| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.27531631009891877, | |
| "eval_steps": 50, | |
| "global_step": 187, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014722797331492984, | |
| "grad_norm": 0.26644960045814514, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 0.296, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014722797331492984, | |
| "eval_loss": 0.4772031009197235, | |
| "eval_runtime": 847.2862, | |
| "eval_samples_per_second": 2.7, | |
| "eval_steps_per_second": 1.35, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029445594662985968, | |
| "grad_norm": 0.4351513385772705, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.408, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004416839199447895, | |
| "grad_norm": 0.3042258024215698, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 0.393, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0058891189325971935, | |
| "grad_norm": 0.3164433538913727, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.409, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007361398665746492, | |
| "grad_norm": 0.37835752964019775, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.2635, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00883367839889579, | |
| "grad_norm": 0.22859500348567963, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 0.2615, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010305958132045089, | |
| "grad_norm": 0.37722575664520264, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 0.296, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011778237865194387, | |
| "grad_norm": 0.8506933450698853, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.2655, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013250517598343685, | |
| "grad_norm": 0.45279720425605774, | |
| "learning_rate": 6.75e-05, | |
| "loss": 0.259, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014722797331492983, | |
| "grad_norm": 0.18526464700698853, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.2053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016195077064642283, | |
| "grad_norm": 0.20497167110443115, | |
| "learning_rate": 8.25e-05, | |
| "loss": 0.1554, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01766735679779158, | |
| "grad_norm": 0.14627239108085632, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.1306, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01913963653094088, | |
| "grad_norm": 0.240932434797287, | |
| "learning_rate": 9.75e-05, | |
| "loss": 0.1564, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.020611916264090178, | |
| "grad_norm": 0.3040555715560913, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 0.1677, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.022084195997239476, | |
| "grad_norm": 0.4959651231765747, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.3867, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023556475730388774, | |
| "grad_norm": 0.20291835069656372, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.2207, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025028755463538072, | |
| "grad_norm": 0.16518566012382507, | |
| "learning_rate": 0.00012749999999999998, | |
| "loss": 0.1309, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02650103519668737, | |
| "grad_norm": 0.18677189946174622, | |
| "learning_rate": 0.000135, | |
| "loss": 0.181, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02797331492983667, | |
| "grad_norm": 0.1576640009880066, | |
| "learning_rate": 0.0001425, | |
| "loss": 0.1562, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.029445594662985967, | |
| "grad_norm": 0.19666102528572083, | |
| "learning_rate": 0.00015, | |
| "loss": 0.2439, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030917874396135265, | |
| "grad_norm": 0.12512515485286713, | |
| "learning_rate": 0.00014998857713672935, | |
| "loss": 0.144, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03239015412928457, | |
| "grad_norm": 0.1219751164317131, | |
| "learning_rate": 0.00014995431202643217, | |
| "loss": 0.1047, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.033862433862433865, | |
| "grad_norm": 0.1390693038702011, | |
| "learning_rate": 0.000149897215106593, | |
| "loss": 0.1022, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03533471359558316, | |
| "grad_norm": 0.19809921085834503, | |
| "learning_rate": 0.0001498173037694868, | |
| "loss": 0.24, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03680699332873246, | |
| "grad_norm": 0.17452572286128998, | |
| "learning_rate": 0.0001497146023568809, | |
| "loss": 0.2497, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03827927306188176, | |
| "grad_norm": 0.10941721498966217, | |
| "learning_rate": 0.00014958914215262048, | |
| "loss": 0.0914, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03975155279503106, | |
| "grad_norm": 0.12793776392936707, | |
| "learning_rate": 0.00014944096137309914, | |
| "loss": 0.114, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.041223832528180356, | |
| "grad_norm": 0.14925755560398102, | |
| "learning_rate": 0.00014927010515561776, | |
| "loss": 0.1931, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.042696112261329654, | |
| "grad_norm": 0.12749770283699036, | |
| "learning_rate": 0.00014907662554463532, | |
| "loss": 0.1342, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04416839199447895, | |
| "grad_norm": 0.12666098773479462, | |
| "learning_rate": 0.0001488605814759156, | |
| "loss": 0.1404, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04564067172762825, | |
| "grad_norm": 0.12451935559511185, | |
| "learning_rate": 0.00014862203875857477, | |
| "loss": 0.1297, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04711295146077755, | |
| "grad_norm": 0.12354013323783875, | |
| "learning_rate": 0.0001483610700550354, | |
| "loss": 0.0667, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.048585231193926846, | |
| "grad_norm": 0.11861127614974976, | |
| "learning_rate": 0.00014807775485889264, | |
| "loss": 0.1057, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.050057510927076145, | |
| "grad_norm": 0.11489235609769821, | |
| "learning_rate": 0.0001477721794706997, | |
| "loss": 0.0717, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05152979066022544, | |
| "grad_norm": 0.15129899978637695, | |
| "learning_rate": 0.0001474444369716801, | |
| "loss": 0.1103, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05300207039337474, | |
| "grad_norm": 0.14446967840194702, | |
| "learning_rate": 0.0001470946271953739, | |
| "loss": 0.1674, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05447435012652404, | |
| "grad_norm": 0.10094312578439713, | |
| "learning_rate": 0.00014672285669722765, | |
| "loss": 0.0696, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05594662985967334, | |
| "grad_norm": 0.17120350897312164, | |
| "learning_rate": 0.00014632923872213652, | |
| "loss": 0.2139, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.057418909592822635, | |
| "grad_norm": 0.14146435260772705, | |
| "learning_rate": 0.00014591389316994876, | |
| "loss": 0.0925, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.058891189325971934, | |
| "grad_norm": 0.14251448214054108, | |
| "learning_rate": 0.0001454769465589431, | |
| "loss": 0.1002, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06036346905912123, | |
| "grad_norm": 0.07004090398550034, | |
| "learning_rate": 0.00014501853198729012, | |
| "loss": 0.0538, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06183574879227053, | |
| "grad_norm": 0.14318852126598358, | |
| "learning_rate": 0.00014453878909250904, | |
| "loss": 0.1316, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06330802852541983, | |
| "grad_norm": 0.10623105615377426, | |
| "learning_rate": 0.00014403786400893302, | |
| "loss": 0.0866, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06478030825856913, | |
| "grad_norm": 0.10893028974533081, | |
| "learning_rate": 0.00014351590932319504, | |
| "loss": 0.0518, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06625258799171843, | |
| "grad_norm": 0.1411529928445816, | |
| "learning_rate": 0.00014297308402774875, | |
| "loss": 0.1357, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06772486772486773, | |
| "grad_norm": 0.10105417668819427, | |
| "learning_rate": 0.0001424095534724375, | |
| "loss": 0.0654, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06919714745801703, | |
| "grad_norm": 0.14420634508132935, | |
| "learning_rate": 0.00014182548931412757, | |
| "loss": 0.0935, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07066942719116633, | |
| "grad_norm": 0.12569449841976166, | |
| "learning_rate": 0.0001412210694644195, | |
| "loss": 0.0848, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07214170692431562, | |
| "grad_norm": 0.09209802001714706, | |
| "learning_rate": 0.00014059647803545467, | |
| "loss": 0.0473, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07361398665746492, | |
| "grad_norm": 0.12560804188251495, | |
| "learning_rate": 0.0001399519052838329, | |
| "loss": 0.0785, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07361398665746492, | |
| "eval_loss": 0.08997488021850586, | |
| "eval_runtime": 784.5444, | |
| "eval_samples_per_second": 2.916, | |
| "eval_steps_per_second": 1.458, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07508626639061422, | |
| "grad_norm": 0.15386323630809784, | |
| "learning_rate": 0.00013928754755265842, | |
| "loss": 0.1427, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.07655854612376352, | |
| "grad_norm": 0.12584620714187622, | |
| "learning_rate": 0.00013860360721173193, | |
| "loss": 0.0863, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.07803082585691282, | |
| "grad_norm": 0.11394777148962021, | |
| "learning_rate": 0.0001379002925959068, | |
| "loss": 0.0691, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.07950310559006211, | |
| "grad_norm": 0.10938312113285065, | |
| "learning_rate": 0.0001371778179416281, | |
| "loss": 0.0826, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.08097538532321141, | |
| "grad_norm": 0.12558647990226746, | |
| "learning_rate": 0.00013643640332167438, | |
| "loss": 0.0766, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08244766505636071, | |
| "grad_norm": 0.10897130519151688, | |
| "learning_rate": 0.00013567627457812106, | |
| "loss": 0.062, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.08391994478951001, | |
| "grad_norm": 0.09030541032552719, | |
| "learning_rate": 0.00013489766325354695, | |
| "loss": 0.0393, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.08539222452265931, | |
| "grad_norm": 0.1143849790096283, | |
| "learning_rate": 0.00013410080652050412, | |
| "loss": 0.1219, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0868645042558086, | |
| "grad_norm": 0.1283547431230545, | |
| "learning_rate": 0.0001332859471092728, | |
| "loss": 0.1195, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0883367839889579, | |
| "grad_norm": 0.11828132718801498, | |
| "learning_rate": 0.00013245333323392333, | |
| "loss": 0.0925, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0898090637221072, | |
| "grad_norm": 0.10878538340330124, | |
| "learning_rate": 0.0001316032185167079, | |
| "loss": 0.0542, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0912813434552565, | |
| "grad_norm": 0.1320784091949463, | |
| "learning_rate": 0.00013073586191080457, | |
| "loss": 0.1005, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0927536231884058, | |
| "grad_norm": 0.10936389863491058, | |
| "learning_rate": 0.00012985152762143778, | |
| "loss": 0.0526, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0942259029215551, | |
| "grad_norm": 0.13538584113121033, | |
| "learning_rate": 0.00012895048502539882, | |
| "loss": 0.0956, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0956981826547044, | |
| "grad_norm": 0.13087764382362366, | |
| "learning_rate": 0.00012803300858899104, | |
| "loss": 0.0795, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.09717046238785369, | |
| "grad_norm": 0.1554757058620453, | |
| "learning_rate": 0.0001270993777844248, | |
| "loss": 0.1455, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.09864274212100299, | |
| "grad_norm": 0.12131679803133011, | |
| "learning_rate": 0.0001261498770046874, | |
| "loss": 0.0625, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.10011502185415229, | |
| "grad_norm": 0.11470583826303482, | |
| "learning_rate": 0.00012518479547691435, | |
| "loss": 0.0903, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.10158730158730159, | |
| "grad_norm": 0.1023801937699318, | |
| "learning_rate": 0.00012420442717428804, | |
| "loss": 0.0845, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.10305958132045089, | |
| "grad_norm": 0.10249310731887817, | |
| "learning_rate": 0.00012320907072649044, | |
| "loss": 0.0539, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10453186105360018, | |
| "grad_norm": 0.10111914575099945, | |
| "learning_rate": 0.0001221990293287378, | |
| "loss": 0.0424, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.10600414078674948, | |
| "grad_norm": 0.16136892139911652, | |
| "learning_rate": 0.00012117461064942435, | |
| "loss": 0.1277, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.10747642051989878, | |
| "grad_norm": 0.13022761046886444, | |
| "learning_rate": 0.00012013612673640363, | |
| "loss": 0.118, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.10894870025304808, | |
| "grad_norm": 0.10115568339824677, | |
| "learning_rate": 0.00011908389392193547, | |
| "loss": 0.0554, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.11042097998619738, | |
| "grad_norm": 0.1352306455373764, | |
| "learning_rate": 0.00011801823272632844, | |
| "loss": 0.0683, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11189325971934667, | |
| "grad_norm": 0.11654029786586761, | |
| "learning_rate": 0.00011693946776030599, | |
| "loss": 0.0656, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.11336553945249597, | |
| "grad_norm": 0.1405310332775116, | |
| "learning_rate": 0.00011584792762612703, | |
| "loss": 0.0681, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.11483781918564527, | |
| "grad_norm": 0.19620081782341003, | |
| "learning_rate": 0.00011474394481749035, | |
| "loss": 0.1183, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.11631009891879457, | |
| "grad_norm": 0.09413562715053558, | |
| "learning_rate": 0.00011362785561825406, | |
| "loss": 0.0377, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.11778237865194387, | |
| "grad_norm": 0.10567747801542282, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.0776, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11925465838509317, | |
| "grad_norm": 0.15690375864505768, | |
| "learning_rate": 0.00011136072151847529, | |
| "loss": 0.0366, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.12072693811824246, | |
| "grad_norm": 0.09006724506616592, | |
| "learning_rate": 0.00011021036720894179, | |
| "loss": 0.0319, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.12219921785139176, | |
| "grad_norm": 0.1135464459657669, | |
| "learning_rate": 0.00010904928748046599, | |
| "loss": 0.0482, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.12367149758454106, | |
| "grad_norm": 0.09596288949251175, | |
| "learning_rate": 0.0001078778360091808, | |
| "loss": 0.0454, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.12514377731769036, | |
| "grad_norm": 0.17637494206428528, | |
| "learning_rate": 0.00010669636963055245, | |
| "loss": 0.1116, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.12661605705083967, | |
| "grad_norm": 0.1744721382856369, | |
| "learning_rate": 0.00010550524823068502, | |
| "loss": 0.0638, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.12808833678398895, | |
| "grad_norm": 0.13608935475349426, | |
| "learning_rate": 0.00010430483463669551, | |
| "loss": 0.0788, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.12956061651713827, | |
| "grad_norm": 0.12516197562217712, | |
| "learning_rate": 0.0001030954945061934, | |
| "loss": 0.0565, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.13103289625028755, | |
| "grad_norm": 0.09498213976621628, | |
| "learning_rate": 0.0001018775962158975, | |
| "loss": 0.0372, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.13250517598343686, | |
| "grad_norm": 0.09999972581863403, | |
| "learning_rate": 0.00010065151074942516, | |
| "loss": 0.0393, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13397745571658615, | |
| "grad_norm": 0.09636418521404266, | |
| "learning_rate": 9.941761158428674e-05, | |
| "loss": 0.0314, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.13544973544973546, | |
| "grad_norm": 0.0872374102473259, | |
| "learning_rate": 9.817627457812105e-05, | |
| "loss": 0.0322, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.13692201518288474, | |
| "grad_norm": 0.11897428333759308, | |
| "learning_rate": 9.692787785420525e-05, | |
| "loss": 0.0726, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.13839429491603406, | |
| "grad_norm": 0.1489570438861847, | |
| "learning_rate": 9.567280168627493e-05, | |
| "loss": 0.0753, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.13986657464918334, | |
| "grad_norm": 0.1237846091389656, | |
| "learning_rate": 9.441142838268905e-05, | |
| "loss": 0.0304, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.14133885438233265, | |
| "grad_norm": 0.11417360603809357, | |
| "learning_rate": 9.314414216997507e-05, | |
| "loss": 0.0466, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.14281113411548194, | |
| "grad_norm": 0.13448922336101532, | |
| "learning_rate": 9.187132907578987e-05, | |
| "loss": 0.0676, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.14428341384863125, | |
| "grad_norm": 0.12376630306243896, | |
| "learning_rate": 9.059337681133192e-05, | |
| "loss": 0.0653, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.14575569358178053, | |
| "grad_norm": 0.13168717920780182, | |
| "learning_rate": 8.931067465324085e-05, | |
| "loss": 0.0414, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.14722797331492984, | |
| "grad_norm": 0.12176292389631271, | |
| "learning_rate": 8.802361332501978e-05, | |
| "loss": 0.0545, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14722797331492984, | |
| "eval_loss": 0.05667497217655182, | |
| "eval_runtime": 573.8343, | |
| "eval_samples_per_second": 3.987, | |
| "eval_steps_per_second": 1.994, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14870025304807913, | |
| "grad_norm": 0.11033546179533005, | |
| "learning_rate": 8.673258487801731e-05, | |
| "loss": 0.0368, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.15017253278122844, | |
| "grad_norm": 0.14303916692733765, | |
| "learning_rate": 8.54379825720049e-05, | |
| "loss": 0.0527, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.15164481251437772, | |
| "grad_norm": 0.10324705392122269, | |
| "learning_rate": 8.414020075538605e-05, | |
| "loss": 0.0217, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.15311709224752704, | |
| "grad_norm": 0.11965189129114151, | |
| "learning_rate": 8.2839634745074e-05, | |
| "loss": 0.0518, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 0.14544668793678284, | |
| "learning_rate": 8.153668070607437e-05, | |
| "loss": 0.0936, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.15606165171382563, | |
| "grad_norm": 0.11407126486301422, | |
| "learning_rate": 8.023173553080938e-05, | |
| "loss": 0.0279, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.15753393144697492, | |
| "grad_norm": 0.11697705090045929, | |
| "learning_rate": 7.89251967182208e-05, | |
| "loss": 0.044, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.15900621118012423, | |
| "grad_norm": 0.18119023740291595, | |
| "learning_rate": 7.761746225268758e-05, | |
| "loss": 0.1192, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.1604784909132735, | |
| "grad_norm": 0.19359427690505981, | |
| "learning_rate": 7.630893048279627e-05, | |
| "loss": 0.1415, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.16195077064642283, | |
| "grad_norm": 0.11051613837480545, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0614, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1634230503795721, | |
| "grad_norm": 0.11084026098251343, | |
| "learning_rate": 7.369106951720373e-05, | |
| "loss": 0.0506, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.16489533011272142, | |
| "grad_norm": 0.08058993518352509, | |
| "learning_rate": 7.238253774731244e-05, | |
| "loss": 0.0232, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.1663676098458707, | |
| "grad_norm": 0.11398748308420181, | |
| "learning_rate": 7.10748032817792e-05, | |
| "loss": 0.077, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.16783988957902002, | |
| "grad_norm": 0.10695286840200424, | |
| "learning_rate": 6.976826446919059e-05, | |
| "loss": 0.0586, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.1693121693121693, | |
| "grad_norm": 0.06323719769716263, | |
| "learning_rate": 6.846331929392562e-05, | |
| "loss": 0.0096, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.17078444904531861, | |
| "grad_norm": 0.09416350722312927, | |
| "learning_rate": 6.7160365254926e-05, | |
| "loss": 0.0552, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.1722567287784679, | |
| "grad_norm": 0.10175611078739166, | |
| "learning_rate": 6.585979924461394e-05, | |
| "loss": 0.0447, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.1737290085116172, | |
| "grad_norm": 0.0726943388581276, | |
| "learning_rate": 6.45620174279951e-05, | |
| "loss": 0.0183, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.1752012882447665, | |
| "grad_norm": 0.12314460426568985, | |
| "learning_rate": 6.326741512198266e-05, | |
| "loss": 0.0912, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.1766735679779158, | |
| "grad_norm": 0.11144654452800751, | |
| "learning_rate": 6.197638667498022e-05, | |
| "loss": 0.0336, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1781458477110651, | |
| "grad_norm": 0.1129511296749115, | |
| "learning_rate": 6.068932534675913e-05, | |
| "loss": 0.0605, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.1796181274442144, | |
| "grad_norm": 0.10868009179830551, | |
| "learning_rate": 5.9406623188668055e-05, | |
| "loss": 0.0592, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.1810904071773637, | |
| "grad_norm": 0.11240071803331375, | |
| "learning_rate": 5.812867092421013e-05, | |
| "loss": 0.0422, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.182562686910513, | |
| "grad_norm": 0.08504848182201385, | |
| "learning_rate": 5.685585783002493e-05, | |
| "loss": 0.0281, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.18403496664366228, | |
| "grad_norm": 0.11616303771734238, | |
| "learning_rate": 5.558857161731093e-05, | |
| "loss": 0.0606, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1855072463768116, | |
| "grad_norm": 0.09546354413032532, | |
| "learning_rate": 5.4327198313725064e-05, | |
| "loss": 0.0295, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.18697952610996088, | |
| "grad_norm": 0.16614162921905518, | |
| "learning_rate": 5.307212214579474e-05, | |
| "loss": 0.0679, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.1884518058431102, | |
| "grad_norm": 0.1870947629213333, | |
| "learning_rate": 5.182372542187895e-05, | |
| "loss": 0.1084, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.18992408557625948, | |
| "grad_norm": 0.12429474294185638, | |
| "learning_rate": 5.058238841571326e-05, | |
| "loss": 0.0768, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.1913963653094088, | |
| "grad_norm": 0.10866294801235199, | |
| "learning_rate": 4.934848925057484e-05, | |
| "loss": 0.0293, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.19286864504255807, | |
| "grad_norm": 0.09623893350362778, | |
| "learning_rate": 4.812240378410248e-05, | |
| "loss": 0.0279, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.19434092477570739, | |
| "grad_norm": 0.12153147906064987, | |
| "learning_rate": 4.690450549380659e-05, | |
| "loss": 0.062, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.19581320450885667, | |
| "grad_norm": 0.14355087280273438, | |
| "learning_rate": 4.569516536330447e-05, | |
| "loss": 0.0639, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.19728548424200598, | |
| "grad_norm": 0.13181179761886597, | |
| "learning_rate": 4.449475176931499e-05, | |
| "loss": 0.0764, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.19875776397515527, | |
| "grad_norm": 0.16418027877807617, | |
| "learning_rate": 4.3303630369447554e-05, | |
| "loss": 0.088, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.20023004370830458, | |
| "grad_norm": 0.10785653442144394, | |
| "learning_rate": 4.212216399081918e-05, | |
| "loss": 0.0341, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.20170232344145386, | |
| "grad_norm": 0.18119709193706512, | |
| "learning_rate": 4.095071251953399e-05, | |
| "loss": 0.0831, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.20317460317460317, | |
| "grad_norm": 0.09372559934854507, | |
| "learning_rate": 3.978963279105821e-05, | |
| "loss": 0.0261, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.2046468829077525, | |
| "grad_norm": 0.08984406292438507, | |
| "learning_rate": 3.863927848152472e-05, | |
| "loss": 0.0399, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.20611916264090177, | |
| "grad_norm": 0.0921633318066597, | |
| "learning_rate": 3.750000000000001e-05, | |
| "loss": 0.0189, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.20759144237405108, | |
| "grad_norm": 0.11086931824684143, | |
| "learning_rate": 3.637214438174593e-05, | |
| "loss": 0.0431, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.20906372210720037, | |
| "grad_norm": 0.1010395959019661, | |
| "learning_rate": 3.525605518250964e-05, | |
| "loss": 0.0696, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.21053600184034968, | |
| "grad_norm": 0.07738685607910156, | |
| "learning_rate": 3.415207237387297e-05, | |
| "loss": 0.0134, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.21200828157349896, | |
| "grad_norm": 0.08697827160358429, | |
| "learning_rate": 3.3060532239693994e-05, | |
| "loss": 0.0294, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.21348056130664828, | |
| "grad_norm": 0.13390277326107025, | |
| "learning_rate": 3.198176727367156e-05, | |
| "loss": 0.064, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.21495284103979756, | |
| "grad_norm": 0.12035319209098816, | |
| "learning_rate": 3.091610607806452e-05, | |
| "loss": 0.0378, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.21642512077294687, | |
| "grad_norm": 0.09978077560663223, | |
| "learning_rate": 2.986387326359637e-05, | |
| "loss": 0.0356, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.21789740050609616, | |
| "grad_norm": 0.09956356137990952, | |
| "learning_rate": 2.8825389350575624e-05, | |
| "loss": 0.0476, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.21936968023924547, | |
| "grad_norm": 0.09759137779474258, | |
| "learning_rate": 2.78009706712622e-05, | |
| "loss": 0.0383, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.22084195997239475, | |
| "grad_norm": 0.06408429890871048, | |
| "learning_rate": 2.6790929273509545e-05, | |
| "loss": 0.0172, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22084195997239475, | |
| "eval_loss": 0.04416579380631447, | |
| "eval_runtime": 1045.846, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 1.094, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22231423970554406, | |
| "grad_norm": 0.07642810791730881, | |
| "learning_rate": 2.579557282571196e-05, | |
| "loss": 0.0281, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.22378651943869335, | |
| "grad_norm": 0.06974484771490097, | |
| "learning_rate": 2.4815204523085654e-05, | |
| "loss": 0.0204, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.22525879917184266, | |
| "grad_norm": 0.0952039286494255, | |
| "learning_rate": 2.385012299531262e-05, | |
| "loss": 0.0515, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.22673107890499195, | |
| "grad_norm": 0.10095140337944031, | |
| "learning_rate": 2.2900622215575197e-05, | |
| "loss": 0.0577, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.22820335863814126, | |
| "grad_norm": 0.09335016459226608, | |
| "learning_rate": 2.1966991411008938e-05, | |
| "loss": 0.0334, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.22967563837129054, | |
| "grad_norm": 0.14227519929409027, | |
| "learning_rate": 2.1049514974601175e-05, | |
| "loss": 0.078, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.23114791810443985, | |
| "grad_norm": 0.09830557554960251, | |
| "learning_rate": 2.0148472378562215e-05, | |
| "loss": 0.0481, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.23262019783758914, | |
| "grad_norm": 0.10622940212488174, | |
| "learning_rate": 1.926413808919542e-05, | |
| "loss": 0.0451, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.23409247757073845, | |
| "grad_norm": 0.12101616710424423, | |
| "learning_rate": 1.8396781483292098e-05, | |
| "loss": 0.0713, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.23556475730388773, | |
| "grad_norm": 0.08884954452514648, | |
| "learning_rate": 1.7546666766076655e-05, | |
| "loss": 0.0447, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.08267998695373535, | |
| "learning_rate": 1.671405289072718e-05, | |
| "loss": 0.0157, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.23850931677018633, | |
| "grad_norm": 0.13504156470298767, | |
| "learning_rate": 1.5899193479495857e-05, | |
| "loss": 0.1002, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.23998159650333564, | |
| "grad_norm": 0.09033524990081787, | |
| "learning_rate": 1.5102336746453053e-05, | |
| "loss": 0.0555, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.24145387623648493, | |
| "grad_norm": 0.11912113428115845, | |
| "learning_rate": 1.4323725421878949e-05, | |
| "loss": 0.0801, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.24292615596963424, | |
| "grad_norm": 0.10221156477928162, | |
| "learning_rate": 1.3563596678325606e-05, | |
| "loss": 0.0453, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.24439843570278352, | |
| "grad_norm": 0.10165137052536011, | |
| "learning_rate": 1.2822182058371878e-05, | |
| "loss": 0.0465, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.24587071543593284, | |
| "grad_norm": 0.07042307406663895, | |
| "learning_rate": 1.2099707404093203e-05, | |
| "loss": 0.0156, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.24734299516908212, | |
| "grad_norm": 0.13063064217567444, | |
| "learning_rate": 1.1396392788268052e-05, | |
| "loss": 0.0635, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.24881527490223143, | |
| "grad_norm": 0.12741073966026306, | |
| "learning_rate": 1.0712452447341582e-05, | |
| "loss": 0.0275, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2502875546353807, | |
| "grad_norm": 0.05055376887321472, | |
| "learning_rate": 1.0048094716167095e-05, | |
| "loss": 0.0101, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.25175983436853, | |
| "grad_norm": 0.11024050414562225, | |
| "learning_rate": 9.40352196454532e-06, | |
| "loss": 0.0496, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.25323211410167934, | |
| "grad_norm": 0.09290501475334167, | |
| "learning_rate": 8.778930535580474e-06, | |
| "loss": 0.042, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.2547043938348286, | |
| "grad_norm": 0.10324755311012268, | |
| "learning_rate": 8.174510685872415e-06, | |
| "loss": 0.0466, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.2561766735679779, | |
| "grad_norm": 0.1255979835987091, | |
| "learning_rate": 7.5904465275624884e-06, | |
| "loss": 0.0731, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.2576489533011272, | |
| "grad_norm": 0.14712050557136536, | |
| "learning_rate": 7.026915972251254e-06, | |
| "loss": 0.0501, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.25912123303427653, | |
| "grad_norm": 0.10622108727693558, | |
| "learning_rate": 6.484090676804926e-06, | |
| "loss": 0.0465, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.2605935127674258, | |
| "grad_norm": 0.08225951343774796, | |
| "learning_rate": 5.962135991066971e-06, | |
| "loss": 0.0322, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.2620657925005751, | |
| "grad_norm": 0.06552782654762268, | |
| "learning_rate": 5.461210907490951e-06, | |
| "loss": 0.0156, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.2635380722337244, | |
| "grad_norm": 0.09848985821008682, | |
| "learning_rate": 4.981468012709877e-06, | |
| "loss": 0.0319, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.2650103519668737, | |
| "grad_norm": 0.11006014794111252, | |
| "learning_rate": 4.523053441056876e-06, | |
| "loss": 0.0384, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.266482631700023, | |
| "grad_norm": 0.07918134331703186, | |
| "learning_rate": 4.086106830051236e-06, | |
| "loss": 0.0424, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.2679549114331723, | |
| "grad_norm": 0.043903008103370667, | |
| "learning_rate": 3.670761277863485e-06, | |
| "loss": 0.0097, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.2694271911663216, | |
| "grad_norm": 0.08103958517313004, | |
| "learning_rate": 3.277143302772342e-06, | |
| "loss": 0.049, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.2708994708994709, | |
| "grad_norm": 0.12223482131958008, | |
| "learning_rate": 2.9053728046260825e-06, | |
| "loss": 0.0317, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.2723717506326202, | |
| "grad_norm": 0.04852719232439995, | |
| "learning_rate": 2.555563028319885e-06, | |
| "loss": 0.0094, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.2738440303657695, | |
| "grad_norm": 0.0753386989235878, | |
| "learning_rate": 2.227820529300264e-06, | |
| "loss": 0.0332, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.27531631009891877, | |
| "grad_norm": 0.11057372391223907, | |
| "learning_rate": 1.9222451411073645e-06, | |
| "loss": 0.0736, | |
| "step": 187 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9745031642666762e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |