| { | |
| "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": 5.258409617793201, | |
| "learning_rate": 8e-06, | |
| "loss": 1.023, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 1.9634639059744294, | |
| "learning_rate": 8e-06, | |
| "loss": 0.6664, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.060759493670886074, | |
| "grad_norm": 1.6410905813104013, | |
| "learning_rate": 8e-06, | |
| "loss": 0.6367, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 1.5255764033722143, | |
| "learning_rate": 8e-06, | |
| "loss": 0.6187, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 2.2780634390160097, | |
| "learning_rate": 8e-06, | |
| "loss": 0.6083, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 1.474797149406696, | |
| "learning_rate": 8e-06, | |
| "loss": 0.6025, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14177215189873418, | |
| "grad_norm": 2.3944918165503664, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5975, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 1.6720203667156721, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5953, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18227848101265823, | |
| "grad_norm": 1.6708145144707192, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5924, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 1.6688201585452036, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5957, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22278481012658227, | |
| "grad_norm": 1.400501705285444, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5874, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2430379746835443, | |
| "grad_norm": 1.3610008251360137, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5848, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26329113924050634, | |
| "grad_norm": 1.6403578074396696, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5836, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28354430379746837, | |
| "grad_norm": 1.5166179164756723, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5731, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 1.2808609682515393, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5839, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3240506329113924, | |
| "grad_norm": 1.4035660584916438, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5829, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34430379746835443, | |
| "grad_norm": 1.2426836487744064, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5827, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36455696202531646, | |
| "grad_norm": 1.4370716574726141, | |
| "learning_rate": 8e-06, | |
| "loss": 0.578, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3848101265822785, | |
| "grad_norm": 1.3154177111284133, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5768, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 1.3183089950018316, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5719, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4253164556962025, | |
| "grad_norm": 1.3984209526600353, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5675, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.44556962025316454, | |
| "grad_norm": 1.426529702700913, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5727, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46582278481012657, | |
| "grad_norm": 1.5418885928517125, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5731, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4860759493670886, | |
| "grad_norm": 1.1275309408936236, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5684, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 1.6444904149299944, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5732, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5265822784810127, | |
| "grad_norm": 1.4645165064247605, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5593, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5468354430379747, | |
| "grad_norm": 1.239534113660614, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5669, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5670886075949367, | |
| "grad_norm": 1.160747881611218, | |
| "learning_rate": 8e-06, | |
| "loss": 0.561, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5873417721518988, | |
| "grad_norm": 1.2972740705973926, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5626, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 1.2294051846938365, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5631, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6278481012658228, | |
| "grad_norm": 1.6283651781356676, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5685, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6481012658227848, | |
| "grad_norm": 1.3897973040030838, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5644, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6683544303797468, | |
| "grad_norm": 1.1798876107097973, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5646, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6886075949367089, | |
| "grad_norm": 1.2610803648917965, | |
| "learning_rate": 8e-06, | |
| "loss": 0.565, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7088607594936709, | |
| "grad_norm": 1.178873507844517, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5664, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7291139240506329, | |
| "grad_norm": 1.1161022354530776, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5686, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7493670886075949, | |
| "grad_norm": 1.4863427961729259, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5615, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.769620253164557, | |
| "grad_norm": 1.2980862414374872, | |
| "learning_rate": 8e-06, | |
| "loss": 0.558, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.789873417721519, | |
| "grad_norm": 1.3666419196350272, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5612, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 1.3300326802050886, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5617, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.830379746835443, | |
| "grad_norm": 1.2099296941610271, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5555, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.850632911392405, | |
| "grad_norm": 1.1894237989819347, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5631, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8708860759493671, | |
| "grad_norm": 1.2894976868142938, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5566, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8911392405063291, | |
| "grad_norm": 1.0173932950343898, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5626, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9113924050632911, | |
| "grad_norm": 1.1202926727940976, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5539, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9316455696202531, | |
| "grad_norm": 1.2137206675899272, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5589, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9518987341772152, | |
| "grad_norm": 1.3311698314365965, | |
| "learning_rate": 8e-06, | |
| "loss": 0.56, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9721518987341772, | |
| "grad_norm": 0.9921211297208837, | |
| "learning_rate": 8e-06, | |
| "loss": 0.5568, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9924050632911392, | |
| "grad_norm": 1.0918047641686206, | |
| "learning_rate": 8e-06, | |
| "loss": 0.554, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9984810126582279, | |
| "eval_loss": 0.06964311003684998, | |
| "eval_runtime": 508.1058, | |
| "eval_samples_per_second": 26.184, | |
| "eval_steps_per_second": 0.409, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.0126582278481013, | |
| "grad_norm": 1.762541165270915, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4992, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0329113924050632, | |
| "grad_norm": 2.5260365015272437, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4536, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0531645569620254, | |
| "grad_norm": 2.3427358097665203, | |
| "learning_rate": 8e-06, | |
| "loss": 0.447, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.0734177215189873, | |
| "grad_norm": 1.3459463110030783, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4475, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0936708860759494, | |
| "grad_norm": 1.2150769887620263, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4429, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1139240506329113, | |
| "grad_norm": 1.104336519159156, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4466, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1341772151898735, | |
| "grad_norm": 1.2529889901894558, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4446, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.1544303797468354, | |
| "grad_norm": 1.0824873303818652, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4521, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1746835443037975, | |
| "grad_norm": 1.0161326357517337, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4521, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1949367088607594, | |
| "grad_norm": 1.076297964842755, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4475, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2151898734177216, | |
| "grad_norm": 1.3158843095936974, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4561, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2354430379746835, | |
| "grad_norm": 1.2366069558199053, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4527, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2556962025316456, | |
| "grad_norm": 1.598397793667301, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4563, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.2759493670886077, | |
| "grad_norm": 1.2828531481756353, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4562, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.2962025316455696, | |
| "grad_norm": 1.293135581933677, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4556, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3164556962025316, | |
| "grad_norm": 1.1688810307671624, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4594, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3367088607594937, | |
| "grad_norm": 1.0991834192928607, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4487, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3569620253164558, | |
| "grad_norm": 1.2923049087985872, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4633, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.3772151898734177, | |
| "grad_norm": 1.387734871984166, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4604, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.3974683544303796, | |
| "grad_norm": 1.0691182672058392, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4593, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.4177215189873418, | |
| "grad_norm": 1.1857105210887937, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4561, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.437974683544304, | |
| "grad_norm": 1.1161475633664233, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4616, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.4582278481012658, | |
| "grad_norm": 1.555753149641079, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4623, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.4784810126582277, | |
| "grad_norm": 1.1260180001391196, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4659, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.4987341772151899, | |
| "grad_norm": 1.290187429480974, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4584, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.518987341772152, | |
| "grad_norm": 1.5826702933985046, | |
| "learning_rate": 8e-06, | |
| "loss": 0.461, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.539240506329114, | |
| "grad_norm": 1.04348958752633, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4614, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.5594936708860758, | |
| "grad_norm": 1.176498636645072, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4605, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.579746835443038, | |
| "grad_norm": 1.3274686512986706, | |
| "learning_rate": 8e-06, | |
| "loss": 0.461, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.7064735719004016, | |
| "learning_rate": 8e-06, | |
| "loss": 0.464, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.620253164556962, | |
| "grad_norm": 1.7607063790022062, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4585, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.640506329113924, | |
| "grad_norm": 1.7018809526653174, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4505, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.660759493670886, | |
| "grad_norm": 1.2309699225444164, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4582, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.6810126582278482, | |
| "grad_norm": 1.2743174412396685, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4546, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.70126582278481, | |
| "grad_norm": 1.1401885492274906, | |
| "learning_rate": 8e-06, | |
| "loss": 0.457, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.721518987341772, | |
| "grad_norm": 1.0949963267924365, | |
| "learning_rate": 8e-06, | |
| "loss": 0.46, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7417721518987341, | |
| "grad_norm": 1.0781291456865303, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4609, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.7620253164556963, | |
| "grad_norm": 1.111363356798856, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4656, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.7822784810126582, | |
| "grad_norm": 1.1706179213117816, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4674, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.80253164556962, | |
| "grad_norm": 1.2203123961643751, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4653, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.8227848101265822, | |
| "grad_norm": 1.1056188147698058, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4643, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8430379746835444, | |
| "grad_norm": 1.1444124530675628, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4668, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.8632911392405065, | |
| "grad_norm": 1.2519400702065764, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4652, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.8835443037974684, | |
| "grad_norm": 1.2512205946982604, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4623, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.9037974683544303, | |
| "grad_norm": 1.2054900960537691, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4659, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.9240506329113924, | |
| "grad_norm": 1.3121801950303555, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4669, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9443037974683546, | |
| "grad_norm": 1.0230567999865412, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4708, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.9645569620253165, | |
| "grad_norm": 1.1620580976482835, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4691, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.9848101265822784, | |
| "grad_norm": 1.1261166847219595, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4701, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.998987341772152, | |
| "eval_loss": 0.07048599421977997, | |
| "eval_runtime": 513.0923, | |
| "eval_samples_per_second": 25.929, | |
| "eval_steps_per_second": 0.405, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 2.0050632911392405, | |
| "grad_norm": 2.0179119266564665, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4369, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.0253164556962027, | |
| "grad_norm": 1.9022077255957954, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3497, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0455696202531644, | |
| "grad_norm": 1.517942081619105, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3424, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.0658227848101265, | |
| "grad_norm": 1.4669334931870377, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3358, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.0860759493670886, | |
| "grad_norm": 1.173043870700386, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3358, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.1063291139240508, | |
| "grad_norm": 1.2239442949532888, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3338, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.1265822784810124, | |
| "grad_norm": 1.7270937310853078, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3438, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.1468354430379746, | |
| "grad_norm": 1.4467147213195026, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3403, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.1670886075949367, | |
| "grad_norm": 1.2231063778230826, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3442, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.187341772151899, | |
| "grad_norm": 1.2462856865522505, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3428, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.207594936708861, | |
| "grad_norm": 1.4702069808891078, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3416, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.2278481012658227, | |
| "grad_norm": 1.5227230628625579, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3499, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.248101265822785, | |
| "grad_norm": 1.4454458462276822, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3452, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.268354430379747, | |
| "grad_norm": 1.449344486199819, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3479, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.2886075949367086, | |
| "grad_norm": 1.2245861220812775, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3481, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.3088607594936708, | |
| "grad_norm": 1.1903186012822253, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3456, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.329113924050633, | |
| "grad_norm": 1.5726196999835074, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3517, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.349367088607595, | |
| "grad_norm": 1.3248499327478453, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3532, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.369620253164557, | |
| "grad_norm": 1.7557061358809325, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3583, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.389873417721519, | |
| "grad_norm": 1.4082851872297522, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3536, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.410126582278481, | |
| "grad_norm": 1.399110019209652, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3529, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.430379746835443, | |
| "grad_norm": 1.5156192751607742, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3519, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4506329113924052, | |
| "grad_norm": 2.1631377057011894, | |
| "learning_rate": 8e-06, | |
| "loss": 0.351, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.470886075949367, | |
| "grad_norm": 1.7931322753704133, | |
| "learning_rate": 8e-06, | |
| "loss": 0.355, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.491139240506329, | |
| "grad_norm": 1.7720678917909556, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3531, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.511392405063291, | |
| "grad_norm": 1.8385519790282414, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3567, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.5316455696202533, | |
| "grad_norm": 1.4444531890891432, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3508, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.5518987341772155, | |
| "grad_norm": 1.2906151093911482, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3467, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.572151898734177, | |
| "grad_norm": 1.2769093278300687, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3528, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.5924050632911393, | |
| "grad_norm": 1.247195598633543, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3565, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.6126582278481014, | |
| "grad_norm": 1.2469850188483607, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3616, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.632911392405063, | |
| "grad_norm": 1.218916528929978, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3577, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.6531645569620252, | |
| "grad_norm": 1.2619787466089587, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3581, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.6734177215189874, | |
| "grad_norm": 1.308043191246096, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3612, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.6936708860759495, | |
| "grad_norm": 1.3193836070392535, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3631, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.7139240506329116, | |
| "grad_norm": 1.2718360884809436, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3619, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.7341772151898733, | |
| "grad_norm": 1.2815568595839768, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3624, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.7544303797468355, | |
| "grad_norm": 1.3747654654246406, | |
| "learning_rate": 8e-06, | |
| "loss": 0.359, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.7746835443037976, | |
| "grad_norm": 1.2653479476808633, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3646, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.7949367088607593, | |
| "grad_norm": 1.2332294857429442, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3629, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.8151898734177214, | |
| "grad_norm": 1.3158256632117944, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3659, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.8354430379746836, | |
| "grad_norm": 1.2444854517150397, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3602, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.8556962025316457, | |
| "grad_norm": 1.2892614182868651, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3684, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.875949367088608, | |
| "grad_norm": 1.2750754798660686, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3651, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.8962025316455695, | |
| "grad_norm": 1.3766164912232581, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3659, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.9164556962025316, | |
| "grad_norm": 1.2250813246254637, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3671, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.9367088607594938, | |
| "grad_norm": 1.292838642797344, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3762, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.9569620253164555, | |
| "grad_norm": 1.2708919014972173, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3658, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.9772151898734176, | |
| "grad_norm": 1.2582700906257276, | |
| "learning_rate": 8e-06, | |
| "loss": 0.3691, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "eval_loss": 0.07653476297855377, | |
| "eval_runtime": 512.0837, | |
| "eval_samples_per_second": 25.98, | |
| "eval_steps_per_second": 0.406, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "step": 1479, | |
| "total_flos": 2477170706350080.0, | |
| "train_loss": 0.4662262036076585, | |
| "train_runtime": 84837.0324, | |
| "train_samples_per_second": 8.938, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "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 | |
| } | |