| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9997336884154461, | |
| "eval_steps": 500, | |
| "global_step": 1877, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005326231691078562, | |
| "grad_norm": 0.5528136747380069, | |
| "learning_rate": 1.0638297872340427e-06, | |
| "loss": 1.7189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002663115845539281, | |
| "grad_norm": 0.5731888996610293, | |
| "learning_rate": 5.319148936170213e-06, | |
| "loss": 1.7582, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005326231691078562, | |
| "grad_norm": 0.5597088455341374, | |
| "learning_rate": 1.0638297872340426e-05, | |
| "loss": 1.7331, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007989347536617843, | |
| "grad_norm": 0.6373028746703387, | |
| "learning_rate": 1.595744680851064e-05, | |
| "loss": 1.7083, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010652463382157125, | |
| "grad_norm": 0.6190956100247592, | |
| "learning_rate": 2.1276595744680852e-05, | |
| "loss": 1.6453, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013315579227696404, | |
| "grad_norm": 0.5346124338518666, | |
| "learning_rate": 2.6595744680851064e-05, | |
| "loss": 1.5715, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015978695073235686, | |
| "grad_norm": 0.25993843509864667, | |
| "learning_rate": 3.191489361702128e-05, | |
| "loss": 1.4359, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018641810918774968, | |
| "grad_norm": 0.45126098872878045, | |
| "learning_rate": 3.723404255319149e-05, | |
| "loss": 1.4122, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02130492676431425, | |
| "grad_norm": 0.16268004246261306, | |
| "learning_rate": 4.2553191489361704e-05, | |
| "loss": 1.3378, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023968042609853527, | |
| "grad_norm": 0.16755798993478008, | |
| "learning_rate": 4.787234042553192e-05, | |
| "loss": 1.3315, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02663115845539281, | |
| "grad_norm": 0.14666977328343594, | |
| "learning_rate": 5.319148936170213e-05, | |
| "loss": 1.3259, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02929427430093209, | |
| "grad_norm": 0.10629659674680719, | |
| "learning_rate": 5.851063829787234e-05, | |
| "loss": 1.288, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03195739014647137, | |
| "grad_norm": 0.11263809733941188, | |
| "learning_rate": 6.382978723404256e-05, | |
| "loss": 1.2763, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03462050599201065, | |
| "grad_norm": 0.14445654795383106, | |
| "learning_rate": 6.914893617021277e-05, | |
| "loss": 1.256, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.037283621837549935, | |
| "grad_norm": 0.07679775841947081, | |
| "learning_rate": 7.446808510638298e-05, | |
| "loss": 1.2481, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03994673768308921, | |
| "grad_norm": 0.07097172061630208, | |
| "learning_rate": 7.978723404255319e-05, | |
| "loss": 1.2417, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0426098535286285, | |
| "grad_norm": 0.07545648577598915, | |
| "learning_rate": 8.510638297872341e-05, | |
| "loss": 1.2048, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.045272969374167776, | |
| "grad_norm": 0.06657701317469632, | |
| "learning_rate": 9.042553191489363e-05, | |
| "loss": 1.2138, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.047936085219707054, | |
| "grad_norm": 0.08276972517588223, | |
| "learning_rate": 9.574468085106384e-05, | |
| "loss": 1.2267, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05059920106524634, | |
| "grad_norm": 0.14086227463755532, | |
| "learning_rate": 0.00010106382978723406, | |
| "loss": 1.2185, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.05326231691078562, | |
| "grad_norm": 0.08222057468849275, | |
| "learning_rate": 0.00010638297872340425, | |
| "loss": 1.2021, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0559254327563249, | |
| "grad_norm": 0.06741247738810993, | |
| "learning_rate": 0.00011170212765957446, | |
| "loss": 1.1957, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.05858854860186418, | |
| "grad_norm": 0.07692927491859038, | |
| "learning_rate": 0.00011702127659574468, | |
| "loss": 1.1901, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06125166444740346, | |
| "grad_norm": 0.08953054401601632, | |
| "learning_rate": 0.0001223404255319149, | |
| "loss": 1.2002, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.06391478029294274, | |
| "grad_norm": 0.066045987418387, | |
| "learning_rate": 0.00012765957446808513, | |
| "loss": 1.2086, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06657789613848203, | |
| "grad_norm": 0.06476207146640194, | |
| "learning_rate": 0.00013297872340425532, | |
| "loss": 1.215, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.0692410119840213, | |
| "grad_norm": 0.07334327374343644, | |
| "learning_rate": 0.00013829787234042554, | |
| "loss": 1.181, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07190412782956059, | |
| "grad_norm": 0.071815699820189, | |
| "learning_rate": 0.00014361702127659576, | |
| "loss": 1.1795, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.07456724367509987, | |
| "grad_norm": 0.08268574123602224, | |
| "learning_rate": 0.00014893617021276596, | |
| "loss": 1.1892, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07723035952063914, | |
| "grad_norm": 0.07585606469879155, | |
| "learning_rate": 0.00015425531914893618, | |
| "loss": 1.173, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07989347536617843, | |
| "grad_norm": 0.06900850276332868, | |
| "learning_rate": 0.00015957446808510637, | |
| "loss": 1.1889, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08255659121171771, | |
| "grad_norm": 0.07702070923317432, | |
| "learning_rate": 0.00016489361702127662, | |
| "loss": 1.1705, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.085219707057257, | |
| "grad_norm": 0.0724505634260966, | |
| "learning_rate": 0.00017021276595744682, | |
| "loss": 1.1801, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08788282290279627, | |
| "grad_norm": 0.07762044850846143, | |
| "learning_rate": 0.000175531914893617, | |
| "loss": 1.1863, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.09054593874833555, | |
| "grad_norm": 0.0825988729050522, | |
| "learning_rate": 0.00018085106382978726, | |
| "loss": 1.1687, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09320905459387484, | |
| "grad_norm": 0.08362625552402488, | |
| "learning_rate": 0.00018617021276595746, | |
| "loss": 1.1875, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.09587217043941411, | |
| "grad_norm": 0.07968629276225715, | |
| "learning_rate": 0.00019148936170212768, | |
| "loss": 1.1629, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0985352862849534, | |
| "grad_norm": 0.09010747938874886, | |
| "learning_rate": 0.00019680851063829787, | |
| "loss": 1.1682, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.10119840213049268, | |
| "grad_norm": 0.10276104499280464, | |
| "learning_rate": 0.00019999930805760402, | |
| "loss": 1.1618, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.10386151797603196, | |
| "grad_norm": 0.07684956533429005, | |
| "learning_rate": 0.00019999152381561955, | |
| "loss": 1.1902, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.10652463382157124, | |
| "grad_norm": 0.09365634557072464, | |
| "learning_rate": 0.0001999750910791767, | |
| "loss": 1.1673, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10918774966711052, | |
| "grad_norm": 0.08320439951882774, | |
| "learning_rate": 0.00019995001126958025, | |
| "loss": 1.1845, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.1118508655126498, | |
| "grad_norm": 0.08595161594886752, | |
| "learning_rate": 0.00019991628655604003, | |
| "loss": 1.1444, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11451398135818908, | |
| "grad_norm": 0.07678856693871118, | |
| "learning_rate": 0.00019987391985548328, | |
| "loss": 1.1724, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.11717709720372836, | |
| "grad_norm": 0.07433277571881601, | |
| "learning_rate": 0.0001998229148323023, | |
| "loss": 1.1469, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.11984021304926765, | |
| "grad_norm": 0.11001095605643386, | |
| "learning_rate": 0.00019976327589803767, | |
| "loss": 1.1383, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.12250332889480692, | |
| "grad_norm": 0.0784178760835021, | |
| "learning_rate": 0.0001996950082109965, | |
| "loss": 1.1818, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12516644474034622, | |
| "grad_norm": 0.08047194112395492, | |
| "learning_rate": 0.00019961811767580648, | |
| "loss": 1.1445, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.1278295605858855, | |
| "grad_norm": 0.0670667235371544, | |
| "learning_rate": 0.0001995326109429049, | |
| "loss": 1.1741, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13049267643142476, | |
| "grad_norm": 0.07072589446768075, | |
| "learning_rate": 0.00019943849540796375, | |
| "loss": 1.157, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.13315579227696406, | |
| "grad_norm": 0.07466892570841129, | |
| "learning_rate": 0.0001993357792112498, | |
| "loss": 1.125, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13581890812250333, | |
| "grad_norm": 0.07302104613788317, | |
| "learning_rate": 0.0001992244712369207, | |
| "loss": 1.1615, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.1384820239680426, | |
| "grad_norm": 0.07211635352591637, | |
| "learning_rate": 0.00019910458111225646, | |
| "loss": 1.1441, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1411451398135819, | |
| "grad_norm": 0.07103357444221702, | |
| "learning_rate": 0.00019897611920682677, | |
| "loss": 1.1493, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.14380825565912117, | |
| "grad_norm": 0.0698227187710226, | |
| "learning_rate": 0.00019883909663159424, | |
| "loss": 1.1568, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.14647137150466044, | |
| "grad_norm": 0.07137557168765225, | |
| "learning_rate": 0.0001986935252379532, | |
| "loss": 1.171, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.14913448735019974, | |
| "grad_norm": 0.07605080544337586, | |
| "learning_rate": 0.00019853941761670483, | |
| "loss": 1.1623, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.151797603195739, | |
| "grad_norm": 0.09532848101140429, | |
| "learning_rate": 0.00019837678709696798, | |
| "loss": 1.1888, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.15446071904127828, | |
| "grad_norm": 0.07485256895909924, | |
| "learning_rate": 0.00019820564774502644, | |
| "loss": 1.1483, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.15712383488681758, | |
| "grad_norm": 0.07483378156117482, | |
| "learning_rate": 0.0001980260143631122, | |
| "loss": 1.1375, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.15978695073235685, | |
| "grad_norm": 0.07954155407009747, | |
| "learning_rate": 0.00019783790248812533, | |
| "loss": 1.1696, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16245006657789615, | |
| "grad_norm": 0.08502452471103343, | |
| "learning_rate": 0.00019764132839029, | |
| "loss": 1.168, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.16511318242343542, | |
| "grad_norm": 0.08384910068571033, | |
| "learning_rate": 0.00019743630907174725, | |
| "loss": 1.1659, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.1677762982689747, | |
| "grad_norm": 0.06905463640642404, | |
| "learning_rate": 0.0001972228622650846, | |
| "loss": 1.1612, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.170439414114514, | |
| "grad_norm": 0.19257912301232658, | |
| "learning_rate": 0.0001970010064318021, | |
| "loss": 1.1517, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.17310252996005326, | |
| "grad_norm": 0.0793114626498931, | |
| "learning_rate": 0.00019677076076071566, | |
| "loss": 1.1385, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.17576564580559254, | |
| "grad_norm": 0.07393026070000318, | |
| "learning_rate": 0.00019653214516629735, | |
| "loss": 1.1426, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.17842876165113183, | |
| "grad_norm": 0.08179432509124362, | |
| "learning_rate": 0.00019628518028695307, | |
| "loss": 1.1104, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.1810918774966711, | |
| "grad_norm": 0.09735291608528279, | |
| "learning_rate": 0.00019602988748323717, | |
| "loss": 1.1563, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.18375499334221038, | |
| "grad_norm": 0.06743724715009518, | |
| "learning_rate": 0.00019576628883600535, | |
| "loss": 1.1406, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.18641810918774968, | |
| "grad_norm": 0.075326384879952, | |
| "learning_rate": 0.00019549440714450444, | |
| "loss": 1.1572, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.18908122503328895, | |
| "grad_norm": 0.07438689728031705, | |
| "learning_rate": 0.00019521426592440072, | |
| "loss": 1.1479, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.19174434087882822, | |
| "grad_norm": 0.07277611336304127, | |
| "learning_rate": 0.00019492588940574586, | |
| "loss": 1.1549, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.19440745672436752, | |
| "grad_norm": 0.0695324135241875, | |
| "learning_rate": 0.0001946293025308813, | |
| "loss": 1.1435, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.1970705725699068, | |
| "grad_norm": 0.06685927618032904, | |
| "learning_rate": 0.00019432453095228076, | |
| "loss": 1.1641, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.19973368841544606, | |
| "grad_norm": 0.0680367135740568, | |
| "learning_rate": 0.00019401160103033174, | |
| "loss": 1.1261, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.20239680426098536, | |
| "grad_norm": 0.08027336453756874, | |
| "learning_rate": 0.00019369053983105532, | |
| "loss": 1.1368, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.20505992010652463, | |
| "grad_norm": 0.0707161713953054, | |
| "learning_rate": 0.00019336137512376532, | |
| "loss": 1.1588, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.20772303595206393, | |
| "grad_norm": 0.07189527593634382, | |
| "learning_rate": 0.00019302413537866642, | |
| "loss": 1.1552, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.2103861517976032, | |
| "grad_norm": 0.0716934364253126, | |
| "learning_rate": 0.0001926788497643916, | |
| "loss": 1.1577, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.21304926764314247, | |
| "grad_norm": 0.065943892133018, | |
| "learning_rate": 0.00019232554814547953, | |
| "loss": 1.1203, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21571238348868177, | |
| "grad_norm": 0.07352621386091099, | |
| "learning_rate": 0.00019196426107979128, | |
| "loss": 1.1266, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.21837549933422104, | |
| "grad_norm": 0.07441803674470306, | |
| "learning_rate": 0.00019159501981586737, | |
| "loss": 1.1432, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.2210386151797603, | |
| "grad_norm": 0.07291702193187057, | |
| "learning_rate": 0.00019121785629022501, | |
| "loss": 1.1344, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.2237017310252996, | |
| "grad_norm": 0.07094925179230635, | |
| "learning_rate": 0.00019083280312459593, | |
| "loss": 1.1137, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.22636484687083888, | |
| "grad_norm": 0.07399044805064979, | |
| "learning_rate": 0.0001904398936231047, | |
| "loss": 1.1533, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.22902796271637815, | |
| "grad_norm": 0.07782197426798759, | |
| "learning_rate": 0.00019003916176938836, | |
| "loss": 1.1458, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.23169107856191745, | |
| "grad_norm": 0.06822071830212563, | |
| "learning_rate": 0.00018963064222365694, | |
| "loss": 1.1448, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.23435419440745672, | |
| "grad_norm": 0.06944246120343146, | |
| "learning_rate": 0.00018921437031969558, | |
| "loss": 1.1577, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.237017310252996, | |
| "grad_norm": 0.07108688216307608, | |
| "learning_rate": 0.0001887903820618087, | |
| "loss": 1.1526, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.2396804260985353, | |
| "grad_norm": 0.08455610060485116, | |
| "learning_rate": 0.00018835871412170563, | |
| "loss": 1.1517, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.24234354194407456, | |
| "grad_norm": 0.06664786445884358, | |
| "learning_rate": 0.0001879194038353289, | |
| "loss": 1.1537, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.24500665778961384, | |
| "grad_norm": 0.07089581724112333, | |
| "learning_rate": 0.00018747248919962498, | |
| "loss": 1.1409, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.24766977363515313, | |
| "grad_norm": 0.07242825833109466, | |
| "learning_rate": 0.00018701800886925782, | |
| "loss": 1.1303, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.25033288948069243, | |
| "grad_norm": 0.06598593287452807, | |
| "learning_rate": 0.00018655600215326546, | |
| "loss": 1.1401, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.2529960053262317, | |
| "grad_norm": 0.07020789015379635, | |
| "learning_rate": 0.00018608650901166032, | |
| "loss": 1.1542, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.255659121171771, | |
| "grad_norm": 0.06441793150662321, | |
| "learning_rate": 0.0001856095700519726, | |
| "loss": 1.1276, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.2583222370173103, | |
| "grad_norm": 0.07254719498292789, | |
| "learning_rate": 0.0001851252265257384, | |
| "loss": 1.1212, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.2609853528628495, | |
| "grad_norm": 0.06917909155716108, | |
| "learning_rate": 0.0001846335203249316, | |
| "loss": 1.1298, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.2636484687083888, | |
| "grad_norm": 0.07470942417701212, | |
| "learning_rate": 0.00018413449397834051, | |
| "loss": 1.1456, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.2663115845539281, | |
| "grad_norm": 0.0693858861935873, | |
| "learning_rate": 0.00018362819064788956, | |
| "loss": 1.1327, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26897470039946736, | |
| "grad_norm": 0.07182079092553902, | |
| "learning_rate": 0.00018311465412490608, | |
| "loss": 1.1628, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.27163781624500666, | |
| "grad_norm": 0.06682954118119949, | |
| "learning_rate": 0.00018259392882633265, | |
| "loss": 1.1528, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.27430093209054596, | |
| "grad_norm": 0.07248673749669132, | |
| "learning_rate": 0.00018206605979088542, | |
| "loss": 1.156, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.2769640479360852, | |
| "grad_norm": 0.06950216959497392, | |
| "learning_rate": 0.0001815310926751586, | |
| "loss": 1.119, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.2796271637816245, | |
| "grad_norm": 0.07067673018407011, | |
| "learning_rate": 0.00018098907374967555, | |
| "loss": 1.1211, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.2822902796271638, | |
| "grad_norm": 0.06820842392733384, | |
| "learning_rate": 0.00018044004989488664, | |
| "loss": 1.1281, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.28495339547270304, | |
| "grad_norm": 0.07418230217074875, | |
| "learning_rate": 0.00017988406859711456, | |
| "loss": 1.1409, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.28761651131824234, | |
| "grad_norm": 0.07009876259688716, | |
| "learning_rate": 0.00017932117794444713, | |
| "loss": 1.1381, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.29027962716378164, | |
| "grad_norm": 0.07129309605598672, | |
| "learning_rate": 0.00017875142662257786, | |
| "loss": 1.1387, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.2929427430093209, | |
| "grad_norm": 0.07830622678131702, | |
| "learning_rate": 0.00017817486391059532, | |
| "loss": 1.1165, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2956058588548602, | |
| "grad_norm": 0.0709756673443606, | |
| "learning_rate": 0.0001775915396767205, | |
| "loss": 1.129, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.2982689747003995, | |
| "grad_norm": 0.06710174636010342, | |
| "learning_rate": 0.00017700150437399405, | |
| "loss": 1.1183, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.3009320905459387, | |
| "grad_norm": 0.07321620332053846, | |
| "learning_rate": 0.0001764048090359121, | |
| "loss": 1.1502, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.303595206391478, | |
| "grad_norm": 0.07613131980579707, | |
| "learning_rate": 0.00017580150527201241, | |
| "loss": 1.1322, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.3062583222370173, | |
| "grad_norm": 0.07480921806539248, | |
| "learning_rate": 0.0001751916452634105, | |
| "loss": 1.1269, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.30892143808255657, | |
| "grad_norm": 0.07386122393966031, | |
| "learning_rate": 0.0001745752817582865, | |
| "loss": 1.1528, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.31158455392809586, | |
| "grad_norm": 0.07032971968151802, | |
| "learning_rate": 0.00017395246806732267, | |
| "loss": 1.1642, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.31424766977363516, | |
| "grad_norm": 0.07910944378906298, | |
| "learning_rate": 0.00017332325805909256, | |
| "loss": 1.1328, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.3169107856191744, | |
| "grad_norm": 0.06775943214366806, | |
| "learning_rate": 0.00017268770615540177, | |
| "loss": 1.1142, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.3195739014647137, | |
| "grad_norm": 0.0858014191359942, | |
| "learning_rate": 0.00017204586732658087, | |
| "loss": 1.1393, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.322237017310253, | |
| "grad_norm": 0.06968407560583738, | |
| "learning_rate": 0.00017139779708673085, | |
| "loss": 1.1428, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.3249001331557923, | |
| "grad_norm": 0.06812443512073688, | |
| "learning_rate": 0.00017074355148892167, | |
| "loss": 1.1592, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.32756324900133155, | |
| "grad_norm": 0.07150170839574509, | |
| "learning_rate": 0.00017008318712034403, | |
| "loss": 1.1018, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.33022636484687085, | |
| "grad_norm": 0.06906369302490485, | |
| "learning_rate": 0.00016941676109741508, | |
| "loss": 1.1442, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.33288948069241014, | |
| "grad_norm": 0.07869503084625909, | |
| "learning_rate": 0.00016874433106083814, | |
| "loss": 1.1132, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.3355525965379494, | |
| "grad_norm": 0.07767900677929127, | |
| "learning_rate": 0.00016806595517061744, | |
| "loss": 1.1362, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.3382157123834887, | |
| "grad_norm": 0.06780573276986938, | |
| "learning_rate": 0.00016738169210102764, | |
| "loss": 1.1382, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.340878828229028, | |
| "grad_norm": 0.07855904717914698, | |
| "learning_rate": 0.00016669160103553884, | |
| "loss": 1.1146, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.34354194407456723, | |
| "grad_norm": 0.06976051466447154, | |
| "learning_rate": 0.00016599574166169782, | |
| "loss": 1.1156, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.34620505992010653, | |
| "grad_norm": 0.0659729198246215, | |
| "learning_rate": 0.0001652941741659655, | |
| "loss": 1.1636, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3488681757656458, | |
| "grad_norm": 0.06820327345322129, | |
| "learning_rate": 0.00016458695922851125, | |
| "loss": 1.1272, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.35153129161118507, | |
| "grad_norm": 0.0706423611601847, | |
| "learning_rate": 0.0001638741580179645, | |
| "loss": 1.15, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.35419440745672437, | |
| "grad_norm": 0.07009862917994238, | |
| "learning_rate": 0.0001631558321861241, | |
| "loss": 1.1133, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.35685752330226367, | |
| "grad_norm": 0.10252097837226529, | |
| "learning_rate": 0.00016243204386262616, | |
| "loss": 1.1275, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.3595206391478029, | |
| "grad_norm": 0.0677270369109815, | |
| "learning_rate": 0.0001617028556495699, | |
| "loss": 1.1463, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.3621837549933422, | |
| "grad_norm": 0.07081566637081647, | |
| "learning_rate": 0.00016096833061610336, | |
| "loss": 1.1557, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.3648468708388815, | |
| "grad_norm": 0.07606309640077409, | |
| "learning_rate": 0.0001602285322929684, | |
| "loss": 1.1279, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.36750998668442075, | |
| "grad_norm": 0.06926585358652293, | |
| "learning_rate": 0.00015948352466700562, | |
| "loss": 1.1058, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.37017310252996005, | |
| "grad_norm": 0.0768394516058797, | |
| "learning_rate": 0.00015873337217562012, | |
| "loss": 1.1451, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.37283621837549935, | |
| "grad_norm": 0.07574776045146851, | |
| "learning_rate": 0.00015797813970120806, | |
| "loss": 1.1529, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3754993342210386, | |
| "grad_norm": 0.08825811667362324, | |
| "learning_rate": 0.00015721789256554493, | |
| "loss": 1.1427, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.3781624500665779, | |
| "grad_norm": 0.07195501325596203, | |
| "learning_rate": 0.00015645269652413572, | |
| "loss": 1.1348, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.3808255659121172, | |
| "grad_norm": 0.07470988656942844, | |
| "learning_rate": 0.00015568261776052747, | |
| "loss": 1.1389, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.38348868175765644, | |
| "grad_norm": 0.07234292608880714, | |
| "learning_rate": 0.0001549077228805851, | |
| "loss": 1.1265, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.38615179760319573, | |
| "grad_norm": 0.07603813138240277, | |
| "learning_rate": 0.00015412807890673012, | |
| "loss": 1.0975, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.38881491344873503, | |
| "grad_norm": 0.06914740850103318, | |
| "learning_rate": 0.00015334375327214435, | |
| "loss": 1.1656, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.3914780292942743, | |
| "grad_norm": 0.0723373355088882, | |
| "learning_rate": 0.00015255481381493686, | |
| "loss": 1.1235, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.3941411451398136, | |
| "grad_norm": 0.07469762097501292, | |
| "learning_rate": 0.00015176132877227672, | |
| "loss": 1.1401, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.3968042609853529, | |
| "grad_norm": 0.06845354027517625, | |
| "learning_rate": 0.00015096336677449123, | |
| "loss": 1.1299, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.3994673768308921, | |
| "grad_norm": 0.07857096344059177, | |
| "learning_rate": 0.0001501609968391295, | |
| "loss": 1.1362, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.4021304926764314, | |
| "grad_norm": 0.07079465135436822, | |
| "learning_rate": 0.00014935428836499332, | |
| "loss": 1.1268, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.4047936085219707, | |
| "grad_norm": 0.07113035589654983, | |
| "learning_rate": 0.0001485433111261346, | |
| "loss": 1.1357, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.40745672436750996, | |
| "grad_norm": 0.0703269232774503, | |
| "learning_rate": 0.0001477281352658203, | |
| "loss": 1.1239, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.41011984021304926, | |
| "grad_norm": 0.07059355929742223, | |
| "learning_rate": 0.00014690883129046584, | |
| "loss": 1.1442, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.41278295605858856, | |
| "grad_norm": 0.07289277380542494, | |
| "learning_rate": 0.0001460854700635366, | |
| "loss": 1.1267, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.41544607190412786, | |
| "grad_norm": 0.06984202720886337, | |
| "learning_rate": 0.00014525812279941896, | |
| "loss": 1.1258, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.4181091877496671, | |
| "grad_norm": 0.07422048925652114, | |
| "learning_rate": 0.00014442686105726067, | |
| "loss": 1.1193, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.4207723035952064, | |
| "grad_norm": 0.0718716738772194, | |
| "learning_rate": 0.00014359175673478162, | |
| "loss": 1.133, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.4234354194407457, | |
| "grad_norm": 0.07204344165616748, | |
| "learning_rate": 0.00014275288206205524, | |
| "loss": 1.0967, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.42609853528628494, | |
| "grad_norm": 0.07353413673583019, | |
| "learning_rate": 0.00014191030959526105, | |
| "loss": 1.1261, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.42876165113182424, | |
| "grad_norm": 0.0707040442967912, | |
| "learning_rate": 0.00014106411221040933, | |
| "loss": 1.128, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.43142476697736354, | |
| "grad_norm": 0.07086259967904554, | |
| "learning_rate": 0.00014021436309703765, | |
| "loss": 1.107, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.4340878828229028, | |
| "grad_norm": 0.06994136097058291, | |
| "learning_rate": 0.00013936113575188075, | |
| "loss": 1.1221, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.4367509986684421, | |
| "grad_norm": 0.06961342073957084, | |
| "learning_rate": 0.00013850450397251345, | |
| "loss": 1.1208, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.4394141145139814, | |
| "grad_norm": 0.07040932769118938, | |
| "learning_rate": 0.0001376445418509679, | |
| "loss": 1.1208, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.4420772303595206, | |
| "grad_norm": 0.07187314857901307, | |
| "learning_rate": 0.00013678132376732517, | |
| "loss": 1.1267, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.4447403462050599, | |
| "grad_norm": 0.07002729221567015, | |
| "learning_rate": 0.00013591492438328183, | |
| "loss": 1.1421, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.4474034620505992, | |
| "grad_norm": 0.07235067324392022, | |
| "learning_rate": 0.0001350454186356924, | |
| "loss": 1.1191, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.45006657789613846, | |
| "grad_norm": 0.07568410556158327, | |
| "learning_rate": 0.00013417288173008776, | |
| "loss": 1.1123, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.45272969374167776, | |
| "grad_norm": 0.07613155957113646, | |
| "learning_rate": 0.00013329738913417068, | |
| "loss": 1.1137, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.45539280958721706, | |
| "grad_norm": 0.06854447943505289, | |
| "learning_rate": 0.00013241901657128825, | |
| "loss": 1.132, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.4580559254327563, | |
| "grad_norm": 0.06884442803824642, | |
| "learning_rate": 0.00013153784001388247, | |
| "loss": 1.1352, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.4607190412782956, | |
| "grad_norm": 0.0818107600119684, | |
| "learning_rate": 0.00013065393567691913, | |
| "loss": 1.101, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.4633821571238349, | |
| "grad_norm": 0.07690425325074156, | |
| "learning_rate": 0.00012976738001129606, | |
| "loss": 1.1052, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.46604527296937415, | |
| "grad_norm": 0.07952080928038242, | |
| "learning_rate": 0.00012887824969723034, | |
| "loss": 1.1172, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.46870838881491345, | |
| "grad_norm": 0.06637081804522467, | |
| "learning_rate": 0.00012798662163762635, | |
| "loss": 1.1236, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.47137150466045274, | |
| "grad_norm": 0.06753657536020181, | |
| "learning_rate": 0.00012709257295142422, | |
| "loss": 1.1304, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.474034620505992, | |
| "grad_norm": 0.07408199495580661, | |
| "learning_rate": 0.00012619618096692943, | |
| "loss": 1.1523, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.4766977363515313, | |
| "grad_norm": 0.07508862680813526, | |
| "learning_rate": 0.0001252975232151248, | |
| "loss": 1.1158, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.4793608521970706, | |
| "grad_norm": 0.07064406721668945, | |
| "learning_rate": 0.0001243966774229645, | |
| "loss": 1.1334, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.48202396804260983, | |
| "grad_norm": 0.0709335857697155, | |
| "learning_rate": 0.00012349372150665118, | |
| "loss": 1.1104, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.48468708388814913, | |
| "grad_norm": 0.06779392856513489, | |
| "learning_rate": 0.00012258873356489714, | |
| "loss": 1.1299, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.4873501997336884, | |
| "grad_norm": 0.07922531663031743, | |
| "learning_rate": 0.00012168179187216893, | |
| "loss": 1.13, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.49001331557922767, | |
| "grad_norm": 0.07185035702343927, | |
| "learning_rate": 0.0001207729748719177, | |
| "loss": 1.1402, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.49267643142476697, | |
| "grad_norm": 0.07162588557593508, | |
| "learning_rate": 0.00011986236116979406, | |
| "loss": 1.1308, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.49533954727030627, | |
| "grad_norm": 0.07242326329471309, | |
| "learning_rate": 0.0001189500295268495, | |
| "loss": 1.106, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.4980026631158455, | |
| "grad_norm": 0.07434286419305244, | |
| "learning_rate": 0.0001180360588527242, | |
| "loss": 1.119, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.5006657789613849, | |
| "grad_norm": 0.07304306593688702, | |
| "learning_rate": 0.00011712052819882171, | |
| "loss": 1.1503, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.5033288948069241, | |
| "grad_norm": 0.07214685709611712, | |
| "learning_rate": 0.00011620351675147195, | |
| "loss": 1.1095, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.5059920106524634, | |
| "grad_norm": 0.07192838129765652, | |
| "learning_rate": 0.0001152851038250819, | |
| "loss": 1.1451, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.5086551264980027, | |
| "grad_norm": 0.06935787206272043, | |
| "learning_rate": 0.00011436536885527576, | |
| "loss": 1.1251, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.511318242343542, | |
| "grad_norm": 0.06801727149157547, | |
| "learning_rate": 0.00011344439139202421, | |
| "loss": 1.1084, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.5139813581890812, | |
| "grad_norm": 0.07024555806497951, | |
| "learning_rate": 0.00011252225109276404, | |
| "loss": 1.1278, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.5166444740346205, | |
| "grad_norm": 0.06796418511383114, | |
| "learning_rate": 0.00011159902771550837, | |
| "loss": 1.1092, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.5193075898801598, | |
| "grad_norm": 0.07219790467805971, | |
| "learning_rate": 0.00011067480111194817, | |
| "loss": 1.1286, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.521970705725699, | |
| "grad_norm": 0.06944360419194191, | |
| "learning_rate": 0.00010974965122054579, | |
| "loss": 1.1184, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.5246338215712384, | |
| "grad_norm": 0.07229326850745169, | |
| "learning_rate": 0.00010882365805962083, | |
| "loss": 1.1212, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.5272969374167776, | |
| "grad_norm": 0.07181125732929394, | |
| "learning_rate": 0.00010789690172042912, | |
| "loss": 1.1137, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.5299600532623169, | |
| "grad_norm": 0.07145294348037948, | |
| "learning_rate": 0.00010696946236023567, | |
| "loss": 1.1365, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.5326231691078562, | |
| "grad_norm": 0.07057067837966788, | |
| "learning_rate": 0.00010604142019538135, | |
| "loss": 1.1176, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5352862849533955, | |
| "grad_norm": 0.07461665274600122, | |
| "learning_rate": 0.00010511285549434509, | |
| "loss": 1.1152, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.5379494007989347, | |
| "grad_norm": 0.07009722058482384, | |
| "learning_rate": 0.00010418384857080117, | |
| "loss": 1.1117, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.5406125166444741, | |
| "grad_norm": 0.07081680661261375, | |
| "learning_rate": 0.00010325447977667263, | |
| "loss": 1.1328, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.5432756324900133, | |
| "grad_norm": 0.06980388274242631, | |
| "learning_rate": 0.00010232482949518156, | |
| "loss": 1.1404, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.5459387483355526, | |
| "grad_norm": 0.06946364728493262, | |
| "learning_rate": 0.00010139497813389654, | |
| "loss": 1.1127, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.5486018641810919, | |
| "grad_norm": 0.06947172503952885, | |
| "learning_rate": 0.00010046500611777798, | |
| "loss": 1.0937, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.5512649800266312, | |
| "grad_norm": 0.07414647895551518, | |
| "learning_rate": 9.953499388222202e-05, | |
| "loss": 1.132, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.5539280958721704, | |
| "grad_norm": 0.07085672498663681, | |
| "learning_rate": 9.860502186610349e-05, | |
| "loss": 1.0998, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.5565912117177098, | |
| "grad_norm": 0.07198312270884867, | |
| "learning_rate": 9.767517050481846e-05, | |
| "loss": 1.1263, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.559254327563249, | |
| "grad_norm": 0.07070349541708286, | |
| "learning_rate": 9.67455202233274e-05, | |
| "loss": 1.1143, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5619174434087882, | |
| "grad_norm": 0.06990981328605791, | |
| "learning_rate": 9.581615142919887e-05, | |
| "loss": 1.1168, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.5645805592543276, | |
| "grad_norm": 0.07221018297233557, | |
| "learning_rate": 9.488714450565491e-05, | |
| "loss": 1.1123, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.5672436750998668, | |
| "grad_norm": 0.06895775963564511, | |
| "learning_rate": 9.395857980461867e-05, | |
| "loss": 1.1294, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.5699067909454061, | |
| "grad_norm": 0.06904508970279108, | |
| "learning_rate": 9.303053763976434e-05, | |
| "loss": 1.1179, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.5725699067909454, | |
| "grad_norm": 0.07131791944898686, | |
| "learning_rate": 9.210309827957089e-05, | |
| "loss": 1.1297, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.5752330226364847, | |
| "grad_norm": 0.07117429268373339, | |
| "learning_rate": 9.117634194037922e-05, | |
| "loss": 1.1285, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.5778961384820239, | |
| "grad_norm": 0.0720403827517469, | |
| "learning_rate": 9.025034877945422e-05, | |
| "loss": 1.1418, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.5805592543275633, | |
| "grad_norm": 0.07399424819774852, | |
| "learning_rate": 8.932519888805185e-05, | |
| "loss": 1.1521, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.5832223701731025, | |
| "grad_norm": 0.06757782738616369, | |
| "learning_rate": 8.840097228449165e-05, | |
| "loss": 1.1468, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.5858854860186418, | |
| "grad_norm": 0.07513462470349377, | |
| "learning_rate": 8.747774890723599e-05, | |
| "loss": 1.1008, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5885486018641811, | |
| "grad_norm": 0.07193663724723076, | |
| "learning_rate": 8.655560860797582e-05, | |
| "loss": 1.1364, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.5912117177097204, | |
| "grad_norm": 0.07451485853238139, | |
| "learning_rate": 8.563463114472425e-05, | |
| "loss": 1.1077, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.5938748335552596, | |
| "grad_norm": 0.07208026414944517, | |
| "learning_rate": 8.471489617491812e-05, | |
| "loss": 1.0828, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.596537949400799, | |
| "grad_norm": 0.06968442188475359, | |
| "learning_rate": 8.379648324852808e-05, | |
| "loss": 1.0975, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.5992010652463382, | |
| "grad_norm": 0.07690321076998301, | |
| "learning_rate": 8.287947180117832e-05, | |
| "loss": 1.1149, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.6018641810918774, | |
| "grad_norm": 0.07088556456471248, | |
| "learning_rate": 8.196394114727585e-05, | |
| "loss": 1.1193, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.6045272969374168, | |
| "grad_norm": 0.07306182012233282, | |
| "learning_rate": 8.104997047315048e-05, | |
| "loss": 1.1222, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.607190412782956, | |
| "grad_norm": 0.0735136578466246, | |
| "learning_rate": 8.013763883020596e-05, | |
| "loss": 1.1326, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.6098535286284953, | |
| "grad_norm": 0.0792004084312011, | |
| "learning_rate": 7.92270251280823e-05, | |
| "loss": 1.1125, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.6125166444740346, | |
| "grad_norm": 0.06995636578434544, | |
| "learning_rate": 7.831820812783108e-05, | |
| "loss": 1.1397, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.6151797603195739, | |
| "grad_norm": 0.07156672219633958, | |
| "learning_rate": 7.741126643510292e-05, | |
| "loss": 1.1047, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.6178428761651131, | |
| "grad_norm": 0.06990042451203095, | |
| "learning_rate": 7.650627849334881e-05, | |
| "loss": 1.0991, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.6205059920106525, | |
| "grad_norm": 0.07175460373797926, | |
| "learning_rate": 7.560332257703555e-05, | |
| "loss": 1.1179, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.6231691078561917, | |
| "grad_norm": 0.07079860289283964, | |
| "learning_rate": 7.470247678487522e-05, | |
| "loss": 1.1179, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.625832223701731, | |
| "grad_norm": 0.06955306779443195, | |
| "learning_rate": 7.380381903307061e-05, | |
| "loss": 1.1261, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.6284953395472703, | |
| "grad_norm": 0.07040121930899221, | |
| "learning_rate": 7.290742704857585e-05, | |
| "loss": 1.128, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.6311584553928096, | |
| "grad_norm": 0.0696134794381735, | |
| "learning_rate": 7.201337836237365e-05, | |
| "loss": 1.1006, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.6338215712383488, | |
| "grad_norm": 0.0731972119965864, | |
| "learning_rate": 7.112175030276969e-05, | |
| "loss": 1.122, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.6364846870838882, | |
| "grad_norm": 0.07600883906312528, | |
| "learning_rate": 7.023261998870395e-05, | |
| "loss": 1.1054, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.6391478029294274, | |
| "grad_norm": 0.06927208348922254, | |
| "learning_rate": 6.934606432308086e-05, | |
| "loss": 1.1128, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6418109187749668, | |
| "grad_norm": 0.06936985978073082, | |
| "learning_rate": 6.846215998611757e-05, | |
| "loss": 1.118, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.644474034620506, | |
| "grad_norm": 0.07077273319280314, | |
| "learning_rate": 6.758098342871174e-05, | |
| "loss": 1.1093, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.6471371504660453, | |
| "grad_norm": 0.07079727575348424, | |
| "learning_rate": 6.670261086582933e-05, | |
| "loss": 1.1231, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.6498002663115846, | |
| "grad_norm": 0.07181688909396321, | |
| "learning_rate": 6.582711826991226e-05, | |
| "loss": 1.1042, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.6524633821571239, | |
| "grad_norm": 0.07337324643783341, | |
| "learning_rate": 6.495458136430765e-05, | |
| "loss": 1.1042, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.6551264980026631, | |
| "grad_norm": 0.07212862237245772, | |
| "learning_rate": 6.408507561671819e-05, | |
| "loss": 1.1509, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.6577896138482024, | |
| "grad_norm": 0.07047120035609092, | |
| "learning_rate": 6.321867623267481e-05, | |
| "loss": 1.1355, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.6604527296937417, | |
| "grad_norm": 0.07459478385718604, | |
| "learning_rate": 6.23554581490321e-05, | |
| "loss": 1.1178, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.6631158455392809, | |
| "grad_norm": 0.06825726344400981, | |
| "learning_rate": 6.149549602748656e-05, | |
| "loss": 1.0862, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.6657789613848203, | |
| "grad_norm": 0.07240193352920372, | |
| "learning_rate": 6.063886424811929e-05, | |
| "loss": 1.1292, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6684420772303595, | |
| "grad_norm": 0.07197359550672061, | |
| "learning_rate": 5.9785636902962374e-05, | |
| "loss": 1.1306, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.6711051930758988, | |
| "grad_norm": 0.07343322507680913, | |
| "learning_rate": 5.893588778959067e-05, | |
| "loss": 1.1365, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.6737683089214381, | |
| "grad_norm": 0.07842185463764602, | |
| "learning_rate": 5.8089690404738925e-05, | |
| "loss": 1.1395, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.6764314247669774, | |
| "grad_norm": 0.07270053681642126, | |
| "learning_rate": 5.7247117937944786e-05, | |
| "loss": 1.1035, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.6790945406125166, | |
| "grad_norm": 0.07124055104083139, | |
| "learning_rate": 5.640824326521841e-05, | |
| "loss": 1.1121, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.681757656458056, | |
| "grad_norm": 0.07031788560347749, | |
| "learning_rate": 5.5573138942739365e-05, | |
| "loss": 1.1192, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.6844207723035952, | |
| "grad_norm": 0.07253058219251593, | |
| "learning_rate": 5.4741877200581057e-05, | |
| "loss": 1.1324, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.6870838881491345, | |
| "grad_norm": 0.0725305584439251, | |
| "learning_rate": 5.391452993646342e-05, | |
| "loss": 1.1387, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.6897470039946738, | |
| "grad_norm": 0.07021354602161774, | |
| "learning_rate": 5.30911687095342e-05, | |
| "loss": 1.126, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.6924101198402131, | |
| "grad_norm": 0.07012940672098344, | |
| "learning_rate": 5.227186473417971e-05, | |
| "loss": 1.1486, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6950732356857523, | |
| "grad_norm": 0.07232533360594767, | |
| "learning_rate": 5.145668887386543e-05, | |
| "loss": 1.1111, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.6977363515312917, | |
| "grad_norm": 0.07242821758103567, | |
| "learning_rate": 5.064571163500667e-05, | |
| "loss": 1.1181, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.7003994673768309, | |
| "grad_norm": 0.07148030530795384, | |
| "learning_rate": 4.983900316087051e-05, | |
| "loss": 1.0922, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.7030625832223701, | |
| "grad_norm": 0.07277623674879777, | |
| "learning_rate": 4.90366332255088e-05, | |
| "loss": 1.0985, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.7057256990679095, | |
| "grad_norm": 0.07450043090731064, | |
| "learning_rate": 4.823867122772329e-05, | |
| "loss": 1.1177, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.7083888149134487, | |
| "grad_norm": 0.07438166449706331, | |
| "learning_rate": 4.744518618506319e-05, | |
| "loss": 1.1225, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.711051930758988, | |
| "grad_norm": 0.07157294185481793, | |
| "learning_rate": 4.665624672785566e-05, | |
| "loss": 1.1291, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.7137150466045273, | |
| "grad_norm": 0.07520781395221099, | |
| "learning_rate": 4.5871921093269875e-05, | |
| "loss": 1.1082, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.7163781624500666, | |
| "grad_norm": 0.07203181974145231, | |
| "learning_rate": 4.5092277119414975e-05, | |
| "loss": 1.1333, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.7190412782956058, | |
| "grad_norm": 0.07130465564504203, | |
| "learning_rate": 4.431738223947252e-05, | |
| "loss": 1.0951, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.7217043941411452, | |
| "grad_norm": 0.075489827909183, | |
| "learning_rate": 4.35473034758643e-05, | |
| "loss": 1.1223, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.7243675099866844, | |
| "grad_norm": 0.07030155738463333, | |
| "learning_rate": 4.2782107434455054e-05, | |
| "loss": 1.1222, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.7270306258322237, | |
| "grad_norm": 0.07218531177873333, | |
| "learning_rate": 4.202186029879195e-05, | |
| "loss": 1.1135, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.729693741677763, | |
| "grad_norm": 0.07513760712282253, | |
| "learning_rate": 4.12666278243799e-05, | |
| "loss": 1.1181, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.7323568575233023, | |
| "grad_norm": 0.07435576640285345, | |
| "learning_rate": 4.0516475332994383e-05, | |
| "loss": 1.119, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.7350199733688415, | |
| "grad_norm": 0.07125188708419379, | |
| "learning_rate": 3.9771467707031615e-05, | |
| "loss": 1.1201, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.7376830892143809, | |
| "grad_norm": 0.07352772721979937, | |
| "learning_rate": 3.903166938389664e-05, | |
| "loss": 1.112, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.7403462050599201, | |
| "grad_norm": 0.07055845215545062, | |
| "learning_rate": 3.8297144350430144e-05, | |
| "loss": 1.1046, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.7430093209054593, | |
| "grad_norm": 0.07019837722638089, | |
| "learning_rate": 3.756795613737388e-05, | |
| "loss": 1.1306, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.7456724367509987, | |
| "grad_norm": 0.07239297940522006, | |
| "learning_rate": 3.684416781387589e-05, | |
| "loss": 1.1184, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.748335552596538, | |
| "grad_norm": 0.07225126596889433, | |
| "learning_rate": 3.6125841982035536e-05, | |
| "loss": 1.0843, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.7509986684420772, | |
| "grad_norm": 0.07431737331558284, | |
| "learning_rate": 3.5413040771488746e-05, | |
| "loss": 1.1145, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.7536617842876165, | |
| "grad_norm": 0.07502128782750854, | |
| "learning_rate": 3.47058258340345e-05, | |
| "loss": 1.1114, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.7563249001331558, | |
| "grad_norm": 0.07207529195587527, | |
| "learning_rate": 3.4004258338302195e-05, | |
| "loss": 1.116, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.758988015978695, | |
| "grad_norm": 0.07002467859956689, | |
| "learning_rate": 3.3308398964461206e-05, | |
| "loss": 1.1198, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.7616511318242344, | |
| "grad_norm": 0.07224058742693344, | |
| "learning_rate": 3.261830789897241e-05, | |
| "loss": 1.1367, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.7643142476697736, | |
| "grad_norm": 0.07150872607987452, | |
| "learning_rate": 3.193404482938256e-05, | |
| "loss": 1.0982, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.7669773635153129, | |
| "grad_norm": 0.07178998194161153, | |
| "learning_rate": 3.1255668939161894e-05, | |
| "loss": 1.1301, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.7696404793608522, | |
| "grad_norm": 0.07537933178179766, | |
| "learning_rate": 3.058323890258498e-05, | |
| "loss": 1.0962, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.7723035952063915, | |
| "grad_norm": 0.07189617812023931, | |
| "learning_rate": 2.9916812879655975e-05, | |
| "loss": 1.1299, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7749667110519307, | |
| "grad_norm": 0.07135524342299995, | |
| "learning_rate": 2.925644851107835e-05, | |
| "loss": 1.1189, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.7776298268974701, | |
| "grad_norm": 0.06926273022163672, | |
| "learning_rate": 2.860220291326915e-05, | |
| "loss": 1.1068, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.7802929427430093, | |
| "grad_norm": 0.07236268331467403, | |
| "learning_rate": 2.7954132673419143e-05, | |
| "loss": 1.0981, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.7829560585885486, | |
| "grad_norm": 0.07137745473045948, | |
| "learning_rate": 2.7312293844598246e-05, | |
| "loss": 1.1045, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.7856191744340879, | |
| "grad_norm": 0.07319916214034358, | |
| "learning_rate": 2.6676741940907478e-05, | |
| "loss": 1.1281, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.7882822902796272, | |
| "grad_norm": 0.07414585611908868, | |
| "learning_rate": 2.6047531932677383e-05, | |
| "loss": 1.1225, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.7909454061251664, | |
| "grad_norm": 0.07066978423343756, | |
| "learning_rate": 2.542471824171353e-05, | |
| "loss": 1.1356, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.7936085219707057, | |
| "grad_norm": 0.07124448208473912, | |
| "learning_rate": 2.4808354736589523e-05, | |
| "loss": 1.1323, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.796271637816245, | |
| "grad_norm": 0.07192509266254882, | |
| "learning_rate": 2.419849472798761e-05, | |
| "loss": 1.1386, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.7989347536617842, | |
| "grad_norm": 0.07470536521159465, | |
| "learning_rate": 2.359519096408791e-05, | |
| "loss": 1.1103, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8015978695073236, | |
| "grad_norm": 0.07210949951260932, | |
| "learning_rate": 2.2998495626005957e-05, | |
| "loss": 1.1108, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.8042609853528628, | |
| "grad_norm": 0.07516415250373631, | |
| "learning_rate": 2.240846032327949e-05, | |
| "loss": 1.1404, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.8069241011984021, | |
| "grad_norm": 0.07560562529629619, | |
| "learning_rate": 2.1825136089404718e-05, | |
| "loss": 1.0935, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.8095872170439414, | |
| "grad_norm": 0.07195974938474745, | |
| "learning_rate": 2.1248573377422155e-05, | |
| "loss": 1.1182, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.8122503328894807, | |
| "grad_norm": 0.07250882969384367, | |
| "learning_rate": 2.0678822055552906e-05, | |
| "loss": 1.1189, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.8149134487350199, | |
| "grad_norm": 0.0721751215640965, | |
| "learning_rate": 2.0115931402885458e-05, | |
| "loss": 1.1115, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.8175765645805593, | |
| "grad_norm": 0.0753848259347461, | |
| "learning_rate": 1.955995010511338e-05, | |
| "loss": 1.1348, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.8202396804260985, | |
| "grad_norm": 0.0719207373284397, | |
| "learning_rate": 1.901092625032448e-05, | |
| "loss": 1.1042, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.8229027962716379, | |
| "grad_norm": 0.07032664869488064, | |
| "learning_rate": 1.84689073248414e-05, | |
| "loss": 1.1009, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.8255659121171771, | |
| "grad_norm": 0.0700654057925292, | |
| "learning_rate": 1.7933940209114597e-05, | |
| "loss": 1.1269, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.8282290279627164, | |
| "grad_norm": 0.07325193867745135, | |
| "learning_rate": 1.7406071173667372e-05, | |
| "loss": 1.1138, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.8308921438082557, | |
| "grad_norm": 0.07059680065497263, | |
| "learning_rate": 1.6885345875093918e-05, | |
| "loss": 1.1202, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.833555259653795, | |
| "grad_norm": 0.06973843219886788, | |
| "learning_rate": 1.6371809352110447e-05, | |
| "loss": 1.109, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.8362183754993342, | |
| "grad_norm": 0.07028429615451927, | |
| "learning_rate": 1.5865506021659516e-05, | |
| "loss": 1.1422, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.8388814913448736, | |
| "grad_norm": 0.07070004444035057, | |
| "learning_rate": 1.5366479675068435e-05, | |
| "loss": 1.1139, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.8415446071904128, | |
| "grad_norm": 0.06902941716806588, | |
| "learning_rate": 1.4874773474261638e-05, | |
| "loss": 1.1179, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.844207723035952, | |
| "grad_norm": 0.07227429481260465, | |
| "learning_rate": 1.4390429948027428e-05, | |
| "loss": 1.1156, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.8468708388814914, | |
| "grad_norm": 0.07067313252269349, | |
| "learning_rate": 1.3913490988339718e-05, | |
| "loss": 1.1209, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.8495339547270306, | |
| "grad_norm": 0.07249077076436629, | |
| "learning_rate": 1.3443997846734535e-05, | |
| "loss": 1.1303, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.8521970705725699, | |
| "grad_norm": 0.07121930519374212, | |
| "learning_rate": 1.2981991130742211e-05, | |
| "loss": 1.1069, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8548601864181092, | |
| "grad_norm": 0.06967637890151408, | |
| "learning_rate": 1.2527510800375043e-05, | |
| "loss": 1.1007, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.8575233022636485, | |
| "grad_norm": 0.07205061200000021, | |
| "learning_rate": 1.20805961646711e-05, | |
| "loss": 1.1199, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.8601864181091877, | |
| "grad_norm": 0.07129006954483187, | |
| "learning_rate": 1.1641285878294372e-05, | |
| "loss": 1.1054, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.8628495339547271, | |
| "grad_norm": 0.07540152645446788, | |
| "learning_rate": 1.1209617938191307e-05, | |
| "loss": 1.1032, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.8655126498002663, | |
| "grad_norm": 0.07238275344561401, | |
| "learning_rate": 1.0785629680304432e-05, | |
| "loss": 1.1246, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.8681757656458056, | |
| "grad_norm": 0.07120538294411066, | |
| "learning_rate": 1.0369357776343103e-05, | |
| "loss": 1.0932, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.8708388814913449, | |
| "grad_norm": 0.07125849884630578, | |
| "learning_rate": 9.960838230611635e-06, | |
| "loss": 1.0728, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.8735019973368842, | |
| "grad_norm": 0.07387109327159767, | |
| "learning_rate": 9.560106376895306e-06, | |
| "loss": 1.1275, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.8761651131824234, | |
| "grad_norm": 0.08867831950654811, | |
| "learning_rate": 9.167196875404094e-06, | |
| "loss": 1.1134, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.8788282290279628, | |
| "grad_norm": 0.07206488784580595, | |
| "learning_rate": 8.782143709775015e-06, | |
| "loss": 1.109, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.881491344873502, | |
| "grad_norm": 0.07037650282884113, | |
| "learning_rate": 8.40498018413266e-06, | |
| "loss": 1.0862, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.8841544607190412, | |
| "grad_norm": 0.07329640323219759, | |
| "learning_rate": 8.035738920208714e-06, | |
| "loss": 1.1539, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.8868175765645806, | |
| "grad_norm": 0.07238224996992595, | |
| "learning_rate": 7.67445185452046e-06, | |
| "loss": 1.14, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.8894806924101198, | |
| "grad_norm": 0.0709614207657161, | |
| "learning_rate": 7.321150235608399e-06, | |
| "loss": 1.1084, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.8921438082556591, | |
| "grad_norm": 0.0726275702018448, | |
| "learning_rate": 6.9758646213336165e-06, | |
| "loss": 1.1227, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.8948069241011984, | |
| "grad_norm": 0.07467788565919785, | |
| "learning_rate": 6.6386248762347004e-06, | |
| "loss": 1.1135, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.8974700399467377, | |
| "grad_norm": 0.07203922681266979, | |
| "learning_rate": 6.309460168944692e-06, | |
| "loss": 1.1071, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.9001331557922769, | |
| "grad_norm": 0.07114745434226347, | |
| "learning_rate": 5.988398969668285e-06, | |
| "loss": 1.1248, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.9027962716378163, | |
| "grad_norm": 0.07111413913413335, | |
| "learning_rate": 5.6754690477192396e-06, | |
| "loss": 1.0872, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.9054593874833555, | |
| "grad_norm": 0.07072306177993802, | |
| "learning_rate": 5.370697469118713e-06, | |
| "loss": 1.0824, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9081225033288948, | |
| "grad_norm": 0.07185114603062198, | |
| "learning_rate": 5.074110594254133e-06, | |
| "loss": 1.107, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.9107856191744341, | |
| "grad_norm": 0.07285137048040193, | |
| "learning_rate": 4.78573407559928e-06, | |
| "loss": 1.1173, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.9134487350199734, | |
| "grad_norm": 0.07013700832744958, | |
| "learning_rate": 4.5055928554955665e-06, | |
| "loss": 1.116, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.9161118508655126, | |
| "grad_norm": 0.06933918410316768, | |
| "learning_rate": 4.233711163994669e-06, | |
| "loss": 1.1038, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.918774966711052, | |
| "grad_norm": 0.072978505928099, | |
| "learning_rate": 3.970112516762825e-06, | |
| "loss": 1.104, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.9214380825565912, | |
| "grad_norm": 0.07096666064833597, | |
| "learning_rate": 3.7148197130469576e-06, | |
| "loss": 1.1169, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.9241011984021305, | |
| "grad_norm": 0.07024364472390462, | |
| "learning_rate": 3.467854833702644e-06, | |
| "loss": 1.1051, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.9267643142476698, | |
| "grad_norm": 0.0725948329149083, | |
| "learning_rate": 3.229239239284354e-06, | |
| "loss": 1.1257, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.929427430093209, | |
| "grad_norm": 0.07215970561357568, | |
| "learning_rate": 2.9989935681979164e-06, | |
| "loss": 1.1262, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.9320905459387483, | |
| "grad_norm": 0.0737761172543898, | |
| "learning_rate": 2.777137734915403e-06, | |
| "loss": 1.1091, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.9347536617842876, | |
| "grad_norm": 0.0714550851543958, | |
| "learning_rate": 2.563690928252749e-06, | |
| "loss": 1.1283, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.9374167776298269, | |
| "grad_norm": 0.07157410935337963, | |
| "learning_rate": 2.358671609710017e-06, | |
| "loss": 1.1239, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.9400798934753661, | |
| "grad_norm": 0.0715459262435765, | |
| "learning_rate": 2.1620975118746835e-06, | |
| "loss": 1.1283, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.9427430093209055, | |
| "grad_norm": 0.07286793622379441, | |
| "learning_rate": 1.9739856368878096e-06, | |
| "loss": 1.1443, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.9454061251664447, | |
| "grad_norm": 0.07254981755374063, | |
| "learning_rate": 1.794352254973597e-06, | |
| "loss": 1.0752, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.948069241011984, | |
| "grad_norm": 0.07583062173231125, | |
| "learning_rate": 1.6232129030320453e-06, | |
| "loss": 1.1011, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.9507323568575233, | |
| "grad_norm": 0.07237886602221254, | |
| "learning_rate": 1.4605823832951948e-06, | |
| "loss": 1.1063, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.9533954727030626, | |
| "grad_norm": 0.07194863306691765, | |
| "learning_rate": 1.3064747620468054e-06, | |
| "loss": 1.0914, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.9560585885486018, | |
| "grad_norm": 0.07189535177125876, | |
| "learning_rate": 1.1609033684057857e-06, | |
| "loss": 1.1048, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.9587217043941412, | |
| "grad_norm": 0.07110020697306084, | |
| "learning_rate": 1.0238807931732487e-06, | |
| "loss": 1.1219, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9613848202396804, | |
| "grad_norm": 0.07370460890021728, | |
| "learning_rate": 8.95418887743571e-07, | |
| "loss": 1.1317, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.9640479360852197, | |
| "grad_norm": 0.07207691237434337, | |
| "learning_rate": 7.75528763079314e-07, | |
| "loss": 1.1126, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.966711051930759, | |
| "grad_norm": 0.07440378502380679, | |
| "learning_rate": 6.642207887502027e-07, | |
| "loss": 1.1262, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.9693741677762983, | |
| "grad_norm": 0.06937782526053558, | |
| "learning_rate": 5.615045920362549e-07, | |
| "loss": 1.1191, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.9720372836218375, | |
| "grad_norm": 0.07098237504174736, | |
| "learning_rate": 4.673890570951023e-07, | |
| "loss": 1.1218, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.9747003994673769, | |
| "grad_norm": 0.07181367245928705, | |
| "learning_rate": 3.8188232419352764e-07, | |
| "loss": 1.1514, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.9773635153129161, | |
| "grad_norm": 0.07128549274991237, | |
| "learning_rate": 3.049917890034837e-07, | |
| "loss": 1.0945, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.9800266311584553, | |
| "grad_norm": 0.07161530878264005, | |
| "learning_rate": 2.3672410196232675e-07, | |
| "loss": 1.1056, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.9826897470039947, | |
| "grad_norm": 0.07090950092701657, | |
| "learning_rate": 1.7708516769769924e-07, | |
| "loss": 1.1109, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.9853528628495339, | |
| "grad_norm": 0.07140303003446424, | |
| "learning_rate": 1.2608014451672702e-07, | |
| "loss": 1.1252, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9880159786950732, | |
| "grad_norm": 0.07103068810909154, | |
| "learning_rate": 8.371344395996516e-08, | |
| "loss": 1.1255, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.9906790945406125, | |
| "grad_norm": 0.07153307782175972, | |
| "learning_rate": 4.998873041975882e-08, | |
| "loss": 1.1365, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.9933422103861518, | |
| "grad_norm": 0.06996817906726589, | |
| "learning_rate": 2.490892082331886e-08, | |
| "loss": 1.1142, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.996005326231691, | |
| "grad_norm": 0.07126895143317796, | |
| "learning_rate": 8.476184380468155e-09, | |
| "loss": 1.1091, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.9986684420772304, | |
| "grad_norm": 0.0706408297239244, | |
| "learning_rate": 6.919423959805826e-10, | |
| "loss": 1.1206, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.9997336884154461, | |
| "eval_loss": 1.118857979774475, | |
| "eval_runtime": 1652.5253, | |
| "eval_samples_per_second": 8.045, | |
| "eval_steps_per_second": 0.503, | |
| "step": 1877 | |
| }, | |
| { | |
| "epoch": 0.9997336884154461, | |
| "step": 1877, | |
| "total_flos": 2.979798729936077e+16, | |
| "train_loss": 1.1429596533467938, | |
| "train_runtime": 55739.5179, | |
| "train_samples_per_second": 2.156, | |
| "train_steps_per_second": 0.034 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1877, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.979798729936077e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |