| { | |
| "best_metric": 0.12453306507935491, | |
| "best_model_checkpoint": "./outputs/common_voice_9_0_fr/wav2vec2-xls-r-1b-ft-ep10/checkpoint-36000", | |
| "epoch": 9.99996533675344, | |
| "global_step": 36060, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.6899611758180813e-06, | |
| "loss": 9.4595, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.463117027176928e-06, | |
| "loss": 3.1185, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.236272878535774e-06, | |
| "loss": 2.9237, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.1009428729894621e-05, | |
| "loss": 1.5923, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.3782584581253465e-05, | |
| "loss": 0.9229, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.5048818588256836, | |
| "eval_runtime": 835.7546, | |
| "eval_samples_per_second": 19.193, | |
| "eval_steps_per_second": 2.4, | |
| "eval_wer": 0.4007663178937791, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.6555740432612314e-05, | |
| "loss": 0.7777, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.932889628397116e-05, | |
| "loss": 0.5771, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.2102052135330005e-05, | |
| "loss": 0.4572, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.4875207986688854e-05, | |
| "loss": 0.4048, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.7648363838047696e-05, | |
| "loss": 0.3823, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.2831491231918335, | |
| "eval_runtime": 739.7164, | |
| "eval_samples_per_second": 21.685, | |
| "eval_steps_per_second": 2.712, | |
| "eval_wer": 0.2296647038847704, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.042151968940655e-05, | |
| "loss": 0.3549, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.319467554076539e-05, | |
| "loss": 0.3433, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.596783139212424e-05, | |
| "loss": 0.328, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.874098724348308e-05, | |
| "loss": 0.3114, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.1514143094841934e-05, | |
| "loss": 0.3079, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.23849168419837952, | |
| "eval_runtime": 738.9338, | |
| "eval_samples_per_second": 21.708, | |
| "eval_steps_per_second": 2.715, | |
| "eval_wer": 0.19510351058172243, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.428729894620078e-05, | |
| "loss": 0.3002, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.7060454797559625e-05, | |
| "loss": 0.2895, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.983361064891847e-05, | |
| "loss": 0.2936, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.2606766500277316e-05, | |
| "loss": 0.2908, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.537992235163616e-05, | |
| "loss": 0.2899, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.22730602324008942, | |
| "eval_runtime": 733.7734, | |
| "eval_samples_per_second": 21.861, | |
| "eval_steps_per_second": 2.734, | |
| "eval_wer": 0.19783303752779183, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.8153078202995014e-05, | |
| "loss": 0.2815, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.092623405435386e-05, | |
| "loss": 0.2866, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.36993899057127e-05, | |
| "loss": 0.285, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.647254575707154e-05, | |
| "loss": 0.2864, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.92457016084304e-05, | |
| "loss": 0.2795, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.23286376893520355, | |
| "eval_runtime": 745.9448, | |
| "eval_samples_per_second": 21.504, | |
| "eval_steps_per_second": 2.689, | |
| "eval_wer": 0.19834562474771097, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 7.201885745978925e-05, | |
| "loss": 0.2801, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.47920133111481e-05, | |
| "loss": 0.2814, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 7.756516916250694e-05, | |
| "loss": 0.2809, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.033832501386578e-05, | |
| "loss": 0.2846, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.311148086522463e-05, | |
| "loss": 0.2863, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.22894535958766937, | |
| "eval_runtime": 746.0584, | |
| "eval_samples_per_second": 21.501, | |
| "eval_steps_per_second": 2.689, | |
| "eval_wer": 0.19914013493858565, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.588463671658348e-05, | |
| "loss": 0.2899, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.865779256794232e-05, | |
| "loss": 0.2825, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.143094841930117e-05, | |
| "loss": 0.2826, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.420410427066003e-05, | |
| "loss": 0.2896, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.697726012201886e-05, | |
| "loss": 0.3063, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.2369552105665207, | |
| "eval_runtime": 741.3652, | |
| "eval_samples_per_second": 21.637, | |
| "eval_steps_per_second": 2.706, | |
| "eval_wer": 0.20460559617097346, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.97504159733777e-05, | |
| "loss": 0.2928, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.971960313058483e-05, | |
| "loss": 0.2767, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.941147470265608e-05, | |
| "loss": 0.2819, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.910334627472732e-05, | |
| "loss": 0.2789, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.879521784679855e-05, | |
| "loss": 0.2766, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.23217500746250153, | |
| "eval_runtime": 739.5397, | |
| "eval_samples_per_second": 21.691, | |
| "eval_steps_per_second": 2.712, | |
| "eval_wer": 0.20213877017511261, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 9.848708941886979e-05, | |
| "loss": 0.2784, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.817896099094103e-05, | |
| "loss": 0.2712, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 9.787083256301228e-05, | |
| "loss": 0.2757, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 9.75627041350835e-05, | |
| "loss": 0.2775, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.725457570715475e-05, | |
| "loss": 0.2749, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.23323854804039001, | |
| "eval_runtime": 741.5404, | |
| "eval_samples_per_second": 21.632, | |
| "eval_steps_per_second": 2.705, | |
| "eval_wer": 0.20545136508384004, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 9.694644727922599e-05, | |
| "loss": 0.2716, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 9.663831885129723e-05, | |
| "loss": 0.2718, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 9.633019042336846e-05, | |
| "loss": 0.2749, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.60220619954397e-05, | |
| "loss": 0.2718, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.571393356751093e-05, | |
| "loss": 0.2769, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.23219896852970123, | |
| "eval_runtime": 739.3463, | |
| "eval_samples_per_second": 21.696, | |
| "eval_steps_per_second": 2.713, | |
| "eval_wer": 0.20350353364814733, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.540580513958219e-05, | |
| "loss": 0.2659, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.509767671165342e-05, | |
| "loss": 0.2668, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.478954828372466e-05, | |
| "loss": 0.2611, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.44814198557959e-05, | |
| "loss": 0.2678, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.417329142786714e-05, | |
| "loss": 0.2628, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.22423435747623444, | |
| "eval_runtime": 735.686, | |
| "eval_samples_per_second": 21.804, | |
| "eval_steps_per_second": 2.727, | |
| "eval_wer": 0.19482799495101588, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.386516299993839e-05, | |
| "loss": 0.2608, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.355703457200961e-05, | |
| "loss": 0.2609, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.324890614408086e-05, | |
| "loss": 0.2592, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.29407777161521e-05, | |
| "loss": 0.2544, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.263264928822334e-05, | |
| "loss": 0.2614, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.23026546835899353, | |
| "eval_runtime": 738.1222, | |
| "eval_samples_per_second": 21.732, | |
| "eval_steps_per_second": 2.718, | |
| "eval_wer": 0.19623760980579352, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 9.232452086029457e-05, | |
| "loss": 0.2555, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 9.201639243236581e-05, | |
| "loss": 0.2649, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 9.170826400443706e-05, | |
| "loss": 0.2518, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 9.14001355765083e-05, | |
| "loss": 0.2548, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.109200714857953e-05, | |
| "loss": 0.2547, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.22376440465450287, | |
| "eval_runtime": 739.914, | |
| "eval_samples_per_second": 21.68, | |
| "eval_steps_per_second": 2.711, | |
| "eval_wer": 0.19202798726220757, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.078387872065077e-05, | |
| "loss": 0.2498, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 9.047575029272201e-05, | |
| "loss": 0.2545, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 9.016762186479325e-05, | |
| "loss": 0.2545, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.98594934368645e-05, | |
| "loss": 0.2438, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.955136500893573e-05, | |
| "loss": 0.2458, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.21862062811851501, | |
| "eval_runtime": 742.7999, | |
| "eval_samples_per_second": 21.595, | |
| "eval_steps_per_second": 2.701, | |
| "eval_wer": 0.18936253371862807, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.924323658100697e-05, | |
| "loss": 0.2495, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.893510815307821e-05, | |
| "loss": 0.2477, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.862697972514945e-05, | |
| "loss": 0.2383, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.831885129722068e-05, | |
| "loss": 0.2373, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 8.801072286929192e-05, | |
| "loss": 0.231, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.21694478392601013, | |
| "eval_runtime": 747.3244, | |
| "eval_samples_per_second": 21.465, | |
| "eval_steps_per_second": 2.684, | |
| "eval_wer": 0.1895291245651018, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.770259444136317e-05, | |
| "loss": 0.2338, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.739446601343441e-05, | |
| "loss": 0.2307, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.708633758550564e-05, | |
| "loss": 0.2375, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.677820915757688e-05, | |
| "loss": 0.2359, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.647008072964812e-05, | |
| "loss": 0.2309, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.21314306557178497, | |
| "eval_runtime": 736.606, | |
| "eval_samples_per_second": 21.777, | |
| "eval_steps_per_second": 2.723, | |
| "eval_wer": 0.187011039847249, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 8.616195230171936e-05, | |
| "loss": 0.2342, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.58538238737906e-05, | |
| "loss": 0.2313, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.554569544586184e-05, | |
| "loss": 0.2299, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.523756701793308e-05, | |
| "loss": 0.2323, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.492943859000432e-05, | |
| "loss": 0.2258, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.21330955624580383, | |
| "eval_runtime": 733.2181, | |
| "eval_samples_per_second": 21.878, | |
| "eval_steps_per_second": 2.736, | |
| "eval_wer": 0.18179546488457177, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.462131016207556e-05, | |
| "loss": 0.2263, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 8.431318173414679e-05, | |
| "loss": 0.2253, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.400505330621803e-05, | |
| "loss": 0.2302, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.369692487828928e-05, | |
| "loss": 0.2266, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.338879645036052e-05, | |
| "loss": 0.2278, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.21764406561851501, | |
| "eval_runtime": 744.2016, | |
| "eval_samples_per_second": 21.555, | |
| "eval_steps_per_second": 2.696, | |
| "eval_wer": 0.1877799206771277, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.308066802243175e-05, | |
| "loss": 0.2313, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.277253959450299e-05, | |
