_loss": 0.7905311584472656, "ntp_loss": 1.1931417286396027, "step": 3870, "tokens": 15851520, "tokens_per_second": 4864.473539707858, "vq_loss": 0.7853118181228638} |
| {"estimated_cost_usd": 0.8348631569529443, "event": "train", "grad_norm": 1.5361558198928833, "learning_rate": 3.1885886516692673e-06, "loss": 2.646721839904785, "ncp_loss": 0.7885836809873581, "ntp_loss": 1.0739716440439224, "step": 3880, "tokens": 15892480, "tokens_per_second": 4864.763191106384, "vq_loss": 0.7841664552688599} |
| {"estimated_cost_usd": 0.8368933859869778, "event": "train", "grad_norm": 1.6349215507507324, "learning_rate": 3.171567177310291e-06, "loss": 2.5877269506454468, "ncp_loss": 0.7956495583057404, "ntp_loss": 1.001755252480507, "step": 3890, "tokens": 15933440, "tokens_per_second": 4865.469340887431, "vq_loss": 0.7903221249580383} |
| {"estimated_cost_usd": 0.8388807552291556, "event": "train", "grad_norm": 1.462572455406189, "learning_rate": 3.1553457120814082e-06, "loss": 2.598081648349762, "ncp_loss": 0.7786461561918259, "ntp_loss": 1.0461738258600235, "step": 3900, "tokens": 15974400, "tokens_per_second": 4866.4206935483935, "vq_loss": 0.7732616513967514} |
| {"estimated_cost_usd": 0.8409378591296666, "event": "train", "grad_norm": 1.4672751426696777, "learning_rate": 3.1399252296394956e-06, "loss": 2.729252576828003, "ncp_loss": 0.7988120317459106, "ntp_loss": 1.1374864280223846, "step": 3910, "tokens": 16015360, "tokens_per_second": 4866.963923420101, "vq_loss": 0.7929541021585464} |
| {"estimated_cost_usd": 0.8429965568036777, "event": "train", "grad_norm": 1.5580551624298096, "learning_rate": 3.1253066555642434e-06, "loss": 2.624499499797821, "ncp_loss": 0.7926281839609146, "ntp_loss": 1.044367104768753, "step": 3920, "tokens": 16056320, "tokens_per_second": 4867.495299548864, "vq_loss": 0.7875042259693146} |
| {"estimated_cost_usd": 0.8451132185591665, "event": "train", "grad_norm": 1.5776118040084839, "learning_rate": 3.1114908673026027e-06, "loss": 2.6988747119903564, "ncp_loss": 0.8022550940513611, "ntp_loss": 1.0981150269508362, "step": 3930, "tokens": 16097280, "tokens_per_second": 4867.690201730443, "vq_loss": 0.7985045611858368} |
| {"estimated_cost_usd": 0.8472474738809888, "event": "train", "grad_norm": 1.548494577407837, "learning_rate": 3.098478694116116e-06, "loss": 2.7375141382217407, "ncp_loss": 0.7799976319074631, "ntp_loss": 1.1820924580097198, "step": 3940, "tokens": 16138240, "tokens_per_second": 4867.783045722258, "vq_loss": 0.7754240930080414} |
| {"estimated_cost_usd": 0.8494761736445998, "event": "train", "grad_norm": 1.6049082279205322, "learning_rate": 3.0862709170311406e-06, "loss": 2.697135090827942, "ncp_loss": 0.7911151945590973, "ntp_loss": 1.117368757724762, "step": 3950, "tokens": 16179200, "tokens_per_second": 4867.334214572445, "vq_loss": 0.7886511832475662} |
| {"estimated_cost_usd": 0.8515993490396999, "event": "train", "grad_norm": 1.5919550657272339, "learning_rate": 3.0748682687919733e-06, "loss": 2.587825119495392, "ncp_loss": 0.7927327901124954, "ntp_loss": 1.0070819556713104, "step": 3960, "tokens": 16220160, "tokens_per_second": 4867.490803831933, "vq_loss": 0.7880104035139084} |
| {"estimated_cost_usd": 0.8538175379827111, "event": "train", "grad_norm": 1.65522038936615, "learning_rate": 3.0642714338168664e-06, "loss": 2.6575818061828613, "ncp_loss": 0.7800626009702682, "ntp_loss": 1.1012215912342072, "step": 3970, "tokens": 16261120, "tokens_per_second": 4867.104938338362, "vq_loss": 0.7762975990772247} |
| {"estimated_cost_usd": 0.8560911547184887, "event": "train", "grad_norm": 1.4293644428253174, "learning_rate": 3.0544810481569455e-06, "loss": 2.584780693054199, "ncp_loss": 0.7851955741643906, "ntp_loss": 1.0187038332223892, "step": 3980, "tokens": 16302080, "tokens_per_second": 4866.405975752733, "vq_loss": 0.780881255865097} |
| {"estimated_cost_usd": 0.8583135846361, "event": "train", "grad_norm": 1.6678746938705444, "learning_rate": 3.0454976994580412e-06, "loss": 2.6416026949882507, "ncp_loss": 0.7787463963031769, "ntp_loss": 1.0890044271945953, "step": 3990, "tokens": 16343040, "tokens_per_second": 4866.00088991648, "vq_loss": 0.7738518416881561} |
| {"estimated_cost_usd": 0.8604425088321332, "event": "train", "grad_norm": 1.5318266153335571, "learning_rate": 3.0373219269254e-06, "loss": 2.7198633551597595, "ncp_loss": 0.7947327941656113, "ntp_loss": 1.132219135761261, "step": 4000, "tokens": 16384000, "tokens_per_second": 4866.126649071778, "vq_loss": 0.7929113954305649} |
| {"estimated_cost_usd": 0.8628110891276222, "event": "train", "grad_norm": 1.5158169269561768, "learning_rate": 3.02995422129134e-06, "loss": 2.7716720700263977, "ncp_loss": 0.7956947833299637, "ntp_loss": 1.1840404272079468, "step": 4010, "tokens": 16424960, "tokens_per_second": 4864.900127815706, "vq_loss": 0.791936919093132} |
| {"estimated_cost_usd": 0.8649303209547333, "event": "train", "grad_norm": 1.5291740894317627, "learning_rate": 3.0233950247857775e-06, "loss": 2.6145272850990295, "ncp_loss": 0.7823889255523682, "ntp_loss": 1.0553236305713654, "step": 4020, "tokens": 16465920, "tokens_per_second": 4865.082459692796, "vq_loss": 0.7768147587776184} |
| {"estimated_cost_usd": 0.8670432936993332, "event": "train", "grad_norm": 1.5156006813049316, "learning_rate": 3.017644731109695e-06, "loss": 2.6947449445724487, "ncp_loss": 0.781466081738472, "ntp_loss": 1.1370627284049988, "step": 4030, "tokens": 16506880, "tokens_per_second": 4865.299022025217, "vq_loss": 0.7762160748243332} |
| {"estimated_cost_usd": 0.8692333711177443, "event": "train", "grad_norm": 1.5572466850280762, "learning_rate": 3.0127036854115078e-06, "loss": 2.6811744570732117, "ncp_loss": 0.7809013724327087, "ntp_loss": 1.1235762685537338, "step": 4040, "tokens": 16547840, "tokens_per_second": 4865.082939701826, "vq_loss": 0.7766968607902527} |
| {"estimated_cost_usd": 0.8714308585979555, "event": "train", "grad_norm": 1.5838515758514404, "learning_rate": 3.0085721842663434e-06, "loss": 2.649507522583008, "ncp_loss": 0.784325510263443, "ntp_loss": 1.085495799779892, "step": 4050, "tokens": 16588800, "tokens_per_second": 4864.826575938226, "vq_loss": 0.7796861529350281} |
| {"estimated_cost_usd": 0.8735183935597778, "event": "train", "grad_norm": 1.6147514581680298, "learning_rate": 3.0052504756582406e-06, "loss": 2.7097660303115845, "ncp_loss": 0.789141446352005, "ntp_loss": 1.1346394717693329, "step": 4060, "tokens": 16629760, "tokens_per_second": 4865.183820842722, "vq_loss": 0.785985141992569} |
| {"estimated_cost_usd": 0.8756053493399444, "event": "train", "grad_norm": 1.558311104774475, "learning_rate": 3.0027387589652722e-06, "loss": 2.7067673206329346, "ncp_loss": 0.7959835380315781, "ntp_loss": 1.1198758482933044, "step": 4070, "tokens": 16670720, "tokens_per_second": 4865.542580710179, "vq_loss": 0.7909079045057297} |
| {"estimated_cost_usd": 0.8776694409054667, "event": "train", "grad_norm": 1.6788707971572876, "learning_rate": 3.0010371849475698e-06, "loss": 2.675687789916992, "ncp_loss": 0.7864901572465897, "ntp_loss": 1.1072965562343597, "step": 4080, "tokens": 16711680, "tokens_per_second": 4866.026396294079, "vq_loss": 0.7819010764360428} |
| {"estimated_cost_usd": 0.8798024250116666, "event": "train", "grad_norm": 1.6437997817993164, "learning_rate": 3.000145855738275e-06, "loss": 2.5596354007720947, "ncp_loss": 0.7879672199487686, "ntp_loss": 0.9871181696653366, "step": 4090, "tokens": 16752640, "tokens_per_second": 4866.126871797894, "vq_loss": 0.7845500409603119} |
| {"codebook_perplexity": 2.3904993534088135, "codebook_usage": 0.3090277910232544, "event": "eval", "loss": 3.4574958980083466, "ncp_loss": 0.799576111137867, "ntp_loss": 1.863869659602642, "step": 4096, "tokens": 16777216, "vq_loss": 0.7940501756966114} |
|
|
