| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 14.993576017130621, |
| "eval_steps": 500, |
| "global_step": 1740, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08565310492505353, |
| "grad_norm": 5.411635875701904, |
| "learning_rate": 9.999339889379647e-06, |
| "loss": 1.5609, |
| "num_input_tokens_seen": 255328, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.17130620985010706, |
| "grad_norm": 0.7214002013206482, |
| "learning_rate": 9.997058249278764e-06, |
| "loss": 0.2055, |
| "num_input_tokens_seen": 510640, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2569593147751606, |
| "grad_norm": 0.47501006722450256, |
| "learning_rate": 9.993147673772869e-06, |
| "loss": 0.184, |
| "num_input_tokens_seen": 763808, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3426124197002141, |
| "grad_norm": 0.20641829073429108, |
| "learning_rate": 9.987609437626955e-06, |
| "loss": 0.1767, |
| "num_input_tokens_seen": 1017472, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.4282655246252677, |
| "grad_norm": 0.49966660141944885, |
| "learning_rate": 9.98044534618898e-06, |
| "loss": 0.1821, |
| "num_input_tokens_seen": 1273488, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5139186295503212, |
| "grad_norm": 0.8994255065917969, |
| "learning_rate": 9.971657734801385e-06, |
| "loss": 0.1819, |
| "num_input_tokens_seen": 1527744, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5995717344753747, |
| "grad_norm": 1.7688418626785278, |
| "learning_rate": 9.961249468039806e-06, |
| "loss": 0.1797, |
| "num_input_tokens_seen": 1785520, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6852248394004282, |
| "grad_norm": 0.7211973071098328, |
| "learning_rate": 9.949223938779286e-06, |
| "loss": 0.1765, |
| "num_input_tokens_seen": 2037648, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7708779443254818, |
| "grad_norm": 0.94338458776474, |
| "learning_rate": 9.935585067088276e-06, |
| "loss": 0.1766, |
| "num_input_tokens_seen": 2292464, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.8565310492505354, |
| "grad_norm": 0.6227909326553345, |
| "learning_rate": 9.920337298950767e-06, |
| "loss": 0.1714, |
| "num_input_tokens_seen": 2547872, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9421841541755889, |
| "grad_norm": 0.5941164493560791, |
| "learning_rate": 9.903485604816993e-06, |
| "loss": 0.1728, |
| "num_input_tokens_seen": 2801536, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.0342612419700214, |
| "grad_norm": 0.4057783782482147, |
| "learning_rate": 9.885035477983184e-06, |
| "loss": 0.1868, |
| "num_input_tokens_seen": 3074416, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.119914346895075, |
| "grad_norm": 0.5549430251121521, |
| "learning_rate": 9.864992932800845e-06, |
| "loss": 0.1679, |
| "num_input_tokens_seen": 3327568, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.2055674518201285, |
| "grad_norm": 0.41472136974334717, |
| "learning_rate": 9.843364502716225e-06, |
| "loss": 0.1671, |
| "num_input_tokens_seen": 3582240, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.291220556745182, |
| "grad_norm": 0.5156757235527039, |
| "learning_rate": 9.820157238140535e-06, |
| "loss": 0.1682, |
| "num_input_tokens_seen": 3838160, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.3768736616702355, |
| "grad_norm": 0.5046593546867371, |
| "learning_rate": 9.795378704151675e-06, |
| "loss": 0.1651, |
| "num_input_tokens_seen": 4092304, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.462526766595289, |
| "grad_norm": 0.5588434338569641, |
| "learning_rate": 9.76903697802817e-06, |
| "loss": 0.1649, |
| "num_input_tokens_seen": 4346640, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.5481798715203428, |
| "grad_norm": 0.46262454986572266, |
| "learning_rate": 9.741140646616161e-06, |
| "loss": 0.1669, |
| "num_input_tokens_seen": 4602192, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.633832976445396, |
| "grad_norm": 0.45427972078323364, |
| "learning_rate": 9.711698803530253e-06, |
| "loss": 0.1674, |
| "num_input_tokens_seen": 4858240, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.7194860813704498, |
| "grad_norm": 0.4514879882335663, |
| "learning_rate": 9.68072104618921e-06, |
| "loss": 0.1641, |
| "num_input_tokens_seen": 5113408, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.805139186295503, |
| "grad_norm": 0.7933849692344666, |
| "learning_rate": 9.648217472687385e-06, |
| "loss": 0.1614, |
| "num_input_tokens_seen": 5368352, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.8907922912205568, |
| "grad_norm": 0.6207934021949768, |
| "learning_rate": 9.614198678502965e-06, |
| "loss": 0.163, |
| "num_input_tokens_seen": 5622128, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.9764453961456103, |
| "grad_norm": 0.8193040490150452, |
| "learning_rate": 9.57867575304406e-06, |
| "loss": 0.1589, |
| "num_input_tokens_seen": 5876816, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.068522483940043, |
| "grad_norm": 1.0469202995300293, |
| "learning_rate": 9.541660276033795e-06, |
| "loss": 0.1755, |
| "num_input_tokens_seen": 6145392, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.154175588865096, |
| "grad_norm": 0.9274189472198486, |
| "learning_rate": 9.503164313735566e-06, |
| "loss": 0.1595, |
| "num_input_tokens_seen": 6399504, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.23982869379015, |
| "grad_norm": 0.6875982880592346, |
| "learning_rate": 9.46320041501969e-06, |
| "loss": 0.1563, |
| "num_input_tokens_seen": 6654160, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.325481798715203, |
| "grad_norm": 0.5835751295089722, |
| "learning_rate": 9.421781607272741e-06, |
| "loss": 0.1554, |
| "num_input_tokens_seen": 6910752, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.411134903640257, |
| "grad_norm": 0.6475698351860046, |
| "learning_rate": 9.378921392150893e-06, |
| "loss": 0.1579, |
| "num_input_tokens_seen": 7166960, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.4967880085653107, |
| "grad_norm": 0.6029316782951355, |
| "learning_rate": 9.33463374117867e-06, |
| "loss": 0.1577, |
| "num_input_tokens_seen": 7420288, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.582441113490364, |
| "grad_norm": 0.6444355845451355, |
| "learning_rate": 9.288933091194524e-06, |
| "loss": 0.1564, |
| "num_input_tokens_seen": 7675184, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.6680942184154177, |
| "grad_norm": 0.5541071891784668, |
| "learning_rate": 9.241834339644726e-06, |
| "loss": 0.1528, |
| "num_input_tokens_seen": 7926976, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.753747323340471, |
| "grad_norm": 0.6703725457191467, |
| "learning_rate": 9.193352839727122e-06, |
| "loss": 0.1549, |
| "num_input_tokens_seen": 8184992, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.8394004282655247, |
| "grad_norm": 0.6515584588050842, |
| "learning_rate": 9.143504395386302e-06, |
| "loss": 0.157, |
| "num_input_tokens_seen": 8439712, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.925053533190578, |
| "grad_norm": 0.5527693629264832, |
| "learning_rate": 9.09230525616186e-06, |
| "loss": 0.157, |
| "num_input_tokens_seen": 8694080, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.017130620985011, |
| "grad_norm": 0.6593677401542664, |
| "learning_rate": 9.039772111891383e-06, |
| "loss": 0.1672, |
| "num_input_tokens_seen": 8965488, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.102783725910064, |
| "grad_norm": 0.5042828917503357, |
| "learning_rate": 8.985922087269916e-06, |
| "loss": 0.1483, |
| "num_input_tokens_seen": 9220480, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.188436830835118, |
| "grad_norm": 0.4123888611793518, |
| "learning_rate": 8.930772736267675e-06, |
| "loss": 0.1532, |
| "num_input_tokens_seen": 9477024, |
| "step": 370 |
| }, |
| { |
| "epoch": 3.274089935760171, |
| "grad_norm": 0.7851901054382324, |
| "learning_rate": 8.874342036407815e-06, |
| "loss": 0.1508, |
| "num_input_tokens_seen": 9731840, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.359743040685225, |
| "grad_norm": 0.7545840740203857, |
| "learning_rate": 8.816648382906154e-06, |
| "loss": 0.1516, |
| "num_input_tokens_seen": 9986704, |
| "step": 390 |
| }, |
| { |
| "epoch": 3.445396145610278, |
| "grad_norm": 0.7439327239990234, |
| "learning_rate": 8.757710582674708e-06, |
| "loss": 0.1506, |
| "num_input_tokens_seen": 10238720, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.531049250535332, |
| "grad_norm": 0.8343164920806885, |
| "learning_rate": 8.697547848191037e-06, |
| "loss": 0.1516, |
| "num_input_tokens_seen": 10491856, |
| "step": 410 |
| }, |
| { |
| "epoch": 3.6167023554603857, |
| "grad_norm": 0.817565381526947, |
| "learning_rate": 8.63617979123539e-06, |
| "loss": 0.1542, |
| "num_input_tokens_seen": 10744240, |
| "step": 420 |
| }, |
| { |
| "epoch": 3.702355460385439, |
| "grad_norm": 0.5334470272064209, |
| "learning_rate": 8.573626416497669e-06, |
| "loss": 0.1446, |
| "num_input_tokens_seen": 10996768, |
| "step": 430 |
| }, |
| { |
| "epoch": 3.7880085653104922, |
| "grad_norm": 0.9441611766815186, |
| "learning_rate": 8.509908115056334e-06, |
| "loss": 0.1515, |
| "num_input_tokens_seen": 11254560, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.873661670235546, |
| "grad_norm": 0.6177489757537842, |
| "learning_rate": 8.445045657731329e-06, |
| "loss": 0.1513, |
| "num_input_tokens_seen": 11512992, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.9593147751605997, |
| "grad_norm": 0.5743350982666016, |
| "learning_rate": 8.379060188313244e-06, |
| "loss": 0.1458, |
| "num_input_tokens_seen": 11765808, |
| "step": 460 |
| }, |
| { |
| "epoch": 4.0513918629550325, |
| "grad_norm": 0.8525713086128235, |
| "learning_rate": 8.311973216670888e-06, |
| "loss": 0.1598, |
| "num_input_tokens_seen": 12036784, |
| "step": 470 |
| }, |
| { |
| "epoch": 4.137044967880086, |
| "grad_norm": 0.6399952173233032, |
| "learning_rate": 8.243806611739516e-06, |
| "loss": 0.1448, |
| "num_input_tokens_seen": 12290592, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.222698072805139, |
| "grad_norm": 0.657546877861023, |
| "learning_rate": 8.17458259439202e-06, |
| "loss": 0.144, |
| "num_input_tokens_seen": 12542464, |
| "step": 490 |
| }, |
| { |
| "epoch": 4.308351177730192, |
| "grad_norm": 0.6414650678634644, |
| "learning_rate": 8.104323730195407e-06, |
| "loss": 0.1406, |
| "num_input_tokens_seen": 12796848, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.394004282655247, |
| "grad_norm": 0.7480872869491577, |
| "learning_rate": 8.033052922054882e-06, |
| "loss": 0.1436, |
| "num_input_tokens_seen": 13051760, |
| "step": 510 |
| }, |
| { |
| "epoch": 4.4796573875803, |
| "grad_norm": 0.7025752067565918, |
| "learning_rate": 7.960793402748001e-06, |
| "loss": 0.147, |
| "num_input_tokens_seen": 13305808, |
| "step": 520 |
| }, |
| { |
| "epoch": 4.565310492505353, |
| "grad_norm": 0.5708986520767212, |
| "learning_rate": 7.887568727351262e-06, |
| "loss": 0.1456, |
| "num_input_tokens_seen": 13563056, |
| "step": 530 |
| }, |
| { |
| "epoch": 4.650963597430406, |
| "grad_norm": 0.6903087496757507, |
| "learning_rate": 7.813402765561664e-06, |
| "loss": 0.143, |
| "num_input_tokens_seen": 13816992, |
| "step": 540 |
| }, |
| { |
| "epoch": 4.736616702355461, |
| "grad_norm": 0.6083903908729553, |
| "learning_rate": 7.738319693915673e-06, |
| "loss": 0.1439, |
| "num_input_tokens_seen": 14071936, |
| "step": 550 |
| }, |
| { |
| "epoch": 4.822269807280514, |
| "grad_norm": 0.6583831906318665, |
| "learning_rate": 7.662343987908195e-06, |
| "loss": 0.147, |
| "num_input_tokens_seen": 14327440, |
| "step": 560 |
| }, |
| { |
| "epoch": 4.907922912205567, |
| "grad_norm": 0.8827478885650635, |
| "learning_rate": 7.585500414014077e-06, |
| "loss": 0.1467, |
| "num_input_tokens_seen": 14582832, |
| "step": 570 |
| }, |
| { |
| "epoch": 4.993576017130621, |
| "grad_norm": 0.8274891972541809, |
| "learning_rate": 7.507814021614761e-06, |
| "loss": 0.1478, |
| "num_input_tokens_seen": 14839136, |
| "step": 580 |
| }, |
| { |
| "epoch": 5.085653104925053, |
| "grad_norm": 1.3195112943649292, |
| "learning_rate": 7.429310134832709e-06, |
| "loss": 0.1517, |
| "num_input_tokens_seen": 15109264, |
| "step": 590 |
| }, |
| { |
| "epoch": 5.1713062098501075, |
| "grad_norm": 0.7981224656105042, |
| "learning_rate": 7.35001434427628e-06, |
| "loss": 0.1396, |
| "num_input_tokens_seen": 15363824, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.256959314775161, |
| "grad_norm": 0.6522560715675354, |
| "learning_rate": 7.269952498697734e-06, |
| "loss": 0.142, |
| "num_input_tokens_seen": 15618576, |
| "step": 610 |
| }, |
| { |
| "epoch": 5.342612419700214, |
| "grad_norm": 0.7629905343055725, |
| "learning_rate": 7.189150696567081e-06, |
| "loss": 0.1384, |
| "num_input_tokens_seen": 15871056, |
| "step": 620 |
| }, |
| { |
| "epoch": 5.428265524625267, |
| "grad_norm": 0.9554848670959473, |
| "learning_rate": 7.10763527756453e-06, |
| "loss": 0.1405, |
| "num_input_tokens_seen": 16124976, |
| "step": 630 |
| }, |
| { |
| "epoch": 5.5139186295503215, |
| "grad_norm": 0.8175866603851318, |
| "learning_rate": 7.025432813994315e-06, |
| "loss": 0.1357, |
| "num_input_tokens_seen": 16381680, |
| "step": 640 |
| }, |
| { |
| "epoch": 5.599571734475375, |
| "grad_norm": 0.7990790009498596, |
| "learning_rate": 6.942570102122679e-06, |
| "loss": 0.1387, |
| "num_input_tokens_seen": 16638048, |
| "step": 650 |
| }, |
| { |
| "epoch": 5.685224839400428, |
| "grad_norm": 0.9116854667663574, |
| "learning_rate": 6.859074153442864e-06, |
| "loss": 0.1414, |
| "num_input_tokens_seen": 16894688, |
| "step": 660 |
| }, |
| { |
| "epoch": 5.770877944325482, |
| "grad_norm": 0.7633938789367676, |
| "learning_rate": 6.774972185869928e-06, |
| "loss": 0.1389, |
| "num_input_tokens_seen": 17147808, |
| "step": 670 |
| }, |
| { |
| "epoch": 5.856531049250536, |
| "grad_norm": 0.8924551606178284, |
| "learning_rate": 6.690291614868287e-06, |
| "loss": 0.1361, |
| "num_input_tokens_seen": 17403280, |
| "step": 680 |
| }, |
| { |
| "epoch": 5.942184154175589, |
| "grad_norm": 0.8566009998321533, |
| "learning_rate": 6.60506004451485e-06, |
| "loss": 0.1356, |
| "num_input_tokens_seen": 17657888, |
| "step": 690 |
| }, |
| { |
| "epoch": 6.034261241970022, |
| "grad_norm": 0.9057173132896423, |
| "learning_rate": 6.5193052585006666e-06, |
| "loss": 0.1483, |
| "num_input_tokens_seen": 17927520, |
| "step": 700 |
| }, |
| { |
| "epoch": 6.119914346895075, |
| "grad_norm": 0.9895085692405701, |
| "learning_rate": 6.433055211074042e-06, |
| "loss": 0.1308, |
| "num_input_tokens_seen": 18184352, |
| "step": 710 |
| }, |
| { |
| "epoch": 6.205567451820128, |
| "grad_norm": 1.0845868587493896, |
| "learning_rate": 6.346338017928036e-06, |
| "loss": 0.1269, |
| "num_input_tokens_seen": 18437792, |
| "step": 720 |
| }, |
| { |
| "epoch": 6.291220556745182, |
| "grad_norm": 1.021283745765686, |
| "learning_rate": 6.2591819470353424e-06, |
| "loss": 0.1301, |
| "num_input_tokens_seen": 18690144, |
| "step": 730 |
| }, |
| { |
| "epoch": 6.376873661670236, |
| "grad_norm": 1.1350120306015015, |
| "learning_rate": 6.171615409433525e-06, |
| "loss": 0.1275, |
| "num_input_tokens_seen": 18944688, |
| "step": 740 |
| }, |
| { |
| "epoch": 6.462526766595289, |
| "grad_norm": 1.0572874546051025, |
| "learning_rate": 6.0836669499636255e-06, |
| "loss": 0.1264, |
| "num_input_tokens_seen": 19199984, |
| "step": 750 |
| }, |
| { |
| "epoch": 6.548179871520342, |
| "grad_norm": 1.1884225606918335, |
| "learning_rate": 5.995365237965144e-06, |
| "loss": 0.1294, |
| "num_input_tokens_seen": 19452032, |
| "step": 760 |
| }, |
| { |
| "epoch": 6.6338329764453965, |
| "grad_norm": 0.9745492339134216, |
| "learning_rate": 5.906739057930439e-06, |
| "loss": 0.1262, |
| "num_input_tokens_seen": 19707040, |
| "step": 770 |
| }, |
| { |
| "epoch": 6.71948608137045, |
| "grad_norm": 1.090391755104065, |
| "learning_rate": 5.817817300121592e-06, |
| "loss": 0.1266, |
| "num_input_tokens_seen": 19962960, |
| "step": 780 |
| }, |
| { |
| "epoch": 6.805139186295503, |
| "grad_norm": 1.1640676259994507, |
| "learning_rate": 5.728628951152799e-06, |
| "loss": 0.1324, |
| "num_input_tokens_seen": 20219008, |
| "step": 790 |
| }, |
| { |
| "epoch": 6.890792291220556, |
| "grad_norm": 0.9813507199287415, |
| "learning_rate": 5.639203084541338e-06, |
| "loss": 0.1338, |
| "num_input_tokens_seen": 20473664, |
| "step": 800 |
| }, |
| { |
| "epoch": 6.9764453961456105, |
| "grad_norm": 1.11289644241333, |
| "learning_rate": 5.549568851230219e-06, |
| "loss": 0.1273, |
| "num_input_tokens_seen": 20727296, |
| "step": 810 |
| }, |
| { |
| "epoch": 7.0685224839400425, |
| "grad_norm": 1.5624918937683105, |
| "learning_rate": 5.459755470085595e-06, |
| "loss": 0.1332, |
| "num_input_tokens_seen": 20996432, |
| "step": 820 |
| }, |
| { |
| "epoch": 7.154175588865097, |
| "grad_norm": 1.3339862823486328, |
| "learning_rate": 5.369792218372026e-06, |
| "loss": 0.1104, |
| "num_input_tokens_seen": 21252272, |
| "step": 830 |
| }, |
| { |
| "epoch": 7.23982869379015, |
| "grad_norm": 1.5236716270446777, |
| "learning_rate": 5.2797084222087105e-06, |
| "loss": 0.1114, |
| "num_input_tokens_seen": 21508208, |
| "step": 840 |
| }, |
| { |
| "epoch": 7.325481798715203, |
| "grad_norm": 1.4154669046401978, |
| "learning_rate": 5.189533447009795e-06, |
| "loss": 0.1134, |
| "num_input_tokens_seen": 21765536, |
| "step": 850 |
| }, |
| { |
| "epoch": 7.4111349036402565, |
| "grad_norm": 1.5260732173919678, |
| "learning_rate": 5.099296687911858e-06, |
| "loss": 0.1102, |
| "num_input_tokens_seen": 22020160, |
| "step": 860 |
| }, |
| { |
| "epoch": 7.496788008565311, |
| "grad_norm": 1.2989623546600342, |
| "learning_rate": 5.009027560191732e-06, |
| "loss": 0.1122, |
| "num_input_tokens_seen": 22274400, |
| "step": 870 |
| }, |
| { |
| "epoch": 7.582441113490364, |
| "grad_norm": 1.4925442934036255, |
| "learning_rate": 4.918755489677729e-06, |
| "loss": 0.1094, |
| "num_input_tokens_seen": 22526464, |
| "step": 880 |
| }, |
| { |
| "epoch": 7.668094218415417, |
| "grad_norm": 1.3059921264648438, |
| "learning_rate": 4.828509903157451e-06, |
| "loss": 0.1128, |
| "num_input_tokens_seen": 22779664, |
| "step": 890 |
| }, |
| { |
| "epoch": 7.7537473233404715, |
| "grad_norm": 1.6819276809692383, |
| "learning_rate": 4.738320218785281e-06, |
| "loss": 0.1146, |
| "num_input_tokens_seen": 23036160, |
| "step": 900 |
| }, |
| { |
| "epoch": 7.839400428265525, |
| "grad_norm": 1.3909580707550049, |
| "learning_rate": 4.648215836492682e-06, |
| "loss": 0.1145, |
| "num_input_tokens_seen": 23292016, |
| "step": 910 |
| }, |
| { |
| "epoch": 7.925053533190578, |
| "grad_norm": 1.7210851907730103, |
| "learning_rate": 4.5582261284044385e-06, |
| "loss": 0.1156, |
| "num_input_tokens_seen": 23544800, |
| "step": 920 |
| }, |
| { |
| "epoch": 8.01713062098501, |
| "grad_norm": 1.2723944187164307, |
| "learning_rate": 4.468380429263973e-06, |
| "loss": 0.1197, |
| "num_input_tokens_seen": 23816288, |
| "step": 930 |
| }, |
| { |
| "epoch": 8.102783725910065, |
| "grad_norm": 1.9091925621032715, |
| "learning_rate": 4.378708026870825e-06, |
| "loss": 0.0916, |
| "num_input_tokens_seen": 24071488, |
| "step": 940 |
| }, |
| { |
| "epoch": 8.188436830835117, |
| "grad_norm": 1.7839370965957642, |
| "learning_rate": 4.289238152533465e-06, |
| "loss": 0.0893, |
| "num_input_tokens_seen": 24324720, |
| "step": 950 |
| }, |
| { |
| "epoch": 8.274089935760172, |
| "grad_norm": 2.00311541557312, |
| "learning_rate": 4.199999971540489e-06, |
| "loss": 0.0889, |
| "num_input_tokens_seen": 24579648, |
| "step": 960 |
| }, |
| { |
| "epoch": 8.359743040685224, |
| "grad_norm": 2.047337293624878, |
| "learning_rate": 4.111022573653366e-06, |
| "loss": 0.0873, |
| "num_input_tokens_seen": 24833840, |
| "step": 970 |
| }, |
| { |
| "epoch": 8.445396145610278, |
| "grad_norm": 1.9115785360336304, |
| "learning_rate": 4.0223349636237766e-06, |
| "loss": 0.0904, |
| "num_input_tokens_seen": 25089776, |
| "step": 980 |
| }, |
| { |
| "epoch": 8.531049250535332, |
| "grad_norm": 1.8445810079574585, |
| "learning_rate": 3.933966051738684e-06, |
| "loss": 0.088, |
| "num_input_tokens_seen": 25345264, |
| "step": 990 |
| }, |
| { |
| "epoch": 8.616702355460385, |
| "grad_norm": 1.6529115438461304, |
| "learning_rate": 3.845944644396194e-06, |
| "loss": 0.0919, |
| "num_input_tokens_seen": 25598112, |
| "step": 1000 |
| }, |
| { |
| "epoch": 8.702355460385439, |
| "grad_norm": 2.129995346069336, |
| "learning_rate": 3.758299434715268e-06, |
| "loss": 0.0906, |
| "num_input_tokens_seen": 25851728, |
| "step": 1010 |
| }, |
| { |
| "epoch": 8.788008565310493, |
| "grad_norm": 2.1039373874664307, |
| "learning_rate": 3.6710589931823837e-06, |
| "loss": 0.0895, |
| "num_input_tokens_seen": 26104704, |
| "step": 1020 |
| }, |
| { |
| "epoch": 8.873661670235546, |
| "grad_norm": 2.058598518371582, |
| "learning_rate": 3.584251758338151e-06, |
| "loss": 0.0923, |
| "num_input_tokens_seen": 26361680, |
| "step": 1030 |
| }, |
| { |
| "epoch": 8.9593147751606, |
| "grad_norm": 1.8930065631866455, |
| "learning_rate": 3.4979060275069576e-06, |
| "loss": 0.0908, |
| "num_input_tokens_seen": 26617536, |
| "step": 1040 |
| }, |
| { |
| "epoch": 9.051391862955033, |
| "grad_norm": 1.8233646154403687, |
| "learning_rate": 3.4120499475726266e-06, |
| "loss": 0.0847, |
| "num_input_tokens_seen": 26888160, |
| "step": 1050 |
| }, |
| { |
| "epoch": 9.137044967880085, |
| "grad_norm": 2.1758053302764893, |
| "learning_rate": 3.3267115058031418e-06, |
| "loss": 0.0657, |
| "num_input_tokens_seen": 27142528, |
| "step": 1060 |
| }, |
| { |
| "epoch": 9.222698072805139, |
| "grad_norm": 2.0327367782592773, |
| "learning_rate": 3.2419185207273816e-06, |
| "loss": 0.0662, |
| "num_input_tokens_seen": 27394144, |
| "step": 1070 |
| }, |
| { |
| "epoch": 9.308351177730193, |
| "grad_norm": 2.2035434246063232, |
| "learning_rate": 3.157698633066863e-06, |
| "loss": 0.0665, |
| "num_input_tokens_seen": 27649488, |
| "step": 1080 |
| }, |
| { |
| "epoch": 9.394004282655246, |
| "grad_norm": 1.9066494703292847, |
| "learning_rate": 3.0740792967254606e-06, |
| "loss": 0.0642, |
| "num_input_tokens_seen": 27904992, |
| "step": 1090 |
| }, |
| { |
| "epoch": 9.4796573875803, |
| "grad_norm": 2.2175674438476562, |
| "learning_rate": 2.991087769840001e-06, |
| "loss": 0.0625, |
| "num_input_tokens_seen": 28160336, |
| "step": 1100 |
| }, |
| { |
| "epoch": 9.565310492505354, |
| "grad_norm": 2.435115337371826, |
| "learning_rate": 2.9087511058947014e-06, |
| "loss": 0.0643, |
| "num_input_tokens_seen": 28417360, |
| "step": 1110 |
| }, |
| { |
| "epoch": 9.650963597430406, |
| "grad_norm": 2.237015724182129, |
| "learning_rate": 2.827096144902289e-06, |
| "loss": 0.0645, |
| "num_input_tokens_seen": 28670512, |
| "step": 1120 |
| }, |
| { |
| "epoch": 9.73661670235546, |
| "grad_norm": 2.473604202270508, |
| "learning_rate": 2.7461495046547436e-06, |
| "loss": 0.068, |
| "num_input_tokens_seen": 28927232, |
| "step": 1130 |
| }, |
| { |
| "epoch": 9.822269807280513, |
| "grad_norm": 2.220705270767212, |
| "learning_rate": 2.665937572046432e-06, |
| "loss": 0.0647, |
| "num_input_tokens_seen": 29182768, |
| "step": 1140 |
| }, |
| { |
| "epoch": 9.907922912205567, |
| "grad_norm": 2.652024269104004, |
| "learning_rate": 2.586486494472572e-06, |
| "loss": 0.0644, |
| "num_input_tokens_seen": 29437936, |
| "step": 1150 |
| }, |
| { |
| "epoch": 9.993576017130621, |
| "grad_norm": 2.180983304977417, |
| "learning_rate": 2.5078221713057048e-06, |
| "loss": 0.0658, |
| "num_input_tokens_seen": 29690944, |
| "step": 1160 |
| }, |
| { |
| "epoch": 10.085653104925054, |
| "grad_norm": 1.6538355350494385, |
| "learning_rate": 2.4299702454530605e-06, |
| "loss": 0.053, |
| "num_input_tokens_seen": 29964448, |
| "step": 1170 |
| }, |
| { |
| "epoch": 10.171306209850107, |
| "grad_norm": 2.229673147201538, |
| "learning_rate": 2.3529560949975184e-06, |
| "loss": 0.0446, |
| "num_input_tokens_seen": 30215952, |
| "step": 1180 |
| }, |
| { |
| "epoch": 10.25695931477516, |
| "grad_norm": 1.8106822967529297, |
| "learning_rate": 2.2768048249248648e-06, |
| "loss": 0.0449, |
| "num_input_tokens_seen": 30471952, |
| "step": 1190 |
| }, |
| { |
| "epoch": 10.342612419700215, |
| "grad_norm": 2.150508403778076, |
| "learning_rate": 2.201541258940129e-06, |
| "loss": 0.0422, |
| "num_input_tokens_seen": 30727376, |
| "step": 1200 |
| }, |
| { |
| "epoch": 10.428265524625267, |
| "grad_norm": 2.0471906661987305, |
| "learning_rate": 2.12718993137555e-06, |
| "loss": 0.0461, |
| "num_input_tokens_seen": 30983760, |
| "step": 1210 |
| }, |
| { |
| "epoch": 10.513918629550322, |
| "grad_norm": 2.299278497695923, |
| "learning_rate": 2.0537750791929296e-06, |
| "loss": 0.0458, |
| "num_input_tokens_seen": 31238720, |
| "step": 1220 |
| }, |
| { |
| "epoch": 10.599571734475374, |
| "grad_norm": 2.1924257278442383, |
| "learning_rate": 1.981320634082873e-06, |
| "loss": 0.0434, |
| "num_input_tokens_seen": 31494560, |
| "step": 1230 |
| }, |
| { |
| "epoch": 10.685224839400428, |
| "grad_norm": 2.3524584770202637, |
| "learning_rate": 1.909850214663575e-06, |
| "loss": 0.0452, |
| "num_input_tokens_seen": 31750784, |
| "step": 1240 |
| }, |
| { |
| "epoch": 10.770877944325482, |
| "grad_norm": 2.2468934059143066, |
| "learning_rate": 1.8393871187816526e-06, |
| "loss": 0.0447, |
| "num_input_tokens_seen": 32005120, |
| "step": 1250 |
| }, |
| { |
| "epoch": 10.856531049250535, |
| "grad_norm": 2.448117971420288, |
| "learning_rate": 1.7699543159175215e-06, |
| "loss": 0.0449, |
| "num_input_tokens_seen": 32258480, |
| "step": 1260 |
| }, |
| { |
| "epoch": 10.942184154175589, |
| "grad_norm": 2.0848143100738525, |
| "learning_rate": 1.7015744396978557e-06, |
| "loss": 0.0442, |
| "num_input_tokens_seen": 32510944, |
| "step": 1270 |
| }, |
| { |
| "epoch": 11.034261241970022, |
| "grad_norm": 1.6036432981491089, |
| "learning_rate": 1.634269780517483e-06, |
| "loss": 0.0435, |
| "num_input_tokens_seen": 32780608, |
| "step": 1280 |
| }, |
| { |
| "epoch": 11.119914346895074, |
| "grad_norm": 3.015963315963745, |
| "learning_rate": 1.568062278273197e-06, |
| "loss": 0.0286, |
| "num_input_tokens_seen": 33034112, |
| "step": 1290 |
| }, |
| { |
| "epoch": 11.205567451820128, |
| "grad_norm": 1.6929532289505005, |
| "learning_rate": 1.5029735152118125e-06, |
| "loss": 0.0308, |
| "num_input_tokens_seen": 33290224, |
| "step": 1300 |
| }, |
| { |
| "epoch": 11.291220556745182, |
| "grad_norm": 1.9741885662078857, |
| "learning_rate": 1.4390247088948073e-06, |
| "loss": 0.0309, |
| "num_input_tokens_seen": 33544448, |
| "step": 1310 |
| }, |
| { |
| "epoch": 11.376873661670235, |
| "grad_norm": 1.5955508947372437, |
| "learning_rate": 1.3762367052818527e-06, |
| "loss": 0.0275, |
| "num_input_tokens_seen": 33799536, |
| "step": 1320 |
| }, |
| { |
| "epoch": 11.462526766595289, |
| "grad_norm": 2.293123245239258, |
| "learning_rate": 1.3146299719354544e-06, |
| "loss": 0.0304, |
| "num_input_tokens_seen": 34055952, |
| "step": 1330 |
| }, |
| { |
| "epoch": 11.548179871520343, |
| "grad_norm": 1.8011912107467651, |
| "learning_rate": 1.254224591348983e-06, |
| "loss": 0.0299, |
| "num_input_tokens_seen": 34310000, |
| "step": 1340 |
| }, |
| { |
| "epoch": 11.633832976445396, |
| "grad_norm": 1.8339879512786865, |
| "learning_rate": 1.1950402544001849e-06, |
| "loss": 0.0311, |
| "num_input_tokens_seen": 34565680, |
| "step": 1350 |
| }, |
| { |
| "epoch": 11.71948608137045, |
| "grad_norm": 1.6808807849884033, |
| "learning_rate": 1.1370962539323837e-06, |
| "loss": 0.0314, |
| "num_input_tokens_seen": 34820768, |
| "step": 1360 |
| }, |
| { |
| "epoch": 11.805139186295504, |
| "grad_norm": 1.7647879123687744, |
| "learning_rate": 1.0804114784654158e-06, |
| "loss": 0.0311, |
| "num_input_tokens_seen": 35074016, |
| "step": 1370 |
| }, |
| { |
| "epoch": 11.890792291220556, |
| "grad_norm": 1.753990650177002, |
| "learning_rate": 1.0250044060383734e-06, |
| "loss": 0.0299, |
| "num_input_tokens_seen": 35328272, |
| "step": 1380 |
| }, |
| { |
| "epoch": 11.97644539614561, |
| "grad_norm": 2.10841965675354, |
| "learning_rate": 9.708930981861603e-07, |
| "loss": 0.03, |
| "num_input_tokens_seen": 35582880, |
| "step": 1390 |
| }, |
| { |
| "epoch": 12.068522483940043, |
| "grad_norm": 1.4194451570510864, |
| "learning_rate": 9.180951940518002e-07, |
| "loss": 0.026, |
| "num_input_tokens_seen": 35853280, |
| "step": 1400 |
| }, |
| { |
| "epoch": 12.154175588865096, |
| "grad_norm": 1.612318515777588, |
| "learning_rate": 8.666279046364595e-07, |
| "loss": 0.0208, |
| "num_input_tokens_seen": 36106816, |
| "step": 1410 |
| }, |
| { |
| "epoch": 12.23982869379015, |
| "grad_norm": 1.6022765636444092, |
| "learning_rate": 8.165080071890208e-07, |
| "loss": 0.0205, |
| "num_input_tokens_seen": 36359232, |
| "step": 1420 |
| }, |
| { |
| "epoch": 12.325481798715204, |
| "grad_norm": 1.608430027961731, |
| "learning_rate": 7.677518397370548e-07, |
| "loss": 0.0228, |
| "num_input_tokens_seen": 36614176, |
| "step": 1430 |
| }, |
| { |
| "epoch": 12.411134903640257, |
| "grad_norm": 1.4423803091049194, |
| "learning_rate": 7.203752957609672e-07, |
| "loss": 0.0207, |
| "num_input_tokens_seen": 36868400, |
| "step": 1440 |
| }, |
| { |
| "epoch": 12.49678800856531, |
| "grad_norm": 1.6684809923171997, |
| "learning_rate": 6.743938190130616e-07, |
| "loss": 0.0215, |
| "num_input_tokens_seen": 37121536, |
| "step": 1450 |
| }, |
| { |
| "epoch": 12.582441113490365, |
| "grad_norm": 1.7179003953933716, |
| "learning_rate": 6.298223984832047e-07, |
| "loss": 0.0216, |
| "num_input_tokens_seen": 37377168, |
| "step": 1460 |
| }, |
| { |
| "epoch": 12.668094218415417, |
| "grad_norm": 1.6454778909683228, |
| "learning_rate": 5.866755635127247e-07, |
| "loss": 0.0207, |
| "num_input_tokens_seen": 37632992, |
| "step": 1470 |
| }, |
| { |
| "epoch": 12.753747323340471, |
| "grad_norm": 1.8044767379760742, |
| "learning_rate": 5.449673790581611e-07, |
| "loss": 0.0217, |
| "num_input_tokens_seen": 37888640, |
| "step": 1480 |
| }, |
| { |
| "epoch": 12.839400428265524, |
| "grad_norm": 1.874295711517334, |
| "learning_rate": 5.04711441106382e-07, |
| "loss": 0.0197, |
| "num_input_tokens_seen": 38143760, |
| "step": 1490 |
| }, |
| { |
| "epoch": 12.925053533190578, |
| "grad_norm": 1.3250926733016968, |
| "learning_rate": 4.659208722425806e-07, |
| "loss": 0.0207, |
| "num_input_tokens_seen": 38398560, |
| "step": 1500 |
| }, |
| { |
| "epoch": 13.01713062098501, |
| "grad_norm": 1.2411588430404663, |
| "learning_rate": 4.2860831737258857e-07, |
| "loss": 0.0216, |
| "num_input_tokens_seen": 38670912, |
| "step": 1510 |
| }, |
| { |
| "epoch": 13.102783725910065, |
| "grad_norm": 1.3138427734375, |
| "learning_rate": 3.9278593960090873e-07, |
| "loss": 0.0167, |
| "num_input_tokens_seen": 38925872, |
| "step": 1520 |
| }, |
| { |
| "epoch": 13.188436830835117, |
| "grad_norm": 1.362457036972046, |
| "learning_rate": 3.5846541626579026e-07, |
| "loss": 0.0159, |
| "num_input_tokens_seen": 39183632, |
| "step": 1530 |
| }, |
| { |
| "epoch": 13.274089935760172, |
| "grad_norm": 1.515376091003418, |
| "learning_rate": 3.256579351326744e-07, |
| "loss": 0.0156, |
| "num_input_tokens_seen": 39440864, |
| "step": 1540 |
| }, |
| { |
| "epoch": 13.359743040685224, |
| "grad_norm": 1.4070255756378174, |
| "learning_rate": 2.94374190747212e-07, |
| "loss": 0.0166, |
| "num_input_tokens_seen": 39695712, |
| "step": 1550 |
| }, |
| { |
| "epoch": 13.445396145610278, |
| "grad_norm": 1.4853448867797852, |
| "learning_rate": 2.64624380949069e-07, |
| "loss": 0.0173, |
| "num_input_tokens_seen": 39950304, |
| "step": 1560 |
| }, |
| { |
| "epoch": 13.531049250535332, |
| "grad_norm": 1.542286992073059, |
| "learning_rate": 2.3641820354764755e-07, |
| "loss": 0.0165, |
| "num_input_tokens_seen": 40203616, |
| "step": 1570 |
| }, |
| { |
| "epoch": 13.616702355460385, |
| "grad_norm": 1.565663456916809, |
| "learning_rate": 2.0976485316080375e-07, |
| "loss": 0.0167, |
| "num_input_tokens_seen": 40458464, |
| "step": 1580 |
| }, |
| { |
| "epoch": 13.702355460385439, |
| "grad_norm": 1.3701163530349731, |
| "learning_rate": 1.846730182175993e-07, |
| "loss": 0.017, |
| "num_input_tokens_seen": 40711216, |
| "step": 1590 |
| }, |
| { |
| "epoch": 13.788008565310493, |
| "grad_norm": 1.4886751174926758, |
| "learning_rate": 1.6115087812605123e-07, |
| "loss": 0.015, |
| "num_input_tokens_seen": 40965856, |
| "step": 1600 |
| }, |
| { |
| "epoch": 13.873661670235546, |
| "grad_norm": 1.2140471935272217, |
| "learning_rate": 1.392061006068246e-07, |
| "loss": 0.0169, |
| "num_input_tokens_seen": 41220736, |
| "step": 1610 |
| }, |
| { |
| "epoch": 13.9593147751606, |
| "grad_norm": 1.314063549041748, |
| "learning_rate": 1.1884583919371251e-07, |
| "loss": 0.0164, |
| "num_input_tokens_seen": 41473952, |
| "step": 1620 |
| }, |
| { |
| "epoch": 14.051391862955033, |
| "grad_norm": 1.2103674411773682, |
| "learning_rate": 1.0007673090173808e-07, |
| "loss": 0.0168, |
| "num_input_tokens_seen": 41742832, |
| "step": 1630 |
| }, |
| { |
| "epoch": 14.137044967880085, |
| "grad_norm": 1.250216007232666, |
| "learning_rate": 8.29048940636279e-08, |
| "loss": 0.0153, |
| "num_input_tokens_seen": 41998320, |
| "step": 1640 |
| }, |
| { |
| "epoch": 14.222698072805139, |
| "grad_norm": 1.114964485168457, |
| "learning_rate": 6.733592633536124e-08, |
| "loss": 0.0148, |
| "num_input_tokens_seen": 42253104, |
| "step": 1650 |
| }, |
| { |
| "epoch": 14.308351177730193, |
| "grad_norm": 1.3133609294891357, |
| "learning_rate": 5.3374902871456965e-08, |
| "loss": 0.0151, |
| "num_input_tokens_seen": 42509584, |
| "step": 1660 |
| }, |
| { |
| "epoch": 14.394004282655246, |
| "grad_norm": 1.3046901226043701, |
| "learning_rate": 4.102637467057746e-08, |
| "loss": 0.0144, |
| "num_input_tokens_seen": 42764768, |
| "step": 1670 |
| }, |
| { |
| "epoch": 14.4796573875803, |
| "grad_norm": 1.3270611763000488, |
| "learning_rate": 3.029436709200084e-08, |
| "loss": 0.0142, |
| "num_input_tokens_seen": 43019376, |
| "step": 1680 |
| }, |
| { |
| "epoch": 14.565310492505354, |
| "grad_norm": 1.1487038135528564, |
| "learning_rate": 2.1182378543438408e-08, |
| "loss": 0.0159, |
| "num_input_tokens_seen": 43273248, |
| "step": 1690 |
| }, |
| { |
| "epoch": 14.650963597430406, |
| "grad_norm": 1.1392930746078491, |
| "learning_rate": 1.3693379340626867e-08, |
| "loss": 0.0148, |
| "num_input_tokens_seen": 43529200, |
| "step": 1700 |
| }, |
| { |
| "epoch": 14.73661670235546, |
| "grad_norm": 1.24246084690094, |
| "learning_rate": 7.829810739069521e-09, |
| "loss": 0.0144, |
| "num_input_tokens_seen": 43781760, |
| "step": 1710 |
| }, |
| { |
| "epoch": 14.822269807280513, |
| "grad_norm": 1.2764571905136108, |
| "learning_rate": 3.593584138237294e-09, |
| "loss": 0.0142, |
| "num_input_tokens_seen": 44036144, |
| "step": 1720 |
| }, |
| { |
| "epoch": 14.907922912205567, |
| "grad_norm": 1.4254299402236938, |
| "learning_rate": 9.860804584937988e-10, |
| "loss": 0.0144, |
| "num_input_tokens_seen": 44292256, |
| "step": 1730 |
| }, |
| { |
| "epoch": 14.993576017130621, |
| "grad_norm": 1.1011109352111816, |
| "learning_rate": 8.149690943204391e-12, |
| "loss": 0.014, |
| "num_input_tokens_seen": 44548112, |
| "step": 1740 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1740, |
| "num_input_tokens_seen": 44548112, |
| "num_train_epochs": 15, |
| "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": 1.9454424851110953e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