| "loss": 0.2319, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 8.246441116657423e-05, | |
| "loss": 0.2264, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 8.215628273864548e-05, | |
| "loss": 0.2301, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 8.18481543107167e-05, | |
| "loss": 0.2263, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 0.2029789835214615, | |
| "eval_runtime": 742.9206, | |
| "eval_samples_per_second": 21.592, | |
| "eval_steps_per_second": 2.7, | |
| "eval_wer": 0.18131491436589758, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 8.154002588278795e-05, | |
| "loss": 0.2287, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 8.123189745485919e-05, | |
| "loss": 0.2285, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 8.092376902693043e-05, | |
| "loss": 0.2272, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 8.061564059900166e-05, | |
| "loss": 0.226, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 8.03075121710729e-05, | |
| "loss": 0.2262, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 0.2076706886291504, | |
| "eval_runtime": 744.0741, | |
| "eval_samples_per_second": 21.558, | |
| "eval_steps_per_second": 2.696, | |
| "eval_wer": 0.1823785328472298, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.999938374314416e-05, | |
| "loss": 0.2232, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.969433659949467e-05, | |
| "loss": 0.2214, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 7.938620817156591e-05, | |
| "loss": 0.2257, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.907807974363715e-05, | |
| "loss": 0.2191, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 7.87699513157084e-05, | |
| "loss": 0.2228, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.21150091290473938, | |
| "eval_runtime": 744.436, | |
| "eval_samples_per_second": 21.548, | |
| "eval_steps_per_second": 2.695, | |
| "eval_wer": 0.1839739605692281, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.846182288777964e-05, | |
| "loss": 0.2249, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 7.815369445985087e-05, | |
| "loss": 0.2181, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.784556603192211e-05, | |
| "loss": 0.2203, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.753743760399335e-05, | |
| "loss": 0.2174, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.72293091760646e-05, | |
| "loss": 0.2118, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.20934706926345825, | |
| "eval_runtime": 749.3869, | |
| "eval_samples_per_second": 21.405, | |
| "eval_steps_per_second": 2.677, | |
| "eval_wer": 0.17822016902563576, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 7.692118074813582e-05, | |
| "loss": 0.2136, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.661305232020707e-05, | |
| "loss": 0.2042, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.630492389227831e-05, | |
| "loss": 0.2078, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.599679546434955e-05, | |
| "loss": 0.2066, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 7.568866703642078e-05, | |
| "loss": 0.2073, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.20042090117931366, | |
| "eval_runtime": 741.0274, | |
| "eval_samples_per_second": 21.647, | |
| "eval_steps_per_second": 2.707, | |
| "eval_wer": 0.1756380109052931, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 7.538053860849202e-05, | |
| "loss": 0.2026, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 7.507241018056326e-05, | |
| "loss": 0.2057, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 7.47642817526345e-05, | |
| "loss": 0.2023, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 7.445615332470575e-05, | |
| "loss": 0.2023, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 7.414802489677698e-05, | |
| "loss": 0.2015, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 0.19883444905281067, | |
| "eval_runtime": 747.9432, | |
| "eval_samples_per_second": 21.447, | |
| "eval_steps_per_second": 2.682, | |
| "eval_wer": 0.17481787135342247, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 7.383989646884822e-05, | |
| "loss": 0.209, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 7.353176804091946e-05, | |
| "loss": 0.2073, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 7.32236396129907e-05, | |
| "loss": 0.2113, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 7.291551118506193e-05, | |
| "loss": 0.2087, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 7.261046404141246e-05, | |
| "loss": 0.214, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.20877334475517273, | |
| "eval_runtime": 743.8468, | |
| "eval_samples_per_second": 21.565, | |
| "eval_steps_per_second": 2.697, | |
| "eval_wer": 0.18157120797585713, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 7.230233561348371e-05, | |
| "loss": 0.2059, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 7.199420718555494e-05, | |
| "loss": 0.2027, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 7.168607875762618e-05, | |
| "loss": 0.2057, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 7.137795032969741e-05, | |
| "loss": 0.2074, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 7.106982190176867e-05, | |
| "loss": 0.2075, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 0.19755592942237854, | |
| "eval_runtime": 739.5406, | |
| "eval_samples_per_second": 21.69, | |
| "eval_steps_per_second": 2.712, | |
| "eval_wer": 0.1746256511459528, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 7.07616934738399e-05, | |
| "loss": 0.2004, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 7.045356504591114e-05, | |
| "loss": 0.2007, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 7.014543661798237e-05, | |
| "loss": 0.2027, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 6.983730819005361e-05, | |
| "loss": 0.2021, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 6.952917976212485e-05, | |
| "loss": 0.2039, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_loss": 0.19584038853645325, | |
| "eval_runtime": 734.9317, | |
| "eval_samples_per_second": 21.827, | |
| "eval_steps_per_second": 2.73, | |
| "eval_wer": 0.17436935753599322, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 6.922413261847538e-05, | |
| "loss": 0.2054, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 6.891600419054662e-05, | |
| "loss": 0.2017, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 6.860787576261786e-05, | |
| "loss": 0.2021, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 6.82997473346891e-05, | |
| "loss": 0.1961, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.799161890676035e-05, | |
| "loss": 0.2003, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_loss": 0.19312596321105957, | |
| "eval_runtime": 744.5794, | |
| "eval_samples_per_second": 21.544, | |
| "eval_steps_per_second": 2.694, | |
| "eval_wer": 0.16931396607954072, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 6.768349047883158e-05, | |
| "loss": 0.1996, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 6.737536205090282e-05, | |
| "loss": 0.1966, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 6.706723362297406e-05, | |
| "loss": 0.1976, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 6.67591051950453e-05, | |
| "loss": 0.201, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 6.645097676711653e-05, | |
| "loss": 0.1886, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_loss": 0.19637233018875122, | |
| "eval_runtime": 744.2941, | |
| "eval_samples_per_second": 21.552, | |
| "eval_steps_per_second": 2.695, | |
| "eval_wer": 0.1686091586521519, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 6.614284833918778e-05, | |
| "loss": 0.1867, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 6.583471991125902e-05, | |
| "loss": 0.1885, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 6.552659148333026e-05, | |
| "loss": 0.1909, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 6.521846305540149e-05, | |
| "loss": 0.189, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 6.491033462747273e-05, | |
| "loss": 0.1943, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "eval_loss": 0.19862689077854156, | |
| "eval_runtime": 743.0072, | |
| "eval_samples_per_second": 21.589, | |
| "eval_steps_per_second": 2.7, | |
| "eval_wer": 0.1745615777434629, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.460220619954397e-05, | |
| "loss": 0.1936, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 6.429407777161522e-05, | |
| "loss": 0.1916, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 6.398594934368644e-05, | |
| "loss": 0.1916, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 6.367782091575769e-05, | |
| "loss": 0.1871, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 6.336969248782893e-05, | |
| "loss": 0.1919, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "eval_loss": 0.19568254053592682, | |
| "eval_runtime": 742.9429, | |
| "eval_samples_per_second": 21.591, | |
| "eval_steps_per_second": 2.7, | |
| "eval_wer": 0.17001877350692954, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 6.306156405990017e-05, | |
| "loss": 0.1955, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 6.275343563197141e-05, | |
| "loss": 0.1907, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 6.244530720404264e-05, | |
| "loss": 0.1931, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 6.213717877611389e-05, | |
| "loss": 0.1889, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 6.182905034818513e-05, | |
| "loss": 0.1857, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "eval_loss": 0.19073382019996643, | |
| "eval_runtime": 741.2082, | |
| "eval_samples_per_second": 21.642, | |
| "eval_steps_per_second": 2.706, | |
| "eval_wer": 0.16714828507538235, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 6.152092192025637e-05, | |
| "loss": 0.1768, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 6.12127934923276e-05, | |
| "loss": 0.1841, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 6.090466506439885e-05, | |
| "loss": 0.1874, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 6.059653663647008e-05, | |
| "loss": 0.1845, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 6.0288408208541326e-05, | |
| "loss": 0.1834, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_loss": 0.18768635392189026, | |
| "eval_runtime": 727.4352, | |
| "eval_samples_per_second": 22.051, | |
| "eval_steps_per_second": 2.758, | |
| "eval_wer": 0.16405994707536956, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 5.9980279780612555e-05, | |
| "loss": 0.1811, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 5.9675232636963086e-05, | |
| "loss": 0.1828, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 5.936710420903433e-05, | |
| "loss": 0.1811, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 5.9058975781105564e-05, | |
| "loss": 0.1788, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 5.8750847353176806e-05, | |
| "loss": 0.18, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "eval_loss": 0.18282969295978546, | |
| "eval_runtime": 737.0087, | |
| "eval_samples_per_second": 21.765, | |
| "eval_steps_per_second": 2.722, | |
| "eval_wer": 0.16002332271850633, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 5.844271892524804e-05, | |
| "loss": 0.1777, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 5.8134590497319284e-05, | |
| "loss": 0.1831, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 5.782646206939053e-05, | |
| "loss": 0.1811, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 5.751833364146176e-05, | |
| "loss": 0.1772, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 5.7210205213533005e-05, | |
| "loss": 0.1774, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 0.1862887740135193, | |
| "eval_runtime": 738.0056, | |
| "eval_samples_per_second": 21.736, | |
| "eval_steps_per_second": 2.718, | |
| "eval_wer": 0.1604590218554376, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 5.690207678560424e-05, | |
| "loss": 0.1761, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 5.659394835767548e-05, | |
| "loss": 0.1764, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 5.628581992974672e-05, | |
| "loss": 0.1781, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 5.597769150181796e-05, | |
| "loss": 0.1781, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 5.5669563073889196e-05, | |
| "loss": 0.1755, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 0.18325339257717133, | |
| "eval_runtime": 728.9102, | |
| "eval_samples_per_second": 22.007, | |
| "eval_steps_per_second": 2.752, | |
| "eval_wer": 0.15946588411684426, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 5.536143464596044e-05, | |
| "loss": 0.1758, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 5.5053306218031675e-05, | |
| "loss": 0.163, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 5.474517779010292e-05, | |
| "loss": 0.1671, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 5.443704936217415e-05, | |
| "loss": 0.1723, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 5.4128920934245395e-05, | |
| "loss": 0.1692, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_loss": 0.18143832683563232, | |
| "eval_runtime": 741.2319, | |
| "eval_samples_per_second": 21.641, | |
| "eval_steps_per_second": 2.706, | |
| "eval_wer": 0.15686450397575463, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 5.382079250631663e-05, | |
| "loss": 0.1714, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 5.351266407838787e-05, | |
| "loss": 0.1638, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 5.320453565045911e-05, | |
| "loss": 0.1626, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 5.289640722253035e-05, | |
| "loss": 0.1657, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 5.25882787946016e-05, | |
| "loss": 0.1674, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_loss": 0.18194520473480225, | |
| "eval_runtime": 737.6255, | |
| "eval_samples_per_second": 21.747, | |
| "eval_steps_per_second": 2.72, | |
| "eval_wer": 0.15655054430355414, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 5.228015036667283e-05, | |
| "loss": 0.1657, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 5.197202193874408e-05, | |
| "loss": 0.1663, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 5.166389351081531e-05, | |
| "loss": 0.1683, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 5.135884636716584e-05, | |
| "loss": 0.1716, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 5.105071793923708e-05, | |
| "loss": 0.1664, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 0.18048684298992157, | |
| "eval_runtime": 745.2746, | |
| "eval_samples_per_second": 21.524, | |
| "eval_steps_per_second": 2.692, | |
| "eval_wer": 0.15724894439069398, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 5.0742589511308316e-05, | |
| "loss": 0.1714, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 5.043446108337956e-05, | |
| "loss": 0.1686, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 5.0126332655450794e-05, | |
| "loss": 0.1672, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 4.9818204227522036e-05, | |
| "loss": 0.1657, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 4.951007579959328e-05, | |
| "loss": 0.1677, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "eval_loss": 0.1802615374326706, | |
| "eval_runtime": 735.367, | |
| "eval_samples_per_second": 21.814, | |
| "eval_steps_per_second": 2.728, | |
| "eval_wer": 0.15595466166039815, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 4.9201947371664514e-05, | |
| "loss": 0.1659, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.889381894373575e-05, | |
| "loss": 0.1663, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 4.858569051580699e-05, | |
| "loss": 0.167, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 4.827756208787823e-05, | |
| "loss": 0.1667, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 4.796943365994947e-05, | |
| "loss": 0.1637, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "eval_loss": 0.17502419650554657, | |
| "eval_runtime": 733.6051, | |
| "eval_samples_per_second": 21.866, | |
| "eval_steps_per_second": 2.734, | |
| "eval_wer": 0.15248188324544598, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 4.7661305232020706e-05, | |
| "loss": 0.1609, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 4.735317680409195e-05, | |
| "loss": 0.1658, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 4.7045048376163184e-05, | |
| "loss": 0.1671, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 4.6736919948234426e-05, | |
| "loss": 0.1631, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 4.643187280458495e-05, | |
| "loss": 0.1628, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "eval_loss": 0.17739933729171753, | |
| "eval_runtime": 734.3058, | |
| "eval_samples_per_second": 21.845, | |
| "eval_steps_per_second": 2.732, | |
| "eval_wer": 0.1531866906728348, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 4.612374437665619e-05, | |
| "loss": 0.166, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 4.581561594872743e-05, | |
| "loss": 0.1666, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 4.550748752079867e-05, | |
| "loss": 0.1623, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 4.5199359092869906e-05, | |
| "loss": 0.166, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 4.489123066494115e-05, | |
| "loss": 0.1645, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_loss": 0.1743806153535843, | |
| "eval_runtime": 735.7033, | |
| "eval_samples_per_second": 21.804, | |
| "eval_steps_per_second": 2.727, | |
| "eval_wer": 0.15269332547366263, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 4.4583102237012384e-05, | |
| "loss": 0.1625, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 4.427497380908363e-05, | |
| "loss": 0.1587, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 4.396684538115487e-05, | |
| "loss": 0.1545, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 4.365871695322611e-05, | |
| "loss": 0.1524, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 4.335058852529735e-05, | |
| "loss": 0.1551, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_loss": 0.17782124876976013, | |
| "eval_runtime": 736.3789, | |
| "eval_samples_per_second": 21.784, | |
| "eval_steps_per_second": 2.724, | |
| "eval_wer": 0.15429516053590994, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 4.304246009736859e-05, | |
| "loss": 0.1528, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 4.2734331669439825e-05, | |
| "loss": 0.1513, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 4.242620324151107e-05, | |
| "loss": 0.1527, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 4.21180748135823e-05, | |
| "loss": 0.1522, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 4.1809946385653545e-05, | |
| "loss": 0.1505, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "eval_loss": 0.1753922700881958, | |
| "eval_runtime": 732.6709, | |
| "eval_samples_per_second": 21.894, | |
| "eval_steps_per_second": 2.738, | |
| "eval_wer": 0.15279584291764645, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 4.150181795772478e-05, | |
| "loss": 0.1528, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 4.119368952979602e-05, | |
| "loss": 0.1533, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 4.088556110186726e-05, | |
| "loss": 0.1529, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 4.05774326739385e-05, | |
| "loss": 0.1516, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 4.026930424600974e-05, | |
| "loss": 0.1499, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "eval_loss": 0.17432022094726562, | |
| "eval_runtime": 727.4564, | |
| "eval_samples_per_second": 22.051, | |
| "eval_steps_per_second": 2.758, | |
| "eval_wer": 0.14998302054834017, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 3.996117581808097e-05, | |
| "loss": 0.1494, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 3.9653047390152215e-05, | |
| "loss": 0.1517, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 3.934491896222346e-05, | |
| "loss": 0.1485, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 3.90367905342947e-05, | |
| "loss": 0.1472, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 3.8728662106365935e-05, | |
| "loss": 0.1491, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "eval_loss": 0.1684291511774063, | |
| "eval_runtime": 725.7122, | |
| "eval_samples_per_second": 22.104, | |
| "eval_steps_per_second": 2.764, | |
| "eval_wer": 0.1472855303035157, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 3.842053367843718e-05, | |
| "loss": 0.1466, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 3.8112405250508413e-05, | |
| "loss": 0.1454, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 3.7804276822579656e-05, | |
| "loss": 0.1473, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 3.749614839465089e-05, | |
| "loss": 0.1447, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 3.7188019966722134e-05, | |
| "loss": 0.1477, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "eval_loss": 0.16609960794448853, | |
| "eval_runtime": 737.8035, | |
| "eval_samples_per_second": 21.742, | |
| "eval_steps_per_second": 2.719, | |
| "eval_wer": 0.14721504956077683, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 3.687989153879337e-05, | |
| "loss": 0.1499, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 3.657176311086461e-05, | |
| "loss": 0.1468, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 3.626363468293585e-05, | |
| "loss": 0.1481, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 3.595550625500709e-05, | |
| "loss": 0.1485, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 3.5647377827078326e-05, | |
| "loss": 0.1456, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "eval_loss": 0.1653786450624466, | |
| "eval_runtime": 730.3018, | |
| "eval_samples_per_second": 21.965, | |
| "eval_steps_per_second": 2.747, | |
| "eval_wer": 0.14399856475578424, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 3.533924939914957e-05, | |
| "loss": 0.1442, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 3.5031120971220804e-05, | |
| "loss": 0.1434, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 3.4722992543292046e-05, | |
| "loss": 0.1494, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 3.441486411536329e-05, | |
| "loss": 0.1463, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 3.4106735687434524e-05, | |
| "loss": 0.1415, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "eval_loss": 0.16542479395866394, | |
| "eval_runtime": 729.304, | |
| "eval_samples_per_second": 21.995, | |
| "eval_steps_per_second": 2.751, | |
| "eval_wer": 0.14476744558566293, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 3.3798607259505766e-05, | |
| "loss": 0.1413, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 3.3490478831577e-05, | |
| "loss": 0.1461, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 3.3182350403648244e-05, | |
| "loss": 0.1392, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 3.287422197571948e-05, | |
| "loss": 0.1311, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 3.256609354779072e-05, | |
| "loss": 0.136, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 0.1615738570690155, | |
| "eval_runtime": 742.2272, | |
| "eval_samples_per_second": 21.612, | |
| "eval_steps_per_second": 2.703, | |
| "eval_wer": 0.1406667478263098, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 3.225796511986196e-05, | |
| "loss": 0.1328, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 3.19498366919332e-05, | |
| "loss": 0.1355, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 3.164787083256301e-05, | |
| "loss": 0.1378, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 3.1339742404634255e-05, | |
| "loss": 0.1321, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 3.103161397670549e-05, | |
| "loss": 0.132, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_loss": 0.16245120763778687, | |
| "eval_runtime": 782.6075, | |
| "eval_samples_per_second": 20.497, | |
| "eval_steps_per_second": 2.563, | |
| "eval_wer": 0.14099992951925727, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 3.072348554877673e-05, | |
| "loss": 0.133, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 3.0415357120847972e-05, | |
| "loss": 0.1325, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 3.010722869291921e-05, | |
| "loss": 0.1323, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 2.9799100264990447e-05, | |
| "loss": 0.1347, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 2.9490971837061686e-05, | |
| "loss": 0.1323, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "eval_loss": 0.16042262315750122, | |
| "eval_runtime": 776.612, | |
| "eval_samples_per_second": 20.655, | |
| "eval_steps_per_second": 2.583, | |
| "eval_wer": 0.14037201017485632, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 2.9182843409132925e-05, | |
| "loss": 0.1321, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 2.8874714981204164e-05, | |
| "loss": 0.1328, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 2.8566586553275403e-05, | |
| "loss": 0.1312, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 2.825845812534665e-05, | |
| "loss": 0.1328, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 2.7950329697417887e-05, | |
| "loss": 0.1338, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_loss": 0.1574241816997528, | |
| "eval_runtime": 761.9403, | |
| "eval_samples_per_second": 21.053, | |
| "eval_steps_per_second": 2.633, | |
| "eval_wer": 0.1386484356478782, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 2.7642201269489126e-05, | |
| "loss": 0.1318, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 2.7334072841560365e-05, | |
| "loss": 0.1319, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 2.7025944413631604e-05, | |
| "loss": 0.1315, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 2.6717815985702843e-05, | |
| "loss": 0.1328, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 2.6409687557774082e-05, | |
| "loss": 0.13, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_loss": 0.15763409435749054, | |
| "eval_runtime": 758.2506, | |
| "eval_samples_per_second": 21.155, | |
| "eval_steps_per_second": 2.646, | |
| "eval_wer": 0.13843058607941258, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 2.610155912984532e-05, | |
| "loss": 0.1278, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 2.579343070191656e-05, | |
| "loss": 0.1299, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 2.54853022739878e-05, | |
| "loss": 0.13, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 2.517717384605904e-05, | |
| "loss": 0.1306, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 2.4869045418130278e-05, | |
| "loss": 0.1291, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "eval_loss": 0.15506793558597565, | |
| "eval_runtime": 748.8913, | |
| "eval_samples_per_second": 21.42, | |
| "eval_steps_per_second": 2.679, | |
| "eval_wer": 0.1365660500669567, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 2.456091699020152e-05, | |
| "loss": 0.1277, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 2.425278856227276e-05, | |
| "loss": 0.1292, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 2.3944660134343998e-05, | |
| "loss": 0.1304, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 2.3636531706415237e-05, | |
| "loss": 0.1306, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 2.3328403278486473e-05, | |
| "loss": 0.1277, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "eval_loss": 0.15418410301208496, | |
| "eval_runtime": 753.0273, | |
| "eval_samples_per_second": 21.302, | |
| "eval_steps_per_second": 2.664, | |
| "eval_wer": 0.1355536903076164, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 2.302027485055771e-05, | |
| "loss": 0.127, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 2.271214642262895e-05, | |
| "loss": 0.1283, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 2.240401799470019e-05, | |
| "loss": 0.1316, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 2.2095889566771432e-05, | |
| "loss": 0.1246, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 2.178776113884267e-05, | |
| "loss": 0.1241, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_loss": 0.15454024076461792, | |
| "eval_runtime": 764.5389, | |
| "eval_samples_per_second": 20.981, | |
| "eval_steps_per_second": 2.624, | |
| "eval_wer": 0.13500906638645233, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 2.147963271091391e-05, | |
| "loss": 0.1229, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 2.117150428298515e-05, | |
| "loss": 0.1252, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 2.0863375855056388e-05, | |
| "loss": 0.123, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 2.0555247427127627e-05, | |
| "loss": 0.1198, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 2.0247118999198866e-05, | |
| "loss": 0.1198, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "eval_loss": 0.15356162190437317, | |
| "eval_runtime": 730.0324, | |
| "eval_samples_per_second": 21.973, | |
| "eval_steps_per_second": 2.748, | |
| "eval_wer": 0.13224109539888898, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 1.9938990571270105e-05, | |
| "loss": 0.1203, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 1.9630862143341347e-05, | |
| "loss": 0.1225, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 1.9322733715412586e-05, | |
| "loss": 0.1192, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 1.9014605287483825e-05, | |
| "loss": 0.1218, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 1.8706476859555064e-05, | |
| "loss": 0.1204, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_loss": 0.15469121932983398, | |
| "eval_runtime": 731.8162, | |
| "eval_samples_per_second": 21.919, | |
| "eval_steps_per_second": 2.741, | |
| "eval_wer": 0.13368915429516054, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 1.8398348431626303e-05, | |
| "loss": 0.1202, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 1.8090220003697542e-05, | |
| "loss": 0.1198, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 1.778209157576878e-05, | |
| "loss": 0.1159, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 1.747396314784002e-05, | |
| "loss": 0.1193, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 1.716583471991126e-05, | |
| "loss": 0.1195, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_loss": 0.14937089383602142, | |
| "eval_runtime": 730.1876, | |
| "eval_samples_per_second": 21.968, | |
| "eval_steps_per_second": 2.747, | |
| "eval_wer": 0.13088273926610325, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 1.68577062919825e-05, | |
| "loss": 0.1176, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 1.6549577864053738e-05, | |
| "loss": 0.1162, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 1.6241449436124977e-05, | |
| "loss": 0.1185, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 1.5936402292475504e-05, | |
| "loss": 0.1164, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 1.5628273864546743e-05, | |
| "loss": 0.1169, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "eval_loss": 0.14900121092796326, | |
| "eval_runtime": 740.5566, | |
| "eval_samples_per_second": 21.661, | |
| "eval_steps_per_second": 2.709, | |
| "eval_wer": 0.12999852631174275, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 1.5320145436617982e-05, | |
| "loss": 0.1173, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 1.5012017008689223e-05, | |
| "loss": 0.1163, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 1.4703888580760462e-05, | |
| "loss": 0.1169, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 1.43957601528317e-05, | |
| "loss": 0.1172, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 1.4087631724902941e-05, | |
| "loss": 0.1159, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "eval_loss": 0.14852623641490936, | |
| "eval_runtime": 733.0221, | |
| "eval_samples_per_second": 21.883, | |
| "eval_steps_per_second": 2.737, | |
| "eval_wer": 0.13053033555240884, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 1.377950329697418e-05, | |
| "loss": 0.1147, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 1.347137486904542e-05, | |
| "loss": 0.1161, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 1.3163246441116658e-05, | |
| "loss": 0.1145, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 1.2855118013187897e-05, | |
| "loss": 0.1156, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 1.2546989585259136e-05, | |
| "loss": 0.1142, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "eval_loss": 0.1478671133518219, | |
| "eval_runtime": 734.6914, | |
| "eval_samples_per_second": 21.834, | |
| "eval_steps_per_second": 2.73, | |
| "eval_wer": 0.12915275739887616, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 1.2238861157330375e-05, | |
| "loss": 0.116, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 1.1930732729401616e-05, | |
| "loss": 0.1132, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 1.1622604301472855e-05, | |
| "loss": 0.1141, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 1.1314475873544094e-05, | |
| "loss": 0.1142, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 1.1006347445615333e-05, | |
| "loss": 0.1087, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "eval_loss": 0.14710813760757446, | |
| "eval_runtime": 730.6434, | |
| "eval_samples_per_second": 21.955, | |
| "eval_steps_per_second": 2.746, | |
| "eval_wer": 0.12841591327024238, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 1.0698219017686572e-05, | |
| "loss": 0.1094, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 1.0390090589757811e-05, | |
| "loss": 0.1072, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 1.008196216182905e-05, | |
| "loss": 0.1082, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 9.773833733900289e-06, | |
| "loss": 0.1097, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 9.46570530597153e-06, | |
| "loss": 0.1076, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "eval_loss": 0.14665587246418, | |
| "eval_runtime": 789.1119, | |
| "eval_samples_per_second": 20.328, | |
| "eval_steps_per_second": 2.542, | |
| "eval_wer": 0.12696144703372184, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 9.157576878042769e-06, | |
| "loss": 0.111, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 8.849448450114008e-06, | |
| "loss": 0.1092, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 8.541320022185247e-06, | |
| "loss": 0.1103, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 8.233191594256488e-06, | |
| "loss": 0.1057, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 7.928144450607015e-06, | |
| "loss": 0.1078, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "eval_loss": 0.14669346809387207, | |
| "eval_runtime": 776.8801, | |
| "eval_samples_per_second": 20.648, | |
| "eval_steps_per_second": 2.582, | |
| "eval_wer": 0.12701911309596273, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 7.620016022678253e-06, | |
| "loss": 0.1106, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 7.311887594749492e-06, | |
| "loss": 0.1057, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 7.003759166820731e-06, | |
| "loss": 0.1069, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 6.695630738891971e-06, | |
| "loss": 0.1089, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 6.38750231096321e-06, | |
| "loss": 0.1073, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "eval_loss": 0.14469479024410248, | |
| "eval_runtime": 770.0295, | |
| "eval_samples_per_second": 20.832, | |
| "eval_steps_per_second": 2.605, | |
| "eval_wer": 0.1256159055814341, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 6.079373883034449e-06, | |
| "loss": 0.1056, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 5.771245455105688e-06, | |
| "loss": 0.105, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 5.463117027176928e-06, | |
| "loss": 0.1078, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 5.154988599248167e-06, | |
| "loss": 0.1061, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 4.8468601713194066e-06, | |
| "loss": 0.108, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 0.14469197392463684, | |
| "eval_runtime": 768.5913, | |
| "eval_samples_per_second": 20.871, | |
| "eval_steps_per_second": 2.61, | |
| "eval_wer": 0.1257248303656669, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 4.538731743390645e-06, | |
| "loss": 0.106, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 4.230603315461885e-06, | |
| "loss": 0.1076, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 3.922474887533124e-06, | |
| "loss": 0.1065, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 3.6143464596043634e-06, | |
| "loss": 0.1045, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 3.306218031675602e-06, | |
| "loss": 0.106, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "eval_loss": 0.14382557570934296, | |
| "eval_runtime": 768.3649, | |
| "eval_samples_per_second": 20.877, | |
| "eval_steps_per_second": 2.611, | |
| "eval_wer": 0.1254813514362053, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 2.998089603746842e-06, | |
| "loss": 0.1051, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 2.6899611758180813e-06, | |
| "loss": 0.1116, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 2.3818327478893203e-06, | |
| "loss": 0.1048, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 2.0737043199605598e-06, | |
| "loss": 0.1057, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 1.771738460590374e-06, | |
| "loss": 0.1052, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_loss": 0.14279937744140625, | |
| "eval_runtime": 740.2589, | |
| "eval_samples_per_second": 21.669, | |
| "eval_steps_per_second": 2.71, | |
| "eval_wer": 0.1247124706063266, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 1.4636100326616134e-06, | |
| "loss": 0.1012, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 1.1554816047328529e-06, | |
| "loss": 0.1051, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 8.473531768040921e-07, | |
| "loss": 0.1043, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 5.392247488753312e-07, | |
| "loss": 0.1038, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 2.3109632094657053e-07, | |
| "loss": 0.1044, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_loss": 0.1430039405822754, | |
| "eval_runtime": 779.4591, | |
| "eval_samples_per_second": 20.58, | |
| "eval_steps_per_second": 2.574, | |
| "eval_wer": 0.12453306507935491, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 36060, | |
| "total_flos": 2.2265672303557702e+21, | |
| "train_loss": 0.23386146696950752, | |
| "train_runtime": 329994.9794, | |
| "train_samples_per_second": 13.987, | |
| "train_steps_per_second": 0.109 | |
| } | |
| ], | |
| "max_steps": 36060, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.2265672303557702e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |