| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9809064397204748, | |
| "global_step": 27000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.999815761247666e-05, | |
| "loss": 4.5119, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.999169171843241e-05, | |
| "loss": 2.6638, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 6.998057503298084e-05, | |
| "loss": 1.183, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.996480903365516e-05, | |
| "loss": 0.7325, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.99443958159349e-05, | |
| "loss": 0.5966, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.991933809296747e-05, | |
| "loss": 0.5263, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.988963919520753e-05, | |
| "loss": 0.5068, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.985530306997431e-05, | |
| "loss": 0.4704, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.981633428092705e-05, | |
| "loss": 0.4521, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.977273800745834e-05, | |
| "loss": 0.4439, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 6.972452004400577e-05, | |
| "loss": 0.421, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 6.96716867992818e-05, | |
| "loss": 0.4105, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 6.961424529542192e-05, | |
| "loss": 0.3998, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 6.955220316705135e-05, | |
| "loss": 0.3971, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.948556866027035e-05, | |
| "loss": 0.3958, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.26585060358047485, | |
| "eval_runtime": 1119.616, | |
| "eval_samples_per_second": 14.297, | |
| "eval_steps_per_second": 1.787, | |
| "eval_wer": 0.2537555992570742, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.941435063155818e-05, | |
| "loss": 0.3828, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.933855854659593e-05, | |
| "loss": 0.3852, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.925820247900854e-05, | |
| "loss": 0.3749, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.917329310902582e-05, | |
| "loss": 0.3853, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 6.90838417220629e-05, | |
| "loss": 0.3692, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 6.898986020722038e-05, | |
| "loss": 0.3676, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 6.889136105570403e-05, | |
| "loss": 0.3697, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 6.878835735916458e-05, | |
| "loss": 0.3608, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.868086280795778e-05, | |
| "loss": 0.3515, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.85688916893247e-05, | |
| "loss": 0.3383, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 6.845245888549281e-05, | |
| "loss": 0.3421, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 6.833157987169802e-05, | |
| "loss": 0.3454, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.820627071412778e-05, | |
| "loss": 0.3499, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.807654806778575e-05, | |
| "loss": 0.3411, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 6.794242917427811e-05, | |
| "loss": 0.3422, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.21751175820827484, | |
| "eval_runtime": 1050.6432, | |
| "eval_samples_per_second": 15.235, | |
| "eval_steps_per_second": 1.905, | |
| "eval_wer": 0.23247159401289194, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 6.780393185952203e-05, | |
| "loss": 0.3378, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 6.766107453137634e-05, | |
| "loss": 0.3354, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 6.751387617719493e-05, | |
| "loss": 0.3332, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.736235636130315e-05, | |
| "loss": 0.3313, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 6.720653522239741e-05, | |
| "loss": 0.3291, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 6.704643347086866e-05, | |
| "loss": 0.3225, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.688207238604962e-05, | |
| "loss": 0.3314, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 6.671347381338648e-05, | |
| "loss": 0.3279, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.654066016153562e-05, | |
| "loss": 0.3248, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.636365439938497e-05, | |
| "loss": 0.3184, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6.618248005300135e-05, | |
| "loss": 0.3312, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.599716120250359e-05, | |
| "loss": 0.3156, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.58077224788619e-05, | |
| "loss": 0.32, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.561418906062424e-05, | |
| "loss": 0.3143, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.541658667056979e-05, | |
| "loss": 0.3151, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.2139398157596588, | |
| "eval_runtime": 1046.9527, | |
| "eval_samples_per_second": 15.289, | |
| "eval_steps_per_second": 1.911, | |
| "eval_wer": 0.19961351469463565, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.521494157229007e-05, | |
| "loss": 0.3228, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.50092805666982e-05, | |
| "loss": 0.3223, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.47996309884668e-05, | |
| "loss": 0.3186, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.45860207023949e-05, | |
| "loss": 0.3069, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.436847809970438e-05, | |
| "loss": 0.3149, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.41470320942664e-05, | |
| "loss": 0.3152, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.392171211875852e-05, | |
| "loss": 0.3054, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.369485868905532e-05, | |
| "loss": 0.3196, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.346191911024053e-05, | |
| "loss": 0.3011, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.322519662061658e-05, | |
| "loss": 0.3103, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.298472268327846e-05, | |
| "loss": 0.305, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.274052925993097e-05, | |
| "loss": 0.3043, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.249264880664065e-05, | |
| "loss": 0.3031, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.224111426952202e-05, | |
| "loss": 0.2988, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.198595908035864e-05, | |
| "loss": 0.3, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.20627757906913757, | |
| "eval_runtime": 1055.8743, | |
| "eval_samples_per_second": 15.16, | |
| "eval_steps_per_second": 1.895, | |
| "eval_wer": 0.20541079427510106, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.172721715215964e-05, | |
| "loss": 0.2983, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.146492287465236e-05, | |
| "loss": 0.3012, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.119911110971146e-05, | |
| "loss": 0.2989, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.092981718672549e-05, | |
| "loss": 0.2909, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.065707689790118e-05, | |
| "loss": 0.3063, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.03809264935062e-05, | |
| "loss": 0.2908, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.0101402677051154e-05, | |
| "loss": 0.309, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.981854260041124e-05, | |
| "loss": 0.2891, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.9532383858888345e-05, | |
| "loss": 0.2902, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.924296448621422e-05, | |
| "loss": 0.289, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.8950322949495356e-05, | |
| "loss": 0.2951, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.8654498144100274e-05, | |
| "loss": 0.2923, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.835552938848987e-05, | |
| "loss": 0.2967, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.805345641899159e-05, | |
| "loss": 0.2863, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.774831938451798e-05, | |
| "loss": 0.2824, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.18351121246814728, | |
| "eval_runtime": 1075.697, | |
| "eval_samples_per_second": 14.881, | |
| "eval_steps_per_second": 1.86, | |
| "eval_wer": 0.18133398885611274, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.744325527887681e-05, | |
| "loss": 0.2833, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.713214180625491e-05, | |
| "loss": 0.2909, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.68180867217851e-05, | |
| "loss": 0.286, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.650113176693846e-05, | |
| "loss": 0.2778, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 5.618131906861165e-05, | |
| "loss": 0.2777, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 5.5858691133527713e-05, | |
| "loss": 0.2829, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.553329084258652e-05, | |
| "loss": 0.2748, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.5205161445165346e-05, | |
| "loss": 0.2827, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5.4874346553370585e-05, | |
| "loss": 0.2712, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5.4540890136241195e-05, | |
| "loss": 0.2792, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 5.420483651390469e-05, | |
| "loss": 0.2815, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.386623035168656e-05, | |
| "loss": 0.2766, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.3525116654173646e-05, | |
| "loss": 0.2704, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.318154075923263e-05, | |
| "loss": 0.2695, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.283554833198404e-05, | |
| "loss": 0.2771, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.18808312714099884, | |
| "eval_runtime": 1061.3581, | |
| "eval_samples_per_second": 15.082, | |
| "eval_steps_per_second": 1.885, | |
| "eval_wer": 0.17624685895334863, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.2487185358732866e-05, | |
| "loss": 0.276, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.213649814085646e-05, | |
| "loss": 0.2647, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.178353328865057e-05, | |
| "loss": 0.2901, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.142833771513431e-05, | |
| "loss": 0.2771, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.107095862981481e-05, | |
| "loss": 0.2706, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.071144353241269e-05, | |
| "loss": 0.2753, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.0353466418956284e-05, | |
| "loss": 0.2777, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.9989843088674705e-05, | |
| "loss": 0.2621, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.962422743878782e-05, | |
| "loss": 0.2628, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.9256668063748734e-05, | |
| "loss": 0.272, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.8887213816353655e-05, | |
| "loss": 0.2683, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.851591380124868e-05, | |
| "loss": 0.2627, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.814281736840332e-05, | |
| "loss": 0.2565, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.776797410655135e-05, | |
| "loss": 0.2619, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.739143383659982e-05, | |
| "loss": 0.2616, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.18062810599803925, | |
| "eval_runtime": 1044.5923, | |
| "eval_samples_per_second": 15.324, | |
| "eval_steps_per_second": 1.916, | |
| "eval_wer": 0.17676581448705342, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.701324660500736e-05, | |
| "loss": 0.2575, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.663346267713244e-05, | |
| "loss": 0.2642, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.625213253055248e-05, | |
| "loss": 0.2561, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.586930684835486e-05, | |
| "loss": 0.2553, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.5485036512400575e-05, | |
| "loss": 0.2533, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.509937259656139e-05, | |
| "loss": 0.2528, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.471236635993164e-05, | |
| "loss": 0.2542, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.432406924001522e-05, | |
| "loss": 0.2506, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.393453284588905e-05, | |
| "loss": 0.2587, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.3543808951343574e-05, | |
| "loss": 0.2503, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.3151949488001475e-05, | |
| "loss": 0.2535, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.275900653841536e-05, | |
| "loss": 0.2526, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.236503232914543e-05, | |
| "loss": 0.253, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.197007922381793e-05, | |
| "loss": 0.2523, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.157419971616547e-05, | |
| "loss": 0.2446, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.1757470816373825, | |
| "eval_runtime": 1062.3089, | |
| "eval_samples_per_second": 15.068, | |
| "eval_steps_per_second": 1.884, | |
| "eval_wer": 0.1589711023708074, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.1177446423050005e-05, | |
| "loss": 0.2473, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.077987207746943e-05, | |
| "loss": 0.2438, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.0381529521548834e-05, | |
| "loss": 0.2468, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.998247169951711e-05, | |
| "loss": 0.2524, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.958275165067014e-05, | |
| "loss": 0.2372, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.91824225023212e-05, | |
| "loss": 0.2324, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.8785548889903e-05, | |
| "loss": 0.2436, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.8384166003361756e-05, | |
| "loss": 0.2405, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.798635370086602e-05, | |
| "loss": 0.2349, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.7584128333900755e-05, | |
| "loss": 0.2424, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.7181559507066575e-05, | |
| "loss": 0.2366, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.677870072631157e-05, | |
| "loss": 0.2435, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.637560553612199e-05, | |
| "loss": 0.2377, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.597232751240556e-05, | |
| "loss": 0.2302, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.556892025537066e-05, | |
| "loss": 0.2377, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.1588028222322464, | |
| "eval_runtime": 1044.908, | |
| "eval_samples_per_second": 15.319, | |
| "eval_steps_per_second": 1.915, | |
| "eval_wer": 0.15275046432863543, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.516543738240223e-05, | |
| "loss": 0.2313, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.476193252093543e-05, | |
| "loss": 0.22, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.4358459301327927e-05, | |
| "loss": 0.214, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.395507134973183e-05, | |
| "loss": 0.2257, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.355182228096618e-05, | |
| "loss": 0.2308, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.314876569139091e-05, | |
| "loss": 0.2244, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.274595515178329e-05, | |
| "loss": 0.2176, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.234344420021777e-05, | |
| "loss": 0.2238, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.194128633495017e-05, | |
| "loss": 0.219, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.153953500730713e-05, | |
| "loss": 0.2265, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.113824361458186e-05, | |
| "loss": 0.2218, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.073746549293703e-05, | |
| "loss": 0.2129, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.0337253910315748e-05, | |
| "loss": 0.2126, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.993766205936171e-05, | |
| "loss": 0.2047, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.9538743050349254e-05, | |
| "loss": 0.2141, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.14499780535697937, | |
| "eval_runtime": 1046.3411, | |
| "eval_samples_per_second": 15.298, | |
| "eval_steps_per_second": 1.912, | |
| "eval_wer": 0.14962307440183548, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.9140549904124422e-05, | |
| "loss": 0.2066, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2.8743135545057887e-05, | |
| "loss": 0.2124, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2.8346552794010703e-05, | |
| "loss": 0.2089, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.7950854361313814e-05, | |
| "loss": 0.2121, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.755609283976226e-05, | |
| "loss": 0.209, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.7162320697625e-05, | |
| "loss": 0.2052, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.676959027167128e-05, | |
| "loss": 0.209, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.6377953760214495e-05, | |
| "loss": 0.2089, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.598746321617443e-05, | |
| "loss": 0.2021, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.5598170540158846e-05, | |
| "loss": 0.2047, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.5210127473565314e-05, | |
| "loss": 0.1979, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.482338559170417e-05, | |
| "loss": 0.2044, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.4437996296943596e-05, | |
| "loss": 0.2082, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.4057843550135512e-05, | |
| "loss": 0.2004, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.3675298110320073e-05, | |
| "loss": 0.1953, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.13918258249759674, | |
| "eval_runtime": 1060.8068, | |
| "eval_samples_per_second": 15.089, | |
| "eval_steps_per_second": 1.886, | |
| "eval_wer": 0.13435485633125752, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.3294257851410495e-05, | |
| "loss": 0.1984, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.2914773417964826e-05, | |
| "loss": 0.1972, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.2536895247754305e-05, | |
| "loss": 0.194, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.2160673565059625e-05, | |
| "loss": 0.2016, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.1786158373995577e-05, | |
| "loss": 0.1973, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.1413399451864916e-05, | |
| "loss": 0.1872, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.1042446342542387e-05, | |
| "loss": 0.2035, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.0673348349889817e-05, | |
| "loss": 0.1937, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.0306154531203048e-05, | |
| "loss": 0.1938, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.994091369069168e-05, | |
| "loss": 0.1953, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.957767437299243e-05, | |
| "loss": 0.1887, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.9216484856717008e-05, | |
| "loss": 0.1921, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.8857393148035336e-05, | |
| "loss": 0.1917, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.8500446974295e-05, | |
| "loss": 0.1836, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.8145693777677743e-05, | |
| "loss": 0.1923, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.1327279508113861, | |
| "eval_runtime": 1039.577, | |
| "eval_samples_per_second": 15.398, | |
| "eval_steps_per_second": 1.925, | |
| "eval_wer": 0.13173959357587675, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.779669459685722e-05, | |
| "loss": 0.1927, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.7446445408141307e-05, | |
| "loss": 0.1959, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.7098529285272e-05, | |
| "loss": 0.1872, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.6752992470235188e-05, | |
| "loss": 0.1848, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.640988088877985e-05, | |
| "loss": 0.184, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.6069240144314012e-05, | |
| "loss": 0.1919, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.5731115511843525e-05, | |
| "loss": 0.176, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.5395551931954524e-05, | |
| "loss": 0.1789, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.5062594004840269e-05, | |
| "loss": 0.1937, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.4732285984373345e-05, | |
| "loss": 0.1861, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.440467177222377e-05, | |
| "loss": 0.1757, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.4079794912023988e-05, | |
| "loss": 0.1839, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.3757698583581431e-05, | |
| "loss": 0.1844, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.3438425597139414e-05, | |
| "loss": 0.1855, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.3122018387687183e-05, | |
| "loss": 0.1804, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.12711018323898315, | |
| "eval_runtime": 1058.0447, | |
| "eval_samples_per_second": 15.129, | |
| "eval_steps_per_second": 1.891, | |
| "eval_wer": 0.12372992461488037, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.280851900931984e-05, | |
| "loss": 0.1833, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.2497969129648841e-05, | |
| "loss": 0.181, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.2190410024263938e-05, | |
| "loss": 0.1719, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.1885882571247166e-05, | |
| "loss": 0.1758, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.1584427245739682e-05, | |
| "loss": 0.1792, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.1286084114562175e-05, | |
| "loss": 0.1774, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.0990892830889517e-05, | |
| "loss": 0.1796, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.0698892628980422e-05, | |
| "loss": 0.1816, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.041012231896276e-05, | |
| "loss": 0.174, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.012462028167525e-05, | |
| "loss": 0.1717, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.842424463566227e-06, | |
| "loss": 0.1793, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.563572371650113e-06, | |
| "loss": 0.1699, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.288101068522322e-06, | |
| "loss": 0.1726, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.016047167433221e-06, | |
| "loss": 0.1734, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 8.747446827421805e-06, | |
| "loss": 0.1776, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.12307832390069962, | |
| "eval_runtime": 1040.1826, | |
| "eval_samples_per_second": 15.389, | |
| "eval_steps_per_second": 1.924, | |
| "eval_wer": 0.1186018245384027, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 8.482335748509769e-06, | |
| "loss": 0.1755, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.220749166956552e-06, | |
| "loss": 0.1717, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 7.962721850576054e-06, | |
| "loss": 0.167, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.708288094115607e-06, | |
| "loss": 0.1698, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.457481714697784e-06, | |
| "loss": 0.1709, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.210336047325761e-06, | |
| "loss": 0.1748, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.9668839404526865e-06, | |
| "loss": 0.1776, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.727157751615771e-06, | |
| "loss": 0.1664, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.491189343135589e-06, | |
| "loss": 0.1754, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.2590100778812376e-06, | |
| "loss": 0.1766, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 6.030650815101828e-06, | |
| "loss": 0.171, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.808367837755271e-06, | |
| "loss": 0.1703, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.5877001747984834e-06, | |
| "loss": 0.164, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.3709417389918604e-06, | |
| "loss": 0.1664, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.158121339981953e-06, | |
| "loss": 0.1671, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 0.11993325501680374, | |
| "eval_runtime": 1045.6599, | |
| "eval_samples_per_second": 15.308, | |
| "eval_steps_per_second": 1.914, | |
| "eval_wer": 0.11479159838304381, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.949267264005701e-06, | |
| "loss": 0.1576, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.7444072701308795e-06, | |
| "loss": 0.1583, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.543568586566601e-06, | |
| "loss": 0.1678, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.346777907044375e-06, | |
| "loss": 0.1687, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.154061387270205e-06, | |
| "loss": 0.1671, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.965444641448219e-06, | |
| "loss": 0.1656, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.780952738876231e-06, | |
| "loss": 0.169, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.600610200613753e-06, | |
| "loss": 0.1619, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.4244409962228724e-06, | |
| "loss": 0.1702, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.252468540582438e-06, | |
| "loss": 0.1654, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.0847156907759337e-06, | |
| "loss": 0.1593, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.92120474305353e-06, | |
| "loss": 0.1622, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.7619574298686577e-06, | |
| "loss": 0.1653, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.6069949169895127e-06, | |
| "loss": 0.1637, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.4578229939112028e-06, | |
| "loss": 0.1597, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.11753135174512863, | |
| "eval_runtime": 1040.817, | |
| "eval_samples_per_second": 15.379, | |
| "eval_steps_per_second": 1.923, | |
| "eval_wer": 0.11268846279908226, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.311447946777479e-06, | |
| "loss": 0.1599, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.1694175777527574e-06, | |
| "loss": 0.1628, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.0317507642787156e-06, | |
| "loss": 0.1638, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.898465803831184e-06, | |
| "loss": 0.1651, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.7695804114881745e-06, | |
| "loss": 0.1629, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.6451117175753708e-06, | |
| "loss": 0.1699, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.5250762653892972e-06, | |
| "loss": 0.1578, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.4094900089985423e-06, | |
| "loss": 0.1648, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.2983683111232683e-06, | |
| "loss": 0.1607, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.1917259410933516e-06, | |
| "loss": 0.1593, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.0895770728853425e-06, | |
| "loss": 0.159, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 9.919352832386174e-07, | |
| "loss": 0.1608, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.988135498508481e-07, | |
| "loss": 0.1619, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.102242496531358e-07, | |
| "loss": 0.163, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.261791571649655e-07, | |
| "loss": 0.1619, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.11700794845819473, | |
| "eval_runtime": 1036.7542, | |
| "eval_samples_per_second": 15.44, | |
| "eval_steps_per_second": 1.93, | |
| "eval_wer": 0.11198514148366656, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.466894429292585e-07, | |
| "loss": 0.1627, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 5.717656720276581e-07, | |
| "loss": 0.165, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 5.014178026763216e-07, | |
| "loss": 0.1685, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.356551849023648e-07, | |
| "loss": 0.1632, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.7448655930113146e-07, | |
| "loss": 0.164, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.179200558744649e-07, | |
| "loss": 0.1649, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.6596319295015436e-07, | |
| "loss": 0.1583, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.1862287618264806e-07, | |
| "loss": 0.1629, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.7630967021918575e-07, | |
| "loss": 0.1608, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.3817439628416527e-07, | |
| "loss": 0.1629, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.0467265308166828e-07, | |
| "loss": 0.1656, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 7.58088933720985e-08, | |
| "loss": 0.1638, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.158695347542152e-08, | |
| "loss": 0.164, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.2010052761280434e-08, | |
| "loss": 0.1632, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.708079322109368e-08, | |
| "loss": 0.1664, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.11697087436914444, | |
| "eval_runtime": 1037.0691, | |
| "eval_samples_per_second": 15.435, | |
| "eval_steps_per_second": 1.929, | |
| "eval_wer": 0.11169152190538621, | |
| "step": 27000 | |
| } | |
| ], | |
| "max_steps": 27260, | |
| "num_train_epochs": 2, | |
| "total_flos": 4.0022174178965815e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |