| { | |
| "best_metric": 0.5752944946289062, | |
| "best_model_checkpoint": "./output/checkpoint-1200", | |
| "epoch": 4.719101123595506, | |
| "eval_steps": 150, | |
| "global_step": 2100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02247191011235955, | |
| "grad_norm": 40.276283264160156, | |
| "learning_rate": 1.25e-06, | |
| "loss": 2.1095, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 15.660475730895996, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.7071, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06741573033707865, | |
| "grad_norm": 32.55162811279297, | |
| "learning_rate": 3.75e-06, | |
| "loss": 1.746, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 15.043834686279297, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5731, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11235955056179775, | |
| "grad_norm": 24.83352279663086, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.3603, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1348314606741573, | |
| "grad_norm": 35.10358428955078, | |
| "learning_rate": 7.5e-06, | |
| "loss": 1.3892, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15730337078651685, | |
| "grad_norm": 35.139347076416016, | |
| "learning_rate": 8.75e-06, | |
| "loss": 1.2658, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 28.40645980834961, | |
| "learning_rate": 1e-05, | |
| "loss": 1.187, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20224719101123595, | |
| "grad_norm": 29.196102142333984, | |
| "learning_rate": 1.125e-05, | |
| "loss": 1.237, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2247191011235955, | |
| "grad_norm": 25.024761199951172, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.2521, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24719101123595505, | |
| "grad_norm": 25.139511108398438, | |
| "learning_rate": 1.2499871543489788e-05, | |
| "loss": 1.1565, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "grad_norm": 12.163933753967285, | |
| "learning_rate": 1.2499486179239496e-05, | |
| "loss": 1.1179, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.29213483146067415, | |
| "grad_norm": 7.7505998611450195, | |
| "learning_rate": 1.2498843923089939e-05, | |
| "loss": 1.1047, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3146067415730337, | |
| "grad_norm": 21.35865592956543, | |
| "learning_rate": 1.249794480144175e-05, | |
| "loss": 1.1226, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.33707865168539325, | |
| "grad_norm": 15.02802562713623, | |
| "learning_rate": 1.24967888512543e-05, | |
| "loss": 0.9727, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.33707865168539325, | |
| "eval_loss": 0.9761117696762085, | |
| "eval_runtime": 28.1312, | |
| "eval_samples_per_second": 14.077, | |
| "eval_steps_per_second": 14.077, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "grad_norm": 21.93962287902832, | |
| "learning_rate": 1.2495376120044174e-05, | |
| "loss": 1.1303, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38202247191011235, | |
| "grad_norm": 22.738882064819336, | |
| "learning_rate": 1.2493706665883217e-05, | |
| "loss": 1.1115, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4044943820224719, | |
| "grad_norm": 19.962158203125, | |
| "learning_rate": 1.2491780557396153e-05, | |
| "loss": 1.0215, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.42696629213483145, | |
| "grad_norm": 22.92249870300293, | |
| "learning_rate": 1.2489597873757757e-05, | |
| "loss": 1.0086, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 20.59571075439453, | |
| "learning_rate": 1.2487158704689602e-05, | |
| "loss": 0.9309, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47191011235955055, | |
| "grad_norm": 21.059810638427734, | |
| "learning_rate": 1.248446315045638e-05, | |
| "loss": 1.0798, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4943820224719101, | |
| "grad_norm": 17.537137985229492, | |
| "learning_rate": 1.2481511321861762e-05, | |
| "loss": 0.9138, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5168539325842697, | |
| "grad_norm": 16.027517318725586, | |
| "learning_rate": 1.2478303340243865e-05, | |
| "loss": 0.9623, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "grad_norm": 18.933513641357422, | |
| "learning_rate": 1.2474839337470245e-05, | |
| "loss": 0.9063, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5617977528089888, | |
| "grad_norm": 18.865337371826172, | |
| "learning_rate": 1.2471119455932489e-05, | |
| "loss": 0.8277, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5842696629213483, | |
| "grad_norm": 17.30205535888672, | |
| "learning_rate": 1.246714384854036e-05, | |
| "loss": 0.7923, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6067415730337079, | |
| "grad_norm": 14.635787963867188, | |
| "learning_rate": 1.2462912678715502e-05, | |
| "loss": 0.8241, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6292134831460674, | |
| "grad_norm": 21.17339324951172, | |
| "learning_rate": 1.245842612038474e-05, | |
| "loss": 0.8488, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.651685393258427, | |
| "grad_norm": 19.38275909423828, | |
| "learning_rate": 1.2453684357972907e-05, | |
| "loss": 1.0164, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6741573033707865, | |
| "grad_norm": 20.8955078125, | |
| "learning_rate": 1.2448687586395288e-05, | |
| "loss": 0.9468, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6741573033707865, | |
| "eval_loss": 0.7623159885406494, | |
| "eval_runtime": 28.3099, | |
| "eval_samples_per_second": 13.988, | |
| "eval_steps_per_second": 13.988, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6966292134831461, | |
| "grad_norm": 14.662369728088379, | |
| "learning_rate": 1.2443436011049593e-05, | |
| "loss": 0.8178, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7191011235955056, | |
| "grad_norm": 15.885370254516602, | |
| "learning_rate": 1.2437929847807512e-05, | |
| "loss": 0.9479, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7415730337078652, | |
| "grad_norm": 14.278594970703125, | |
| "learning_rate": 1.2432169323005851e-05, | |
| "loss": 0.8635, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7640449438202247, | |
| "grad_norm": 14.948090553283691, | |
| "learning_rate": 1.2426154673437223e-05, | |
| "loss": 0.7926, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7865168539325843, | |
| "grad_norm": 20.756702423095703, | |
| "learning_rate": 1.2419886146340315e-05, | |
| "loss": 0.7433, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8089887640449438, | |
| "grad_norm": 13.336278915405273, | |
| "learning_rate": 1.2413363999389718e-05, | |
| "loss": 0.9501, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8314606741573034, | |
| "grad_norm": 18.14997100830078, | |
| "learning_rate": 1.2406588500685356e-05, | |
| "loss": 0.7787, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8539325842696629, | |
| "grad_norm": 14.070672988891602, | |
| "learning_rate": 1.2399559928741435e-05, | |
| "loss": 0.8501, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8764044943820225, | |
| "grad_norm": 12.321798324584961, | |
| "learning_rate": 1.2392278572475025e-05, | |
| "loss": 0.8531, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 13.217580795288086, | |
| "learning_rate": 1.2384744731194159e-05, | |
| "loss": 0.7066, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9213483146067416, | |
| "grad_norm": 21.007793426513672, | |
| "learning_rate": 1.2376958714585546e-05, | |
| "loss": 0.7631, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9438202247191011, | |
| "grad_norm": 25.68875503540039, | |
| "learning_rate": 1.2368920842701831e-05, | |
| "loss": 0.6831, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9662921348314607, | |
| "grad_norm": 18.43454933166504, | |
| "learning_rate": 1.2360631445948449e-05, | |
| "loss": 0.7968, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9887640449438202, | |
| "grad_norm": 11.963883399963379, | |
| "learning_rate": 1.2352090865070027e-05, | |
| "loss": 0.7182, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0112359550561798, | |
| "grad_norm": 19.328462600708008, | |
| "learning_rate": 1.2343299451136397e-05, | |
| "loss": 0.7027, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0112359550561798, | |
| "eval_loss": 0.6809844970703125, | |
| "eval_runtime": 28.6076, | |
| "eval_samples_per_second": 13.842, | |
| "eval_steps_per_second": 13.842, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0337078651685394, | |
| "grad_norm": 17.414684295654297, | |
| "learning_rate": 1.2334257565528155e-05, | |
| "loss": 0.5859, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0561797752808988, | |
| "grad_norm": 15.297569274902344, | |
| "learning_rate": 1.2324965579921801e-05, | |
| "loss": 0.4641, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0786516853932584, | |
| "grad_norm": 18.19464874267578, | |
| "learning_rate": 1.2315423876274468e-05, | |
| "loss": 0.5484, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.101123595505618, | |
| "grad_norm": 9.914576530456543, | |
| "learning_rate": 1.2305632846808221e-05, | |
| "loss": 0.6468, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1235955056179776, | |
| "grad_norm": 14.114611625671387, | |
| "learning_rate": 1.2295592893993934e-05, | |
| "loss": 0.6038, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.146067415730337, | |
| "grad_norm": 16.208505630493164, | |
| "learning_rate": 1.2285304430534745e-05, | |
| "loss": 0.5434, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1685393258426966, | |
| "grad_norm": 9.227933883666992, | |
| "learning_rate": 1.2274767879349083e-05, | |
| "loss": 0.5278, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.1910112359550562, | |
| "grad_norm": 13.076558113098145, | |
| "learning_rate": 1.2263983673553307e-05, | |
| "loss": 0.7342, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2134831460674158, | |
| "grad_norm": 14.731674194335938, | |
| "learning_rate": 1.2252952256443871e-05, | |
| "loss": 0.5825, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2359550561797752, | |
| "grad_norm": 12.931262016296387, | |
| "learning_rate": 1.2241674081479129e-05, | |
| "loss": 0.6817, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2584269662921348, | |
| "grad_norm": 19.48564910888672, | |
| "learning_rate": 1.223014961226068e-05, | |
| "loss": 0.6012, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2808988764044944, | |
| "grad_norm": 17.863492965698242, | |
| "learning_rate": 1.2218379322514316e-05, | |
| "loss": 0.6, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.303370786516854, | |
| "grad_norm": 16.681968688964844, | |
| "learning_rate": 1.2206363696070545e-05, | |
| "loss": 0.5687, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3258426966292136, | |
| "grad_norm": 11.682393074035645, | |
| "learning_rate": 1.219410322684471e-05, | |
| "loss": 0.6333, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.348314606741573, | |
| "grad_norm": 10.291793823242188, | |
| "learning_rate": 1.2181598418816679e-05, | |
| "loss": 0.5697, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.348314606741573, | |
| "eval_loss": 0.648504376411438, | |
| "eval_runtime": 28.6285, | |
| "eval_samples_per_second": 13.832, | |
| "eval_steps_per_second": 13.832, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.3707865168539326, | |
| "grad_norm": 18.982742309570312, | |
| "learning_rate": 1.2168849786010134e-05, | |
| "loss": 0.4987, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.3932584269662922, | |
| "grad_norm": 6.644986629486084, | |
| "learning_rate": 1.2155857852471433e-05, | |
| "loss": 0.6424, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4157303370786516, | |
| "grad_norm": 10.34019947052002, | |
| "learning_rate": 1.2142623152248081e-05, | |
| "loss": 0.674, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4382022471910112, | |
| "grad_norm": 20.887239456176758, | |
| "learning_rate": 1.2129146229366767e-05, | |
| "loss": 0.5793, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4606741573033708, | |
| "grad_norm": 19.285852432250977, | |
| "learning_rate": 1.2115427637811003e-05, | |
| "loss": 0.5608, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4831460674157304, | |
| "grad_norm": 14.167954444885254, | |
| "learning_rate": 1.2101467941498358e-05, | |
| "loss": 0.4507, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.50561797752809, | |
| "grad_norm": 17.428260803222656, | |
| "learning_rate": 1.208726771425727e-05, | |
| "loss": 0.4813, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5280898876404494, | |
| "grad_norm": 14.576336860656738, | |
| "learning_rate": 1.2072827539803463e-05, | |
| "loss": 0.6145, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.550561797752809, | |
| "grad_norm": 11.203570365905762, | |
| "learning_rate": 1.205814801171595e-05, | |
| "loss": 0.4898, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.5730337078651684, | |
| "grad_norm": 16.303321838378906, | |
| "learning_rate": 1.2043229733412637e-05, | |
| "loss": 0.5359, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.595505617977528, | |
| "grad_norm": 12.990396499633789, | |
| "learning_rate": 1.2028073318125511e-05, | |
| "loss": 0.5608, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6179775280898876, | |
| "grad_norm": 15.660808563232422, | |
| "learning_rate": 1.2012679388875442e-05, | |
| "loss": 0.5824, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6404494382022472, | |
| "grad_norm": 20.047142028808594, | |
| "learning_rate": 1.1997048578446569e-05, | |
| "loss": 0.4947, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6629213483146068, | |
| "grad_norm": 15.481894493103027, | |
| "learning_rate": 1.1981181529360284e-05, | |
| "loss": 0.6934, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.6853932584269664, | |
| "grad_norm": 13.069948196411133, | |
| "learning_rate": 1.1965078893848829e-05, | |
| "loss": 0.5284, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.6853932584269664, | |
| "eval_loss": 0.5964965224266052, | |
| "eval_runtime": 28.8612, | |
| "eval_samples_per_second": 13.721, | |
| "eval_steps_per_second": 13.721, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7078651685393258, | |
| "grad_norm": 15.860553741455078, | |
| "learning_rate": 1.1948741333828482e-05, | |
| "loss": 0.5074, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7303370786516854, | |
| "grad_norm": 15.73456859588623, | |
| "learning_rate": 1.1932169520872344e-05, | |
| "loss": 0.5663, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7528089887640448, | |
| "grad_norm": 15.158873558044434, | |
| "learning_rate": 1.1915364136182738e-05, | |
| "loss": 0.5084, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.7752808988764044, | |
| "grad_norm": 18.966686248779297, | |
| "learning_rate": 1.189832587056321e-05, | |
| "loss": 0.5863, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.797752808988764, | |
| "grad_norm": 16.93968391418457, | |
| "learning_rate": 1.188105542439012e-05, | |
| "loss": 0.4685, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8202247191011236, | |
| "grad_norm": 15.844802856445312, | |
| "learning_rate": 1.186355350758387e-05, | |
| "loss": 0.4631, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8426966292134832, | |
| "grad_norm": 6.261096000671387, | |
| "learning_rate": 1.1845820839579707e-05, | |
| "loss": 0.4791, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8651685393258428, | |
| "grad_norm": 21.932397842407227, | |
| "learning_rate": 1.1827858149298162e-05, | |
| "loss": 0.5318, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.8876404494382022, | |
| "grad_norm": 20.80328369140625, | |
| "learning_rate": 1.1809666175115075e-05, | |
| "loss": 0.4769, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.9101123595505618, | |
| "grad_norm": 11.984331130981445, | |
| "learning_rate": 1.1791245664831252e-05, | |
| "loss": 0.4934, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9325842696629212, | |
| "grad_norm": 15.739178657531738, | |
| "learning_rate": 1.177259737564172e-05, | |
| "loss": 0.546, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9550561797752808, | |
| "grad_norm": 18.232080459594727, | |
| "learning_rate": 1.1753722074104613e-05, | |
| "loss": 0.5, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9775280898876404, | |
| "grad_norm": 19.222999572753906, | |
| "learning_rate": 1.1734620536109645e-05, | |
| "loss": 0.5939, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 20.398212432861328, | |
| "learning_rate": 1.1715293546846223e-05, | |
| "loss": 0.5186, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0224719101123596, | |
| "grad_norm": 15.60082721710205, | |
| "learning_rate": 1.1695741900771185e-05, | |
| "loss": 0.2977, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0224719101123596, | |
| "eval_loss": 0.5883856415748596, | |
| "eval_runtime": 28.4376, | |
| "eval_samples_per_second": 13.925, | |
| "eval_steps_per_second": 13.925, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.044943820224719, | |
| "grad_norm": 11.865720748901367, | |
| "learning_rate": 1.1675966401576116e-05, | |
| "loss": 0.3224, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.067415730337079, | |
| "grad_norm": 13.449054718017578, | |
| "learning_rate": 1.1655967862154335e-05, | |
| "loss": 0.3297, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.0898876404494384, | |
| "grad_norm": 18.293087005615234, | |
| "learning_rate": 1.1635747104567469e-05, | |
| "loss": 0.282, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1123595505617976, | |
| "grad_norm": 15.209367752075195, | |
| "learning_rate": 1.1615304960011663e-05, | |
| "loss": 0.3504, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.134831460674157, | |
| "grad_norm": 17.038095474243164, | |
| "learning_rate": 1.1594642268783414e-05, | |
| "loss": 0.2422, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.157303370786517, | |
| "grad_norm": 14.031147956848145, | |
| "learning_rate": 1.1573759880245028e-05, | |
| "loss": 0.2884, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.1797752808988764, | |
| "grad_norm": 16.43686294555664, | |
| "learning_rate": 1.1552658652789704e-05, | |
| "loss": 0.2729, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.202247191011236, | |
| "grad_norm": 18.40167808532715, | |
| "learning_rate": 1.153133945380626e-05, | |
| "loss": 0.3775, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.2247191011235956, | |
| "grad_norm": 11.52310848236084, | |
| "learning_rate": 1.1509803159643458e-05, | |
| "loss": 0.4183, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.247191011235955, | |
| "grad_norm": 17.900732040405273, | |
| "learning_rate": 1.1488050655574003e-05, | |
| "loss": 0.3087, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.2696629213483144, | |
| "grad_norm": 12.462130546569824, | |
| "learning_rate": 1.1466082835758142e-05, | |
| "loss": 0.371, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.292134831460674, | |
| "grad_norm": 15.067594528198242, | |
| "learning_rate": 1.1443900603206901e-05, | |
| "loss": 0.2704, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.3146067415730336, | |
| "grad_norm": 12.72071647644043, | |
| "learning_rate": 1.1421504869744979e-05, | |
| "loss": 0.2859, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.337078651685393, | |
| "grad_norm": 19.164932250976562, | |
| "learning_rate": 1.139889655597326e-05, | |
| "loss": 0.3761, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.359550561797753, | |
| "grad_norm": 12.603534698486328, | |
| "learning_rate": 1.1376076591230975e-05, | |
| "loss": 0.3465, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.359550561797753, | |
| "eval_loss": 0.5863937735557556, | |
| "eval_runtime": 28.6419, | |
| "eval_samples_per_second": 13.826, | |
| "eval_steps_per_second": 13.826, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.3820224719101124, | |
| "grad_norm": 13.150344848632812, | |
| "learning_rate": 1.1353045913557491e-05, | |
| "loss": 0.3628, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.404494382022472, | |
| "grad_norm": 13.253989219665527, | |
| "learning_rate": 1.1329805469653767e-05, | |
| "loss": 0.3521, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4269662921348316, | |
| "grad_norm": 15.47899055480957, | |
| "learning_rate": 1.1306356214843423e-05, | |
| "loss": 0.2289, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.449438202247191, | |
| "grad_norm": 20.19160270690918, | |
| "learning_rate": 1.1282699113033476e-05, | |
| "loss": 0.2723, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.4719101123595504, | |
| "grad_norm": 16.03728485107422, | |
| "learning_rate": 1.125883513667473e-05, | |
| "loss": 0.3398, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.49438202247191, | |
| "grad_norm": 21.989660263061523, | |
| "learning_rate": 1.123476526672178e-05, | |
| "loss": 0.3926, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.5168539325842696, | |
| "grad_norm": 16.33092498779297, | |
| "learning_rate": 1.1210490492592705e-05, | |
| "loss": 0.2243, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.539325842696629, | |
| "grad_norm": 17.589994430541992, | |
| "learning_rate": 1.118601181212839e-05, | |
| "loss": 0.3433, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.561797752808989, | |
| "grad_norm": 10.739886283874512, | |
| "learning_rate": 1.1161330231551516e-05, | |
| "loss": 0.2862, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.5842696629213484, | |
| "grad_norm": 15.978007316589355, | |
| "learning_rate": 1.1136446765425187e-05, | |
| "loss": 0.2902, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.606741573033708, | |
| "grad_norm": 12.640671730041504, | |
| "learning_rate": 1.1111362436611233e-05, | |
| "loss": 0.3325, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.629213483146067, | |
| "grad_norm": 16.383241653442383, | |
| "learning_rate": 1.1086078276228168e-05, | |
| "loss": 0.3235, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.6516853932584272, | |
| "grad_norm": 14.427544593811035, | |
| "learning_rate": 1.1060595323608789e-05, | |
| "loss": 0.3674, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.6741573033707864, | |
| "grad_norm": 12.737131118774414, | |
| "learning_rate": 1.1034914626257467e-05, | |
| "loss": 0.2976, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.696629213483146, | |
| "grad_norm": 13.494490623474121, | |
| "learning_rate": 1.1009037239807091e-05, | |
| "loss": 0.3386, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.696629213483146, | |
| "eval_loss": 0.5752944946289062, | |
| "eval_runtime": 28.5405, | |
| "eval_samples_per_second": 13.875, | |
| "eval_steps_per_second": 13.875, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.7191011235955056, | |
| "grad_norm": 18.343557357788086, | |
| "learning_rate": 1.098296422797566e-05, | |
| "loss": 0.4059, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.741573033707865, | |
| "grad_norm": 14.710756301879883, | |
| "learning_rate": 1.095669666252257e-05, | |
| "loss": 0.3214, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.764044943820225, | |
| "grad_norm": 14.75973892211914, | |
| "learning_rate": 1.0930235623204552e-05, | |
| "loss": 0.3608, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.7865168539325844, | |
| "grad_norm": 9.905698776245117, | |
| "learning_rate": 1.0903582197731294e-05, | |
| "loss": 0.299, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.808988764044944, | |
| "grad_norm": 12.442407608032227, | |
| "learning_rate": 1.0876737481720722e-05, | |
| "loss": 0.4008, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.831460674157303, | |
| "grad_norm": 11.765353202819824, | |
| "learning_rate": 1.0849702578653969e-05, | |
| "loss": 0.3743, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.853932584269663, | |
| "grad_norm": 21.303213119506836, | |
| "learning_rate": 1.0822478599830009e-05, | |
| "loss": 0.4142, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.8764044943820224, | |
| "grad_norm": 12.464083671569824, | |
| "learning_rate": 1.0795066664319983e-05, | |
| "loss": 0.3029, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.898876404494382, | |
| "grad_norm": 20.486202239990234, | |
| "learning_rate": 1.0767467898921198e-05, | |
| "loss": 0.3827, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.9213483146067416, | |
| "grad_norm": 16.888824462890625, | |
| "learning_rate": 1.0739683438110799e-05, | |
| "loss": 0.3854, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.943820224719101, | |
| "grad_norm": 17.157941818237305, | |
| "learning_rate": 1.0711714423999145e-05, | |
| "loss": 0.3273, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.966292134831461, | |
| "grad_norm": 16.582439422607422, | |
| "learning_rate": 1.0683562006282862e-05, | |
| "loss": 0.3334, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.98876404494382, | |
| "grad_norm": 19.243640899658203, | |
| "learning_rate": 1.0655227342197573e-05, | |
| "loss": 0.3262, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.0112359550561796, | |
| "grad_norm": 10.776522636413574, | |
| "learning_rate": 1.0626711596470345e-05, | |
| "loss": 0.2177, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.033707865168539, | |
| "grad_norm": 13.728617668151855, | |
| "learning_rate": 1.0598015941271792e-05, | |
| "loss": 0.1772, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.033707865168539, | |
| "eval_loss": 0.6071353554725647, | |
| "eval_runtime": 28.1538, | |
| "eval_samples_per_second": 14.066, | |
| "eval_steps_per_second": 14.066, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.056179775280899, | |
| "grad_norm": 15.800386428833008, | |
| "learning_rate": 1.0569141556167905e-05, | |
| "loss": 0.1571, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.0786516853932584, | |
| "grad_norm": 11.595304489135742, | |
| "learning_rate": 1.0540089628071565e-05, | |
| "loss": 0.1715, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.101123595505618, | |
| "grad_norm": 19.881999969482422, | |
| "learning_rate": 1.0510861351193747e-05, | |
| "loss": 0.1924, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.1235955056179776, | |
| "grad_norm": 18.425518035888672, | |
| "learning_rate": 1.0481457926994435e-05, | |
| "loss": 0.1942, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.146067415730337, | |
| "grad_norm": 19.82516098022461, | |
| "learning_rate": 1.045188056413323e-05, | |
| "loss": 0.1355, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.168539325842697, | |
| "grad_norm": 21.702138900756836, | |
| "learning_rate": 1.0422130478419676e-05, | |
| "loss": 0.1985, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.191011235955056, | |
| "grad_norm": 9.89587116241455, | |
| "learning_rate": 1.0392208892763269e-05, | |
| "loss": 0.1726, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.2134831460674156, | |
| "grad_norm": 18.09695053100586, | |
| "learning_rate": 1.0362117037123204e-05, | |
| "loss": 0.2026, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 3.235955056179775, | |
| "grad_norm": 18.88958168029785, | |
| "learning_rate": 1.0331856148457804e-05, | |
| "loss": 0.1631, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 3.258426966292135, | |
| "grad_norm": 17.335662841796875, | |
| "learning_rate": 1.030142747067368e-05, | |
| "loss": 0.162, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.2808988764044944, | |
| "grad_norm": 24.29629898071289, | |
| "learning_rate": 1.027083225457459e-05, | |
| "loss": 0.1695, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 3.303370786516854, | |
| "grad_norm": 11.860310554504395, | |
| "learning_rate": 1.0240071757810035e-05, | |
| "loss": 0.1698, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 3.3258426966292136, | |
| "grad_norm": 20.780662536621094, | |
| "learning_rate": 1.0209147244823564e-05, | |
| "loss": 0.1495, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 3.348314606741573, | |
| "grad_norm": 21.13768768310547, | |
| "learning_rate": 1.0178059986800773e-05, | |
| "loss": 0.1736, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 3.370786516853933, | |
| "grad_norm": 11.82013988494873, | |
| "learning_rate": 1.0146811261617086e-05, | |
| "loss": 0.2058, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.370786516853933, | |
| "eval_loss": 0.5937667489051819, | |
| "eval_runtime": 28.4093, | |
| "eval_samples_per_second": 13.939, | |
| "eval_steps_per_second": 13.939, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.393258426966292, | |
| "grad_norm": 7.896106719970703, | |
| "learning_rate": 1.0115402353785198e-05, | |
| "loss": 0.1455, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.4157303370786516, | |
| "grad_norm": 15.18211555480957, | |
| "learning_rate": 1.0083834554402293e-05, | |
| "loss": 0.1313, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.438202247191011, | |
| "grad_norm": 14.026439666748047, | |
| "learning_rate": 1.0052109161096959e-05, | |
| "loss": 0.2089, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.460674157303371, | |
| "grad_norm": 17.17043113708496, | |
| "learning_rate": 1.0020227477975852e-05, | |
| "loss": 0.214, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.4831460674157304, | |
| "grad_norm": 16.3658447265625, | |
| "learning_rate": 9.988190815570101e-06, | |
| "loss": 0.2524, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.50561797752809, | |
| "grad_norm": 13.139276504516602, | |
| "learning_rate": 9.95600049078141e-06, | |
| "loss": 0.1869, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.5280898876404496, | |
| "grad_norm": 12.490981101989746, | |
| "learning_rate": 9.923657826827957e-06, | |
| "loss": 0.1826, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.550561797752809, | |
| "grad_norm": 15.54690170288086, | |
| "learning_rate": 9.891164153189975e-06, | |
| "loss": 0.1897, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.5730337078651684, | |
| "grad_norm": 15.49406623840332, | |
| "learning_rate": 9.858520805555123e-06, | |
| "loss": 0.1425, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.595505617977528, | |
| "grad_norm": 15.071846008300781, | |
| "learning_rate": 9.825729125763562e-06, | |
| "loss": 0.2484, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.6179775280898876, | |
| "grad_norm": 17.417387008666992, | |
| "learning_rate": 9.792790461752813e-06, | |
| "loss": 0.1701, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.640449438202247, | |
| "grad_norm": 17.218463897705078, | |
| "learning_rate": 9.759706167502343e-06, | |
| "loss": 0.1796, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.662921348314607, | |
| "grad_norm": 15.873698234558105, | |
| "learning_rate": 9.726477602977906e-06, | |
| "loss": 0.197, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.6853932584269664, | |
| "grad_norm": 19.27431297302246, | |
| "learning_rate": 9.693106134075641e-06, | |
| "loss": 0.2239, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.7078651685393256, | |
| "grad_norm": 16.935728073120117, | |
| "learning_rate": 9.659593132565929e-06, | |
| "loss": 0.1388, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.7078651685393256, | |
| "eval_loss": 0.5907432436943054, | |
| "eval_runtime": 28.0316, | |
| "eval_samples_per_second": 14.127, | |
| "eval_steps_per_second": 14.127, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.7303370786516856, | |
| "grad_norm": 15.374393463134766, | |
| "learning_rate": 9.625939976037002e-06, | |
| "loss": 0.2022, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.752808988764045, | |
| "grad_norm": 13.357222557067871, | |
| "learning_rate": 9.59214804783831e-06, | |
| "loss": 0.1715, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.7752808988764044, | |
| "grad_norm": 15.346492767333984, | |
| "learning_rate": 9.558218737023673e-06, | |
| "loss": 0.2355, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.797752808988764, | |
| "grad_norm": 8.775595664978027, | |
| "learning_rate": 9.524153438294159e-06, | |
| "loss": 0.192, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.8202247191011236, | |
| "grad_norm": 18.73467254638672, | |
| "learning_rate": 9.489953551940784e-06, | |
| "loss": 0.226, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.842696629213483, | |
| "grad_norm": 16.3373966217041, | |
| "learning_rate": 9.455620483786914e-06, | |
| "loss": 0.2295, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 3.865168539325843, | |
| "grad_norm": 14.356298446655273, | |
| "learning_rate": 9.421155645130514e-06, | |
| "loss": 0.1508, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 3.8876404494382024, | |
| "grad_norm": 20.167428970336914, | |
| "learning_rate": 9.386560452686111e-06, | |
| "loss": 0.2378, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 3.9101123595505616, | |
| "grad_norm": 18.679561614990234, | |
| "learning_rate": 9.351836328526564e-06, | |
| "loss": 0.2386, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 3.932584269662921, | |
| "grad_norm": 13.456331253051758, | |
| "learning_rate": 9.316984700024613e-06, | |
| "loss": 0.1977, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.955056179775281, | |
| "grad_norm": 16.58353042602539, | |
| "learning_rate": 9.282006999794201e-06, | |
| "loss": 0.2215, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 3.9775280898876404, | |
| "grad_norm": 12.72409439086914, | |
| "learning_rate": 9.246904665631587e-06, | |
| "loss": 0.166, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 15.713534355163574, | |
| "learning_rate": 9.211679140456241e-06, | |
| "loss": 0.1595, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 4.022471910112359, | |
| "grad_norm": 17.47097396850586, | |
| "learning_rate": 9.176331872251538e-06, | |
| "loss": 0.1038, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 4.044943820224719, | |
| "grad_norm": 15.764228820800781, | |
| "learning_rate": 9.140864314005223e-06, | |
| "loss": 0.1084, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.044943820224719, | |
| "eval_loss": 0.6473093032836914, | |
| "eval_runtime": 28.5511, | |
| "eval_samples_per_second": 13.87, | |
| "eval_steps_per_second": 13.87, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.067415730337078, | |
| "grad_norm": 19.521255493164062, | |
| "learning_rate": 9.105277923649698e-06, | |
| "loss": 0.1045, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 4.089887640449438, | |
| "grad_norm": 6.521065711975098, | |
| "learning_rate": 9.069574164002092e-06, | |
| "loss": 0.0885, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 4.112359550561798, | |
| "grad_norm": 10.468367576599121, | |
| "learning_rate": 9.033754502704119e-06, | |
| "loss": 0.0933, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 4.134831460674158, | |
| "grad_norm": 8.916471481323242, | |
| "learning_rate": 8.997820412161765e-06, | |
| "loss": 0.1004, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 4.157303370786517, | |
| "grad_norm": 7.306938171386719, | |
| "learning_rate": 8.961773369484739e-06, | |
| "loss": 0.1019, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 4.179775280898877, | |
| "grad_norm": 16.291723251342773, | |
| "learning_rate": 8.925614856425787e-06, | |
| "loss": 0.1043, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 4.202247191011236, | |
| "grad_norm": 11.017843246459961, | |
| "learning_rate": 8.88934635931975e-06, | |
| "loss": 0.1468, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 4.224719101123595, | |
| "grad_norm": 11.328751564025879, | |
| "learning_rate": 8.852969369022494e-06, | |
| "loss": 0.1022, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 4.247191011235955, | |
| "grad_norm": 10.77855396270752, | |
| "learning_rate": 8.816485380849613e-06, | |
| "loss": 0.1098, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 4.269662921348314, | |
| "grad_norm": 21.963041305541992, | |
| "learning_rate": 8.779895894514961e-06, | |
| "loss": 0.0932, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.292134831460674, | |
| "grad_norm": 10.421232223510742, | |
| "learning_rate": 8.743202414069012e-06, | |
| "loss": 0.1115, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 4.314606741573034, | |
| "grad_norm": 12.438689231872559, | |
| "learning_rate": 8.706406447837024e-06, | |
| "loss": 0.093, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 4.337078651685394, | |
| "grad_norm": 15.851973533630371, | |
| "learning_rate": 8.669509508357052e-06, | |
| "loss": 0.1099, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 4.359550561797753, | |
| "grad_norm": 12.311159133911133, | |
| "learning_rate": 8.632513112317761e-06, | |
| "loss": 0.1131, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 4.382022471910112, | |
| "grad_norm": 13.830821990966797, | |
| "learning_rate": 8.59541878049609e-06, | |
| "loss": 0.1418, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 4.382022471910112, | |
| "eval_loss": 0.6235558390617371, | |
| "eval_runtime": 28.0922, | |
| "eval_samples_per_second": 14.096, | |
| "eval_steps_per_second": 14.096, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 4.404494382022472, | |
| "grad_norm": 20.932544708251953, | |
| "learning_rate": 8.558228037694728e-06, | |
| "loss": 0.0978, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 4.426966292134831, | |
| "grad_norm": 17.910070419311523, | |
| "learning_rate": 8.520942412679448e-06, | |
| "loss": 0.1239, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 4.449438202247191, | |
| "grad_norm": 13.0515718460083, | |
| "learning_rate": 8.483563438116257e-06, | |
| "loss": 0.0958, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 4.47191011235955, | |
| "grad_norm": 14.775212287902832, | |
| "learning_rate": 8.446092650508393e-06, | |
| "loss": 0.0913, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 4.49438202247191, | |
| "grad_norm": 14.85338306427002, | |
| "learning_rate": 8.408531590133173e-06, | |
| "loss": 0.1077, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.51685393258427, | |
| "grad_norm": 10.560493469238281, | |
| "learning_rate": 8.370881800978673e-06, | |
| "loss": 0.1092, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 4.539325842696629, | |
| "grad_norm": 11.044146537780762, | |
| "learning_rate": 8.333144830680262e-06, | |
| "loss": 0.1359, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 4.561797752808989, | |
| "grad_norm": 10.464937210083008, | |
| "learning_rate": 8.29532223045698e-06, | |
| "loss": 0.0996, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 4.584269662921348, | |
| "grad_norm": 11.029562950134277, | |
| "learning_rate": 8.257415555047786e-06, | |
| "loss": 0.1169, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 4.606741573033708, | |
| "grad_norm": 7.897212028503418, | |
| "learning_rate": 8.219426362647631e-06, | |
| "loss": 0.101, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 4.629213483146067, | |
| "grad_norm": 12.705263137817383, | |
| "learning_rate": 8.181356214843423e-06, | |
| "loss": 0.1036, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 4.651685393258427, | |
| "grad_norm": 18.093433380126953, | |
| "learning_rate": 8.143206676549826e-06, | |
| "loss": 0.1008, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 4.674157303370786, | |
| "grad_norm": 15.597516059875488, | |
| "learning_rate": 8.104979315944941e-06, | |
| "loss": 0.1057, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 4.696629213483146, | |
| "grad_norm": 11.599696159362793, | |
| "learning_rate": 8.066675704405837e-06, | |
| "loss": 0.102, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 4.719101123595506, | |
| "grad_norm": 13.57479190826416, | |
| "learning_rate": 8.028297416443953e-06, | |
| "loss": 0.1374, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.719101123595506, | |
| "eval_loss": 0.6200308203697205, | |
| "eval_runtime": 28.1044, | |
| "eval_samples_per_second": 14.09, | |
| "eval_steps_per_second": 14.09, | |
| "step": 2100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0762916960406733e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |