| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.8, | |
| "global_step": 36000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 16.4891, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 7.453255653381348, | |
| "eval_runtime": 17.1907, | |
| "eval_samples_per_second": 4.654, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.999555535801592e-05, | |
| "loss": 3.6143, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 3.6875462532043457, | |
| "eval_runtime": 17.2862, | |
| "eval_samples_per_second": 4.628, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.999111071603183e-05, | |
| "loss": 3.0476, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 3.5380682945251465, | |
| "eval_runtime": 17.234, | |
| "eval_samples_per_second": 4.642, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.998666607404774e-05, | |
| "loss": 3.0296, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 3.5734219551086426, | |
| "eval_runtime": 17.3146, | |
| "eval_samples_per_second": 4.62, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.998222143206365e-05, | |
| "loss": 3.04, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 3.5502994060516357, | |
| "eval_runtime": 17.3078, | |
| "eval_samples_per_second": 4.622, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.997777679007957e-05, | |
| "loss": Infinity, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 3.3948416709899902, | |
| "eval_runtime": 17.323, | |
| "eval_samples_per_second": 4.618, | |
| "eval_wer": 1.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.997333214809547e-05, | |
| "loss": NaN, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 3.2798409461975098, | |
| "eval_runtime": 17.422, | |
| "eval_samples_per_second": 4.592, | |
| "eval_wer": 1.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.996888750611138e-05, | |
| "loss": NaN, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 3.1693687438964844, | |
| "eval_runtime": 17.3276, | |
| "eval_samples_per_second": 4.617, | |
| "eval_wer": 1.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.99644428641273e-05, | |
| "loss": NaN, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 3.0904104709625244, | |
| "eval_runtime": 17.3305, | |
| "eval_samples_per_second": 4.616, | |
| "eval_wer": 1.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.995999822214322e-05, | |
| "loss": NaN, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 2.940812587738037, | |
| "eval_runtime": 17.5447, | |
| "eval_samples_per_second": 4.56, | |
| "eval_wer": 0.9968992248062015, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.995555358015912e-05, | |
| "loss": NaN, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.078176259994507, | |
| "eval_runtime": 17.4887, | |
| "eval_samples_per_second": 4.574, | |
| "eval_wer": 0.9906976744186047, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.995110893817503e-05, | |
| "loss": NaN, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.6720739603042603, | |
| "eval_runtime": 17.4985, | |
| "eval_samples_per_second": 4.572, | |
| "eval_wer": 0.9023255813953488, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.994666429619095e-05, | |
| "loss": NaN, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.5600072145462036, | |
| "eval_runtime": 17.6605, | |
| "eval_samples_per_second": 4.53, | |
| "eval_wer": 0.8635658914728682, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.994221965420686e-05, | |
| "loss": NaN, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.4188871383666992, | |
| "eval_runtime": 17.4862, | |
| "eval_samples_per_second": 4.575, | |
| "eval_wer": 0.8356589147286821, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.993777501222276e-05, | |
| "loss": NaN, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.2592538595199585, | |
| "eval_runtime": 17.3951, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.7906976744186046, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.993333037023869e-05, | |
| "loss": NaN, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.1907216310501099, | |
| "eval_runtime": 17.4046, | |
| "eval_samples_per_second": 4.596, | |
| "eval_wer": 0.7565891472868217, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.99288857282546e-05, | |
| "loss": NaN, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.3044092655181885, | |
| "eval_runtime": 17.3968, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.7829457364341085, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.992444108627051e-05, | |
| "loss": NaN, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.1965358257293701, | |
| "eval_runtime": 17.3177, | |
| "eval_samples_per_second": 4.62, | |
| "eval_wer": 0.7503875968992249, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.991999644428641e-05, | |
| "loss": NaN, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.1158918142318726, | |
| "eval_runtime": 17.4315, | |
| "eval_samples_per_second": 4.589, | |
| "eval_wer": 0.7007751937984497, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.991555180230233e-05, | |
| "loss": NaN, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.139773964881897, | |
| "eval_runtime": 17.4304, | |
| "eval_samples_per_second": 4.59, | |
| "eval_wer": 0.7286821705426356, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.991110716031824e-05, | |
| "loss": NaN, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.9968563318252563, | |
| "eval_runtime": 17.3268, | |
| "eval_samples_per_second": 4.617, | |
| "eval_wer": 0.6821705426356589, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.990666251833415e-05, | |
| "loss": NaN, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.9753952026367188, | |
| "eval_runtime": 17.36, | |
| "eval_samples_per_second": 4.608, | |
| "eval_wer": 0.6666666666666666, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.990221787635007e-05, | |
| "loss": NaN, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.9655939340591431, | |
| "eval_runtime": 17.3128, | |
| "eval_samples_per_second": 4.621, | |
| "eval_wer": 0.6651162790697674, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.989777323436598e-05, | |
| "loss": NaN, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.9793145060539246, | |
| "eval_runtime": 17.3154, | |
| "eval_samples_per_second": 4.62, | |
| "eval_wer": 0.6604651162790698, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.989332859238189e-05, | |
| "loss": NaN, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.9911659955978394, | |
| "eval_runtime": 17.3868, | |
| "eval_samples_per_second": 4.601, | |
| "eval_wer": 0.6558139534883721, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.98888839503978e-05, | |
| "loss": NaN, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.9256990551948547, | |
| "eval_runtime": 17.3404, | |
| "eval_samples_per_second": 4.613, | |
| "eval_wer": 0.6713178294573643, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.988443930841371e-05, | |
| "loss": NaN, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.8806975483894348, | |
| "eval_runtime": 17.3516, | |
| "eval_samples_per_second": 4.611, | |
| "eval_wer": 0.6325581395348837, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.987999466642962e-05, | |
| "loss": NaN, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.9201020002365112, | |
| "eval_runtime": 17.4402, | |
| "eval_samples_per_second": 4.587, | |
| "eval_wer": 0.6604651162790698, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.987555002444555e-05, | |
| "loss": NaN, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.8914031982421875, | |
| "eval_runtime": 17.3777, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.6248062015503876, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.987110538246144e-05, | |
| "loss": NaN, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.8329198956489563, | |
| "eval_runtime": 17.334, | |
| "eval_samples_per_second": 4.615, | |
| "eval_wer": 0.6186046511627907, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.986666074047736e-05, | |
| "loss": NaN, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.8818947672843933, | |
| "eval_runtime": 17.4737, | |
| "eval_samples_per_second": 4.578, | |
| "eval_wer": 0.6248062015503876, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.986221609849327e-05, | |
| "loss": NaN, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.9315568804740906, | |
| "eval_runtime": 17.3225, | |
| "eval_samples_per_second": 4.618, | |
| "eval_wer": 0.6155038759689923, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.985777145650919e-05, | |
| "loss": NaN, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.891169548034668, | |
| "eval_runtime": 17.3188, | |
| "eval_samples_per_second": 4.619, | |
| "eval_wer": 0.6062015503875969, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.985332681452509e-05, | |
| "loss": NaN, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.8204320073127747, | |
| "eval_runtime": 17.2776, | |
| "eval_samples_per_second": 4.63, | |
| "eval_wer": 0.6217054263565891, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.9848882172541e-05, | |
| "loss": NaN, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.7907635569572449, | |
| "eval_runtime": 17.4135, | |
| "eval_samples_per_second": 4.594, | |
| "eval_wer": 0.6124031007751938, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.984443753055693e-05, | |
| "loss": NaN, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.7738734483718872, | |
| "eval_runtime": 17.2483, | |
| "eval_samples_per_second": 4.638, | |
| "eval_wer": 0.5922480620155038, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.983999288857284e-05, | |
| "loss": NaN, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.8443992733955383, | |
| "eval_runtime": 17.3843, | |
| "eval_samples_per_second": 4.602, | |
| "eval_wer": 0.6341085271317829, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.983554824658873e-05, | |
| "loss": NaN, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.8256866335868835, | |
| "eval_runtime": 17.372, | |
| "eval_samples_per_second": 4.605, | |
| "eval_wer": 0.6031007751937985, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.983110360460466e-05, | |
| "loss": NaN, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.8002794981002808, | |
| "eval_runtime": 17.2749, | |
| "eval_samples_per_second": 4.631, | |
| "eval_wer": 0.5953488372093023, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.982665896262057e-05, | |
| "loss": NaN, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.7931162118911743, | |
| "eval_runtime": 17.3293, | |
| "eval_samples_per_second": 4.616, | |
| "eval_wer": 0.5891472868217055, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.982221432063648e-05, | |
| "loss": NaN, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.7502455711364746, | |
| "eval_runtime": 17.2431, | |
| "eval_samples_per_second": 4.64, | |
| "eval_wer": 0.5751937984496124, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.981776967865238e-05, | |
| "loss": NaN, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.752181887626648, | |
| "eval_runtime": 17.2919, | |
| "eval_samples_per_second": 4.626, | |
| "eval_wer": 0.5705426356589147, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.98133250366683e-05, | |
| "loss": NaN, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 0.8146766424179077, | |
| "eval_runtime": 17.3018, | |
| "eval_samples_per_second": 4.624, | |
| "eval_wer": 0.5767441860465117, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.980888039468422e-05, | |
| "loss": NaN, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.7647853493690491, | |
| "eval_runtime": 17.3393, | |
| "eval_samples_per_second": 4.614, | |
| "eval_wer": 0.5674418604651162, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.980443575270013e-05, | |
| "loss": NaN, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.8016502261161804, | |
| "eval_runtime": 17.3476, | |
| "eval_samples_per_second": 4.612, | |
| "eval_wer": 0.5751937984496124, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.979999111071604e-05, | |
| "loss": NaN, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.779055118560791, | |
| "eval_runtime": 17.31, | |
| "eval_samples_per_second": 4.622, | |
| "eval_wer": 0.5937984496124031, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.979554646873195e-05, | |
| "loss": NaN, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.7754725813865662, | |
| "eval_runtime": 17.4442, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.5705426356589147, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.979110182674786e-05, | |
| "loss": NaN, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.7565076947212219, | |
| "eval_runtime": 17.3494, | |
| "eval_samples_per_second": 4.611, | |
| "eval_wer": 0.5875968992248062, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.978665718476377e-05, | |
| "loss": NaN, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.7285895347595215, | |
| "eval_runtime": 17.2713, | |
| "eval_samples_per_second": 4.632, | |
| "eval_wer": 0.5720930232558139, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.978221254277968e-05, | |
| "loss": NaN, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.7842145562171936, | |
| "eval_runtime": 17.3978, | |
| "eval_samples_per_second": 4.598, | |
| "eval_wer": 0.5782945736434109, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.97777679007956e-05, | |
| "loss": NaN, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.7423646450042725, | |
| "eval_runtime": 17.3779, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.5767441860465117, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.977332325881152e-05, | |
| "loss": NaN, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.7223240733146667, | |
| "eval_runtime": 17.3244, | |
| "eval_samples_per_second": 4.618, | |
| "eval_wer": 0.5627906976744186, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.976887861682742e-05, | |
| "loss": NaN, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.8006032705307007, | |
| "eval_runtime": 17.3458, | |
| "eval_samples_per_second": 4.612, | |
| "eval_wer": 0.5767441860465117, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.976443397484333e-05, | |
| "loss": NaN, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.777060866355896, | |
| "eval_runtime": 17.3762, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.5891472868217055, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.975998933285924e-05, | |
| "loss": NaN, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.8182930946350098, | |
| "eval_runtime": 17.3543, | |
| "eval_samples_per_second": 4.61, | |
| "eval_wer": 0.5488372093023256, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.975554469087516e-05, | |
| "loss": NaN, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.8928201794624329, | |
| "eval_runtime": 17.3737, | |
| "eval_samples_per_second": 4.605, | |
| "eval_wer": 0.5534883720930233, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.975110004889106e-05, | |
| "loss": NaN, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.8263363838195801, | |
| "eval_runtime": 17.3975, | |
| "eval_samples_per_second": 4.598, | |
| "eval_wer": 0.57984496124031, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.974665540690697e-05, | |
| "loss": NaN, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.785165548324585, | |
| "eval_runtime": 17.3799, | |
| "eval_samples_per_second": 4.603, | |
| "eval_wer": 0.5565891472868217, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.97422107649229e-05, | |
| "loss": NaN, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.7735041379928589, | |
| "eval_runtime": 17.2943, | |
| "eval_samples_per_second": 4.626, | |
| "eval_wer": 0.5488372093023256, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.973776612293881e-05, | |
| "loss": NaN, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.7752858400344849, | |
| "eval_runtime": 17.3964, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.5596899224806201, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.97333214809547e-05, | |
| "loss": NaN, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.7791776657104492, | |
| "eval_runtime": 17.3616, | |
| "eval_samples_per_second": 4.608, | |
| "eval_wer": 0.5658914728682171, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.972887683897063e-05, | |
| "loss": NaN, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.9012916684150696, | |
| "eval_runtime": 17.2944, | |
| "eval_samples_per_second": 4.626, | |
| "eval_wer": 0.5612403100775194, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.972443219698654e-05, | |
| "loss": NaN, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.819232165813446, | |
| "eval_runtime": 17.2609, | |
| "eval_samples_per_second": 4.635, | |
| "eval_wer": 0.5503875968992248, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.971998755500245e-05, | |
| "loss": NaN, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.7208074331283569, | |
| "eval_runtime": 17.342, | |
| "eval_samples_per_second": 4.613, | |
| "eval_wer": 0.5565891472868217, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.971554291301835e-05, | |
| "loss": NaN, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.8276127576828003, | |
| "eval_runtime": 17.2796, | |
| "eval_samples_per_second": 4.63, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.971109827103428e-05, | |
| "loss": NaN, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.6788396835327148, | |
| "eval_runtime": 17.3982, | |
| "eval_samples_per_second": 4.598, | |
| "eval_wer": 0.537984496124031, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.970665362905019e-05, | |
| "loss": NaN, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.7748047113418579, | |
| "eval_runtime": 17.3475, | |
| "eval_samples_per_second": 4.612, | |
| "eval_wer": 0.5581395348837209, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.97022089870661e-05, | |
| "loss": NaN, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.728911280632019, | |
| "eval_runtime": 17.3832, | |
| "eval_samples_per_second": 4.602, | |
| "eval_wer": 0.5581395348837209, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.969776434508201e-05, | |
| "loss": NaN, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.711087703704834, | |
| "eval_runtime": 17.3922, | |
| "eval_samples_per_second": 4.6, | |
| "eval_wer": 0.5674418604651162, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.969331970309792e-05, | |
| "loss": NaN, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.6784836649894714, | |
| "eval_runtime": 17.4107, | |
| "eval_samples_per_second": 4.595, | |
| "eval_wer": 0.5441860465116279, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.968887506111383e-05, | |
| "loss": NaN, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.6995629072189331, | |
| "eval_runtime": 17.3942, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.5503875968992248, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.968443041912974e-05, | |
| "loss": NaN, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.7547804713249207, | |
| "eval_runtime": 17.3298, | |
| "eval_samples_per_second": 4.616, | |
| "eval_wer": 0.5519379844961241, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.967998577714565e-05, | |
| "loss": NaN, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.7266980409622192, | |
| "eval_runtime": 17.3345, | |
| "eval_samples_per_second": 4.615, | |
| "eval_wer": 0.5720930232558139, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.967554113516157e-05, | |
| "loss": NaN, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.7356825470924377, | |
| "eval_runtime": 17.3815, | |
| "eval_samples_per_second": 4.603, | |
| "eval_wer": 0.5457364341085271, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.967109649317749e-05, | |
| "loss": NaN, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6732177734375, | |
| "eval_runtime": 17.3666, | |
| "eval_samples_per_second": 4.607, | |
| "eval_wer": 0.5643410852713179, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.966665185119339e-05, | |
| "loss": NaN, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.6623905897140503, | |
| "eval_runtime": 17.3816, | |
| "eval_samples_per_second": 4.603, | |
| "eval_wer": 0.5457364341085271, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.96622072092093e-05, | |
| "loss": NaN, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.6646267175674438, | |
| "eval_runtime": 17.3087, | |
| "eval_samples_per_second": 4.622, | |
| "eval_wer": 0.5255813953488372, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.965776256722521e-05, | |
| "loss": NaN, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 0.6843534708023071, | |
| "eval_runtime": 17.3598, | |
| "eval_samples_per_second": 4.608, | |
| "eval_wer": 0.5472868217054263, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.965331792524114e-05, | |
| "loss": NaN, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 0.6367862224578857, | |
| "eval_runtime": 17.4366, | |
| "eval_samples_per_second": 4.588, | |
| "eval_wer": 0.5286821705426357, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.964887328325703e-05, | |
| "loss": NaN, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.6785103678703308, | |
| "eval_runtime": 17.4096, | |
| "eval_samples_per_second": 4.595, | |
| "eval_wer": 0.5596899224806201, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.964442864127294e-05, | |
| "loss": NaN, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.7153035998344421, | |
| "eval_runtime": 17.3734, | |
| "eval_samples_per_second": 4.605, | |
| "eval_wer": 0.5457364341085271, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.963998399928887e-05, | |
| "loss": NaN, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.6959100961685181, | |
| "eval_runtime": 17.3566, | |
| "eval_samples_per_second": 4.609, | |
| "eval_wer": 0.5395348837209303, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.963553935730478e-05, | |
| "loss": NaN, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.6857380270957947, | |
| "eval_runtime": 17.3435, | |
| "eval_samples_per_second": 4.613, | |
| "eval_wer": 0.5317829457364341, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.963109471532068e-05, | |
| "loss": NaN, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.6444656848907471, | |
| "eval_runtime": 17.3941, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.5333333333333333, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.96266500733366e-05, | |
| "loss": NaN, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.7181092500686646, | |
| "eval_runtime": 17.4167, | |
| "eval_samples_per_second": 4.593, | |
| "eval_wer": 0.5224806201550387, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 9.962220543135251e-05, | |
| "loss": NaN, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.7113466262817383, | |
| "eval_runtime": 17.4584, | |
| "eval_samples_per_second": 4.582, | |
| "eval_wer": 0.5333333333333333, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.961776078936843e-05, | |
| "loss": NaN, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.737747073173523, | |
| "eval_runtime": 17.3407, | |
| "eval_samples_per_second": 4.613, | |
| "eval_wer": 0.5472868217054263, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.961331614738432e-05, | |
| "loss": NaN, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.7109254598617554, | |
| "eval_runtime": 17.4806, | |
| "eval_samples_per_second": 4.577, | |
| "eval_wer": 0.5534883720930233, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 9.960887150540025e-05, | |
| "loss": NaN, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.774544358253479, | |
| "eval_runtime": 17.4029, | |
| "eval_samples_per_second": 4.597, | |
| "eval_wer": 0.5627906976744186, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.960442686341616e-05, | |
| "loss": NaN, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.7585596442222595, | |
| "eval_runtime": 17.4002, | |
| "eval_samples_per_second": 4.598, | |
| "eval_wer": 0.5317829457364341, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 9.959998222143207e-05, | |
| "loss": NaN, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.7920966744422913, | |
| "eval_runtime": 17.3362, | |
| "eval_samples_per_second": 4.615, | |
| "eval_wer": 0.5364341085271318, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 9.959553757944798e-05, | |
| "loss": NaN, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.7708950638771057, | |
| "eval_runtime": 17.4086, | |
| "eval_samples_per_second": 4.595, | |
| "eval_wer": 0.5333333333333333, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 9.959109293746389e-05, | |
| "loss": NaN, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.6876834630966187, | |
| "eval_runtime": 17.378, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.5612403100775194, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.95866482954798e-05, | |
| "loss": NaN, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.7105833292007446, | |
| "eval_runtime": 17.3931, | |
| "eval_samples_per_second": 4.6, | |
| "eval_wer": 0.5317829457364341, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 9.958220365349572e-05, | |
| "loss": NaN, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.7411137819290161, | |
| "eval_runtime": 17.4436, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.537984496124031, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 9.957775901151163e-05, | |
| "loss": NaN, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.703761875629425, | |
| "eval_runtime": 17.4301, | |
| "eval_samples_per_second": 4.59, | |
| "eval_wer": 0.5302325581395348, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 9.957331436952754e-05, | |
| "loss": NaN, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.6908837556838989, | |
| "eval_runtime": 17.4234, | |
| "eval_samples_per_second": 4.592, | |
| "eval_wer": 0.5286821705426357, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 9.956886972754345e-05, | |
| "loss": NaN, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.6668051481246948, | |
| "eval_runtime": 17.4034, | |
| "eval_samples_per_second": 4.597, | |
| "eval_wer": 0.5317829457364341, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 9.956442508555936e-05, | |
| "loss": NaN, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.7552028894424438, | |
| "eval_runtime": 17.4346, | |
| "eval_samples_per_second": 4.589, | |
| "eval_wer": 0.5426356589147286, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 9.955998044357527e-05, | |
| "loss": NaN, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.7529067397117615, | |
| "eval_runtime": 17.3764, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.5271317829457365, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.955553580159118e-05, | |
| "loss": NaN, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.6945570111274719, | |
| "eval_runtime": 17.5096, | |
| "eval_samples_per_second": 4.569, | |
| "eval_wer": 0.5348837209302325, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.955109115960711e-05, | |
| "loss": NaN, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.7381066679954529, | |
| "eval_runtime": 17.3519, | |
| "eval_samples_per_second": 4.61, | |
| "eval_wer": 0.5271317829457365, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.9546646517623e-05, | |
| "loss": NaN, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 0.7733180522918701, | |
| "eval_runtime": 17.3513, | |
| "eval_samples_per_second": 4.611, | |
| "eval_wer": 0.5395348837209303, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.954220187563892e-05, | |
| "loss": NaN, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.7235101461410522, | |
| "eval_runtime": 17.276, | |
| "eval_samples_per_second": 4.631, | |
| "eval_wer": 0.5162790697674419, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.953775723365484e-05, | |
| "loss": NaN, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.756510853767395, | |
| "eval_runtime": 17.3233, | |
| "eval_samples_per_second": 4.618, | |
| "eval_wer": 0.5162790697674419, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.953331259167075e-05, | |
| "loss": NaN, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.7486532330513, | |
| "eval_runtime": 17.3251, | |
| "eval_samples_per_second": 4.618, | |
| "eval_wer": 0.517829457364341, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.952886794968665e-05, | |
| "loss": NaN, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.8009279370307922, | |
| "eval_runtime": 17.3932, | |
| "eval_samples_per_second": 4.6, | |
| "eval_wer": 0.5333333333333333, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.952442330770258e-05, | |
| "loss": NaN, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.7493506073951721, | |
| "eval_runtime": 17.5083, | |
| "eval_samples_per_second": 4.569, | |
| "eval_wer": 0.517829457364341, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 9.951997866571849e-05, | |
| "loss": NaN, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.6919007301330566, | |
| "eval_runtime": 17.3761, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.95155340237344e-05, | |
| "loss": NaN, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.6828303933143616, | |
| "eval_runtime": 17.3932, | |
| "eval_samples_per_second": 4.6, | |
| "eval_wer": 0.524031007751938, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 9.95110893817503e-05, | |
| "loss": NaN, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.6986581683158875, | |
| "eval_runtime": 17.3758, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.5348837209302325, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9.950664473976622e-05, | |
| "loss": NaN, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.686642050743103, | |
| "eval_runtime": 17.3613, | |
| "eval_samples_per_second": 4.608, | |
| "eval_wer": 0.5395348837209303, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.950220009778213e-05, | |
| "loss": NaN, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 0.6886032223701477, | |
| "eval_runtime": 17.3873, | |
| "eval_samples_per_second": 4.601, | |
| "eval_wer": 0.5023255813953489, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.949775545579804e-05, | |
| "loss": NaN, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.6399986147880554, | |
| "eval_runtime": 17.4574, | |
| "eval_samples_per_second": 4.583, | |
| "eval_wer": 0.5162790697674419, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.949331081381395e-05, | |
| "loss": NaN, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.6944009065628052, | |
| "eval_runtime": 17.4437, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.4992248062015504, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.948886617182987e-05, | |
| "loss": NaN, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 0.7042981386184692, | |
| "eval_runtime": 17.4509, | |
| "eval_samples_per_second": 4.584, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.948442152984578e-05, | |
| "loss": NaN, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.6655673980712891, | |
| "eval_runtime": 17.4233, | |
| "eval_samples_per_second": 4.592, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.947997688786169e-05, | |
| "loss": NaN, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.6955547332763672, | |
| "eval_runtime": 17.3935, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 9.94755322458776e-05, | |
| "loss": NaN, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.7002443075180054, | |
| "eval_runtime": 17.4036, | |
| "eval_samples_per_second": 4.597, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.947108760389351e-05, | |
| "loss": NaN, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.6780632734298706, | |
| "eval_runtime": 17.4488, | |
| "eval_samples_per_second": 4.585, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.946664296190942e-05, | |
| "loss": NaN, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.7334409356117249, | |
| "eval_runtime": 17.3983, | |
| "eval_samples_per_second": 4.598, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.946219831992533e-05, | |
| "loss": NaN, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.7420142889022827, | |
| "eval_runtime": 17.4073, | |
| "eval_samples_per_second": 4.596, | |
| "eval_wer": 0.5224806201550387, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.945775367794124e-05, | |
| "loss": NaN, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.680244505405426, | |
| "eval_runtime": 17.4234, | |
| "eval_samples_per_second": 4.592, | |
| "eval_wer": 0.5038759689922481, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.945330903595716e-05, | |
| "loss": NaN, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 0.7066457867622375, | |
| "eval_runtime": 17.4153, | |
| "eval_samples_per_second": 4.594, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 9.944886439397308e-05, | |
| "loss": NaN, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.637787938117981, | |
| "eval_runtime": 17.3934, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 9.944441975198898e-05, | |
| "loss": NaN, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 0.6452146768569946, | |
| "eval_runtime": 17.4649, | |
| "eval_samples_per_second": 4.581, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 9.943997511000489e-05, | |
| "loss": NaN, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.6308380365371704, | |
| "eval_runtime": 17.4706, | |
| "eval_samples_per_second": 4.579, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.943553046802081e-05, | |
| "loss": NaN, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.6226298809051514, | |
| "eval_runtime": 17.3657, | |
| "eval_samples_per_second": 4.607, | |
| "eval_wer": 0.5131782945736434, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 9.943108582603672e-05, | |
| "loss": NaN, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.6554073095321655, | |
| "eval_runtime": 17.4972, | |
| "eval_samples_per_second": 4.572, | |
| "eval_wer": 0.517829457364341, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 9.942664118405262e-05, | |
| "loss": NaN, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.7324713468551636, | |
| "eval_runtime": 17.4373, | |
| "eval_samples_per_second": 4.588, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 9.942219654206855e-05, | |
| "loss": NaN, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.6392424702644348, | |
| "eval_runtime": 17.4258, | |
| "eval_samples_per_second": 4.591, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 9.941775190008446e-05, | |
| "loss": NaN, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.6548818349838257, | |
| "eval_runtime": 17.3702, | |
| "eval_samples_per_second": 4.606, | |
| "eval_wer": 0.5255813953488372, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 9.941330725810037e-05, | |
| "loss": NaN, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.687231183052063, | |
| "eval_runtime": 17.3777, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.5023255813953489, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 9.940886261611627e-05, | |
| "loss": NaN, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.705328106880188, | |
| "eval_runtime": 17.4159, | |
| "eval_samples_per_second": 4.594, | |
| "eval_wer": 0.517829457364341, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.940441797413219e-05, | |
| "loss": NaN, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.7033597230911255, | |
| "eval_runtime": 17.4035, | |
| "eval_samples_per_second": 4.597, | |
| "eval_wer": 0.517829457364341, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 9.93999733321481e-05, | |
| "loss": NaN, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.7513315081596375, | |
| "eval_runtime": 17.4233, | |
| "eval_samples_per_second": 4.592, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.939552869016401e-05, | |
| "loss": NaN, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.7186664342880249, | |
| "eval_runtime": 17.423, | |
| "eval_samples_per_second": 4.592, | |
| "eval_wer": 0.5286821705426357, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 9.939108404817993e-05, | |
| "loss": NaN, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.7211223840713501, | |
| "eval_runtime": 17.3974, | |
| "eval_samples_per_second": 4.598, | |
| "eval_wer": 0.517829457364341, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 9.938663940619584e-05, | |
| "loss": NaN, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.6921149492263794, | |
| "eval_runtime": 17.4244, | |
| "eval_samples_per_second": 4.591, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 9.938219476421175e-05, | |
| "loss": NaN, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.8026927709579468, | |
| "eval_runtime": 17.4647, | |
| "eval_samples_per_second": 4.581, | |
| "eval_wer": 0.5317829457364341, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 9.937775012222766e-05, | |
| "loss": NaN, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.7409325838088989, | |
| "eval_runtime": 17.4438, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.517829457364341, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 9.937330548024357e-05, | |
| "loss": NaN, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.6671923995018005, | |
| "eval_runtime": 17.3839, | |
| "eval_samples_per_second": 4.602, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 9.936886083825948e-05, | |
| "loss": NaN, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 0.6567109823226929, | |
| "eval_runtime": 17.3915, | |
| "eval_samples_per_second": 4.6, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 9.93644161962754e-05, | |
| "loss": NaN, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.707842230796814, | |
| "eval_runtime": 17.4097, | |
| "eval_samples_per_second": 4.595, | |
| "eval_wer": 0.5038759689922481, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.93599715542913e-05, | |
| "loss": NaN, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.7037177085876465, | |
| "eval_runtime": 17.5565, | |
| "eval_samples_per_second": 4.557, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 9.935552691230722e-05, | |
| "loss": NaN, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.7334758043289185, | |
| "eval_runtime": 17.5057, | |
| "eval_samples_per_second": 4.57, | |
| "eval_wer": 0.5736434108527132, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 9.935108227032313e-05, | |
| "loss": NaN, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.6860212087631226, | |
| "eval_runtime": 17.4444, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.5224806201550387, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.934663762833905e-05, | |
| "loss": NaN, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.6953790187835693, | |
| "eval_runtime": 17.4429, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 9.934219298635495e-05, | |
| "loss": NaN, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.7358990907669067, | |
| "eval_runtime": 17.4828, | |
| "eval_samples_per_second": 4.576, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.933774834437086e-05, | |
| "loss": NaN, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6997208595275879, | |
| "eval_runtime": 17.4415, | |
| "eval_samples_per_second": 4.587, | |
| "eval_wer": 0.5271317829457365, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.933330370238679e-05, | |
| "loss": NaN, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.6580943465232849, | |
| "eval_runtime": 17.4313, | |
| "eval_samples_per_second": 4.589, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.93288590604027e-05, | |
| "loss": NaN, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.6659531593322754, | |
| "eval_runtime": 17.4095, | |
| "eval_samples_per_second": 4.595, | |
| "eval_wer": 0.5224806201550387, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.93244144184186e-05, | |
| "loss": NaN, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.7017448544502258, | |
| "eval_runtime": 17.4403, | |
| "eval_samples_per_second": 4.587, | |
| "eval_wer": 0.5224806201550387, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.931996977643452e-05, | |
| "loss": NaN, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 0.7005801796913147, | |
| "eval_runtime": 17.4039, | |
| "eval_samples_per_second": 4.597, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.931552513445043e-05, | |
| "loss": NaN, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 0.646070659160614, | |
| "eval_runtime": 17.377, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.931108049246634e-05, | |
| "loss": NaN, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.6526376008987427, | |
| "eval_runtime": 17.4521, | |
| "eval_samples_per_second": 4.584, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.930663585048224e-05, | |
| "loss": NaN, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.7334516644477844, | |
| "eval_runtime": 17.501, | |
| "eval_samples_per_second": 4.571, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.930219120849816e-05, | |
| "loss": NaN, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 0.6918967366218567, | |
| "eval_runtime": 17.5122, | |
| "eval_samples_per_second": 4.568, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.929774656651408e-05, | |
| "loss": NaN, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.6813740730285645, | |
| "eval_runtime": 17.4079, | |
| "eval_samples_per_second": 4.596, | |
| "eval_wer": 0.4883720930232558, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.929330192452999e-05, | |
| "loss": NaN, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.704567551612854, | |
| "eval_runtime": 17.4009, | |
| "eval_samples_per_second": 4.597, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.92888572825459e-05, | |
| "loss": NaN, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.7084250450134277, | |
| "eval_runtime": 17.3953, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.524031007751938, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 9.928441264056181e-05, | |
| "loss": NaN, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.7336726188659668, | |
| "eval_runtime": 17.5249, | |
| "eval_samples_per_second": 4.565, | |
| "eval_wer": 0.5317829457364341, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.927996799857772e-05, | |
| "loss": NaN, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.7087512016296387, | |
| "eval_runtime": 17.4343, | |
| "eval_samples_per_second": 4.589, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 9.927552335659363e-05, | |
| "loss": NaN, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 0.7270997166633606, | |
| "eval_runtime": 17.4461, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.927107871460954e-05, | |
| "loss": NaN, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.7297137379646301, | |
| "eval_runtime": 17.3651, | |
| "eval_samples_per_second": 4.607, | |
| "eval_wer": 0.5131782945736434, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 9.926663407262545e-05, | |
| "loss": NaN, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 0.7396950125694275, | |
| "eval_runtime": 17.4544, | |
| "eval_samples_per_second": 4.583, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 9.926218943064137e-05, | |
| "loss": NaN, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 0.6693302392959595, | |
| "eval_runtime": 17.4093, | |
| "eval_samples_per_second": 4.595, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 9.925774478865728e-05, | |
| "loss": NaN, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.681401252746582, | |
| "eval_runtime": 17.4358, | |
| "eval_samples_per_second": 4.588, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 9.925330014667319e-05, | |
| "loss": NaN, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 0.6969695687294006, | |
| "eval_runtime": 17.4628, | |
| "eval_samples_per_second": 4.581, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 9.92488555046891e-05, | |
| "loss": NaN, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.7665321826934814, | |
| "eval_runtime": 17.4427, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.5007751937984496, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 9.924441086270502e-05, | |
| "loss": NaN, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.6652202606201172, | |
| "eval_runtime": 17.3856, | |
| "eval_samples_per_second": 4.602, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 9.923996622072092e-05, | |
| "loss": NaN, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 0.6718670129776001, | |
| "eval_runtime": 17.5534, | |
| "eval_samples_per_second": 4.558, | |
| "eval_wer": 0.4930232558139535, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 9.923552157873683e-05, | |
| "loss": NaN, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.7141027450561523, | |
| "eval_runtime": 17.3511, | |
| "eval_samples_per_second": 4.611, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.923107693675276e-05, | |
| "loss": NaN, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.69825279712677, | |
| "eval_runtime": 17.3767, | |
| "eval_samples_per_second": 4.604, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 9.922663229476867e-05, | |
| "loss": NaN, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 0.7104494571685791, | |
| "eval_runtime": 17.4248, | |
| "eval_samples_per_second": 4.591, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 9.922218765278457e-05, | |
| "loss": NaN, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 0.7555495500564575, | |
| "eval_runtime": 17.4089, | |
| "eval_samples_per_second": 4.595, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 9.921774301080049e-05, | |
| "loss": NaN, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.7753702998161316, | |
| "eval_runtime": 17.5354, | |
| "eval_samples_per_second": 4.562, | |
| "eval_wer": 0.5131782945736434, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 9.92132983688164e-05, | |
| "loss": NaN, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.7617055177688599, | |
| "eval_runtime": 17.6842, | |
| "eval_samples_per_second": 4.524, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 9.92088537268323e-05, | |
| "loss": NaN, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 0.8150382041931152, | |
| "eval_runtime": 17.4098, | |
| "eval_samples_per_second": 4.595, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.920440908484821e-05, | |
| "loss": NaN, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.8014766573905945, | |
| "eval_runtime": 17.5133, | |
| "eval_samples_per_second": 4.568, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.919996444286414e-05, | |
| "loss": NaN, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.6994240283966064, | |
| "eval_runtime": 17.5258, | |
| "eval_samples_per_second": 4.565, | |
| "eval_wer": 0.5038759689922481, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.919551980088005e-05, | |
| "loss": NaN, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 0.7259965538978577, | |
| "eval_runtime": 17.5442, | |
| "eval_samples_per_second": 4.56, | |
| "eval_wer": 0.5162790697674419, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.919107515889595e-05, | |
| "loss": NaN, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 0.7805743217468262, | |
| "eval_runtime": 17.6196, | |
| "eval_samples_per_second": 4.54, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.918663051691187e-05, | |
| "loss": NaN, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.7654392123222351, | |
| "eval_runtime": 17.5555, | |
| "eval_samples_per_second": 4.557, | |
| "eval_wer": 0.4992248062015504, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.918218587492778e-05, | |
| "loss": NaN, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 0.7141100168228149, | |
| "eval_runtime": 17.5057, | |
| "eval_samples_per_second": 4.57, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.917774123294369e-05, | |
| "loss": NaN, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 0.6688128113746643, | |
| "eval_runtime": 17.4377, | |
| "eval_samples_per_second": 4.588, | |
| "eval_wer": 0.49147286821705427, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.91732965909596e-05, | |
| "loss": NaN, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.6818010807037354, | |
| "eval_runtime": 17.3635, | |
| "eval_samples_per_second": 4.607, | |
| "eval_wer": 0.5038759689922481, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.916885194897552e-05, | |
| "loss": NaN, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 0.6905618906021118, | |
| "eval_runtime": 17.4231, | |
| "eval_samples_per_second": 4.592, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 9.916440730699143e-05, | |
| "loss": NaN, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.646501362323761, | |
| "eval_runtime": 17.4802, | |
| "eval_samples_per_second": 4.577, | |
| "eval_wer": 0.5271317829457365, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 9.915996266500734e-05, | |
| "loss": NaN, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.6760914325714111, | |
| "eval_runtime": 17.5136, | |
| "eval_samples_per_second": 4.568, | |
| "eval_wer": 0.5209302325581395, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 9.915551802302325e-05, | |
| "loss": NaN, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 0.7431942224502563, | |
| "eval_runtime": 17.3946, | |
| "eval_samples_per_second": 4.599, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 9.915107338103916e-05, | |
| "loss": NaN, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 0.7671061754226685, | |
| "eval_runtime": 17.5834, | |
| "eval_samples_per_second": 4.55, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 9.914662873905507e-05, | |
| "loss": NaN, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 0.7126530408859253, | |
| "eval_runtime": 17.5901, | |
| "eval_samples_per_second": 4.548, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 9.914218409707098e-05, | |
| "loss": NaN, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.727730929851532, | |
| "eval_runtime": 17.6577, | |
| "eval_samples_per_second": 4.531, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.91377394550869e-05, | |
| "loss": NaN, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.6788039207458496, | |
| "eval_runtime": 17.6112, | |
| "eval_samples_per_second": 4.543, | |
| "eval_wer": 0.48992248062015503, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 9.91332948131028e-05, | |
| "loss": NaN, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 0.6633437871932983, | |
| "eval_runtime": 17.6623, | |
| "eval_samples_per_second": 4.529, | |
| "eval_wer": 0.4821705426356589, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 9.912885017111873e-05, | |
| "loss": NaN, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 0.630849301815033, | |
| "eval_runtime": 17.4181, | |
| "eval_samples_per_second": 4.593, | |
| "eval_wer": 0.4728682170542636, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.912440552913463e-05, | |
| "loss": NaN, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.6438859701156616, | |
| "eval_runtime": 17.5582, | |
| "eval_samples_per_second": 4.556, | |
| "eval_wer": 0.48992248062015503, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 9.911996088715054e-05, | |
| "loss": NaN, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.6492059826850891, | |
| "eval_runtime": 17.5321, | |
| "eval_samples_per_second": 4.563, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 9.911551624516646e-05, | |
| "loss": NaN, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 0.6646106839179993, | |
| "eval_runtime": 17.4882, | |
| "eval_samples_per_second": 4.575, | |
| "eval_wer": 0.48372093023255813, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 9.911107160318237e-05, | |
| "loss": NaN, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.6617286801338196, | |
| "eval_runtime": 17.4701, | |
| "eval_samples_per_second": 4.579, | |
| "eval_wer": 0.48372093023255813, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 9.910662696119827e-05, | |
| "loss": NaN, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 0.6755768060684204, | |
| "eval_runtime": 17.5213, | |
| "eval_samples_per_second": 4.566, | |
| "eval_wer": 0.4806201550387597, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 9.910218231921418e-05, | |
| "loss": NaN, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 0.633080005645752, | |
| "eval_runtime": 17.4548, | |
| "eval_samples_per_second": 4.583, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 9.909773767723011e-05, | |
| "loss": NaN, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 0.665341317653656, | |
| "eval_runtime": 17.6885, | |
| "eval_samples_per_second": 4.523, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 9.909329303524602e-05, | |
| "loss": NaN, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 0.6483832597732544, | |
| "eval_runtime": 17.6251, | |
| "eval_samples_per_second": 4.539, | |
| "eval_wer": 0.475968992248062, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 9.908884839326192e-05, | |
| "loss": NaN, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 0.6416093111038208, | |
| "eval_runtime": 17.5412, | |
| "eval_samples_per_second": 4.561, | |
| "eval_wer": 0.4496124031007752, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 9.908440375127784e-05, | |
| "loss": NaN, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.6763391494750977, | |
| "eval_runtime": 17.5193, | |
| "eval_samples_per_second": 4.566, | |
| "eval_wer": 0.4806201550387597, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 9.907995910929375e-05, | |
| "loss": NaN, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 0.654536783695221, | |
| "eval_runtime": 17.4594, | |
| "eval_samples_per_second": 4.582, | |
| "eval_wer": 0.4930232558139535, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 9.907551446730966e-05, | |
| "loss": NaN, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 0.6497390866279602, | |
| "eval_runtime": 17.4598, | |
| "eval_samples_per_second": 4.582, | |
| "eval_wer": 0.4883720930232558, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.907106982532558e-05, | |
| "loss": NaN, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.7144044041633606, | |
| "eval_runtime": 17.4935, | |
| "eval_samples_per_second": 4.573, | |
| "eval_wer": 0.4930232558139535, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 9.906662518334149e-05, | |
| "loss": NaN, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 0.6466220021247864, | |
| "eval_runtime": 17.5042, | |
| "eval_samples_per_second": 4.57, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 9.90621805413574e-05, | |
| "loss": NaN, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 0.6383641362190247, | |
| "eval_runtime": 17.5022, | |
| "eval_samples_per_second": 4.571, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 9.905773589937331e-05, | |
| "loss": NaN, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 0.6846612691879272, | |
| "eval_runtime": 17.4796, | |
| "eval_samples_per_second": 4.577, | |
| "eval_wer": 0.48527131782945737, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 9.905329125738922e-05, | |
| "loss": NaN, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 0.65887850522995, | |
| "eval_runtime": 17.6832, | |
| "eval_samples_per_second": 4.524, | |
| "eval_wer": 0.5038759689922481, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 9.904884661540513e-05, | |
| "loss": NaN, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 0.7195907831192017, | |
| "eval_runtime": 17.5562, | |
| "eval_samples_per_second": 4.557, | |
| "eval_wer": 0.5131782945736434, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.904440197342104e-05, | |
| "loss": NaN, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.6677905321121216, | |
| "eval_runtime": 17.6786, | |
| "eval_samples_per_second": 4.525, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 9.903995733143695e-05, | |
| "loss": NaN, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.6715782880783081, | |
| "eval_runtime": 17.5941, | |
| "eval_samples_per_second": 4.547, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.903551268945287e-05, | |
| "loss": NaN, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.6809279918670654, | |
| "eval_runtime": 17.4894, | |
| "eval_samples_per_second": 4.574, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 9.903106804746878e-05, | |
| "loss": NaN, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 0.7200478911399841, | |
| "eval_runtime": 17.4913, | |
| "eval_samples_per_second": 4.574, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 9.90266234054847e-05, | |
| "loss": NaN, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.7086242437362671, | |
| "eval_runtime": 17.7177, | |
| "eval_samples_per_second": 4.515, | |
| "eval_wer": 0.5131782945736434, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.90221787635006e-05, | |
| "loss": NaN, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 0.7738662958145142, | |
| "eval_runtime": 17.5778, | |
| "eval_samples_per_second": 4.551, | |
| "eval_wer": 0.4930232558139535, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 9.901773412151651e-05, | |
| "loss": NaN, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.719960629940033, | |
| "eval_runtime": 17.7048, | |
| "eval_samples_per_second": 4.519, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 9.901328947953244e-05, | |
| "loss": NaN, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 0.6674638986587524, | |
| "eval_runtime": 17.7977, | |
| "eval_samples_per_second": 4.495, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.900884483754835e-05, | |
| "loss": NaN, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 0.6668637990951538, | |
| "eval_runtime": 17.6814, | |
| "eval_samples_per_second": 4.525, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.900440019556424e-05, | |
| "loss": NaN, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.7027889490127563, | |
| "eval_runtime": 17.5701, | |
| "eval_samples_per_second": 4.553, | |
| "eval_wer": 0.5317829457364341, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.899995555358016e-05, | |
| "loss": NaN, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_loss": 0.7082899212837219, | |
| "eval_runtime": 17.636, | |
| "eval_samples_per_second": 4.536, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.899551091159608e-05, | |
| "loss": NaN, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 0.690900981426239, | |
| "eval_runtime": 17.5784, | |
| "eval_samples_per_second": 4.551, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.899106626961199e-05, | |
| "loss": NaN, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 0.6628085374832153, | |
| "eval_runtime": 17.7779, | |
| "eval_samples_per_second": 4.5, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 9.898662162762789e-05, | |
| "loss": NaN, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.7275087833404541, | |
| "eval_runtime": 17.8126, | |
| "eval_samples_per_second": 4.491, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 9.898217698564381e-05, | |
| "loss": NaN, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_loss": 0.7226203680038452, | |
| "eval_runtime": 17.6988, | |
| "eval_samples_per_second": 4.52, | |
| "eval_wer": 0.48527131782945737, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.897773234365973e-05, | |
| "loss": NaN, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 0.6935572028160095, | |
| "eval_runtime": 17.7653, | |
| "eval_samples_per_second": 4.503, | |
| "eval_wer": 0.4883720930232558, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 9.897328770167564e-05, | |
| "loss": NaN, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 0.7608216404914856, | |
| "eval_runtime": 17.8167, | |
| "eval_samples_per_second": 4.49, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 9.896884305969155e-05, | |
| "loss": NaN, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 0.8762000203132629, | |
| "eval_runtime": 17.7039, | |
| "eval_samples_per_second": 4.519, | |
| "eval_wer": 0.48992248062015503, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 9.896439841770746e-05, | |
| "loss": NaN, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 0.8612931370735168, | |
| "eval_runtime": 17.6357, | |
| "eval_samples_per_second": 4.536, | |
| "eval_wer": 0.524031007751938, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.895995377572337e-05, | |
| "loss": NaN, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_loss": 0.6559737920761108, | |
| "eval_runtime": 17.6948, | |
| "eval_samples_per_second": 4.521, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 9.895550913373928e-05, | |
| "loss": NaN, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_loss": 0.7084537148475647, | |
| "eval_runtime": 17.6392, | |
| "eval_samples_per_second": 4.535, | |
| "eval_wer": 0.4930232558139535, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 9.895106449175519e-05, | |
| "loss": NaN, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "eval_loss": 0.6912034749984741, | |
| "eval_runtime": 17.7427, | |
| "eval_samples_per_second": 4.509, | |
| "eval_wer": 0.49147286821705427, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 9.89466198497711e-05, | |
| "loss": NaN, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 0.7391806840896606, | |
| "eval_runtime": 17.7803, | |
| "eval_samples_per_second": 4.499, | |
| "eval_wer": 0.48372093023255813, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 9.894217520778702e-05, | |
| "loss": NaN, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.7380479574203491, | |
| "eval_runtime": 17.7057, | |
| "eval_samples_per_second": 4.518, | |
| "eval_wer": 0.5007751937984496, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.893773056580293e-05, | |
| "loss": NaN, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.6259809732437134, | |
| "eval_runtime": 17.7735, | |
| "eval_samples_per_second": 4.501, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.893328592381884e-05, | |
| "loss": NaN, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_loss": 0.6884532570838928, | |
| "eval_runtime": 17.6673, | |
| "eval_samples_per_second": 4.528, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 9.892884128183475e-05, | |
| "loss": NaN, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 0.693473219871521, | |
| "eval_runtime": 17.7372, | |
| "eval_samples_per_second": 4.51, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 9.892439663985067e-05, | |
| "loss": NaN, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_loss": 0.6742721199989319, | |
| "eval_runtime": 17.6443, | |
| "eval_samples_per_second": 4.534, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 9.891995199786657e-05, | |
| "loss": NaN, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_loss": 0.7249454259872437, | |
| "eval_runtime": 17.6261, | |
| "eval_samples_per_second": 4.539, | |
| "eval_wer": 0.5162790697674419, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 9.891550735588248e-05, | |
| "loss": NaN, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 0.6982861757278442, | |
| "eval_runtime": 17.6565, | |
| "eval_samples_per_second": 4.531, | |
| "eval_wer": 0.5162790697674419, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 9.89110627138984e-05, | |
| "loss": NaN, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 0.6899422407150269, | |
| "eval_runtime": 17.8327, | |
| "eval_samples_per_second": 4.486, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 9.890661807191432e-05, | |
| "loss": NaN, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_loss": 0.7489897012710571, | |
| "eval_runtime": 17.7463, | |
| "eval_samples_per_second": 4.508, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 9.890217342993022e-05, | |
| "loss": NaN, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "eval_loss": 0.6491571664810181, | |
| "eval_runtime": 17.9426, | |
| "eval_samples_per_second": 4.459, | |
| "eval_wer": 0.4992248062015504, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 9.889772878794613e-05, | |
| "loss": NaN, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_loss": 0.6521108150482178, | |
| "eval_runtime": 17.6592, | |
| "eval_samples_per_second": 4.53, | |
| "eval_wer": 0.48372093023255813, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 9.889328414596205e-05, | |
| "loss": NaN, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 0.6570430397987366, | |
| "eval_runtime": 17.7233, | |
| "eval_samples_per_second": 4.514, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 9.888883950397796e-05, | |
| "loss": NaN, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_loss": 0.6758342385292053, | |
| "eval_runtime": 18.0274, | |
| "eval_samples_per_second": 4.438, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 9.888439486199386e-05, | |
| "loss": NaN, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 0.6588055491447449, | |
| "eval_runtime": 17.7155, | |
| "eval_samples_per_second": 4.516, | |
| "eval_wer": 0.4883720930232558, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 9.887995022000979e-05, | |
| "loss": NaN, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_loss": 0.6541072130203247, | |
| "eval_runtime": 17.6533, | |
| "eval_samples_per_second": 4.532, | |
| "eval_wer": 0.5023255813953489, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 9.88755055780257e-05, | |
| "loss": NaN, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_loss": 0.7445347309112549, | |
| "eval_runtime": 17.8422, | |
| "eval_samples_per_second": 4.484, | |
| "eval_wer": 0.537984496124031, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.887106093604161e-05, | |
| "loss": NaN, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 0.6562886238098145, | |
| "eval_runtime": 18.0886, | |
| "eval_samples_per_second": 4.423, | |
| "eval_wer": 0.5023255813953489, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 9.886661629405752e-05, | |
| "loss": NaN, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 0.6530973315238953, | |
| "eval_runtime": 17.8674, | |
| "eval_samples_per_second": 4.477, | |
| "eval_wer": 0.5023255813953489, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 9.886217165207343e-05, | |
| "loss": NaN, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "eval_loss": 0.700346827507019, | |
| "eval_runtime": 17.7178, | |
| "eval_samples_per_second": 4.515, | |
| "eval_wer": 0.5348837209302325, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 9.885772701008934e-05, | |
| "loss": NaN, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 0.7025777697563171, | |
| "eval_runtime": 17.7283, | |
| "eval_samples_per_second": 4.513, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 9.885328236810525e-05, | |
| "loss": NaN, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 0.6949543356895447, | |
| "eval_runtime": 17.8409, | |
| "eval_samples_per_second": 4.484, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 9.884883772612116e-05, | |
| "loss": NaN, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.6976181268692017, | |
| "eval_runtime": 17.7292, | |
| "eval_samples_per_second": 4.512, | |
| "eval_wer": 0.5271317829457365, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 9.884439308413708e-05, | |
| "loss": NaN, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 0.776595950126648, | |
| "eval_runtime": 17.6407, | |
| "eval_samples_per_second": 4.535, | |
| "eval_wer": 0.5023255813953489, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 9.883994844215299e-05, | |
| "loss": NaN, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_loss": 0.7193652987480164, | |
| "eval_runtime": 17.7195, | |
| "eval_samples_per_second": 4.515, | |
| "eval_wer": 0.48992248062015503, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 9.88355038001689e-05, | |
| "loss": NaN, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_loss": 0.7061530351638794, | |
| "eval_runtime": 17.6793, | |
| "eval_samples_per_second": 4.525, | |
| "eval_wer": 0.49147286821705427, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.883105915818481e-05, | |
| "loss": NaN, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 0.7101202011108398, | |
| "eval_runtime": 17.6388, | |
| "eval_samples_per_second": 4.535, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 9.882661451620072e-05, | |
| "loss": NaN, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "eval_loss": 0.7322906255722046, | |
| "eval_runtime": 17.5209, | |
| "eval_samples_per_second": 4.566, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 9.882216987421665e-05, | |
| "loss": NaN, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 0.759114682674408, | |
| "eval_runtime": 17.7065, | |
| "eval_samples_per_second": 4.518, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 9.881772523223254e-05, | |
| "loss": NaN, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_loss": 0.8165428042411804, | |
| "eval_runtime": 17.7222, | |
| "eval_samples_per_second": 4.514, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 9.881328059024845e-05, | |
| "loss": NaN, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 0.7161229252815247, | |
| "eval_runtime": 17.8272, | |
| "eval_samples_per_second": 4.488, | |
| "eval_wer": 0.48992248062015503, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 9.880883594826437e-05, | |
| "loss": NaN, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_loss": 0.738871693611145, | |
| "eval_runtime": 17.6582, | |
| "eval_samples_per_second": 4.53, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 9.880439130628029e-05, | |
| "loss": NaN, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 0.6424237489700317, | |
| "eval_runtime": 17.8001, | |
| "eval_samples_per_second": 4.494, | |
| "eval_wer": 0.475968992248062, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 9.879994666429619e-05, | |
| "loss": NaN, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 0.7210354208946228, | |
| "eval_runtime": 17.9075, | |
| "eval_samples_per_second": 4.467, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 9.87955020223121e-05, | |
| "loss": NaN, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "eval_loss": 0.684795081615448, | |
| "eval_runtime": 17.8466, | |
| "eval_samples_per_second": 4.483, | |
| "eval_wer": 0.5038759689922481, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 9.879105738032802e-05, | |
| "loss": NaN, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 0.6793242692947388, | |
| "eval_runtime": 17.9938, | |
| "eval_samples_per_second": 4.446, | |
| "eval_wer": 0.5116279069767442, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 9.878661273834394e-05, | |
| "loss": NaN, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_loss": 0.7072234749794006, | |
| "eval_runtime": 17.7391, | |
| "eval_samples_per_second": 4.51, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 9.878216809635983e-05, | |
| "loss": NaN, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_loss": 0.794607400894165, | |
| "eval_runtime": 17.713, | |
| "eval_samples_per_second": 4.516, | |
| "eval_wer": 0.5224806201550387, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 9.877772345437576e-05, | |
| "loss": NaN, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "eval_loss": 0.7146335244178772, | |
| "eval_runtime": 17.8755, | |
| "eval_samples_per_second": 4.475, | |
| "eval_wer": 0.5162790697674419, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 9.877327881239167e-05, | |
| "loss": NaN, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_loss": 0.7817438244819641, | |
| "eval_runtime": 17.78, | |
| "eval_samples_per_second": 4.499, | |
| "eval_wer": 0.5054263565891473, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 9.876883417040758e-05, | |
| "loss": NaN, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "eval_loss": 0.7325385808944702, | |
| "eval_runtime": 17.8427, | |
| "eval_samples_per_second": 4.484, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 9.876438952842349e-05, | |
| "loss": NaN, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_loss": 0.8487836718559265, | |
| "eval_runtime": 17.8001, | |
| "eval_samples_per_second": 4.494, | |
| "eval_wer": 0.5007751937984496, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 9.87599448864394e-05, | |
| "loss": NaN, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "eval_loss": 0.8588669896125793, | |
| "eval_runtime": 17.9789, | |
| "eval_samples_per_second": 4.45, | |
| "eval_wer": 0.5023255813953489, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 9.875550024445531e-05, | |
| "loss": NaN, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 0.8295779228210449, | |
| "eval_runtime": 17.7403, | |
| "eval_samples_per_second": 4.51, | |
| "eval_wer": 0.48527131782945737, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 9.875105560247123e-05, | |
| "loss": NaN, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_loss": 0.6985501646995544, | |
| "eval_runtime": 17.5929, | |
| "eval_samples_per_second": 4.547, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 9.874661096048714e-05, | |
| "loss": NaN, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_loss": 0.8200405240058899, | |
| "eval_runtime": 17.9213, | |
| "eval_samples_per_second": 4.464, | |
| "eval_wer": 0.5193798449612403, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 9.874216631850305e-05, | |
| "loss": NaN, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_loss": 0.8269991874694824, | |
| "eval_runtime": 17.6268, | |
| "eval_samples_per_second": 4.539, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 9.873772167651896e-05, | |
| "loss": NaN, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_loss": 0.8213759660720825, | |
| "eval_runtime": 17.9751, | |
| "eval_samples_per_second": 4.451, | |
| "eval_wer": 0.5302325581395348, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 9.873327703453487e-05, | |
| "loss": NaN, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_loss": 0.6891577243804932, | |
| "eval_runtime": 17.7686, | |
| "eval_samples_per_second": 4.502, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 9.872883239255078e-05, | |
| "loss": NaN, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_loss": 0.6482048034667969, | |
| "eval_runtime": 17.6883, | |
| "eval_samples_per_second": 4.523, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.87243877505667e-05, | |
| "loss": NaN, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_loss": 0.7204601168632507, | |
| "eval_runtime": 17.5891, | |
| "eval_samples_per_second": 4.548, | |
| "eval_wer": 0.517829457364341, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 9.871994310858262e-05, | |
| "loss": NaN, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "eval_loss": 0.723224937915802, | |
| "eval_runtime": 17.7967, | |
| "eval_samples_per_second": 4.495, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 9.871549846659852e-05, | |
| "loss": NaN, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_loss": 0.6662874221801758, | |
| "eval_runtime": 17.7906, | |
| "eval_samples_per_second": 4.497, | |
| "eval_wer": 0.475968992248062, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 9.871105382461443e-05, | |
| "loss": NaN, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_loss": 0.6662710905075073, | |
| "eval_runtime": 17.8296, | |
| "eval_samples_per_second": 4.487, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 9.870660918263034e-05, | |
| "loss": NaN, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_loss": 0.7283247709274292, | |
| "eval_runtime": 17.8161, | |
| "eval_samples_per_second": 4.49, | |
| "eval_wer": 0.48992248062015503, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 9.870216454064626e-05, | |
| "loss": NaN, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_loss": 0.7031872868537903, | |
| "eval_runtime": 17.7282, | |
| "eval_samples_per_second": 4.513, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 9.869771989866216e-05, | |
| "loss": NaN, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 0.6514617204666138, | |
| "eval_runtime": 17.7963, | |
| "eval_samples_per_second": 4.495, | |
| "eval_wer": 0.4883720930232558, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 9.869327525667807e-05, | |
| "loss": NaN, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_loss": 0.6518000364303589, | |
| "eval_runtime": 17.8676, | |
| "eval_samples_per_second": 4.477, | |
| "eval_wer": 0.47131782945736433, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 9.8688830614694e-05, | |
| "loss": NaN, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_loss": 0.7044751048088074, | |
| "eval_runtime": 17.8213, | |
| "eval_samples_per_second": 4.489, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 9.868438597270991e-05, | |
| "loss": NaN, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "eval_loss": 0.7028575539588928, | |
| "eval_runtime": 17.7101, | |
| "eval_samples_per_second": 4.517, | |
| "eval_wer": 0.4930232558139535, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 9.86799413307258e-05, | |
| "loss": NaN, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 0.735122799873352, | |
| "eval_runtime": 17.5395, | |
| "eval_samples_per_second": 4.561, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 9.867549668874173e-05, | |
| "loss": NaN, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 0.7852219939231873, | |
| "eval_runtime": 17.5067, | |
| "eval_samples_per_second": 4.57, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.867105204675764e-05, | |
| "loss": NaN, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.7610275149345398, | |
| "eval_runtime": 17.6453, | |
| "eval_samples_per_second": 4.534, | |
| "eval_wer": 0.5023255813953489, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.866660740477355e-05, | |
| "loss": NaN, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 0.8094395399093628, | |
| "eval_runtime": 17.7642, | |
| "eval_samples_per_second": 4.503, | |
| "eval_wer": 0.4806201550387597, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.866216276278946e-05, | |
| "loss": NaN, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_loss": 0.8135471343994141, | |
| "eval_runtime": 17.6874, | |
| "eval_samples_per_second": 4.523, | |
| "eval_wer": 0.4992248062015504, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 9.865771812080538e-05, | |
| "loss": NaN, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 0.7297781109809875, | |
| "eval_runtime": 17.539, | |
| "eval_samples_per_second": 4.561, | |
| "eval_wer": 0.49767441860465117, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 9.865327347882129e-05, | |
| "loss": NaN, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 0.7608882784843445, | |
| "eval_runtime": 17.6916, | |
| "eval_samples_per_second": 4.522, | |
| "eval_wer": 0.5007751937984496, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 9.86488288368372e-05, | |
| "loss": NaN, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "eval_loss": 0.7042602300643921, | |
| "eval_runtime": 17.6883, | |
| "eval_samples_per_second": 4.523, | |
| "eval_wer": 0.5100775193798449, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 9.864438419485311e-05, | |
| "loss": NaN, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_loss": 0.6467885971069336, | |
| "eval_runtime": 17.6906, | |
| "eval_samples_per_second": 4.522, | |
| "eval_wer": 0.47751937984496123, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 9.863993955286902e-05, | |
| "loss": NaN, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 0.7081225514411926, | |
| "eval_runtime": 17.6982, | |
| "eval_samples_per_second": 4.52, | |
| "eval_wer": 0.4992248062015504, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 9.863549491088493e-05, | |
| "loss": NaN, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 0.6654272675514221, | |
| "eval_runtime": 17.5676, | |
| "eval_samples_per_second": 4.554, | |
| "eval_wer": 0.48372093023255813, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 9.863105026890084e-05, | |
| "loss": NaN, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 0.6897600889205933, | |
| "eval_runtime": 17.7155, | |
| "eval_samples_per_second": 4.516, | |
| "eval_wer": 0.48527131782945737, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 9.862660562691675e-05, | |
| "loss": NaN, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_loss": 0.629447340965271, | |
| "eval_runtime": 17.7496, | |
| "eval_samples_per_second": 4.507, | |
| "eval_wer": 0.4728682170542636, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.862216098493267e-05, | |
| "loss": NaN, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_loss": 0.637413501739502, | |
| "eval_runtime": 17.659, | |
| "eval_samples_per_second": 4.53, | |
| "eval_wer": 0.48372093023255813, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.861771634294859e-05, | |
| "loss": NaN, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "eval_loss": 0.6577144861221313, | |
| "eval_runtime": 17.6907, | |
| "eval_samples_per_second": 4.522, | |
| "eval_wer": 0.4883720930232558, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 9.861327170096449e-05, | |
| "loss": NaN, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "eval_loss": 0.7151761054992676, | |
| "eval_runtime": 17.836, | |
| "eval_samples_per_second": 4.485, | |
| "eval_wer": 0.4883720930232558, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 9.86088270589804e-05, | |
| "loss": NaN, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_loss": 0.7481046915054321, | |
| "eval_runtime": 17.7063, | |
| "eval_samples_per_second": 4.518, | |
| "eval_wer": 0.49147286821705427, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 9.860438241699631e-05, | |
| "loss": NaN, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_loss": 0.7165336608886719, | |
| "eval_runtime": 17.7286, | |
| "eval_samples_per_second": 4.512, | |
| "eval_wer": 0.48992248062015503, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 9.859993777501224e-05, | |
| "loss": NaN, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "eval_loss": 0.7002926468849182, | |
| "eval_runtime": 17.6498, | |
| "eval_samples_per_second": 4.533, | |
| "eval_wer": 0.5007751937984496, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 9.859549313302813e-05, | |
| "loss": NaN, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "eval_loss": 0.6786822080612183, | |
| "eval_runtime": 17.5909, | |
| "eval_samples_per_second": 4.548, | |
| "eval_wer": 0.4806201550387597, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 9.859104849104404e-05, | |
| "loss": NaN, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 0.7046242952346802, | |
| "eval_runtime": 17.6497, | |
| "eval_samples_per_second": 4.533, | |
| "eval_wer": 0.4821705426356589, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 9.858660384905997e-05, | |
| "loss": NaN, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "eval_loss": 0.747069776058197, | |
| "eval_runtime": 17.7298, | |
| "eval_samples_per_second": 4.512, | |
| "eval_wer": 0.5224806201550387, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 9.858215920707588e-05, | |
| "loss": NaN, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "eval_loss": 0.676543116569519, | |
| "eval_runtime": 17.7787, | |
| "eval_samples_per_second": 4.5, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 9.857771456509178e-05, | |
| "loss": NaN, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "eval_loss": 0.6780596971511841, | |
| "eval_runtime": 17.7101, | |
| "eval_samples_per_second": 4.517, | |
| "eval_wer": 0.5147286821705427, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 9.85732699231077e-05, | |
| "loss": NaN, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_loss": 0.7229406237602234, | |
| "eval_runtime": 17.6392, | |
| "eval_samples_per_second": 4.535, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 9.856882528112361e-05, | |
| "loss": NaN, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_loss": 0.7299832105636597, | |
| "eval_runtime": 17.6718, | |
| "eval_samples_per_second": 4.527, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 9.856438063913952e-05, | |
| "loss": NaN, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "eval_loss": 0.6965775489807129, | |
| "eval_runtime": 17.7649, | |
| "eval_samples_per_second": 4.503, | |
| "eval_wer": 0.4930232558139535, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 9.855993599715544e-05, | |
| "loss": NaN, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 0.6707865595817566, | |
| "eval_runtime": 17.5045, | |
| "eval_samples_per_second": 4.57, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 9.855549135517135e-05, | |
| "loss": NaN, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 0.6962494254112244, | |
| "eval_runtime": 17.5191, | |
| "eval_samples_per_second": 4.566, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 9.855104671318726e-05, | |
| "loss": NaN, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "eval_loss": 0.7435300350189209, | |
| "eval_runtime": 17.5234, | |
| "eval_samples_per_second": 4.565, | |
| "eval_wer": 0.4806201550387597, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 9.854660207120317e-05, | |
| "loss": NaN, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_loss": 0.8106309771537781, | |
| "eval_runtime": 17.5548, | |
| "eval_samples_per_second": 4.557, | |
| "eval_wer": 0.475968992248062, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 9.854215742921908e-05, | |
| "loss": NaN, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_loss": 0.7216034531593323, | |
| "eval_runtime": 17.5922, | |
| "eval_samples_per_second": 4.547, | |
| "eval_wer": 0.4635658914728682, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 9.853771278723499e-05, | |
| "loss": NaN, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_loss": 0.7068824172019958, | |
| "eval_runtime": 17.4424, | |
| "eval_samples_per_second": 4.587, | |
| "eval_wer": 0.4806201550387597, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 9.85332681452509e-05, | |
| "loss": NaN, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "eval_loss": 0.6770612001419067, | |
| "eval_runtime": 17.5754, | |
| "eval_samples_per_second": 4.552, | |
| "eval_wer": 0.4821705426356589, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 9.852882350326681e-05, | |
| "loss": NaN, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 0.7043319940567017, | |
| "eval_runtime": 17.5764, | |
| "eval_samples_per_second": 4.552, | |
| "eval_wer": 0.48372093023255813, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 9.852437886128273e-05, | |
| "loss": NaN, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "eval_loss": 0.7157676815986633, | |
| "eval_runtime": 17.5258, | |
| "eval_samples_per_second": 4.565, | |
| "eval_wer": 0.4992248062015504, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 9.851993421929864e-05, | |
| "loss": NaN, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "eval_loss": 0.622586190700531, | |
| "eval_runtime": 17.5815, | |
| "eval_samples_per_second": 4.55, | |
| "eval_wer": 0.4635658914728682, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 9.851548957731456e-05, | |
| "loss": NaN, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_loss": 0.656098484992981, | |
| "eval_runtime": 17.501, | |
| "eval_samples_per_second": 4.571, | |
| "eval_wer": 0.4635658914728682, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.851104493533046e-05, | |
| "loss": NaN, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 0.6705238223075867, | |
| "eval_runtime": 17.5581, | |
| "eval_samples_per_second": 4.556, | |
| "eval_wer": 0.47131782945736433, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 9.850660029334637e-05, | |
| "loss": NaN, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "eval_loss": 0.6990655660629272, | |
| "eval_runtime": 17.553, | |
| "eval_samples_per_second": 4.558, | |
| "eval_wer": 0.4728682170542636, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 9.850215565136228e-05, | |
| "loss": NaN, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 0.6776248216629028, | |
| "eval_runtime": 17.5252, | |
| "eval_samples_per_second": 4.565, | |
| "eval_wer": 0.47131782945736433, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 9.849771100937821e-05, | |
| "loss": NaN, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "eval_loss": 0.6578621864318848, | |
| "eval_runtime": 17.5632, | |
| "eval_samples_per_second": 4.555, | |
| "eval_wer": 0.4728682170542636, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 9.84932663673941e-05, | |
| "loss": NaN, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_loss": 0.6970942616462708, | |
| "eval_runtime": 17.555, | |
| "eval_samples_per_second": 4.557, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 9.848882172541002e-05, | |
| "loss": NaN, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 0.6826914548873901, | |
| "eval_runtime": 17.5393, | |
| "eval_samples_per_second": 4.561, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 9.848437708342594e-05, | |
| "loss": NaN, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "eval_loss": 0.6816051602363586, | |
| "eval_runtime": 17.5537, | |
| "eval_samples_per_second": 4.557, | |
| "eval_wer": 0.4728682170542636, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 9.847993244144185e-05, | |
| "loss": NaN, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_loss": 0.7528648972511292, | |
| "eval_runtime": 17.5699, | |
| "eval_samples_per_second": 4.553, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 9.847548779945775e-05, | |
| "loss": NaN, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "eval_loss": 0.6876388788223267, | |
| "eval_runtime": 17.4887, | |
| "eval_samples_per_second": 4.574, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 9.847104315747367e-05, | |
| "loss": NaN, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 0.7198226451873779, | |
| "eval_runtime": 17.4698, | |
| "eval_samples_per_second": 4.579, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 9.846659851548959e-05, | |
| "loss": NaN, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "eval_loss": 0.7185400724411011, | |
| "eval_runtime": 17.5466, | |
| "eval_samples_per_second": 4.559, | |
| "eval_wer": 0.47751937984496123, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 9.84621538735055e-05, | |
| "loss": NaN, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 0.7706559896469116, | |
| "eval_runtime": 17.5053, | |
| "eval_samples_per_second": 4.57, | |
| "eval_wer": 0.5069767441860465, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 9.845770923152141e-05, | |
| "loss": NaN, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "eval_loss": 0.8254127502441406, | |
| "eval_runtime": 17.5689, | |
| "eval_samples_per_second": 4.553, | |
| "eval_wer": 0.4945736434108527, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 9.845326458953732e-05, | |
| "loss": NaN, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_loss": 0.8003772497177124, | |
| "eval_runtime": 17.4204, | |
| "eval_samples_per_second": 4.592, | |
| "eval_wer": 0.4883720930232558, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 9.844881994755323e-05, | |
| "loss": NaN, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_loss": 0.6992226839065552, | |
| "eval_runtime": 17.4907, | |
| "eval_samples_per_second": 4.574, | |
| "eval_wer": 0.5085271317829457, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 9.844437530556914e-05, | |
| "loss": NaN, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_loss": 0.7514958381652832, | |
| "eval_runtime": 17.4878, | |
| "eval_samples_per_second": 4.575, | |
| "eval_wer": 0.49612403100775193, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 9.843993066358505e-05, | |
| "loss": NaN, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 0.7265327572822571, | |
| "eval_runtime": 17.4636, | |
| "eval_samples_per_second": 4.581, | |
| "eval_wer": 0.4682170542635659, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 9.843548602160096e-05, | |
| "loss": NaN, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "eval_loss": 0.7364674806594849, | |
| "eval_runtime": 17.5101, | |
| "eval_samples_per_second": 4.569, | |
| "eval_wer": 0.47751937984496123, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 9.843104137961688e-05, | |
| "loss": NaN, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "eval_loss": 0.6975224018096924, | |
| "eval_runtime": 17.4555, | |
| "eval_samples_per_second": 4.583, | |
| "eval_wer": 0.47751937984496123, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 9.842659673763279e-05, | |
| "loss": NaN, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "eval_loss": 0.6800852417945862, | |
| "eval_runtime": 17.5482, | |
| "eval_samples_per_second": 4.559, | |
| "eval_wer": 0.4868217054263566, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 9.84221520956487e-05, | |
| "loss": NaN, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 0.7129591703414917, | |
| "eval_runtime": 17.5425, | |
| "eval_samples_per_second": 4.56, | |
| "eval_wer": 0.4992248062015504, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 9.841770745366461e-05, | |
| "loss": NaN, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "eval_loss": 0.7202149033546448, | |
| "eval_runtime": 17.5335, | |
| "eval_samples_per_second": 4.563, | |
| "eval_wer": 0.4930232558139535, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 9.841326281168053e-05, | |
| "loss": NaN, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "eval_loss": 0.6712242960929871, | |
| "eval_runtime": 17.5011, | |
| "eval_samples_per_second": 4.571, | |
| "eval_wer": 0.48527131782945737, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 9.840881816969643e-05, | |
| "loss": NaN, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "eval_loss": 0.8096708059310913, | |
| "eval_runtime": 17.5196, | |
| "eval_samples_per_second": 4.566, | |
| "eval_wer": 0.49147286821705427, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.840437352771234e-05, | |
| "loss": NaN, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 0.6871185898780823, | |
| "eval_runtime": 17.4561, | |
| "eval_samples_per_second": 4.583, | |
| "eval_wer": 0.47751937984496123, | |
| "step": 36000 | |
| } | |
| ], | |
| "max_steps": 2250000, | |
| "num_train_epochs": 300, | |
| "total_flos": 2.3169703440557314e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |