| { | |
| "best_metric": 0.9998191681735985, | |
| "best_model_checkpoint": "outputs/whisper-small-keyword-spotting/checkpoint-637", | |
| "epoch": 4.988235294117647, | |
| "global_step": 1590, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.289308176100629e-05, | |
| "loss": 0.6892, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00012578616352201257, | |
| "loss": 0.6605, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018867924528301889, | |
| "loss": 0.6284, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00025157232704402514, | |
| "loss": 0.577, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00031446540880503143, | |
| "loss": 0.5128, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00037735849056603777, | |
| "loss": 0.4114, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00044025157232704406, | |
| "loss": 0.3091, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0005031446540880503, | |
| "loss": 0.2469, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0005660377358490566, | |
| "loss": 0.1943, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0006289308176100629, | |
| "loss": 0.1421, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0006918238993710692, | |
| "loss": 0.1142, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0007547169811320755, | |
| "loss": 0.0857, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0008176100628930818, | |
| "loss": 0.0679, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0008805031446540881, | |
| "loss": 0.0663, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0009433962264150943, | |
| "loss": 0.0443, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0009993011879804333, | |
| "loss": 0.047, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.000992313067784766, | |
| "loss": 0.0362, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0009853249475890984, | |
| "loss": 0.0382, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0009783368273934311, | |
| "loss": 0.0522, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0009713487071977638, | |
| "loss": 0.022, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0009643605870020965, | |
| "loss": 0.0408, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0009573724668064291, | |
| "loss": 0.0392, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0009503843466107617, | |
| "loss": 0.0289, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0009433962264150943, | |
| "loss": 0.0249, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0009364081062194269, | |
| "loss": 0.0434, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0009294199860237596, | |
| "loss": 0.036, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0009224318658280922, | |
| "loss": 0.0372, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0009154437456324249, | |
| "loss": 0.0438, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0009084556254367576, | |
| "loss": 0.0273, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0009014675052410902, | |
| "loss": 0.022, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0008944793850454228, | |
| "loss": 0.0268, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9685352622061483, | |
| "eval_loss": 0.0720464363694191, | |
| "eval_runtime": 218.3559, | |
| "eval_samples_per_second": 25.326, | |
| "eval_steps_per_second": 0.792, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0008874912648497554, | |
| "loss": 0.0216, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0008805031446540881, | |
| "loss": 0.0128, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0008735150244584207, | |
| "loss": 0.0152, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0008665269042627534, | |
| "loss": 0.0225, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.000859538784067086, | |
| "loss": 0.022, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0008525506638714185, | |
| "loss": 0.019, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0008455625436757512, | |
| "loss": 0.0228, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0008385744234800838, | |
| "loss": 0.0206, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0008315863032844165, | |
| "loss": 0.0163, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0008245981830887491, | |
| "loss": 0.0193, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0008176100628930818, | |
| "loss": 0.0239, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0008106219426974144, | |
| "loss": 0.0268, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.000803633822501747, | |
| "loss": 0.0201, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0007966457023060797, | |
| "loss": 0.0159, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0007896575821104123, | |
| "loss": 0.0171, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.000782669461914745, | |
| "loss": 0.0201, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0007756813417190776, | |
| "loss": 0.016, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0007686932215234103, | |
| "loss": 0.0155, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0007617051013277429, | |
| "loss": 0.0144, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0007547169811320755, | |
| "loss": 0.0065, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0007477288609364081, | |
| "loss": 0.0117, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0007407407407407407, | |
| "loss": 0.0174, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0007337526205450734, | |
| "loss": 0.0117, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.000726764500349406, | |
| "loss": 0.0165, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0007197763801537387, | |
| "loss": 0.0152, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0007127882599580712, | |
| "loss": 0.0111, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0007058001397624039, | |
| "loss": 0.0119, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0006988120195667366, | |
| "loss": 0.0134, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0006918238993710692, | |
| "loss": 0.0166, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0006848357791754019, | |
| "loss": 0.0271, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0006778476589797345, | |
| "loss": 0.0186, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0006708595387840672, | |
| "loss": 0.0195, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9998191681735985, | |
| "eval_loss": 0.01826309971511364, | |
| "eval_runtime": 324.2355, | |
| "eval_samples_per_second": 17.056, | |
| "eval_steps_per_second": 0.534, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0006638714185883997, | |
| "loss": 0.0159, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0006568832983927324, | |
| "loss": 0.0125, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.000649895178197065, | |
| "loss": 0.0205, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0006429070580013976, | |
| "loss": 0.0187, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0006359189378057303, | |
| "loss": 0.0138, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0006289308176100629, | |
| "loss": 0.0104, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0006219426974143956, | |
| "loss": 0.0114, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0006149545772187281, | |
| "loss": 0.0128, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0006079664570230608, | |
| "loss": 0.0073, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0006009783368273934, | |
| "loss": 0.0056, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.000593990216631726, | |
| "loss": 0.0041, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0005870020964360588, | |
| "loss": 0.0106, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.0005800139762403914, | |
| "loss": 0.0126, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.000573025856044724, | |
| "loss": 0.0123, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0005660377358490566, | |
| "loss": 0.0117, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0005590496156533893, | |
| "loss": 0.0162, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0005520614954577219, | |
| "loss": 0.0107, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0005450733752620545, | |
| "loss": 0.0156, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0005380852550663872, | |
| "loss": 0.0108, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0005310971348707198, | |
| "loss": 0.0096, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0005241090146750524, | |
| "loss": 0.0139, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.000517120894479385, | |
| "loss": 0.0089, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0005101327742837177, | |
| "loss": 0.0097, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0005031446540880503, | |
| "loss": 0.0096, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.000496156533892383, | |
| "loss": 0.0063, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0004891684136967156, | |
| "loss": 0.0092, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.00048218029350104825, | |
| "loss": 0.0113, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.00047519217330538083, | |
| "loss": 0.0079, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00046820405310971346, | |
| "loss": 0.0112, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0004612159329140461, | |
| "loss": 0.0045, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.0004542278127183788, | |
| "loss": 0.0069, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0004472396925227114, | |
| "loss": 0.0111, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9168173598553345, | |
| "eval_loss": 0.20090103149414062, | |
| "eval_runtime": 323.1789, | |
| "eval_samples_per_second": 17.111, | |
| "eval_steps_per_second": 0.535, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.00044025157232704406, | |
| "loss": 0.0061, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0004332634521313767, | |
| "loss": 0.0069, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0004262753319357093, | |
| "loss": 0.017, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0004192872117400419, | |
| "loss": 0.0054, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.00041229909154437454, | |
| "loss": 0.0112, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.0004053109713487072, | |
| "loss": 0.0132, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.00039832285115303987, | |
| "loss": 0.0105, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0003913347309573725, | |
| "loss": 0.0121, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.00038434661076170514, | |
| "loss": 0.0077, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.00037735849056603777, | |
| "loss": 0.0039, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00037037037037037035, | |
| "loss": 0.0074, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.000363382250174703, | |
| "loss": 0.0107, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0003563941299790356, | |
| "loss": 0.0092, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.0003494060097833683, | |
| "loss": 0.0032, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.00034241788958770095, | |
| "loss": 0.0145, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 0.0003354297693920336, | |
| "loss": 0.0044, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.0003284416491963662, | |
| "loss": 0.0059, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.0003214535290006988, | |
| "loss": 0.0052, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.00031446540880503143, | |
| "loss": 0.0101, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.00030747728860936407, | |
| "loss": 0.0125, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.0003004891684136967, | |
| "loss": 0.0097, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.0002935010482180294, | |
| "loss": 0.0075, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.000286512928022362, | |
| "loss": 0.0057, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.00027952480782669466, | |
| "loss": 0.008, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.00027253668763102724, | |
| "loss": 0.0081, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.0002655485674353599, | |
| "loss": 0.0046, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.0002585604472396925, | |
| "loss": 0.0087, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 0.00025157232704402514, | |
| "loss": 0.0067, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.0002445842068483578, | |
| "loss": 0.0062, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.00023759608665269041, | |
| "loss": 0.0037, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00023060796645702305, | |
| "loss": 0.006, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.0002236198462613557, | |
| "loss": 0.0065, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8544303797468354, | |
| "eval_loss": 0.28469616174697876, | |
| "eval_runtime": 254.8847, | |
| "eval_samples_per_second": 21.696, | |
| "eval_steps_per_second": 0.679, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.00021663172606568835, | |
| "loss": 0.0092, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00020964360587002095, | |
| "loss": 0.0068, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.0002026554856743536, | |
| "loss": 0.0058, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00019566736547868625, | |
| "loss": 0.0083, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00018867924528301889, | |
| "loss": 0.0049, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.0001816911250873515, | |
| "loss": 0.0085, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.00017470300489168416, | |
| "loss": 0.0071, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 0.0001677148846960168, | |
| "loss": 0.0047, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 0.0001607267645003494, | |
| "loss": 0.0073, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00015373864430468203, | |
| "loss": 0.0051, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.0001467505241090147, | |
| "loss": 0.0061, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00013976240391334733, | |
| "loss": 0.0043, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.00013277428371767994, | |
| "loss": 0.0046, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 0.00012578616352201257, | |
| "loss": 0.0102, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.00011879804332634521, | |
| "loss": 0.0061, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00011180992313067786, | |
| "loss": 0.0089, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.00010482180293501048, | |
| "loss": 0.0038, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 9.783368273934313e-05, | |
| "loss": 0.0033, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 9.084556254367575e-05, | |
| "loss": 0.0078, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 8.38574423480084e-05, | |
| "loss": 0.006, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 7.686932215234102e-05, | |
| "loss": 0.0077, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 6.988120195667366e-05, | |
| "loss": 0.005, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 6.289308176100629e-05, | |
| "loss": 0.005, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 5.590496156533893e-05, | |
| "loss": 0.0046, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 4.891684136967156e-05, | |
| "loss": 0.0044, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.19287211740042e-05, | |
| "loss": 0.0051, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 3.494060097833683e-05, | |
| "loss": 0.0078, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 2.7952480782669464e-05, | |
| "loss": 0.0021, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 2.09643605870021e-05, | |
| "loss": 0.0043, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 1.3976240391334732e-05, | |
| "loss": 0.0041, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 6.988120195667366e-06, | |
| "loss": 0.0049, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.0086, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9168173598553345, | |
| "eval_loss": 0.18948502838611603, | |
| "eval_runtime": 224.532, | |
| "eval_samples_per_second": 24.629, | |
| "eval_steps_per_second": 0.77, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "step": 1590, | |
| "total_flos": 2.5540381823039996e+19, | |
| "train_loss": 0.042007273906525575, | |
| "train_runtime": 10719.7329, | |
| "train_samples_per_second": 19.016, | |
| "train_steps_per_second": 0.148 | |
| } | |
| ], | |
| "max_steps": 1590, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.5540381823039996e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |