| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 30, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.022222222222222223, |
| "grad_norm": 0.7641538977622986, |
| "learning_rate": 9.99695413509548e-05, |
| "loss": 0.4714, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.044444444444444446, |
| "grad_norm": 0.05706603452563286, |
| "learning_rate": 9.987820251299122e-05, |
| "loss": 0.0194, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06666666666666667, |
| "grad_norm": 0.007792987395077944, |
| "learning_rate": 9.972609476841367e-05, |
| "loss": 0.0044, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.06666666666666667, |
| "eval_loss": 0.004266363102942705, |
| "eval_runtime": 215.0719, |
| "eval_samples_per_second": 9.299, |
| "eval_steps_per_second": 0.232, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08888888888888889, |
| "grad_norm": 0.013519592583179474, |
| "learning_rate": 9.951340343707852e-05, |
| "loss": 0.0041, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 0.017202626913785934, |
| "learning_rate": 9.924038765061042e-05, |
| "loss": 0.004, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "grad_norm": 0.009044675156474113, |
| "learning_rate": 9.890738003669029e-05, |
| "loss": 0.0039, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "eval_loss": 0.003868637140840292, |
| "eval_runtime": 214.9966, |
| "eval_samples_per_second": 9.302, |
| "eval_steps_per_second": 0.233, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.15555555555555556, |
| "grad_norm": 0.007734662853181362, |
| "learning_rate": 9.851478631379982e-05, |
| "loss": 0.0039, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.17777777777777778, |
| "grad_norm": 0.00847636815160513, |
| "learning_rate": 9.806308479691595e-05, |
| "loss": 0.0038, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.010983753949403763, |
| "learning_rate": 9.755282581475769e-05, |
| "loss": 0.0039, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 0.0037890244275331497, |
| "eval_runtime": 215.057, |
| "eval_samples_per_second": 9.3, |
| "eval_steps_per_second": 0.232, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 0.039544351398944855, |
| "learning_rate": 9.698463103929542e-05, |
| "loss": 0.0038, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.24444444444444444, |
| "grad_norm": 0.011466417461633682, |
| "learning_rate": 9.635919272833938e-05, |
| "loss": 0.0038, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 0.020617613568902016, |
| "learning_rate": 9.567727288213005e-05, |
| "loss": 0.0038, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "eval_loss": 0.0038526125717908144, |
| "eval_runtime": 214.983, |
| "eval_samples_per_second": 9.303, |
| "eval_steps_per_second": 0.233, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.28888888888888886, |
| "grad_norm": 0.012847725301980972, |
| "learning_rate": 9.493970231495835e-05, |
| "loss": 0.0038, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.3111111111111111, |
| "grad_norm": 0.02477414160966873, |
| "learning_rate": 9.414737964294636e-05, |
| "loss": 0.0038, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.014771663583815098, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 0.0038, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "eval_loss": 0.003661703085526824, |
| "eval_runtime": 215.005, |
| "eval_samples_per_second": 9.302, |
| "eval_steps_per_second": 0.233, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.017922697588801384, |
| "learning_rate": 9.24024048078213e-05, |
| "loss": 0.0037, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.37777777777777777, |
| "grad_norm": 0.033902786672115326, |
| "learning_rate": 9.145187862775209e-05, |
| "loss": 0.0036, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.020672762766480446, |
| "learning_rate": 9.045084971874738e-05, |
| "loss": 0.0036, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 0.0034463535994291306, |
| "eval_runtime": 215.0519, |
| "eval_samples_per_second": 9.3, |
| "eval_steps_per_second": 0.233, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.4222222222222222, |
| "grad_norm": 0.021494735032320023, |
| "learning_rate": 8.940053768033609e-05, |
| "loss": 0.0035, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 0.03562169522047043, |
| "learning_rate": 8.83022221559489e-05, |
| "loss": 0.0032, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4666666666666667, |
| "grad_norm": 0.014103920198976994, |
| "learning_rate": 8.715724127386972e-05, |
| "loss": 0.0034, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.4666666666666667, |
| "eval_loss": 0.003306599799543619, |
| "eval_runtime": 215.0517, |
| "eval_samples_per_second": 9.3, |
| "eval_steps_per_second": 0.233, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.4888888888888889, |
| "grad_norm": 0.019676154479384422, |
| "learning_rate": 8.596699001693255e-05, |
| "loss": 0.0032, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.5111111111111111, |
| "grad_norm": 0.011821040883660316, |
| "learning_rate": 8.473291852294987e-05, |
| "loss": 0.0034, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 0.010281533934175968, |
| "learning_rate": 8.345653031794292e-05, |
| "loss": 0.0028, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "eval_loss": 0.0027289013378322124, |
| "eval_runtime": 215.069, |
| "eval_samples_per_second": 9.299, |
| "eval_steps_per_second": 0.232, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 0.0231550931930542, |
| "learning_rate": 8.213938048432697e-05, |
| "loss": 0.0028, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5777777777777777, |
| "grad_norm": 0.02239130064845085, |
| "learning_rate": 8.07830737662829e-05, |
| "loss": 0.0029, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.022564468905329704, |
| "learning_rate": 7.938926261462366e-05, |
| "loss": 0.0026, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_loss": 0.002367404056712985, |
| "eval_runtime": 215.0087, |
| "eval_samples_per_second": 9.302, |
| "eval_steps_per_second": 0.233, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6222222222222222, |
| "grad_norm": 0.01638098619878292, |
| "learning_rate": 7.795964517353735e-05, |
| "loss": 0.0024, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.6444444444444445, |
| "grad_norm": 0.03278963640332222, |
| "learning_rate": 7.649596321166024e-05, |
| "loss": 0.0024, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.03586648404598236, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.0022, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "eval_loss": 0.002185327000916004, |
| "eval_runtime": 215.0432, |
| "eval_samples_per_second": 9.3, |
| "eval_steps_per_second": 0.233, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6888888888888889, |
| "grad_norm": 0.018881576135754585, |
| "learning_rate": 7.347357813929454e-05, |
| "loss": 0.0022, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.062055736780166626, |
| "learning_rate": 7.191855733945387e-05, |
| "loss": 0.0019, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.7333333333333333, |
| "grad_norm": 0.02213781699538231, |
| "learning_rate": 7.033683215379002e-05, |
| "loss": 0.0025, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7333333333333333, |
| "eval_loss": 0.002024175366386771, |
| "eval_runtime": 215.0776, |
| "eval_samples_per_second": 9.299, |
| "eval_steps_per_second": 0.232, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7555555555555555, |
| "grad_norm": 0.030647626146674156, |
| "learning_rate": 6.873032967079561e-05, |
| "loss": 0.0021, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.7777777777777778, |
| "grad_norm": 0.02288457192480564, |
| "learning_rate": 6.710100716628344e-05, |
| "loss": 0.002, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.021721992641687393, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 0.0019, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 0.0019156673224642873, |
| "eval_runtime": 215.0243, |
| "eval_samples_per_second": 9.301, |
| "eval_steps_per_second": 0.233, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.8222222222222222, |
| "grad_norm": 0.028448602184653282, |
| "learning_rate": 6.378186779084995e-05, |
| "loss": 0.0018, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.8444444444444444, |
| "grad_norm": 0.017557110637426376, |
| "learning_rate": 6.209609477998338e-05, |
| "loss": 0.0018, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.8666666666666667, |
| "grad_norm": 0.026540469378232956, |
| "learning_rate": 6.0395584540887963e-05, |
| "loss": 0.0021, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.8666666666666667, |
| "eval_loss": 0.0018348968587815762, |
| "eval_runtime": 214.9922, |
| "eval_samples_per_second": 9.303, |
| "eval_steps_per_second": 0.233, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.015121403150260448, |
| "learning_rate": 5.868240888334653e-05, |
| "loss": 0.0016, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9111111111111111, |
| "grad_norm": 0.035505831241607666, |
| "learning_rate": 5.695865504800327e-05, |
| "loss": 0.0016, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "grad_norm": 0.0437658354640007, |
| "learning_rate": 5.522642316338268e-05, |
| "loss": 0.0017, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "eval_loss": 0.001731859752908349, |
| "eval_runtime": 215.067, |
| "eval_samples_per_second": 9.299, |
| "eval_steps_per_second": 0.232, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9555555555555556, |
| "grad_norm": 0.02948390692472458, |
| "learning_rate": 5.348782368720626e-05, |
| "loss": 0.0018, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.9777777777777777, |
| "grad_norm": 0.031176254153251648, |
| "learning_rate": 5.174497483512506e-05, |
| "loss": 0.0017, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.020768124610185623, |
| "learning_rate": 5e-05, |
| "loss": 0.0017, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.0017366266110911965, |
| "eval_runtime": 215.0611, |
| "eval_samples_per_second": 9.3, |
| "eval_steps_per_second": 0.232, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.0222222222222221, |
| "grad_norm": 0.01959955506026745, |
| "learning_rate": 4.825502516487497e-05, |
| "loss": 0.0016, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.0444444444444445, |
| "grad_norm": 0.028036223724484444, |
| "learning_rate": 4.6512176312793736e-05, |
| "loss": 0.0017, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.017765428870916367, |
| "learning_rate": 4.477357683661734e-05, |
| "loss": 0.0017, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "eval_loss": 0.0016992929158732295, |
| "eval_runtime": 215.0184, |
| "eval_samples_per_second": 9.302, |
| "eval_steps_per_second": 0.233, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.0888888888888888, |
| "grad_norm": 0.023638742044568062, |
| "learning_rate": 4.3041344951996746e-05, |
| "loss": 0.0017, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 0.042691878974437714, |
| "learning_rate": 4.131759111665349e-05, |
| "loss": 0.0017, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.1333333333333333, |
| "grad_norm": 0.02193632535636425, |
| "learning_rate": 3.960441545911204e-05, |
| "loss": 0.0015, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.1333333333333333, |
| "eval_loss": 0.0016052849823608994, |
| "eval_runtime": 215.0768, |
| "eval_samples_per_second": 9.299, |
| "eval_steps_per_second": 0.232, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.1555555555555554, |
| "grad_norm": 0.02485978789627552, |
| "learning_rate": 3.790390522001662e-05, |
| "loss": 0.0014, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.1777777777777778, |
| "grad_norm": 0.031728435307741165, |
| "learning_rate": 3.6218132209150045e-05, |
| "loss": 0.0017, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.014328447170555592, |
| "learning_rate": 3.4549150281252636e-05, |
| "loss": 0.0015, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_loss": 0.001597618917003274, |
| "eval_runtime": 215.0417, |
| "eval_samples_per_second": 9.301, |
| "eval_steps_per_second": 0.233, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.2222222222222223, |
| "grad_norm": 0.03361846134066582, |
| "learning_rate": 3.289899283371657e-05, |
| "loss": 0.0014, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.2444444444444445, |
| "grad_norm": 0.025456570088863373, |
| "learning_rate": 3.12696703292044e-05, |
| "loss": 0.0013, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.2666666666666666, |
| "grad_norm": 0.022314872592687607, |
| "learning_rate": 2.9663167846209998e-05, |
| "loss": 0.0014, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.2666666666666666, |
| "eval_loss": 0.0015569779789075255, |
| "eval_runtime": 215.007, |
| "eval_samples_per_second": 9.302, |
| "eval_steps_per_second": 0.233, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.2888888888888888, |
| "grad_norm": 0.023371824994683266, |
| "learning_rate": 2.8081442660546125e-05, |
| "loss": 0.0013, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.3111111111111111, |
| "grad_norm": 0.05439267307519913, |
| "learning_rate": 2.6526421860705473e-05, |
| "loss": 0.0017, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.024191023781895638, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 0.0017, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "eval_loss": 0.001447125687263906, |
| "eval_runtime": 214.3438, |
| "eval_samples_per_second": 9.331, |
| "eval_steps_per_second": 0.233, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.3555555555555556, |
| "grad_norm": 0.028389817103743553, |
| "learning_rate": 2.350403678833976e-05, |
| "loss": 0.0015, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.3777777777777778, |
| "grad_norm": 0.02619648166000843, |
| "learning_rate": 2.2040354826462668e-05, |
| "loss": 0.0015, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.03590937331318855, |
| "learning_rate": 2.061073738537635e-05, |
| "loss": 0.0014, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.4, |
| "eval_loss": 0.0013506748946383595, |
| "eval_runtime": 214.2897, |
| "eval_samples_per_second": 9.333, |
| "eval_steps_per_second": 0.233, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.017976148054003716, |
| "learning_rate": 1.9216926233717085e-05, |
| "loss": 0.0012, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.4444444444444444, |
| "grad_norm": 0.020171979442238808, |
| "learning_rate": 1.7860619515673033e-05, |
| "loss": 0.0013, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.4666666666666668, |
| "grad_norm": 0.02652370184659958, |
| "learning_rate": 1.6543469682057106e-05, |
| "loss": 0.0012, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.4666666666666668, |
| "eval_loss": 0.001308620790950954, |
| "eval_runtime": 214.5085, |
| "eval_samples_per_second": 9.324, |
| "eval_steps_per_second": 0.233, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.488888888888889, |
| "grad_norm": 0.03529377654194832, |
| "learning_rate": 1.526708147705013e-05, |
| "loss": 0.001, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.511111111111111, |
| "grad_norm": 0.024932963773608208, |
| "learning_rate": 1.4033009983067452e-05, |
| "loss": 0.0014, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.5333333333333332, |
| "grad_norm": 0.033637382090091705, |
| "learning_rate": 1.2842758726130283e-05, |
| "loss": 0.0012, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.5333333333333332, |
| "eval_loss": 0.001253950409591198, |
| "eval_runtime": 214.564, |
| "eval_samples_per_second": 9.321, |
| "eval_steps_per_second": 0.233, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.5555555555555556, |
| "grad_norm": 0.02963503636419773, |
| "learning_rate": 1.1697777844051105e-05, |
| "loss": 0.0014, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.5777777777777777, |
| "grad_norm": 0.03318825364112854, |
| "learning_rate": 1.0599462319663905e-05, |
| "loss": 0.0013, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.03878423571586609, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 0.0012, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_loss": 0.0012294509215280414, |
| "eval_runtime": 214.5656, |
| "eval_samples_per_second": 9.321, |
| "eval_steps_per_second": 0.233, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.6222222222222222, |
| "grad_norm": 0.024266881868243217, |
| "learning_rate": 8.548121372247918e-06, |
| "loss": 0.0011, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.6444444444444444, |
| "grad_norm": 0.0440036915242672, |
| "learning_rate": 7.597595192178702e-06, |
| "loss": 0.001, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 0.06052534282207489, |
| "learning_rate": 6.698729810778065e-06, |
| "loss": 0.0011, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "eval_loss": 0.001226729596965015, |
| "eval_runtime": 214.5149, |
| "eval_samples_per_second": 9.323, |
| "eval_steps_per_second": 0.233, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.6888888888888889, |
| "grad_norm": 0.09705264121294022, |
| "learning_rate": 5.852620357053651e-06, |
| "loss": 0.0013, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.7111111111111112, |
| "grad_norm": 0.04110162332653999, |
| "learning_rate": 5.060297685041659e-06, |
| "loss": 0.001, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.7333333333333334, |
| "grad_norm": 0.024598602205514908, |
| "learning_rate": 4.322727117869951e-06, |
| "loss": 0.0009, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.7333333333333334, |
| "eval_loss": 0.0011484515853226185, |
| "eval_runtime": 214.5902, |
| "eval_samples_per_second": 9.32, |
| "eval_steps_per_second": 0.233, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.7555555555555555, |
| "grad_norm": 0.03334140032529831, |
| "learning_rate": 3.6408072716606346e-06, |
| "loss": 0.0011, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.04029354080557823, |
| "learning_rate": 3.0153689607045845e-06, |
| "loss": 0.0011, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.03721322864294052, |
| "learning_rate": 2.4471741852423237e-06, |
| "loss": 0.0012, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.8, |
| "eval_loss": 0.0011356236645951867, |
| "eval_runtime": 214.4957, |
| "eval_samples_per_second": 9.324, |
| "eval_steps_per_second": 0.233, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.8222222222222222, |
| "grad_norm": 0.03811410814523697, |
| "learning_rate": 1.9369152030840556e-06, |
| "loss": 0.0014, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.8444444444444446, |
| "grad_norm": 0.03319837152957916, |
| "learning_rate": 1.4852136862001764e-06, |
| "loss": 0.0011, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.8666666666666667, |
| "grad_norm": 0.04190688952803612, |
| "learning_rate": 1.0926199633097157e-06, |
| "loss": 0.0012, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.8666666666666667, |
| "eval_loss": 0.0011292207054793835, |
| "eval_runtime": 214.5416, |
| "eval_samples_per_second": 9.322, |
| "eval_steps_per_second": 0.233, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.8888888888888888, |
| "grad_norm": 0.02963530644774437, |
| "learning_rate": 7.596123493895991e-07, |
| "loss": 0.001, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.911111111111111, |
| "grad_norm": 0.03373124450445175, |
| "learning_rate": 4.865965629214819e-07, |
| "loss": 0.0012, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.9333333333333333, |
| "grad_norm": 0.03655708208680153, |
| "learning_rate": 2.7390523158633554e-07, |
| "loss": 0.0012, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.9333333333333333, |
| "eval_loss": 0.0011296386364847422, |
| "eval_runtime": 214.4559, |
| "eval_samples_per_second": 9.326, |
| "eval_steps_per_second": 0.233, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.9555555555555557, |
| "grad_norm": 0.0480160191655159, |
| "learning_rate": 1.2179748700879012e-07, |
| "loss": 0.001, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.9777777777777779, |
| "grad_norm": 0.03997540473937988, |
| "learning_rate": 3.04586490452119e-08, |
| "loss": 0.001, |
| "step": 890 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.038164664059877396, |
| "learning_rate": 0.0, |
| "loss": 0.001, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.001129699987359345, |
| "eval_runtime": 214.5889, |
| "eval_samples_per_second": 9.32, |
| "eval_steps_per_second": 0.233, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 900, |
| "total_flos": 3.320673433989153e+18, |
| "train_loss": 0.00749445440661576, |
| "train_runtime": 18806.7916, |
| "train_samples_per_second": 1.914, |
| "train_steps_per_second": 0.048 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 900, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 3.320673433989153e+18, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
