| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02284174099749883, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002284174099749883, | |
| "grad_norm": 0.6011635661125183, | |
| "learning_rate": 0.00019995065603657316, | |
| "loss": 2.2538, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004568348199499766, | |
| "grad_norm": 0.8175456523895264, | |
| "learning_rate": 0.00019980267284282717, | |
| "loss": 2.1126, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006852522299249648, | |
| "grad_norm": 1.1491563320159912, | |
| "learning_rate": 0.00019955619646030802, | |
| "loss": 2.228, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009136696398999532, | |
| "grad_norm": 1.0827499628067017, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 2.1703, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0011420870498749414, | |
| "grad_norm": 1.157465934753418, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 2.0955, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0013705044598499297, | |
| "grad_norm": 1.0857897996902466, | |
| "learning_rate": 0.0001982287250728689, | |
| "loss": 2.1769, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0015989218698249181, | |
| "grad_norm": 1.377300500869751, | |
| "learning_rate": 0.00019759167619387476, | |
| "loss": 2.1335, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0018273392797999064, | |
| "grad_norm": 0.8308928608894348, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 2.0746, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0020557566897748945, | |
| "grad_norm": 1.1545639038085938, | |
| "learning_rate": 0.0001960293685676943, | |
| "loss": 2.3118, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0022841740997498828, | |
| "grad_norm": 0.9956186413764954, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.1476, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002512591509724871, | |
| "grad_norm": 1.1778929233551025, | |
| "learning_rate": 0.00019408807689542257, | |
| "loss": 1.9218, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0027410089196998593, | |
| "grad_norm": 1.2166578769683838, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 2.1764, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.002969426329674848, | |
| "grad_norm": 0.9831048846244812, | |
| "learning_rate": 0.00019177546256839812, | |
| "loss": 2.1327, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0031978437396498363, | |
| "grad_norm": 0.9150891900062561, | |
| "learning_rate": 0.00019048270524660196, | |
| "loss": 2.0719, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0034262611496248246, | |
| "grad_norm": 1.078007459640503, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 2.1048, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003654678559599813, | |
| "grad_norm": 0.9422916173934937, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.0419, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.003883095969574801, | |
| "grad_norm": 1.0269567966461182, | |
| "learning_rate": 0.0001860742027003944, | |
| "loss": 2.0837, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.004111513379549789, | |
| "grad_norm": 0.9426142573356628, | |
| "learning_rate": 0.00018443279255020152, | |
| "loss": 2.0422, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.004339930789524778, | |
| "grad_norm": 1.018721103668213, | |
| "learning_rate": 0.00018270805742745617, | |
| "loss": 2.1384, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0045683481994997655, | |
| "grad_norm": 1.1313502788543701, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.1318, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004796765609474754, | |
| "grad_norm": 0.6934864521026611, | |
| "learning_rate": 0.00017901550123756906, | |
| "loss": 2.2722, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.005025183019449742, | |
| "grad_norm": 0.8822490572929382, | |
| "learning_rate": 0.00017705132427757895, | |
| "loss": 2.0774, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.005253600429424731, | |
| "grad_norm": 1.1275163888931274, | |
| "learning_rate": 0.00017501110696304596, | |
| "loss": 2.1253, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.005482017839399719, | |
| "grad_norm": 1.0035189390182495, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 2.1624, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.005710435249374707, | |
| "grad_norm": 0.8009467124938965, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0543, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.005938852659349696, | |
| "grad_norm": 0.9582347869873047, | |
| "learning_rate": 0.00016845471059286887, | |
| "loss": 2.1542, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.006167270069324684, | |
| "grad_norm": 1.0823897123336792, | |
| "learning_rate": 0.00016613118653236518, | |
| "loss": 2.3268, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.006395687479299673, | |
| "grad_norm": 0.9078360795974731, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 2.0749, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.0066241048892746604, | |
| "grad_norm": 1.0934821367263794, | |
| "learning_rate": 0.00016129070536529766, | |
| "loss": 2.2403, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.006852522299249649, | |
| "grad_norm": 1.464321494102478, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 2.0575, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.007080939709224637, | |
| "grad_norm": 0.9363439679145813, | |
| "learning_rate": 0.00015620833778521307, | |
| "loss": 2.3062, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.007309357119199626, | |
| "grad_norm": 1.1936748027801514, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 2.081, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.0075377745291746135, | |
| "grad_norm": 0.8682211637496948, | |
| "learning_rate": 0.00015090414157503714, | |
| "loss": 2.0289, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.007766191939149602, | |
| "grad_norm": 1.123822569847107, | |
| "learning_rate": 0.00014817536741017152, | |
| "loss": 2.2525, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.00799460934912459, | |
| "grad_norm": 0.8017176389694214, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 2.213, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.008223026759099578, | |
| "grad_norm": 0.8773420453071594, | |
| "learning_rate": 0.00014257792915650728, | |
| "loss": 2.0703, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.008451444169074568, | |
| "grad_norm": 1.1905558109283447, | |
| "learning_rate": 0.00013971478906347806, | |
| "loss": 2.1984, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.008679861579049555, | |
| "grad_norm": 0.8345734477043152, | |
| "learning_rate": 0.00013681245526846783, | |
| "loss": 2.0921, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.008908278989024543, | |
| "grad_norm": 1.126680612564087, | |
| "learning_rate": 0.00013387379202452917, | |
| "loss": 2.0888, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.009136696398999531, | |
| "grad_norm": 1.0113277435302734, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0344, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.00936511380897452, | |
| "grad_norm": 1.6838539838790894, | |
| "learning_rate": 0.00012789911060392294, | |
| "loss": 2.0585, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.009593531218949508, | |
| "grad_norm": 0.9599931240081787, | |
| "learning_rate": 0.0001248689887164855, | |
| "loss": 2.1937, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.009821948628924496, | |
| "grad_norm": 1.091261386871338, | |
| "learning_rate": 0.00012181432413965428, | |
| "loss": 2.2075, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.010050366038899484, | |
| "grad_norm": 1.618888020515442, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 2.0918, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.010278783448874474, | |
| "grad_norm": 0.8518305420875549, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 2.0674, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.010507200858849462, | |
| "grad_norm": 0.823520839214325, | |
| "learning_rate": 0.00011253332335643043, | |
| "loss": 2.118, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.01073561826882445, | |
| "grad_norm": 1.0874645709991455, | |
| "learning_rate": 0.00010941083133185146, | |
| "loss": 2.1401, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.010964035678799437, | |
| "grad_norm": 1.0509600639343262, | |
| "learning_rate": 0.00010627905195293135, | |
| "loss": 2.2394, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.011192453088774427, | |
| "grad_norm": 0.8310794234275818, | |
| "learning_rate": 0.00010314107590781284, | |
| "loss": 2.09, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.011420870498749415, | |
| "grad_norm": 0.963942289352417, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0202, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.011649287908724403, | |
| "grad_norm": 0.9792200326919556, | |
| "learning_rate": 9.685892409218717e-05, | |
| "loss": 2.2468, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.011877705318699392, | |
| "grad_norm": 0.8218494653701782, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 2.3187, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.01210612272867438, | |
| "grad_norm": 1.120417833328247, | |
| "learning_rate": 9.058916866814858e-05, | |
| "loss": 2.1024, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.012334540138649368, | |
| "grad_norm": 1.0600074529647827, | |
| "learning_rate": 8.746667664356956e-05, | |
| "loss": 2.1056, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.012562957548624356, | |
| "grad_norm": 1.0849493741989136, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.0486, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.012791374958599345, | |
| "grad_norm": 0.9597050547599792, | |
| "learning_rate": 8.126186854142752e-05, | |
| "loss": 2.1524, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.013019792368574333, | |
| "grad_norm": 0.6964913010597229, | |
| "learning_rate": 7.818567586034577e-05, | |
| "loss": 2.5253, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.013248209778549321, | |
| "grad_norm": 0.8805552124977112, | |
| "learning_rate": 7.513101128351454e-05, | |
| "loss": 1.9732, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.013476627188524309, | |
| "grad_norm": 0.8434686660766602, | |
| "learning_rate": 7.210088939607708e-05, | |
| "loss": 2.1449, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.013705044598499298, | |
| "grad_norm": 0.7308034896850586, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.9493, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.013933462008474286, | |
| "grad_norm": 0.7747200131416321, | |
| "learning_rate": 6.612620797547087e-05, | |
| "loss": 2.4289, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.014161879418449274, | |
| "grad_norm": 0.9479460716247559, | |
| "learning_rate": 6.318754473153221e-05, | |
| "loss": 2.0873, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.014390296828424262, | |
| "grad_norm": 0.8679899573326111, | |
| "learning_rate": 6.0285210936521955e-05, | |
| "loss": 2.1007, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.014618714238399251, | |
| "grad_norm": 1.1402413845062256, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.9974, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.01484713164837424, | |
| "grad_norm": 0.944284975528717, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 2.1228, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.015075549058349227, | |
| "grad_norm": 1.2122584581375122, | |
| "learning_rate": 5.182463258982846e-05, | |
| "loss": 2.1118, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.015303966468324215, | |
| "grad_norm": 0.8726314306259155, | |
| "learning_rate": 4.909585842496287e-05, | |
| "loss": 2.0166, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.015532383878299204, | |
| "grad_norm": 0.8935607075691223, | |
| "learning_rate": 4.6417320502100316e-05, | |
| "loss": 2.0992, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.01576080128827419, | |
| "grad_norm": 0.7619888186454773, | |
| "learning_rate": 4.379166221478697e-05, | |
| "loss": 2.1272, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.01598921869824918, | |
| "grad_norm": 0.9617013931274414, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.0397, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.01621763610822417, | |
| "grad_norm": 0.7471845746040344, | |
| "learning_rate": 3.8709294634702376e-05, | |
| "loss": 2.1752, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.016446053518199156, | |
| "grad_norm": 0.8926049470901489, | |
| "learning_rate": 3.6257601025131026e-05, | |
| "loss": 2.0067, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.016674470928174145, | |
| "grad_norm": 0.885032594203949, | |
| "learning_rate": 3.386881346763483e-05, | |
| "loss": 2.0448, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.016902888338149135, | |
| "grad_norm": 1.1092376708984375, | |
| "learning_rate": 3.154528940713113e-05, | |
| "loss": 2.1073, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.01713130574812412, | |
| "grad_norm": 1.155680537223816, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.978, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.01735972315809911, | |
| "grad_norm": 0.829304575920105, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.9944, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.0175881405680741, | |
| "grad_norm": 0.8414214849472046, | |
| "learning_rate": 2.4988893036954043e-05, | |
| "loss": 2.5413, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.017816557978049086, | |
| "grad_norm": 0.9645959138870239, | |
| "learning_rate": 2.2948675722421086e-05, | |
| "loss": 2.2689, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.018044975388024076, | |
| "grad_norm": 0.8575518727302551, | |
| "learning_rate": 2.098449876243096e-05, | |
| "loss": 2.1654, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.018273392797999062, | |
| "grad_norm": 0.8750948309898376, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.2528, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.01850181020797405, | |
| "grad_norm": 0.7940350770950317, | |
| "learning_rate": 1.7291942572543807e-05, | |
| "loss": 1.9905, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.01873022761794904, | |
| "grad_norm": 0.9825338125228882, | |
| "learning_rate": 1.5567207449798515e-05, | |
| "loss": 2.0347, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.018958645027924027, | |
| "grad_norm": 0.7255304455757141, | |
| "learning_rate": 1.3925797299605647e-05, | |
| "loss": 2.0235, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.019187062437899017, | |
| "grad_norm": 0.9329121708869934, | |
| "learning_rate": 1.2369331995613665e-05, | |
| "loss": 2.0792, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.019415479847874006, | |
| "grad_norm": 0.8776724934577942, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.0174, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.019643897257848993, | |
| "grad_norm": 0.9908276796340942, | |
| "learning_rate": 9.517294753398064e-06, | |
| "loss": 1.9447, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.019872314667823982, | |
| "grad_norm": 0.9467048645019531, | |
| "learning_rate": 8.224537431601886e-06, | |
| "loss": 2.1375, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.02010073207779897, | |
| "grad_norm": 1.004712700843811, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 2.3284, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.020329149487773958, | |
| "grad_norm": 1.0520464181900024, | |
| "learning_rate": 5.911923104577455e-06, | |
| "loss": 2.0863, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.020557566897748947, | |
| "grad_norm": 0.8571903109550476, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 2.0996, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.020785984307723934, | |
| "grad_norm": 0.9216386079788208, | |
| "learning_rate": 3.970631432305694e-06, | |
| "loss": 2.0802, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.021014401717698923, | |
| "grad_norm": 0.9897679686546326, | |
| "learning_rate": 3.1416838871368924e-06, | |
| "loss": 2.2645, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.021242819127673913, | |
| "grad_norm": 0.94163578748703, | |
| "learning_rate": 2.4083238061252567e-06, | |
| "loss": 2.1278, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.0214712365376489, | |
| "grad_norm": 0.8382057547569275, | |
| "learning_rate": 1.771274927131139e-06, | |
| "loss": 2.1074, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.02169965394762389, | |
| "grad_norm": 0.9168360829353333, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 1.993, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.021928071357598874, | |
| "grad_norm": 1.0946999788284302, | |
| "learning_rate": 7.885298685522235e-07, | |
| "loss": 2.1184, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.022156488767573864, | |
| "grad_norm": 0.8011813163757324, | |
| "learning_rate": 4.438035396920004e-07, | |
| "loss": 2.1275, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.022384906177548854, | |
| "grad_norm": 1.2118070125579834, | |
| "learning_rate": 1.973271571728441e-07, | |
| "loss": 2.0635, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.02261332358752384, | |
| "grad_norm": 0.8423234820365906, | |
| "learning_rate": 4.934396342684e-08, | |
| "loss": 2.049, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.02284174099749883, | |
| "grad_norm": 1.2177627086639404, | |
| "learning_rate": 0.0, | |
| "loss": 2.2816, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.681733252309811e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |