|
{ |
|
"best_metric": 0.17314769327640533, |
|
"best_model_checkpoint": "ai-light-dance_singing6_ft_wav2vec2-large-xlsr-53-5gram-v4-2/checkpoint-7866", |
|
"epoch": 49.99926953981008, |
|
"global_step": 8550, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.2e-07, |
|
"loss": 0.4738, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 7.2e-07, |
|
"loss": 0.4674, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.08e-06, |
|
"loss": 0.4675, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.44e-06, |
|
"loss": 0.454, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.84e-06, |
|
"loss": 0.4568, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 2.24e-06, |
|
"loss": 0.4853, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 2.64e-06, |
|
"loss": 0.4603, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 3.0399999999999997e-06, |
|
"loss": 0.4375, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 3.4399999999999997e-06, |
|
"loss": 0.4581, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 3.84e-06, |
|
"loss": 0.4727, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 3.997159763313609e-06, |
|
"loss": 0.4465, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 3.992426035502959e-06, |
|
"loss": 0.4571, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 3.987692307692307e-06, |
|
"loss": 0.4599, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 3.982958579881657e-06, |
|
"loss": 0.4783, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 3.978224852071005e-06, |
|
"loss": 0.4498, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 3.973491124260355e-06, |
|
"loss": 0.4508, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 3.968757396449704e-06, |
|
"loss": 0.4688, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.18223193287849426, |
|
"eval_runtime": 204.6985, |
|
"eval_samples_per_second": 5.945, |
|
"eval_steps_per_second": 0.747, |
|
"eval_wer": 0.09862855908714589, |
|
"step": 171 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 3.964023668639053e-06, |
|
"loss": 0.4795, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 3.959289940828402e-06, |
|
"loss": 0.4957, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 3.954556213017752e-06, |
|
"loss": 0.4621, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 3.9498224852071e-06, |
|
"loss": 0.4511, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 3.94508875739645e-06, |
|
"loss": 0.4515, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 3.9403550295857985e-06, |
|
"loss": 0.4654, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 3.935621301775148e-06, |
|
"loss": 0.4664, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 3.9308875739644966e-06, |
|
"loss": 0.4535, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 3.926153846153846e-06, |
|
"loss": 0.4629, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 3.9218934911242605e-06, |
|
"loss": 0.4593, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 3.917159763313609e-06, |
|
"loss": 0.4575, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 3.9124260355029585e-06, |
|
"loss": 0.4378, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 3.907692307692307e-06, |
|
"loss": 0.4513, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 3.902958579881657e-06, |
|
"loss": 0.4612, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 3.898224852071006e-06, |
|
"loss": 0.4581, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 3.893491124260355e-06, |
|
"loss": 0.4285, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 3.888757396449704e-06, |
|
"loss": 0.4505, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.18223337829113007, |
|
"eval_runtime": 203.1854, |
|
"eval_samples_per_second": 5.99, |
|
"eval_steps_per_second": 0.753, |
|
"eval_wer": 0.09945646305028617, |
|
"step": 342 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 3.884023668639054e-06, |
|
"loss": 0.478, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 3.879289940828402e-06, |
|
"loss": 0.4677, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 3.874556213017752e-06, |
|
"loss": 0.4334, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 3.8698224852071e-06, |
|
"loss": 0.4495, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 3.86508875739645e-06, |
|
"loss": 0.4653, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 3.860355029585798e-06, |
|
"loss": 0.4634, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 3.855621301775148e-06, |
|
"loss": 0.4436, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 3.8508875739644965e-06, |
|
"loss": 0.4335, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 3.846153846153846e-06, |
|
"loss": 0.4596, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 3.8414201183431946e-06, |
|
"loss": 0.4591, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 3.836686390532544e-06, |
|
"loss": 0.4654, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 3.8319526627218935e-06, |
|
"loss": 0.4468, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 3.827218934911242e-06, |
|
"loss": 0.445, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 3.8224852071005916e-06, |
|
"loss": 0.4834, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 3.817751479289941e-06, |
|
"loss": 0.4615, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 3.8130177514792897e-06, |
|
"loss": 0.4448, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 3.8082840236686387e-06, |
|
"loss": 0.4418, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.18191970884799957, |
|
"eval_runtime": 203.1484, |
|
"eval_samples_per_second": 5.991, |
|
"eval_steps_per_second": 0.753, |
|
"eval_wer": 0.09963644217270796, |
|
"step": 513 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 3.803550295857988e-06, |
|
"loss": 0.464, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 3.7988165680473368e-06, |
|
"loss": 0.4711, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 3.7940828402366862e-06, |
|
"loss": 0.4535, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"learning_rate": 3.7893491124260357e-06, |
|
"loss": 0.4537, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 3.27, |
|
"learning_rate": 3.7846153846153843e-06, |
|
"loss": 0.4545, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 3.7798816568047338e-06, |
|
"loss": 0.4658, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 3.775147928994083e-06, |
|
"loss": 0.4653, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 3.770414201183432e-06, |
|
"loss": 0.4501, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"learning_rate": 3.765680473372781e-06, |
|
"loss": 0.4429, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 3.7609467455621304e-06, |
|
"loss": 0.4686, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 3.756213017751479e-06, |
|
"loss": 0.4592, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 3.7514792899408284e-06, |
|
"loss": 0.4376, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"learning_rate": 3.7467455621301775e-06, |
|
"loss": 0.4512, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 3.7420118343195265e-06, |
|
"loss": 0.4815, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 3.7372781065088756e-06, |
|
"loss": 0.4584, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 3.92, |
|
"learning_rate": 3.7325443786982246e-06, |
|
"loss": 0.4505, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 3.7278106508875736e-06, |
|
"loss": 0.4505, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 0.18415826559066772, |
|
"eval_runtime": 202.8154, |
|
"eval_samples_per_second": 6.001, |
|
"eval_steps_per_second": 0.754, |
|
"eval_wer": 0.10089629602966056, |
|
"step": 684 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 3.723076923076923e-06, |
|
"loss": 0.4574, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 4.09, |
|
"learning_rate": 3.7183431952662717e-06, |
|
"loss": 0.474, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 4.15, |
|
"learning_rate": 3.713609467455621e-06, |
|
"loss": 0.4617, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 3.7088757396449702e-06, |
|
"loss": 0.4261, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 3.7041420118343193e-06, |
|
"loss": 0.4625, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 3.6994082840236683e-06, |
|
"loss": 0.4612, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 3.6946745562130178e-06, |
|
"loss": 0.4386, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 4.44, |
|
"learning_rate": 3.6899408284023664e-06, |
|
"loss": 0.4524, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 4.5, |
|
"learning_rate": 3.685207100591716e-06, |
|
"loss": 0.4324, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 4.56, |
|
"learning_rate": 3.680473372781065e-06, |
|
"loss": 0.4751, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 3.675739644970414e-06, |
|
"loss": 0.4776, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 3.671005917159763e-06, |
|
"loss": 0.4545, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"learning_rate": 3.6662721893491124e-06, |
|
"loss": 0.4646, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"learning_rate": 3.661538461538461e-06, |
|
"loss": 0.4721, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 3.6568047337278105e-06, |
|
"loss": 0.4624, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 3.65207100591716e-06, |
|
"loss": 0.4484, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"learning_rate": 3.6473372781065086e-06, |
|
"loss": 0.4403, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 0.18165241181850433, |
|
"eval_runtime": 202.983, |
|
"eval_samples_per_second": 5.996, |
|
"eval_steps_per_second": 0.754, |
|
"eval_wer": 0.09834059249127101, |
|
"step": 855 |
|
}, |
|
{ |
|
"epoch": 5.03, |
|
"learning_rate": 3.642603550295858e-06, |
|
"loss": 0.4662, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 5.09, |
|
"learning_rate": 3.637869822485207e-06, |
|
"loss": 0.4799, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 5.15, |
|
"learning_rate": 3.633136094674556e-06, |
|
"loss": 0.4484, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 5.2, |
|
"learning_rate": 3.628402366863905e-06, |
|
"loss": 0.4606, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 5.26, |
|
"learning_rate": 3.6236686390532546e-06, |
|
"loss": 0.4394, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 5.32, |
|
"learning_rate": 3.6189349112426033e-06, |
|
"loss": 0.4775, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 5.38, |
|
"learning_rate": 3.6142011834319527e-06, |
|
"loss": 0.4406, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 5.44, |
|
"learning_rate": 3.6094674556213013e-06, |
|
"loss": 0.4534, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 5.5, |
|
"learning_rate": 3.6052071005917158e-06, |
|
"loss": 0.4485, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 5.56, |
|
"learning_rate": 3.600473372781065e-06, |
|
"loss": 0.4741, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"learning_rate": 3.595739644970414e-06, |
|
"loss": 0.4669, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 5.67, |
|
"learning_rate": 3.591005917159763e-06, |
|
"loss": 0.4402, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 5.73, |
|
"learning_rate": 3.5862721893491123e-06, |
|
"loss": 0.456, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 3.581538461538461e-06, |
|
"loss": 0.4594, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 5.85, |
|
"learning_rate": 3.5768047337278104e-06, |
|
"loss": 0.4678, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 5.91, |
|
"learning_rate": 3.57207100591716e-06, |
|
"loss": 0.4602, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 5.96, |
|
"learning_rate": 3.5673372781065085e-06, |
|
"loss": 0.4362, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 0.18196654319763184, |
|
"eval_runtime": 204.2134, |
|
"eval_samples_per_second": 5.959, |
|
"eval_steps_per_second": 0.749, |
|
"eval_wer": 0.100140383715489, |
|
"step": 1026 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 3.562603550295858e-06, |
|
"loss": 0.4506, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"learning_rate": 3.557869822485207e-06, |
|
"loss": 0.4852, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 6.14, |
|
"learning_rate": 3.553136094674556e-06, |
|
"loss": 0.4499, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 6.2, |
|
"learning_rate": 3.548402366863905e-06, |
|
"loss": 0.4524, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 6.26, |
|
"learning_rate": 3.5436686390532546e-06, |
|
"loss": 0.4422, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 6.32, |
|
"learning_rate": 3.538934911242603e-06, |
|
"loss": 0.4698, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 6.37, |
|
"learning_rate": 3.5342011834319526e-06, |
|
"loss": 0.4595, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 6.43, |
|
"learning_rate": 3.5294674556213017e-06, |
|
"loss": 0.4426, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 6.49, |
|
"learning_rate": 3.5247337278106507e-06, |
|
"loss": 0.4504, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 6.55, |
|
"learning_rate": 3.5199999999999998e-06, |
|
"loss": 0.4423, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 6.61, |
|
"learning_rate": 3.5152662721893492e-06, |
|
"loss": 0.4521, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 6.67, |
|
"learning_rate": 3.510532544378698e-06, |
|
"loss": 0.4492, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 6.72, |
|
"learning_rate": 3.5057988165680473e-06, |
|
"loss": 0.4322, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 6.78, |
|
"learning_rate": 3.5010650887573963e-06, |
|
"loss": 0.4664, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 6.84, |
|
"learning_rate": 3.4963313609467454e-06, |
|
"loss": 0.4754, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 6.9, |
|
"learning_rate": 3.4915976331360944e-06, |
|
"loss": 0.4453, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 6.96, |
|
"learning_rate": 3.486863905325444e-06, |
|
"loss": 0.4546, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 0.17951874434947968, |
|
"eval_runtime": 203.704, |
|
"eval_samples_per_second": 5.974, |
|
"eval_steps_per_second": 0.751, |
|
"eval_wer": 0.0979086425974587, |
|
"step": 1197 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"learning_rate": 3.4821301775147925e-06, |
|
"loss": 0.4157, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 7.08, |
|
"learning_rate": 3.477396449704142e-06, |
|
"loss": 0.4768, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 7.13, |
|
"learning_rate": 3.472662721893491e-06, |
|
"loss": 0.4576, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 7.19, |
|
"learning_rate": 3.46792899408284e-06, |
|
"loss": 0.4589, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 7.25, |
|
"learning_rate": 3.463195266272189e-06, |
|
"loss": 0.4568, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 7.31, |
|
"learning_rate": 3.458461538461538e-06, |
|
"loss": 0.4818, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 7.37, |
|
"learning_rate": 3.453727810650887e-06, |
|
"loss": 0.4389, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 7.43, |
|
"learning_rate": 3.4489940828402366e-06, |
|
"loss": 0.4448, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 7.49, |
|
"learning_rate": 3.4442603550295852e-06, |
|
"loss": 0.4393, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 7.54, |
|
"learning_rate": 3.4395266272189347e-06, |
|
"loss": 0.4532, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 7.6, |
|
"learning_rate": 3.434792899408284e-06, |
|
"loss": 0.4638, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 7.66, |
|
"learning_rate": 3.4300591715976328e-06, |
|
"loss": 0.4479, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 7.72, |
|
"learning_rate": 3.4253254437869822e-06, |
|
"loss": 0.4213, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 7.78, |
|
"learning_rate": 3.4205917159763313e-06, |
|
"loss": 0.4374, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 7.84, |
|
"learning_rate": 3.4158579881656803e-06, |
|
"loss": 0.4695, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 7.89, |
|
"learning_rate": 3.4111242603550294e-06, |
|
"loss": 0.4404, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 7.95, |
|
"learning_rate": 3.406390532544379e-06, |
|
"loss": 0.4283, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 0.18410374224185944, |
|
"eval_runtime": 205.2946, |
|
"eval_samples_per_second": 5.928, |
|
"eval_steps_per_second": 0.745, |
|
"eval_wer": 0.10042835031136388, |
|
"step": 1368 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 3.4016568047337274e-06, |
|
"loss": 0.4457, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 8.07, |
|
"learning_rate": 3.396923076923077e-06, |
|
"loss": 0.4687, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 8.13, |
|
"learning_rate": 3.392189349112426e-06, |
|
"loss": 0.4679, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 8.19, |
|
"learning_rate": 3.387455621301775e-06, |
|
"loss": 0.4584, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 8.25, |
|
"learning_rate": 3.382721893491124e-06, |
|
"loss": 0.4336, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 8.3, |
|
"learning_rate": 3.3779881656804735e-06, |
|
"loss": 0.4636, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 8.36, |
|
"learning_rate": 3.373254437869822e-06, |
|
"loss": 0.4534, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 8.42, |
|
"learning_rate": 3.3685207100591716e-06, |
|
"loss": 0.4326, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 8.48, |
|
"learning_rate": 3.3637869822485206e-06, |
|
"loss": 0.4519, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 8.54, |
|
"learning_rate": 3.3590532544378697e-06, |
|
"loss": 0.4608, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 8.6, |
|
"learning_rate": 3.3543195266272187e-06, |
|
"loss": 0.4838, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 8.65, |
|
"learning_rate": 3.349585798816568e-06, |
|
"loss": 0.4378, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 8.71, |
|
"learning_rate": 3.3448520710059168e-06, |
|
"loss": 0.4386, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 8.77, |
|
"learning_rate": 3.3401183431952662e-06, |
|
"loss": 0.4411, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 8.83, |
|
"learning_rate": 3.335384615384615e-06, |
|
"loss": 0.4632, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 8.89, |
|
"learning_rate": 3.3306508875739643e-06, |
|
"loss": 0.4355, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 8.95, |
|
"learning_rate": 3.3259171597633134e-06, |
|
"loss": 0.4289, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 0.17826400697231293, |
|
"eval_runtime": 205.1698, |
|
"eval_samples_per_second": 5.932, |
|
"eval_steps_per_second": 0.746, |
|
"eval_wer": 0.09697275116086534, |
|
"step": 1539 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 3.3211834319526624e-06, |
|
"loss": 0.4529, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 9.06, |
|
"learning_rate": 3.3164497041420114e-06, |
|
"loss": 0.4706, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 9.12, |
|
"learning_rate": 3.311715976331361e-06, |
|
"loss": 0.4505, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 9.18, |
|
"learning_rate": 3.3069822485207095e-06, |
|
"loss": 0.4465, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 9.24, |
|
"learning_rate": 3.302248520710059e-06, |
|
"loss": 0.4335, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 9.3, |
|
"learning_rate": 3.2975147928994084e-06, |
|
"loss": 0.4725, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 9.36, |
|
"learning_rate": 3.292781065088757e-06, |
|
"loss": 0.4762, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 9.41, |
|
"learning_rate": 3.2880473372781065e-06, |
|
"loss": 0.4539, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 9.47, |
|
"learning_rate": 3.2833136094674556e-06, |
|
"loss": 0.4143, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 9.53, |
|
"learning_rate": 3.2785798816568046e-06, |
|
"loss": 0.4662, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 9.59, |
|
"learning_rate": 3.2738461538461536e-06, |
|
"loss": 0.4624, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 9.65, |
|
"learning_rate": 3.269112426035503e-06, |
|
"loss": 0.4482, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 9.71, |
|
"learning_rate": 3.2643786982248517e-06, |
|
"loss": 0.4191, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 9.77, |
|
"learning_rate": 3.259644970414201e-06, |
|
"loss": 0.4575, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 9.82, |
|
"learning_rate": 3.2549112426035502e-06, |
|
"loss": 0.4516, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 9.88, |
|
"learning_rate": 3.2501775147928993e-06, |
|
"loss": 0.45, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 9.94, |
|
"learning_rate": 3.2454437869822483e-06, |
|
"loss": 0.4442, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 3.2407100591715978e-06, |
|
"loss": 0.445, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_loss": 0.17852193117141724, |
|
"eval_runtime": 204.8602, |
|
"eval_samples_per_second": 5.941, |
|
"eval_steps_per_second": 0.747, |
|
"eval_wer": 0.09693675533638098, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 10.06, |
|
"learning_rate": 3.2359763313609464e-06, |
|
"loss": 0.4756, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 10.12, |
|
"learning_rate": 3.231242603550296e-06, |
|
"loss": 0.4602, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 10.18, |
|
"learning_rate": 3.226508875739645e-06, |
|
"loss": 0.4489, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 10.23, |
|
"learning_rate": 3.221775147928994e-06, |
|
"loss": 0.4337, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 10.29, |
|
"learning_rate": 3.217041420118343e-06, |
|
"loss": 0.4584, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 10.35, |
|
"learning_rate": 3.212307692307692e-06, |
|
"loss": 0.4869, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 10.41, |
|
"learning_rate": 3.207573964497041e-06, |
|
"loss": 0.4518, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 10.47, |
|
"learning_rate": 3.2028402366863905e-06, |
|
"loss": 0.4513, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 10.53, |
|
"learning_rate": 3.198106508875739e-06, |
|
"loss": 0.4602, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 10.58, |
|
"learning_rate": 3.1933727810650886e-06, |
|
"loss": 0.4373, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 10.64, |
|
"learning_rate": 3.1886390532544376e-06, |
|
"loss": 0.4375, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 10.7, |
|
"learning_rate": 3.1839053254437867e-06, |
|
"loss": 0.4182, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 10.76, |
|
"learning_rate": 3.1791715976331357e-06, |
|
"loss": 0.4475, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 10.82, |
|
"learning_rate": 3.174437869822485e-06, |
|
"loss": 0.4819, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 10.88, |
|
"learning_rate": 3.169704142011834e-06, |
|
"loss": 0.4502, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 10.93, |
|
"learning_rate": 3.1649704142011833e-06, |
|
"loss": 0.4264, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 10.99, |
|
"learning_rate": 3.1602366863905327e-06, |
|
"loss": 0.4483, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"eval_loss": 0.17809000611305237, |
|
"eval_runtime": 204.1811, |
|
"eval_samples_per_second": 5.96, |
|
"eval_steps_per_second": 0.749, |
|
"eval_wer": 0.09902451315647384, |
|
"step": 1881 |
|
}, |
|
{ |
|
"epoch": 11.05, |
|
"learning_rate": 3.1555029585798813e-06, |
|
"loss": 0.4622, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 11.11, |
|
"learning_rate": 3.150769230769231e-06, |
|
"loss": 0.47, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 11.17, |
|
"learning_rate": 3.14603550295858e-06, |
|
"loss": 0.4462, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 11.23, |
|
"learning_rate": 3.141301775147929e-06, |
|
"loss": 0.4254, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 11.29, |
|
"learning_rate": 3.136568047337278e-06, |
|
"loss": 0.4621, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 11.34, |
|
"learning_rate": 3.1318343195266274e-06, |
|
"loss": 0.4677, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 11.4, |
|
"learning_rate": 3.127100591715976e-06, |
|
"loss": 0.4593, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 11.46, |
|
"learning_rate": 3.1223668639053255e-06, |
|
"loss": 0.4358, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 11.52, |
|
"learning_rate": 3.1176331360946745e-06, |
|
"loss": 0.4606, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 11.58, |
|
"learning_rate": 3.1128994082840235e-06, |
|
"loss": 0.4538, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 11.64, |
|
"learning_rate": 3.1081656804733726e-06, |
|
"loss": 0.4357, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 11.7, |
|
"learning_rate": 3.103431952662722e-06, |
|
"loss": 0.4398, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 11.75, |
|
"learning_rate": 3.0986982248520707e-06, |
|
"loss": 0.4467, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 11.81, |
|
"learning_rate": 3.09396449704142e-06, |
|
"loss": 0.4668, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 11.87, |
|
"learning_rate": 3.089230769230769e-06, |
|
"loss": 0.4535, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 11.93, |
|
"learning_rate": 3.084497041420118e-06, |
|
"loss": 0.4475, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 11.99, |
|
"learning_rate": 3.0797633136094672e-06, |
|
"loss": 0.4319, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"eval_loss": 0.18109293282032013, |
|
"eval_runtime": 204.6905, |
|
"eval_samples_per_second": 5.946, |
|
"eval_steps_per_second": 0.747, |
|
"eval_wer": 0.09952845469925489, |
|
"step": 2052 |
|
}, |
|
{ |
|
"epoch": 12.05, |
|
"learning_rate": 3.0750295857988163e-06, |
|
"loss": 0.4523, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 12.11, |
|
"learning_rate": 3.0702958579881653e-06, |
|
"loss": 0.4717, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 12.16, |
|
"learning_rate": 3.065562130177515e-06, |
|
"loss": 0.4441, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 12.22, |
|
"learning_rate": 3.0608284023668634e-06, |
|
"loss": 0.4355, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 12.28, |
|
"learning_rate": 3.056094674556213e-06, |
|
"loss": 0.4585, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 12.34, |
|
"learning_rate": 3.051360946745562e-06, |
|
"loss": 0.4717, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 12.4, |
|
"learning_rate": 3.046627218934911e-06, |
|
"loss": 0.434, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 12.46, |
|
"learning_rate": 3.04189349112426e-06, |
|
"loss": 0.4573, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 12.51, |
|
"learning_rate": 3.0371597633136095e-06, |
|
"loss": 0.4321, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 12.57, |
|
"learning_rate": 3.032426035502958e-06, |
|
"loss": 0.434, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 12.63, |
|
"learning_rate": 3.0276923076923075e-06, |
|
"loss": 0.4437, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 12.69, |
|
"learning_rate": 3.022958579881657e-06, |
|
"loss": 0.4336, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 12.75, |
|
"learning_rate": 3.0182248520710056e-06, |
|
"loss": 0.4232, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 12.81, |
|
"learning_rate": 3.013491124260355e-06, |
|
"loss": 0.4747, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 12.86, |
|
"learning_rate": 3.008757396449704e-06, |
|
"loss": 0.4515, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 12.92, |
|
"learning_rate": 3.004023668639053e-06, |
|
"loss": 0.4315, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 12.98, |
|
"learning_rate": 2.999289940828402e-06, |
|
"loss": 0.4175, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"eval_loss": 0.17807559669017792, |
|
"eval_runtime": 205.1909, |
|
"eval_samples_per_second": 5.931, |
|
"eval_steps_per_second": 0.746, |
|
"eval_wer": 0.09794463842194305, |
|
"step": 2223 |
|
}, |
|
{ |
|
"epoch": 13.04, |
|
"learning_rate": 2.9945562130177517e-06, |
|
"loss": 0.4532, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 13.1, |
|
"learning_rate": 2.9898224852071003e-06, |
|
"loss": 0.4635, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 13.16, |
|
"learning_rate": 2.9850887573964497e-06, |
|
"loss": 0.4374, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 13.22, |
|
"learning_rate": 2.9803550295857988e-06, |
|
"loss": 0.4321, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 13.27, |
|
"learning_rate": 2.975621301775148e-06, |
|
"loss": 0.45, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 13.33, |
|
"learning_rate": 2.970887573964497e-06, |
|
"loss": 0.4662, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 13.39, |
|
"learning_rate": 2.9661538461538463e-06, |
|
"loss": 0.44, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 13.45, |
|
"learning_rate": 2.961420118343195e-06, |
|
"loss": 0.445, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 13.51, |
|
"learning_rate": 2.9566863905325444e-06, |
|
"loss": 0.4508, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 13.57, |
|
"learning_rate": 2.951952662721893e-06, |
|
"loss": 0.4631, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 13.63, |
|
"learning_rate": 2.9472189349112425e-06, |
|
"loss": 0.4452, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 13.68, |
|
"learning_rate": 2.9424852071005915e-06, |
|
"loss": 0.4521, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 13.74, |
|
"learning_rate": 2.9377514792899406e-06, |
|
"loss": 0.4471, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 13.8, |
|
"learning_rate": 2.9330177514792896e-06, |
|
"loss": 0.4607, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 13.86, |
|
"learning_rate": 2.928284023668639e-06, |
|
"loss": 0.4575, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 13.92, |
|
"learning_rate": 2.9235502958579877e-06, |
|
"loss": 0.4357, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 13.98, |
|
"learning_rate": 2.918816568047337e-06, |
|
"loss": 0.4298, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"eval_loss": 0.17605595290660858, |
|
"eval_runtime": 206.2655, |
|
"eval_samples_per_second": 5.9, |
|
"eval_steps_per_second": 0.742, |
|
"eval_wer": 0.09690075951189663, |
|
"step": 2394 |
|
}, |
|
{ |
|
"epoch": 14.04, |
|
"learning_rate": 2.914082840236686e-06, |
|
"loss": 0.4561, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 14.09, |
|
"learning_rate": 2.9093491124260352e-06, |
|
"loss": 0.4599, |
|
"step": 2410 |
|
}, |
|
{ |
|
"epoch": 14.15, |
|
"learning_rate": 2.9046153846153843e-06, |
|
"loss": 0.4525, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 14.21, |
|
"learning_rate": 2.8998816568047337e-06, |
|
"loss": 0.4069, |
|
"step": 2430 |
|
}, |
|
{ |
|
"epoch": 14.27, |
|
"learning_rate": 2.8951479289940823e-06, |
|
"loss": 0.4296, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 14.33, |
|
"learning_rate": 2.890414201183432e-06, |
|
"loss": 0.4748, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 14.39, |
|
"learning_rate": 2.8856804733727813e-06, |
|
"loss": 0.4542, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 14.44, |
|
"learning_rate": 2.88094674556213e-06, |
|
"loss": 0.4509, |
|
"step": 2470 |
|
}, |
|
{ |
|
"epoch": 14.5, |
|
"learning_rate": 2.8762130177514794e-06, |
|
"loss": 0.4476, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 14.56, |
|
"learning_rate": 2.8714792899408284e-06, |
|
"loss": 0.4668, |
|
"step": 2490 |
|
}, |
|
{ |
|
"epoch": 14.62, |
|
"learning_rate": 2.8667455621301774e-06, |
|
"loss": 0.4478, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 14.68, |
|
"learning_rate": 2.8620118343195265e-06, |
|
"loss": 0.4465, |
|
"step": 2510 |
|
}, |
|
{ |
|
"epoch": 14.74, |
|
"learning_rate": 2.857278106508876e-06, |
|
"loss": 0.4337, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 14.79, |
|
"learning_rate": 2.8525443786982246e-06, |
|
"loss": 0.4524, |
|
"step": 2530 |
|
}, |
|
{ |
|
"epoch": 14.85, |
|
"learning_rate": 2.847810650887574e-06, |
|
"loss": 0.4562, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 14.91, |
|
"learning_rate": 2.843076923076923e-06, |
|
"loss": 0.4348, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 14.97, |
|
"learning_rate": 2.838343195266272e-06, |
|
"loss": 0.4511, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"eval_loss": 0.17410650849342346, |
|
"eval_runtime": 205.5116, |
|
"eval_samples_per_second": 5.922, |
|
"eval_steps_per_second": 0.744, |
|
"eval_wer": 0.09499298081422555, |
|
"step": 2565 |
|
}, |
|
{ |
|
"epoch": 15.03, |
|
"learning_rate": 2.833609467455621e-06, |
|
"loss": 0.4744, |
|
"step": 2570 |
|
}, |
|
{ |
|
"epoch": 15.09, |
|
"learning_rate": 2.8288757396449706e-06, |
|
"loss": 0.4622, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 15.15, |
|
"learning_rate": 2.8241420118343192e-06, |
|
"loss": 0.4607, |
|
"step": 2590 |
|
}, |
|
{ |
|
"epoch": 15.2, |
|
"learning_rate": 2.8194082840236687e-06, |
|
"loss": 0.4387, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 15.26, |
|
"learning_rate": 2.8146745562130173e-06, |
|
"loss": 0.4325, |
|
"step": 2610 |
|
}, |
|
{ |
|
"epoch": 15.32, |
|
"learning_rate": 2.8099408284023668e-06, |
|
"loss": 0.4815, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 15.38, |
|
"learning_rate": 2.805207100591716e-06, |
|
"loss": 0.4552, |
|
"step": 2630 |
|
}, |
|
{ |
|
"epoch": 15.44, |
|
"learning_rate": 2.800473372781065e-06, |
|
"loss": 0.4378, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 15.5, |
|
"learning_rate": 2.795739644970414e-06, |
|
"loss": 0.4129, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 15.56, |
|
"learning_rate": 2.7910059171597633e-06, |
|
"loss": 0.454, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 15.61, |
|
"learning_rate": 2.786272189349112e-06, |
|
"loss": 0.4502, |
|
"step": 2670 |
|
}, |
|
{ |
|
"epoch": 15.67, |
|
"learning_rate": 2.7815384615384614e-06, |
|
"loss": 0.4414, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 15.73, |
|
"learning_rate": 2.7768047337278105e-06, |
|
"loss": 0.4323, |
|
"step": 2690 |
|
}, |
|
{ |
|
"epoch": 15.79, |
|
"learning_rate": 2.7720710059171595e-06, |
|
"loss": 0.4537, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 15.85, |
|
"learning_rate": 2.7673372781065085e-06, |
|
"loss": 0.4663, |
|
"step": 2710 |
|
}, |
|
{ |
|
"epoch": 15.91, |
|
"learning_rate": 2.762603550295858e-06, |
|
"loss": 0.4319, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 15.96, |
|
"learning_rate": 2.7578698224852066e-06, |
|
"loss": 0.4287, |
|
"step": 2730 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"eval_loss": 0.17714881896972656, |
|
"eval_runtime": 204.7866, |
|
"eval_samples_per_second": 5.943, |
|
"eval_steps_per_second": 0.747, |
|
"eval_wer": 0.09758468017709945, |
|
"step": 2736 |
|
}, |
|
{ |
|
"epoch": 16.02, |
|
"learning_rate": 2.753136094674556e-06, |
|
"loss": 0.4414, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 16.08, |
|
"learning_rate": 2.7484023668639056e-06, |
|
"loss": 0.4433, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 16.14, |
|
"learning_rate": 2.743668639053254e-06, |
|
"loss": 0.4565, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 16.2, |
|
"learning_rate": 2.7389349112426036e-06, |
|
"loss": 0.4257, |
|
"step": 2770 |
|
}, |
|
{ |
|
"epoch": 16.26, |
|
"learning_rate": 2.7342011834319527e-06, |
|
"loss": 0.4445, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 16.32, |
|
"learning_rate": 2.7294674556213017e-06, |
|
"loss": 0.4703, |
|
"step": 2790 |
|
}, |
|
{ |
|
"epoch": 16.37, |
|
"learning_rate": 2.7247337278106508e-06, |
|
"loss": 0.4377, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 16.43, |
|
"learning_rate": 2.7200000000000002e-06, |
|
"loss": 0.43, |
|
"step": 2810 |
|
}, |
|
{ |
|
"epoch": 16.49, |
|
"learning_rate": 2.715266272189349e-06, |
|
"loss": 0.4516, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 16.55, |
|
"learning_rate": 2.7105325443786983e-06, |
|
"loss": 0.4528, |
|
"step": 2830 |
|
}, |
|
{ |
|
"epoch": 16.61, |
|
"learning_rate": 2.7057988165680473e-06, |
|
"loss": 0.4725, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 16.67, |
|
"learning_rate": 2.7010650887573964e-06, |
|
"loss": 0.4528, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 16.72, |
|
"learning_rate": 2.6963313609467454e-06, |
|
"loss": 0.4428, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 16.78, |
|
"learning_rate": 2.6915976331360945e-06, |
|
"loss": 0.4427, |
|
"step": 2870 |
|
}, |
|
{ |
|
"epoch": 16.84, |
|
"learning_rate": 2.6868639053254435e-06, |
|
"loss": 0.463, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 16.9, |
|
"learning_rate": 2.682130177514793e-06, |
|
"loss": 0.4549, |
|
"step": 2890 |
|
}, |
|
{ |
|
"epoch": 16.96, |
|
"learning_rate": 2.6773964497041416e-06, |
|
"loss": 0.4417, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"eval_loss": 0.17799387872219086, |
|
"eval_runtime": 205.3444, |
|
"eval_samples_per_second": 5.927, |
|
"eval_steps_per_second": 0.745, |
|
"eval_wer": 0.09787264677297433, |
|
"step": 2907 |
|
}, |
|
{ |
|
"epoch": 17.02, |
|
"learning_rate": 2.672662721893491e-06, |
|
"loss": 0.4528, |
|
"step": 2910 |
|
}, |
|
{ |
|
"epoch": 17.08, |
|
"learning_rate": 2.66792899408284e-06, |
|
"loss": 0.4459, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 17.13, |
|
"learning_rate": 2.663195266272189e-06, |
|
"loss": 0.4407, |
|
"step": 2930 |
|
}, |
|
{ |
|
"epoch": 17.19, |
|
"learning_rate": 2.658461538461538e-06, |
|
"loss": 0.446, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 17.25, |
|
"learning_rate": 2.6537278106508876e-06, |
|
"loss": 0.4381, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 17.31, |
|
"learning_rate": 2.6489940828402362e-06, |
|
"loss": 0.4801, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 17.37, |
|
"learning_rate": 2.6442603550295857e-06, |
|
"loss": 0.4605, |
|
"step": 2970 |
|
}, |
|
{ |
|
"epoch": 17.43, |
|
"learning_rate": 2.6395266272189347e-06, |
|
"loss": 0.427, |
|
"step": 2980 |
|
}, |
|
{ |
|
"epoch": 17.49, |
|
"learning_rate": 2.6347928994082838e-06, |
|
"loss": 0.4448, |
|
"step": 2990 |
|
}, |
|
{ |
|
"epoch": 17.54, |
|
"learning_rate": 2.630059171597633e-06, |
|
"loss": 0.4421, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 17.6, |
|
"learning_rate": 2.6253254437869823e-06, |
|
"loss": 0.4398, |
|
"step": 3010 |
|
}, |
|
{ |
|
"epoch": 17.66, |
|
"learning_rate": 2.620591715976331e-06, |
|
"loss": 0.4476, |
|
"step": 3020 |
|
}, |
|
{ |
|
"epoch": 17.72, |
|
"learning_rate": 2.6158579881656804e-06, |
|
"loss": 0.4243, |
|
"step": 3030 |
|
}, |
|
{ |
|
"epoch": 17.78, |
|
"learning_rate": 2.61112426035503e-06, |
|
"loss": 0.4526, |
|
"step": 3040 |
|
}, |
|
{ |
|
"epoch": 17.84, |
|
"learning_rate": 2.6063905325443784e-06, |
|
"loss": 0.4538, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 17.89, |
|
"learning_rate": 2.601656804733728e-06, |
|
"loss": 0.4529, |
|
"step": 3060 |
|
}, |
|
{ |
|
"epoch": 17.95, |
|
"learning_rate": 2.596923076923077e-06, |
|
"loss": 0.4257, |
|
"step": 3070 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"eval_loss": 0.1761552393436432, |
|
"eval_runtime": 206.3338, |
|
"eval_samples_per_second": 5.898, |
|
"eval_steps_per_second": 0.742, |
|
"eval_wer": 0.0962888304956625, |
|
"step": 3078 |
|
}, |
|
{ |
|
"epoch": 18.01, |
|
"learning_rate": 2.592189349112426e-06, |
|
"loss": 0.4498, |
|
"step": 3080 |
|
}, |
|
{ |
|
"epoch": 18.07, |
|
"learning_rate": 2.587455621301775e-06, |
|
"loss": 0.4412, |
|
"step": 3090 |
|
}, |
|
{ |
|
"epoch": 18.13, |
|
"learning_rate": 2.5827218934911245e-06, |
|
"loss": 0.4535, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 18.19, |
|
"learning_rate": 2.577988165680473e-06, |
|
"loss": 0.437, |
|
"step": 3110 |
|
}, |
|
{ |
|
"epoch": 18.25, |
|
"learning_rate": 2.5732544378698226e-06, |
|
"loss": 0.4135, |
|
"step": 3120 |
|
}, |
|
{ |
|
"epoch": 18.3, |
|
"learning_rate": 2.5685207100591716e-06, |
|
"loss": 0.4681, |
|
"step": 3130 |
|
}, |
|
{ |
|
"epoch": 18.36, |
|
"learning_rate": 2.5637869822485207e-06, |
|
"loss": 0.4378, |
|
"step": 3140 |
|
}, |
|
{ |
|
"epoch": 18.42, |
|
"learning_rate": 2.5590532544378697e-06, |
|
"loss": 0.439, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 18.48, |
|
"learning_rate": 2.5543195266272187e-06, |
|
"loss": 0.4382, |
|
"step": 3160 |
|
}, |
|
{ |
|
"epoch": 18.54, |
|
"learning_rate": 2.5495857988165678e-06, |
|
"loss": 0.4548, |
|
"step": 3170 |
|
}, |
|
{ |
|
"epoch": 18.6, |
|
"learning_rate": 2.5448520710059172e-06, |
|
"loss": 0.4543, |
|
"step": 3180 |
|
}, |
|
{ |
|
"epoch": 18.65, |
|
"learning_rate": 2.540118343195266e-06, |
|
"loss": 0.4508, |
|
"step": 3190 |
|
}, |
|
{ |
|
"epoch": 18.71, |
|
"learning_rate": 2.5353846153846153e-06, |
|
"loss": 0.411, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 18.77, |
|
"learning_rate": 2.5306508875739644e-06, |
|
"loss": 0.4558, |
|
"step": 3210 |
|
}, |
|
{ |
|
"epoch": 18.83, |
|
"learning_rate": 2.5259171597633134e-06, |
|
"loss": 0.47, |
|
"step": 3220 |
|
}, |
|
{ |
|
"epoch": 18.89, |
|
"learning_rate": 2.5211834319526624e-06, |
|
"loss": 0.4527, |
|
"step": 3230 |
|
}, |
|
{ |
|
"epoch": 18.95, |
|
"learning_rate": 2.516449704142012e-06, |
|
"loss": 0.4588, |
|
"step": 3240 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"eval_loss": 0.17500481009483337, |
|
"eval_runtime": 205.4451, |
|
"eval_samples_per_second": 5.924, |
|
"eval_steps_per_second": 0.745, |
|
"eval_wer": 0.0957488931283971, |
|
"step": 3249 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 2.5117159763313605e-06, |
|
"loss": 0.4455, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 19.06, |
|
"learning_rate": 2.50698224852071e-06, |
|
"loss": 0.4635, |
|
"step": 3260 |
|
}, |
|
{ |
|
"epoch": 19.12, |
|
"learning_rate": 2.502248520710059e-06, |
|
"loss": 0.4497, |
|
"step": 3270 |
|
}, |
|
{ |
|
"epoch": 19.18, |
|
"learning_rate": 2.497514792899408e-06, |
|
"loss": 0.4457, |
|
"step": 3280 |
|
}, |
|
{ |
|
"epoch": 19.24, |
|
"learning_rate": 2.492781065088757e-06, |
|
"loss": 0.4345, |
|
"step": 3290 |
|
}, |
|
{ |
|
"epoch": 19.3, |
|
"learning_rate": 2.4880473372781066e-06, |
|
"loss": 0.4488, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 19.36, |
|
"learning_rate": 2.483313609467455e-06, |
|
"loss": 0.4548, |
|
"step": 3310 |
|
}, |
|
{ |
|
"epoch": 19.41, |
|
"learning_rate": 2.4785798816568046e-06, |
|
"loss": 0.4508, |
|
"step": 3320 |
|
}, |
|
{ |
|
"epoch": 19.47, |
|
"learning_rate": 2.473846153846154e-06, |
|
"loss": 0.4156, |
|
"step": 3330 |
|
}, |
|
{ |
|
"epoch": 19.53, |
|
"learning_rate": 2.4691124260355027e-06, |
|
"loss": 0.4488, |
|
"step": 3340 |
|
}, |
|
{ |
|
"epoch": 19.59, |
|
"learning_rate": 2.464378698224852e-06, |
|
"loss": 0.4492, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 19.65, |
|
"learning_rate": 2.4596449704142012e-06, |
|
"loss": 0.4405, |
|
"step": 3360 |
|
}, |
|
{ |
|
"epoch": 19.71, |
|
"learning_rate": 2.4549112426035503e-06, |
|
"loss": 0.4491, |
|
"step": 3370 |
|
}, |
|
{ |
|
"epoch": 19.77, |
|
"learning_rate": 2.4501775147928993e-06, |
|
"loss": 0.4388, |
|
"step": 3380 |
|
}, |
|
{ |
|
"epoch": 19.82, |
|
"learning_rate": 2.4454437869822488e-06, |
|
"loss": 0.4597, |
|
"step": 3390 |
|
}, |
|
{ |
|
"epoch": 19.88, |
|
"learning_rate": 2.4407100591715974e-06, |
|
"loss": 0.4217, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 19.94, |
|
"learning_rate": 2.435976331360947e-06, |
|
"loss": 0.4287, |
|
"step": 3410 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 2.4312426035502955e-06, |
|
"loss": 0.4439, |
|
"step": 3420 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"eval_loss": 0.17584607005119324, |
|
"eval_runtime": 205.1496, |
|
"eval_samples_per_second": 5.932, |
|
"eval_steps_per_second": 0.746, |
|
"eval_wer": 0.0968287678629279, |
|
"step": 3420 |
|
}, |
|
{ |
|
"epoch": 20.06, |
|
"learning_rate": 2.426508875739645e-06, |
|
"loss": 0.4561, |
|
"step": 3430 |
|
}, |
|
{ |
|
"epoch": 20.12, |
|
"learning_rate": 2.421775147928994e-06, |
|
"loss": 0.4528, |
|
"step": 3440 |
|
}, |
|
{ |
|
"epoch": 20.18, |
|
"learning_rate": 2.417041420118343e-06, |
|
"loss": 0.4404, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 20.23, |
|
"learning_rate": 2.412307692307692e-06, |
|
"loss": 0.4255, |
|
"step": 3460 |
|
}, |
|
{ |
|
"epoch": 20.29, |
|
"learning_rate": 2.4075739644970415e-06, |
|
"loss": 0.4492, |
|
"step": 3470 |
|
}, |
|
{ |
|
"epoch": 20.35, |
|
"learning_rate": 2.40284023668639e-06, |
|
"loss": 0.463, |
|
"step": 3480 |
|
}, |
|
{ |
|
"epoch": 20.41, |
|
"learning_rate": 2.3981065088757396e-06, |
|
"loss": 0.4309, |
|
"step": 3490 |
|
}, |
|
{ |
|
"epoch": 20.47, |
|
"learning_rate": 2.3933727810650886e-06, |
|
"loss": 0.4393, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 20.53, |
|
"learning_rate": 2.3886390532544377e-06, |
|
"loss": 0.4339, |
|
"step": 3510 |
|
}, |
|
{ |
|
"epoch": 20.58, |
|
"learning_rate": 2.3839053254437867e-06, |
|
"loss": 0.4713, |
|
"step": 3520 |
|
}, |
|
{ |
|
"epoch": 20.64, |
|
"learning_rate": 2.379171597633136e-06, |
|
"loss": 0.4424, |
|
"step": 3530 |
|
}, |
|
{ |
|
"epoch": 20.7, |
|
"learning_rate": 2.374437869822485e-06, |
|
"loss": 0.4328, |
|
"step": 3540 |
|
}, |
|
{ |
|
"epoch": 20.76, |
|
"learning_rate": 2.3697041420118343e-06, |
|
"loss": 0.4324, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 20.82, |
|
"learning_rate": 2.3649704142011833e-06, |
|
"loss": 0.4605, |
|
"step": 3560 |
|
}, |
|
{ |
|
"epoch": 20.88, |
|
"learning_rate": 2.3602366863905323e-06, |
|
"loss": 0.4392, |
|
"step": 3570 |
|
}, |
|
{ |
|
"epoch": 20.93, |
|
"learning_rate": 2.3555029585798814e-06, |
|
"loss": 0.4251, |
|
"step": 3580 |
|
}, |
|
{ |
|
"epoch": 20.99, |
|
"learning_rate": 2.350769230769231e-06, |
|
"loss": 0.4515, |
|
"step": 3590 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"eval_loss": 0.1781645119190216, |
|
"eval_runtime": 205.9109, |
|
"eval_samples_per_second": 5.91, |
|
"eval_steps_per_second": 0.743, |
|
"eval_wer": 0.0966487887405061, |
|
"step": 3591 |
|
}, |
|
{ |
|
"epoch": 21.05, |
|
"learning_rate": 2.3460355029585795e-06, |
|
"loss": 0.4745, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 21.11, |
|
"learning_rate": 2.341301775147929e-06, |
|
"loss": 0.4425, |
|
"step": 3610 |
|
}, |
|
{ |
|
"epoch": 21.17, |
|
"learning_rate": 2.3365680473372784e-06, |
|
"loss": 0.4351, |
|
"step": 3620 |
|
}, |
|
{ |
|
"epoch": 21.23, |
|
"learning_rate": 2.331834319526627e-06, |
|
"loss": 0.4288, |
|
"step": 3630 |
|
}, |
|
{ |
|
"epoch": 21.29, |
|
"learning_rate": 2.3271005917159765e-06, |
|
"loss": 0.4408, |
|
"step": 3640 |
|
}, |
|
{ |
|
"epoch": 21.34, |
|
"learning_rate": 2.3223668639053255e-06, |
|
"loss": 0.4549, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 21.4, |
|
"learning_rate": 2.3176331360946745e-06, |
|
"loss": 0.4277, |
|
"step": 3660 |
|
}, |
|
{ |
|
"epoch": 21.46, |
|
"learning_rate": 2.3128994082840236e-06, |
|
"loss": 0.4075, |
|
"step": 3670 |
|
}, |
|
{ |
|
"epoch": 21.52, |
|
"learning_rate": 2.3081656804733726e-06, |
|
"loss": 0.4463, |
|
"step": 3680 |
|
}, |
|
{ |
|
"epoch": 21.58, |
|
"learning_rate": 2.3034319526627217e-06, |
|
"loss": 0.4542, |
|
"step": 3690 |
|
}, |
|
{ |
|
"epoch": 21.64, |
|
"learning_rate": 2.298698224852071e-06, |
|
"loss": 0.4531, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 21.7, |
|
"learning_rate": 2.2939644970414197e-06, |
|
"loss": 0.4383, |
|
"step": 3710 |
|
}, |
|
{ |
|
"epoch": 21.75, |
|
"learning_rate": 2.289230769230769e-06, |
|
"loss": 0.4393, |
|
"step": 3720 |
|
}, |
|
{ |
|
"epoch": 21.81, |
|
"learning_rate": 2.2844970414201182e-06, |
|
"loss": 0.46, |
|
"step": 3730 |
|
}, |
|
{ |
|
"epoch": 21.87, |
|
"learning_rate": 2.2797633136094673e-06, |
|
"loss": 0.4389, |
|
"step": 3740 |
|
}, |
|
{ |
|
"epoch": 21.93, |
|
"learning_rate": 2.2750295857988163e-06, |
|
"loss": 0.4615, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 21.99, |
|
"learning_rate": 2.270295857988166e-06, |
|
"loss": 0.4311, |
|
"step": 3760 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"eval_loss": 0.1774301826953888, |
|
"eval_runtime": 206.2702, |
|
"eval_samples_per_second": 5.9, |
|
"eval_steps_per_second": 0.742, |
|
"eval_wer": 0.0975486843526151, |
|
"step": 3762 |
|
}, |
|
{ |
|
"epoch": 22.05, |
|
"learning_rate": 2.2655621301775144e-06, |
|
"loss": 0.4511, |
|
"step": 3770 |
|
}, |
|
{ |
|
"epoch": 22.11, |
|
"learning_rate": 2.260828402366864e-06, |
|
"loss": 0.471, |
|
"step": 3780 |
|
}, |
|
{ |
|
"epoch": 22.16, |
|
"learning_rate": 2.256094674556213e-06, |
|
"loss": 0.4512, |
|
"step": 3790 |
|
}, |
|
{ |
|
"epoch": 22.22, |
|
"learning_rate": 2.251360946745562e-06, |
|
"loss": 0.4258, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 22.28, |
|
"learning_rate": 2.246627218934911e-06, |
|
"loss": 0.4488, |
|
"step": 3810 |
|
}, |
|
{ |
|
"epoch": 22.34, |
|
"learning_rate": 2.2418934911242605e-06, |
|
"loss": 0.4539, |
|
"step": 3820 |
|
}, |
|
{ |
|
"epoch": 22.4, |
|
"learning_rate": 2.237159763313609e-06, |
|
"loss": 0.4365, |
|
"step": 3830 |
|
}, |
|
{ |
|
"epoch": 22.46, |
|
"learning_rate": 2.2324260355029585e-06, |
|
"loss": 0.4351, |
|
"step": 3840 |
|
}, |
|
{ |
|
"epoch": 22.51, |
|
"learning_rate": 2.2276923076923076e-06, |
|
"loss": 0.4356, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 22.57, |
|
"learning_rate": 2.2229585798816566e-06, |
|
"loss": 0.4441, |
|
"step": 3860 |
|
}, |
|
{ |
|
"epoch": 22.63, |
|
"learning_rate": 2.2182248520710057e-06, |
|
"loss": 0.4498, |
|
"step": 3870 |
|
}, |
|
{ |
|
"epoch": 22.69, |
|
"learning_rate": 2.213491124260355e-06, |
|
"loss": 0.4193, |
|
"step": 3880 |
|
}, |
|
{ |
|
"epoch": 22.75, |
|
"learning_rate": 2.2087573964497037e-06, |
|
"loss": 0.448, |
|
"step": 3890 |
|
}, |
|
{ |
|
"epoch": 22.81, |
|
"learning_rate": 2.204023668639053e-06, |
|
"loss": 0.4534, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 22.86, |
|
"learning_rate": 2.1992899408284027e-06, |
|
"loss": 0.4428, |
|
"step": 3910 |
|
}, |
|
{ |
|
"epoch": 22.92, |
|
"learning_rate": 2.1945562130177513e-06, |
|
"loss": 0.4266, |
|
"step": 3920 |
|
}, |
|
{ |
|
"epoch": 22.98, |
|
"learning_rate": 2.1898224852071007e-06, |
|
"loss": 0.403, |
|
"step": 3930 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"eval_loss": 0.17578263580799103, |
|
"eval_runtime": 205.9625, |
|
"eval_samples_per_second": 5.909, |
|
"eval_steps_per_second": 0.743, |
|
"eval_wer": 0.09632482632014687, |
|
"step": 3933 |
|
}, |
|
{ |
|
"epoch": 23.04, |
|
"learning_rate": 2.1850887573964498e-06, |
|
"loss": 0.4626, |
|
"step": 3940 |
|
}, |
|
{ |
|
"epoch": 23.1, |
|
"learning_rate": 2.180355029585799e-06, |
|
"loss": 0.455, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 23.16, |
|
"learning_rate": 2.175621301775148e-06, |
|
"loss": 0.4376, |
|
"step": 3960 |
|
}, |
|
{ |
|
"epoch": 23.22, |
|
"learning_rate": 2.170887573964497e-06, |
|
"loss": 0.4254, |
|
"step": 3970 |
|
}, |
|
{ |
|
"epoch": 23.27, |
|
"learning_rate": 2.166153846153846e-06, |
|
"loss": 0.4395, |
|
"step": 3980 |
|
}, |
|
{ |
|
"epoch": 23.33, |
|
"learning_rate": 2.1614201183431954e-06, |
|
"loss": 0.4631, |
|
"step": 3990 |
|
}, |
|
{ |
|
"epoch": 23.39, |
|
"learning_rate": 2.156686390532544e-06, |
|
"loss": 0.4473, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 23.45, |
|
"learning_rate": 2.1519526627218935e-06, |
|
"loss": 0.4283, |
|
"step": 4010 |
|
}, |
|
{ |
|
"epoch": 23.51, |
|
"learning_rate": 2.1472189349112425e-06, |
|
"loss": 0.461, |
|
"step": 4020 |
|
}, |
|
{ |
|
"epoch": 23.57, |
|
"learning_rate": 2.1424852071005916e-06, |
|
"loss": 0.4612, |
|
"step": 4030 |
|
}, |
|
{ |
|
"epoch": 23.63, |
|
"learning_rate": 2.1377514792899406e-06, |
|
"loss": 0.4203, |
|
"step": 4040 |
|
}, |
|
{ |
|
"epoch": 23.68, |
|
"learning_rate": 2.13301775147929e-06, |
|
"loss": 0.4286, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 23.74, |
|
"learning_rate": 2.1282840236686387e-06, |
|
"loss": 0.4338, |
|
"step": 4060 |
|
}, |
|
{ |
|
"epoch": 23.8, |
|
"learning_rate": 2.123550295857988e-06, |
|
"loss": 0.4533, |
|
"step": 4070 |
|
}, |
|
{ |
|
"epoch": 23.86, |
|
"learning_rate": 2.118816568047337e-06, |
|
"loss": 0.4448, |
|
"step": 4080 |
|
}, |
|
{ |
|
"epoch": 23.92, |
|
"learning_rate": 2.1140828402366862e-06, |
|
"loss": 0.4291, |
|
"step": 4090 |
|
}, |
|
{ |
|
"epoch": 23.98, |
|
"learning_rate": 2.1093491124260353e-06, |
|
"loss": 0.4168, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 24.0, |
|
"eval_loss": 0.17746154963970184, |
|
"eval_runtime": 205.6593, |
|
"eval_samples_per_second": 5.918, |
|
"eval_steps_per_second": 0.744, |
|
"eval_wer": 0.09722472193225586, |
|
"step": 4104 |
|
}, |
|
{ |
|
"epoch": 24.04, |
|
"learning_rate": 2.1046153846153847e-06, |
|
"loss": 0.4407, |
|
"step": 4110 |
|
}, |
|
{ |
|
"epoch": 24.09, |
|
"learning_rate": 2.0998816568047333e-06, |
|
"loss": 0.4677, |
|
"step": 4120 |
|
}, |
|
{ |
|
"epoch": 24.15, |
|
"learning_rate": 2.095147928994083e-06, |
|
"loss": 0.4371, |
|
"step": 4130 |
|
}, |
|
{ |
|
"epoch": 24.21, |
|
"learning_rate": 2.090414201183432e-06, |
|
"loss": 0.4394, |
|
"step": 4140 |
|
}, |
|
{ |
|
"epoch": 24.27, |
|
"learning_rate": 2.085680473372781e-06, |
|
"loss": 0.4446, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 24.33, |
|
"learning_rate": 2.08094674556213e-06, |
|
"loss": 0.4708, |
|
"step": 4160 |
|
}, |
|
{ |
|
"epoch": 24.39, |
|
"learning_rate": 2.0762130177514794e-06, |
|
"loss": 0.4261, |
|
"step": 4170 |
|
}, |
|
{ |
|
"epoch": 24.44, |
|
"learning_rate": 2.071479289940828e-06, |
|
"loss": 0.4278, |
|
"step": 4180 |
|
}, |
|
{ |
|
"epoch": 24.5, |
|
"learning_rate": 2.0667455621301775e-06, |
|
"loss": 0.4344, |
|
"step": 4190 |
|
}, |
|
{ |
|
"epoch": 24.56, |
|
"learning_rate": 2.062011834319527e-06, |
|
"loss": 0.448, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 24.62, |
|
"learning_rate": 2.0572781065088756e-06, |
|
"loss": 0.4592, |
|
"step": 4210 |
|
}, |
|
{ |
|
"epoch": 24.68, |
|
"learning_rate": 2.052544378698225e-06, |
|
"loss": 0.4337, |
|
"step": 4220 |
|
}, |
|
{ |
|
"epoch": 24.74, |
|
"learning_rate": 2.0478106508875736e-06, |
|
"loss": 0.4335, |
|
"step": 4230 |
|
}, |
|
{ |
|
"epoch": 24.79, |
|
"learning_rate": 2.043076923076923e-06, |
|
"loss": 0.4486, |
|
"step": 4240 |
|
}, |
|
{ |
|
"epoch": 24.85, |
|
"learning_rate": 2.038343195266272e-06, |
|
"loss": 0.4542, |
|
"step": 4250 |
|
}, |
|
{ |
|
"epoch": 24.91, |
|
"learning_rate": 2.033609467455621e-06, |
|
"loss": 0.416, |
|
"step": 4260 |
|
}, |
|
{ |
|
"epoch": 24.97, |
|
"learning_rate": 2.0288757396449702e-06, |
|
"loss": 0.425, |
|
"step": 4270 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"eval_loss": 0.17422078549861908, |
|
"eval_runtime": 206.7093, |
|
"eval_samples_per_second": 5.887, |
|
"eval_steps_per_second": 0.74, |
|
"eval_wer": 0.09524495158561606, |
|
"step": 4275 |
|
}, |
|
{ |
|
"epoch": 25.03, |
|
"learning_rate": 2.0241420118343197e-06, |
|
"loss": 0.4449, |
|
"step": 4280 |
|
}, |
|
{ |
|
"epoch": 25.09, |
|
"learning_rate": 2.0194082840236683e-06, |
|
"loss": 0.4636, |
|
"step": 4290 |
|
}, |
|
{ |
|
"epoch": 25.15, |
|
"learning_rate": 2.0146745562130178e-06, |
|
"loss": 0.445, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 25.2, |
|
"learning_rate": 2.009940828402367e-06, |
|
"loss": 0.4248, |
|
"step": 4310 |
|
}, |
|
{ |
|
"epoch": 25.26, |
|
"learning_rate": 2.005207100591716e-06, |
|
"loss": 0.4325, |
|
"step": 4320 |
|
}, |
|
{ |
|
"epoch": 25.32, |
|
"learning_rate": 2.000473372781065e-06, |
|
"loss": 0.4469, |
|
"step": 4330 |
|
}, |
|
{ |
|
"epoch": 25.38, |
|
"learning_rate": 1.995739644970414e-06, |
|
"loss": 0.4293, |
|
"step": 4340 |
|
}, |
|
{ |
|
"epoch": 25.44, |
|
"learning_rate": 1.9910059171597634e-06, |
|
"loss": 0.4422, |
|
"step": 4350 |
|
}, |
|
{ |
|
"epoch": 25.5, |
|
"learning_rate": 1.9862721893491124e-06, |
|
"loss": 0.4331, |
|
"step": 4360 |
|
}, |
|
{ |
|
"epoch": 25.56, |
|
"learning_rate": 1.9815384615384615e-06, |
|
"loss": 0.4546, |
|
"step": 4370 |
|
}, |
|
{ |
|
"epoch": 25.61, |
|
"learning_rate": 1.9768047337278105e-06, |
|
"loss": 0.4582, |
|
"step": 4380 |
|
}, |
|
{ |
|
"epoch": 25.67, |
|
"learning_rate": 1.9720710059171595e-06, |
|
"loss": 0.4206, |
|
"step": 4390 |
|
}, |
|
{ |
|
"epoch": 25.73, |
|
"learning_rate": 1.9673372781065086e-06, |
|
"loss": 0.4286, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 25.79, |
|
"learning_rate": 1.962603550295858e-06, |
|
"loss": 0.4306, |
|
"step": 4410 |
|
}, |
|
{ |
|
"epoch": 25.85, |
|
"learning_rate": 1.957869822485207e-06, |
|
"loss": 0.4581, |
|
"step": 4420 |
|
}, |
|
{ |
|
"epoch": 25.91, |
|
"learning_rate": 1.953136094674556e-06, |
|
"loss": 0.4458, |
|
"step": 4430 |
|
}, |
|
{ |
|
"epoch": 25.96, |
|
"learning_rate": 1.948402366863905e-06, |
|
"loss": 0.4493, |
|
"step": 4440 |
|
}, |
|
{ |
|
"epoch": 26.0, |
|
"eval_loss": 0.17492450773715973, |
|
"eval_runtime": 205.6238, |
|
"eval_samples_per_second": 5.919, |
|
"eval_steps_per_second": 0.744, |
|
"eval_wer": 0.09625283467117815, |
|
"step": 4446 |
|
}, |
|
{ |
|
"epoch": 26.02, |
|
"learning_rate": 1.943668639053254e-06, |
|
"loss": 0.4298, |
|
"step": 4450 |
|
}, |
|
{ |
|
"epoch": 26.08, |
|
"learning_rate": 1.9389349112426032e-06, |
|
"loss": 0.4584, |
|
"step": 4460 |
|
}, |
|
{ |
|
"epoch": 26.14, |
|
"learning_rate": 1.9342011834319523e-06, |
|
"loss": 0.4289, |
|
"step": 4470 |
|
}, |
|
{ |
|
"epoch": 26.2, |
|
"learning_rate": 1.9294674556213017e-06, |
|
"loss": 0.4355, |
|
"step": 4480 |
|
}, |
|
{ |
|
"epoch": 26.26, |
|
"learning_rate": 1.924733727810651e-06, |
|
"loss": 0.4267, |
|
"step": 4490 |
|
}, |
|
{ |
|
"epoch": 26.32, |
|
"learning_rate": 1.92e-06, |
|
"loss": 0.4648, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 26.37, |
|
"learning_rate": 1.9152662721893493e-06, |
|
"loss": 0.4543, |
|
"step": 4510 |
|
}, |
|
{ |
|
"epoch": 26.43, |
|
"learning_rate": 1.9105325443786983e-06, |
|
"loss": 0.4511, |
|
"step": 4520 |
|
}, |
|
{ |
|
"epoch": 26.49, |
|
"learning_rate": 1.9057988165680472e-06, |
|
"loss": 0.4229, |
|
"step": 4530 |
|
}, |
|
{ |
|
"epoch": 26.55, |
|
"learning_rate": 1.9010650887573964e-06, |
|
"loss": 0.4531, |
|
"step": 4540 |
|
}, |
|
{ |
|
"epoch": 26.61, |
|
"learning_rate": 1.8963313609467455e-06, |
|
"loss": 0.4343, |
|
"step": 4550 |
|
}, |
|
{ |
|
"epoch": 26.67, |
|
"learning_rate": 1.8915976331360945e-06, |
|
"loss": 0.4156, |
|
"step": 4560 |
|
}, |
|
{ |
|
"epoch": 26.72, |
|
"learning_rate": 1.8868639053254435e-06, |
|
"loss": 0.4142, |
|
"step": 4570 |
|
}, |
|
{ |
|
"epoch": 26.78, |
|
"learning_rate": 1.8821301775147928e-06, |
|
"loss": 0.4399, |
|
"step": 4580 |
|
}, |
|
{ |
|
"epoch": 26.84, |
|
"learning_rate": 1.8773964497041418e-06, |
|
"loss": 0.4516, |
|
"step": 4590 |
|
}, |
|
{ |
|
"epoch": 26.9, |
|
"learning_rate": 1.8726627218934909e-06, |
|
"loss": 0.442, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 26.96, |
|
"learning_rate": 1.8679289940828401e-06, |
|
"loss": 0.4232, |
|
"step": 4610 |
|
}, |
|
{ |
|
"epoch": 27.0, |
|
"eval_loss": 0.17490798234939575, |
|
"eval_runtime": 207.2125, |
|
"eval_samples_per_second": 5.873, |
|
"eval_steps_per_second": 0.738, |
|
"eval_wer": 0.09661279291602175, |
|
"step": 4617 |
|
}, |
|
{ |
|
"epoch": 27.02, |
|
"learning_rate": 1.8631952662721892e-06, |
|
"loss": 0.4358, |
|
"step": 4620 |
|
}, |
|
{ |
|
"epoch": 27.08, |
|
"learning_rate": 1.8584615384615384e-06, |
|
"loss": 0.445, |
|
"step": 4630 |
|
}, |
|
{ |
|
"epoch": 27.13, |
|
"learning_rate": 1.8537278106508877e-06, |
|
"loss": 0.4409, |
|
"step": 4640 |
|
}, |
|
{ |
|
"epoch": 27.19, |
|
"learning_rate": 1.8489940828402367e-06, |
|
"loss": 0.4308, |
|
"step": 4650 |
|
}, |
|
{ |
|
"epoch": 27.25, |
|
"learning_rate": 1.8442603550295857e-06, |
|
"loss": 0.4393, |
|
"step": 4660 |
|
}, |
|
{ |
|
"epoch": 27.31, |
|
"learning_rate": 1.839526627218935e-06, |
|
"loss": 0.4455, |
|
"step": 4670 |
|
}, |
|
{ |
|
"epoch": 27.37, |
|
"learning_rate": 1.834792899408284e-06, |
|
"loss": 0.467, |
|
"step": 4680 |
|
}, |
|
{ |
|
"epoch": 27.43, |
|
"learning_rate": 1.830059171597633e-06, |
|
"loss": 0.4352, |
|
"step": 4690 |
|
}, |
|
{ |
|
"epoch": 27.49, |
|
"learning_rate": 1.8253254437869821e-06, |
|
"loss": 0.4312, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 27.54, |
|
"learning_rate": 1.8205917159763314e-06, |
|
"loss": 0.4411, |
|
"step": 4710 |
|
}, |
|
{ |
|
"epoch": 27.6, |
|
"learning_rate": 1.8158579881656804e-06, |
|
"loss": 0.4562, |
|
"step": 4720 |
|
}, |
|
{ |
|
"epoch": 27.66, |
|
"learning_rate": 1.8111242603550294e-06, |
|
"loss": 0.4298, |
|
"step": 4730 |
|
}, |
|
{ |
|
"epoch": 27.72, |
|
"learning_rate": 1.8063905325443787e-06, |
|
"loss": 0.42, |
|
"step": 4740 |
|
}, |
|
{ |
|
"epoch": 27.78, |
|
"learning_rate": 1.8016568047337277e-06, |
|
"loss": 0.4477, |
|
"step": 4750 |
|
}, |
|
{ |
|
"epoch": 27.84, |
|
"learning_rate": 1.7969230769230768e-06, |
|
"loss": 0.4549, |
|
"step": 4760 |
|
}, |
|
{ |
|
"epoch": 27.89, |
|
"learning_rate": 1.792189349112426e-06, |
|
"loss": 0.4483, |
|
"step": 4770 |
|
}, |
|
{ |
|
"epoch": 27.95, |
|
"learning_rate": 1.787455621301775e-06, |
|
"loss": 0.4331, |
|
"step": 4780 |
|
}, |
|
{ |
|
"epoch": 28.0, |
|
"eval_loss": 0.17543496191501617, |
|
"eval_runtime": 207.7338, |
|
"eval_samples_per_second": 5.858, |
|
"eval_steps_per_second": 0.737, |
|
"eval_wer": 0.09643281379359994, |
|
"step": 4788 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 1.782721893491124e-06, |
|
"loss": 0.4393, |
|
"step": 4790 |
|
}, |
|
{ |
|
"epoch": 28.07, |
|
"learning_rate": 1.7779881656804734e-06, |
|
"loss": 0.4537, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 28.13, |
|
"learning_rate": 1.7732544378698224e-06, |
|
"loss": 0.4488, |
|
"step": 4810 |
|
}, |
|
{ |
|
"epoch": 28.19, |
|
"learning_rate": 1.7685207100591714e-06, |
|
"loss": 0.4487, |
|
"step": 4820 |
|
}, |
|
{ |
|
"epoch": 28.25, |
|
"learning_rate": 1.7637869822485207e-06, |
|
"loss": 0.4238, |
|
"step": 4830 |
|
}, |
|
{ |
|
"epoch": 28.3, |
|
"learning_rate": 1.7590532544378697e-06, |
|
"loss": 0.4544, |
|
"step": 4840 |
|
}, |
|
{ |
|
"epoch": 28.36, |
|
"learning_rate": 1.7543195266272188e-06, |
|
"loss": 0.4604, |
|
"step": 4850 |
|
}, |
|
{ |
|
"epoch": 28.42, |
|
"learning_rate": 1.7495857988165678e-06, |
|
"loss": 0.4358, |
|
"step": 4860 |
|
}, |
|
{ |
|
"epoch": 28.48, |
|
"learning_rate": 1.744852071005917e-06, |
|
"loss": 0.4211, |
|
"step": 4870 |
|
}, |
|
{ |
|
"epoch": 28.54, |
|
"learning_rate": 1.740118343195266e-06, |
|
"loss": 0.4364, |
|
"step": 4880 |
|
}, |
|
{ |
|
"epoch": 28.6, |
|
"learning_rate": 1.7353846153846151e-06, |
|
"loss": 0.4588, |
|
"step": 4890 |
|
}, |
|
{ |
|
"epoch": 28.65, |
|
"learning_rate": 1.7306508875739644e-06, |
|
"loss": 0.4304, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 28.71, |
|
"learning_rate": 1.7259171597633134e-06, |
|
"loss": 0.4328, |
|
"step": 4910 |
|
}, |
|
{ |
|
"epoch": 28.77, |
|
"learning_rate": 1.7211834319526627e-06, |
|
"loss": 0.4487, |
|
"step": 4920 |
|
}, |
|
{ |
|
"epoch": 28.83, |
|
"learning_rate": 1.716449704142012e-06, |
|
"loss": 0.4552, |
|
"step": 4930 |
|
}, |
|
{ |
|
"epoch": 28.89, |
|
"learning_rate": 1.711715976331361e-06, |
|
"loss": 0.4444, |
|
"step": 4940 |
|
}, |
|
{ |
|
"epoch": 28.95, |
|
"learning_rate": 1.70698224852071e-06, |
|
"loss": 0.4306, |
|
"step": 4950 |
|
}, |
|
{ |
|
"epoch": 29.0, |
|
"eval_loss": 0.17555944621562958, |
|
"eval_runtime": 206.7332, |
|
"eval_samples_per_second": 5.887, |
|
"eval_steps_per_second": 0.74, |
|
"eval_wer": 0.09672078038947482, |
|
"step": 4959 |
|
}, |
|
{ |
|
"epoch": 29.01, |
|
"learning_rate": 1.7022485207100593e-06, |
|
"loss": 0.4551, |
|
"step": 4960 |
|
}, |
|
{ |
|
"epoch": 29.06, |
|
"learning_rate": 1.6975147928994083e-06, |
|
"loss": 0.4623, |
|
"step": 4970 |
|
}, |
|
{ |
|
"epoch": 29.12, |
|
"learning_rate": 1.6927810650887573e-06, |
|
"loss": 0.4508, |
|
"step": 4980 |
|
}, |
|
{ |
|
"epoch": 29.18, |
|
"learning_rate": 1.6880473372781064e-06, |
|
"loss": 0.4394, |
|
"step": 4990 |
|
}, |
|
{ |
|
"epoch": 29.24, |
|
"learning_rate": 1.6833136094674556e-06, |
|
"loss": 0.4328, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 29.3, |
|
"learning_rate": 1.6785798816568047e-06, |
|
"loss": 0.4438, |
|
"step": 5010 |
|
}, |
|
{ |
|
"epoch": 29.36, |
|
"learning_rate": 1.6743195266272187e-06, |
|
"loss": 0.4503, |
|
"step": 5020 |
|
}, |
|
{ |
|
"epoch": 29.41, |
|
"learning_rate": 1.669585798816568e-06, |
|
"loss": 0.4309, |
|
"step": 5030 |
|
}, |
|
{ |
|
"epoch": 29.47, |
|
"learning_rate": 1.664852071005917e-06, |
|
"loss": 0.4241, |
|
"step": 5040 |
|
}, |
|
{ |
|
"epoch": 29.53, |
|
"learning_rate": 1.660118343195266e-06, |
|
"loss": 0.4551, |
|
"step": 5050 |
|
}, |
|
{ |
|
"epoch": 29.59, |
|
"learning_rate": 1.6553846153846155e-06, |
|
"loss": 0.4475, |
|
"step": 5060 |
|
}, |
|
{ |
|
"epoch": 29.65, |
|
"learning_rate": 1.6506508875739645e-06, |
|
"loss": 0.4356, |
|
"step": 5070 |
|
}, |
|
{ |
|
"epoch": 29.71, |
|
"learning_rate": 1.6459171597633136e-06, |
|
"loss": 0.4254, |
|
"step": 5080 |
|
}, |
|
{ |
|
"epoch": 29.77, |
|
"learning_rate": 1.6411834319526628e-06, |
|
"loss": 0.456, |
|
"step": 5090 |
|
}, |
|
{ |
|
"epoch": 29.82, |
|
"learning_rate": 1.6364497041420119e-06, |
|
"loss": 0.4553, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 29.88, |
|
"learning_rate": 1.6317159763313609e-06, |
|
"loss": 0.438, |
|
"step": 5110 |
|
}, |
|
{ |
|
"epoch": 29.94, |
|
"learning_rate": 1.6269822485207101e-06, |
|
"loss": 0.4394, |
|
"step": 5120 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 1.6222485207100592e-06, |
|
"loss": 0.4261, |
|
"step": 5130 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"eval_loss": 0.17526455223560333, |
|
"eval_runtime": 206.7678, |
|
"eval_samples_per_second": 5.886, |
|
"eval_steps_per_second": 0.74, |
|
"eval_wer": 0.09693675533638098, |
|
"step": 5130 |
|
}, |
|
{ |
|
"epoch": 30.06, |
|
"learning_rate": 1.6175147928994082e-06, |
|
"loss": 0.4866, |
|
"step": 5140 |
|
}, |
|
{ |
|
"epoch": 30.12, |
|
"learning_rate": 1.6127810650887573e-06, |
|
"loss": 0.4542, |
|
"step": 5150 |
|
}, |
|
{ |
|
"epoch": 30.18, |
|
"learning_rate": 1.6080473372781065e-06, |
|
"loss": 0.4354, |
|
"step": 5160 |
|
}, |
|
{ |
|
"epoch": 30.23, |
|
"learning_rate": 1.6033136094674556e-06, |
|
"loss": 0.4254, |
|
"step": 5170 |
|
}, |
|
{ |
|
"epoch": 30.29, |
|
"learning_rate": 1.5985798816568046e-06, |
|
"loss": 0.4404, |
|
"step": 5180 |
|
}, |
|
{ |
|
"epoch": 30.35, |
|
"learning_rate": 1.5938461538461538e-06, |
|
"loss": 0.4453, |
|
"step": 5190 |
|
}, |
|
{ |
|
"epoch": 30.41, |
|
"learning_rate": 1.5891124260355029e-06, |
|
"loss": 0.4226, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 30.47, |
|
"learning_rate": 1.584378698224852e-06, |
|
"loss": 0.4292, |
|
"step": 5210 |
|
}, |
|
{ |
|
"epoch": 30.53, |
|
"learning_rate": 1.5796449704142012e-06, |
|
"loss": 0.4399, |
|
"step": 5220 |
|
}, |
|
{ |
|
"epoch": 30.58, |
|
"learning_rate": 1.5749112426035502e-06, |
|
"loss": 0.4508, |
|
"step": 5230 |
|
}, |
|
{ |
|
"epoch": 30.64, |
|
"learning_rate": 1.5701775147928993e-06, |
|
"loss": 0.4463, |
|
"step": 5240 |
|
}, |
|
{ |
|
"epoch": 30.7, |
|
"learning_rate": 1.5654437869822485e-06, |
|
"loss": 0.4195, |
|
"step": 5250 |
|
}, |
|
{ |
|
"epoch": 30.76, |
|
"learning_rate": 1.5607100591715976e-06, |
|
"loss": 0.4443, |
|
"step": 5260 |
|
}, |
|
{ |
|
"epoch": 30.82, |
|
"learning_rate": 1.5559763313609466e-06, |
|
"loss": 0.4596, |
|
"step": 5270 |
|
}, |
|
{ |
|
"epoch": 30.88, |
|
"learning_rate": 1.5512426035502956e-06, |
|
"loss": 0.4416, |
|
"step": 5280 |
|
}, |
|
{ |
|
"epoch": 30.93, |
|
"learning_rate": 1.5465088757396449e-06, |
|
"loss": 0.4291, |
|
"step": 5290 |
|
}, |
|
{ |
|
"epoch": 30.99, |
|
"learning_rate": 1.541775147928994e-06, |
|
"loss": 0.4284, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 31.0, |
|
"eval_loss": 0.17487050592899323, |
|
"eval_runtime": 207.7475, |
|
"eval_samples_per_second": 5.858, |
|
"eval_steps_per_second": 0.736, |
|
"eval_wer": 0.09578488895288147, |
|
"step": 5301 |
|
}, |
|
{ |
|
"epoch": 31.05, |
|
"learning_rate": 1.537041420118343e-06, |
|
"loss": 0.4519, |
|
"step": 5310 |
|
}, |
|
{ |
|
"epoch": 31.11, |
|
"learning_rate": 1.5323076923076922e-06, |
|
"loss": 0.4588, |
|
"step": 5320 |
|
}, |
|
{ |
|
"epoch": 31.17, |
|
"learning_rate": 1.5275739644970413e-06, |
|
"loss": 0.4403, |
|
"step": 5330 |
|
}, |
|
{ |
|
"epoch": 31.23, |
|
"learning_rate": 1.5228402366863903e-06, |
|
"loss": 0.4262, |
|
"step": 5340 |
|
}, |
|
{ |
|
"epoch": 31.29, |
|
"learning_rate": 1.5181065088757398e-06, |
|
"loss": 0.4248, |
|
"step": 5350 |
|
}, |
|
{ |
|
"epoch": 31.34, |
|
"learning_rate": 1.5133727810650888e-06, |
|
"loss": 0.4617, |
|
"step": 5360 |
|
}, |
|
{ |
|
"epoch": 31.4, |
|
"learning_rate": 1.5086390532544378e-06, |
|
"loss": 0.4535, |
|
"step": 5370 |
|
}, |
|
{ |
|
"epoch": 31.46, |
|
"learning_rate": 1.503905325443787e-06, |
|
"loss": 0.4322, |
|
"step": 5380 |
|
}, |
|
{ |
|
"epoch": 31.52, |
|
"learning_rate": 1.4991715976331361e-06, |
|
"loss": 0.4331, |
|
"step": 5390 |
|
}, |
|
{ |
|
"epoch": 31.58, |
|
"learning_rate": 1.4944378698224852e-06, |
|
"loss": 0.4426, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 31.64, |
|
"learning_rate": 1.4897041420118342e-06, |
|
"loss": 0.4223, |
|
"step": 5410 |
|
}, |
|
{ |
|
"epoch": 31.7, |
|
"learning_rate": 1.4849704142011835e-06, |
|
"loss": 0.4369, |
|
"step": 5420 |
|
}, |
|
{ |
|
"epoch": 31.75, |
|
"learning_rate": 1.4802366863905325e-06, |
|
"loss": 0.4442, |
|
"step": 5430 |
|
}, |
|
{ |
|
"epoch": 31.81, |
|
"learning_rate": 1.4755029585798815e-06, |
|
"loss": 0.4558, |
|
"step": 5440 |
|
}, |
|
{ |
|
"epoch": 31.87, |
|
"learning_rate": 1.4707692307692308e-06, |
|
"loss": 0.4527, |
|
"step": 5450 |
|
}, |
|
{ |
|
"epoch": 31.93, |
|
"learning_rate": 1.4660355029585798e-06, |
|
"loss": 0.4171, |
|
"step": 5460 |
|
}, |
|
{ |
|
"epoch": 31.99, |
|
"learning_rate": 1.4613017751479289e-06, |
|
"loss": 0.4322, |
|
"step": 5470 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"eval_loss": 0.17483986914157867, |
|
"eval_runtime": 207.1484, |
|
"eval_samples_per_second": 5.875, |
|
"eval_steps_per_second": 0.739, |
|
"eval_wer": 0.09520895576113171, |
|
"step": 5472 |
|
}, |
|
{ |
|
"epoch": 32.05, |
|
"learning_rate": 1.4565680473372781e-06, |
|
"loss": 0.4596, |
|
"step": 5480 |
|
}, |
|
{ |
|
"epoch": 32.11, |
|
"learning_rate": 1.4518343195266272e-06, |
|
"loss": 0.4628, |
|
"step": 5490 |
|
}, |
|
{ |
|
"epoch": 32.16, |
|
"learning_rate": 1.4471005917159762e-06, |
|
"loss": 0.4325, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 32.22, |
|
"learning_rate": 1.4423668639053255e-06, |
|
"loss": 0.4233, |
|
"step": 5510 |
|
}, |
|
{ |
|
"epoch": 32.28, |
|
"learning_rate": 1.4376331360946745e-06, |
|
"loss": 0.4335, |
|
"step": 5520 |
|
}, |
|
{ |
|
"epoch": 32.34, |
|
"learning_rate": 1.4328994082840235e-06, |
|
"loss": 0.4571, |
|
"step": 5530 |
|
}, |
|
{ |
|
"epoch": 32.4, |
|
"learning_rate": 1.4281656804733728e-06, |
|
"loss": 0.45, |
|
"step": 5540 |
|
}, |
|
{ |
|
"epoch": 32.46, |
|
"learning_rate": 1.4234319526627218e-06, |
|
"loss": 0.4182, |
|
"step": 5550 |
|
}, |
|
{ |
|
"epoch": 32.51, |
|
"learning_rate": 1.4186982248520709e-06, |
|
"loss": 0.4339, |
|
"step": 5560 |
|
}, |
|
{ |
|
"epoch": 32.57, |
|
"learning_rate": 1.41396449704142e-06, |
|
"loss": 0.4619, |
|
"step": 5570 |
|
}, |
|
{ |
|
"epoch": 32.63, |
|
"learning_rate": 1.4092307692307692e-06, |
|
"loss": 0.4327, |
|
"step": 5580 |
|
}, |
|
{ |
|
"epoch": 32.69, |
|
"learning_rate": 1.4044970414201182e-06, |
|
"loss": 0.4434, |
|
"step": 5590 |
|
}, |
|
{ |
|
"epoch": 32.75, |
|
"learning_rate": 1.3997633136094672e-06, |
|
"loss": 0.4402, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 32.81, |
|
"learning_rate": 1.3950295857988165e-06, |
|
"loss": 0.447, |
|
"step": 5610 |
|
}, |
|
{ |
|
"epoch": 32.86, |
|
"learning_rate": 1.3902958579881655e-06, |
|
"loss": 0.4336, |
|
"step": 5620 |
|
}, |
|
{ |
|
"epoch": 32.92, |
|
"learning_rate": 1.3855621301775146e-06, |
|
"loss": 0.4464, |
|
"step": 5630 |
|
}, |
|
{ |
|
"epoch": 32.98, |
|
"learning_rate": 1.380828402366864e-06, |
|
"loss": 0.4225, |
|
"step": 5640 |
|
}, |
|
{ |
|
"epoch": 33.0, |
|
"eval_loss": 0.1746746152639389, |
|
"eval_runtime": 206.6326, |
|
"eval_samples_per_second": 5.89, |
|
"eval_steps_per_second": 0.74, |
|
"eval_wer": 0.09520895576113171, |
|
"step": 5643 |
|
}, |
|
{ |
|
"epoch": 33.04, |
|
"learning_rate": 1.376094674556213e-06, |
|
"loss": 0.4305, |
|
"step": 5650 |
|
}, |
|
{ |
|
"epoch": 33.1, |
|
"learning_rate": 1.3713609467455621e-06, |
|
"loss": 0.451, |
|
"step": 5660 |
|
}, |
|
{ |
|
"epoch": 33.16, |
|
"learning_rate": 1.3666272189349114e-06, |
|
"loss": 0.4399, |
|
"step": 5670 |
|
}, |
|
{ |
|
"epoch": 33.22, |
|
"learning_rate": 1.3618934911242604e-06, |
|
"loss": 0.4424, |
|
"step": 5680 |
|
}, |
|
{ |
|
"epoch": 33.27, |
|
"learning_rate": 1.3571597633136094e-06, |
|
"loss": 0.4348, |
|
"step": 5690 |
|
}, |
|
{ |
|
"epoch": 33.33, |
|
"learning_rate": 1.3524260355029585e-06, |
|
"loss": 0.4544, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 33.39, |
|
"learning_rate": 1.3476923076923077e-06, |
|
"loss": 0.4341, |
|
"step": 5710 |
|
}, |
|
{ |
|
"epoch": 33.45, |
|
"learning_rate": 1.3429585798816568e-06, |
|
"loss": 0.4331, |
|
"step": 5720 |
|
}, |
|
{ |
|
"epoch": 33.51, |
|
"learning_rate": 1.3382248520710058e-06, |
|
"loss": 0.4099, |
|
"step": 5730 |
|
}, |
|
{ |
|
"epoch": 33.57, |
|
"learning_rate": 1.333491124260355e-06, |
|
"loss": 0.4637, |
|
"step": 5740 |
|
}, |
|
{ |
|
"epoch": 33.63, |
|
"learning_rate": 1.3287573964497041e-06, |
|
"loss": 0.4399, |
|
"step": 5750 |
|
}, |
|
{ |
|
"epoch": 33.68, |
|
"learning_rate": 1.3240236686390532e-06, |
|
"loss": 0.4361, |
|
"step": 5760 |
|
}, |
|
{ |
|
"epoch": 33.74, |
|
"learning_rate": 1.3192899408284024e-06, |
|
"loss": 0.4447, |
|
"step": 5770 |
|
}, |
|
{ |
|
"epoch": 33.8, |
|
"learning_rate": 1.3145562130177514e-06, |
|
"loss": 0.4403, |
|
"step": 5780 |
|
}, |
|
{ |
|
"epoch": 33.86, |
|
"learning_rate": 1.3098224852071005e-06, |
|
"loss": 0.4479, |
|
"step": 5790 |
|
}, |
|
{ |
|
"epoch": 33.92, |
|
"learning_rate": 1.3050887573964497e-06, |
|
"loss": 0.4208, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 33.98, |
|
"learning_rate": 1.3003550295857988e-06, |
|
"loss": 0.4179, |
|
"step": 5810 |
|
}, |
|
{ |
|
"epoch": 34.0, |
|
"eval_loss": 0.17488279938697815, |
|
"eval_runtime": 206.498, |
|
"eval_samples_per_second": 5.894, |
|
"eval_steps_per_second": 0.741, |
|
"eval_wer": 0.09546092653252222, |
|
"step": 5814 |
|
}, |
|
{ |
|
"epoch": 34.04, |
|
"learning_rate": 1.2956213017751478e-06, |
|
"loss": 0.4297, |
|
"step": 5820 |
|
}, |
|
{ |
|
"epoch": 34.09, |
|
"learning_rate": 1.2908875739644969e-06, |
|
"loss": 0.4728, |
|
"step": 5830 |
|
}, |
|
{ |
|
"epoch": 34.15, |
|
"learning_rate": 1.286153846153846e-06, |
|
"loss": 0.4515, |
|
"step": 5840 |
|
}, |
|
{ |
|
"epoch": 34.21, |
|
"learning_rate": 1.2814201183431951e-06, |
|
"loss": 0.4335, |
|
"step": 5850 |
|
}, |
|
{ |
|
"epoch": 34.27, |
|
"learning_rate": 1.2766863905325442e-06, |
|
"loss": 0.4369, |
|
"step": 5860 |
|
}, |
|
{ |
|
"epoch": 34.33, |
|
"learning_rate": 1.2719526627218934e-06, |
|
"loss": 0.4443, |
|
"step": 5870 |
|
}, |
|
{ |
|
"epoch": 34.39, |
|
"learning_rate": 1.2672189349112425e-06, |
|
"loss": 0.4485, |
|
"step": 5880 |
|
}, |
|
{ |
|
"epoch": 34.44, |
|
"learning_rate": 1.2624852071005915e-06, |
|
"loss": 0.434, |
|
"step": 5890 |
|
}, |
|
{ |
|
"epoch": 34.5, |
|
"learning_rate": 1.2577514792899408e-06, |
|
"loss": 0.4324, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 34.56, |
|
"learning_rate": 1.2530177514792898e-06, |
|
"loss": 0.4545, |
|
"step": 5910 |
|
}, |
|
{ |
|
"epoch": 34.62, |
|
"learning_rate": 1.2482840236686388e-06, |
|
"loss": 0.442, |
|
"step": 5920 |
|
}, |
|
{ |
|
"epoch": 34.68, |
|
"learning_rate": 1.2435502958579883e-06, |
|
"loss": 0.421, |
|
"step": 5930 |
|
}, |
|
{ |
|
"epoch": 34.74, |
|
"learning_rate": 1.2388165680473374e-06, |
|
"loss": 0.4066, |
|
"step": 5940 |
|
}, |
|
{ |
|
"epoch": 34.79, |
|
"learning_rate": 1.2340828402366864e-06, |
|
"loss": 0.4452, |
|
"step": 5950 |
|
}, |
|
{ |
|
"epoch": 34.85, |
|
"learning_rate": 1.2293491124260354e-06, |
|
"loss": 0.4516, |
|
"step": 5960 |
|
}, |
|
{ |
|
"epoch": 34.91, |
|
"learning_rate": 1.2246153846153847e-06, |
|
"loss": 0.4415, |
|
"step": 5970 |
|
}, |
|
{ |
|
"epoch": 34.97, |
|
"learning_rate": 1.2198816568047337e-06, |
|
"loss": 0.4264, |
|
"step": 5980 |
|
}, |
|
{ |
|
"epoch": 35.0, |
|
"eval_loss": 0.17572873830795288, |
|
"eval_runtime": 206.7153, |
|
"eval_samples_per_second": 5.887, |
|
"eval_steps_per_second": 0.74, |
|
"eval_wer": 0.09661279291602175, |
|
"step": 5985 |
|
}, |
|
{ |
|
"epoch": 35.03, |
|
"learning_rate": 1.2151479289940828e-06, |
|
"loss": 0.4426, |
|
"step": 5990 |
|
}, |
|
{ |
|
"epoch": 35.09, |
|
"learning_rate": 1.210414201183432e-06, |
|
"loss": 0.4538, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 35.15, |
|
"learning_rate": 1.205680473372781e-06, |
|
"loss": 0.4429, |
|
"step": 6010 |
|
}, |
|
{ |
|
"epoch": 35.2, |
|
"learning_rate": 1.20094674556213e-06, |
|
"loss": 0.4401, |
|
"step": 6020 |
|
}, |
|
{ |
|
"epoch": 35.26, |
|
"learning_rate": 1.1962130177514793e-06, |
|
"loss": 0.4444, |
|
"step": 6030 |
|
}, |
|
{ |
|
"epoch": 35.32, |
|
"learning_rate": 1.1914792899408284e-06, |
|
"loss": 0.4504, |
|
"step": 6040 |
|
}, |
|
{ |
|
"epoch": 35.38, |
|
"learning_rate": 1.1867455621301774e-06, |
|
"loss": 0.4523, |
|
"step": 6050 |
|
}, |
|
{ |
|
"epoch": 35.44, |
|
"learning_rate": 1.1820118343195267e-06, |
|
"loss": 0.4559, |
|
"step": 6060 |
|
}, |
|
{ |
|
"epoch": 35.5, |
|
"learning_rate": 1.1772781065088757e-06, |
|
"loss": 0.4122, |
|
"step": 6070 |
|
}, |
|
{ |
|
"epoch": 35.56, |
|
"learning_rate": 1.1725443786982248e-06, |
|
"loss": 0.466, |
|
"step": 6080 |
|
}, |
|
{ |
|
"epoch": 35.61, |
|
"learning_rate": 1.167810650887574e-06, |
|
"loss": 0.4504, |
|
"step": 6090 |
|
}, |
|
{ |
|
"epoch": 35.67, |
|
"learning_rate": 1.163076923076923e-06, |
|
"loss": 0.4411, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 35.73, |
|
"learning_rate": 1.158343195266272e-06, |
|
"loss": 0.4393, |
|
"step": 6110 |
|
}, |
|
{ |
|
"epoch": 35.79, |
|
"learning_rate": 1.1540828402366863e-06, |
|
"loss": 0.4469, |
|
"step": 6120 |
|
}, |
|
{ |
|
"epoch": 35.85, |
|
"learning_rate": 1.1493491124260356e-06, |
|
"loss": 0.4629, |
|
"step": 6130 |
|
}, |
|
{ |
|
"epoch": 35.91, |
|
"learning_rate": 1.1446153846153846e-06, |
|
"loss": 0.4217, |
|
"step": 6140 |
|
}, |
|
{ |
|
"epoch": 35.96, |
|
"learning_rate": 1.1398816568047336e-06, |
|
"loss": 0.4217, |
|
"step": 6150 |
|
}, |
|
{ |
|
"epoch": 36.0, |
|
"eval_loss": 0.17530620098114014, |
|
"eval_runtime": 207.4169, |
|
"eval_samples_per_second": 5.867, |
|
"eval_steps_per_second": 0.738, |
|
"eval_wer": 0.09553291818149094, |
|
"step": 6156 |
|
}, |
|
{ |
|
"epoch": 36.02, |
|
"learning_rate": 1.135147928994083e-06, |
|
"loss": 0.4508, |
|
"step": 6160 |
|
}, |
|
{ |
|
"epoch": 36.08, |
|
"learning_rate": 1.130414201183432e-06, |
|
"loss": 0.4675, |
|
"step": 6170 |
|
}, |
|
{ |
|
"epoch": 36.14, |
|
"learning_rate": 1.125680473372781e-06, |
|
"loss": 0.4444, |
|
"step": 6180 |
|
}, |
|
{ |
|
"epoch": 36.2, |
|
"learning_rate": 1.1209467455621302e-06, |
|
"loss": 0.4437, |
|
"step": 6190 |
|
}, |
|
{ |
|
"epoch": 36.26, |
|
"learning_rate": 1.1162130177514793e-06, |
|
"loss": 0.4295, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 36.32, |
|
"learning_rate": 1.1114792899408283e-06, |
|
"loss": 0.4522, |
|
"step": 6210 |
|
}, |
|
{ |
|
"epoch": 36.37, |
|
"learning_rate": 1.1067455621301776e-06, |
|
"loss": 0.4431, |
|
"step": 6220 |
|
}, |
|
{ |
|
"epoch": 36.43, |
|
"learning_rate": 1.1020118343195266e-06, |
|
"loss": 0.4463, |
|
"step": 6230 |
|
}, |
|
{ |
|
"epoch": 36.49, |
|
"learning_rate": 1.0972781065088756e-06, |
|
"loss": 0.4279, |
|
"step": 6240 |
|
}, |
|
{ |
|
"epoch": 36.55, |
|
"learning_rate": 1.0925443786982249e-06, |
|
"loss": 0.4574, |
|
"step": 6250 |
|
}, |
|
{ |
|
"epoch": 36.61, |
|
"learning_rate": 1.087810650887574e-06, |
|
"loss": 0.4494, |
|
"step": 6260 |
|
}, |
|
{ |
|
"epoch": 36.67, |
|
"learning_rate": 1.083076923076923e-06, |
|
"loss": 0.4252, |
|
"step": 6270 |
|
}, |
|
{ |
|
"epoch": 36.72, |
|
"learning_rate": 1.078343195266272e-06, |
|
"loss": 0.4181, |
|
"step": 6280 |
|
}, |
|
{ |
|
"epoch": 36.78, |
|
"learning_rate": 1.0736094674556213e-06, |
|
"loss": 0.4525, |
|
"step": 6290 |
|
}, |
|
{ |
|
"epoch": 36.84, |
|
"learning_rate": 1.0688757396449703e-06, |
|
"loss": 0.446, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 36.9, |
|
"learning_rate": 1.0641420118343193e-06, |
|
"loss": 0.4191, |
|
"step": 6310 |
|
}, |
|
{ |
|
"epoch": 36.96, |
|
"learning_rate": 1.0594082840236686e-06, |
|
"loss": 0.4556, |
|
"step": 6320 |
|
}, |
|
{ |
|
"epoch": 37.0, |
|
"eval_loss": 0.17492040991783142, |
|
"eval_runtime": 205.989, |
|
"eval_samples_per_second": 5.908, |
|
"eval_steps_per_second": 0.743, |
|
"eval_wer": 0.09571289730391275, |
|
"step": 6327 |
|
}, |
|
{ |
|
"epoch": 37.02, |
|
"learning_rate": 1.0546745562130176e-06, |
|
"loss": 0.4346, |
|
"step": 6330 |
|
}, |
|
{ |
|
"epoch": 37.08, |
|
"learning_rate": 1.0499408284023667e-06, |
|
"loss": 0.4565, |
|
"step": 6340 |
|
}, |
|
{ |
|
"epoch": 37.13, |
|
"learning_rate": 1.045207100591716e-06, |
|
"loss": 0.4239, |
|
"step": 6350 |
|
}, |
|
{ |
|
"epoch": 37.19, |
|
"learning_rate": 1.040473372781065e-06, |
|
"loss": 0.4415, |
|
"step": 6360 |
|
}, |
|
{ |
|
"epoch": 37.25, |
|
"learning_rate": 1.035739644970414e-06, |
|
"loss": 0.4341, |
|
"step": 6370 |
|
}, |
|
{ |
|
"epoch": 37.31, |
|
"learning_rate": 1.0310059171597635e-06, |
|
"loss": 0.4505, |
|
"step": 6380 |
|
}, |
|
{ |
|
"epoch": 37.37, |
|
"learning_rate": 1.0262721893491125e-06, |
|
"loss": 0.4375, |
|
"step": 6390 |
|
}, |
|
{ |
|
"epoch": 37.43, |
|
"learning_rate": 1.0215384615384615e-06, |
|
"loss": 0.4267, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 37.49, |
|
"learning_rate": 1.0168047337278106e-06, |
|
"loss": 0.4337, |
|
"step": 6410 |
|
}, |
|
{ |
|
"epoch": 37.54, |
|
"learning_rate": 1.0120710059171598e-06, |
|
"loss": 0.4464, |
|
"step": 6420 |
|
}, |
|
{ |
|
"epoch": 37.6, |
|
"learning_rate": 1.0073372781065089e-06, |
|
"loss": 0.4591, |
|
"step": 6430 |
|
}, |
|
{ |
|
"epoch": 37.66, |
|
"learning_rate": 1.002603550295858e-06, |
|
"loss": 0.4264, |
|
"step": 6440 |
|
}, |
|
{ |
|
"epoch": 37.72, |
|
"learning_rate": 9.97869822485207e-07, |
|
"loss": 0.4347, |
|
"step": 6450 |
|
}, |
|
{ |
|
"epoch": 37.78, |
|
"learning_rate": 9.931360946745562e-07, |
|
"loss": 0.453, |
|
"step": 6460 |
|
}, |
|
{ |
|
"epoch": 37.84, |
|
"learning_rate": 9.884023668639053e-07, |
|
"loss": 0.4583, |
|
"step": 6470 |
|
}, |
|
{ |
|
"epoch": 37.89, |
|
"learning_rate": 9.836686390532543e-07, |
|
"loss": 0.459, |
|
"step": 6480 |
|
}, |
|
{ |
|
"epoch": 37.95, |
|
"learning_rate": 9.789349112426035e-07, |
|
"loss": 0.4181, |
|
"step": 6490 |
|
}, |
|
{ |
|
"epoch": 38.0, |
|
"eval_loss": 0.1755959838628769, |
|
"eval_runtime": 206.3645, |
|
"eval_samples_per_second": 5.897, |
|
"eval_steps_per_second": 0.741, |
|
"eval_wer": 0.09722472193225586, |
|
"step": 6498 |
|
}, |
|
{ |
|
"epoch": 38.01, |
|
"learning_rate": 9.742011834319526e-07, |
|
"loss": 0.4206, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 38.07, |
|
"learning_rate": 9.694674556213016e-07, |
|
"loss": 0.4356, |
|
"step": 6510 |
|
}, |
|
{ |
|
"epoch": 38.13, |
|
"learning_rate": 9.647337278106509e-07, |
|
"loss": 0.4553, |
|
"step": 6520 |
|
}, |
|
{ |
|
"epoch": 38.19, |
|
"learning_rate": 9.6e-07, |
|
"loss": 0.4365, |
|
"step": 6530 |
|
}, |
|
{ |
|
"epoch": 38.25, |
|
"learning_rate": 9.552662721893492e-07, |
|
"loss": 0.4216, |
|
"step": 6540 |
|
}, |
|
{ |
|
"epoch": 38.3, |
|
"learning_rate": 9.505325443786982e-07, |
|
"loss": 0.4588, |
|
"step": 6550 |
|
}, |
|
{ |
|
"epoch": 38.36, |
|
"learning_rate": 9.457988165680472e-07, |
|
"loss": 0.4481, |
|
"step": 6560 |
|
}, |
|
{ |
|
"epoch": 38.42, |
|
"learning_rate": 9.410650887573964e-07, |
|
"loss": 0.4591, |
|
"step": 6570 |
|
}, |
|
{ |
|
"epoch": 38.48, |
|
"learning_rate": 9.363313609467454e-07, |
|
"loss": 0.4296, |
|
"step": 6580 |
|
}, |
|
{ |
|
"epoch": 38.54, |
|
"learning_rate": 9.315976331360946e-07, |
|
"loss": 0.4665, |
|
"step": 6590 |
|
}, |
|
{ |
|
"epoch": 38.6, |
|
"learning_rate": 9.268639053254438e-07, |
|
"loss": 0.4355, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 38.65, |
|
"learning_rate": 9.221301775147929e-07, |
|
"loss": 0.4336, |
|
"step": 6610 |
|
}, |
|
{ |
|
"epoch": 38.71, |
|
"learning_rate": 9.17396449704142e-07, |
|
"loss": 0.4203, |
|
"step": 6620 |
|
}, |
|
{ |
|
"epoch": 38.77, |
|
"learning_rate": 9.126627218934911e-07, |
|
"loss": 0.4494, |
|
"step": 6630 |
|
}, |
|
{ |
|
"epoch": 38.83, |
|
"learning_rate": 9.079289940828402e-07, |
|
"loss": 0.4722, |
|
"step": 6640 |
|
}, |
|
{ |
|
"epoch": 38.89, |
|
"learning_rate": 9.031952662721893e-07, |
|
"loss": 0.4412, |
|
"step": 6650 |
|
}, |
|
{ |
|
"epoch": 38.95, |
|
"learning_rate": 8.984615384615384e-07, |
|
"loss": 0.4286, |
|
"step": 6660 |
|
}, |
|
{ |
|
"epoch": 39.0, |
|
"eval_loss": 0.17471006512641907, |
|
"eval_runtime": 207.454, |
|
"eval_samples_per_second": 5.866, |
|
"eval_steps_per_second": 0.738, |
|
"eval_wer": 0.09560490983045966, |
|
"step": 6669 |
|
}, |
|
{ |
|
"epoch": 39.01, |
|
"learning_rate": 8.937278106508875e-07, |
|
"loss": 0.4359, |
|
"step": 6670 |
|
}, |
|
{ |
|
"epoch": 39.06, |
|
"learning_rate": 8.889940828402367e-07, |
|
"loss": 0.4392, |
|
"step": 6680 |
|
}, |
|
{ |
|
"epoch": 39.12, |
|
"learning_rate": 8.842603550295857e-07, |
|
"loss": 0.4599, |
|
"step": 6690 |
|
}, |
|
{ |
|
"epoch": 39.18, |
|
"learning_rate": 8.795266272189349e-07, |
|
"loss": 0.426, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 39.24, |
|
"learning_rate": 8.747928994082839e-07, |
|
"loss": 0.4321, |
|
"step": 6710 |
|
}, |
|
{ |
|
"epoch": 39.3, |
|
"learning_rate": 8.70059171597633e-07, |
|
"loss": 0.4475, |
|
"step": 6720 |
|
}, |
|
{ |
|
"epoch": 39.36, |
|
"learning_rate": 8.653254437869822e-07, |
|
"loss": 0.4518, |
|
"step": 6730 |
|
}, |
|
{ |
|
"epoch": 39.41, |
|
"learning_rate": 8.605917159763313e-07, |
|
"loss": 0.4403, |
|
"step": 6740 |
|
}, |
|
{ |
|
"epoch": 39.47, |
|
"learning_rate": 8.558579881656805e-07, |
|
"loss": 0.4289, |
|
"step": 6750 |
|
}, |
|
{ |
|
"epoch": 39.53, |
|
"learning_rate": 8.511242603550296e-07, |
|
"loss": 0.4506, |
|
"step": 6760 |
|
}, |
|
{ |
|
"epoch": 39.59, |
|
"learning_rate": 8.463905325443787e-07, |
|
"loss": 0.4501, |
|
"step": 6770 |
|
}, |
|
{ |
|
"epoch": 39.65, |
|
"learning_rate": 8.416568047337278e-07, |
|
"loss": 0.4566, |
|
"step": 6780 |
|
}, |
|
{ |
|
"epoch": 39.71, |
|
"learning_rate": 8.369230769230769e-07, |
|
"loss": 0.4272, |
|
"step": 6790 |
|
}, |
|
{ |
|
"epoch": 39.77, |
|
"learning_rate": 8.32189349112426e-07, |
|
"loss": 0.4198, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 39.82, |
|
"learning_rate": 8.274556213017752e-07, |
|
"loss": 0.4525, |
|
"step": 6810 |
|
}, |
|
{ |
|
"epoch": 39.88, |
|
"learning_rate": 8.227218934911242e-07, |
|
"loss": 0.4281, |
|
"step": 6820 |
|
}, |
|
{ |
|
"epoch": 39.94, |
|
"learning_rate": 8.179881656804733e-07, |
|
"loss": 0.4319, |
|
"step": 6830 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"learning_rate": 8.132544378698224e-07, |
|
"loss": 0.4427, |
|
"step": 6840 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"eval_loss": 0.17470921576023102, |
|
"eval_runtime": 206.2034, |
|
"eval_samples_per_second": 5.902, |
|
"eval_steps_per_second": 0.742, |
|
"eval_wer": 0.09646880961808431, |
|
"step": 6840 |
|
}, |
|
{ |
|
"epoch": 40.06, |
|
"learning_rate": 8.085207100591715e-07, |
|
"loss": 0.4556, |
|
"step": 6850 |
|
}, |
|
{ |
|
"epoch": 40.12, |
|
"learning_rate": 8.037869822485207e-07, |
|
"loss": 0.4625, |
|
"step": 6860 |
|
}, |
|
{ |
|
"epoch": 40.18, |
|
"learning_rate": 7.990532544378697e-07, |
|
"loss": 0.4383, |
|
"step": 6870 |
|
}, |
|
{ |
|
"epoch": 40.23, |
|
"learning_rate": 7.943195266272189e-07, |
|
"loss": 0.4221, |
|
"step": 6880 |
|
}, |
|
{ |
|
"epoch": 40.29, |
|
"learning_rate": 7.895857988165681e-07, |
|
"loss": 0.4548, |
|
"step": 6890 |
|
}, |
|
{ |
|
"epoch": 40.35, |
|
"learning_rate": 7.848520710059171e-07, |
|
"loss": 0.4566, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 40.41, |
|
"learning_rate": 7.801183431952663e-07, |
|
"loss": 0.4354, |
|
"step": 6910 |
|
}, |
|
{ |
|
"epoch": 40.47, |
|
"learning_rate": 7.753846153846153e-07, |
|
"loss": 0.4353, |
|
"step": 6920 |
|
}, |
|
{ |
|
"epoch": 40.53, |
|
"learning_rate": 7.706508875739645e-07, |
|
"loss": 0.4464, |
|
"step": 6930 |
|
}, |
|
{ |
|
"epoch": 40.58, |
|
"learning_rate": 7.659171597633136e-07, |
|
"loss": 0.4496, |
|
"step": 6940 |
|
}, |
|
{ |
|
"epoch": 40.64, |
|
"learning_rate": 7.611834319526627e-07, |
|
"loss": 0.4369, |
|
"step": 6950 |
|
}, |
|
{ |
|
"epoch": 40.7, |
|
"learning_rate": 7.564497041420118e-07, |
|
"loss": 0.4416, |
|
"step": 6960 |
|
}, |
|
{ |
|
"epoch": 40.76, |
|
"learning_rate": 7.51715976331361e-07, |
|
"loss": 0.4305, |
|
"step": 6970 |
|
}, |
|
{ |
|
"epoch": 40.82, |
|
"learning_rate": 7.4698224852071e-07, |
|
"loss": 0.4575, |
|
"step": 6980 |
|
}, |
|
{ |
|
"epoch": 40.88, |
|
"learning_rate": 7.422485207100591e-07, |
|
"loss": 0.4398, |
|
"step": 6990 |
|
}, |
|
{ |
|
"epoch": 40.93, |
|
"learning_rate": 7.375147928994082e-07, |
|
"loss": 0.4382, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 40.99, |
|
"learning_rate": 7.327810650887573e-07, |
|
"loss": 0.4292, |
|
"step": 7010 |
|
}, |
|
{ |
|
"epoch": 41.0, |
|
"eval_loss": 0.17421963810920715, |
|
"eval_runtime": 207.797, |
|
"eval_samples_per_second": 5.857, |
|
"eval_steps_per_second": 0.736, |
|
"eval_wer": 0.09553291818149094, |
|
"step": 7011 |
|
}, |
|
{ |
|
"epoch": 41.05, |
|
"learning_rate": 7.280473372781065e-07, |
|
"loss": 0.4498, |
|
"step": 7020 |
|
}, |
|
{ |
|
"epoch": 41.11, |
|
"learning_rate": 7.233136094674556e-07, |
|
"loss": 0.4713, |
|
"step": 7030 |
|
}, |
|
{ |
|
"epoch": 41.17, |
|
"learning_rate": 7.185798816568048e-07, |
|
"loss": 0.435, |
|
"step": 7040 |
|
}, |
|
{ |
|
"epoch": 41.23, |
|
"learning_rate": 7.138461538461538e-07, |
|
"loss": 0.4325, |
|
"step": 7050 |
|
}, |
|
{ |
|
"epoch": 41.29, |
|
"learning_rate": 7.09112426035503e-07, |
|
"loss": 0.4416, |
|
"step": 7060 |
|
}, |
|
{ |
|
"epoch": 41.34, |
|
"learning_rate": 7.043786982248521e-07, |
|
"loss": 0.4617, |
|
"step": 7070 |
|
}, |
|
{ |
|
"epoch": 41.4, |
|
"learning_rate": 6.996449704142011e-07, |
|
"loss": 0.4299, |
|
"step": 7080 |
|
}, |
|
{ |
|
"epoch": 41.46, |
|
"learning_rate": 6.949112426035503e-07, |
|
"loss": 0.4314, |
|
"step": 7090 |
|
}, |
|
{ |
|
"epoch": 41.52, |
|
"learning_rate": 6.901775147928994e-07, |
|
"loss": 0.4381, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 41.58, |
|
"learning_rate": 6.854437869822485e-07, |
|
"loss": 0.4388, |
|
"step": 7110 |
|
}, |
|
{ |
|
"epoch": 41.64, |
|
"learning_rate": 6.807100591715976e-07, |
|
"loss": 0.4414, |
|
"step": 7120 |
|
}, |
|
{ |
|
"epoch": 41.7, |
|
"learning_rate": 6.759763313609467e-07, |
|
"loss": 0.4419, |
|
"step": 7130 |
|
}, |
|
{ |
|
"epoch": 41.75, |
|
"learning_rate": 6.712426035502958e-07, |
|
"loss": 0.4403, |
|
"step": 7140 |
|
}, |
|
{ |
|
"epoch": 41.81, |
|
"learning_rate": 6.665088757396449e-07, |
|
"loss": 0.4438, |
|
"step": 7150 |
|
}, |
|
{ |
|
"epoch": 41.87, |
|
"learning_rate": 6.61775147928994e-07, |
|
"loss": 0.4384, |
|
"step": 7160 |
|
}, |
|
{ |
|
"epoch": 41.93, |
|
"learning_rate": 6.570414201183431e-07, |
|
"loss": 0.4297, |
|
"step": 7170 |
|
}, |
|
{ |
|
"epoch": 41.99, |
|
"learning_rate": 6.523076923076923e-07, |
|
"loss": 0.424, |
|
"step": 7180 |
|
}, |
|
{ |
|
"epoch": 42.0, |
|
"eval_loss": 0.17400115728378296, |
|
"eval_runtime": 207.2344, |
|
"eval_samples_per_second": 5.873, |
|
"eval_steps_per_second": 0.738, |
|
"eval_wer": 0.09517295993664734, |
|
"step": 7182 |
|
}, |
|
{ |
|
"epoch": 42.05, |
|
"learning_rate": 6.475739644970414e-07, |
|
"loss": 0.4625, |
|
"step": 7190 |
|
}, |
|
{ |
|
"epoch": 42.11, |
|
"learning_rate": 6.428402366863906e-07, |
|
"loss": 0.4499, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 42.16, |
|
"learning_rate": 6.381065088757396e-07, |
|
"loss": 0.4575, |
|
"step": 7210 |
|
}, |
|
{ |
|
"epoch": 42.22, |
|
"learning_rate": 6.333727810650888e-07, |
|
"loss": 0.4289, |
|
"step": 7220 |
|
}, |
|
{ |
|
"epoch": 42.28, |
|
"learning_rate": 6.286390532544379e-07, |
|
"loss": 0.4462, |
|
"step": 7230 |
|
}, |
|
{ |
|
"epoch": 42.34, |
|
"learning_rate": 6.239053254437869e-07, |
|
"loss": 0.4492, |
|
"step": 7240 |
|
}, |
|
{ |
|
"epoch": 42.4, |
|
"learning_rate": 6.191715976331361e-07, |
|
"loss": 0.4358, |
|
"step": 7250 |
|
}, |
|
{ |
|
"epoch": 42.46, |
|
"learning_rate": 6.144378698224851e-07, |
|
"loss": 0.4296, |
|
"step": 7260 |
|
}, |
|
{ |
|
"epoch": 42.51, |
|
"learning_rate": 6.097041420118343e-07, |
|
"loss": 0.4449, |
|
"step": 7270 |
|
}, |
|
{ |
|
"epoch": 42.57, |
|
"learning_rate": 6.049704142011834e-07, |
|
"loss": 0.4762, |
|
"step": 7280 |
|
}, |
|
{ |
|
"epoch": 42.63, |
|
"learning_rate": 6.002366863905325e-07, |
|
"loss": 0.4238, |
|
"step": 7290 |
|
}, |
|
{ |
|
"epoch": 42.69, |
|
"learning_rate": 5.955029585798816e-07, |
|
"loss": 0.4233, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 42.75, |
|
"learning_rate": 5.907692307692307e-07, |
|
"loss": 0.4359, |
|
"step": 7310 |
|
}, |
|
{ |
|
"epoch": 42.81, |
|
"learning_rate": 5.860355029585798e-07, |
|
"loss": 0.457, |
|
"step": 7320 |
|
}, |
|
{ |
|
"epoch": 42.86, |
|
"learning_rate": 5.81301775147929e-07, |
|
"loss": 0.4572, |
|
"step": 7330 |
|
}, |
|
{ |
|
"epoch": 42.92, |
|
"learning_rate": 5.765680473372781e-07, |
|
"loss": 0.444, |
|
"step": 7340 |
|
}, |
|
{ |
|
"epoch": 42.98, |
|
"learning_rate": 5.718343195266272e-07, |
|
"loss": 0.4314, |
|
"step": 7350 |
|
}, |
|
{ |
|
"epoch": 43.0, |
|
"eval_loss": 0.17434477806091309, |
|
"eval_runtime": 205.8743, |
|
"eval_samples_per_second": 5.911, |
|
"eval_steps_per_second": 0.743, |
|
"eval_wer": 0.09625283467117815, |
|
"step": 7353 |
|
}, |
|
{ |
|
"epoch": 43.04, |
|
"learning_rate": 5.671005917159764e-07, |
|
"loss": 0.432, |
|
"step": 7360 |
|
}, |
|
{ |
|
"epoch": 43.1, |
|
"learning_rate": 5.623668639053254e-07, |
|
"loss": 0.4486, |
|
"step": 7370 |
|
}, |
|
{ |
|
"epoch": 43.16, |
|
"learning_rate": 5.576331360946746e-07, |
|
"loss": 0.437, |
|
"step": 7380 |
|
}, |
|
{ |
|
"epoch": 43.22, |
|
"learning_rate": 5.528994082840236e-07, |
|
"loss": 0.4184, |
|
"step": 7390 |
|
}, |
|
{ |
|
"epoch": 43.27, |
|
"learning_rate": 5.481656804733727e-07, |
|
"loss": 0.4531, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 43.33, |
|
"learning_rate": 5.434319526627219e-07, |
|
"loss": 0.4501, |
|
"step": 7410 |
|
}, |
|
{ |
|
"epoch": 43.39, |
|
"learning_rate": 5.386982248520709e-07, |
|
"loss": 0.4446, |
|
"step": 7420 |
|
}, |
|
{ |
|
"epoch": 43.45, |
|
"learning_rate": 5.339644970414201e-07, |
|
"loss": 0.4402, |
|
"step": 7430 |
|
}, |
|
{ |
|
"epoch": 43.51, |
|
"learning_rate": 5.292307692307692e-07, |
|
"loss": 0.4467, |
|
"step": 7440 |
|
}, |
|
{ |
|
"epoch": 43.57, |
|
"learning_rate": 5.244970414201183e-07, |
|
"loss": 0.4539, |
|
"step": 7450 |
|
}, |
|
{ |
|
"epoch": 43.63, |
|
"learning_rate": 5.197633136094674e-07, |
|
"loss": 0.4521, |
|
"step": 7460 |
|
}, |
|
{ |
|
"epoch": 43.68, |
|
"learning_rate": 5.150295857988166e-07, |
|
"loss": 0.4276, |
|
"step": 7470 |
|
}, |
|
{ |
|
"epoch": 43.74, |
|
"learning_rate": 5.102958579881657e-07, |
|
"loss": 0.4322, |
|
"step": 7480 |
|
}, |
|
{ |
|
"epoch": 43.8, |
|
"learning_rate": 5.060355029585799e-07, |
|
"loss": 0.4651, |
|
"step": 7490 |
|
}, |
|
{ |
|
"epoch": 43.86, |
|
"learning_rate": 5.01301775147929e-07, |
|
"loss": 0.4702, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 43.92, |
|
"learning_rate": 4.965680473372781e-07, |
|
"loss": 0.4334, |
|
"step": 7510 |
|
}, |
|
{ |
|
"epoch": 43.98, |
|
"learning_rate": 4.918343195266271e-07, |
|
"loss": 0.4359, |
|
"step": 7520 |
|
}, |
|
{ |
|
"epoch": 44.0, |
|
"eval_loss": 0.17438200116157532, |
|
"eval_runtime": 207.954, |
|
"eval_samples_per_second": 5.852, |
|
"eval_steps_per_second": 0.736, |
|
"eval_wer": 0.09517295993664734, |
|
"step": 7524 |
|
}, |
|
{ |
|
"epoch": 44.04, |
|
"learning_rate": 4.871005917159763e-07, |
|
"loss": 0.446, |
|
"step": 7530 |
|
}, |
|
{ |
|
"epoch": 44.09, |
|
"learning_rate": 4.823668639053254e-07, |
|
"loss": 0.4632, |
|
"step": 7540 |
|
}, |
|
{ |
|
"epoch": 44.15, |
|
"learning_rate": 4.776331360946746e-07, |
|
"loss": 0.4326, |
|
"step": 7550 |
|
}, |
|
{ |
|
"epoch": 44.21, |
|
"learning_rate": 4.728994082840236e-07, |
|
"loss": 0.4245, |
|
"step": 7560 |
|
}, |
|
{ |
|
"epoch": 44.27, |
|
"learning_rate": 4.681656804733727e-07, |
|
"loss": 0.4541, |
|
"step": 7570 |
|
}, |
|
{ |
|
"epoch": 44.33, |
|
"learning_rate": 4.634319526627219e-07, |
|
"loss": 0.4713, |
|
"step": 7580 |
|
}, |
|
{ |
|
"epoch": 44.39, |
|
"learning_rate": 4.58698224852071e-07, |
|
"loss": 0.4612, |
|
"step": 7590 |
|
}, |
|
{ |
|
"epoch": 44.44, |
|
"learning_rate": 4.539644970414201e-07, |
|
"loss": 0.4299, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 44.5, |
|
"learning_rate": 4.492307692307692e-07, |
|
"loss": 0.4323, |
|
"step": 7610 |
|
}, |
|
{ |
|
"epoch": 44.56, |
|
"learning_rate": 4.4449704142011834e-07, |
|
"loss": 0.4566, |
|
"step": 7620 |
|
}, |
|
{ |
|
"epoch": 44.62, |
|
"learning_rate": 4.3976331360946743e-07, |
|
"loss": 0.4544, |
|
"step": 7630 |
|
}, |
|
{ |
|
"epoch": 44.68, |
|
"learning_rate": 4.350295857988165e-07, |
|
"loss": 0.4311, |
|
"step": 7640 |
|
}, |
|
{ |
|
"epoch": 44.74, |
|
"learning_rate": 4.3029585798816567e-07, |
|
"loss": 0.43, |
|
"step": 7650 |
|
}, |
|
{ |
|
"epoch": 44.79, |
|
"learning_rate": 4.255621301775148e-07, |
|
"loss": 0.4713, |
|
"step": 7660 |
|
}, |
|
{ |
|
"epoch": 44.85, |
|
"learning_rate": 4.208284023668639e-07, |
|
"loss": 0.4517, |
|
"step": 7670 |
|
}, |
|
{ |
|
"epoch": 44.91, |
|
"learning_rate": 4.16094674556213e-07, |
|
"loss": 0.4487, |
|
"step": 7680 |
|
}, |
|
{ |
|
"epoch": 44.97, |
|
"learning_rate": 4.113609467455621e-07, |
|
"loss": 0.4195, |
|
"step": 7690 |
|
}, |
|
{ |
|
"epoch": 45.0, |
|
"eval_loss": 0.1735733300447464, |
|
"eval_runtime": 206.8295, |
|
"eval_samples_per_second": 5.884, |
|
"eval_steps_per_second": 0.74, |
|
"eval_wer": 0.09488499334077247, |
|
"step": 7695 |
|
}, |
|
{ |
|
"epoch": 45.03, |
|
"learning_rate": 4.066272189349112e-07, |
|
"loss": 0.4575, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 45.09, |
|
"learning_rate": 4.0189349112426033e-07, |
|
"loss": 0.4487, |
|
"step": 7710 |
|
}, |
|
{ |
|
"epoch": 45.15, |
|
"learning_rate": 3.9715976331360943e-07, |
|
"loss": 0.4486, |
|
"step": 7720 |
|
}, |
|
{ |
|
"epoch": 45.2, |
|
"learning_rate": 3.9242603550295857e-07, |
|
"loss": 0.4372, |
|
"step": 7730 |
|
}, |
|
{ |
|
"epoch": 45.26, |
|
"learning_rate": 3.8769230769230767e-07, |
|
"loss": 0.4421, |
|
"step": 7740 |
|
}, |
|
{ |
|
"epoch": 45.32, |
|
"learning_rate": 3.829585798816568e-07, |
|
"loss": 0.4593, |
|
"step": 7750 |
|
}, |
|
{ |
|
"epoch": 45.38, |
|
"learning_rate": 3.782248520710059e-07, |
|
"loss": 0.4618, |
|
"step": 7760 |
|
}, |
|
{ |
|
"epoch": 45.44, |
|
"learning_rate": 3.73491124260355e-07, |
|
"loss": 0.4333, |
|
"step": 7770 |
|
}, |
|
{ |
|
"epoch": 45.5, |
|
"learning_rate": 3.687573964497041e-07, |
|
"loss": 0.4254, |
|
"step": 7780 |
|
}, |
|
{ |
|
"epoch": 45.56, |
|
"learning_rate": 3.6402366863905324e-07, |
|
"loss": 0.4626, |
|
"step": 7790 |
|
}, |
|
{ |
|
"epoch": 45.61, |
|
"learning_rate": 3.592899408284024e-07, |
|
"loss": 0.4369, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 45.67, |
|
"learning_rate": 3.545562130177515e-07, |
|
"loss": 0.4328, |
|
"step": 7810 |
|
}, |
|
{ |
|
"epoch": 45.73, |
|
"learning_rate": 3.4982248520710057e-07, |
|
"loss": 0.4375, |
|
"step": 7820 |
|
}, |
|
{ |
|
"epoch": 45.79, |
|
"learning_rate": 3.450887573964497e-07, |
|
"loss": 0.4648, |
|
"step": 7830 |
|
}, |
|
{ |
|
"epoch": 45.85, |
|
"learning_rate": 3.403550295857988e-07, |
|
"loss": 0.4523, |
|
"step": 7840 |
|
}, |
|
{ |
|
"epoch": 45.91, |
|
"learning_rate": 3.356213017751479e-07, |
|
"loss": 0.4385, |
|
"step": 7850 |
|
}, |
|
{ |
|
"epoch": 45.96, |
|
"learning_rate": 3.30887573964497e-07, |
|
"loss": 0.4214, |
|
"step": 7860 |
|
}, |
|
{ |
|
"epoch": 46.0, |
|
"eval_loss": 0.17314769327640533, |
|
"eval_runtime": 206.986, |
|
"eval_samples_per_second": 5.88, |
|
"eval_steps_per_second": 0.739, |
|
"eval_wer": 0.09492098916525683, |
|
"step": 7866 |
|
}, |
|
{ |
|
"epoch": 46.02, |
|
"learning_rate": 3.2615384615384614e-07, |
|
"loss": 0.4572, |
|
"step": 7870 |
|
}, |
|
{ |
|
"epoch": 46.08, |
|
"learning_rate": 3.214201183431953e-07, |
|
"loss": 0.4638, |
|
"step": 7880 |
|
}, |
|
{ |
|
"epoch": 46.14, |
|
"learning_rate": 3.166863905325444e-07, |
|
"loss": 0.4389, |
|
"step": 7890 |
|
}, |
|
{ |
|
"epoch": 46.2, |
|
"learning_rate": 3.1195266272189347e-07, |
|
"loss": 0.434, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 46.26, |
|
"learning_rate": 3.0721893491124256e-07, |
|
"loss": 0.4489, |
|
"step": 7910 |
|
}, |
|
{ |
|
"epoch": 46.32, |
|
"learning_rate": 3.024852071005917e-07, |
|
"loss": 0.4474, |
|
"step": 7920 |
|
}, |
|
{ |
|
"epoch": 46.37, |
|
"learning_rate": 2.977514792899408e-07, |
|
"loss": 0.4682, |
|
"step": 7930 |
|
}, |
|
{ |
|
"epoch": 46.43, |
|
"learning_rate": 2.930177514792899e-07, |
|
"loss": 0.4335, |
|
"step": 7940 |
|
}, |
|
{ |
|
"epoch": 46.49, |
|
"learning_rate": 2.8828402366863904e-07, |
|
"loss": 0.4175, |
|
"step": 7950 |
|
}, |
|
{ |
|
"epoch": 46.55, |
|
"learning_rate": 2.835502958579882e-07, |
|
"loss": 0.4691, |
|
"step": 7960 |
|
}, |
|
{ |
|
"epoch": 46.61, |
|
"learning_rate": 2.788165680473373e-07, |
|
"loss": 0.4516, |
|
"step": 7970 |
|
}, |
|
{ |
|
"epoch": 46.67, |
|
"learning_rate": 2.7408284023668637e-07, |
|
"loss": 0.4433, |
|
"step": 7980 |
|
}, |
|
{ |
|
"epoch": 46.72, |
|
"learning_rate": 2.6934911242603546e-07, |
|
"loss": 0.444, |
|
"step": 7990 |
|
}, |
|
{ |
|
"epoch": 46.78, |
|
"learning_rate": 2.646153846153846e-07, |
|
"loss": 0.4594, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 46.84, |
|
"learning_rate": 2.598816568047337e-07, |
|
"loss": 0.4479, |
|
"step": 8010 |
|
}, |
|
{ |
|
"epoch": 46.9, |
|
"learning_rate": 2.5514792899408285e-07, |
|
"loss": 0.4384, |
|
"step": 8020 |
|
}, |
|
{ |
|
"epoch": 46.96, |
|
"learning_rate": 2.5041420118343194e-07, |
|
"loss": 0.4358, |
|
"step": 8030 |
|
}, |
|
{ |
|
"epoch": 47.0, |
|
"eval_loss": 0.17378680408000946, |
|
"eval_runtime": 208.3124, |
|
"eval_samples_per_second": 5.842, |
|
"eval_steps_per_second": 0.734, |
|
"eval_wer": 0.09524495158561606, |
|
"step": 8037 |
|
}, |
|
{ |
|
"epoch": 47.02, |
|
"learning_rate": 2.4568047337278104e-07, |
|
"loss": 0.4527, |
|
"step": 8040 |
|
}, |
|
{ |
|
"epoch": 47.08, |
|
"learning_rate": 2.409467455621302e-07, |
|
"loss": 0.4558, |
|
"step": 8050 |
|
}, |
|
{ |
|
"epoch": 47.13, |
|
"learning_rate": 2.3621301775147927e-07, |
|
"loss": 0.4502, |
|
"step": 8060 |
|
}, |
|
{ |
|
"epoch": 47.19, |
|
"learning_rate": 2.314792899408284e-07, |
|
"loss": 0.4325, |
|
"step": 8070 |
|
}, |
|
{ |
|
"epoch": 47.25, |
|
"learning_rate": 2.267455621301775e-07, |
|
"loss": 0.4368, |
|
"step": 8080 |
|
}, |
|
{ |
|
"epoch": 47.31, |
|
"learning_rate": 2.220118343195266e-07, |
|
"loss": 0.4705, |
|
"step": 8090 |
|
}, |
|
{ |
|
"epoch": 47.37, |
|
"learning_rate": 2.1727810650887573e-07, |
|
"loss": 0.4587, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 47.43, |
|
"learning_rate": 2.1254437869822484e-07, |
|
"loss": 0.4383, |
|
"step": 8110 |
|
}, |
|
{ |
|
"epoch": 47.49, |
|
"learning_rate": 2.0781065088757396e-07, |
|
"loss": 0.4363, |
|
"step": 8120 |
|
}, |
|
{ |
|
"epoch": 47.54, |
|
"learning_rate": 2.0307692307692306e-07, |
|
"loss": 0.4443, |
|
"step": 8130 |
|
}, |
|
{ |
|
"epoch": 47.6, |
|
"learning_rate": 1.983431952662722e-07, |
|
"loss": 0.4583, |
|
"step": 8140 |
|
}, |
|
{ |
|
"epoch": 47.66, |
|
"learning_rate": 1.936094674556213e-07, |
|
"loss": 0.4403, |
|
"step": 8150 |
|
}, |
|
{ |
|
"epoch": 47.72, |
|
"learning_rate": 1.8887573964497041e-07, |
|
"loss": 0.4406, |
|
"step": 8160 |
|
}, |
|
{ |
|
"epoch": 47.78, |
|
"learning_rate": 1.841420118343195e-07, |
|
"loss": 0.4729, |
|
"step": 8170 |
|
}, |
|
{ |
|
"epoch": 47.84, |
|
"learning_rate": 1.7940828402366865e-07, |
|
"loss": 0.4675, |
|
"step": 8180 |
|
}, |
|
{ |
|
"epoch": 47.89, |
|
"learning_rate": 1.7467455621301775e-07, |
|
"loss": 0.4463, |
|
"step": 8190 |
|
}, |
|
{ |
|
"epoch": 47.95, |
|
"learning_rate": 1.6994082840236684e-07, |
|
"loss": 0.4347, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"eval_loss": 0.17417344450950623, |
|
"eval_runtime": 206.5973, |
|
"eval_samples_per_second": 5.891, |
|
"eval_steps_per_second": 0.741, |
|
"eval_wer": 0.09556891400597531, |
|
"step": 8208 |
|
}, |
|
{ |
|
"epoch": 48.01, |
|
"learning_rate": 1.6520710059171596e-07, |
|
"loss": 0.4382, |
|
"step": 8210 |
|
}, |
|
{ |
|
"epoch": 48.07, |
|
"learning_rate": 1.6047337278106508e-07, |
|
"loss": 0.4637, |
|
"step": 8220 |
|
}, |
|
{ |
|
"epoch": 48.13, |
|
"learning_rate": 1.557396449704142e-07, |
|
"loss": 0.4703, |
|
"step": 8230 |
|
}, |
|
{ |
|
"epoch": 48.19, |
|
"learning_rate": 1.510059171597633e-07, |
|
"loss": 0.4446, |
|
"step": 8240 |
|
}, |
|
{ |
|
"epoch": 48.25, |
|
"learning_rate": 1.4627218934911244e-07, |
|
"loss": 0.4281, |
|
"step": 8250 |
|
}, |
|
{ |
|
"epoch": 48.3, |
|
"learning_rate": 1.4153846153846153e-07, |
|
"loss": 0.453, |
|
"step": 8260 |
|
}, |
|
{ |
|
"epoch": 48.36, |
|
"learning_rate": 1.3680473372781065e-07, |
|
"loss": 0.4693, |
|
"step": 8270 |
|
}, |
|
{ |
|
"epoch": 48.42, |
|
"learning_rate": 1.3207100591715974e-07, |
|
"loss": 0.4534, |
|
"step": 8280 |
|
}, |
|
{ |
|
"epoch": 48.48, |
|
"learning_rate": 1.273372781065089e-07, |
|
"loss": 0.4243, |
|
"step": 8290 |
|
}, |
|
{ |
|
"epoch": 48.54, |
|
"learning_rate": 1.2260355029585798e-07, |
|
"loss": 0.4559, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 48.6, |
|
"learning_rate": 1.1786982248520709e-07, |
|
"loss": 0.4515, |
|
"step": 8310 |
|
}, |
|
{ |
|
"epoch": 48.65, |
|
"learning_rate": 1.131360946745562e-07, |
|
"loss": 0.4362, |
|
"step": 8320 |
|
}, |
|
{ |
|
"epoch": 48.71, |
|
"learning_rate": 1.0840236686390531e-07, |
|
"loss": 0.4602, |
|
"step": 8330 |
|
}, |
|
{ |
|
"epoch": 48.77, |
|
"learning_rate": 1.0366863905325443e-07, |
|
"loss": 0.465, |
|
"step": 8340 |
|
}, |
|
{ |
|
"epoch": 48.83, |
|
"learning_rate": 9.893491124260355e-08, |
|
"loss": 0.4431, |
|
"step": 8350 |
|
}, |
|
{ |
|
"epoch": 48.89, |
|
"learning_rate": 9.420118343195266e-08, |
|
"loss": 0.4438, |
|
"step": 8360 |
|
}, |
|
{ |
|
"epoch": 48.95, |
|
"learning_rate": 8.946745562130178e-08, |
|
"loss": 0.4032, |
|
"step": 8370 |
|
}, |
|
{ |
|
"epoch": 49.0, |
|
"eval_loss": 0.17385847866535187, |
|
"eval_runtime": 207.4304, |
|
"eval_samples_per_second": 5.867, |
|
"eval_steps_per_second": 0.738, |
|
"eval_wer": 0.09560490983045966, |
|
"step": 8379 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 8.473372781065088e-08, |
|
"loss": 0.4554, |
|
"step": 8380 |
|
}, |
|
{ |
|
"epoch": 49.06, |
|
"learning_rate": 8e-08, |
|
"loss": 0.4545, |
|
"step": 8390 |
|
}, |
|
{ |
|
"epoch": 49.12, |
|
"learning_rate": 7.526627218934911e-08, |
|
"loss": 0.4694, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 49.18, |
|
"learning_rate": 7.053254437869823e-08, |
|
"loss": 0.4457, |
|
"step": 8410 |
|
}, |
|
{ |
|
"epoch": 49.24, |
|
"learning_rate": 6.579881656804733e-08, |
|
"loss": 0.4537, |
|
"step": 8420 |
|
}, |
|
{ |
|
"epoch": 49.3, |
|
"learning_rate": 6.106508875739644e-08, |
|
"loss": 0.4499, |
|
"step": 8430 |
|
}, |
|
{ |
|
"epoch": 49.36, |
|
"learning_rate": 5.633136094674556e-08, |
|
"loss": 0.4518, |
|
"step": 8440 |
|
}, |
|
{ |
|
"epoch": 49.41, |
|
"learning_rate": 5.159763313609467e-08, |
|
"loss": 0.4499, |
|
"step": 8450 |
|
}, |
|
{ |
|
"epoch": 49.47, |
|
"learning_rate": 4.6863905325443784e-08, |
|
"loss": 0.4264, |
|
"step": 8460 |
|
}, |
|
{ |
|
"epoch": 49.53, |
|
"learning_rate": 4.21301775147929e-08, |
|
"loss": 0.4585, |
|
"step": 8470 |
|
}, |
|
{ |
|
"epoch": 49.59, |
|
"learning_rate": 3.739644970414201e-08, |
|
"loss": 0.46, |
|
"step": 8480 |
|
}, |
|
{ |
|
"epoch": 49.65, |
|
"learning_rate": 3.266272189349112e-08, |
|
"loss": 0.4407, |
|
"step": 8490 |
|
}, |
|
{ |
|
"epoch": 49.71, |
|
"learning_rate": 2.7928994082840235e-08, |
|
"loss": 0.4322, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 49.77, |
|
"learning_rate": 2.3195266272189348e-08, |
|
"loss": 0.4504, |
|
"step": 8510 |
|
}, |
|
{ |
|
"epoch": 49.82, |
|
"learning_rate": 1.846153846153846e-08, |
|
"loss": 0.4713, |
|
"step": 8520 |
|
}, |
|
{ |
|
"epoch": 49.88, |
|
"learning_rate": 1.3727810650887574e-08, |
|
"loss": 0.4376, |
|
"step": 8530 |
|
}, |
|
{ |
|
"epoch": 49.94, |
|
"learning_rate": 8.994082840236686e-09, |
|
"loss": 0.4331, |
|
"step": 8540 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"learning_rate": 4.260355029585798e-09, |
|
"loss": 0.441, |
|
"step": 8550 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"eval_loss": 0.17365868389606476, |
|
"eval_runtime": 207.2082, |
|
"eval_samples_per_second": 5.873, |
|
"eval_steps_per_second": 0.738, |
|
"eval_wer": 0.0957488931283971, |
|
"step": 8550 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"step": 8550, |
|
"total_flos": 2.398969462266787e+20, |
|
"train_loss": 0.4461798803987559, |
|
"train_runtime": 152968.1729, |
|
"train_samples_per_second": 3.578, |
|
"train_steps_per_second": 0.056 |
|
} |
|
], |
|
"max_steps": 8550, |
|
"num_train_epochs": 50, |
|
"total_flos": 2.398969462266787e+20, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|