|
{ |
|
"best_metric": 0.9998782269849001, |
|
"best_model_checkpoint": "outputs/whisper-small-keyword-spotting-m/checkpoint-1068", |
|
"epoch": 4.996491228070175, |
|
"global_step": 1780, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 5.617977528089888e-05, |
|
"loss": 0.6888, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00011235955056179776, |
|
"loss": 0.6607, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00016853932584269662, |
|
"loss": 0.6216, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00022471910112359551, |
|
"loss": 0.5691, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0002808988764044944, |
|
"loss": 0.4873, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00033707865168539324, |
|
"loss": 0.4088, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00039325842696629214, |
|
"loss": 0.3054, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00044943820224719103, |
|
"loss": 0.2488, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0005056179775280899, |
|
"loss": 0.1907, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0005617977528089888, |
|
"loss": 0.1314, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0006179775280898876, |
|
"loss": 0.1293, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0006741573033707865, |
|
"loss": 0.113, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0007303370786516854, |
|
"loss": 0.0941, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0007865168539325843, |
|
"loss": 0.0778, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.0008426966292134832, |
|
"loss": 0.073, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.0008988764044943821, |
|
"loss": 0.0464, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.000955056179775281, |
|
"loss": 0.0567, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.0009987515605493133, |
|
"loss": 0.071, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.00099250936329588, |
|
"loss": 0.0482, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.000986267166042447, |
|
"loss": 0.0383, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0009800249687890138, |
|
"loss": 0.0461, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.0009737827715355806, |
|
"loss": 0.0349, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.0009675405742821474, |
|
"loss": 0.0265, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0009612983770287141, |
|
"loss": 0.024, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.000955056179775281, |
|
"loss": 0.041, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.0009488139825218477, |
|
"loss": 0.0247, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.0009425717852684144, |
|
"loss": 0.0253, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0009363295880149813, |
|
"loss": 0.0209, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.0009300873907615481, |
|
"loss": 0.0219, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.0009238451935081149, |
|
"loss": 0.0198, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.0009176029962546817, |
|
"loss": 0.0218, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.0009113607990012485, |
|
"loss": 0.0206, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.0009051186017478152, |
|
"loss": 0.0237, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.0008988764044943821, |
|
"loss": 0.0184, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.0008926342072409488, |
|
"loss": 0.0146, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9924500730638091, |
|
"eval_loss": 0.023062072694301605, |
|
"eval_runtime": 311.5051, |
|
"eval_samples_per_second": 26.362, |
|
"eval_steps_per_second": 0.825, |
|
"step": 356 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0008863920099875155, |
|
"loss": 0.0222, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.0008801498127340825, |
|
"loss": 0.0225, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0008739076154806492, |
|
"loss": 0.0191, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.000867665418227216, |
|
"loss": 0.0195, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.0008614232209737828, |
|
"loss": 0.0145, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.0008551810237203496, |
|
"loss": 0.0106, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.0008489388264669163, |
|
"loss": 0.0108, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.0008426966292134832, |
|
"loss": 0.0179, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.00083645443196005, |
|
"loss": 0.0153, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.0008302122347066168, |
|
"loss": 0.018, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.0008239700374531835, |
|
"loss": 0.021, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.0008177278401997503, |
|
"loss": 0.0178, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 0.0008114856429463171, |
|
"loss": 0.0348, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.0008052434456928838, |
|
"loss": 0.0146, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.0007990012484394507, |
|
"loss": 0.0109, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 0.0007927590511860175, |
|
"loss": 0.0131, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 0.0007865168539325843, |
|
"loss": 0.0163, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.0007802746566791511, |
|
"loss": 0.018, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.0007740324594257179, |
|
"loss": 0.0071, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.0007677902621722846, |
|
"loss": 0.0119, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 0.0007615480649188515, |
|
"loss": 0.0101, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.0007553058676654182, |
|
"loss": 0.0209, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 0.000749063670411985, |
|
"loss": 0.0133, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 0.0007428214731585519, |
|
"loss": 0.0099, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.0007365792759051186, |
|
"loss": 0.0174, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.0007303370786516854, |
|
"loss": 0.0113, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.0007240948813982522, |
|
"loss": 0.0081, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.000717852684144819, |
|
"loss": 0.014, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.0007116104868913857, |
|
"loss": 0.0129, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.0007053682896379526, |
|
"loss": 0.0074, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.0006991260923845194, |
|
"loss": 0.0115, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.0006928838951310862, |
|
"loss": 0.012, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 0.000686641697877653, |
|
"loss": 0.0071, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 0.0006803995006242197, |
|
"loss": 0.0056, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.0006741573033707865, |
|
"loss": 0.0128, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.0006679151061173533, |
|
"loss": 0.0124, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9976863127131028, |
|
"eval_loss": 0.010450506582856178, |
|
"eval_runtime": 311.6252, |
|
"eval_samples_per_second": 26.352, |
|
"eval_steps_per_second": 0.825, |
|
"step": 712 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 0.0006616729088639201, |
|
"loss": 0.0105, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 0.0006554307116104869, |
|
"loss": 0.0057, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.0006491885143570538, |
|
"loss": 0.0165, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 0.0006429463171036205, |
|
"loss": 0.0098, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.0006367041198501873, |
|
"loss": 0.0069, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 0.000630461922596754, |
|
"loss": 0.0118, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.0006242197253433209, |
|
"loss": 0.0146, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 0.0006179775280898876, |
|
"loss": 0.0066, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 0.0006117353308364544, |
|
"loss": 0.0125, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 0.0006054931335830213, |
|
"loss": 0.0115, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 0.000599250936329588, |
|
"loss": 0.0065, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 0.0005930087390761548, |
|
"loss": 0.0082, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 0.0005867665418227216, |
|
"loss": 0.0132, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 0.0005805243445692884, |
|
"loss": 0.0101, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 0.0005742821473158551, |
|
"loss": 0.0115, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 0.0005680399500624221, |
|
"loss": 0.0123, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 2.47, |
|
"learning_rate": 0.0005617977528089888, |
|
"loss": 0.0095, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 0.0005555555555555556, |
|
"loss": 0.0088, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 0.0005493133583021224, |
|
"loss": 0.0111, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 0.0005430711610486891, |
|
"loss": 0.0066, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 0.0005368289637952559, |
|
"loss": 0.01, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 0.0005305867665418227, |
|
"loss": 0.0143, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 0.0005243445692883895, |
|
"loss": 0.0062, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 0.0005181023720349563, |
|
"loss": 0.0104, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 0.0005118601747815232, |
|
"loss": 0.0051, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 0.0005056179775280899, |
|
"loss": 0.01, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 0.0004993757802746567, |
|
"loss": 0.0072, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 0.0004931335830212235, |
|
"loss": 0.006, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 0.0004868913857677903, |
|
"loss": 0.0066, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 0.00048064918851435705, |
|
"loss": 0.0085, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 0.00047440699126092385, |
|
"loss": 0.0124, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 0.00046816479400749064, |
|
"loss": 0.0082, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 0.00046192259675405744, |
|
"loss": 0.0083, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 0.00045568039950062423, |
|
"loss": 0.0075, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 0.00044943820224719103, |
|
"loss": 0.0091, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9998782269849001, |
|
"eval_loss": 0.0014641775051131845, |
|
"eval_runtime": 311.5509, |
|
"eval_samples_per_second": 26.358, |
|
"eval_steps_per_second": 0.825, |
|
"step": 1068 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.00044319600499375777, |
|
"loss": 0.01, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 0.0004369538077403246, |
|
"loss": 0.0126, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 0.0004307116104868914, |
|
"loss": 0.0112, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 0.00042446941323345816, |
|
"loss": 0.0145, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 0.000418227215980025, |
|
"loss": 0.0091, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 3.14, |
|
"learning_rate": 0.00041198501872659175, |
|
"loss": 0.0091, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"learning_rate": 0.00040574282147315855, |
|
"loss": 0.0055, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 0.00039950062421972534, |
|
"loss": 0.0087, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 3.23, |
|
"learning_rate": 0.00039325842696629214, |
|
"loss": 0.0158, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"learning_rate": 0.00038701622971285893, |
|
"loss": 0.0067, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 0.00038077403245942573, |
|
"loss": 0.007, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 3.31, |
|
"learning_rate": 0.0003745318352059925, |
|
"loss": 0.0057, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 0.0003682896379525593, |
|
"loss": 0.0078, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 3.37, |
|
"learning_rate": 0.0003620474406991261, |
|
"loss": 0.0063, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 0.00035580524344569286, |
|
"loss": 0.0054, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 3.42, |
|
"learning_rate": 0.0003495630461922597, |
|
"loss": 0.0091, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 0.0003433208489388265, |
|
"loss": 0.0047, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 0.00033707865168539324, |
|
"loss": 0.0126, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"learning_rate": 0.00033083645443196004, |
|
"loss": 0.0124, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 3.54, |
|
"learning_rate": 0.0003245942571785269, |
|
"loss": 0.0082, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 0.00031835205992509363, |
|
"loss": 0.0081, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 3.59, |
|
"learning_rate": 0.00031210986267166043, |
|
"loss": 0.0073, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"learning_rate": 0.0003058676654182272, |
|
"loss": 0.0044, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"learning_rate": 0.000299625468164794, |
|
"loss": 0.0082, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 0.0002933832709113608, |
|
"loss": 0.0039, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 0.00028714107365792756, |
|
"loss": 0.0089, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"learning_rate": 0.0002808988764044944, |
|
"loss": 0.0073, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 0.0002746566791510612, |
|
"loss": 0.0047, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 0.00026841448189762794, |
|
"loss": 0.0055, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"learning_rate": 0.00026217228464419474, |
|
"loss": 0.0051, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 0.0002559300873907616, |
|
"loss": 0.0078, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 0.00024968789013732833, |
|
"loss": 0.005, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 3.9, |
|
"learning_rate": 0.00024344569288389515, |
|
"loss": 0.0048, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"learning_rate": 0.00023720349563046192, |
|
"loss": 0.0062, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 0.00023096129837702872, |
|
"loss": 0.0139, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 3.99, |
|
"learning_rate": 0.00022471910112359551, |
|
"loss": 0.0101, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.9993911349245007, |
|
"eval_loss": 0.002844765782356262, |
|
"eval_runtime": 311.5882, |
|
"eval_samples_per_second": 26.355, |
|
"eval_steps_per_second": 0.825, |
|
"step": 1425 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 0.0002184769038701623, |
|
"loss": 0.0087, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 0.00021223470661672908, |
|
"loss": 0.0059, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 0.00020599250936329587, |
|
"loss": 0.0059, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 0.00019975031210986267, |
|
"loss": 0.0077, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 4.13, |
|
"learning_rate": 0.00019350811485642947, |
|
"loss": 0.0037, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 4.15, |
|
"learning_rate": 0.00018726591760299626, |
|
"loss": 0.0034, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 0.00018102372034956306, |
|
"loss": 0.0051, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 0.00017478152309612985, |
|
"loss": 0.0038, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 4.24, |
|
"learning_rate": 0.00016853932584269662, |
|
"loss": 0.0081, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 0.00016229712858926345, |
|
"loss": 0.0035, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 0.00015605493133583021, |
|
"loss": 0.0036, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 0.000149812734082397, |
|
"loss": 0.0106, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"learning_rate": 0.00014357053682896378, |
|
"loss": 0.0059, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 0.0001373283395755306, |
|
"loss": 0.0043, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 0.00013108614232209737, |
|
"loss": 0.0077, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 4.44, |
|
"learning_rate": 0.00012484394506866417, |
|
"loss": 0.0066, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 0.00011860174781523096, |
|
"loss": 0.0079, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"learning_rate": 0.00011235955056179776, |
|
"loss": 0.0043, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"learning_rate": 0.00010611735330836454, |
|
"loss": 0.0051, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 9.987515605493134e-05, |
|
"loss": 0.0057, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 4.58, |
|
"learning_rate": 9.363295880149813e-05, |
|
"loss": 0.0052, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 8.739076154806493e-05, |
|
"loss": 0.0114, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 4.63, |
|
"learning_rate": 8.114856429463172e-05, |
|
"loss": 0.006, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 4.66, |
|
"learning_rate": 7.49063670411985e-05, |
|
"loss": 0.0042, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 6.86641697877653e-05, |
|
"loss": 0.0058, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 4.72, |
|
"learning_rate": 6.242197253433208e-05, |
|
"loss": 0.0061, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"learning_rate": 5.617977528089888e-05, |
|
"loss": 0.004, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 4.993757802746567e-05, |
|
"loss": 0.005, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 4.3695380774032463e-05, |
|
"loss": 0.0091, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 4.83, |
|
"learning_rate": 3.745318352059925e-05, |
|
"loss": 0.0038, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 3.121098626716604e-05, |
|
"loss": 0.0056, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 2.4968789013732834e-05, |
|
"loss": 0.0028, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 1.8726591760299626e-05, |
|
"loss": 0.0046, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 4.94, |
|
"learning_rate": 1.2484394506866417e-05, |
|
"loss": 0.0041, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"learning_rate": 6.2421972534332085e-06, |
|
"loss": 0.0025, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.0094, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.9995129079396006, |
|
"eval_loss": 0.0021576141007244587, |
|
"eval_runtime": 311.5505, |
|
"eval_samples_per_second": 26.358, |
|
"eval_steps_per_second": 0.825, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"step": 1780, |
|
"total_flos": 2.8607738987116802e+19, |
|
"train_loss": 0.03821301929589905, |
|
"train_runtime": 10304.0646, |
|
"train_samples_per_second": 22.126, |
|
"train_steps_per_second": 0.173 |
|
} |
|
], |
|
"max_steps": 1780, |
|
"num_train_epochs": 5, |
|
"total_flos": 2.8607738987116802e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|