| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.962593516209477, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04987531172069826, | |
| "grad_norm": 39.54836654663086, | |
| "learning_rate": 1.9940000000000002e-05, | |
| "loss": 7.4096, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09975062344139651, | |
| "grad_norm": 47.2942008972168, | |
| "learning_rate": 1.9873333333333335e-05, | |
| "loss": 5.883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14962593516209477, | |
| "grad_norm": 44.06085968017578, | |
| "learning_rate": 1.9806666666666668e-05, | |
| "loss": 3.9265, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19950124688279303, | |
| "grad_norm": 19.404735565185547, | |
| "learning_rate": 1.974e-05, | |
| "loss": 1.9858, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24937655860349128, | |
| "grad_norm": 1.9771770238876343, | |
| "learning_rate": 1.9673333333333337e-05, | |
| "loss": 1.0943, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29925187032418954, | |
| "grad_norm": 0.6882551312446594, | |
| "learning_rate": 1.9606666666666666e-05, | |
| "loss": 0.9006, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3491271820448878, | |
| "grad_norm": 0.7775446772575378, | |
| "learning_rate": 1.9540000000000003e-05, | |
| "loss": 0.8786, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.39900249376558605, | |
| "grad_norm": 0.720007598400116, | |
| "learning_rate": 1.9473333333333335e-05, | |
| "loss": 0.858, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4488778054862843, | |
| "grad_norm": 0.6773384809494019, | |
| "learning_rate": 1.940666666666667e-05, | |
| "loss": 0.811, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.49875311720698257, | |
| "grad_norm": 0.6907929182052612, | |
| "learning_rate": 1.934e-05, | |
| "loss": 0.7896, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5486284289276808, | |
| "grad_norm": 0.7552163600921631, | |
| "learning_rate": 1.9273333333333334e-05, | |
| "loss": 0.7589, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5985037406483791, | |
| "grad_norm": 0.7480026483535767, | |
| "learning_rate": 1.920666666666667e-05, | |
| "loss": 0.7347, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6483790523690773, | |
| "grad_norm": 0.9136413931846619, | |
| "learning_rate": 1.914e-05, | |
| "loss": 0.7218, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6982543640897756, | |
| "grad_norm": 0.7177766561508179, | |
| "learning_rate": 1.9073333333333336e-05, | |
| "loss": 0.6983, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7481296758104738, | |
| "grad_norm": 0.7291643023490906, | |
| "learning_rate": 1.900666666666667e-05, | |
| "loss": 0.6811, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7980049875311721, | |
| "grad_norm": 0.8402264714241028, | |
| "learning_rate": 1.894e-05, | |
| "loss": 0.6518, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8478802992518704, | |
| "grad_norm": 0.7445259690284729, | |
| "learning_rate": 1.8873333333333334e-05, | |
| "loss": 0.6621, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8977556109725686, | |
| "grad_norm": 0.7637977004051208, | |
| "learning_rate": 1.8806666666666667e-05, | |
| "loss": 0.623, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9476309226932669, | |
| "grad_norm": 0.7605411410331726, | |
| "learning_rate": 1.8740000000000004e-05, | |
| "loss": 0.642, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.9975062344139651, | |
| "grad_norm": 0.7474659085273743, | |
| "learning_rate": 1.8673333333333333e-05, | |
| "loss": 0.6081, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9975062344139651, | |
| "eval_loss": 0.6107227802276611, | |
| "eval_runtime": 57.9983, | |
| "eval_samples_per_second": 17.294, | |
| "eval_steps_per_second": 3.466, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0473815461346634, | |
| "grad_norm": 0.7955527901649475, | |
| "learning_rate": 1.860666666666667e-05, | |
| "loss": 0.6313, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.0972568578553616, | |
| "grad_norm": 0.8842599391937256, | |
| "learning_rate": 1.8540000000000002e-05, | |
| "loss": 0.5837, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.14713216957606, | |
| "grad_norm": 0.9143279790878296, | |
| "learning_rate": 1.8473333333333335e-05, | |
| "loss": 0.5668, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.1970074812967582, | |
| "grad_norm": 0.8860597610473633, | |
| "learning_rate": 1.8406666666666668e-05, | |
| "loss": 0.565, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.2468827930174564, | |
| "grad_norm": 0.8665011525154114, | |
| "learning_rate": 1.834e-05, | |
| "loss": 0.5611, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.2967581047381547, | |
| "grad_norm": 0.8916261196136475, | |
| "learning_rate": 1.8273333333333333e-05, | |
| "loss": 0.5461, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.346633416458853, | |
| "grad_norm": 0.8792281150817871, | |
| "learning_rate": 1.820666666666667e-05, | |
| "loss": 0.5569, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.3965087281795512, | |
| "grad_norm": 0.8166815638542175, | |
| "learning_rate": 1.8140000000000003e-05, | |
| "loss": 0.5435, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.4463840399002494, | |
| "grad_norm": 0.9711934328079224, | |
| "learning_rate": 1.8073333333333335e-05, | |
| "loss": 0.5205, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.4962593516209477, | |
| "grad_norm": 0.8851374983787537, | |
| "learning_rate": 1.8006666666666668e-05, | |
| "loss": 0.5269, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.546134663341646, | |
| "grad_norm": 0.940987765789032, | |
| "learning_rate": 1.794e-05, | |
| "loss": 0.5177, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.5960099750623442, | |
| "grad_norm": 1.1342016458511353, | |
| "learning_rate": 1.7873333333333337e-05, | |
| "loss": 0.4981, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.6458852867830425, | |
| "grad_norm": 1.0847837924957275, | |
| "learning_rate": 1.7806666666666667e-05, | |
| "loss": 0.5056, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.6957605985037407, | |
| "grad_norm": 0.979576587677002, | |
| "learning_rate": 1.7740000000000003e-05, | |
| "loss": 0.5048, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.745635910224439, | |
| "grad_norm": 0.9637285470962524, | |
| "learning_rate": 1.7673333333333336e-05, | |
| "loss": 0.5076, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.7955112219451372, | |
| "grad_norm": 0.9592918157577515, | |
| "learning_rate": 1.760666666666667e-05, | |
| "loss": 0.512, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.8453865336658355, | |
| "grad_norm": 0.9521375894546509, | |
| "learning_rate": 1.754e-05, | |
| "loss": 0.4993, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.8952618453865338, | |
| "grad_norm": 1.1952577829360962, | |
| "learning_rate": 1.7473333333333334e-05, | |
| "loss": 0.4933, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.945137157107232, | |
| "grad_norm": 0.8078787326812744, | |
| "learning_rate": 1.7406666666666667e-05, | |
| "loss": 0.4894, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.9950124688279303, | |
| "grad_norm": 1.0912864208221436, | |
| "learning_rate": 1.734e-05, | |
| "loss": 0.4865, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.49822476506233215, | |
| "eval_runtime": 57.9997, | |
| "eval_samples_per_second": 17.293, | |
| "eval_steps_per_second": 3.466, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 2.0448877805486285, | |
| "grad_norm": 0.9705982804298401, | |
| "learning_rate": 1.7273333333333336e-05, | |
| "loss": 0.4976, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.0947630922693268, | |
| "grad_norm": 1.0686686038970947, | |
| "learning_rate": 1.7206666666666666e-05, | |
| "loss": 0.4851, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.144638403990025, | |
| "grad_norm": 1.0422980785369873, | |
| "learning_rate": 1.7140000000000002e-05, | |
| "loss": 0.4577, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.1945137157107233, | |
| "grad_norm": 1.0678831338882446, | |
| "learning_rate": 1.7073333333333335e-05, | |
| "loss": 0.5092, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.2443890274314215, | |
| "grad_norm": 1.1621687412261963, | |
| "learning_rate": 1.7006666666666668e-05, | |
| "loss": 0.4897, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.29426433915212, | |
| "grad_norm": 0.9376991391181946, | |
| "learning_rate": 1.694e-05, | |
| "loss": 0.4788, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.344139650872818, | |
| "grad_norm": 1.0832690000534058, | |
| "learning_rate": 1.6873333333333333e-05, | |
| "loss": 0.4864, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.3940149625935163, | |
| "grad_norm": 1.1426657438278198, | |
| "learning_rate": 1.680666666666667e-05, | |
| "loss": 0.4659, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.4438902743142146, | |
| "grad_norm": 1.016119122505188, | |
| "learning_rate": 1.6740000000000002e-05, | |
| "loss": 0.4636, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.493765586034913, | |
| "grad_norm": 1.1347243785858154, | |
| "learning_rate": 1.6673333333333335e-05, | |
| "loss": 0.4663, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.543640897755611, | |
| "grad_norm": 1.087796926498413, | |
| "learning_rate": 1.6606666666666668e-05, | |
| "loss": 0.4729, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.5935162094763093, | |
| "grad_norm": 1.1080952882766724, | |
| "learning_rate": 1.654e-05, | |
| "loss": 0.4803, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.6433915211970076, | |
| "grad_norm": 0.9999821186065674, | |
| "learning_rate": 1.6473333333333334e-05, | |
| "loss": 0.4872, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.693266832917706, | |
| "grad_norm": 1.2594393491744995, | |
| "learning_rate": 1.640666666666667e-05, | |
| "loss": 0.4708, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.743142144638404, | |
| "grad_norm": 1.012904167175293, | |
| "learning_rate": 1.634e-05, | |
| "loss": 0.46, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.7930174563591024, | |
| "grad_norm": 1.052252173423767, | |
| "learning_rate": 1.6273333333333336e-05, | |
| "loss": 0.4664, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.8428927680798006, | |
| "grad_norm": 1.2155933380126953, | |
| "learning_rate": 1.620666666666667e-05, | |
| "loss": 0.4518, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.892768079800499, | |
| "grad_norm": 1.064907193183899, | |
| "learning_rate": 1.614e-05, | |
| "loss": 0.4933, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.942643391521197, | |
| "grad_norm": 1.0846999883651733, | |
| "learning_rate": 1.6073333333333334e-05, | |
| "loss": 0.4724, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.9925187032418954, | |
| "grad_norm": 1.2878086566925049, | |
| "learning_rate": 1.6006666666666667e-05, | |
| "loss": 0.4895, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.997506234413965, | |
| "eval_loss": 0.47463858127593994, | |
| "eval_runtime": 57.9983, | |
| "eval_samples_per_second": 17.294, | |
| "eval_steps_per_second": 3.466, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 3.0423940149625937, | |
| "grad_norm": 1.141946792602539, | |
| "learning_rate": 1.5940000000000003e-05, | |
| "loss": 0.4808, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.092269326683292, | |
| "grad_norm": 1.1112643480300903, | |
| "learning_rate": 1.5873333333333333e-05, | |
| "loss": 0.4525, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.14214463840399, | |
| "grad_norm": 1.0057584047317505, | |
| "learning_rate": 1.580666666666667e-05, | |
| "loss": 0.4699, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.1920199501246884, | |
| "grad_norm": 1.3252357244491577, | |
| "learning_rate": 1.5740000000000002e-05, | |
| "loss": 0.4631, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.2418952618453867, | |
| "grad_norm": 1.1567648649215698, | |
| "learning_rate": 1.5673333333333335e-05, | |
| "loss": 0.4559, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.291770573566085, | |
| "grad_norm": 1.0659315586090088, | |
| "learning_rate": 1.5606666666666667e-05, | |
| "loss": 0.4575, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.341645885286783, | |
| "grad_norm": 1.1061469316482544, | |
| "learning_rate": 1.554e-05, | |
| "loss": 0.4592, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.3915211970074814, | |
| "grad_norm": 1.342760443687439, | |
| "learning_rate": 1.5473333333333333e-05, | |
| "loss": 0.4459, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.4413965087281797, | |
| "grad_norm": 1.080640196800232, | |
| "learning_rate": 1.5406666666666666e-05, | |
| "loss": 0.4801, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.491271820448878, | |
| "grad_norm": 1.1660523414611816, | |
| "learning_rate": 1.5340000000000002e-05, | |
| "loss": 0.4536, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.541147132169576, | |
| "grad_norm": 1.0911084413528442, | |
| "learning_rate": 1.5273333333333335e-05, | |
| "loss": 0.4536, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.5910224438902745, | |
| "grad_norm": 1.1449761390686035, | |
| "learning_rate": 1.5206666666666668e-05, | |
| "loss": 0.4663, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.6408977556109727, | |
| "grad_norm": 1.0596632957458496, | |
| "learning_rate": 1.514e-05, | |
| "loss": 0.4633, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.690773067331671, | |
| "grad_norm": 1.1071261167526245, | |
| "learning_rate": 1.5073333333333335e-05, | |
| "loss": 0.4579, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.7406483790523692, | |
| "grad_norm": 1.3376258611679077, | |
| "learning_rate": 1.5006666666666666e-05, | |
| "loss": 0.4526, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.7905236907730675, | |
| "grad_norm": 1.2122935056686401, | |
| "learning_rate": 1.4940000000000001e-05, | |
| "loss": 0.4602, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.8403990024937658, | |
| "grad_norm": 1.1372263431549072, | |
| "learning_rate": 1.4873333333333335e-05, | |
| "loss": 0.4733, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.890274314214464, | |
| "grad_norm": 1.1192553043365479, | |
| "learning_rate": 1.4806666666666667e-05, | |
| "loss": 0.466, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.9401496259351623, | |
| "grad_norm": 1.1695116758346558, | |
| "learning_rate": 1.4740000000000001e-05, | |
| "loss": 0.4485, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.9900249376558605, | |
| "grad_norm": 1.2374085187911987, | |
| "learning_rate": 1.4673333333333336e-05, | |
| "loss": 0.4428, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.4639199376106262, | |
| "eval_runtime": 58.0007, | |
| "eval_samples_per_second": 17.293, | |
| "eval_steps_per_second": 3.465, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 4.039900249376559, | |
| "grad_norm": 1.2248201370239258, | |
| "learning_rate": 1.4606666666666667e-05, | |
| "loss": 0.4765, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.089775561097257, | |
| "grad_norm": 1.0709633827209473, | |
| "learning_rate": 1.4540000000000001e-05, | |
| "loss": 0.458, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.139650872817955, | |
| "grad_norm": 1.245808482170105, | |
| "learning_rate": 1.4473333333333334e-05, | |
| "loss": 0.4413, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.1895261845386536, | |
| "grad_norm": 1.0952578783035278, | |
| "learning_rate": 1.4406666666666669e-05, | |
| "loss": 0.4466, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.239401496259352, | |
| "grad_norm": 1.3013060092926025, | |
| "learning_rate": 1.434e-05, | |
| "loss": 0.4579, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.28927680798005, | |
| "grad_norm": 1.40675687789917, | |
| "learning_rate": 1.4273333333333334e-05, | |
| "loss": 0.4547, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.339152119700748, | |
| "grad_norm": 1.0993843078613281, | |
| "learning_rate": 1.4206666666666669e-05, | |
| "loss": 0.4326, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.389027431421447, | |
| "grad_norm": 1.279954195022583, | |
| "learning_rate": 1.414e-05, | |
| "loss": 0.4528, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.438902743142145, | |
| "grad_norm": 1.1767985820770264, | |
| "learning_rate": 1.4073333333333335e-05, | |
| "loss": 0.4678, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.488778054862843, | |
| "grad_norm": 1.2366374731063843, | |
| "learning_rate": 1.400666666666667e-05, | |
| "loss": 0.4383, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.538653366583541, | |
| "grad_norm": 1.3890389204025269, | |
| "learning_rate": 1.394e-05, | |
| "loss": 0.4586, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.58852867830424, | |
| "grad_norm": 1.288946509361267, | |
| "learning_rate": 1.3873333333333335e-05, | |
| "loss": 0.4329, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.638403990024938, | |
| "grad_norm": 1.5377354621887207, | |
| "learning_rate": 1.3806666666666668e-05, | |
| "loss": 0.4524, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.688279301745636, | |
| "grad_norm": 1.1805988550186157, | |
| "learning_rate": 1.3740000000000002e-05, | |
| "loss": 0.4421, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 4.738154613466334, | |
| "grad_norm": 1.2433724403381348, | |
| "learning_rate": 1.3673333333333333e-05, | |
| "loss": 0.4463, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.788029925187033, | |
| "grad_norm": 1.5534576177597046, | |
| "learning_rate": 1.3606666666666668e-05, | |
| "loss": 0.4529, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 4.837905236907731, | |
| "grad_norm": 1.1943343877792358, | |
| "learning_rate": 1.3540000000000003e-05, | |
| "loss": 0.4342, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 4.887780548628429, | |
| "grad_norm": 1.4089887142181396, | |
| "learning_rate": 1.3473333333333334e-05, | |
| "loss": 0.4474, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 4.937655860349127, | |
| "grad_norm": 1.2032736539840698, | |
| "learning_rate": 1.3406666666666668e-05, | |
| "loss": 0.4367, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.987531172069826, | |
| "grad_norm": 1.2193266153335571, | |
| "learning_rate": 1.3340000000000001e-05, | |
| "loss": 0.4617, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.997506234413965, | |
| "eval_loss": 0.457111656665802, | |
| "eval_runtime": 58.0103, | |
| "eval_samples_per_second": 17.29, | |
| "eval_steps_per_second": 3.465, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 5.037406483790524, | |
| "grad_norm": 1.2309563159942627, | |
| "learning_rate": 1.3273333333333334e-05, | |
| "loss": 0.4802, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 5.087281795511222, | |
| "grad_norm": 1.3006610870361328, | |
| "learning_rate": 1.3206666666666668e-05, | |
| "loss": 0.4304, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.13715710723192, | |
| "grad_norm": 1.1411958932876587, | |
| "learning_rate": 1.3140000000000001e-05, | |
| "loss": 0.4379, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.187032418952619, | |
| "grad_norm": 1.489011287689209, | |
| "learning_rate": 1.3073333333333334e-05, | |
| "loss": 0.4377, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.236907730673317, | |
| "grad_norm": 1.127456784248352, | |
| "learning_rate": 1.3006666666666667e-05, | |
| "loss": 0.4401, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 5.286783042394015, | |
| "grad_norm": 1.1423261165618896, | |
| "learning_rate": 1.2940000000000001e-05, | |
| "loss": 0.4195, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 5.3366583541147135, | |
| "grad_norm": 1.2664945125579834, | |
| "learning_rate": 1.2873333333333336e-05, | |
| "loss": 0.4421, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 5.386533665835412, | |
| "grad_norm": 1.3833181858062744, | |
| "learning_rate": 1.2806666666666667e-05, | |
| "loss": 0.4493, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 5.43640897755611, | |
| "grad_norm": 1.2505003213882446, | |
| "learning_rate": 1.2740000000000002e-05, | |
| "loss": 0.4322, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 5.486284289276808, | |
| "grad_norm": 1.1786164045333862, | |
| "learning_rate": 1.2673333333333335e-05, | |
| "loss": 0.4474, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.5361596009975065, | |
| "grad_norm": 1.3222135305404663, | |
| "learning_rate": 1.2606666666666667e-05, | |
| "loss": 0.4434, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 5.586034912718205, | |
| "grad_norm": 1.1747450828552246, | |
| "learning_rate": 1.254e-05, | |
| "loss": 0.4577, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 5.635910224438903, | |
| "grad_norm": 1.299611210823059, | |
| "learning_rate": 1.2473333333333335e-05, | |
| "loss": 0.4306, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 5.685785536159601, | |
| "grad_norm": 1.353705883026123, | |
| "learning_rate": 1.2406666666666668e-05, | |
| "loss": 0.4438, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 5.7356608478802995, | |
| "grad_norm": 1.195237398147583, | |
| "learning_rate": 1.234e-05, | |
| "loss": 0.4203, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5.785536159600998, | |
| "grad_norm": 1.4759230613708496, | |
| "learning_rate": 1.2273333333333335e-05, | |
| "loss": 0.4399, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 5.835411471321696, | |
| "grad_norm": 1.1856341361999512, | |
| "learning_rate": 1.2206666666666666e-05, | |
| "loss": 0.4566, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 5.885286783042394, | |
| "grad_norm": 1.369195818901062, | |
| "learning_rate": 1.214e-05, | |
| "loss": 0.4568, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 5.9351620947630925, | |
| "grad_norm": 1.2702898979187012, | |
| "learning_rate": 1.2073333333333335e-05, | |
| "loss": 0.4372, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 5.985037406483791, | |
| "grad_norm": 1.5332574844360352, | |
| "learning_rate": 1.2006666666666668e-05, | |
| "loss": 0.454, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.45269879698753357, | |
| "eval_runtime": 57.8329, | |
| "eval_samples_per_second": 17.343, | |
| "eval_steps_per_second": 3.476, | |
| "step": 1203 | |
| }, | |
| { | |
| "epoch": 6.034912718204489, | |
| "grad_norm": 1.502089500427246, | |
| "learning_rate": 1.1940000000000001e-05, | |
| "loss": 0.4509, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 6.084788029925187, | |
| "grad_norm": 1.1866357326507568, | |
| "learning_rate": 1.1873333333333334e-05, | |
| "loss": 0.4315, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.134663341645886, | |
| "grad_norm": 1.2971949577331543, | |
| "learning_rate": 1.1806666666666668e-05, | |
| "loss": 0.4378, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 6.184538653366584, | |
| "grad_norm": 1.3105353116989136, | |
| "learning_rate": 1.1740000000000001e-05, | |
| "loss": 0.4462, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 6.234413965087282, | |
| "grad_norm": 1.6913713216781616, | |
| "learning_rate": 1.1673333333333334e-05, | |
| "loss": 0.4273, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 6.28428927680798, | |
| "grad_norm": 1.2743034362792969, | |
| "learning_rate": 1.1606666666666668e-05, | |
| "loss": 0.4308, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 6.334164588528679, | |
| "grad_norm": 1.2764904499053955, | |
| "learning_rate": 1.154e-05, | |
| "loss": 0.4416, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 6.384039900249377, | |
| "grad_norm": 1.2375209331512451, | |
| "learning_rate": 1.1473333333333334e-05, | |
| "loss": 0.4279, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 6.433915211970075, | |
| "grad_norm": 1.2813770771026611, | |
| "learning_rate": 1.1406666666666669e-05, | |
| "loss": 0.4318, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 6.483790523690773, | |
| "grad_norm": 1.413662314414978, | |
| "learning_rate": 1.134e-05, | |
| "loss": 0.4299, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.533665835411472, | |
| "grad_norm": 1.4377459287643433, | |
| "learning_rate": 1.1273333333333334e-05, | |
| "loss": 0.4538, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 6.58354114713217, | |
| "grad_norm": 1.280629277229309, | |
| "learning_rate": 1.1206666666666667e-05, | |
| "loss": 0.4305, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.633416458852868, | |
| "grad_norm": 1.4439893960952759, | |
| "learning_rate": 1.1140000000000002e-05, | |
| "loss": 0.4382, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 6.683291770573566, | |
| "grad_norm": 1.290280818939209, | |
| "learning_rate": 1.1073333333333333e-05, | |
| "loss": 0.4395, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 6.733167082294265, | |
| "grad_norm": 1.7553201913833618, | |
| "learning_rate": 1.1006666666666667e-05, | |
| "loss": 0.4633, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 6.783042394014963, | |
| "grad_norm": 1.3317337036132812, | |
| "learning_rate": 1.0940000000000002e-05, | |
| "loss": 0.4396, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 6.832917705735661, | |
| "grad_norm": 1.4611096382141113, | |
| "learning_rate": 1.0873333333333333e-05, | |
| "loss": 0.4306, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 6.882793017456359, | |
| "grad_norm": 1.461767554283142, | |
| "learning_rate": 1.0806666666666668e-05, | |
| "loss": 0.4363, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 6.932668329177058, | |
| "grad_norm": 1.2594436407089233, | |
| "learning_rate": 1.0740000000000002e-05, | |
| "loss": 0.4311, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 6.982543640897756, | |
| "grad_norm": 1.339422345161438, | |
| "learning_rate": 1.0673333333333333e-05, | |
| "loss": 0.4359, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.997506234413965, | |
| "eval_loss": 0.4493270516395569, | |
| "eval_runtime": 57.825, | |
| "eval_samples_per_second": 17.345, | |
| "eval_steps_per_second": 3.476, | |
| "step": 1403 | |
| }, | |
| { | |
| "epoch": 7.032418952618454, | |
| "grad_norm": 1.5040308237075806, | |
| "learning_rate": 1.0606666666666668e-05, | |
| "loss": 0.4513, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 7.082294264339152, | |
| "grad_norm": 1.3062398433685303, | |
| "learning_rate": 1.054e-05, | |
| "loss": 0.4286, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 7.132169576059851, | |
| "grad_norm": 1.2743724584579468, | |
| "learning_rate": 1.0473333333333334e-05, | |
| "loss": 0.4308, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 7.182044887780549, | |
| "grad_norm": 1.335893154144287, | |
| "learning_rate": 1.0406666666666666e-05, | |
| "loss": 0.4467, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 7.231920199501247, | |
| "grad_norm": 1.5432289838790894, | |
| "learning_rate": 1.0340000000000001e-05, | |
| "loss": 0.4249, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 7.2817955112219455, | |
| "grad_norm": 1.3191583156585693, | |
| "learning_rate": 1.0273333333333335e-05, | |
| "loss": 0.4308, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 7.331670822942644, | |
| "grad_norm": 1.4070515632629395, | |
| "learning_rate": 1.0206666666666667e-05, | |
| "loss": 0.4346, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 7.381546134663342, | |
| "grad_norm": 1.2089998722076416, | |
| "learning_rate": 1.0140000000000001e-05, | |
| "loss": 0.4261, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 7.43142144638404, | |
| "grad_norm": 1.349908709526062, | |
| "learning_rate": 1.0073333333333336e-05, | |
| "loss": 0.4506, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 7.4812967581047385, | |
| "grad_norm": 1.3772706985473633, | |
| "learning_rate": 1.0006666666666667e-05, | |
| "loss": 0.4194, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.531172069825437, | |
| "grad_norm": 1.265548586845398, | |
| "learning_rate": 9.940000000000001e-06, | |
| "loss": 0.4109, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 7.581047381546135, | |
| "grad_norm": 1.4737778902053833, | |
| "learning_rate": 9.873333333333334e-06, | |
| "loss": 0.4335, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 7.630922693266833, | |
| "grad_norm": 1.2900265455245972, | |
| "learning_rate": 9.806666666666667e-06, | |
| "loss": 0.4489, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 7.6807980049875315, | |
| "grad_norm": 1.3885109424591064, | |
| "learning_rate": 9.74e-06, | |
| "loss": 0.4246, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 7.73067331670823, | |
| "grad_norm": 1.4786447286605835, | |
| "learning_rate": 9.673333333333334e-06, | |
| "loss": 0.4307, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 7.780548628428928, | |
| "grad_norm": 1.4943320751190186, | |
| "learning_rate": 9.606666666666667e-06, | |
| "loss": 0.4272, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 7.830423940149626, | |
| "grad_norm": 1.2281179428100586, | |
| "learning_rate": 9.54e-06, | |
| "loss": 0.4361, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 7.8802992518703245, | |
| "grad_norm": 1.4099763631820679, | |
| "learning_rate": 9.473333333333335e-06, | |
| "loss": 0.4328, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 7.930174563591023, | |
| "grad_norm": 1.2165679931640625, | |
| "learning_rate": 9.406666666666668e-06, | |
| "loss": 0.4325, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 7.980049875311721, | |
| "grad_norm": 1.5678939819335938, | |
| "learning_rate": 9.340000000000002e-06, | |
| "loss": 0.4431, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.4465142786502838, | |
| "eval_runtime": 57.9689, | |
| "eval_samples_per_second": 17.302, | |
| "eval_steps_per_second": 3.467, | |
| "step": 1604 | |
| }, | |
| { | |
| "epoch": 8.029925187032418, | |
| "grad_norm": 1.3903255462646484, | |
| "learning_rate": 9.273333333333335e-06, | |
| "loss": 0.4489, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 8.079800498753118, | |
| "grad_norm": 1.4039775133132935, | |
| "learning_rate": 9.206666666666668e-06, | |
| "loss": 0.4282, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 8.129675810473815, | |
| "grad_norm": 1.238571286201477, | |
| "learning_rate": 9.14e-06, | |
| "loss": 0.4352, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 8.179551122194514, | |
| "grad_norm": 1.418980360031128, | |
| "learning_rate": 9.073333333333333e-06, | |
| "loss": 0.4232, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 8.229426433915211, | |
| "grad_norm": 1.362851619720459, | |
| "learning_rate": 9.006666666666666e-06, | |
| "loss": 0.4251, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 8.27930174563591, | |
| "grad_norm": 1.3849656581878662, | |
| "learning_rate": 8.94e-06, | |
| "loss": 0.4367, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 8.329177057356608, | |
| "grad_norm": 1.4366765022277832, | |
| "learning_rate": 8.873333333333334e-06, | |
| "loss": 0.4348, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 8.379052369077307, | |
| "grad_norm": 1.3090085983276367, | |
| "learning_rate": 8.806666666666668e-06, | |
| "loss": 0.4349, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 8.428927680798004, | |
| "grad_norm": 1.3340786695480347, | |
| "learning_rate": 8.740000000000001e-06, | |
| "loss": 0.4292, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 8.478802992518704, | |
| "grad_norm": 1.224572777748108, | |
| "learning_rate": 8.673333333333334e-06, | |
| "loss": 0.4225, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 8.528678304239401, | |
| "grad_norm": 1.3066871166229248, | |
| "learning_rate": 8.606666666666668e-06, | |
| "loss": 0.4295, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 8.5785536159601, | |
| "grad_norm": 1.3138604164123535, | |
| "learning_rate": 8.540000000000001e-06, | |
| "loss": 0.4249, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 8.628428927680797, | |
| "grad_norm": 1.3178144693374634, | |
| "learning_rate": 8.473333333333334e-06, | |
| "loss": 0.4295, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 8.678304239401497, | |
| "grad_norm": 1.5216317176818848, | |
| "learning_rate": 8.406666666666667e-06, | |
| "loss": 0.4249, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 8.728179551122194, | |
| "grad_norm": 1.3315293788909912, | |
| "learning_rate": 8.34e-06, | |
| "loss": 0.4156, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 8.778054862842893, | |
| "grad_norm": 1.613593578338623, | |
| "learning_rate": 8.273333333333334e-06, | |
| "loss": 0.418, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 8.82793017456359, | |
| "grad_norm": 1.2980856895446777, | |
| "learning_rate": 8.206666666666667e-06, | |
| "loss": 0.4234, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 8.87780548628429, | |
| "grad_norm": 1.4451056718826294, | |
| "learning_rate": 8.14e-06, | |
| "loss": 0.4427, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 8.927680798004987, | |
| "grad_norm": 1.3692457675933838, | |
| "learning_rate": 8.073333333333335e-06, | |
| "loss": 0.4394, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 8.977556109725686, | |
| "grad_norm": 1.4997522830963135, | |
| "learning_rate": 8.006666666666667e-06, | |
| "loss": 0.4299, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 8.997506234413965, | |
| "eval_loss": 0.4446782171726227, | |
| "eval_runtime": 57.956, | |
| "eval_samples_per_second": 17.306, | |
| "eval_steps_per_second": 3.468, | |
| "step": 1804 | |
| }, | |
| { | |
| "epoch": 9.027431421446384, | |
| "grad_norm": 1.4114794731140137, | |
| "learning_rate": 7.94e-06, | |
| "loss": 0.4409, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 9.077306733167083, | |
| "grad_norm": 1.2984321117401123, | |
| "learning_rate": 7.873333333333335e-06, | |
| "loss": 0.4091, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 9.12718204488778, | |
| "grad_norm": 1.3625205755233765, | |
| "learning_rate": 7.806666666666668e-06, | |
| "loss": 0.4224, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 9.17705735660848, | |
| "grad_norm": 1.4072176218032837, | |
| "learning_rate": 7.74e-06, | |
| "loss": 0.4416, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 9.226932668329177, | |
| "grad_norm": 1.2547061443328857, | |
| "learning_rate": 7.673333333333333e-06, | |
| "loss": 0.4228, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 9.276807980049876, | |
| "grad_norm": 1.5764844417572021, | |
| "learning_rate": 7.606666666666668e-06, | |
| "loss": 0.4346, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 9.326683291770573, | |
| "grad_norm": 1.4493110179901123, | |
| "learning_rate": 7.540000000000001e-06, | |
| "loss": 0.438, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 9.376558603491272, | |
| "grad_norm": 1.3886995315551758, | |
| "learning_rate": 7.4733333333333335e-06, | |
| "loss": 0.4282, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 9.42643391521197, | |
| "grad_norm": 1.5260852575302124, | |
| "learning_rate": 7.406666666666667e-06, | |
| "loss": 0.4267, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 9.476309226932669, | |
| "grad_norm": 1.7208826541900635, | |
| "learning_rate": 7.340000000000001e-06, | |
| "loss": 0.4195, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 9.526184538653366, | |
| "grad_norm": 1.3822261095046997, | |
| "learning_rate": 7.2733333333333346e-06, | |
| "loss": 0.4254, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 9.576059850374065, | |
| "grad_norm": 1.6141988039016724, | |
| "learning_rate": 7.206666666666667e-06, | |
| "loss": 0.4165, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 9.625935162094763, | |
| "grad_norm": 1.4055383205413818, | |
| "learning_rate": 7.14e-06, | |
| "loss": 0.4149, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 9.675810473815462, | |
| "grad_norm": 1.3142189979553223, | |
| "learning_rate": 7.073333333333334e-06, | |
| "loss": 0.4107, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 9.72568578553616, | |
| "grad_norm": 1.2457393407821655, | |
| "learning_rate": 7.006666666666667e-06, | |
| "loss": 0.4296, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 9.775561097256858, | |
| "grad_norm": 1.4622180461883545, | |
| "learning_rate": 6.9400000000000005e-06, | |
| "loss": 0.4422, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 9.825436408977556, | |
| "grad_norm": 1.4130418300628662, | |
| "learning_rate": 6.873333333333334e-06, | |
| "loss": 0.4317, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 9.875311720698255, | |
| "grad_norm": 1.311515212059021, | |
| "learning_rate": 6.806666666666667e-06, | |
| "loss": 0.4184, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 9.925187032418952, | |
| "grad_norm": 1.4601870775222778, | |
| "learning_rate": 6.740000000000001e-06, | |
| "loss": 0.4136, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 9.975062344139651, | |
| "grad_norm": 1.3348491191864014, | |
| "learning_rate": 6.6733333333333335e-06, | |
| "loss": 0.4409, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.44308173656463623, | |
| "eval_runtime": 57.9177, | |
| "eval_samples_per_second": 17.318, | |
| "eval_steps_per_second": 3.47, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 10.024937655860349, | |
| "grad_norm": 1.3334033489227295, | |
| "learning_rate": 6.606666666666666e-06, | |
| "loss": 0.4456, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 10.074812967581048, | |
| "grad_norm": 1.5118451118469238, | |
| "learning_rate": 6.540000000000001e-06, | |
| "loss": 0.4385, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 10.124688279301745, | |
| "grad_norm": 1.3644325733184814, | |
| "learning_rate": 6.473333333333334e-06, | |
| "loss": 0.4208, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 10.174563591022444, | |
| "grad_norm": 1.426771640777588, | |
| "learning_rate": 6.4066666666666674e-06, | |
| "loss": 0.4201, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 10.224438902743142, | |
| "grad_norm": 1.3023799657821655, | |
| "learning_rate": 6.34e-06, | |
| "loss": 0.4068, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 10.27431421446384, | |
| "grad_norm": 1.3506182432174683, | |
| "learning_rate": 6.273333333333333e-06, | |
| "loss": 0.4264, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 10.324189526184538, | |
| "grad_norm": 1.4448788166046143, | |
| "learning_rate": 6.206666666666668e-06, | |
| "loss": 0.4249, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 10.374064837905237, | |
| "grad_norm": 1.3727625608444214, | |
| "learning_rate": 6.1400000000000005e-06, | |
| "loss": 0.4351, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 10.423940149625935, | |
| "grad_norm": 1.512022614479065, | |
| "learning_rate": 6.073333333333333e-06, | |
| "loss": 0.4332, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 10.473815461346634, | |
| "grad_norm": 1.305282473564148, | |
| "learning_rate": 6.006666666666667e-06, | |
| "loss": 0.4248, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 10.523690773067331, | |
| "grad_norm": 1.4088374376296997, | |
| "learning_rate": 5.94e-06, | |
| "loss": 0.4323, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 10.57356608478803, | |
| "grad_norm": 1.4796631336212158, | |
| "learning_rate": 5.873333333333334e-06, | |
| "loss": 0.4254, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 10.623441396508728, | |
| "grad_norm": 1.556593418121338, | |
| "learning_rate": 5.806666666666667e-06, | |
| "loss": 0.4117, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 10.673316708229427, | |
| "grad_norm": 1.3857340812683105, | |
| "learning_rate": 5.74e-06, | |
| "loss": 0.4241, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 10.723192019950124, | |
| "grad_norm": 1.6449425220489502, | |
| "learning_rate": 5.673333333333334e-06, | |
| "loss": 0.4144, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 10.773067331670823, | |
| "grad_norm": 1.8624916076660156, | |
| "learning_rate": 5.606666666666667e-06, | |
| "loss": 0.4239, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 10.82294264339152, | |
| "grad_norm": 1.3718584775924683, | |
| "learning_rate": 5.540000000000001e-06, | |
| "loss": 0.4081, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 10.87281795511222, | |
| "grad_norm": 1.4391957521438599, | |
| "learning_rate": 5.473333333333334e-06, | |
| "loss": 0.4195, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 10.922693266832917, | |
| "grad_norm": 1.6265774965286255, | |
| "learning_rate": 5.406666666666667e-06, | |
| "loss": 0.4446, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 10.972568578553616, | |
| "grad_norm": 1.5026485919952393, | |
| "learning_rate": 5.3400000000000005e-06, | |
| "loss": 0.4229, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 10.997506234413965, | |
| "eval_loss": 0.44174298644065857, | |
| "eval_runtime": 57.9098, | |
| "eval_samples_per_second": 17.32, | |
| "eval_steps_per_second": 3.471, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 11.022443890274314, | |
| "grad_norm": 1.452600121498108, | |
| "learning_rate": 5.273333333333333e-06, | |
| "loss": 0.4326, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 11.072319201995013, | |
| "grad_norm": 1.3822201490402222, | |
| "learning_rate": 5.206666666666668e-06, | |
| "loss": 0.4264, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 11.12219451371571, | |
| "grad_norm": 1.468363642692566, | |
| "learning_rate": 5.140000000000001e-06, | |
| "loss": 0.4078, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 11.17206982543641, | |
| "grad_norm": 1.495955467224121, | |
| "learning_rate": 5.073333333333334e-06, | |
| "loss": 0.4173, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 11.221945137157107, | |
| "grad_norm": 1.441292405128479, | |
| "learning_rate": 5.006666666666667e-06, | |
| "loss": 0.415, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 11.271820448877806, | |
| "grad_norm": 1.421720266342163, | |
| "learning_rate": 4.94e-06, | |
| "loss": 0.4126, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 11.321695760598503, | |
| "grad_norm": 1.2590454816818237, | |
| "learning_rate": 4.873333333333334e-06, | |
| "loss": 0.4193, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 11.371571072319203, | |
| "grad_norm": 1.48396897315979, | |
| "learning_rate": 4.8066666666666675e-06, | |
| "loss": 0.4266, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 11.4214463840399, | |
| "grad_norm": 1.3837693929672241, | |
| "learning_rate": 4.74e-06, | |
| "loss": 0.4199, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 11.471321695760599, | |
| "grad_norm": 1.5965029001235962, | |
| "learning_rate": 4.673333333333333e-06, | |
| "loss": 0.4148, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 11.521197007481296, | |
| "grad_norm": 1.4824038743972778, | |
| "learning_rate": 4.606666666666667e-06, | |
| "loss": 0.4369, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 11.571072319201996, | |
| "grad_norm": 1.4421814680099487, | |
| "learning_rate": 4.540000000000001e-06, | |
| "loss": 0.4182, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 11.620947630922693, | |
| "grad_norm": 1.4961748123168945, | |
| "learning_rate": 4.473333333333334e-06, | |
| "loss": 0.4117, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 11.670822942643392, | |
| "grad_norm": 1.63477623462677, | |
| "learning_rate": 4.406666666666667e-06, | |
| "loss": 0.4237, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 11.72069825436409, | |
| "grad_norm": 1.6593093872070312, | |
| "learning_rate": 4.34e-06, | |
| "loss": 0.4279, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 11.770573566084789, | |
| "grad_norm": 1.5250682830810547, | |
| "learning_rate": 4.273333333333334e-06, | |
| "loss": 0.4264, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 11.820448877805486, | |
| "grad_norm": 1.5515984296798706, | |
| "learning_rate": 4.206666666666667e-06, | |
| "loss": 0.4341, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 11.870324189526185, | |
| "grad_norm": 1.6062873601913452, | |
| "learning_rate": 4.14e-06, | |
| "loss": 0.4247, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 11.920199501246882, | |
| "grad_norm": 1.760644793510437, | |
| "learning_rate": 4.073333333333334e-06, | |
| "loss": 0.4417, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 11.970074812967582, | |
| "grad_norm": 1.2911533117294312, | |
| "learning_rate": 4.006666666666667e-06, | |
| "loss": 0.4159, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.44075635075569153, | |
| "eval_runtime": 57.9093, | |
| "eval_samples_per_second": 17.32, | |
| "eval_steps_per_second": 3.471, | |
| "step": 2406 | |
| }, | |
| { | |
| "epoch": 12.019950124688279, | |
| "grad_norm": 1.5172271728515625, | |
| "learning_rate": 3.94e-06, | |
| "loss": 0.437, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 12.069825436408978, | |
| "grad_norm": 1.4542344808578491, | |
| "learning_rate": 3.873333333333333e-06, | |
| "loss": 0.4314, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 12.119700748129675, | |
| "grad_norm": 1.4818074703216553, | |
| "learning_rate": 3.806666666666667e-06, | |
| "loss": 0.4184, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 12.169576059850375, | |
| "grad_norm": 1.4975398778915405, | |
| "learning_rate": 3.74e-06, | |
| "loss": 0.4087, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 12.219451371571072, | |
| "grad_norm": 1.3974961042404175, | |
| "learning_rate": 3.673333333333334e-06, | |
| "loss": 0.4135, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 12.269326683291771, | |
| "grad_norm": 1.6019673347473145, | |
| "learning_rate": 3.606666666666667e-06, | |
| "loss": 0.4238, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 12.319201995012468, | |
| "grad_norm": 1.7037951946258545, | |
| "learning_rate": 3.54e-06, | |
| "loss": 0.4218, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 12.369077306733168, | |
| "grad_norm": 1.5602372884750366, | |
| "learning_rate": 3.4733333333333337e-06, | |
| "loss": 0.4192, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 12.418952618453865, | |
| "grad_norm": 1.391041874885559, | |
| "learning_rate": 3.406666666666667e-06, | |
| "loss": 0.414, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 12.468827930174564, | |
| "grad_norm": 1.5659008026123047, | |
| "learning_rate": 3.3400000000000006e-06, | |
| "loss": 0.4251, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 12.518703241895262, | |
| "grad_norm": 1.4149389266967773, | |
| "learning_rate": 3.2733333333333335e-06, | |
| "loss": 0.4299, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 12.56857855361596, | |
| "grad_norm": 1.5269657373428345, | |
| "learning_rate": 3.2066666666666667e-06, | |
| "loss": 0.4355, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 12.618453865336658, | |
| "grad_norm": 1.6707123517990112, | |
| "learning_rate": 3.1400000000000004e-06, | |
| "loss": 0.4282, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 12.668329177057357, | |
| "grad_norm": 1.3647090196609497, | |
| "learning_rate": 3.0733333333333337e-06, | |
| "loss": 0.3994, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 12.718204488778055, | |
| "grad_norm": 1.4243894815444946, | |
| "learning_rate": 3.0066666666666674e-06, | |
| "loss": 0.4181, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 12.768079800498754, | |
| "grad_norm": 1.3579431772232056, | |
| "learning_rate": 2.9400000000000002e-06, | |
| "loss": 0.4251, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 12.817955112219451, | |
| "grad_norm": 1.6759490966796875, | |
| "learning_rate": 2.8733333333333335e-06, | |
| "loss": 0.4143, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 12.86783042394015, | |
| "grad_norm": 1.5581449270248413, | |
| "learning_rate": 2.806666666666667e-06, | |
| "loss": 0.4083, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 12.917705735660848, | |
| "grad_norm": 1.607188105583191, | |
| "learning_rate": 2.7400000000000004e-06, | |
| "loss": 0.4236, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 12.967581047381547, | |
| "grad_norm": 1.3592510223388672, | |
| "learning_rate": 2.6733333333333333e-06, | |
| "loss": 0.4108, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 12.997506234413965, | |
| "eval_loss": 0.44020339846611023, | |
| "eval_runtime": 57.8997, | |
| "eval_samples_per_second": 17.323, | |
| "eval_steps_per_second": 3.472, | |
| "step": 2606 | |
| }, | |
| { | |
| "epoch": 13.017456359102244, | |
| "grad_norm": 1.461461067199707, | |
| "learning_rate": 2.606666666666667e-06, | |
| "loss": 0.4439, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 13.067331670822943, | |
| "grad_norm": 1.40589439868927, | |
| "learning_rate": 2.5400000000000002e-06, | |
| "loss": 0.4057, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 13.11720698254364, | |
| "grad_norm": 1.665216088294983, | |
| "learning_rate": 2.4733333333333335e-06, | |
| "loss": 0.4053, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 13.16708229426434, | |
| "grad_norm": 1.4636025428771973, | |
| "learning_rate": 2.4066666666666668e-06, | |
| "loss": 0.4199, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 13.216957605985037, | |
| "grad_norm": 1.4638257026672363, | |
| "learning_rate": 2.3400000000000005e-06, | |
| "loss": 0.4062, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 13.266832917705736, | |
| "grad_norm": 1.4565849304199219, | |
| "learning_rate": 2.2733333333333333e-06, | |
| "loss": 0.4354, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 13.316708229426434, | |
| "grad_norm": 1.4819647073745728, | |
| "learning_rate": 2.206666666666667e-06, | |
| "loss": 0.4088, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 13.366583541147133, | |
| "grad_norm": 1.5023897886276245, | |
| "learning_rate": 2.1400000000000003e-06, | |
| "loss": 0.4313, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 13.41645885286783, | |
| "grad_norm": 1.4261906147003174, | |
| "learning_rate": 2.0733333333333335e-06, | |
| "loss": 0.4179, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 13.46633416458853, | |
| "grad_norm": 1.6513773202896118, | |
| "learning_rate": 2.006666666666667e-06, | |
| "loss": 0.4341, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 13.516209476309227, | |
| "grad_norm": 1.6153149604797363, | |
| "learning_rate": 1.94e-06, | |
| "loss": 0.4231, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 13.566084788029926, | |
| "grad_norm": 1.6202324628829956, | |
| "learning_rate": 1.8733333333333333e-06, | |
| "loss": 0.4173, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 13.615960099750623, | |
| "grad_norm": 1.2559431791305542, | |
| "learning_rate": 1.8066666666666668e-06, | |
| "loss": 0.4238, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 13.665835411471322, | |
| "grad_norm": 1.3010227680206299, | |
| "learning_rate": 1.74e-06, | |
| "loss": 0.4287, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 13.71571072319202, | |
| "grad_norm": 1.432409644126892, | |
| "learning_rate": 1.6733333333333335e-06, | |
| "loss": 0.4143, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 13.765586034912719, | |
| "grad_norm": 1.4686477184295654, | |
| "learning_rate": 1.606666666666667e-06, | |
| "loss": 0.4192, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 13.815461346633416, | |
| "grad_norm": 1.526962161064148, | |
| "learning_rate": 1.54e-06, | |
| "loss": 0.4199, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 13.865336658354115, | |
| "grad_norm": 1.5790767669677734, | |
| "learning_rate": 1.4733333333333336e-06, | |
| "loss": 0.4089, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 13.915211970074813, | |
| "grad_norm": 1.4289913177490234, | |
| "learning_rate": 1.4066666666666668e-06, | |
| "loss": 0.4195, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 13.965087281795512, | |
| "grad_norm": 1.613978624343872, | |
| "learning_rate": 1.34e-06, | |
| "loss": 0.4279, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.439765065908432, | |
| "eval_runtime": 57.9105, | |
| "eval_samples_per_second": 17.32, | |
| "eval_steps_per_second": 3.471, | |
| "step": 2807 | |
| }, | |
| { | |
| "epoch": 14.01496259351621, | |
| "grad_norm": 1.4722168445587158, | |
| "learning_rate": 1.2733333333333334e-06, | |
| "loss": 0.445, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 14.064837905236908, | |
| "grad_norm": 1.6725043058395386, | |
| "learning_rate": 1.2066666666666668e-06, | |
| "loss": 0.4313, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 14.114713216957606, | |
| "grad_norm": 1.4227081537246704, | |
| "learning_rate": 1.14e-06, | |
| "loss": 0.4181, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 14.164588528678305, | |
| "grad_norm": 1.5610967874526978, | |
| "learning_rate": 1.0733333333333334e-06, | |
| "loss": 0.4229, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 14.214463840399002, | |
| "grad_norm": 1.520051121711731, | |
| "learning_rate": 1.0066666666666668e-06, | |
| "loss": 0.4301, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 14.264339152119701, | |
| "grad_norm": 1.4826945066452026, | |
| "learning_rate": 9.400000000000001e-07, | |
| "loss": 0.443, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 14.314214463840399, | |
| "grad_norm": 1.6496617794036865, | |
| "learning_rate": 8.733333333333334e-07, | |
| "loss": 0.4109, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 14.364089775561098, | |
| "grad_norm": 1.472607135772705, | |
| "learning_rate": 8.066666666666667e-07, | |
| "loss": 0.4075, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 14.413965087281795, | |
| "grad_norm": 1.4754953384399414, | |
| "learning_rate": 7.4e-07, | |
| "loss": 0.4257, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 14.463840399002494, | |
| "grad_norm": 1.6782726049423218, | |
| "learning_rate": 6.733333333333334e-07, | |
| "loss": 0.4099, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 14.513715710723192, | |
| "grad_norm": 1.4635963439941406, | |
| "learning_rate": 6.066666666666668e-07, | |
| "loss": 0.3977, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 14.563591022443891, | |
| "grad_norm": 1.5924144983291626, | |
| "learning_rate": 5.4e-07, | |
| "loss": 0.4181, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 14.613466334164588, | |
| "grad_norm": 1.346475601196289, | |
| "learning_rate": 4.7333333333333334e-07, | |
| "loss": 0.4132, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 14.663341645885287, | |
| "grad_norm": 1.4001176357269287, | |
| "learning_rate": 4.0666666666666666e-07, | |
| "loss": 0.4007, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 14.713216957605985, | |
| "grad_norm": 1.6243798732757568, | |
| "learning_rate": 3.4000000000000003e-07, | |
| "loss": 0.4332, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 14.763092269326684, | |
| "grad_norm": 1.5413304567337036, | |
| "learning_rate": 2.7333333333333335e-07, | |
| "loss": 0.4083, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 14.812967581047381, | |
| "grad_norm": 1.4332594871520996, | |
| "learning_rate": 2.066666666666667e-07, | |
| "loss": 0.4206, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 14.86284289276808, | |
| "grad_norm": 1.4844541549682617, | |
| "learning_rate": 1.4e-07, | |
| "loss": 0.4285, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 14.912718204488778, | |
| "grad_norm": 1.471591830253601, | |
| "learning_rate": 7.333333333333334e-08, | |
| "loss": 0.4118, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 14.962593516209477, | |
| "grad_norm": 1.3903006315231323, | |
| "learning_rate": 6.666666666666667e-09, | |
| "loss": 0.4145, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.48818315264e+16, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |