| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 12.121212121212121, |
| "eval_steps": 500, |
| "global_step": 1750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.03181853145360947, |
| "learning_rate": 0.0002, |
| "loss": 0.0117, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.03301709145307541, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.12774519622325897, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.189144566655159, |
| "learning_rate": 0.0002, |
| "loss": 0.0167, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.15458767116069794, |
| "learning_rate": 0.0002, |
| "loss": 0.0116, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.23779332637786865, |
| "learning_rate": 0.0002, |
| "loss": 0.0124, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.17651872336864471, |
| "learning_rate": 0.0002, |
| "loss": 0.0081, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.2730236053466797, |
| "learning_rate": 0.0002, |
| "loss": 0.0196, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.17761944234371185, |
| "learning_rate": 0.0002, |
| "loss": 0.0123, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.02090522274374962, |
| "learning_rate": 0.0002, |
| "loss": 0.008, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.19568940997123718, |
| "learning_rate": 0.0002, |
| "loss": 0.0137, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.09299980849027634, |
| "learning_rate": 0.0002, |
| "loss": 0.0179, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.039965927600860596, |
| "learning_rate": 0.0002, |
| "loss": 0.0094, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.05453222617506981, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.04, |
| "grad_norm": 0.08042442053556442, |
| "learning_rate": 0.0002, |
| "loss": 0.0144, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.11, |
| "grad_norm": 0.066365547478199, |
| "learning_rate": 0.0002, |
| "loss": 0.0106, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.18, |
| "grad_norm": 0.06514760106801987, |
| "learning_rate": 0.0002, |
| "loss": 0.0104, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 0.019024183973670006, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.32, |
| "grad_norm": 0.1361686736345291, |
| "learning_rate": 0.0002, |
| "loss": 0.013, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.39, |
| "grad_norm": 0.07207699865102768, |
| "learning_rate": 0.0002, |
| "loss": 0.0093, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.45, |
| "grad_norm": 0.03459335118532181, |
| "learning_rate": 0.0002, |
| "loss": 0.0106, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.52, |
| "grad_norm": 0.03898346796631813, |
| "learning_rate": 0.0002, |
| "loss": 0.0103, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.59, |
| "grad_norm": 0.17066022753715515, |
| "learning_rate": 0.0002, |
| "loss": 0.0154, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.66, |
| "grad_norm": 0.11916259676218033, |
| "learning_rate": 0.0002, |
| "loss": 0.0054, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.73, |
| "grad_norm": 0.1582280397415161, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.11945289373397827, |
| "learning_rate": 0.0002, |
| "loss": 0.0168, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.87, |
| "grad_norm": 0.11030268669128418, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.94, |
| "grad_norm": 0.19329409301280975, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.01, |
| "grad_norm": 0.19244401156902313, |
| "learning_rate": 0.0002, |
| "loss": 0.0079, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.08, |
| "grad_norm": 0.17133064568042755, |
| "learning_rate": 0.0002, |
| "loss": 0.0121, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.15, |
| "grad_norm": 0.2458006590604782, |
| "learning_rate": 0.0002, |
| "loss": 0.0099, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.22, |
| "grad_norm": 0.04351121559739113, |
| "learning_rate": 0.0002, |
| "loss": 0.0151, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.29, |
| "grad_norm": 0.11653552204370499, |
| "learning_rate": 0.0002, |
| "loss": 0.0215, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.35, |
| "grad_norm": 0.17622575163841248, |
| "learning_rate": 0.0002, |
| "loss": 0.0113, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.42, |
| "grad_norm": 0.06326813995838165, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.49, |
| "grad_norm": 0.05258811265230179, |
| "learning_rate": 0.0002, |
| "loss": 0.0209, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.56, |
| "grad_norm": 0.14271198213100433, |
| "learning_rate": 0.0002, |
| "loss": 0.0165, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.63, |
| "grad_norm": 0.2666095495223999, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 380 |
| }, |
| { |
| "epoch": 2.7, |
| "grad_norm": 0.33327990770339966, |
| "learning_rate": 0.0002, |
| "loss": 0.0119, |
| "step": 390 |
| }, |
| { |
| "epoch": 2.77, |
| "grad_norm": 0.16939572989940643, |
| "learning_rate": 0.0002, |
| "loss": 0.0198, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.84, |
| "grad_norm": 0.15744081139564514, |
| "learning_rate": 0.0002, |
| "loss": 0.0128, |
| "step": 410 |
| }, |
| { |
| "epoch": 2.91, |
| "grad_norm": 0.08405949920415878, |
| "learning_rate": 0.0002, |
| "loss": 0.0097, |
| "step": 420 |
| }, |
| { |
| "epoch": 2.98, |
| "grad_norm": 0.19052201509475708, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 430 |
| }, |
| { |
| "epoch": 3.05, |
| "grad_norm": 0.07543158531188965, |
| "learning_rate": 0.0002, |
| "loss": 0.013, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.12, |
| "grad_norm": 0.13838960230350494, |
| "learning_rate": 0.0002, |
| "loss": 0.0128, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.19, |
| "grad_norm": 0.1489538550376892, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 460 |
| }, |
| { |
| "epoch": 3.26, |
| "grad_norm": 0.14335639774799347, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 470 |
| }, |
| { |
| "epoch": 3.32, |
| "grad_norm": 0.07466119527816772, |
| "learning_rate": 0.0002, |
| "loss": 0.0124, |
| "step": 480 |
| }, |
| { |
| "epoch": 3.39, |
| "grad_norm": 0.175484761595726, |
| "learning_rate": 0.0002, |
| "loss": 0.012, |
| "step": 490 |
| }, |
| { |
| "epoch": 3.46, |
| "grad_norm": 0.15107689797878265, |
| "learning_rate": 0.0002, |
| "loss": 0.0091, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.53, |
| "grad_norm": 0.18606631457805634, |
| "learning_rate": 0.0002, |
| "loss": 0.0141, |
| "step": 510 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 0.12696044147014618, |
| "learning_rate": 0.0002, |
| "loss": 0.0125, |
| "step": 520 |
| }, |
| { |
| "epoch": 3.67, |
| "grad_norm": 0.11616098135709763, |
| "learning_rate": 0.0002, |
| "loss": 0.0129, |
| "step": 530 |
| }, |
| { |
| "epoch": 3.74, |
| "grad_norm": 0.3160938620567322, |
| "learning_rate": 0.0002, |
| "loss": 0.0085, |
| "step": 540 |
| }, |
| { |
| "epoch": 3.81, |
| "grad_norm": 0.08054643124341965, |
| "learning_rate": 0.0002, |
| "loss": 0.0163, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.88, |
| "grad_norm": 0.06550751626491547, |
| "learning_rate": 0.0002, |
| "loss": 0.0133, |
| "step": 560 |
| }, |
| { |
| "epoch": 3.95, |
| "grad_norm": 0.04109380394220352, |
| "learning_rate": 0.0002, |
| "loss": 0.0085, |
| "step": 570 |
| }, |
| { |
| "epoch": 4.02, |
| "grad_norm": 0.09408660233020782, |
| "learning_rate": 0.0002, |
| "loss": 0.0127, |
| "step": 580 |
| }, |
| { |
| "epoch": 4.09, |
| "grad_norm": 0.2768724858760834, |
| "learning_rate": 0.0002, |
| "loss": 0.0114, |
| "step": 590 |
| }, |
| { |
| "epoch": 4.16, |
| "grad_norm": 0.02514655888080597, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 600 |
| }, |
| { |
| "epoch": 4.23, |
| "grad_norm": 0.26696744561195374, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 610 |
| }, |
| { |
| "epoch": 4.29, |
| "grad_norm": 0.19320635497570038, |
| "learning_rate": 0.0002, |
| "loss": 0.0135, |
| "step": 620 |
| }, |
| { |
| "epoch": 4.36, |
| "grad_norm": 0.08179598301649094, |
| "learning_rate": 0.0002, |
| "loss": 0.0067, |
| "step": 630 |
| }, |
| { |
| "epoch": 4.43, |
| "grad_norm": 0.30935776233673096, |
| "learning_rate": 0.0002, |
| "loss": 0.0083, |
| "step": 640 |
| }, |
| { |
| "epoch": 4.5, |
| "grad_norm": 0.21668316423892975, |
| "learning_rate": 0.0002, |
| "loss": 0.0144, |
| "step": 650 |
| }, |
| { |
| "epoch": 4.57, |
| "grad_norm": 0.18344347178936005, |
| "learning_rate": 0.0002, |
| "loss": 0.0131, |
| "step": 660 |
| }, |
| { |
| "epoch": 4.64, |
| "grad_norm": 0.31796884536743164, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 670 |
| }, |
| { |
| "epoch": 4.71, |
| "grad_norm": 0.04909071326255798, |
| "learning_rate": 0.0002, |
| "loss": 0.0108, |
| "step": 680 |
| }, |
| { |
| "epoch": 4.78, |
| "grad_norm": 0.08679769188165665, |
| "learning_rate": 0.0002, |
| "loss": 0.0197, |
| "step": 690 |
| }, |
| { |
| "epoch": 4.85, |
| "grad_norm": 0.05100365728139877, |
| "learning_rate": 0.0002, |
| "loss": 0.013, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.92, |
| "grad_norm": 0.08279485255479813, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 710 |
| }, |
| { |
| "epoch": 4.99, |
| "grad_norm": 0.05374281853437424, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 720 |
| }, |
| { |
| "epoch": 5.06, |
| "grad_norm": 0.10421579331159592, |
| "learning_rate": 0.0002, |
| "loss": 0.0115, |
| "step": 730 |
| }, |
| { |
| "epoch": 5.13, |
| "grad_norm": 0.022278541699051857, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 740 |
| }, |
| { |
| "epoch": 5.19, |
| "grad_norm": 0.014159414917230606, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 750 |
| }, |
| { |
| "epoch": 5.26, |
| "grad_norm": 0.15521597862243652, |
| "learning_rate": 0.0002, |
| "loss": 0.0122, |
| "step": 760 |
| }, |
| { |
| "epoch": 5.33, |
| "grad_norm": 0.0737166702747345, |
| "learning_rate": 0.0002, |
| "loss": 0.0077, |
| "step": 770 |
| }, |
| { |
| "epoch": 5.4, |
| "grad_norm": 0.03631032258272171, |
| "learning_rate": 0.0002, |
| "loss": 0.0051, |
| "step": 780 |
| }, |
| { |
| "epoch": 5.47, |
| "grad_norm": 0.11575569957494736, |
| "learning_rate": 0.0002, |
| "loss": 0.0057, |
| "step": 790 |
| }, |
| { |
| "epoch": 5.54, |
| "grad_norm": 0.13107435405254364, |
| "learning_rate": 0.0002, |
| "loss": 0.0104, |
| "step": 800 |
| }, |
| { |
| "epoch": 5.61, |
| "grad_norm": 0.11719845235347748, |
| "learning_rate": 0.0002, |
| "loss": 0.004, |
| "step": 810 |
| }, |
| { |
| "epoch": 5.68, |
| "grad_norm": 0.024636002257466316, |
| "learning_rate": 0.0002, |
| "loss": 0.0048, |
| "step": 820 |
| }, |
| { |
| "epoch": 5.75, |
| "grad_norm": 0.05650615319609642, |
| "learning_rate": 0.0002, |
| "loss": 0.009, |
| "step": 830 |
| }, |
| { |
| "epoch": 5.82, |
| "grad_norm": 0.11958178132772446, |
| "learning_rate": 0.0002, |
| "loss": 0.0096, |
| "step": 840 |
| }, |
| { |
| "epoch": 5.89, |
| "grad_norm": 0.3462698757648468, |
| "learning_rate": 0.0002, |
| "loss": 0.0079, |
| "step": 850 |
| }, |
| { |
| "epoch": 5.96, |
| "grad_norm": 0.07302005589008331, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 860 |
| }, |
| { |
| "epoch": 6.03, |
| "grad_norm": 0.24322502315044403, |
| "learning_rate": 0.0002, |
| "loss": 0.0118, |
| "step": 870 |
| }, |
| { |
| "epoch": 6.1, |
| "grad_norm": 0.024749072268605232, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 880 |
| }, |
| { |
| "epoch": 6.16, |
| "grad_norm": 0.03444315120577812, |
| "learning_rate": 0.0002, |
| "loss": 0.0056, |
| "step": 890 |
| }, |
| { |
| "epoch": 6.23, |
| "grad_norm": 0.36686971783638, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 900 |
| }, |
| { |
| "epoch": 6.3, |
| "grad_norm": 0.25445130467414856, |
| "learning_rate": 0.0002, |
| "loss": 0.0114, |
| "step": 910 |
| }, |
| { |
| "epoch": 6.37, |
| "grad_norm": 0.09220030158758163, |
| "learning_rate": 0.0002, |
| "loss": 0.0076, |
| "step": 920 |
| }, |
| { |
| "epoch": 6.44, |
| "grad_norm": 0.2540806531906128, |
| "learning_rate": 0.0002, |
| "loss": 0.0102, |
| "step": 930 |
| }, |
| { |
| "epoch": 6.51, |
| "grad_norm": 0.1557808369398117, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 940 |
| }, |
| { |
| "epoch": 6.58, |
| "grad_norm": 0.05450637638568878, |
| "learning_rate": 0.0002, |
| "loss": 0.0086, |
| "step": 950 |
| }, |
| { |
| "epoch": 6.65, |
| "grad_norm": 0.04527583718299866, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 960 |
| }, |
| { |
| "epoch": 6.72, |
| "grad_norm": 0.11897213757038116, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 970 |
| }, |
| { |
| "epoch": 6.79, |
| "grad_norm": 0.10568214952945709, |
| "learning_rate": 0.0002, |
| "loss": 0.0158, |
| "step": 980 |
| }, |
| { |
| "epoch": 6.86, |
| "grad_norm": 0.07142580300569534, |
| "learning_rate": 0.0002, |
| "loss": 0.0077, |
| "step": 990 |
| }, |
| { |
| "epoch": 6.93, |
| "grad_norm": 0.04490859434008598, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 1000 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.030944261699914932, |
| "learning_rate": 0.0002, |
| "loss": 0.0049, |
| "step": 1010 |
| }, |
| { |
| "epoch": 7.06, |
| "grad_norm": 0.23092027008533478, |
| "learning_rate": 0.0002, |
| "loss": 0.012, |
| "step": 1020 |
| }, |
| { |
| "epoch": 7.13, |
| "grad_norm": 0.07528150826692581, |
| "learning_rate": 0.0002, |
| "loss": 0.005, |
| "step": 1030 |
| }, |
| { |
| "epoch": 7.2, |
| "grad_norm": 0.011815500445663929, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 1040 |
| }, |
| { |
| "epoch": 7.27, |
| "grad_norm": 0.08818691223859787, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 1050 |
| }, |
| { |
| "epoch": 7.34, |
| "grad_norm": 0.013633369468152523, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 1060 |
| }, |
| { |
| "epoch": 7.41, |
| "grad_norm": 0.014418787322938442, |
| "learning_rate": 0.0002, |
| "loss": 0.0071, |
| "step": 1070 |
| }, |
| { |
| "epoch": 7.48, |
| "grad_norm": 0.12523452937602997, |
| "learning_rate": 0.0002, |
| "loss": 0.0072, |
| "step": 1080 |
| }, |
| { |
| "epoch": 7.55, |
| "grad_norm": 0.13877837359905243, |
| "learning_rate": 0.0002, |
| "loss": 0.0097, |
| "step": 1090 |
| }, |
| { |
| "epoch": 7.62, |
| "grad_norm": 0.24948883056640625, |
| "learning_rate": 0.0002, |
| "loss": 0.006, |
| "step": 1100 |
| }, |
| { |
| "epoch": 7.69, |
| "grad_norm": 0.021404897794127464, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 1110 |
| }, |
| { |
| "epoch": 7.76, |
| "grad_norm": 0.1368672251701355, |
| "learning_rate": 0.0002, |
| "loss": 0.0059, |
| "step": 1120 |
| }, |
| { |
| "epoch": 7.83, |
| "grad_norm": 0.03312192112207413, |
| "learning_rate": 0.0002, |
| "loss": 0.007, |
| "step": 1130 |
| }, |
| { |
| "epoch": 7.9, |
| "grad_norm": 0.032206010073423386, |
| "learning_rate": 0.0002, |
| "loss": 0.0021, |
| "step": 1140 |
| }, |
| { |
| "epoch": 7.97, |
| "grad_norm": 0.03399817645549774, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 1150 |
| }, |
| { |
| "epoch": 8.03, |
| "grad_norm": 0.18925493955612183, |
| "learning_rate": 0.0002, |
| "loss": 0.0093, |
| "step": 1160 |
| }, |
| { |
| "epoch": 8.1, |
| "grad_norm": 0.1772252917289734, |
| "learning_rate": 0.0002, |
| "loss": 0.003, |
| "step": 1170 |
| }, |
| { |
| "epoch": 8.17, |
| "grad_norm": 0.007787138223648071, |
| "learning_rate": 0.0002, |
| "loss": 0.0034, |
| "step": 1180 |
| }, |
| { |
| "epoch": 8.24, |
| "grad_norm": 0.01511111855506897, |
| "learning_rate": 0.0002, |
| "loss": 0.002, |
| "step": 1190 |
| }, |
| { |
| "epoch": 8.31, |
| "grad_norm": 0.03841459006071091, |
| "learning_rate": 0.0002, |
| "loss": 0.0072, |
| "step": 1200 |
| }, |
| { |
| "epoch": 8.38, |
| "grad_norm": 0.0446455255150795, |
| "learning_rate": 0.0002, |
| "loss": 0.0066, |
| "step": 1210 |
| }, |
| { |
| "epoch": 8.45, |
| "grad_norm": 0.050412483513355255, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 1220 |
| }, |
| { |
| "epoch": 8.52, |
| "grad_norm": 0.05555203557014465, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 1230 |
| }, |
| { |
| "epoch": 8.59, |
| "grad_norm": 0.07313160598278046, |
| "learning_rate": 0.0002, |
| "loss": 0.0096, |
| "step": 1240 |
| }, |
| { |
| "epoch": 8.66, |
| "grad_norm": 0.06051426753401756, |
| "learning_rate": 0.0002, |
| "loss": 0.0176, |
| "step": 1250 |
| }, |
| { |
| "epoch": 8.73, |
| "grad_norm": 0.052646949887275696, |
| "learning_rate": 0.0002, |
| "loss": 0.0038, |
| "step": 1260 |
| }, |
| { |
| "epoch": 8.8, |
| "grad_norm": 0.05086590349674225, |
| "learning_rate": 0.0002, |
| "loss": 0.0099, |
| "step": 1270 |
| }, |
| { |
| "epoch": 8.87, |
| "grad_norm": 0.07178761065006256, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 1280 |
| }, |
| { |
| "epoch": 8.94, |
| "grad_norm": 0.009413959458470345, |
| "learning_rate": 0.0002, |
| "loss": 0.0064, |
| "step": 1290 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.10240955650806427, |
| "learning_rate": 0.0002, |
| "loss": 0.0143, |
| "step": 1300 |
| }, |
| { |
| "epoch": 9.07, |
| "grad_norm": 0.01897740177810192, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 1310 |
| }, |
| { |
| "epoch": 9.14, |
| "grad_norm": 0.022444820031523705, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 1320 |
| }, |
| { |
| "epoch": 9.21, |
| "grad_norm": 0.0814051404595375, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 1330 |
| }, |
| { |
| "epoch": 9.28, |
| "grad_norm": 0.18547141551971436, |
| "learning_rate": 0.0002, |
| "loss": 0.0112, |
| "step": 1340 |
| }, |
| { |
| "epoch": 9.35, |
| "grad_norm": 0.022853808477520943, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 1350 |
| }, |
| { |
| "epoch": 9.42, |
| "grad_norm": 0.14588187634944916, |
| "learning_rate": 0.0002, |
| "loss": 0.0068, |
| "step": 1360 |
| }, |
| { |
| "epoch": 9.49, |
| "grad_norm": 0.10406211018562317, |
| "learning_rate": 0.0002, |
| "loss": 0.0045, |
| "step": 1370 |
| }, |
| { |
| "epoch": 9.56, |
| "grad_norm": 0.02087993547320366, |
| "learning_rate": 0.0002, |
| "loss": 0.0144, |
| "step": 1380 |
| }, |
| { |
| "epoch": 9.63, |
| "grad_norm": 0.015244157053530216, |
| "learning_rate": 0.0002, |
| "loss": 0.0044, |
| "step": 1390 |
| }, |
| { |
| "epoch": 9.7, |
| "grad_norm": 0.030207380652427673, |
| "learning_rate": 0.0002, |
| "loss": 0.0062, |
| "step": 1400 |
| }, |
| { |
| "epoch": 9.77, |
| "grad_norm": 0.17009080946445465, |
| "learning_rate": 0.0002, |
| "loss": 0.0113, |
| "step": 1410 |
| }, |
| { |
| "epoch": 9.84, |
| "grad_norm": 0.11179855465888977, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 1420 |
| }, |
| { |
| "epoch": 9.9, |
| "grad_norm": 0.07035847008228302, |
| "learning_rate": 0.0002, |
| "loss": 0.0051, |
| "step": 1430 |
| }, |
| { |
| "epoch": 9.97, |
| "grad_norm": 0.2190101593732834, |
| "learning_rate": 0.0002, |
| "loss": 0.0058, |
| "step": 1440 |
| }, |
| { |
| "epoch": 10.04, |
| "grad_norm": 0.043730515986680984, |
| "learning_rate": 0.0002, |
| "loss": 0.0096, |
| "step": 1450 |
| }, |
| { |
| "epoch": 10.11, |
| "grad_norm": 0.05817865580320358, |
| "learning_rate": 0.0002, |
| "loss": 0.0084, |
| "step": 1460 |
| }, |
| { |
| "epoch": 10.18, |
| "grad_norm": 0.26322343945503235, |
| "learning_rate": 0.0002, |
| "loss": 0.0069, |
| "step": 1470 |
| }, |
| { |
| "epoch": 10.25, |
| "grad_norm": 0.0707869678735733, |
| "learning_rate": 0.0002, |
| "loss": 0.0063, |
| "step": 1480 |
| }, |
| { |
| "epoch": 10.32, |
| "grad_norm": 0.06895614415407181, |
| "learning_rate": 0.0002, |
| "loss": 0.0107, |
| "step": 1490 |
| }, |
| { |
| "epoch": 10.39, |
| "grad_norm": 0.014940924942493439, |
| "learning_rate": 0.0002, |
| "loss": 0.006, |
| "step": 1500 |
| }, |
| { |
| "epoch": 10.46, |
| "grad_norm": 0.12346550822257996, |
| "learning_rate": 0.0002, |
| "loss": 0.0101, |
| "step": 1510 |
| }, |
| { |
| "epoch": 10.53, |
| "grad_norm": 0.06773683428764343, |
| "learning_rate": 0.0002, |
| "loss": 0.0108, |
| "step": 1520 |
| }, |
| { |
| "epoch": 10.6, |
| "grad_norm": 0.08521382510662079, |
| "learning_rate": 0.0002, |
| "loss": 0.0088, |
| "step": 1530 |
| }, |
| { |
| "epoch": 10.67, |
| "grad_norm": 0.3153349459171295, |
| "learning_rate": 0.0002, |
| "loss": 0.0113, |
| "step": 1540 |
| }, |
| { |
| "epoch": 10.74, |
| "grad_norm": 0.32351627945899963, |
| "learning_rate": 0.0002, |
| "loss": 0.0095, |
| "step": 1550 |
| }, |
| { |
| "epoch": 10.81, |
| "grad_norm": 0.1824280321598053, |
| "learning_rate": 0.0002, |
| "loss": 0.0163, |
| "step": 1560 |
| }, |
| { |
| "epoch": 10.87, |
| "grad_norm": 0.1012108325958252, |
| "learning_rate": 0.0002, |
| "loss": 0.0078, |
| "step": 1570 |
| }, |
| { |
| "epoch": 10.94, |
| "grad_norm": 0.12629801034927368, |
| "learning_rate": 0.0002, |
| "loss": 0.0086, |
| "step": 1580 |
| }, |
| { |
| "epoch": 11.01, |
| "grad_norm": 0.0864088237285614, |
| "learning_rate": 0.0002, |
| "loss": 0.0104, |
| "step": 1590 |
| }, |
| { |
| "epoch": 11.08, |
| "grad_norm": 0.09980332106351852, |
| "learning_rate": 0.0002, |
| "loss": 0.0082, |
| "step": 1600 |
| }, |
| { |
| "epoch": 11.15, |
| "grad_norm": 0.3955361545085907, |
| "learning_rate": 0.0002, |
| "loss": 0.0161, |
| "step": 1610 |
| }, |
| { |
| "epoch": 11.22, |
| "grad_norm": 0.3551037013530731, |
| "learning_rate": 0.0002, |
| "loss": 0.0105, |
| "step": 1620 |
| }, |
| { |
| "epoch": 11.29, |
| "grad_norm": 0.1988571435213089, |
| "learning_rate": 0.0002, |
| "loss": 0.013, |
| "step": 1630 |
| }, |
| { |
| "epoch": 11.36, |
| "grad_norm": 0.09209605306386948, |
| "learning_rate": 0.0002, |
| "loss": 0.009, |
| "step": 1640 |
| }, |
| { |
| "epoch": 11.43, |
| "grad_norm": 0.08203499764204025, |
| "learning_rate": 0.0002, |
| "loss": 0.0118, |
| "step": 1650 |
| }, |
| { |
| "epoch": 11.5, |
| "grad_norm": 0.05315827578306198, |
| "learning_rate": 0.0002, |
| "loss": 0.0074, |
| "step": 1660 |
| }, |
| { |
| "epoch": 11.57, |
| "grad_norm": 0.06285399943590164, |
| "learning_rate": 0.0002, |
| "loss": 0.014, |
| "step": 1670 |
| }, |
| { |
| "epoch": 11.64, |
| "grad_norm": 0.2484624832868576, |
| "learning_rate": 0.0002, |
| "loss": 0.0154, |
| "step": 1680 |
| }, |
| { |
| "epoch": 11.71, |
| "grad_norm": 0.2875213623046875, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 1690 |
| }, |
| { |
| "epoch": 11.77, |
| "grad_norm": 0.043303802609443665, |
| "learning_rate": 0.0002, |
| "loss": 0.0096, |
| "step": 1700 |
| }, |
| { |
| "epoch": 11.84, |
| "grad_norm": 0.1575409173965454, |
| "learning_rate": 0.0002, |
| "loss": 0.0129, |
| "step": 1710 |
| }, |
| { |
| "epoch": 11.91, |
| "grad_norm": 0.07893040031194687, |
| "learning_rate": 0.0002, |
| "loss": 0.0061, |
| "step": 1720 |
| }, |
| { |
| "epoch": 11.98, |
| "grad_norm": 0.18039758503437042, |
| "learning_rate": 0.0002, |
| "loss": 0.0118, |
| "step": 1730 |
| }, |
| { |
| "epoch": 12.05, |
| "grad_norm": 0.07571464776992798, |
| "learning_rate": 0.0002, |
| "loss": 0.0135, |
| "step": 1740 |
| }, |
| { |
| "epoch": 12.12, |
| "grad_norm": 0.3126212954521179, |
| "learning_rate": 0.0002, |
| "loss": 0.0086, |
| "step": 1750 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1750, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 13, |
| "save_steps": 250, |
| "total_flos": 2.123929865873141e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
