| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.89010989010989, | |
| "eval_steps": 500, | |
| "global_step": 1810, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10989010989010989, | |
| "grad_norm": 6.35939884185791, | |
| "learning_rate": 2.1978021978021977e-05, | |
| "loss": 1.3933, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "grad_norm": 3.3019938468933105, | |
| "learning_rate": 4.3956043956043955e-05, | |
| "loss": 0.6013, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.32967032967032966, | |
| "grad_norm": 1.7010605335235596, | |
| "learning_rate": 6.593406593406594e-05, | |
| "loss": 0.3661, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 1.9770668745040894, | |
| "learning_rate": 8.791208791208791e-05, | |
| "loss": 0.2746, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5494505494505495, | |
| "grad_norm": 1.2615512609481812, | |
| "learning_rate": 0.0001098901098901099, | |
| "loss": 0.2108, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 0.9937906265258789, | |
| "learning_rate": 0.00013186813186813188, | |
| "loss": 0.1888, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.7049073576927185, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.166, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.6901200413703918, | |
| "learning_rate": 0.00017582417582417582, | |
| "loss": 0.1526, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.989010989010989, | |
| "grad_norm": 1.3578896522521973, | |
| "learning_rate": 0.0001978021978021978, | |
| "loss": 0.1373, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.098901098901099, | |
| "grad_norm": 0.9918624758720398, | |
| "learning_rate": 0.00019998647325745995, | |
| "loss": 0.1303, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2087912087912087, | |
| "grad_norm": 0.9448220133781433, | |
| "learning_rate": 0.00019993971884561357, | |
| "loss": 0.1236, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.3186813186813187, | |
| "grad_norm": 0.5491310358047485, | |
| "learning_rate": 0.00019985958537951462, | |
| "loss": 0.1164, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.6634742617607117, | |
| "learning_rate": 0.00019974609962308986, | |
| "loss": 0.1024, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.652184784412384, | |
| "learning_rate": 0.00019959929947966, | |
| "loss": 0.108, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.6483516483516483, | |
| "grad_norm": 0.42199188470840454, | |
| "learning_rate": 0.00019941923397928047, | |
| "loss": 0.0963, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7582417582417582, | |
| "grad_norm": 0.7065568566322327, | |
| "learning_rate": 0.0001992059632623657, | |
| "loss": 0.099, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.8681318681318682, | |
| "grad_norm": 0.6244102120399475, | |
| "learning_rate": 0.0001989595585596026, | |
| "loss": 0.0897, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.978021978021978, | |
| "grad_norm": 0.6415707468986511, | |
| "learning_rate": 0.00019868010216816034, | |
| "loss": 0.0781, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.087912087912088, | |
| "grad_norm": 0.3453947603702545, | |
| "learning_rate": 0.00019836768742420352, | |
| "loss": 0.079, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.197802197802198, | |
| "grad_norm": 0.37823784351348877, | |
| "learning_rate": 0.00019802241867171878, | |
| "loss": 0.075, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 0.8650999069213867, | |
| "learning_rate": 0.00019764441122766476, | |
| "loss": 0.0796, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.4175824175824174, | |
| "grad_norm": 0.4968554973602295, | |
| "learning_rate": 0.000197233791343457, | |
| "loss": 0.0754, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.5274725274725274, | |
| "grad_norm": 0.5782051682472229, | |
| "learning_rate": 0.00019679069616280133, | |
| "loss": 0.076, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.6373626373626373, | |
| "grad_norm": 0.4181021749973297, | |
| "learning_rate": 0.00019631527367588864, | |
| "loss": 0.0769, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.7472527472527473, | |
| "grad_norm": 0.41538622975349426, | |
| "learning_rate": 0.00019580768266996756, | |
| "loss": 0.0653, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.3886262774467468, | |
| "learning_rate": 0.00019526809267631073, | |
| "loss": 0.0723, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.967032967032967, | |
| "grad_norm": 0.466183602809906, | |
| "learning_rate": 0.0001946966839135928, | |
| "loss": 0.0702, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.34900644421577454, | |
| "learning_rate": 0.00019409364722769882, | |
| "loss": 0.0638, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.186813186813187, | |
| "grad_norm": 0.5098071694374084, | |
| "learning_rate": 0.00019345918402798314, | |
| "loss": 0.0645, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.2967032967032965, | |
| "grad_norm": 0.45593976974487305, | |
| "learning_rate": 0.00019279350622000054, | |
| "loss": 0.0691, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.4065934065934065, | |
| "grad_norm": 0.3932492733001709, | |
| "learning_rate": 0.0001920968361347314, | |
| "loss": 0.0706, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.5164835164835164, | |
| "grad_norm": 0.3770773708820343, | |
| "learning_rate": 0.00019136940645432494, | |
| "loss": 0.0646, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.6263736263736264, | |
| "grad_norm": 0.432841420173645, | |
| "learning_rate": 0.00019061146013438527, | |
| "loss": 0.0557, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.7362637362637363, | |
| "grad_norm": 0.5559947490692139, | |
| "learning_rate": 0.00018982325032282615, | |
| "loss": 0.0729, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 0.5822933912277222, | |
| "learning_rate": 0.00018900504027532185, | |
| "loss": 0.0632, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.956043956043956, | |
| "grad_norm": 0.5372587442398071, | |
| "learning_rate": 0.0001881571032673816, | |
| "loss": 0.0666, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.065934065934066, | |
| "grad_norm": 0.4164665937423706, | |
| "learning_rate": 0.000187279722503078, | |
| "loss": 0.0566, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.175824175824176, | |
| "grad_norm": 0.570026695728302, | |
| "learning_rate": 0.00018637319102045912, | |
| "loss": 0.0621, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.3998757302761078, | |
| "learning_rate": 0.00018543781159367607, | |
| "loss": 0.0587, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.395604395604396, | |
| "grad_norm": 0.3779265880584717, | |
| "learning_rate": 0.00018447389663185906, | |
| "loss": 0.0568, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.5054945054945055, | |
| "grad_norm": 0.4073057174682617, | |
| "learning_rate": 0.0001834817680747751, | |
| "loss": 0.0615, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 0.3638319969177246, | |
| "learning_rate": 0.00018246175728530296, | |
| "loss": 0.0548, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.725274725274725, | |
| "grad_norm": 0.2937782108783722, | |
| "learning_rate": 0.00018141420493876035, | |
| "loss": 0.0601, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.835164835164835, | |
| "grad_norm": 0.4016660749912262, | |
| "learning_rate": 0.00018033946090912148, | |
| "loss": 0.0563, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.945054945054945, | |
| "grad_norm": 0.39952585101127625, | |
| "learning_rate": 0.00017923788415216175, | |
| "loss": 0.0554, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.054945054945055, | |
| "grad_norm": 0.3408401906490326, | |
| "learning_rate": 0.00017810984258556957, | |
| "loss": 0.0515, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.164835164835165, | |
| "grad_norm": 0.3611335754394531, | |
| "learning_rate": 0.00017695571296606465, | |
| "loss": 0.0511, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.274725274725275, | |
| "grad_norm": 0.24698808789253235, | |
| "learning_rate": 0.00017577588076356465, | |
| "loss": 0.0531, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.384615384615385, | |
| "grad_norm": 0.40450191497802734, | |
| "learning_rate": 0.000174570740032441, | |
| "loss": 0.048, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.4945054945054945, | |
| "grad_norm": 0.44147250056266785, | |
| "learning_rate": 0.00017334069327990816, | |
| "loss": 0.0545, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.604395604395604, | |
| "grad_norm": 0.45513996481895447, | |
| "learning_rate": 0.00017208615133158946, | |
| "loss": 0.0505, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.3807731568813324, | |
| "learning_rate": 0.00017080753319430452, | |
| "loss": 0.0509, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.824175824175824, | |
| "grad_norm": 0.288381427526474, | |
| "learning_rate": 0.00016950526591612462, | |
| "loss": 0.0493, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.934065934065934, | |
| "grad_norm": 0.234198197722435, | |
| "learning_rate": 0.00016817978444374194, | |
| "loss": 0.0552, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.043956043956044, | |
| "grad_norm": 0.33030226826667786, | |
| "learning_rate": 0.00016683153147720097, | |
| "loss": 0.0453, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 0.30306366086006165, | |
| "learning_rate": 0.00016546095732204022, | |
| "loss": 0.0521, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.263736263736264, | |
| "grad_norm": 0.32483500242233276, | |
| "learning_rate": 0.00016406851973889392, | |
| "loss": 0.0473, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.373626373626374, | |
| "grad_norm": 0.3211219310760498, | |
| "learning_rate": 0.00016265468379060365, | |
| "loss": 0.0527, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.483516483516484, | |
| "grad_norm": 0.2360507994890213, | |
| "learning_rate": 0.00016121992168689108, | |
| "loss": 0.0449, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.593406593406593, | |
| "grad_norm": 0.3557351231575012, | |
| "learning_rate": 0.00015976471262664382, | |
| "loss": 0.0471, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.7032967032967035, | |
| "grad_norm": 0.3993636667728424, | |
| "learning_rate": 0.00015828954263786687, | |
| "loss": 0.0461, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.813186813186813, | |
| "grad_norm": 0.4391331076622009, | |
| "learning_rate": 0.00015679490441535324, | |
| "loss": 0.0431, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.923076923076923, | |
| "grad_norm": 0.311146080493927, | |
| "learning_rate": 0.0001552812971561278, | |
| "loss": 0.0497, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.032967032967033, | |
| "grad_norm": 0.29637405276298523, | |
| "learning_rate": 0.00015374922639271963, | |
| "loss": 0.0466, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.142857142857143, | |
| "grad_norm": 0.24265693128108978, | |
| "learning_rate": 0.0001521992038243182, | |
| "loss": 0.048, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.252747252747253, | |
| "grad_norm": 0.3331180214881897, | |
| "learning_rate": 0.0001506317471458701, | |
| "loss": 0.0444, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.362637362637362, | |
| "grad_norm": 0.29099053144454956, | |
| "learning_rate": 0.00014904737987517293, | |
| "loss": 0.0446, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.472527472527473, | |
| "grad_norm": 0.26169735193252563, | |
| "learning_rate": 0.00014744663117802475, | |
| "loss": 0.0442, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.582417582417582, | |
| "grad_norm": 0.27879634499549866, | |
| "learning_rate": 0.00014583003569148712, | |
| "loss": 0.0424, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 0.3208893835544586, | |
| "learning_rate": 0.00014419813334532036, | |
| "loss": 0.0421, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.802197802197802, | |
| "grad_norm": 0.2651744484901428, | |
| "learning_rate": 0.0001425514691816516, | |
| "loss": 0.046, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.912087912087912, | |
| "grad_norm": 0.30851149559020996, | |
| "learning_rate": 0.00014089059317293524, | |
| "loss": 0.046, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.021978021978022, | |
| "grad_norm": 0.32210397720336914, | |
| "learning_rate": 0.00013921606003826627, | |
| "loss": 0.0448, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.131868131868131, | |
| "grad_norm": 0.49959078431129456, | |
| "learning_rate": 0.00013752842905810896, | |
| "loss": 0.0447, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.241758241758241, | |
| "grad_norm": 0.5785067677497864, | |
| "learning_rate": 0.00013582826388750153, | |
| "loss": 0.0397, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.351648351648352, | |
| "grad_norm": 0.28836700320243835, | |
| "learning_rate": 0.00013411613236779995, | |
| "loss": 0.0493, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.461538461538462, | |
| "grad_norm": 0.26861655712127686, | |
| "learning_rate": 0.00013239260633702364, | |
| "loss": 0.0442, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "grad_norm": 0.3270936608314514, | |
| "learning_rate": 0.00013065826143886616, | |
| "loss": 0.0489, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.68131868131868, | |
| "grad_norm": 0.24692483246326447, | |
| "learning_rate": 0.00012891367693043478, | |
| "loss": 0.0441, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.791208791208792, | |
| "grad_norm": 0.32261839509010315, | |
| "learning_rate": 0.00012715943548878355, | |
| "loss": 0.042, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.901098901098901, | |
| "grad_norm": 0.22817495465278625, | |
| "learning_rate": 0.00012539612301630377, | |
| "loss": 0.0415, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.010989010989011, | |
| "grad_norm": 0.16383874416351318, | |
| "learning_rate": 0.00012362432844503725, | |
| "loss": 0.0366, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 9.12087912087912, | |
| "grad_norm": 0.35975322127342224, | |
| "learning_rate": 0.00012184464353997796, | |
| "loss": 0.0424, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 0.22110863029956818, | |
| "learning_rate": 0.00012005766270142724, | |
| "loss": 0.0334, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.340659340659341, | |
| "grad_norm": 0.26277679204940796, | |
| "learning_rate": 0.00011826398276646897, | |
| "loss": 0.041, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.45054945054945, | |
| "grad_norm": 0.29648274183273315, | |
| "learning_rate": 0.00011646420280963081, | |
| "loss": 0.0358, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.56043956043956, | |
| "grad_norm": 0.27250102162361145, | |
| "learning_rate": 0.00011465892394279814, | |
| "loss": 0.0402, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 9.67032967032967, | |
| "grad_norm": 0.24232593178749084, | |
| "learning_rate": 0.00011284874911444763, | |
| "loss": 0.0372, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.780219780219781, | |
| "grad_norm": 0.25964832305908203, | |
| "learning_rate": 0.00011103428290826736, | |
| "loss": 0.0427, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.89010989010989, | |
| "grad_norm": 0.31330835819244385, | |
| "learning_rate": 0.00010921613134123068, | |
| "loss": 0.0397, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.3337639570236206, | |
| "learning_rate": 0.00010739490166119155, | |
| "loss": 0.0363, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 10.10989010989011, | |
| "grad_norm": 0.1793065071105957, | |
| "learning_rate": 0.00010557120214406875, | |
| "loss": 0.0341, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 10.219780219780219, | |
| "grad_norm": 0.32348737120628357, | |
| "learning_rate": 0.00010374564189068641, | |
| "loss": 0.0381, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 10.32967032967033, | |
| "grad_norm": 0.3930850625038147, | |
| "learning_rate": 0.00010191883062333965, | |
| "loss": 0.0398, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.43956043956044, | |
| "grad_norm": 0.2554318308830261, | |
| "learning_rate": 0.00010009137848215195, | |
| "loss": 0.034, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 10.54945054945055, | |
| "grad_norm": 0.2729535698890686, | |
| "learning_rate": 9.826389582129352e-05, | |
| "loss": 0.0408, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 10.659340659340659, | |
| "grad_norm": 0.2841566503047943, | |
| "learning_rate": 9.64369930051278e-05, | |
| "loss": 0.0373, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 10.76923076923077, | |
| "grad_norm": 0.18831486999988556, | |
| "learning_rate": 9.4611280204355e-05, | |
| "loss": 0.0354, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 10.87912087912088, | |
| "grad_norm": 0.25787901878356934, | |
| "learning_rate": 9.278736719221964e-05, | |
| "loss": 0.0357, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 10.989010989010989, | |
| "grad_norm": 0.268319696187973, | |
| "learning_rate": 9.096586314085162e-05, | |
| "loss": 0.0357, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.098901098901099, | |
| "grad_norm": 0.29258257150650024, | |
| "learning_rate": 8.914737641780738e-05, | |
| "loss": 0.0298, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 11.208791208791208, | |
| "grad_norm": 0.26910606026649475, | |
| "learning_rate": 8.733251438288032e-05, | |
| "loss": 0.0385, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 11.31868131868132, | |
| "grad_norm": 0.275666207075119, | |
| "learning_rate": 8.552188318524737e-05, | |
| "loss": 0.0371, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 0.3032730221748352, | |
| "learning_rate": 8.371608756102028e-05, | |
| "loss": 0.0298, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 11.538461538461538, | |
| "grad_norm": 0.19398105144500732, | |
| "learning_rate": 8.191573063126842e-05, | |
| "loss": 0.032, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 11.648351648351648, | |
| "grad_norm": 0.23560473322868347, | |
| "learning_rate": 8.012141370058151e-05, | |
| "loss": 0.0294, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 11.758241758241759, | |
| "grad_norm": 0.24311786890029907, | |
| "learning_rate": 7.833373605623855e-05, | |
| "loss": 0.034, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 11.868131868131869, | |
| "grad_norm": 0.1695002168416977, | |
| "learning_rate": 7.655329476805095e-05, | |
| "loss": 0.0345, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 11.978021978021978, | |
| "grad_norm": 0.1906553953886032, | |
| "learning_rate": 7.478068448894577e-05, | |
| "loss": 0.03, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 12.087912087912088, | |
| "grad_norm": 0.18722419440746307, | |
| "learning_rate": 7.301649725635689e-05, | |
| "loss": 0.0327, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.197802197802197, | |
| "grad_norm": 0.2109653502702713, | |
| "learning_rate": 7.126132229448883e-05, | |
| "loss": 0.03, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 0.3317616879940033, | |
| "learning_rate": 6.95157458175211e-05, | |
| "loss": 0.0289, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 12.417582417582418, | |
| "grad_norm": 0.18462032079696655, | |
| "learning_rate": 6.778035083381708e-05, | |
| "loss": 0.0336, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 12.527472527472527, | |
| "grad_norm": 0.17815662920475006, | |
| "learning_rate": 6.60557169512042e-05, | |
| "loss": 0.0317, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 12.637362637362637, | |
| "grad_norm": 0.19909383356571198, | |
| "learning_rate": 6.434242018338947e-05, | |
| "loss": 0.0317, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 12.747252747252748, | |
| "grad_norm": 0.21948197484016418, | |
| "learning_rate": 6.264103275757578e-05, | |
| "loss": 0.0288, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 12.857142857142858, | |
| "grad_norm": 0.30106085538864136, | |
| "learning_rate": 6.095212292334232e-05, | |
| "loss": 0.0298, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 12.967032967032967, | |
| "grad_norm": 0.3014363944530487, | |
| "learning_rate": 5.927625476285426e-05, | |
| "loss": 0.0318, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 13.076923076923077, | |
| "grad_norm": 0.5095160007476807, | |
| "learning_rate": 5.761398800246354e-05, | |
| "loss": 0.0272, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 13.186813186813186, | |
| "grad_norm": 0.19524632394313812, | |
| "learning_rate": 5.596587782576509e-05, | |
| "loss": 0.0294, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.296703296703297, | |
| "grad_norm": 0.20751602947711945, | |
| "learning_rate": 5.433247468816977e-05, | |
| "loss": 0.0295, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 13.406593406593407, | |
| "grad_norm": 0.12134165316820145, | |
| "learning_rate": 5.271432413305687e-05, | |
| "loss": 0.0258, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 13.516483516483516, | |
| "grad_norm": 0.2958245277404785, | |
| "learning_rate": 5.111196660956703e-05, | |
| "loss": 0.0328, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 13.626373626373626, | |
| "grad_norm": 0.1860036551952362, | |
| "learning_rate": 4.952593729209671e-05, | |
| "loss": 0.028, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 13.736263736263737, | |
| "grad_norm": 0.16853293776512146, | |
| "learning_rate": 4.7956765901554065e-05, | |
| "loss": 0.0259, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 13.846153846153847, | |
| "grad_norm": 0.22942283749580383, | |
| "learning_rate": 4.640497652843672e-05, | |
| "loss": 0.0303, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 13.956043956043956, | |
| "grad_norm": 0.1646496206521988, | |
| "learning_rate": 4.4871087457789584e-05, | |
| "loss": 0.0263, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 14.065934065934066, | |
| "grad_norm": 0.22191093862056732, | |
| "learning_rate": 4.3355610996102e-05, | |
| "loss": 0.033, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 14.175824175824175, | |
| "grad_norm": 0.19444125890731812, | |
| "learning_rate": 4.185905330020143e-05, | |
| "loss": 0.0268, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 14.285714285714286, | |
| "grad_norm": 0.16687805950641632, | |
| "learning_rate": 4.038191420820139e-05, | |
| "loss": 0.0293, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 14.395604395604396, | |
| "grad_norm": 0.21555913984775543, | |
| "learning_rate": 3.892468707255923e-05, | |
| "loss": 0.0269, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 14.505494505494505, | |
| "grad_norm": 0.1728578358888626, | |
| "learning_rate": 3.7487858595300884e-05, | |
| "loss": 0.0222, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 14.615384615384615, | |
| "grad_norm": 0.25217944383621216, | |
| "learning_rate": 3.607190866546578e-05, | |
| "loss": 0.023, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 14.725274725274724, | |
| "grad_norm": 0.45261967182159424, | |
| "learning_rate": 3.467731019882838e-05, | |
| "loss": 0.0366, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 14.835164835164836, | |
| "grad_norm": 0.19587543606758118, | |
| "learning_rate": 3.330452897994773e-05, | |
| "loss": 0.0249, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 14.945054945054945, | |
| "grad_norm": 0.16712340712547302, | |
| "learning_rate": 3.195402350659945e-05, | |
| "loss": 0.0291, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 15.054945054945055, | |
| "grad_norm": 0.3442732095718384, | |
| "learning_rate": 3.0626244836640993e-05, | |
| "loss": 0.0267, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 15.164835164835164, | |
| "grad_norm": 0.20348604023456573, | |
| "learning_rate": 2.9321636437362253e-05, | |
| "loss": 0.0255, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 15.274725274725276, | |
| "grad_norm": 0.18801550567150116, | |
| "learning_rate": 2.8040634037370728e-05, | |
| "loss": 0.0247, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 15.384615384615385, | |
| "grad_norm": 0.2544891834259033, | |
| "learning_rate": 2.6783665481062113e-05, | |
| "loss": 0.0275, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.494505494505495, | |
| "grad_norm": 0.3431093394756317, | |
| "learning_rate": 2.5551150585723415e-05, | |
| "loss": 0.0238, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 15.604395604395604, | |
| "grad_norm": 0.17770768702030182, | |
| "learning_rate": 2.4343501001317605e-05, | |
| "loss": 0.0251, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 15.714285714285714, | |
| "grad_norm": 0.170986145734787, | |
| "learning_rate": 2.3161120072995757e-05, | |
| "loss": 0.0243, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 15.824175824175825, | |
| "grad_norm": 0.19961877167224884, | |
| "learning_rate": 2.2004402706383043e-05, | |
| "loss": 0.0237, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 15.934065934065934, | |
| "grad_norm": 0.38295048475265503, | |
| "learning_rate": 2.0873735235683535e-05, | |
| "loss": 0.0239, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 16.043956043956044, | |
| "grad_norm": 0.15348948538303375, | |
| "learning_rate": 1.976949529464771e-05, | |
| "loss": 0.0282, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 16.153846153846153, | |
| "grad_norm": 0.3392385244369507, | |
| "learning_rate": 1.8692051690445743e-05, | |
| "loss": 0.0283, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 16.263736263736263, | |
| "grad_norm": 0.15572497248649597, | |
| "learning_rate": 1.764176428048908e-05, | |
| "loss": 0.0245, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 16.373626373626372, | |
| "grad_norm": 0.2224312424659729, | |
| "learning_rate": 1.661898385224079e-05, | |
| "loss": 0.0258, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 16.483516483516482, | |
| "grad_norm": 0.17235592007637024, | |
| "learning_rate": 1.5624052006055544e-05, | |
| "loss": 0.0248, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.593406593406595, | |
| "grad_norm": 0.17149613797664642, | |
| "learning_rate": 1.4657301041087812e-05, | |
| "loss": 0.0243, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 16.703296703296704, | |
| "grad_norm": 0.18543320894241333, | |
| "learning_rate": 1.3719053844306706e-05, | |
| "loss": 0.0272, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 16.813186813186814, | |
| "grad_norm": 0.1908874362707138, | |
| "learning_rate": 1.2809623782654223e-05, | |
| "loss": 0.0235, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 16.923076923076923, | |
| "grad_norm": 0.18022581934928894, | |
| "learning_rate": 1.1929314598383423e-05, | |
| "loss": 0.0263, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 17.032967032967033, | |
| "grad_norm": 0.1982187032699585, | |
| "learning_rate": 1.1078420307610783e-05, | |
| "loss": 0.0252, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 0.1451161950826645, | |
| "learning_rate": 1.0257225102117363e-05, | |
| "loss": 0.025, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 17.252747252747252, | |
| "grad_norm": 0.1547311544418335, | |
| "learning_rate": 9.466003254430934e-06, | |
| "loss": 0.024, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 17.36263736263736, | |
| "grad_norm": 0.20238442718982697, | |
| "learning_rate": 8.705019026221317e-06, | |
| "loss": 0.0249, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 17.47252747252747, | |
| "grad_norm": 0.18659718334674835, | |
| "learning_rate": 7.974526580038988e-06, | |
| "loss": 0.0257, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 17.582417582417584, | |
| "grad_norm": 0.2173370122909546, | |
| "learning_rate": 7.2747698944269915e-06, | |
| "loss": 0.0248, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.692307692307693, | |
| "grad_norm": 0.12479448318481445, | |
| "learning_rate": 6.605982682433953e-06, | |
| "loss": 0.0263, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 17.802197802197803, | |
| "grad_norm": 0.17071430385112762, | |
| "learning_rate": 5.968388313555895e-06, | |
| "loss": 0.0225, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 17.912087912087912, | |
| "grad_norm": 0.2871854901313782, | |
| "learning_rate": 5.3621997391326565e-06, | |
| "loss": 0.0191, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 18.021978021978022, | |
| "grad_norm": 0.39435771107673645, | |
| "learning_rate": 4.7876194212238434e-06, | |
| "loss": 0.0291, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 18.13186813186813, | |
| "grad_norm": 0.18047714233398438, | |
| "learning_rate": 4.24483926498812e-06, | |
| "loss": 0.0207, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 18.24175824175824, | |
| "grad_norm": 0.19172823429107666, | |
| "learning_rate": 3.734040554588514e-06, | |
| "loss": 0.0214, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 18.35164835164835, | |
| "grad_norm": 0.2549908757209778, | |
| "learning_rate": 3.255393892644909e-06, | |
| "loss": 0.0205, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 18.46153846153846, | |
| "grad_norm": 0.21838967502117157, | |
| "learning_rate": 2.8090591432542e-06, | |
| "loss": 0.0214, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 18.571428571428573, | |
| "grad_norm": 0.2188936024904251, | |
| "learning_rate": 2.3951853785969537e-06, | |
| "loss": 0.0227, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 18.681318681318682, | |
| "grad_norm": 0.15396256744861603, | |
| "learning_rate": 2.0139108291485574e-06, | |
| "loss": 0.0286, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 18.791208791208792, | |
| "grad_norm": 0.22776196897029877, | |
| "learning_rate": 1.6653628375112972e-06, | |
| "loss": 0.0248, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 18.9010989010989, | |
| "grad_norm": 0.17969872057437897, | |
| "learning_rate": 1.349657815883032e-06, | |
| "loss": 0.0227, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 19.01098901098901, | |
| "grad_norm": 0.22254760563373566, | |
| "learning_rate": 1.0669012071764073e-06, | |
| "loss": 0.0197, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 19.12087912087912, | |
| "grad_norm": 0.1676974892616272, | |
| "learning_rate": 8.171874498018039e-07, | |
| "loss": 0.0264, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 19.23076923076923, | |
| "grad_norm": 0.21863488852977753, | |
| "learning_rate": 6.005999461256684e-07, | |
| "loss": 0.0224, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 19.34065934065934, | |
| "grad_norm": 0.13759975135326385, | |
| "learning_rate": 4.172110346148506e-07, | |
| "loss": 0.0265, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 19.45054945054945, | |
| "grad_norm": 0.16070395708084106, | |
| "learning_rate": 2.670819656760526e-07, | |
| "loss": 0.0233, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 19.560439560439562, | |
| "grad_norm": 0.2525140643119812, | |
| "learning_rate": 1.502628811987483e-07, | |
| "loss": 0.0241, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 19.67032967032967, | |
| "grad_norm": 0.16685707867145538, | |
| "learning_rate": 6.679279780821279e-08, | |
| "loss": 0.0248, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 19.78021978021978, | |
| "grad_norm": 0.17456871271133423, | |
| "learning_rate": 1.6699593834224036e-08, | |
| "loss": 0.0259, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 19.89010989010989, | |
| "grad_norm": 0.18164990842342377, | |
| "learning_rate": 0.0, | |
| "loss": 0.0233, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 19.89010989010989, | |
| "step": 1810, | |
| "total_flos": 2.654273592491328e+17, | |
| "train_loss": 0.05974875727246479, | |
| "train_runtime": 2083.4502, | |
| "train_samples_per_second": 55.6, | |
| "train_steps_per_second": 0.869 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1810, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.654273592491328e+17, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |