{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.308707124010554, "eval_steps": 500, "global_step": 3500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.989006156552331e-05, "loss": 1.8212, "step": 10 }, { "epoch": 0.01, "learning_rate": 4.978012313104662e-05, "loss": 1.7676, "step": 20 }, { "epoch": 0.02, "learning_rate": 4.967018469656992e-05, "loss": 1.7575, "step": 30 }, { "epoch": 0.03, "learning_rate": 4.956024626209323e-05, "loss": 1.6747, "step": 40 }, { "epoch": 0.03, "learning_rate": 4.9450307827616535e-05, "loss": 1.5765, "step": 50 }, { "epoch": 0.04, "learning_rate": 4.934036939313985e-05, "loss": 1.6145, "step": 60 }, { "epoch": 0.05, "learning_rate": 4.9230430958663146e-05, "loss": 1.5378, "step": 70 }, { "epoch": 0.05, "learning_rate": 4.912049252418646e-05, "loss": 1.6184, "step": 80 }, { "epoch": 0.06, "learning_rate": 4.901055408970976e-05, "loss": 1.5486, "step": 90 }, { "epoch": 0.07, "learning_rate": 4.8900615655233075e-05, "loss": 1.5721, "step": 100 }, { "epoch": 0.07, "learning_rate": 4.879067722075638e-05, "loss": 1.5253, "step": 110 }, { "epoch": 0.08, "learning_rate": 4.8680738786279686e-05, "loss": 1.521, "step": 120 }, { "epoch": 0.09, "learning_rate": 4.857080035180299e-05, "loss": 1.5171, "step": 130 }, { "epoch": 0.09, "learning_rate": 4.84608619173263e-05, "loss": 1.5259, "step": 140 }, { "epoch": 0.1, "learning_rate": 4.835092348284961e-05, "loss": 1.5831, "step": 150 }, { "epoch": 0.11, "learning_rate": 4.824098504837291e-05, "loss": 1.5398, "step": 160 }, { "epoch": 0.11, "learning_rate": 4.813104661389622e-05, "loss": 1.5684, "step": 170 }, { "epoch": 0.12, "learning_rate": 4.802110817941953e-05, "loss": 1.5382, "step": 180 }, { "epoch": 0.13, "learning_rate": 4.7911169744942836e-05, "loss": 1.5588, "step": 190 }, { "epoch": 0.13, "learning_rate": 4.780123131046614e-05, "loss": 1.5192, "step": 200 }, { "epoch": 0.14, "learning_rate": 4.7691292875989446e-05, "loss": 1.6004, "step": 210 }, { "epoch": 0.15, "learning_rate": 4.758135444151275e-05, "loss": 1.5603, "step": 220 }, { "epoch": 0.15, "learning_rate": 4.7471416007036063e-05, "loss": 1.5532, "step": 230 }, { "epoch": 0.16, "learning_rate": 4.736147757255937e-05, "loss": 1.5632, "step": 240 }, { "epoch": 0.16, "learning_rate": 4.7251539138082674e-05, "loss": 1.5598, "step": 250 }, { "epoch": 0.17, "learning_rate": 4.714160070360598e-05, "loss": 1.54, "step": 260 }, { "epoch": 0.18, "learning_rate": 4.703166226912929e-05, "loss": 1.4843, "step": 270 }, { "epoch": 0.18, "learning_rate": 4.6921723834652596e-05, "loss": 1.5328, "step": 280 }, { "epoch": 0.19, "learning_rate": 4.681178540017591e-05, "loss": 1.5677, "step": 290 }, { "epoch": 0.2, "learning_rate": 4.670184696569921e-05, "loss": 1.5629, "step": 300 }, { "epoch": 0.2, "learning_rate": 4.659190853122252e-05, "loss": 1.5426, "step": 310 }, { "epoch": 0.21, "learning_rate": 4.6481970096745824e-05, "loss": 1.4997, "step": 320 }, { "epoch": 0.22, "learning_rate": 4.6372031662269136e-05, "loss": 1.5409, "step": 330 }, { "epoch": 0.22, "learning_rate": 4.6262093227792435e-05, "loss": 1.5269, "step": 340 }, { "epoch": 0.23, "learning_rate": 4.615215479331575e-05, "loss": 1.5079, "step": 350 }, { "epoch": 0.24, "learning_rate": 4.604221635883905e-05, "loss": 1.5031, "step": 360 }, { "epoch": 0.24, "learning_rate": 4.593227792436236e-05, "loss": 1.5412, "step": 370 }, { "epoch": 0.25, "learning_rate": 4.582233948988567e-05, "loss": 1.5096, "step": 380 }, { "epoch": 0.26, "learning_rate": 4.5712401055408974e-05, "loss": 1.5605, "step": 390 }, { "epoch": 0.26, "learning_rate": 4.560246262093228e-05, "loss": 1.5628, "step": 400 }, { "epoch": 0.27, "learning_rate": 4.5492524186455585e-05, "loss": 1.5396, "step": 410 }, { "epoch": 0.28, "learning_rate": 4.53825857519789e-05, "loss": 1.4757, "step": 420 }, { "epoch": 0.28, "learning_rate": 4.52726473175022e-05, "loss": 1.5366, "step": 430 }, { "epoch": 0.29, "learning_rate": 4.516270888302551e-05, "loss": 1.5037, "step": 440 }, { "epoch": 0.3, "learning_rate": 4.505277044854881e-05, "loss": 1.5336, "step": 450 }, { "epoch": 0.3, "learning_rate": 4.4942832014072125e-05, "loss": 1.5067, "step": 460 }, { "epoch": 0.31, "learning_rate": 4.483289357959543e-05, "loss": 1.4911, "step": 470 }, { "epoch": 0.32, "learning_rate": 4.4722955145118735e-05, "loss": 1.4891, "step": 480 }, { "epoch": 0.32, "learning_rate": 4.461301671064204e-05, "loss": 1.5337, "step": 490 }, { "epoch": 0.33, "learning_rate": 4.450307827616535e-05, "loss": 1.5254, "step": 500 }, { "epoch": 0.34, "learning_rate": 4.439313984168866e-05, "loss": 1.537, "step": 510 }, { "epoch": 0.34, "learning_rate": 4.428320140721196e-05, "loss": 1.4969, "step": 520 }, { "epoch": 0.35, "learning_rate": 4.417326297273527e-05, "loss": 1.4863, "step": 530 }, { "epoch": 0.36, "learning_rate": 4.406332453825858e-05, "loss": 1.5168, "step": 540 }, { "epoch": 0.36, "learning_rate": 4.3953386103781885e-05, "loss": 1.5242, "step": 550 }, { "epoch": 0.37, "learning_rate": 4.384344766930519e-05, "loss": 1.5307, "step": 560 }, { "epoch": 0.38, "learning_rate": 4.3733509234828496e-05, "loss": 1.5087, "step": 570 }, { "epoch": 0.38, "learning_rate": 4.36235708003518e-05, "loss": 1.5043, "step": 580 }, { "epoch": 0.39, "learning_rate": 4.351363236587511e-05, "loss": 1.4933, "step": 590 }, { "epoch": 0.4, "learning_rate": 4.340369393139842e-05, "loss": 1.5111, "step": 600 }, { "epoch": 0.4, "learning_rate": 4.329375549692173e-05, "loss": 1.4897, "step": 610 }, { "epoch": 0.41, "learning_rate": 4.318381706244503e-05, "loss": 1.502, "step": 620 }, { "epoch": 0.42, "learning_rate": 4.307387862796834e-05, "loss": 1.5016, "step": 630 }, { "epoch": 0.42, "learning_rate": 4.2963940193491646e-05, "loss": 1.5328, "step": 640 }, { "epoch": 0.43, "learning_rate": 4.285400175901496e-05, "loss": 1.5442, "step": 650 }, { "epoch": 0.44, "learning_rate": 4.2744063324538256e-05, "loss": 1.527, "step": 660 }, { "epoch": 0.44, "learning_rate": 4.263412489006157e-05, "loss": 1.5327, "step": 670 }, { "epoch": 0.45, "learning_rate": 4.2524186455584874e-05, "loss": 1.5571, "step": 680 }, { "epoch": 0.46, "learning_rate": 4.2414248021108186e-05, "loss": 1.5297, "step": 690 }, { "epoch": 0.46, "learning_rate": 4.230430958663149e-05, "loss": 1.4894, "step": 700 }, { "epoch": 0.47, "learning_rate": 4.2194371152154796e-05, "loss": 1.5008, "step": 710 }, { "epoch": 0.47, "learning_rate": 4.20844327176781e-05, "loss": 1.5135, "step": 720 }, { "epoch": 0.48, "learning_rate": 4.1974494283201407e-05, "loss": 1.5081, "step": 730 }, { "epoch": 0.49, "learning_rate": 4.186455584872472e-05, "loss": 1.5003, "step": 740 }, { "epoch": 0.49, "learning_rate": 4.1754617414248024e-05, "loss": 1.5154, "step": 750 }, { "epoch": 0.5, "learning_rate": 4.164467897977133e-05, "loss": 1.4863, "step": 760 }, { "epoch": 0.51, "learning_rate": 4.1534740545294634e-05, "loss": 1.5193, "step": 770 }, { "epoch": 0.51, "learning_rate": 4.1424802110817946e-05, "loss": 1.4906, "step": 780 }, { "epoch": 0.52, "learning_rate": 4.131486367634125e-05, "loss": 1.5434, "step": 790 }, { "epoch": 0.53, "learning_rate": 4.120492524186456e-05, "loss": 1.5458, "step": 800 }, { "epoch": 0.53, "learning_rate": 4.109498680738786e-05, "loss": 1.5612, "step": 810 }, { "epoch": 0.54, "learning_rate": 4.0985048372911174e-05, "loss": 1.5537, "step": 820 }, { "epoch": 0.55, "learning_rate": 4.087510993843448e-05, "loss": 1.5206, "step": 830 }, { "epoch": 0.55, "learning_rate": 4.0765171503957784e-05, "loss": 1.492, "step": 840 }, { "epoch": 0.56, "learning_rate": 4.065523306948109e-05, "loss": 1.4721, "step": 850 }, { "epoch": 0.57, "learning_rate": 4.05452946350044e-05, "loss": 1.5354, "step": 860 }, { "epoch": 0.57, "learning_rate": 4.043535620052771e-05, "loss": 1.5165, "step": 870 }, { "epoch": 0.58, "learning_rate": 4.032541776605102e-05, "loss": 1.5407, "step": 880 }, { "epoch": 0.59, "learning_rate": 4.021547933157432e-05, "loss": 1.5151, "step": 890 }, { "epoch": 0.59, "learning_rate": 4.010554089709763e-05, "loss": 1.5483, "step": 900 }, { "epoch": 0.6, "learning_rate": 3.9995602462620935e-05, "loss": 1.4871, "step": 910 }, { "epoch": 0.61, "learning_rate": 3.988566402814424e-05, "loss": 1.5558, "step": 920 }, { "epoch": 0.61, "learning_rate": 3.9775725593667545e-05, "loss": 1.5084, "step": 930 }, { "epoch": 0.62, "learning_rate": 3.966578715919085e-05, "loss": 1.509, "step": 940 }, { "epoch": 0.63, "learning_rate": 3.955584872471416e-05, "loss": 1.5116, "step": 950 }, { "epoch": 0.63, "learning_rate": 3.944591029023747e-05, "loss": 1.482, "step": 960 }, { "epoch": 0.64, "learning_rate": 3.933597185576078e-05, "loss": 1.4935, "step": 970 }, { "epoch": 0.65, "learning_rate": 3.922603342128408e-05, "loss": 1.5034, "step": 980 }, { "epoch": 0.65, "learning_rate": 3.911609498680739e-05, "loss": 1.5448, "step": 990 }, { "epoch": 0.66, "learning_rate": 3.9006156552330695e-05, "loss": 1.481, "step": 1000 }, { "epoch": 0.67, "learning_rate": 3.889621811785401e-05, "loss": 1.5543, "step": 1010 }, { "epoch": 0.67, "learning_rate": 3.8786279683377306e-05, "loss": 1.5157, "step": 1020 }, { "epoch": 0.68, "learning_rate": 3.867634124890062e-05, "loss": 1.5021, "step": 1030 }, { "epoch": 0.69, "learning_rate": 3.856640281442392e-05, "loss": 1.531, "step": 1040 }, { "epoch": 0.69, "learning_rate": 3.8456464379947235e-05, "loss": 1.5539, "step": 1050 }, { "epoch": 0.7, "learning_rate": 3.834652594547054e-05, "loss": 1.5171, "step": 1060 }, { "epoch": 0.71, "learning_rate": 3.8236587510993846e-05, "loss": 1.4989, "step": 1070 }, { "epoch": 0.71, "learning_rate": 3.812664907651715e-05, "loss": 1.5138, "step": 1080 }, { "epoch": 0.72, "learning_rate": 3.801671064204046e-05, "loss": 1.5117, "step": 1090 }, { "epoch": 0.73, "learning_rate": 3.790677220756377e-05, "loss": 1.5541, "step": 1100 }, { "epoch": 0.73, "learning_rate": 3.779683377308707e-05, "loss": 1.5125, "step": 1110 }, { "epoch": 0.74, "learning_rate": 3.768689533861038e-05, "loss": 1.5128, "step": 1120 }, { "epoch": 0.75, "learning_rate": 3.7576956904133684e-05, "loss": 1.5147, "step": 1130 }, { "epoch": 0.75, "learning_rate": 3.7467018469656996e-05, "loss": 1.5715, "step": 1140 }, { "epoch": 0.76, "learning_rate": 3.73570800351803e-05, "loss": 1.5225, "step": 1150 }, { "epoch": 0.77, "learning_rate": 3.7247141600703606e-05, "loss": 1.4698, "step": 1160 }, { "epoch": 0.77, "learning_rate": 3.713720316622691e-05, "loss": 1.555, "step": 1170 }, { "epoch": 0.78, "learning_rate": 3.7027264731750223e-05, "loss": 1.5199, "step": 1180 }, { "epoch": 0.78, "learning_rate": 3.691732629727353e-05, "loss": 1.5247, "step": 1190 }, { "epoch": 0.79, "learning_rate": 3.680738786279684e-05, "loss": 1.526, "step": 1200 }, { "epoch": 0.8, "learning_rate": 3.669744942832014e-05, "loss": 1.5052, "step": 1210 }, { "epoch": 0.8, "learning_rate": 3.658751099384345e-05, "loss": 1.538, "step": 1220 }, { "epoch": 0.81, "learning_rate": 3.6477572559366756e-05, "loss": 1.556, "step": 1230 }, { "epoch": 0.82, "learning_rate": 3.636763412489007e-05, "loss": 1.5293, "step": 1240 }, { "epoch": 0.82, "learning_rate": 3.625769569041337e-05, "loss": 1.5147, "step": 1250 }, { "epoch": 0.83, "learning_rate": 3.614775725593668e-05, "loss": 1.5624, "step": 1260 }, { "epoch": 0.84, "learning_rate": 3.6037818821459984e-05, "loss": 1.5602, "step": 1270 }, { "epoch": 0.84, "learning_rate": 3.592788038698329e-05, "loss": 1.538, "step": 1280 }, { "epoch": 0.85, "learning_rate": 3.58179419525066e-05, "loss": 1.4977, "step": 1290 }, { "epoch": 0.86, "learning_rate": 3.5708003518029907e-05, "loss": 1.4757, "step": 1300 }, { "epoch": 0.86, "learning_rate": 3.559806508355321e-05, "loss": 1.4651, "step": 1310 }, { "epoch": 0.87, "learning_rate": 3.548812664907652e-05, "loss": 1.5383, "step": 1320 }, { "epoch": 0.88, "learning_rate": 3.537818821459983e-05, "loss": 1.4823, "step": 1330 }, { "epoch": 0.88, "learning_rate": 3.526824978012313e-05, "loss": 1.5179, "step": 1340 }, { "epoch": 0.89, "learning_rate": 3.515831134564644e-05, "loss": 1.5145, "step": 1350 }, { "epoch": 0.9, "learning_rate": 3.5048372911169745e-05, "loss": 1.5376, "step": 1360 }, { "epoch": 0.9, "learning_rate": 3.493843447669306e-05, "loss": 1.5336, "step": 1370 }, { "epoch": 0.91, "learning_rate": 3.482849604221636e-05, "loss": 1.5321, "step": 1380 }, { "epoch": 0.92, "learning_rate": 3.471855760773967e-05, "loss": 1.5058, "step": 1390 }, { "epoch": 0.92, "learning_rate": 3.460861917326297e-05, "loss": 1.5246, "step": 1400 }, { "epoch": 0.93, "learning_rate": 3.4498680738786285e-05, "loss": 1.5131, "step": 1410 }, { "epoch": 0.94, "learning_rate": 3.438874230430959e-05, "loss": 1.5222, "step": 1420 }, { "epoch": 0.94, "learning_rate": 3.4278803869832895e-05, "loss": 1.5237, "step": 1430 }, { "epoch": 0.95, "learning_rate": 3.41688654353562e-05, "loss": 1.4969, "step": 1440 }, { "epoch": 0.96, "learning_rate": 3.405892700087951e-05, "loss": 1.5395, "step": 1450 }, { "epoch": 0.96, "learning_rate": 3.394898856640282e-05, "loss": 1.5556, "step": 1460 }, { "epoch": 0.97, "learning_rate": 3.383905013192612e-05, "loss": 1.4817, "step": 1470 }, { "epoch": 0.98, "learning_rate": 3.372911169744943e-05, "loss": 1.4663, "step": 1480 }, { "epoch": 0.98, "learning_rate": 3.361917326297273e-05, "loss": 1.507, "step": 1490 }, { "epoch": 0.99, "learning_rate": 3.3509234828496045e-05, "loss": 1.5354, "step": 1500 }, { "epoch": 1.0, "learning_rate": 3.339929639401935e-05, "loss": 1.535, "step": 1510 }, { "epoch": 1.0, "learning_rate": 3.3289357959542656e-05, "loss": 1.4749, "step": 1520 }, { "epoch": 1.01, "learning_rate": 3.317941952506596e-05, "loss": 1.5225, "step": 1530 }, { "epoch": 1.02, "learning_rate": 3.306948109058927e-05, "loss": 1.4958, "step": 1540 }, { "epoch": 1.02, "learning_rate": 3.295954265611258e-05, "loss": 1.5231, "step": 1550 }, { "epoch": 1.03, "learning_rate": 3.284960422163589e-05, "loss": 1.5163, "step": 1560 }, { "epoch": 1.04, "learning_rate": 3.273966578715919e-05, "loss": 1.511, "step": 1570 }, { "epoch": 1.04, "learning_rate": 3.26297273526825e-05, "loss": 1.5182, "step": 1580 }, { "epoch": 1.05, "learning_rate": 3.2519788918205806e-05, "loss": 1.4787, "step": 1590 }, { "epoch": 1.06, "learning_rate": 3.240985048372912e-05, "loss": 1.5121, "step": 1600 }, { "epoch": 1.06, "learning_rate": 3.2299912049252416e-05, "loss": 1.528, "step": 1610 }, { "epoch": 1.07, "learning_rate": 3.218997361477573e-05, "loss": 1.5127, "step": 1620 }, { "epoch": 1.08, "learning_rate": 3.2080035180299034e-05, "loss": 1.515, "step": 1630 }, { "epoch": 1.08, "learning_rate": 3.197009674582234e-05, "loss": 1.5095, "step": 1640 }, { "epoch": 1.09, "learning_rate": 3.186015831134565e-05, "loss": 1.4925, "step": 1650 }, { "epoch": 1.09, "learning_rate": 3.1750219876868956e-05, "loss": 1.5544, "step": 1660 }, { "epoch": 1.1, "learning_rate": 3.164028144239226e-05, "loss": 1.5112, "step": 1670 }, { "epoch": 1.11, "learning_rate": 3.1530343007915567e-05, "loss": 1.5813, "step": 1680 }, { "epoch": 1.11, "learning_rate": 3.142040457343888e-05, "loss": 1.4828, "step": 1690 }, { "epoch": 1.12, "learning_rate": 3.131046613896218e-05, "loss": 1.4995, "step": 1700 }, { "epoch": 1.13, "learning_rate": 3.120052770448549e-05, "loss": 1.4446, "step": 1710 }, { "epoch": 1.13, "learning_rate": 3.1090589270008794e-05, "loss": 1.5179, "step": 1720 }, { "epoch": 1.14, "learning_rate": 3.0980650835532106e-05, "loss": 1.492, "step": 1730 }, { "epoch": 1.15, "learning_rate": 3.087071240105541e-05, "loss": 1.5156, "step": 1740 }, { "epoch": 1.15, "learning_rate": 3.076077396657872e-05, "loss": 1.5034, "step": 1750 }, { "epoch": 1.16, "learning_rate": 3.065083553210202e-05, "loss": 1.545, "step": 1760 }, { "epoch": 1.17, "learning_rate": 3.0540897097625334e-05, "loss": 1.488, "step": 1770 }, { "epoch": 1.17, "learning_rate": 3.043095866314864e-05, "loss": 1.5143, "step": 1780 }, { "epoch": 1.18, "learning_rate": 3.032102022867194e-05, "loss": 1.4847, "step": 1790 }, { "epoch": 1.19, "learning_rate": 3.021108179419525e-05, "loss": 1.4672, "step": 1800 }, { "epoch": 1.19, "learning_rate": 3.010114335971856e-05, "loss": 1.519, "step": 1810 }, { "epoch": 1.2, "learning_rate": 2.9991204925241867e-05, "loss": 1.4834, "step": 1820 }, { "epoch": 1.21, "learning_rate": 2.9881266490765176e-05, "loss": 1.5087, "step": 1830 }, { "epoch": 1.21, "learning_rate": 2.9771328056288477e-05, "loss": 1.5183, "step": 1840 }, { "epoch": 1.22, "learning_rate": 2.9661389621811786e-05, "loss": 1.5511, "step": 1850 }, { "epoch": 1.23, "learning_rate": 2.9551451187335095e-05, "loss": 1.5068, "step": 1860 }, { "epoch": 1.23, "learning_rate": 2.9441512752858403e-05, "loss": 1.5117, "step": 1870 }, { "epoch": 1.24, "learning_rate": 2.9331574318381705e-05, "loss": 1.5237, "step": 1880 }, { "epoch": 1.25, "learning_rate": 2.9221635883905014e-05, "loss": 1.4935, "step": 1890 }, { "epoch": 1.25, "learning_rate": 2.9111697449428322e-05, "loss": 1.4949, "step": 1900 }, { "epoch": 1.26, "learning_rate": 2.900175901495163e-05, "loss": 1.5423, "step": 1910 }, { "epoch": 1.27, "learning_rate": 2.8891820580474936e-05, "loss": 1.5472, "step": 1920 }, { "epoch": 1.27, "learning_rate": 2.878188214599824e-05, "loss": 1.4831, "step": 1930 }, { "epoch": 1.28, "learning_rate": 2.8671943711521547e-05, "loss": 1.5156, "step": 1940 }, { "epoch": 1.29, "learning_rate": 2.8562005277044855e-05, "loss": 1.4705, "step": 1950 }, { "epoch": 1.29, "learning_rate": 2.8452066842568164e-05, "loss": 1.5085, "step": 1960 }, { "epoch": 1.3, "learning_rate": 2.8342128408091473e-05, "loss": 1.5012, "step": 1970 }, { "epoch": 1.31, "learning_rate": 2.8232189973614774e-05, "loss": 1.5566, "step": 1980 }, { "epoch": 1.31, "learning_rate": 2.8122251539138083e-05, "loss": 1.464, "step": 1990 }, { "epoch": 1.32, "learning_rate": 2.801231310466139e-05, "loss": 1.5347, "step": 2000 }, { "epoch": 1.33, "learning_rate": 2.79023746701847e-05, "loss": 1.5288, "step": 2010 }, { "epoch": 1.33, "learning_rate": 2.7792436235708002e-05, "loss": 1.5391, "step": 2020 }, { "epoch": 1.34, "learning_rate": 2.768249780123131e-05, "loss": 1.5014, "step": 2030 }, { "epoch": 1.35, "learning_rate": 2.757255936675462e-05, "loss": 1.4414, "step": 2040 }, { "epoch": 1.35, "learning_rate": 2.7462620932277928e-05, "loss": 1.548, "step": 2050 }, { "epoch": 1.36, "learning_rate": 2.7352682497801237e-05, "loss": 1.5047, "step": 2060 }, { "epoch": 1.37, "learning_rate": 2.724274406332454e-05, "loss": 1.5444, "step": 2070 }, { "epoch": 1.37, "learning_rate": 2.7132805628847847e-05, "loss": 1.4671, "step": 2080 }, { "epoch": 1.38, "learning_rate": 2.7022867194371156e-05, "loss": 1.4547, "step": 2090 }, { "epoch": 1.39, "learning_rate": 2.691292875989446e-05, "loss": 1.5203, "step": 2100 }, { "epoch": 1.39, "learning_rate": 2.6802990325417766e-05, "loss": 1.5027, "step": 2110 }, { "epoch": 1.4, "learning_rate": 2.6693051890941075e-05, "loss": 1.532, "step": 2120 }, { "epoch": 1.41, "learning_rate": 2.658311345646438e-05, "loss": 1.4929, "step": 2130 }, { "epoch": 1.41, "learning_rate": 2.647317502198769e-05, "loss": 1.4825, "step": 2140 }, { "epoch": 1.42, "learning_rate": 2.6363236587510997e-05, "loss": 1.4972, "step": 2150 }, { "epoch": 1.42, "learning_rate": 2.62532981530343e-05, "loss": 1.5265, "step": 2160 }, { "epoch": 1.43, "learning_rate": 2.6143359718557608e-05, "loss": 1.5471, "step": 2170 }, { "epoch": 1.44, "learning_rate": 2.6033421284080916e-05, "loss": 1.5148, "step": 2180 }, { "epoch": 1.44, "learning_rate": 2.5923482849604225e-05, "loss": 1.476, "step": 2190 }, { "epoch": 1.45, "learning_rate": 2.5813544415127527e-05, "loss": 1.5239, "step": 2200 }, { "epoch": 1.46, "learning_rate": 2.5703605980650835e-05, "loss": 1.5092, "step": 2210 }, { "epoch": 1.46, "learning_rate": 2.5593667546174144e-05, "loss": 1.5069, "step": 2220 }, { "epoch": 1.47, "learning_rate": 2.5483729111697453e-05, "loss": 1.5178, "step": 2230 }, { "epoch": 1.48, "learning_rate": 2.537379067722076e-05, "loss": 1.5253, "step": 2240 }, { "epoch": 1.48, "learning_rate": 2.5263852242744063e-05, "loss": 1.5163, "step": 2250 }, { "epoch": 1.49, "learning_rate": 2.5153913808267372e-05, "loss": 1.5331, "step": 2260 }, { "epoch": 1.5, "learning_rate": 2.504397537379068e-05, "loss": 1.5488, "step": 2270 }, { "epoch": 1.5, "learning_rate": 2.4934036939313986e-05, "loss": 1.5243, "step": 2280 }, { "epoch": 1.51, "learning_rate": 2.482409850483729e-05, "loss": 1.4977, "step": 2290 }, { "epoch": 1.52, "learning_rate": 2.47141600703606e-05, "loss": 1.4903, "step": 2300 }, { "epoch": 1.52, "learning_rate": 2.4604221635883905e-05, "loss": 1.5155, "step": 2310 }, { "epoch": 1.53, "learning_rate": 2.4494283201407213e-05, "loss": 1.5496, "step": 2320 }, { "epoch": 1.54, "learning_rate": 2.438434476693052e-05, "loss": 1.5006, "step": 2330 }, { "epoch": 1.54, "learning_rate": 2.4274406332453827e-05, "loss": 1.5028, "step": 2340 }, { "epoch": 1.55, "learning_rate": 2.4164467897977133e-05, "loss": 1.5113, "step": 2350 }, { "epoch": 1.56, "learning_rate": 2.405452946350044e-05, "loss": 1.5134, "step": 2360 }, { "epoch": 1.56, "learning_rate": 2.3944591029023746e-05, "loss": 1.5285, "step": 2370 }, { "epoch": 1.57, "learning_rate": 2.3834652594547055e-05, "loss": 1.5204, "step": 2380 }, { "epoch": 1.58, "learning_rate": 2.372471416007036e-05, "loss": 1.5241, "step": 2390 }, { "epoch": 1.58, "learning_rate": 2.361477572559367e-05, "loss": 1.5429, "step": 2400 }, { "epoch": 1.59, "learning_rate": 2.3504837291116977e-05, "loss": 1.5294, "step": 2410 }, { "epoch": 1.6, "learning_rate": 2.3394898856640283e-05, "loss": 1.4897, "step": 2420 }, { "epoch": 1.6, "learning_rate": 2.328496042216359e-05, "loss": 1.4645, "step": 2430 }, { "epoch": 1.61, "learning_rate": 2.3175021987686897e-05, "loss": 1.5092, "step": 2440 }, { "epoch": 1.62, "learning_rate": 2.3065083553210205e-05, "loss": 1.4895, "step": 2450 }, { "epoch": 1.62, "learning_rate": 2.295514511873351e-05, "loss": 1.4866, "step": 2460 }, { "epoch": 1.63, "learning_rate": 2.284520668425682e-05, "loss": 1.4851, "step": 2470 }, { "epoch": 1.64, "learning_rate": 2.2735268249780124e-05, "loss": 1.4937, "step": 2480 }, { "epoch": 1.64, "learning_rate": 2.262532981530343e-05, "loss": 1.5312, "step": 2490 }, { "epoch": 1.65, "learning_rate": 2.2515391380826738e-05, "loss": 1.5397, "step": 2500 }, { "epoch": 1.66, "learning_rate": 2.2405452946350043e-05, "loss": 1.5214, "step": 2510 }, { "epoch": 1.66, "learning_rate": 2.2295514511873352e-05, "loss": 1.4721, "step": 2520 }, { "epoch": 1.67, "learning_rate": 2.2185576077396657e-05, "loss": 1.5434, "step": 2530 }, { "epoch": 1.68, "learning_rate": 2.2075637642919966e-05, "loss": 1.5435, "step": 2540 }, { "epoch": 1.68, "learning_rate": 2.196569920844327e-05, "loss": 1.4782, "step": 2550 }, { "epoch": 1.69, "learning_rate": 2.185576077396658e-05, "loss": 1.5048, "step": 2560 }, { "epoch": 1.7, "learning_rate": 2.174582233948989e-05, "loss": 1.5362, "step": 2570 }, { "epoch": 1.7, "learning_rate": 2.1635883905013194e-05, "loss": 1.493, "step": 2580 }, { "epoch": 1.71, "learning_rate": 2.1525945470536502e-05, "loss": 1.499, "step": 2590 }, { "epoch": 1.72, "learning_rate": 2.1416007036059807e-05, "loss": 1.516, "step": 2600 }, { "epoch": 1.72, "learning_rate": 2.1306068601583116e-05, "loss": 1.5204, "step": 2610 }, { "epoch": 1.73, "learning_rate": 2.119613016710642e-05, "loss": 1.5017, "step": 2620 }, { "epoch": 1.73, "learning_rate": 2.108619173262973e-05, "loss": 1.5261, "step": 2630 }, { "epoch": 1.74, "learning_rate": 2.0976253298153035e-05, "loss": 1.4976, "step": 2640 }, { "epoch": 1.75, "learning_rate": 2.0866314863676344e-05, "loss": 1.5322, "step": 2650 }, { "epoch": 1.75, "learning_rate": 2.075637642919965e-05, "loss": 1.5053, "step": 2660 }, { "epoch": 1.76, "learning_rate": 2.0646437994722954e-05, "loss": 1.4931, "step": 2670 }, { "epoch": 1.77, "learning_rate": 2.0536499560246263e-05, "loss": 1.5391, "step": 2680 }, { "epoch": 1.77, "learning_rate": 2.0426561125769568e-05, "loss": 1.5083, "step": 2690 }, { "epoch": 1.78, "learning_rate": 2.0316622691292877e-05, "loss": 1.5144, "step": 2700 }, { "epoch": 1.79, "learning_rate": 2.0206684256816182e-05, "loss": 1.5414, "step": 2710 }, { "epoch": 1.79, "learning_rate": 2.009674582233949e-05, "loss": 1.4979, "step": 2720 }, { "epoch": 1.8, "learning_rate": 1.9986807387862796e-05, "loss": 1.4678, "step": 2730 }, { "epoch": 1.81, "learning_rate": 1.9876868953386104e-05, "loss": 1.5413, "step": 2740 }, { "epoch": 1.81, "learning_rate": 1.9766930518909413e-05, "loss": 1.5032, "step": 2750 }, { "epoch": 1.82, "learning_rate": 1.965699208443272e-05, "loss": 1.5097, "step": 2760 }, { "epoch": 1.83, "learning_rate": 1.9547053649956027e-05, "loss": 1.5324, "step": 2770 }, { "epoch": 1.83, "learning_rate": 1.9437115215479332e-05, "loss": 1.4762, "step": 2780 }, { "epoch": 1.84, "learning_rate": 1.932717678100264e-05, "loss": 1.5123, "step": 2790 }, { "epoch": 1.85, "learning_rate": 1.9217238346525946e-05, "loss": 1.4932, "step": 2800 }, { "epoch": 1.85, "learning_rate": 1.9107299912049255e-05, "loss": 1.4953, "step": 2810 }, { "epoch": 1.86, "learning_rate": 1.899736147757256e-05, "loss": 1.4754, "step": 2820 }, { "epoch": 1.87, "learning_rate": 1.888742304309587e-05, "loss": 1.5279, "step": 2830 }, { "epoch": 1.87, "learning_rate": 1.8777484608619174e-05, "loss": 1.4789, "step": 2840 }, { "epoch": 1.88, "learning_rate": 1.866754617414248e-05, "loss": 1.5413, "step": 2850 }, { "epoch": 1.89, "learning_rate": 1.8557607739665788e-05, "loss": 1.5265, "step": 2860 }, { "epoch": 1.89, "learning_rate": 1.8447669305189093e-05, "loss": 1.5501, "step": 2870 }, { "epoch": 1.9, "learning_rate": 1.83377308707124e-05, "loss": 1.5043, "step": 2880 }, { "epoch": 1.91, "learning_rate": 1.8227792436235707e-05, "loss": 1.4825, "step": 2890 }, { "epoch": 1.91, "learning_rate": 1.8117854001759015e-05, "loss": 1.5153, "step": 2900 }, { "epoch": 1.92, "learning_rate": 1.8007915567282324e-05, "loss": 1.5237, "step": 2910 }, { "epoch": 1.93, "learning_rate": 1.789797713280563e-05, "loss": 1.5184, "step": 2920 }, { "epoch": 1.93, "learning_rate": 1.7788038698328938e-05, "loss": 1.5329, "step": 2930 }, { "epoch": 1.94, "learning_rate": 1.7678100263852243e-05, "loss": 1.538, "step": 2940 }, { "epoch": 1.95, "learning_rate": 1.756816182937555e-05, "loss": 1.5327, "step": 2950 }, { "epoch": 1.95, "learning_rate": 1.7458223394898857e-05, "loss": 1.5112, "step": 2960 }, { "epoch": 1.96, "learning_rate": 1.7348284960422166e-05, "loss": 1.4899, "step": 2970 }, { "epoch": 1.97, "learning_rate": 1.723834652594547e-05, "loss": 1.5306, "step": 2980 }, { "epoch": 1.97, "learning_rate": 1.712840809146878e-05, "loss": 1.4908, "step": 2990 }, { "epoch": 1.98, "learning_rate": 1.7018469656992088e-05, "loss": 1.4992, "step": 3000 }, { "epoch": 1.99, "learning_rate": 1.6908531222515393e-05, "loss": 1.5382, "step": 3010 }, { "epoch": 1.99, "learning_rate": 1.67985927880387e-05, "loss": 1.5033, "step": 3020 }, { "epoch": 2.0, "learning_rate": 1.6688654353562007e-05, "loss": 1.5204, "step": 3030 }, { "epoch": 2.01, "learning_rate": 1.6578715919085312e-05, "loss": 1.4727, "step": 3040 }, { "epoch": 2.01, "learning_rate": 1.6468777484608618e-05, "loss": 1.4722, "step": 3050 }, { "epoch": 2.02, "learning_rate": 1.6358839050131926e-05, "loss": 1.5185, "step": 3060 }, { "epoch": 2.03, "learning_rate": 1.624890061565523e-05, "loss": 1.5082, "step": 3070 }, { "epoch": 2.03, "learning_rate": 1.613896218117854e-05, "loss": 1.4765, "step": 3080 }, { "epoch": 2.04, "learning_rate": 1.602902374670185e-05, "loss": 1.4771, "step": 3090 }, { "epoch": 2.04, "learning_rate": 1.5919085312225154e-05, "loss": 1.4948, "step": 3100 }, { "epoch": 2.05, "learning_rate": 1.5809146877748463e-05, "loss": 1.5318, "step": 3110 }, { "epoch": 2.06, "learning_rate": 1.5699208443271768e-05, "loss": 1.509, "step": 3120 }, { "epoch": 2.06, "learning_rate": 1.5589270008795076e-05, "loss": 1.4926, "step": 3130 }, { "epoch": 2.07, "learning_rate": 1.547933157431838e-05, "loss": 1.4821, "step": 3140 }, { "epoch": 2.08, "learning_rate": 1.536939313984169e-05, "loss": 1.522, "step": 3150 }, { "epoch": 2.08, "learning_rate": 1.5259454705364995e-05, "loss": 1.495, "step": 3160 }, { "epoch": 2.09, "learning_rate": 1.5149516270888302e-05, "loss": 1.4935, "step": 3170 }, { "epoch": 2.1, "learning_rate": 1.5039577836411611e-05, "loss": 1.546, "step": 3180 }, { "epoch": 2.1, "learning_rate": 1.4929639401934916e-05, "loss": 1.4994, "step": 3190 }, { "epoch": 2.11, "learning_rate": 1.4819700967458225e-05, "loss": 1.4838, "step": 3200 }, { "epoch": 2.12, "learning_rate": 1.470976253298153e-05, "loss": 1.5, "step": 3210 }, { "epoch": 2.12, "learning_rate": 1.4599824098504839e-05, "loss": 1.4879, "step": 3220 }, { "epoch": 2.13, "learning_rate": 1.4489885664028144e-05, "loss": 1.5259, "step": 3230 }, { "epoch": 2.14, "learning_rate": 1.4379947229551453e-05, "loss": 1.4358, "step": 3240 }, { "epoch": 2.14, "learning_rate": 1.427000879507476e-05, "loss": 1.4648, "step": 3250 }, { "epoch": 2.15, "learning_rate": 1.4160070360598065e-05, "loss": 1.5326, "step": 3260 }, { "epoch": 2.16, "learning_rate": 1.4050131926121373e-05, "loss": 1.5289, "step": 3270 }, { "epoch": 2.16, "learning_rate": 1.3940193491644679e-05, "loss": 1.4928, "step": 3280 }, { "epoch": 2.17, "learning_rate": 1.3830255057167987e-05, "loss": 1.478, "step": 3290 }, { "epoch": 2.18, "learning_rate": 1.3720316622691292e-05, "loss": 1.4618, "step": 3300 }, { "epoch": 2.18, "learning_rate": 1.3610378188214601e-05, "loss": 1.492, "step": 3310 }, { "epoch": 2.19, "learning_rate": 1.3500439753737906e-05, "loss": 1.4682, "step": 3320 }, { "epoch": 2.2, "learning_rate": 1.3390501319261215e-05, "loss": 1.4612, "step": 3330 }, { "epoch": 2.2, "learning_rate": 1.3280562884784522e-05, "loss": 1.5, "step": 3340 }, { "epoch": 2.21, "learning_rate": 1.3170624450307827e-05, "loss": 1.5045, "step": 3350 }, { "epoch": 2.22, "learning_rate": 1.3060686015831136e-05, "loss": 1.5552, "step": 3360 }, { "epoch": 2.22, "learning_rate": 1.2950747581354441e-05, "loss": 1.4744, "step": 3370 }, { "epoch": 2.23, "learning_rate": 1.284080914687775e-05, "loss": 1.5347, "step": 3380 }, { "epoch": 2.24, "learning_rate": 1.2730870712401055e-05, "loss": 1.4956, "step": 3390 }, { "epoch": 2.24, "learning_rate": 1.2620932277924363e-05, "loss": 1.5048, "step": 3400 }, { "epoch": 2.25, "learning_rate": 1.2510993843447669e-05, "loss": 1.5075, "step": 3410 }, { "epoch": 2.26, "learning_rate": 1.2401055408970977e-05, "loss": 1.4969, "step": 3420 }, { "epoch": 2.26, "learning_rate": 1.2291116974494284e-05, "loss": 1.5188, "step": 3430 }, { "epoch": 2.27, "learning_rate": 1.2181178540017591e-05, "loss": 1.5184, "step": 3440 }, { "epoch": 2.28, "learning_rate": 1.2071240105540896e-05, "loss": 1.5067, "step": 3450 }, { "epoch": 2.28, "learning_rate": 1.1961301671064203e-05, "loss": 1.5001, "step": 3460 }, { "epoch": 2.29, "learning_rate": 1.1851363236587512e-05, "loss": 1.5666, "step": 3470 }, { "epoch": 2.3, "learning_rate": 1.1741424802110819e-05, "loss": 1.469, "step": 3480 }, { "epoch": 2.3, "learning_rate": 1.1631486367634126e-05, "loss": 1.4966, "step": 3490 }, { "epoch": 2.31, "learning_rate": 1.1521547933157433e-05, "loss": 1.505, "step": 3500 } ], "logging_steps": 10, "max_steps": 4548, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 2.211770864322478e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }