|
{ |
|
"best_metric": 0.15721334517002106, |
|
"best_model_checkpoint": "voidful/wav2vec2-xlsr-53-espeak-librispeech-ft-all/checkpoint-2400", |
|
"epoch": 0.35046728971962615, |
|
"global_step": 2400, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2.34e-05, |
|
"loss": 0.2473, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4.68e-05, |
|
"loss": 0.2506, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 7.02e-05, |
|
"loss": 0.2243, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 9.36e-05, |
|
"loss": 0.2569, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.000117, |
|
"loss": 0.429, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0001404, |
|
"loss": 0.2216, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0001638, |
|
"loss": 0.2044, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0001872, |
|
"loss": 0.2037, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0002106, |
|
"loss": 0.2444, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.000234, |
|
"loss": 0.4259, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00023399430352013243, |
|
"loss": 0.2284, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00023398860704026487, |
|
"loss": 0.2131, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00023398291056039728, |
|
"loss": 0.2125, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0002339772140805297, |
|
"loss": 0.2449, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00023397151760066215, |
|
"loss": 0.3585, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00023396582112079458, |
|
"loss": 0.2464, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00023396012464092702, |
|
"loss": 0.2342, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00023395442816105943, |
|
"loss": 0.2261, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00023394873168119186, |
|
"loss": 0.2682, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0002339430352013243, |
|
"loss": 0.3853, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00023393733872145673, |
|
"loss": 0.2098, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00023393164224158917, |
|
"loss": 0.2502, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00023392594576172158, |
|
"loss": 0.2289, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.000233920249281854, |
|
"loss": 0.2539, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00023391455280198645, |
|
"loss": 0.3958, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00023390885632211888, |
|
"loss": 0.2165, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00023390315984225135, |
|
"loss": 0.215, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00023389746336238375, |
|
"loss": 0.2255, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0002338917668825162, |
|
"loss": 0.2072, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00023388607040264863, |
|
"loss": 0.3403, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00023388037392278106, |
|
"loss": 0.2147, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0002338746774429135, |
|
"loss": 0.1936, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0002338689809630459, |
|
"loss": 0.2352, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00023386328448317834, |
|
"loss": 0.2696, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00023385758800331078, |
|
"loss": 0.3343, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0002338518915234432, |
|
"loss": 0.202, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00023384619504357565, |
|
"loss": 0.2138, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00023384049856370806, |
|
"loss": 0.2142, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0002338348020838405, |
|
"loss": 0.2535, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00023382910560397293, |
|
"loss": 0.392, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"eval_cer": 0.13186392030593033, |
|
"eval_loss": 0.17454230785369873, |
|
"eval_runtime": 360.3554, |
|
"eval_samples_per_second": 14.516, |
|
"eval_steps_per_second": 0.486, |
|
"eval_wer": 0.9709424584209521, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00023382340912410536, |
|
"loss": 0.225, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0002338177126442378, |
|
"loss": 0.2077, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0002338120161643702, |
|
"loss": 0.2306, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00023380631968450264, |
|
"loss": 0.2642, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00023380119285262182, |
|
"loss": 0.3968, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00023379549637275425, |
|
"loss": 0.1817, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0002337897998928867, |
|
"loss": 0.2048, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00023378410341301912, |
|
"loss": 0.211, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00023377840693315156, |
|
"loss": 0.2555, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.000233772710453284, |
|
"loss": 0.3959, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00023376701397341643, |
|
"loss": 0.2082, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00023376131749354887, |
|
"loss": 0.1888, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0002337556210136813, |
|
"loss": 0.2242, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0002337499245338137, |
|
"loss": 0.2365, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00023374422805394615, |
|
"loss": 0.3182, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00023373853157407858, |
|
"loss": 0.2074, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00023373283509421102, |
|
"loss": 0.2005, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00023372713861434345, |
|
"loss": 0.2163, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0002337214421344759, |
|
"loss": 0.2461, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0002337157456546083, |
|
"loss": 0.3741, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00023371061882272747, |
|
"loss": 0.21, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0002337049223428599, |
|
"loss": 0.2095, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00023369922586299234, |
|
"loss": 0.1971, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00023369352938312478, |
|
"loss": 0.2462, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00023368783290325722, |
|
"loss": 0.3378, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00023368213642338962, |
|
"loss": 0.2211, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00023367643994352206, |
|
"loss": 0.1843, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0002336707434636545, |
|
"loss": 0.198, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00023366504698378693, |
|
"loss": 0.2688, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00023365935050391937, |
|
"loss": 0.3775, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00023365365402405177, |
|
"loss": 0.1945, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00023364795754418424, |
|
"loss": 0.2172, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00023364226106431667, |
|
"loss": 0.2145, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0002336365645844491, |
|
"loss": 0.2712, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00023363086810458154, |
|
"loss": 0.3371, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00023362517162471395, |
|
"loss": 0.2176, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0002336194751448464, |
|
"loss": 0.1926, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00023361377866497882, |
|
"loss": 0.2002, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00023360808218511126, |
|
"loss": 0.2345, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0002336023857052437, |
|
"loss": 0.3921, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_cer": 0.10110303888191077, |
|
"eval_loss": 0.17119961977005005, |
|
"eval_runtime": 359.8523, |
|
"eval_samples_per_second": 14.537, |
|
"eval_steps_per_second": 0.486, |
|
"eval_wer": 0.941884916841904, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0002335966892253761, |
|
"loss": 0.2154, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00023359099274550854, |
|
"loss": 0.213, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00023358529626564097, |
|
"loss": 0.1914, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0002335795997857734, |
|
"loss": 0.2188, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00023357390330590585, |
|
"loss": 0.344, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00023356820682603825, |
|
"loss": 0.1963, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002335625103461707, |
|
"loss": 0.198, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00023355681386630312, |
|
"loss": 0.2368, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00023355111738643556, |
|
"loss": 0.2333, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.000233545420906568, |
|
"loss": 0.3454, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002335397244267004, |
|
"loss": 0.21, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00023353402794683284, |
|
"loss": 0.1849, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00023352833146696528, |
|
"loss": 0.1982, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0002335226349870977, |
|
"loss": 0.2371, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00023351750815521691, |
|
"loss": 0.346, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00023351181167534935, |
|
"loss": 0.2024, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00023350611519548179, |
|
"loss": 0.1852, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0002335004187156142, |
|
"loss": 0.2196, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00023349472223574663, |
|
"loss": 0.2333, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00023348902575587906, |
|
"loss": 0.3275, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0002334833292760115, |
|
"loss": 0.1848, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00023347763279614394, |
|
"loss": 0.1784, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00023347193631627634, |
|
"loss": 0.1954, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00023346623983640878, |
|
"loss": 0.211, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00023346054335654122, |
|
"loss": 0.3037, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00023345484687667365, |
|
"loss": 0.2249, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0002334491503968061, |
|
"loss": 0.1877, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0002334434539169385, |
|
"loss": 0.1877, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00023343775743707093, |
|
"loss": 0.2514, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00023343206095720337, |
|
"loss": 0.3478, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0002334263644773358, |
|
"loss": 0.2016, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00023342066799746824, |
|
"loss": 0.1919, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00023341497151760065, |
|
"loss": 0.2027, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00023340927503773308, |
|
"loss": 0.2362, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00023340357855786552, |
|
"loss": 0.3776, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00023339788207799795, |
|
"loss": 0.2072, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0002333921855981304, |
|
"loss": 0.21, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0002333864891182628, |
|
"loss": 0.2136, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00023338079263839523, |
|
"loss": 0.2236, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00023337509615852767, |
|
"loss": 0.3523, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"eval_cer": 0.10916811901518182, |
|
"eval_loss": 0.16797101497650146, |
|
"eval_runtime": 357.2006, |
|
"eval_samples_per_second": 14.644, |
|
"eval_steps_per_second": 0.49, |
|
"eval_wer": 0.9625310648059644, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0002333693996786601, |
|
"loss": 0.1918, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00023336370319879254, |
|
"loss": 0.2046, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00023335800671892495, |
|
"loss": 0.2033, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00023335231023905738, |
|
"loss": 0.2217, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00023334661375918982, |
|
"loss": 0.332, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00023334091727932228, |
|
"loss": 0.2168, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00023333522079945472, |
|
"loss": 0.1957, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00023332952431958713, |
|
"loss": 0.1912, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00023332382783971956, |
|
"loss": 0.2479, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.000233318131359852, |
|
"loss": 0.3616, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00023331243487998443, |
|
"loss": 0.2171, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00023330673840011687, |
|
"loss": 0.1931, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00023330104192024928, |
|
"loss": 0.2406, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0002332953454403817, |
|
"loss": 0.2337, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00023328964896051415, |
|
"loss": 0.3704, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00023328395248064658, |
|
"loss": 0.2246, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00023327825600077902, |
|
"loss": 0.2027, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00023327255952091143, |
|
"loss": 0.2162, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00023326686304104386, |
|
"loss": 0.238, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0002332611665611763, |
|
"loss": 0.3327, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00023325547008130873, |
|
"loss": 0.2206, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00023324977360144117, |
|
"loss": 0.2087, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00023324407712157358, |
|
"loss": 0.2095, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.000233238380641706, |
|
"loss": 0.2335, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00023323268416183845, |
|
"loss": 0.3777, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00023322698768197088, |
|
"loss": 0.1873, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00023322129120210332, |
|
"loss": 0.1953, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00023321559472223573, |
|
"loss": 0.2137, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00023320989824236816, |
|
"loss": 0.2647, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0002332042017625006, |
|
"loss": 0.3354, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00023319850528263303, |
|
"loss": 0.2053, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00023319280880276547, |
|
"loss": 0.2, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00023318711232289788, |
|
"loss": 0.2223, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00023318141584303031, |
|
"loss": 0.2289, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00023317571936316275, |
|
"loss": 0.3805, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00023317002288329519, |
|
"loss": 0.2144, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00023316432640342762, |
|
"loss": 0.1852, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00023315862992356006, |
|
"loss": 0.1926, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0002331529334436925, |
|
"loss": 0.2233, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00023314723696382493, |
|
"loss": 0.3165, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"eval_cer": 0.10628673416007632, |
|
"eval_loss": 0.16792798042297363, |
|
"eval_runtime": 368.4708, |
|
"eval_samples_per_second": 14.197, |
|
"eval_steps_per_second": 0.475, |
|
"eval_wer": 0.9545020072643854, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00023314154048395736, |
|
"loss": 0.2055, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0002331358440040898, |
|
"loss": 0.1796, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0002331301475242222, |
|
"loss": 0.2126, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00023312445104435464, |
|
"loss": 0.2269, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00023311875456448708, |
|
"loss": 0.3827, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00023311305808461951, |
|
"loss": 0.2356, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00023310736160475195, |
|
"loss": 0.2162, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00023310166512488436, |
|
"loss": 0.2021, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0002330959686450168, |
|
"loss": 0.2629, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00023309027216514923, |
|
"loss": 0.3539, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00023308457568528166, |
|
"loss": 0.1938, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0002330788792054141, |
|
"loss": 0.2117, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0002330731827255465, |
|
"loss": 0.2037, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00023306748624567894, |
|
"loss": 0.2314, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00023306178976581138, |
|
"loss": 0.3471, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00023305609328594382, |
|
"loss": 0.206, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00023305039680607625, |
|
"loss": 0.1968, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00023304470032620866, |
|
"loss": 0.2046, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0002330390038463411, |
|
"loss": 0.2072, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00023303330736647353, |
|
"loss": 0.3442, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00023302761088660597, |
|
"loss": 0.2232, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002330219144067384, |
|
"loss": 0.1899, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002330162179268708, |
|
"loss": 0.2074, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00023301052144700325, |
|
"loss": 0.2778, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00023300482496713568, |
|
"loss": 0.367, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00023299912848726812, |
|
"loss": 0.2327, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00023299343200740055, |
|
"loss": 0.1955, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00023298773552753296, |
|
"loss": 0.2023, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0002329820390476654, |
|
"loss": 0.2603, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00023297634256779786, |
|
"loss": 0.3668, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0002329706460879303, |
|
"loss": 0.1981, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00023296494960806273, |
|
"loss": 0.2515, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00023295925312819514, |
|
"loss": 0.1854, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00023295355664832757, |
|
"loss": 0.2656, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00023294786016846, |
|
"loss": 0.3529, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00023294216368859245, |
|
"loss": 0.2059, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00023293646720872488, |
|
"loss": 0.1898, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0002329307707288573, |
|
"loss": 0.2393, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00023292507424898973, |
|
"loss": 0.2417, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00023291937776912216, |
|
"loss": 0.3633, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"eval_cer": 0.09183784796918316, |
|
"eval_loss": 0.1622667759656906, |
|
"eval_runtime": 378.6594, |
|
"eval_samples_per_second": 13.815, |
|
"eval_steps_per_second": 0.462, |
|
"eval_wer": 0.9124450391894475, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0002329136812892546, |
|
"loss": 0.2131, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00023290798480938703, |
|
"loss": 0.2096, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00023290228832951944, |
|
"loss": 0.2113, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00023289659184965188, |
|
"loss": 0.2428, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0002328908953697843, |
|
"loss": 0.364, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00023288519888991675, |
|
"loss": 0.1823, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00023287950241004918, |
|
"loss": 0.1999, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0002328738059301816, |
|
"loss": 0.1921, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00023286810945031403, |
|
"loss": 0.2185, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00023286241297044646, |
|
"loss": 0.3339, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0002328567164905789, |
|
"loss": 0.1856, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00023285102001071133, |
|
"loss": 0.1971, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00023284532353084374, |
|
"loss": 0.1749, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00023283962705097618, |
|
"loss": 0.202, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0002328339305711086, |
|
"loss": 0.3775, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00023282823409124105, |
|
"loss": 0.2029, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00023282253761137348, |
|
"loss": 0.2078, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0002328168411315059, |
|
"loss": 0.2169, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00023281114465163833, |
|
"loss": 0.2519, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00023280544817177076, |
|
"loss": 0.3249, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0002327997516919032, |
|
"loss": 0.1929, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00023279405521203563, |
|
"loss": 0.192, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00023278835873216807, |
|
"loss": 0.1953, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0002327826622523005, |
|
"loss": 0.2662, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00023277696577243294, |
|
"loss": 0.3353, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00023277126929256538, |
|
"loss": 0.2348, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0002327655728126978, |
|
"loss": 0.207, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00023275987633283022, |
|
"loss": 0.221, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00023275417985296266, |
|
"loss": 0.2328, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0002327484833730951, |
|
"loss": 0.3737, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00023274278689322753, |
|
"loss": 0.2214, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00023273709041335996, |
|
"loss": 0.2035, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00023273139393349237, |
|
"loss": 0.2373, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0002327256974536248, |
|
"loss": 0.2607, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00023272000097375724, |
|
"loss": 0.3317, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00023271430449388968, |
|
"loss": 0.1983, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00023270860801402211, |
|
"loss": 0.2118, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00023270291153415452, |
|
"loss": 0.2143, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00023269721505428696, |
|
"loss": 0.2277, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.0002326915185744194, |
|
"loss": 0.3574, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"eval_cer": 0.0956312051182347, |
|
"eval_loss": 0.15721334517002106, |
|
"eval_runtime": 363.9845, |
|
"eval_samples_per_second": 14.371, |
|
"eval_steps_per_second": 0.481, |
|
"eval_wer": 0.9361498757407761, |
|
"step": 2400 |
|
} |
|
], |
|
"max_steps": 410880, |
|
"num_train_epochs": 60, |
|
"total_flos": 2.442475321551867e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|