| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9954430379746837, | |
| "eval_steps": 500, | |
| "global_step": 1479, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020253164556962026, | |
| "grad_norm": 12.120276772132307, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3197, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 3.3282798950621606, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7042, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.060759493670886074, | |
| "grad_norm": 1.852628562201542, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6472, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 1.8595883040832657, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6266, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 2.3347809060064737, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6144, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 1.5723585971477918, | |
| "learning_rate": 1e-05, | |
| "loss": 0.608, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14177215189873418, | |
| "grad_norm": 1.3994357935247357, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6034, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 1.447049621938385, | |
| "learning_rate": 1e-05, | |
| "loss": 0.599, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18227848101265823, | |
| "grad_norm": 1.2428690822989794, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5981, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 1.3914703840449831, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6011, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22278481012658227, | |
| "grad_norm": 1.5592092104237008, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5939, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2430379746835443, | |
| "grad_norm": 1.471433544307161, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5912, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26329113924050634, | |
| "grad_norm": 1.2679735338498985, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5897, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28354430379746837, | |
| "grad_norm": 1.6702226860109868, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5788, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 1.3067789351691594, | |
| "learning_rate": 1e-05, | |
| "loss": 0.588, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3240506329113924, | |
| "grad_norm": 1.1703696399532784, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5863, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34430379746835443, | |
| "grad_norm": 1.121107144958954, | |
| "learning_rate": 1e-05, | |
| "loss": 0.588, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36455696202531646, | |
| "grad_norm": 1.5075601932855025, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5843, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3848101265822785, | |
| "grad_norm": 1.338012688042743, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5829, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 1.1821708199327476, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5779, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4253164556962025, | |
| "grad_norm": 1.4310888733583513, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5738, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.44556962025316454, | |
| "grad_norm": 1.2425719507952644, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5793, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46582278481012657, | |
| "grad_norm": 1.284207417856141, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5789, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4860759493670886, | |
| "grad_norm": 1.287170935711038, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5747, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 2.4058688944413764, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5796, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5265822784810127, | |
| "grad_norm": 1.6394596935536183, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5666, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5468354430379747, | |
| "grad_norm": 1.6683438715363992, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5721, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5670886075949367, | |
| "grad_norm": 1.1622746081977664, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5649, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5873417721518988, | |
| "grad_norm": 1.1921031772245787, | |
| "learning_rate": 1e-05, | |
| "loss": 0.566, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 1.2152166551469124, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5671, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6278481012658228, | |
| "grad_norm": 1.502458614540582, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5745, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6481012658227848, | |
| "grad_norm": 1.3818767210076068, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5707, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6683544303797468, | |
| "grad_norm": 1.2097710361150822, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5694, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6886075949367089, | |
| "grad_norm": 1.079086895654196, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5696, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7088607594936709, | |
| "grad_norm": 1.157190965982707, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5715, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7291139240506329, | |
| "grad_norm": 1.1550319402689113, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5743, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7493670886075949, | |
| "grad_norm": 1.2470855203394164, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5675, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.769620253164557, | |
| "grad_norm": 1.3106394417346152, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5642, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.789873417721519, | |
| "grad_norm": 1.4375961620431188, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5669, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 1.1354365824942318, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5664, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.830379746835443, | |
| "grad_norm": 1.1099955442432055, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5604, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.850632911392405, | |
| "grad_norm": 1.0248354813245797, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5693, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8708860759493671, | |
| "grad_norm": 1.1695037280013965, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5633, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8911392405063291, | |
| "grad_norm": 1.0066881046376932, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5691, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9113924050632911, | |
| "grad_norm": 1.1463091892812078, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5603, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9316455696202531, | |
| "grad_norm": 1.0788249736854203, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5655, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9518987341772152, | |
| "grad_norm": 1.239072255047288, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5664, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9721518987341772, | |
| "grad_norm": 1.0915164665788082, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5637, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9924050632911392, | |
| "grad_norm": 1.0969372897726506, | |
| "learning_rate": 1e-05, | |
| "loss": 0.56, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9984810126582279, | |
| "eval_loss": 0.07033738493919373, | |
| "eval_runtime": 504.4731, | |
| "eval_samples_per_second": 26.372, | |
| "eval_steps_per_second": 0.412, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.0126582278481013, | |
| "grad_norm": 1.7003665830327457, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4975, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0329113924050632, | |
| "grad_norm": 1.2635282362069415, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4476, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0531645569620254, | |
| "grad_norm": 1.4874167170265886, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4419, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.0734177215189873, | |
| "grad_norm": 1.2207382792396062, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4418, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0936708860759494, | |
| "grad_norm": 1.2290216181181564, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4368, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1139240506329113, | |
| "grad_norm": 1.6678262115708307, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4393, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1341772151898735, | |
| "grad_norm": 1.0698168475317462, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4357, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.1544303797468354, | |
| "grad_norm": 1.4082917170488416, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4424, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1746835443037975, | |
| "grad_norm": 1.2669419785340237, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4415, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1949367088607594, | |
| "grad_norm": 1.230550253708558, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4357, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2151898734177216, | |
| "grad_norm": 1.2542289011497672, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4442, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2354430379746835, | |
| "grad_norm": 1.110140026650854, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4419, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2556962025316456, | |
| "grad_norm": 1.1673077840894608, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4471, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.2759493670886077, | |
| "grad_norm": 1.1952693191466754, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4503, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.2962025316455696, | |
| "grad_norm": 1.2811688264876502, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4504, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3164556962025316, | |
| "grad_norm": 1.201361948961674, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4546, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3367088607594937, | |
| "grad_norm": 1.1153919438488649, | |
| "learning_rate": 1e-05, | |
| "loss": 0.444, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3569620253164558, | |
| "grad_norm": 1.1049424729490929, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4589, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.3772151898734177, | |
| "grad_norm": 1.1545393310939402, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4565, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.3974683544303796, | |
| "grad_norm": 1.11029297429295, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4556, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.4177215189873418, | |
| "grad_norm": 1.047113325677032, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4524, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.437974683544304, | |
| "grad_norm": 1.0379588408596967, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4591, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.4582278481012658, | |
| "grad_norm": 1.2432868288193164, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4602, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.4784810126582277, | |
| "grad_norm": 1.125133727987033, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4638, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.4987341772151899, | |
| "grad_norm": 1.1243180240639854, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4553, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.518987341772152, | |
| "grad_norm": 1.2646245667315335, | |
| "learning_rate": 1e-05, | |
| "loss": 0.458, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.539240506329114, | |
| "grad_norm": 1.0026618924941482, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4591, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.5594936708860758, | |
| "grad_norm": 1.119323006377659, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4589, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.579746835443038, | |
| "grad_norm": 1.2367498859475263, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4596, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.0563847142257616, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4613, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.620253164556962, | |
| "grad_norm": 1.2639836828415751, | |
| "learning_rate": 1e-05, | |
| "loss": 0.458, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.640506329113924, | |
| "grad_norm": 1.015054309602122, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4518, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.660759493670886, | |
| "grad_norm": 1.0938189623403691, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4609, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.6810126582278482, | |
| "grad_norm": 1.1944856866424804, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4572, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.70126582278481, | |
| "grad_norm": 0.9913091951101142, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4592, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.721518987341772, | |
| "grad_norm": 1.0583438868425272, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4614, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7417721518987341, | |
| "grad_norm": 1.0753652786030234, | |
| "learning_rate": 1e-05, | |
| "loss": 0.462, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.7620253164556963, | |
| "grad_norm": 1.0641685034731208, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4656, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.7822784810126582, | |
| "grad_norm": 1.1115091053423183, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4669, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.80253164556962, | |
| "grad_norm": 1.1762455233061868, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4643, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.8227848101265822, | |
| "grad_norm": 1.0488806003684397, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4634, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8430379746835444, | |
| "grad_norm": 1.137548743512461, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4653, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.8632911392405065, | |
| "grad_norm": 1.2277896309279472, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4642, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.8835443037974684, | |
| "grad_norm": 1.1031182132626522, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4617, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.9037974683544303, | |
| "grad_norm": 1.17361252748904, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4645, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.9240506329113924, | |
| "grad_norm": 1.1510248983778957, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4658, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9443037974683546, | |
| "grad_norm": 0.9489143733406166, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4695, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.9645569620253165, | |
| "grad_norm": 1.03558420599709, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4675, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.9848101265822784, | |
| "grad_norm": 0.9879031581948011, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4685, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.998987341772152, | |
| "eval_loss": 0.07146137207746506, | |
| "eval_runtime": 505.4639, | |
| "eval_samples_per_second": 26.32, | |
| "eval_steps_per_second": 0.412, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 2.0050632911392405, | |
| "grad_norm": 1.892066865726991, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4323, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.0253164556962027, | |
| "grad_norm": 1.5719039003024942, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3341, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0455696202531644, | |
| "grad_norm": 1.449884706175893, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3244, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.0658227848101265, | |
| "grad_norm": 1.2852913794473613, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3184, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.0860759493670886, | |
| "grad_norm": 1.1603083163194567, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3194, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.1063291139240508, | |
| "grad_norm": 1.3069767179205787, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3174, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.1265822784810124, | |
| "grad_norm": 1.6903160262293084, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3271, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.1468354430379746, | |
| "grad_norm": 1.1612363707549425, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3226, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.1670886075949367, | |
| "grad_norm": 1.2336974410905899, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3272, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.187341772151899, | |
| "grad_norm": 1.4860870096822676, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3254, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.207594936708861, | |
| "grad_norm": 1.2327704954496135, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3232, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.2278481012658227, | |
| "grad_norm": 1.2728744826855773, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3303, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.248101265822785, | |
| "grad_norm": 1.564435586204242, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3268, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.268354430379747, | |
| "grad_norm": 1.1796512878110514, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3295, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.2886075949367086, | |
| "grad_norm": 1.3761953620771636, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3314, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.3088607594936708, | |
| "grad_norm": 1.2084195608367814, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3281, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.329113924050633, | |
| "grad_norm": 1.3640182632104951, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3331, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.349367088607595, | |
| "grad_norm": 1.2183639117868437, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3338, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.369620253164557, | |
| "grad_norm": 1.5867826943310064, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3345, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.389873417721519, | |
| "grad_norm": 1.671471525105439, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3349, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.410126582278481, | |
| "grad_norm": 1.3298853522150373, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3358, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.430379746835443, | |
| "grad_norm": 1.2730109312885425, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3343, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4506329113924052, | |
| "grad_norm": 1.2457421709970629, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3346, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.470886075949367, | |
| "grad_norm": 1.3431855699425361, | |
| "learning_rate": 1e-05, | |
| "loss": 0.339, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.491139240506329, | |
| "grad_norm": 1.2603843195755815, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3403, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.511392405063291, | |
| "grad_norm": 1.4062229291125676, | |
| "learning_rate": 1e-05, | |
| "loss": 0.344, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.5316455696202533, | |
| "grad_norm": 1.322597016772209, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3385, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.5518987341772155, | |
| "grad_norm": 1.373766133387267, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3362, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.572151898734177, | |
| "grad_norm": 1.2344056168917583, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3422, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.5924050632911393, | |
| "grad_norm": 1.2900507739859943, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3434, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.6126582278481014, | |
| "grad_norm": 1.1094628286667152, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3491, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.632911392405063, | |
| "grad_norm": 1.2155731176288158, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3441, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.6531645569620252, | |
| "grad_norm": 1.1792690382009903, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3449, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.6734177215189874, | |
| "grad_norm": 1.1807087130030214, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3478, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.6936708860759495, | |
| "grad_norm": 1.304918179872075, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3492, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.7139240506329116, | |
| "grad_norm": 1.2726713376838257, | |
| "learning_rate": 1e-05, | |
| "loss": 0.349, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.7341772151898733, | |
| "grad_norm": 1.3016244218498019, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3494, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.7544303797468355, | |
| "grad_norm": 1.2698985747702052, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3455, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.7746835443037976, | |
| "grad_norm": 1.2610899461992577, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3513, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.7949367088607593, | |
| "grad_norm": 1.3344761420732612, | |
| "learning_rate": 1e-05, | |
| "loss": 0.349, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.8151898734177214, | |
| "grad_norm": 1.2470207135941664, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3518, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.8354430379746836, | |
| "grad_norm": 1.2318168043565298, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3463, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.8556962025316457, | |
| "grad_norm": 1.2597107398114282, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3542, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.875949367088608, | |
| "grad_norm": 1.2248062173263479, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3516, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.8962025316455695, | |
| "grad_norm": 1.3227956688116478, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3518, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.9164556962025316, | |
| "grad_norm": 1.2776070215734827, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3535, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.9367088607594938, | |
| "grad_norm": 1.154652010117705, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3621, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.9569620253164555, | |
| "grad_norm": 1.1923022485239954, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3521, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.9772151898734176, | |
| "grad_norm": 1.2357715823045246, | |
| "learning_rate": 1e-05, | |
| "loss": 0.356, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "eval_loss": 0.07828417420387268, | |
| "eval_runtime": 506.1814, | |
| "eval_samples_per_second": 26.283, | |
| "eval_steps_per_second": 0.411, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "step": 1479, | |
| "total_flos": 2477170706350080.0, | |
| "train_loss": 0.4641323921404794, | |
| "train_runtime": 83870.3724, | |
| "train_samples_per_second": 9.041, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1479, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2477170706350080.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |