|
{ |
|
"best_metric": 0.221947580575943, |
|
"best_model_checkpoint": "ai-light-dance_singing4_ft_wav2vec2-large-xlsr-53-5gram-v4-2-1/checkpoint-4536", |
|
"epoch": 99.99653979238754, |
|
"global_step": 7200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 7.2e-08, |
|
"loss": 0.4621, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.5199999999999998e-07, |
|
"loss": 0.4646, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 2.32e-07, |
|
"loss": 0.4476, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 3.12e-07, |
|
"loss": 0.4621, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 3.92e-07, |
|
"loss": 0.4377, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 4.64e-07, |
|
"loss": 0.4635, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 5.44e-07, |
|
"loss": 0.4531, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.23165254294872284, |
|
"eval_runtime": 126.6094, |
|
"eval_samples_per_second": 4.202, |
|
"eval_steps_per_second": 0.529, |
|
"eval_wer": 0.10214051552355853, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 6.24e-07, |
|
"loss": 0.4717, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 7.04e-07, |
|
"loss": 0.4522, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 7.84e-07, |
|
"loss": 0.4412, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 8.639999999999999e-07, |
|
"loss": 0.4597, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 9.439999999999999e-07, |
|
"loss": 0.4595, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 1.024e-06, |
|
"loss": 0.4521, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 1.1040000000000001e-06, |
|
"loss": 0.4479, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.23347443342208862, |
|
"eval_runtime": 124.9327, |
|
"eval_samples_per_second": 4.258, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.10136915857813203, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 1.1839999999999998e-06, |
|
"loss": 0.4792, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 1.2639999999999999e-06, |
|
"loss": 0.4494, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 1.344e-06, |
|
"loss": 0.4469, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 1.4239999999999998e-06, |
|
"loss": 0.4624, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 1.504e-06, |
|
"loss": 0.4364, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 1.584e-06, |
|
"loss": 0.4601, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 1.6639999999999999e-06, |
|
"loss": 0.4475, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.23399044573307037, |
|
"eval_runtime": 125.3196, |
|
"eval_samples_per_second": 4.245, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.10001928392363567, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 1.744e-06, |
|
"loss": 0.4664, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"learning_rate": 1.824e-06, |
|
"loss": 0.4455, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 1.904e-06, |
|
"loss": 0.4482, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 1.984e-06, |
|
"loss": 0.451, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 2.064e-06, |
|
"loss": 0.4502, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 2.144e-06, |
|
"loss": 0.4504, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 2.2240000000000002e-06, |
|
"loss": 0.4432, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 0.23715920746326447, |
|
"eval_runtime": 124.7994, |
|
"eval_samples_per_second": 4.263, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.09931220672366138, |
|
"step": 288 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 2.304e-06, |
|
"loss": 0.47, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 4.17, |
|
"learning_rate": 2.384e-06, |
|
"loss": 0.435, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 2.464e-06, |
|
"loss": 0.4677, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 4.44, |
|
"learning_rate": 2.544e-06, |
|
"loss": 0.4356, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 4.58, |
|
"learning_rate": 2.624e-06, |
|
"loss": 0.4442, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 4.72, |
|
"learning_rate": 2.704e-06, |
|
"loss": 0.4308, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 2.7759999999999998e-06, |
|
"loss": 0.4478, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 2.856e-06, |
|
"loss": 0.447, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 0.2350255399942398, |
|
"eval_runtime": 125.4131, |
|
"eval_samples_per_second": 4.242, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.10079064086906216, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 5.14, |
|
"learning_rate": 2.936e-06, |
|
"loss": 0.4296, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 5.28, |
|
"learning_rate": 3.016e-06, |
|
"loss": 0.457, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 5.42, |
|
"learning_rate": 3.096e-06, |
|
"loss": 0.4365, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 5.55, |
|
"learning_rate": 3.176e-06, |
|
"loss": 0.4591, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 5.69, |
|
"learning_rate": 3.256e-06, |
|
"loss": 0.4347, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 5.83, |
|
"learning_rate": 3.336e-06, |
|
"loss": 0.4483, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"learning_rate": 3.4159999999999996e-06, |
|
"loss": 0.4318, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 0.23317080736160278, |
|
"eval_runtime": 126.3474, |
|
"eval_samples_per_second": 4.211, |
|
"eval_steps_per_second": 0.53, |
|
"eval_wer": 0.09892652825094812, |
|
"step": 432 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"learning_rate": 3.4959999999999996e-06, |
|
"loss": 0.4901, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 6.25, |
|
"learning_rate": 3.5759999999999997e-06, |
|
"loss": 0.4506, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 6.39, |
|
"learning_rate": 3.656e-06, |
|
"loss": 0.426, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 6.53, |
|
"learning_rate": 3.736e-06, |
|
"loss": 0.454, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 6.66, |
|
"learning_rate": 3.8159999999999995e-06, |
|
"loss": 0.4333, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 6.8, |
|
"learning_rate": 3.896e-06, |
|
"loss": 0.4458, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 6.94, |
|
"learning_rate": 3.976e-06, |
|
"loss": 0.4162, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 0.23383821547031403, |
|
"eval_runtime": 126.1137, |
|
"eval_samples_per_second": 4.218, |
|
"eval_steps_per_second": 0.531, |
|
"eval_wer": 0.10021212315999228, |
|
"step": 504 |
|
}, |
|
{ |
|
"epoch": 7.08, |
|
"learning_rate": 3.995820895522388e-06, |
|
"loss": 0.4629, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 7.22, |
|
"learning_rate": 3.989850746268656e-06, |
|
"loss": 0.4289, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 7.36, |
|
"learning_rate": 3.9838805970149255e-06, |
|
"loss": 0.4559, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 7.5, |
|
"learning_rate": 3.977910447761194e-06, |
|
"loss": 0.4399, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 7.64, |
|
"learning_rate": 3.971940298507463e-06, |
|
"loss": 0.4251, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 7.78, |
|
"learning_rate": 3.965970149253731e-06, |
|
"loss": 0.4426, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 7.91, |
|
"learning_rate": 3.96e-06, |
|
"loss": 0.4365, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 0.23214896023273468, |
|
"eval_runtime": 126.1399, |
|
"eval_samples_per_second": 4.218, |
|
"eval_steps_per_second": 0.531, |
|
"eval_wer": 0.09899080799640034, |
|
"step": 576 |
|
}, |
|
{ |
|
"epoch": 8.06, |
|
"learning_rate": 3.9540298507462685e-06, |
|
"loss": 0.4666, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 8.19, |
|
"learning_rate": 3.948059701492537e-06, |
|
"loss": 0.4234, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 8.33, |
|
"learning_rate": 3.942089552238806e-06, |
|
"loss": 0.4545, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 8.47, |
|
"learning_rate": 3.936119402985075e-06, |
|
"loss": 0.4237, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 8.61, |
|
"learning_rate": 3.930149253731343e-06, |
|
"loss": 0.425, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 8.75, |
|
"learning_rate": 3.9241791044776114e-06, |
|
"loss": 0.441, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 8.89, |
|
"learning_rate": 3.9182089552238806e-06, |
|
"loss": 0.4318, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 0.23131322860717773, |
|
"eval_runtime": 126.2911, |
|
"eval_samples_per_second": 4.212, |
|
"eval_steps_per_second": 0.531, |
|
"eval_wer": 0.09924792697820917, |
|
"step": 648 |
|
}, |
|
{ |
|
"epoch": 9.03, |
|
"learning_rate": 3.912238805970149e-06, |
|
"loss": 0.4601, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 9.17, |
|
"learning_rate": 3.90686567164179e-06, |
|
"loss": 0.4201, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 9.3, |
|
"learning_rate": 3.9008955223880595e-06, |
|
"loss": 0.4424, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 9.44, |
|
"learning_rate": 3.894925373134329e-06, |
|
"loss": 0.4252, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 9.58, |
|
"learning_rate": 3.888955223880597e-06, |
|
"loss": 0.4373, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 9.72, |
|
"learning_rate": 3.882985074626865e-06, |
|
"loss": 0.4415, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 9.86, |
|
"learning_rate": 3.877014925373134e-06, |
|
"loss": 0.4281, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 3.8710447761194025e-06, |
|
"loss": 0.4513, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_loss": 0.23356570303440094, |
|
"eval_runtime": 125.575, |
|
"eval_samples_per_second": 4.237, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.0994407662145658, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 10.14, |
|
"learning_rate": 3.865074626865672e-06, |
|
"loss": 0.4331, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 10.28, |
|
"learning_rate": 3.85910447761194e-06, |
|
"loss": 0.4264, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 10.42, |
|
"learning_rate": 3.853134328358209e-06, |
|
"loss": 0.4301, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 10.55, |
|
"learning_rate": 3.847761194029851e-06, |
|
"loss": 0.4435, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 10.69, |
|
"learning_rate": 3.841791044776119e-06, |
|
"loss": 0.4203, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 10.83, |
|
"learning_rate": 3.835820895522388e-06, |
|
"loss": 0.4418, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 10.97, |
|
"learning_rate": 3.829850746268656e-06, |
|
"loss": 0.4257, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"eval_loss": 0.23102988302707672, |
|
"eval_runtime": 125.7826, |
|
"eval_samples_per_second": 4.23, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09815517130552164, |
|
"step": 792 |
|
}, |
|
{ |
|
"epoch": 11.11, |
|
"learning_rate": 3.823880597014925e-06, |
|
"loss": 0.4345, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 11.25, |
|
"learning_rate": 3.8179104477611936e-06, |
|
"loss": 0.4446, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 11.39, |
|
"learning_rate": 3.8119402985074623e-06, |
|
"loss": 0.4121, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 11.53, |
|
"learning_rate": 3.8059701492537314e-06, |
|
"loss": 0.443, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 11.66, |
|
"learning_rate": 3.7999999999999996e-06, |
|
"loss": 0.4219, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 11.8, |
|
"learning_rate": 3.7940298507462683e-06, |
|
"loss": 0.4513, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 11.94, |
|
"learning_rate": 3.7880597014925374e-06, |
|
"loss": 0.418, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"eval_loss": 0.23161809146404266, |
|
"eval_runtime": 125.0189, |
|
"eval_samples_per_second": 4.255, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09886224850549592, |
|
"step": 864 |
|
}, |
|
{ |
|
"epoch": 12.08, |
|
"learning_rate": 3.7820895522388057e-06, |
|
"loss": 0.4422, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 12.22, |
|
"learning_rate": 3.7761194029850743e-06, |
|
"loss": 0.4359, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 12.36, |
|
"learning_rate": 3.7701492537313435e-06, |
|
"loss": 0.4273, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 12.5, |
|
"learning_rate": 3.7641791044776117e-06, |
|
"loss": 0.4492, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 12.64, |
|
"learning_rate": 3.7582089552238804e-06, |
|
"loss": 0.4029, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 12.78, |
|
"learning_rate": 3.7522388059701495e-06, |
|
"loss": 0.4208, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 12.91, |
|
"learning_rate": 3.7462686567164178e-06, |
|
"loss": 0.4122, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"eval_loss": 0.23408491909503937, |
|
"eval_runtime": 124.3203, |
|
"eval_samples_per_second": 4.279, |
|
"eval_steps_per_second": 0.539, |
|
"eval_wer": 0.0971266953782863, |
|
"step": 936 |
|
}, |
|
{ |
|
"epoch": 13.06, |
|
"learning_rate": 3.7402985074626864e-06, |
|
"loss": 0.4455, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 13.19, |
|
"learning_rate": 3.7343283582089547e-06, |
|
"loss": 0.425, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 13.33, |
|
"learning_rate": 3.728358208955224e-06, |
|
"loss": 0.433, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 13.47, |
|
"learning_rate": 3.7223880597014925e-06, |
|
"loss": 0.4276, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 13.61, |
|
"learning_rate": 3.7164179104477607e-06, |
|
"loss": 0.4283, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 13.75, |
|
"learning_rate": 3.71044776119403e-06, |
|
"loss": 0.426, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 13.89, |
|
"learning_rate": 3.7044776119402985e-06, |
|
"loss": 0.4265, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"eval_loss": 0.23222699761390686, |
|
"eval_runtime": 124.1252, |
|
"eval_samples_per_second": 4.286, |
|
"eval_steps_per_second": 0.54, |
|
"eval_wer": 0.09918364723275695, |
|
"step": 1008 |
|
}, |
|
{ |
|
"epoch": 14.03, |
|
"learning_rate": 3.698507462686567e-06, |
|
"loss": 0.4399, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 14.17, |
|
"learning_rate": 3.692537313432836e-06, |
|
"loss": 0.4244, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 14.3, |
|
"learning_rate": 3.6865671641791046e-06, |
|
"loss": 0.4149, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 14.44, |
|
"learning_rate": 3.680597014925373e-06, |
|
"loss": 0.4164, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 14.58, |
|
"learning_rate": 3.6746268656716415e-06, |
|
"loss": 0.4284, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 14.72, |
|
"learning_rate": 3.66865671641791e-06, |
|
"loss": 0.4111, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 14.86, |
|
"learning_rate": 3.662686567164179e-06, |
|
"loss": 0.4195, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"learning_rate": 3.6567164179104476e-06, |
|
"loss": 0.4477, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"eval_loss": 0.23339033126831055, |
|
"eval_runtime": 124.9182, |
|
"eval_samples_per_second": 4.259, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.0986694092691393, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 15.14, |
|
"learning_rate": 3.6507462686567162e-06, |
|
"loss": 0.4251, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 15.28, |
|
"learning_rate": 3.644776119402985e-06, |
|
"loss": 0.4115, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 15.42, |
|
"learning_rate": 3.6388059701492536e-06, |
|
"loss": 0.4181, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 15.55, |
|
"learning_rate": 3.6328358208955223e-06, |
|
"loss": 0.4333, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 15.69, |
|
"learning_rate": 3.626865671641791e-06, |
|
"loss": 0.4153, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 15.83, |
|
"learning_rate": 3.6208955223880597e-06, |
|
"loss": 0.4348, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 15.97, |
|
"learning_rate": 3.614925373134328e-06, |
|
"loss": 0.4023, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"eval_loss": 0.23507945239543915, |
|
"eval_runtime": 124.2611, |
|
"eval_samples_per_second": 4.281, |
|
"eval_steps_per_second": 0.539, |
|
"eval_wer": 0.0971266953782863, |
|
"step": 1152 |
|
}, |
|
{ |
|
"epoch": 16.11, |
|
"learning_rate": 3.608955223880597e-06, |
|
"loss": 0.4396, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 16.25, |
|
"learning_rate": 3.6029850746268653e-06, |
|
"loss": 0.433, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 16.39, |
|
"learning_rate": 3.597014925373134e-06, |
|
"loss": 0.4088, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 16.53, |
|
"learning_rate": 3.591044776119403e-06, |
|
"loss": 0.4323, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 16.66, |
|
"learning_rate": 3.5850746268656713e-06, |
|
"loss": 0.3976, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 16.8, |
|
"learning_rate": 3.57910447761194e-06, |
|
"loss": 0.4169, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 16.94, |
|
"learning_rate": 3.573134328358209e-06, |
|
"loss": 0.4095, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"eval_loss": 0.23035521805286407, |
|
"eval_runtime": 124.8202, |
|
"eval_samples_per_second": 4.262, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.09770521308735618, |
|
"step": 1224 |
|
}, |
|
{ |
|
"epoch": 17.08, |
|
"learning_rate": 3.5671641791044774e-06, |
|
"loss": 0.4468, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 17.22, |
|
"learning_rate": 3.561194029850746e-06, |
|
"loss": 0.4146, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 17.36, |
|
"learning_rate": 3.5552238805970147e-06, |
|
"loss": 0.422, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 17.5, |
|
"learning_rate": 3.5492537313432834e-06, |
|
"loss": 0.4375, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 17.64, |
|
"learning_rate": 3.543283582089552e-06, |
|
"loss": 0.4114, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 17.78, |
|
"learning_rate": 3.537313432835821e-06, |
|
"loss": 0.4268, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 17.91, |
|
"learning_rate": 3.5313432835820895e-06, |
|
"loss": 0.42, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"eval_loss": 0.23128649592399597, |
|
"eval_runtime": 124.8652, |
|
"eval_samples_per_second": 4.261, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.09757665359645176, |
|
"step": 1296 |
|
}, |
|
{ |
|
"epoch": 18.06, |
|
"learning_rate": 3.525373134328358e-06, |
|
"loss": 0.4477, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 18.19, |
|
"learning_rate": 3.5194029850746264e-06, |
|
"loss": 0.3985, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 18.33, |
|
"learning_rate": 3.5134328358208955e-06, |
|
"loss": 0.4244, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 18.47, |
|
"learning_rate": 3.507462686567164e-06, |
|
"loss": 0.4056, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 18.61, |
|
"learning_rate": 3.5014925373134325e-06, |
|
"loss": 0.4266, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 18.75, |
|
"learning_rate": 3.495522388059701e-06, |
|
"loss": 0.4456, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 18.89, |
|
"learning_rate": 3.4895522388059702e-06, |
|
"loss": 0.3988, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"eval_loss": 0.22993487119674683, |
|
"eval_runtime": 124.5356, |
|
"eval_samples_per_second": 4.272, |
|
"eval_steps_per_second": 0.538, |
|
"eval_wer": 0.09841229028733046, |
|
"step": 1368 |
|
}, |
|
{ |
|
"epoch": 19.03, |
|
"learning_rate": 3.4835820895522385e-06, |
|
"loss": 0.4348, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 19.17, |
|
"learning_rate": 3.477611940298507e-06, |
|
"loss": 0.3964, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 19.3, |
|
"learning_rate": 3.4716417910447763e-06, |
|
"loss": 0.4333, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 19.44, |
|
"learning_rate": 3.4656716417910446e-06, |
|
"loss": 0.4075, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 19.58, |
|
"learning_rate": 3.4597014925373132e-06, |
|
"loss": 0.4262, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 19.72, |
|
"learning_rate": 3.453731343283582e-06, |
|
"loss": 0.4285, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 19.86, |
|
"learning_rate": 3.4477611940298506e-06, |
|
"loss": 0.4238, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 3.4417910447761193e-06, |
|
"loss": 0.4078, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"eval_loss": 0.23102743923664093, |
|
"eval_runtime": 124.8343, |
|
"eval_samples_per_second": 4.262, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.09699813588738189, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 20.14, |
|
"learning_rate": 3.4358208955223875e-06, |
|
"loss": 0.4065, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 20.28, |
|
"learning_rate": 3.4298507462686566e-06, |
|
"loss": 0.4342, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 20.42, |
|
"learning_rate": 3.4238805970149253e-06, |
|
"loss": 0.407, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 20.55, |
|
"learning_rate": 3.4179104477611936e-06, |
|
"loss": 0.4357, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 20.69, |
|
"learning_rate": 3.4119402985074627e-06, |
|
"loss": 0.4246, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 20.83, |
|
"learning_rate": 3.4059701492537314e-06, |
|
"loss": 0.4308, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 20.97, |
|
"learning_rate": 3.3999999999999996e-06, |
|
"loss": 0.4131, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"eval_loss": 0.22929777204990387, |
|
"eval_runtime": 124.8341, |
|
"eval_samples_per_second": 4.262, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.10066208137815774, |
|
"step": 1512 |
|
}, |
|
{ |
|
"epoch": 21.11, |
|
"learning_rate": 3.3940298507462687e-06, |
|
"loss": 0.4298, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 21.25, |
|
"learning_rate": 3.388059701492537e-06, |
|
"loss": 0.4325, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 21.39, |
|
"learning_rate": 3.3820895522388057e-06, |
|
"loss": 0.4119, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 21.53, |
|
"learning_rate": 3.3761194029850748e-06, |
|
"loss": 0.4125, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 21.66, |
|
"learning_rate": 3.370149253731343e-06, |
|
"loss": 0.4056, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 21.8, |
|
"learning_rate": 3.3641791044776117e-06, |
|
"loss": 0.4231, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 21.94, |
|
"learning_rate": 3.3582089552238804e-06, |
|
"loss": 0.4209, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"eval_loss": 0.23128026723861694, |
|
"eval_runtime": 124.6598, |
|
"eval_samples_per_second": 4.268, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.09982644468727904, |
|
"step": 1584 |
|
}, |
|
{ |
|
"epoch": 22.08, |
|
"learning_rate": 3.352238805970149e-06, |
|
"loss": 0.4451, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 22.22, |
|
"learning_rate": 3.3462686567164178e-06, |
|
"loss": 0.4075, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 22.36, |
|
"learning_rate": 3.3402985074626865e-06, |
|
"loss": 0.3901, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 22.5, |
|
"learning_rate": 3.334328358208955e-06, |
|
"loss": 0.4239, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 22.64, |
|
"learning_rate": 3.328358208955224e-06, |
|
"loss": 0.4078, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 22.78, |
|
"learning_rate": 3.3223880597014925e-06, |
|
"loss": 0.4088, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 22.91, |
|
"learning_rate": 3.316417910447761e-06, |
|
"loss": 0.3931, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"eval_loss": 0.23513072729110718, |
|
"eval_runtime": 124.6587, |
|
"eval_samples_per_second": 4.268, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.10136915857813203, |
|
"step": 1656 |
|
}, |
|
{ |
|
"epoch": 23.06, |
|
"learning_rate": 3.31044776119403e-06, |
|
"loss": 0.4395, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 23.19, |
|
"learning_rate": 3.304477611940298e-06, |
|
"loss": 0.4026, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 23.33, |
|
"learning_rate": 3.298507462686567e-06, |
|
"loss": 0.409, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 23.47, |
|
"learning_rate": 3.292537313432836e-06, |
|
"loss": 0.4048, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 23.61, |
|
"learning_rate": 3.286567164179104e-06, |
|
"loss": 0.4109, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 23.75, |
|
"learning_rate": 3.280597014925373e-06, |
|
"loss": 0.4106, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 23.89, |
|
"learning_rate": 3.274626865671642e-06, |
|
"loss": 0.406, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 24.0, |
|
"eval_loss": 0.2336040586233139, |
|
"eval_runtime": 125.2143, |
|
"eval_samples_per_second": 4.249, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09924792697820917, |
|
"step": 1728 |
|
}, |
|
{ |
|
"epoch": 24.03, |
|
"learning_rate": 3.2686567164179102e-06, |
|
"loss": 0.4278, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 24.17, |
|
"learning_rate": 3.262686567164179e-06, |
|
"loss": 0.4007, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 24.3, |
|
"learning_rate": 3.256716417910448e-06, |
|
"loss": 0.4044, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 24.44, |
|
"learning_rate": 3.2507462686567163e-06, |
|
"loss": 0.4042, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 24.58, |
|
"learning_rate": 3.244776119402985e-06, |
|
"loss": 0.4142, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 24.72, |
|
"learning_rate": 3.238805970149253e-06, |
|
"loss": 0.4143, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 24.86, |
|
"learning_rate": 3.2328358208955223e-06, |
|
"loss": 0.4181, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"learning_rate": 3.226865671641791e-06, |
|
"loss": 0.3998, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"eval_loss": 0.23545674979686737, |
|
"eval_runtime": 125.3467, |
|
"eval_samples_per_second": 4.244, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.10091920035996657, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 25.14, |
|
"learning_rate": 3.2208955223880593e-06, |
|
"loss": 0.419, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 25.28, |
|
"learning_rate": 3.2149253731343284e-06, |
|
"loss": 0.4179, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 25.42, |
|
"learning_rate": 3.208955223880597e-06, |
|
"loss": 0.3833, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 25.55, |
|
"learning_rate": 3.2029850746268653e-06, |
|
"loss": 0.4144, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 25.69, |
|
"learning_rate": 3.1970149253731344e-06, |
|
"loss": 0.3931, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 25.83, |
|
"learning_rate": 3.191044776119403e-06, |
|
"loss": 0.4065, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 25.97, |
|
"learning_rate": 3.1850746268656713e-06, |
|
"loss": 0.4197, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 26.0, |
|
"eval_loss": 0.2346036732196808, |
|
"eval_runtime": 125.3587, |
|
"eval_samples_per_second": 4.244, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09956932570547021, |
|
"step": 1872 |
|
}, |
|
{ |
|
"epoch": 26.11, |
|
"learning_rate": 3.17910447761194e-06, |
|
"loss": 0.4426, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 26.25, |
|
"learning_rate": 3.1731343283582087e-06, |
|
"loss": 0.429, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 26.39, |
|
"learning_rate": 3.1671641791044774e-06, |
|
"loss": 0.4249, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 26.53, |
|
"learning_rate": 3.161194029850746e-06, |
|
"loss": 0.4435, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 26.66, |
|
"learning_rate": 3.1552238805970148e-06, |
|
"loss": 0.4441, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 26.8, |
|
"learning_rate": 3.1492537313432834e-06, |
|
"loss": 0.4313, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 26.94, |
|
"learning_rate": 3.143283582089552e-06, |
|
"loss": 0.4289, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 27.0, |
|
"eval_loss": 0.22830109298229218, |
|
"eval_runtime": 125.702, |
|
"eval_samples_per_second": 4.232, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.10008356366908787, |
|
"step": 1944 |
|
}, |
|
{ |
|
"epoch": 27.08, |
|
"learning_rate": 3.137313432835821e-06, |
|
"loss": 0.4548, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 27.22, |
|
"learning_rate": 3.1313432835820895e-06, |
|
"loss": 0.4179, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 27.36, |
|
"learning_rate": 3.125373134328358e-06, |
|
"loss": 0.4299, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 27.5, |
|
"learning_rate": 3.1194029850746264e-06, |
|
"loss": 0.4469, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 27.64, |
|
"learning_rate": 3.1134328358208955e-06, |
|
"loss": 0.4339, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 27.78, |
|
"learning_rate": 3.1074626865671642e-06, |
|
"loss": 0.4391, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 27.91, |
|
"learning_rate": 3.1014925373134325e-06, |
|
"loss": 0.4197, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 28.0, |
|
"eval_loss": 0.2280617654323578, |
|
"eval_runtime": 124.6934, |
|
"eval_samples_per_second": 4.266, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.10001928392363567, |
|
"step": 2016 |
|
}, |
|
{ |
|
"epoch": 28.06, |
|
"learning_rate": 3.0955223880597016e-06, |
|
"loss": 0.4685, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 28.19, |
|
"learning_rate": 3.08955223880597e-06, |
|
"loss": 0.4268, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 28.33, |
|
"learning_rate": 3.0835820895522385e-06, |
|
"loss": 0.4345, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 28.47, |
|
"learning_rate": 3.0776119402985076e-06, |
|
"loss": 0.4228, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 28.61, |
|
"learning_rate": 3.071641791044776e-06, |
|
"loss": 0.4209, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 28.75, |
|
"learning_rate": 3.0656716417910446e-06, |
|
"loss": 0.446, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 28.89, |
|
"learning_rate": 3.0597014925373137e-06, |
|
"loss": 0.4107, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 29.0, |
|
"eval_loss": 0.23273050785064697, |
|
"eval_runtime": 125.3572, |
|
"eval_samples_per_second": 4.244, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.10072636112360996, |
|
"step": 2088 |
|
}, |
|
{ |
|
"epoch": 29.03, |
|
"learning_rate": 3.053731343283582e-06, |
|
"loss": 0.4617, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 29.17, |
|
"learning_rate": 3.0477611940298506e-06, |
|
"loss": 0.4099, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 29.3, |
|
"learning_rate": 3.0417910447761193e-06, |
|
"loss": 0.4415, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 29.44, |
|
"learning_rate": 3.035820895522388e-06, |
|
"loss": 0.4229, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 29.58, |
|
"learning_rate": 3.0298507462686567e-06, |
|
"loss": 0.4489, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 29.72, |
|
"learning_rate": 3.023880597014925e-06, |
|
"loss": 0.4309, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 29.86, |
|
"learning_rate": 3.017910447761194e-06, |
|
"loss": 0.4379, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 3.0119402985074627e-06, |
|
"loss": 0.442, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"eval_loss": 0.22788067162036896, |
|
"eval_runtime": 124.9649, |
|
"eval_samples_per_second": 4.257, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09854084977823488, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 30.14, |
|
"learning_rate": 3.005970149253731e-06, |
|
"loss": 0.437, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 30.28, |
|
"learning_rate": 3e-06, |
|
"loss": 0.4323, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 30.42, |
|
"learning_rate": 2.9940298507462688e-06, |
|
"loss": 0.4024, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 30.55, |
|
"learning_rate": 2.988059701492537e-06, |
|
"loss": 0.4315, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 30.69, |
|
"learning_rate": 2.9820895522388057e-06, |
|
"loss": 0.4301, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 30.83, |
|
"learning_rate": 2.976119402985075e-06, |
|
"loss": 0.4343, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 30.97, |
|
"learning_rate": 2.970149253731343e-06, |
|
"loss": 0.4315, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 31.0, |
|
"eval_loss": 0.2284124493598938, |
|
"eval_runtime": 125.7482, |
|
"eval_samples_per_second": 4.231, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09931220672366138, |
|
"step": 2232 |
|
}, |
|
{ |
|
"epoch": 31.11, |
|
"learning_rate": 2.9641791044776117e-06, |
|
"loss": 0.4485, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 31.25, |
|
"learning_rate": 2.9582089552238804e-06, |
|
"loss": 0.4253, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 31.39, |
|
"learning_rate": 2.952238805970149e-06, |
|
"loss": 0.4263, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 31.53, |
|
"learning_rate": 2.946268656716418e-06, |
|
"loss": 0.4351, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 31.66, |
|
"learning_rate": 2.940298507462686e-06, |
|
"loss": 0.4364, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 31.8, |
|
"learning_rate": 2.934328358208955e-06, |
|
"loss": 0.4482, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 31.94, |
|
"learning_rate": 2.928358208955224e-06, |
|
"loss": 0.4095, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"eval_loss": 0.22750599682331085, |
|
"eval_runtime": 125.3304, |
|
"eval_samples_per_second": 4.245, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09982644468727904, |
|
"step": 2304 |
|
}, |
|
{ |
|
"epoch": 32.08, |
|
"learning_rate": 2.922388059701492e-06, |
|
"loss": 0.4481, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 32.22, |
|
"learning_rate": 2.916417910447761e-06, |
|
"loss": 0.4222, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 32.36, |
|
"learning_rate": 2.91044776119403e-06, |
|
"loss": 0.4327, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 32.5, |
|
"learning_rate": 2.904477611940298e-06, |
|
"loss": 0.4206, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 32.64, |
|
"learning_rate": 2.8985074626865673e-06, |
|
"loss": 0.4174, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 32.78, |
|
"learning_rate": 2.8925373134328355e-06, |
|
"loss": 0.4398, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 32.91, |
|
"learning_rate": 2.886567164179104e-06, |
|
"loss": 0.4277, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 33.0, |
|
"eval_loss": 0.22814472019672394, |
|
"eval_runtime": 125.8994, |
|
"eval_samples_per_second": 4.226, |
|
"eval_steps_per_second": 0.532, |
|
"eval_wer": 0.09963360545092241, |
|
"step": 2376 |
|
}, |
|
{ |
|
"epoch": 33.06, |
|
"learning_rate": 2.8805970149253733e-06, |
|
"loss": 0.4398, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 33.19, |
|
"learning_rate": 2.8746268656716416e-06, |
|
"loss": 0.4151, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 33.33, |
|
"learning_rate": 2.8686567164179102e-06, |
|
"loss": 0.4287, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 33.47, |
|
"learning_rate": 2.862686567164179e-06, |
|
"loss": 0.4433, |
|
"step": 2410 |
|
}, |
|
{ |
|
"epoch": 33.61, |
|
"learning_rate": 2.8567164179104476e-06, |
|
"loss": 0.4202, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 33.75, |
|
"learning_rate": 2.8507462686567163e-06, |
|
"loss": 0.4238, |
|
"step": 2430 |
|
}, |
|
{ |
|
"epoch": 33.89, |
|
"learning_rate": 2.844776119402985e-06, |
|
"loss": 0.4114, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 34.0, |
|
"eval_loss": 0.22670897841453552, |
|
"eval_runtime": 125.3477, |
|
"eval_samples_per_second": 4.244, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.10079064086906216, |
|
"step": 2448 |
|
}, |
|
{ |
|
"epoch": 34.03, |
|
"learning_rate": 2.8388059701492537e-06, |
|
"loss": 0.4307, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 34.17, |
|
"learning_rate": 2.8328358208955223e-06, |
|
"loss": 0.4307, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 34.3, |
|
"learning_rate": 2.826865671641791e-06, |
|
"loss": 0.4326, |
|
"step": 2470 |
|
}, |
|
{ |
|
"epoch": 34.44, |
|
"learning_rate": 2.8208955223880597e-06, |
|
"loss": 0.4165, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 34.58, |
|
"learning_rate": 2.8149253731343284e-06, |
|
"loss": 0.4447, |
|
"step": 2490 |
|
}, |
|
{ |
|
"epoch": 34.72, |
|
"learning_rate": 2.8089552238805966e-06, |
|
"loss": 0.408, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 34.86, |
|
"learning_rate": 2.8029850746268653e-06, |
|
"loss": 0.4165, |
|
"step": 2510 |
|
}, |
|
{ |
|
"epoch": 35.0, |
|
"learning_rate": 2.7970149253731344e-06, |
|
"loss": 0.4311, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 35.0, |
|
"eval_loss": 0.22740690410137177, |
|
"eval_runtime": 125.7503, |
|
"eval_samples_per_second": 4.231, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09821945105097384, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 35.14, |
|
"learning_rate": 2.7910447761194027e-06, |
|
"loss": 0.4246, |
|
"step": 2530 |
|
}, |
|
{ |
|
"epoch": 35.28, |
|
"learning_rate": 2.7850746268656714e-06, |
|
"loss": 0.4575, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 35.42, |
|
"learning_rate": 2.7791044776119405e-06, |
|
"loss": 0.4118, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 35.55, |
|
"learning_rate": 2.7731343283582087e-06, |
|
"loss": 0.427, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 35.69, |
|
"learning_rate": 2.7671641791044774e-06, |
|
"loss": 0.424, |
|
"step": 2570 |
|
}, |
|
{ |
|
"epoch": 35.83, |
|
"learning_rate": 2.7611940298507465e-06, |
|
"loss": 0.4406, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 35.97, |
|
"learning_rate": 2.7552238805970148e-06, |
|
"loss": 0.4193, |
|
"step": 2590 |
|
}, |
|
{ |
|
"epoch": 36.0, |
|
"eval_loss": 0.225921630859375, |
|
"eval_runtime": 125.0894, |
|
"eval_samples_per_second": 4.253, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09873368901459151, |
|
"step": 2592 |
|
}, |
|
{ |
|
"epoch": 36.11, |
|
"learning_rate": 2.7492537313432835e-06, |
|
"loss": 0.444, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 36.25, |
|
"learning_rate": 2.7432835820895517e-06, |
|
"loss": 0.4176, |
|
"step": 2610 |
|
}, |
|
{ |
|
"epoch": 36.39, |
|
"learning_rate": 2.737313432835821e-06, |
|
"loss": 0.4242, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 36.53, |
|
"learning_rate": 2.7313432835820895e-06, |
|
"loss": 0.4243, |
|
"step": 2630 |
|
}, |
|
{ |
|
"epoch": 36.66, |
|
"learning_rate": 2.7253731343283578e-06, |
|
"loss": 0.4109, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 36.8, |
|
"learning_rate": 2.719402985074627e-06, |
|
"loss": 0.4367, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 36.94, |
|
"learning_rate": 2.7134328358208956e-06, |
|
"loss": 0.421, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 37.0, |
|
"eval_loss": 0.22772617638111115, |
|
"eval_runtime": 125.5324, |
|
"eval_samples_per_second": 4.238, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09886224850549592, |
|
"step": 2664 |
|
}, |
|
{ |
|
"epoch": 37.08, |
|
"learning_rate": 2.707462686567164e-06, |
|
"loss": 0.4478, |
|
"step": 2670 |
|
}, |
|
{ |
|
"epoch": 37.22, |
|
"learning_rate": 2.701492537313433e-06, |
|
"loss": 0.4204, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 37.36, |
|
"learning_rate": 2.6955223880597016e-06, |
|
"loss": 0.4171, |
|
"step": 2690 |
|
}, |
|
{ |
|
"epoch": 37.5, |
|
"learning_rate": 2.68955223880597e-06, |
|
"loss": 0.4294, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 37.64, |
|
"learning_rate": 2.6835820895522385e-06, |
|
"loss": 0.4296, |
|
"step": 2710 |
|
}, |
|
{ |
|
"epoch": 37.78, |
|
"learning_rate": 2.6776119402985072e-06, |
|
"loss": 0.433, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 37.91, |
|
"learning_rate": 2.671641791044776e-06, |
|
"loss": 0.4084, |
|
"step": 2730 |
|
}, |
|
{ |
|
"epoch": 38.0, |
|
"eval_loss": 0.22683019936084747, |
|
"eval_runtime": 125.0438, |
|
"eval_samples_per_second": 4.255, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09924792697820917, |
|
"step": 2736 |
|
}, |
|
{ |
|
"epoch": 38.06, |
|
"learning_rate": 2.6656716417910446e-06, |
|
"loss": 0.4419, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 38.19, |
|
"learning_rate": 2.6597014925373133e-06, |
|
"loss": 0.4241, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 38.33, |
|
"learning_rate": 2.653731343283582e-06, |
|
"loss": 0.4344, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 38.47, |
|
"learning_rate": 2.6477611940298506e-06, |
|
"loss": 0.418, |
|
"step": 2770 |
|
}, |
|
{ |
|
"epoch": 38.61, |
|
"learning_rate": 2.6417910447761193e-06, |
|
"loss": 0.4198, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 38.75, |
|
"learning_rate": 2.635820895522388e-06, |
|
"loss": 0.43, |
|
"step": 2790 |
|
}, |
|
{ |
|
"epoch": 38.89, |
|
"learning_rate": 2.6298507462686567e-06, |
|
"loss": 0.4302, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 39.0, |
|
"eval_loss": 0.22871556878089905, |
|
"eval_runtime": 125.1142, |
|
"eval_samples_per_second": 4.252, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09963360545092241, |
|
"step": 2808 |
|
}, |
|
{ |
|
"epoch": 39.03, |
|
"learning_rate": 2.623880597014925e-06, |
|
"loss": 0.4474, |
|
"step": 2810 |
|
}, |
|
{ |
|
"epoch": 39.17, |
|
"learning_rate": 2.617910447761194e-06, |
|
"loss": 0.4153, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 39.3, |
|
"learning_rate": 2.6119402985074627e-06, |
|
"loss": 0.4475, |
|
"step": 2830 |
|
}, |
|
{ |
|
"epoch": 39.44, |
|
"learning_rate": 2.605970149253731e-06, |
|
"loss": 0.417, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 39.58, |
|
"learning_rate": 2.6e-06, |
|
"loss": 0.4165, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 39.72, |
|
"learning_rate": 2.5940298507462684e-06, |
|
"loss": 0.4131, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 39.86, |
|
"learning_rate": 2.588059701492537e-06, |
|
"loss": 0.4266, |
|
"step": 2870 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"learning_rate": 2.582089552238806e-06, |
|
"loss": 0.4379, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"eval_loss": 0.2281065583229065, |
|
"eval_runtime": 124.996, |
|
"eval_samples_per_second": 4.256, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09841229028733046, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 40.14, |
|
"learning_rate": 2.5761194029850744e-06, |
|
"loss": 0.4193, |
|
"step": 2890 |
|
}, |
|
{ |
|
"epoch": 40.28, |
|
"learning_rate": 2.570149253731343e-06, |
|
"loss": 0.4225, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 40.42, |
|
"learning_rate": 2.564179104477612e-06, |
|
"loss": 0.4271, |
|
"step": 2910 |
|
}, |
|
{ |
|
"epoch": 40.55, |
|
"learning_rate": 2.5582089552238804e-06, |
|
"loss": 0.4216, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 40.69, |
|
"learning_rate": 2.552238805970149e-06, |
|
"loss": 0.4183, |
|
"step": 2930 |
|
}, |
|
{ |
|
"epoch": 40.83, |
|
"learning_rate": 2.546268656716418e-06, |
|
"loss": 0.4506, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 40.97, |
|
"learning_rate": 2.5402985074626865e-06, |
|
"loss": 0.415, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 41.0, |
|
"eval_loss": 0.22702236473560333, |
|
"eval_runtime": 125.4148, |
|
"eval_samples_per_second": 4.242, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.10059780163270554, |
|
"step": 2952 |
|
}, |
|
{ |
|
"epoch": 41.11, |
|
"learning_rate": 2.534328358208955e-06, |
|
"loss": 0.4323, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 41.25, |
|
"learning_rate": 2.5283582089552234e-06, |
|
"loss": 0.4268, |
|
"step": 2970 |
|
}, |
|
{ |
|
"epoch": 41.39, |
|
"learning_rate": 2.5223880597014925e-06, |
|
"loss": 0.4167, |
|
"step": 2980 |
|
}, |
|
{ |
|
"epoch": 41.53, |
|
"learning_rate": 2.5164179104477612e-06, |
|
"loss": 0.4206, |
|
"step": 2990 |
|
}, |
|
{ |
|
"epoch": 41.66, |
|
"learning_rate": 2.5104477611940295e-06, |
|
"loss": 0.4221, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 41.8, |
|
"learning_rate": 2.5044776119402986e-06, |
|
"loss": 0.4336, |
|
"step": 3010 |
|
}, |
|
{ |
|
"epoch": 41.94, |
|
"learning_rate": 2.4985074626865673e-06, |
|
"loss": 0.4035, |
|
"step": 3020 |
|
}, |
|
{ |
|
"epoch": 42.0, |
|
"eval_loss": 0.22987306118011475, |
|
"eval_runtime": 126.744, |
|
"eval_samples_per_second": 4.197, |
|
"eval_steps_per_second": 0.529, |
|
"eval_wer": 0.09924792697820917, |
|
"step": 3024 |
|
}, |
|
{ |
|
"epoch": 42.08, |
|
"learning_rate": 2.4925373134328355e-06, |
|
"loss": 0.4517, |
|
"step": 3030 |
|
}, |
|
{ |
|
"epoch": 42.22, |
|
"learning_rate": 2.486567164179104e-06, |
|
"loss": 0.4289, |
|
"step": 3040 |
|
}, |
|
{ |
|
"epoch": 42.36, |
|
"learning_rate": 2.4805970149253733e-06, |
|
"loss": 0.4277, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 42.5, |
|
"learning_rate": 2.4746268656716416e-06, |
|
"loss": 0.4282, |
|
"step": 3060 |
|
}, |
|
{ |
|
"epoch": 42.64, |
|
"learning_rate": 2.4686567164179103e-06, |
|
"loss": 0.4109, |
|
"step": 3070 |
|
}, |
|
{ |
|
"epoch": 42.78, |
|
"learning_rate": 2.462686567164179e-06, |
|
"loss": 0.4498, |
|
"step": 3080 |
|
}, |
|
{ |
|
"epoch": 42.91, |
|
"learning_rate": 2.4567164179104476e-06, |
|
"loss": 0.4103, |
|
"step": 3090 |
|
}, |
|
{ |
|
"epoch": 43.0, |
|
"eval_loss": 0.22572675347328186, |
|
"eval_runtime": 125.2778, |
|
"eval_samples_per_second": 4.247, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09873368901459151, |
|
"step": 3096 |
|
}, |
|
{ |
|
"epoch": 43.06, |
|
"learning_rate": 2.4507462686567163e-06, |
|
"loss": 0.4306, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 43.19, |
|
"learning_rate": 2.444776119402985e-06, |
|
"loss": 0.4088, |
|
"step": 3110 |
|
}, |
|
{ |
|
"epoch": 43.33, |
|
"learning_rate": 2.4388059701492537e-06, |
|
"loss": 0.4366, |
|
"step": 3120 |
|
}, |
|
{ |
|
"epoch": 43.47, |
|
"learning_rate": 2.4328358208955224e-06, |
|
"loss": 0.4041, |
|
"step": 3130 |
|
}, |
|
{ |
|
"epoch": 43.61, |
|
"learning_rate": 2.4268656716417906e-06, |
|
"loss": 0.4179, |
|
"step": 3140 |
|
}, |
|
{ |
|
"epoch": 43.75, |
|
"learning_rate": 2.4208955223880597e-06, |
|
"loss": 0.4407, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 43.89, |
|
"learning_rate": 2.4149253731343284e-06, |
|
"loss": 0.4187, |
|
"step": 3160 |
|
}, |
|
{ |
|
"epoch": 44.0, |
|
"eval_loss": 0.22597859799861908, |
|
"eval_runtime": 125.1911, |
|
"eval_samples_per_second": 4.25, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09751237385099955, |
|
"step": 3168 |
|
}, |
|
{ |
|
"epoch": 44.03, |
|
"learning_rate": 2.4089552238805967e-06, |
|
"loss": 0.4559, |
|
"step": 3170 |
|
}, |
|
{ |
|
"epoch": 44.17, |
|
"learning_rate": 2.4029850746268658e-06, |
|
"loss": 0.4097, |
|
"step": 3180 |
|
}, |
|
{ |
|
"epoch": 44.3, |
|
"learning_rate": 2.3970149253731344e-06, |
|
"loss": 0.4434, |
|
"step": 3190 |
|
}, |
|
{ |
|
"epoch": 44.44, |
|
"learning_rate": 2.3910447761194027e-06, |
|
"loss": 0.432, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 44.58, |
|
"learning_rate": 2.385074626865672e-06, |
|
"loss": 0.4564, |
|
"step": 3210 |
|
}, |
|
{ |
|
"epoch": 44.72, |
|
"learning_rate": 2.37910447761194e-06, |
|
"loss": 0.4238, |
|
"step": 3220 |
|
}, |
|
{ |
|
"epoch": 44.86, |
|
"learning_rate": 2.3731343283582087e-06, |
|
"loss": 0.4229, |
|
"step": 3230 |
|
}, |
|
{ |
|
"epoch": 45.0, |
|
"learning_rate": 2.3671641791044774e-06, |
|
"loss": 0.4254, |
|
"step": 3240 |
|
}, |
|
{ |
|
"epoch": 45.0, |
|
"eval_loss": 0.22727687656879425, |
|
"eval_runtime": 125.509, |
|
"eval_samples_per_second": 4.239, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09854084977823488, |
|
"step": 3240 |
|
}, |
|
{ |
|
"epoch": 45.14, |
|
"learning_rate": 2.361194029850746e-06, |
|
"loss": 0.427, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 45.28, |
|
"learning_rate": 2.355223880597015e-06, |
|
"loss": 0.431, |
|
"step": 3260 |
|
}, |
|
{ |
|
"epoch": 45.42, |
|
"learning_rate": 2.3492537313432835e-06, |
|
"loss": 0.4048, |
|
"step": 3270 |
|
}, |
|
{ |
|
"epoch": 45.55, |
|
"learning_rate": 2.343283582089552e-06, |
|
"loss": 0.4244, |
|
"step": 3280 |
|
}, |
|
{ |
|
"epoch": 45.69, |
|
"learning_rate": 2.337313432835821e-06, |
|
"loss": 0.415, |
|
"step": 3290 |
|
}, |
|
{ |
|
"epoch": 45.83, |
|
"learning_rate": 2.3313432835820895e-06, |
|
"loss": 0.4268, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 45.97, |
|
"learning_rate": 2.325373134328358e-06, |
|
"loss": 0.415, |
|
"step": 3310 |
|
}, |
|
{ |
|
"epoch": 46.0, |
|
"eval_loss": 0.23116381466388702, |
|
"eval_runtime": 125.5156, |
|
"eval_samples_per_second": 4.239, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.10001928392363567, |
|
"step": 3312 |
|
}, |
|
{ |
|
"epoch": 46.11, |
|
"learning_rate": 2.319402985074627e-06, |
|
"loss": 0.4418, |
|
"step": 3320 |
|
}, |
|
{ |
|
"epoch": 46.25, |
|
"learning_rate": 2.313432835820895e-06, |
|
"loss": 0.4431, |
|
"step": 3330 |
|
}, |
|
{ |
|
"epoch": 46.39, |
|
"learning_rate": 2.307462686567164e-06, |
|
"loss": 0.4155, |
|
"step": 3340 |
|
}, |
|
{ |
|
"epoch": 46.53, |
|
"learning_rate": 2.301492537313433e-06, |
|
"loss": 0.4153, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 46.66, |
|
"learning_rate": 2.295522388059701e-06, |
|
"loss": 0.4178, |
|
"step": 3360 |
|
}, |
|
{ |
|
"epoch": 46.8, |
|
"learning_rate": 2.28955223880597e-06, |
|
"loss": 0.4192, |
|
"step": 3370 |
|
}, |
|
{ |
|
"epoch": 46.94, |
|
"learning_rate": 2.283582089552239e-06, |
|
"loss": 0.4069, |
|
"step": 3380 |
|
}, |
|
{ |
|
"epoch": 47.0, |
|
"eval_loss": 0.22701291739940643, |
|
"eval_runtime": 125.3957, |
|
"eval_samples_per_second": 4.243, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.1003406826508967, |
|
"step": 3384 |
|
}, |
|
{ |
|
"epoch": 47.08, |
|
"learning_rate": 2.2776119402985072e-06, |
|
"loss": 0.4551, |
|
"step": 3390 |
|
}, |
|
{ |
|
"epoch": 47.22, |
|
"learning_rate": 2.271641791044776e-06, |
|
"loss": 0.4232, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 47.36, |
|
"learning_rate": 2.265671641791045e-06, |
|
"loss": 0.4247, |
|
"step": 3410 |
|
}, |
|
{ |
|
"epoch": 47.5, |
|
"learning_rate": 2.2597014925373133e-06, |
|
"loss": 0.4336, |
|
"step": 3420 |
|
}, |
|
{ |
|
"epoch": 47.64, |
|
"learning_rate": 2.253731343283582e-06, |
|
"loss": 0.4172, |
|
"step": 3430 |
|
}, |
|
{ |
|
"epoch": 47.78, |
|
"learning_rate": 2.2477611940298502e-06, |
|
"loss": 0.4349, |
|
"step": 3440 |
|
}, |
|
{ |
|
"epoch": 47.91, |
|
"learning_rate": 2.2417910447761193e-06, |
|
"loss": 0.4085, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"eval_loss": 0.2230219542980194, |
|
"eval_runtime": 125.3969, |
|
"eval_samples_per_second": 4.243, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09776949283280838, |
|
"step": 3456 |
|
}, |
|
{ |
|
"epoch": 48.06, |
|
"learning_rate": 2.235820895522388e-06, |
|
"loss": 0.4506, |
|
"step": 3460 |
|
}, |
|
{ |
|
"epoch": 48.19, |
|
"learning_rate": 2.2298507462686563e-06, |
|
"loss": 0.3975, |
|
"step": 3470 |
|
}, |
|
{ |
|
"epoch": 48.33, |
|
"learning_rate": 2.2238805970149254e-06, |
|
"loss": 0.4288, |
|
"step": 3480 |
|
}, |
|
{ |
|
"epoch": 48.47, |
|
"learning_rate": 2.217910447761194e-06, |
|
"loss": 0.4193, |
|
"step": 3490 |
|
}, |
|
{ |
|
"epoch": 48.61, |
|
"learning_rate": 2.2119402985074623e-06, |
|
"loss": 0.4233, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 48.75, |
|
"learning_rate": 2.2059701492537314e-06, |
|
"loss": 0.4285, |
|
"step": 3510 |
|
}, |
|
{ |
|
"epoch": 48.89, |
|
"learning_rate": 2.2e-06, |
|
"loss": 0.4287, |
|
"step": 3520 |
|
}, |
|
{ |
|
"epoch": 49.0, |
|
"eval_loss": 0.22409839928150177, |
|
"eval_runtime": 126.73, |
|
"eval_samples_per_second": 4.198, |
|
"eval_steps_per_second": 0.529, |
|
"eval_wer": 0.09892652825094812, |
|
"step": 3528 |
|
}, |
|
{ |
|
"epoch": 49.03, |
|
"learning_rate": 2.1940298507462684e-06, |
|
"loss": 0.4305, |
|
"step": 3530 |
|
}, |
|
{ |
|
"epoch": 49.17, |
|
"learning_rate": 2.1880597014925375e-06, |
|
"loss": 0.4212, |
|
"step": 3540 |
|
}, |
|
{ |
|
"epoch": 49.3, |
|
"learning_rate": 2.182089552238806e-06, |
|
"loss": 0.4304, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 49.44, |
|
"learning_rate": 2.1761194029850744e-06, |
|
"loss": 0.4182, |
|
"step": 3560 |
|
}, |
|
{ |
|
"epoch": 49.58, |
|
"learning_rate": 2.170149253731343e-06, |
|
"loss": 0.4489, |
|
"step": 3570 |
|
}, |
|
{ |
|
"epoch": 49.72, |
|
"learning_rate": 2.1641791044776118e-06, |
|
"loss": 0.4002, |
|
"step": 3580 |
|
}, |
|
{ |
|
"epoch": 49.86, |
|
"learning_rate": 2.1582089552238805e-06, |
|
"loss": 0.4334, |
|
"step": 3590 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"learning_rate": 2.152238805970149e-06, |
|
"loss": 0.4227, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"eval_loss": 0.22334957122802734, |
|
"eval_runtime": 125.4431, |
|
"eval_samples_per_second": 4.241, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09937648646911358, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 50.14, |
|
"learning_rate": 2.146268656716418e-06, |
|
"loss": 0.4402, |
|
"step": 3610 |
|
}, |
|
{ |
|
"epoch": 50.28, |
|
"learning_rate": 2.1402985074626865e-06, |
|
"loss": 0.4395, |
|
"step": 3620 |
|
}, |
|
{ |
|
"epoch": 50.42, |
|
"learning_rate": 2.134328358208955e-06, |
|
"loss": 0.4091, |
|
"step": 3630 |
|
}, |
|
{ |
|
"epoch": 50.55, |
|
"learning_rate": 2.128358208955224e-06, |
|
"loss": 0.4262, |
|
"step": 3640 |
|
}, |
|
{ |
|
"epoch": 50.69, |
|
"learning_rate": 2.1223880597014926e-06, |
|
"loss": 0.4091, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 50.83, |
|
"learning_rate": 2.1164179104477612e-06, |
|
"loss": 0.4412, |
|
"step": 3660 |
|
}, |
|
{ |
|
"epoch": 50.97, |
|
"learning_rate": 2.1104477611940295e-06, |
|
"loss": 0.3998, |
|
"step": 3670 |
|
}, |
|
{ |
|
"epoch": 51.0, |
|
"eval_loss": 0.2267557680606842, |
|
"eval_runtime": 125.5758, |
|
"eval_samples_per_second": 4.236, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09905508774185254, |
|
"step": 3672 |
|
}, |
|
{ |
|
"epoch": 51.11, |
|
"learning_rate": 2.1044776119402986e-06, |
|
"loss": 0.4393, |
|
"step": 3680 |
|
}, |
|
{ |
|
"epoch": 51.25, |
|
"learning_rate": 2.098507462686567e-06, |
|
"loss": 0.427, |
|
"step": 3690 |
|
}, |
|
{ |
|
"epoch": 51.39, |
|
"learning_rate": 2.0925373134328355e-06, |
|
"loss": 0.4146, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 51.53, |
|
"learning_rate": 2.0865671641791047e-06, |
|
"loss": 0.4272, |
|
"step": 3710 |
|
}, |
|
{ |
|
"epoch": 51.66, |
|
"learning_rate": 2.080597014925373e-06, |
|
"loss": 0.421, |
|
"step": 3720 |
|
}, |
|
{ |
|
"epoch": 51.8, |
|
"learning_rate": 2.0746268656716416e-06, |
|
"loss": 0.4396, |
|
"step": 3730 |
|
}, |
|
{ |
|
"epoch": 51.94, |
|
"learning_rate": 2.0686567164179107e-06, |
|
"loss": 0.4139, |
|
"step": 3740 |
|
}, |
|
{ |
|
"epoch": 52.0, |
|
"eval_loss": 0.2224283367395401, |
|
"eval_runtime": 125.8107, |
|
"eval_samples_per_second": 4.229, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09873368901459151, |
|
"step": 3744 |
|
}, |
|
{ |
|
"epoch": 52.08, |
|
"learning_rate": 2.062686567164179e-06, |
|
"loss": 0.4231, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 52.22, |
|
"learning_rate": 2.0567164179104476e-06, |
|
"loss": 0.4083, |
|
"step": 3760 |
|
}, |
|
{ |
|
"epoch": 52.36, |
|
"learning_rate": 2.0507462686567163e-06, |
|
"loss": 0.4282, |
|
"step": 3770 |
|
}, |
|
{ |
|
"epoch": 52.5, |
|
"learning_rate": 2.044776119402985e-06, |
|
"loss": 0.4148, |
|
"step": 3780 |
|
}, |
|
{ |
|
"epoch": 52.64, |
|
"learning_rate": 2.0388059701492537e-06, |
|
"loss": 0.4095, |
|
"step": 3790 |
|
}, |
|
{ |
|
"epoch": 52.78, |
|
"learning_rate": 2.032835820895522e-06, |
|
"loss": 0.4266, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 52.91, |
|
"learning_rate": 2.026865671641791e-06, |
|
"loss": 0.409, |
|
"step": 3810 |
|
}, |
|
{ |
|
"epoch": 53.0, |
|
"eval_loss": 0.2255866378545761, |
|
"eval_runtime": 126.4301, |
|
"eval_samples_per_second": 4.208, |
|
"eval_steps_per_second": 0.53, |
|
"eval_wer": 0.10014784341454008, |
|
"step": 3816 |
|
}, |
|
{ |
|
"epoch": 53.06, |
|
"learning_rate": 2.0208955223880597e-06, |
|
"loss": 0.436, |
|
"step": 3820 |
|
}, |
|
{ |
|
"epoch": 53.19, |
|
"learning_rate": 2.014925373134328e-06, |
|
"loss": 0.4056, |
|
"step": 3830 |
|
}, |
|
{ |
|
"epoch": 53.33, |
|
"learning_rate": 2.008955223880597e-06, |
|
"loss": 0.415, |
|
"step": 3840 |
|
}, |
|
{ |
|
"epoch": 53.47, |
|
"learning_rate": 2.0029850746268658e-06, |
|
"loss": 0.4066, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 53.61, |
|
"learning_rate": 1.9970149253731345e-06, |
|
"loss": 0.4369, |
|
"step": 3860 |
|
}, |
|
{ |
|
"epoch": 53.75, |
|
"learning_rate": 1.9910447761194027e-06, |
|
"loss": 0.4141, |
|
"step": 3870 |
|
}, |
|
{ |
|
"epoch": 53.89, |
|
"learning_rate": 1.9850746268656714e-06, |
|
"loss": 0.4191, |
|
"step": 3880 |
|
}, |
|
{ |
|
"epoch": 54.0, |
|
"eval_loss": 0.22644391655921936, |
|
"eval_runtime": 125.4586, |
|
"eval_samples_per_second": 4.24, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09911936748730475, |
|
"step": 3888 |
|
}, |
|
{ |
|
"epoch": 54.03, |
|
"learning_rate": 1.97910447761194e-06, |
|
"loss": 0.4229, |
|
"step": 3890 |
|
}, |
|
{ |
|
"epoch": 54.17, |
|
"learning_rate": 1.9731343283582088e-06, |
|
"loss": 0.4172, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 54.3, |
|
"learning_rate": 1.9671641791044775e-06, |
|
"loss": 0.4179, |
|
"step": 3910 |
|
}, |
|
{ |
|
"epoch": 54.44, |
|
"learning_rate": 1.961194029850746e-06, |
|
"loss": 0.415, |
|
"step": 3920 |
|
}, |
|
{ |
|
"epoch": 54.58, |
|
"learning_rate": 1.955223880597015e-06, |
|
"loss": 0.4219, |
|
"step": 3930 |
|
}, |
|
{ |
|
"epoch": 54.72, |
|
"learning_rate": 1.9492537313432835e-06, |
|
"loss": 0.4227, |
|
"step": 3940 |
|
}, |
|
{ |
|
"epoch": 54.86, |
|
"learning_rate": 1.943283582089552e-06, |
|
"loss": 0.4262, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 55.0, |
|
"learning_rate": 1.937313432835821e-06, |
|
"loss": 0.4156, |
|
"step": 3960 |
|
}, |
|
{ |
|
"epoch": 55.0, |
|
"eval_loss": 0.22371676564216614, |
|
"eval_runtime": 125.5217, |
|
"eval_samples_per_second": 4.238, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09931220672366138, |
|
"step": 3960 |
|
}, |
|
{ |
|
"epoch": 55.14, |
|
"learning_rate": 1.9313432835820895e-06, |
|
"loss": 0.4135, |
|
"step": 3970 |
|
}, |
|
{ |
|
"epoch": 55.28, |
|
"learning_rate": 1.9253731343283582e-06, |
|
"loss": 0.4117, |
|
"step": 3980 |
|
}, |
|
{ |
|
"epoch": 55.42, |
|
"learning_rate": 1.919402985074627e-06, |
|
"loss": 0.421, |
|
"step": 3990 |
|
}, |
|
{ |
|
"epoch": 55.55, |
|
"learning_rate": 1.9134328358208956e-06, |
|
"loss": 0.4335, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 55.69, |
|
"learning_rate": 1.9074626865671643e-06, |
|
"loss": 0.4079, |
|
"step": 4010 |
|
}, |
|
{ |
|
"epoch": 55.83, |
|
"learning_rate": 1.9014925373134327e-06, |
|
"loss": 0.4376, |
|
"step": 4020 |
|
}, |
|
{ |
|
"epoch": 55.97, |
|
"learning_rate": 1.8955223880597014e-06, |
|
"loss": 0.4252, |
|
"step": 4030 |
|
}, |
|
{ |
|
"epoch": 56.0, |
|
"eval_loss": 0.22503013908863068, |
|
"eval_runtime": 124.7493, |
|
"eval_samples_per_second": 4.265, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.09879796876004371, |
|
"step": 4032 |
|
}, |
|
{ |
|
"epoch": 56.11, |
|
"learning_rate": 1.8895522388059701e-06, |
|
"loss": 0.4338, |
|
"step": 4040 |
|
}, |
|
{ |
|
"epoch": 56.25, |
|
"learning_rate": 1.8835820895522388e-06, |
|
"loss": 0.4169, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 56.39, |
|
"learning_rate": 1.8776119402985073e-06, |
|
"loss": 0.4113, |
|
"step": 4060 |
|
}, |
|
{ |
|
"epoch": 56.53, |
|
"learning_rate": 1.871641791044776e-06, |
|
"loss": 0.4196, |
|
"step": 4070 |
|
}, |
|
{ |
|
"epoch": 56.66, |
|
"learning_rate": 1.8656716417910448e-06, |
|
"loss": 0.4034, |
|
"step": 4080 |
|
}, |
|
{ |
|
"epoch": 56.8, |
|
"learning_rate": 1.8597014925373133e-06, |
|
"loss": 0.4026, |
|
"step": 4090 |
|
}, |
|
{ |
|
"epoch": 56.94, |
|
"learning_rate": 1.853731343283582e-06, |
|
"loss": 0.4207, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 57.0, |
|
"eval_loss": 0.2246323823928833, |
|
"eval_runtime": 126.2519, |
|
"eval_samples_per_second": 4.214, |
|
"eval_steps_per_second": 0.531, |
|
"eval_wer": 0.09892652825094812, |
|
"step": 4104 |
|
}, |
|
{ |
|
"epoch": 57.08, |
|
"learning_rate": 1.8477611940298507e-06, |
|
"loss": 0.4413, |
|
"step": 4110 |
|
}, |
|
{ |
|
"epoch": 57.22, |
|
"learning_rate": 1.8417910447761194e-06, |
|
"loss": 0.4186, |
|
"step": 4120 |
|
}, |
|
{ |
|
"epoch": 57.36, |
|
"learning_rate": 1.835820895522388e-06, |
|
"loss": 0.4201, |
|
"step": 4130 |
|
}, |
|
{ |
|
"epoch": 57.5, |
|
"learning_rate": 1.8298507462686565e-06, |
|
"loss": 0.4153, |
|
"step": 4140 |
|
}, |
|
{ |
|
"epoch": 57.64, |
|
"learning_rate": 1.8238805970149254e-06, |
|
"loss": 0.4035, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 57.78, |
|
"learning_rate": 1.8179104477611939e-06, |
|
"loss": 0.4272, |
|
"step": 4160 |
|
}, |
|
{ |
|
"epoch": 57.91, |
|
"learning_rate": 1.8119402985074626e-06, |
|
"loss": 0.4143, |
|
"step": 4170 |
|
}, |
|
{ |
|
"epoch": 58.0, |
|
"eval_loss": 0.2247840166091919, |
|
"eval_runtime": 125.1569, |
|
"eval_samples_per_second": 4.251, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09809089156006942, |
|
"step": 4176 |
|
}, |
|
{ |
|
"epoch": 58.06, |
|
"learning_rate": 1.8059701492537314e-06, |
|
"loss": 0.443, |
|
"step": 4180 |
|
}, |
|
{ |
|
"epoch": 58.19, |
|
"learning_rate": 1.8e-06, |
|
"loss": 0.3987, |
|
"step": 4190 |
|
}, |
|
{ |
|
"epoch": 58.33, |
|
"learning_rate": 1.7940298507462686e-06, |
|
"loss": 0.4314, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 58.47, |
|
"learning_rate": 1.788059701492537e-06, |
|
"loss": 0.4199, |
|
"step": 4210 |
|
}, |
|
{ |
|
"epoch": 58.61, |
|
"learning_rate": 1.782089552238806e-06, |
|
"loss": 0.4277, |
|
"step": 4220 |
|
}, |
|
{ |
|
"epoch": 58.75, |
|
"learning_rate": 1.7761194029850746e-06, |
|
"loss": 0.4259, |
|
"step": 4230 |
|
}, |
|
{ |
|
"epoch": 58.89, |
|
"learning_rate": 1.7701492537313431e-06, |
|
"loss": 0.4261, |
|
"step": 4240 |
|
}, |
|
{ |
|
"epoch": 59.0, |
|
"eval_loss": 0.2237170934677124, |
|
"eval_runtime": 125.3236, |
|
"eval_samples_per_second": 4.245, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09725525486919072, |
|
"step": 4248 |
|
}, |
|
{ |
|
"epoch": 59.03, |
|
"learning_rate": 1.7641791044776118e-06, |
|
"loss": 0.4321, |
|
"step": 4250 |
|
}, |
|
{ |
|
"epoch": 59.17, |
|
"learning_rate": 1.7582089552238805e-06, |
|
"loss": 0.4089, |
|
"step": 4260 |
|
}, |
|
{ |
|
"epoch": 59.3, |
|
"learning_rate": 1.7522388059701492e-06, |
|
"loss": 0.4321, |
|
"step": 4270 |
|
}, |
|
{ |
|
"epoch": 59.44, |
|
"learning_rate": 1.7462686567164178e-06, |
|
"loss": 0.4063, |
|
"step": 4280 |
|
}, |
|
{ |
|
"epoch": 59.58, |
|
"learning_rate": 1.7402985074626865e-06, |
|
"loss": 0.4372, |
|
"step": 4290 |
|
}, |
|
{ |
|
"epoch": 59.72, |
|
"learning_rate": 1.7343283582089552e-06, |
|
"loss": 0.4009, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 59.86, |
|
"learning_rate": 1.7283582089552237e-06, |
|
"loss": 0.4091, |
|
"step": 4310 |
|
}, |
|
{ |
|
"epoch": 60.0, |
|
"learning_rate": 1.7223880597014924e-06, |
|
"loss": 0.4212, |
|
"step": 4320 |
|
}, |
|
{ |
|
"epoch": 60.0, |
|
"eval_loss": 0.2242782860994339, |
|
"eval_runtime": 124.9101, |
|
"eval_samples_per_second": 4.259, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09764093334190396, |
|
"step": 4320 |
|
}, |
|
{ |
|
"epoch": 60.14, |
|
"learning_rate": 1.7164179104477613e-06, |
|
"loss": 0.4299, |
|
"step": 4330 |
|
}, |
|
{ |
|
"epoch": 60.28, |
|
"learning_rate": 1.7104477611940297e-06, |
|
"loss": 0.4231, |
|
"step": 4340 |
|
}, |
|
{ |
|
"epoch": 60.42, |
|
"learning_rate": 1.7044776119402984e-06, |
|
"loss": 0.4101, |
|
"step": 4350 |
|
}, |
|
{ |
|
"epoch": 60.55, |
|
"learning_rate": 1.6991044776119402e-06, |
|
"loss": 0.4101, |
|
"step": 4360 |
|
}, |
|
{ |
|
"epoch": 60.69, |
|
"learning_rate": 1.693134328358209e-06, |
|
"loss": 0.4224, |
|
"step": 4370 |
|
}, |
|
{ |
|
"epoch": 60.83, |
|
"learning_rate": 1.6871641791044776e-06, |
|
"loss": 0.4237, |
|
"step": 4380 |
|
}, |
|
{ |
|
"epoch": 60.97, |
|
"learning_rate": 1.681194029850746e-06, |
|
"loss": 0.426, |
|
"step": 4390 |
|
}, |
|
{ |
|
"epoch": 61.0, |
|
"eval_loss": 0.22302205860614777, |
|
"eval_runtime": 125.2359, |
|
"eval_samples_per_second": 4.248, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09828373079642605, |
|
"step": 4392 |
|
}, |
|
{ |
|
"epoch": 61.11, |
|
"learning_rate": 1.675223880597015e-06, |
|
"loss": 0.4369, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 61.25, |
|
"learning_rate": 1.6692537313432834e-06, |
|
"loss": 0.407, |
|
"step": 4410 |
|
}, |
|
{ |
|
"epoch": 61.39, |
|
"learning_rate": 1.6632835820895521e-06, |
|
"loss": 0.4225, |
|
"step": 4420 |
|
}, |
|
{ |
|
"epoch": 61.53, |
|
"learning_rate": 1.657313432835821e-06, |
|
"loss": 0.4214, |
|
"step": 4430 |
|
}, |
|
{ |
|
"epoch": 61.66, |
|
"learning_rate": 1.6513432835820895e-06, |
|
"loss": 0.4069, |
|
"step": 4440 |
|
}, |
|
{ |
|
"epoch": 61.8, |
|
"learning_rate": 1.6453731343283582e-06, |
|
"loss": 0.4198, |
|
"step": 4450 |
|
}, |
|
{ |
|
"epoch": 61.94, |
|
"learning_rate": 1.6394029850746266e-06, |
|
"loss": 0.4257, |
|
"step": 4460 |
|
}, |
|
{ |
|
"epoch": 62.0, |
|
"eval_loss": 0.22298336029052734, |
|
"eval_runtime": 125.6188, |
|
"eval_samples_per_second": 4.235, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09770521308735618, |
|
"step": 4464 |
|
}, |
|
{ |
|
"epoch": 62.08, |
|
"learning_rate": 1.6334328358208955e-06, |
|
"loss": 0.4381, |
|
"step": 4470 |
|
}, |
|
{ |
|
"epoch": 62.22, |
|
"learning_rate": 1.6274626865671642e-06, |
|
"loss": 0.4198, |
|
"step": 4480 |
|
}, |
|
{ |
|
"epoch": 62.36, |
|
"learning_rate": 1.6214925373134327e-06, |
|
"loss": 0.4134, |
|
"step": 4490 |
|
}, |
|
{ |
|
"epoch": 62.5, |
|
"learning_rate": 1.6155223880597014e-06, |
|
"loss": 0.4187, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 62.64, |
|
"learning_rate": 1.60955223880597e-06, |
|
"loss": 0.4102, |
|
"step": 4510 |
|
}, |
|
{ |
|
"epoch": 62.78, |
|
"learning_rate": 1.6035820895522387e-06, |
|
"loss": 0.4316, |
|
"step": 4520 |
|
}, |
|
{ |
|
"epoch": 62.91, |
|
"learning_rate": 1.5976119402985074e-06, |
|
"loss": 0.4102, |
|
"step": 4530 |
|
}, |
|
{ |
|
"epoch": 63.0, |
|
"eval_loss": 0.221947580575943, |
|
"eval_runtime": 124.8306, |
|
"eval_samples_per_second": 4.262, |
|
"eval_steps_per_second": 0.537, |
|
"eval_wer": 0.09757665359645176, |
|
"step": 4536 |
|
}, |
|
{ |
|
"epoch": 63.06, |
|
"learning_rate": 1.591641791044776e-06, |
|
"loss": 0.4442, |
|
"step": 4540 |
|
}, |
|
{ |
|
"epoch": 63.19, |
|
"learning_rate": 1.5856716417910448e-06, |
|
"loss": 0.402, |
|
"step": 4550 |
|
}, |
|
{ |
|
"epoch": 63.33, |
|
"learning_rate": 1.5797014925373132e-06, |
|
"loss": 0.43, |
|
"step": 4560 |
|
}, |
|
{ |
|
"epoch": 63.47, |
|
"learning_rate": 1.573731343283582e-06, |
|
"loss": 0.4125, |
|
"step": 4570 |
|
}, |
|
{ |
|
"epoch": 63.61, |
|
"learning_rate": 1.5677611940298508e-06, |
|
"loss": 0.4186, |
|
"step": 4580 |
|
}, |
|
{ |
|
"epoch": 63.75, |
|
"learning_rate": 1.5617910447761193e-06, |
|
"loss": 0.4305, |
|
"step": 4590 |
|
}, |
|
{ |
|
"epoch": 63.89, |
|
"learning_rate": 1.555820895522388e-06, |
|
"loss": 0.4133, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 64.0, |
|
"eval_loss": 0.22209423780441284, |
|
"eval_runtime": 125.5387, |
|
"eval_samples_per_second": 4.238, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09841229028733046, |
|
"step": 4608 |
|
}, |
|
{ |
|
"epoch": 64.03, |
|
"learning_rate": 1.5498507462686566e-06, |
|
"loss": 0.4389, |
|
"step": 4610 |
|
}, |
|
{ |
|
"epoch": 64.17, |
|
"learning_rate": 1.5438805970149253e-06, |
|
"loss": 0.4117, |
|
"step": 4620 |
|
}, |
|
{ |
|
"epoch": 64.3, |
|
"learning_rate": 1.537910447761194e-06, |
|
"loss": 0.4234, |
|
"step": 4630 |
|
}, |
|
{ |
|
"epoch": 64.44, |
|
"learning_rate": 1.5319402985074625e-06, |
|
"loss": 0.41, |
|
"step": 4640 |
|
}, |
|
{ |
|
"epoch": 64.58, |
|
"learning_rate": 1.5259701492537314e-06, |
|
"loss": 0.4303, |
|
"step": 4650 |
|
}, |
|
{ |
|
"epoch": 64.72, |
|
"learning_rate": 1.5199999999999998e-06, |
|
"loss": 0.4186, |
|
"step": 4660 |
|
}, |
|
{ |
|
"epoch": 64.86, |
|
"learning_rate": 1.5140298507462685e-06, |
|
"loss": 0.413, |
|
"step": 4670 |
|
}, |
|
{ |
|
"epoch": 65.0, |
|
"learning_rate": 1.5080597014925372e-06, |
|
"loss": 0.4257, |
|
"step": 4680 |
|
}, |
|
{ |
|
"epoch": 65.0, |
|
"eval_loss": 0.22358950972557068, |
|
"eval_runtime": 125.5546, |
|
"eval_samples_per_second": 4.237, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09815517130552164, |
|
"step": 4680 |
|
}, |
|
{ |
|
"epoch": 65.14, |
|
"learning_rate": 1.5020895522388059e-06, |
|
"loss": 0.421, |
|
"step": 4690 |
|
}, |
|
{ |
|
"epoch": 65.28, |
|
"learning_rate": 1.4961194029850746e-06, |
|
"loss": 0.4224, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 65.42, |
|
"learning_rate": 1.490149253731343e-06, |
|
"loss": 0.4014, |
|
"step": 4710 |
|
}, |
|
{ |
|
"epoch": 65.55, |
|
"learning_rate": 1.484179104477612e-06, |
|
"loss": 0.4157, |
|
"step": 4720 |
|
}, |
|
{ |
|
"epoch": 65.69, |
|
"learning_rate": 1.4782089552238806e-06, |
|
"loss": 0.4156, |
|
"step": 4730 |
|
}, |
|
{ |
|
"epoch": 65.83, |
|
"learning_rate": 1.472238805970149e-06, |
|
"loss": 0.4291, |
|
"step": 4740 |
|
}, |
|
{ |
|
"epoch": 65.97, |
|
"learning_rate": 1.4662686567164178e-06, |
|
"loss": 0.4006, |
|
"step": 4750 |
|
}, |
|
{ |
|
"epoch": 66.0, |
|
"eval_loss": 0.22307933866977692, |
|
"eval_runtime": 125.6208, |
|
"eval_samples_per_second": 4.235, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09924792697820917, |
|
"step": 4752 |
|
}, |
|
{ |
|
"epoch": 66.11, |
|
"learning_rate": 1.4602985074626867e-06, |
|
"loss": 0.4356, |
|
"step": 4760 |
|
}, |
|
{ |
|
"epoch": 66.25, |
|
"learning_rate": 1.4543283582089551e-06, |
|
"loss": 0.4209, |
|
"step": 4770 |
|
}, |
|
{ |
|
"epoch": 66.39, |
|
"learning_rate": 1.4483582089552238e-06, |
|
"loss": 0.4167, |
|
"step": 4780 |
|
}, |
|
{ |
|
"epoch": 66.53, |
|
"learning_rate": 1.4423880597014925e-06, |
|
"loss": 0.4166, |
|
"step": 4790 |
|
}, |
|
{ |
|
"epoch": 66.66, |
|
"learning_rate": 1.4364179104477612e-06, |
|
"loss": 0.3998, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 66.8, |
|
"learning_rate": 1.4304477611940299e-06, |
|
"loss": 0.4148, |
|
"step": 4810 |
|
}, |
|
{ |
|
"epoch": 66.94, |
|
"learning_rate": 1.4244776119402983e-06, |
|
"loss": 0.404, |
|
"step": 4820 |
|
}, |
|
{ |
|
"epoch": 67.0, |
|
"eval_loss": 0.22272136807441711, |
|
"eval_runtime": 125.0862, |
|
"eval_samples_per_second": 4.253, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09834801054187825, |
|
"step": 4824 |
|
}, |
|
{ |
|
"epoch": 67.08, |
|
"learning_rate": 1.4185074626865672e-06, |
|
"loss": 0.429, |
|
"step": 4830 |
|
}, |
|
{ |
|
"epoch": 67.22, |
|
"learning_rate": 1.4125373134328357e-06, |
|
"loss": 0.4102, |
|
"step": 4840 |
|
}, |
|
{ |
|
"epoch": 67.36, |
|
"learning_rate": 1.4065671641791044e-06, |
|
"loss": 0.4212, |
|
"step": 4850 |
|
}, |
|
{ |
|
"epoch": 67.5, |
|
"learning_rate": 1.400597014925373e-06, |
|
"loss": 0.417, |
|
"step": 4860 |
|
}, |
|
{ |
|
"epoch": 67.64, |
|
"learning_rate": 1.3946268656716418e-06, |
|
"loss": 0.4192, |
|
"step": 4870 |
|
}, |
|
{ |
|
"epoch": 67.78, |
|
"learning_rate": 1.3886567164179104e-06, |
|
"loss": 0.43, |
|
"step": 4880 |
|
}, |
|
{ |
|
"epoch": 67.91, |
|
"learning_rate": 1.382686567164179e-06, |
|
"loss": 0.409, |
|
"step": 4890 |
|
}, |
|
{ |
|
"epoch": 68.0, |
|
"eval_loss": 0.22348527610301971, |
|
"eval_runtime": 125.2017, |
|
"eval_samples_per_second": 4.249, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09905508774185254, |
|
"step": 4896 |
|
}, |
|
{ |
|
"epoch": 68.06, |
|
"learning_rate": 1.3767164179104478e-06, |
|
"loss": 0.438, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 68.19, |
|
"learning_rate": 1.3707462686567165e-06, |
|
"loss": 0.4121, |
|
"step": 4910 |
|
}, |
|
{ |
|
"epoch": 68.33, |
|
"learning_rate": 1.364776119402985e-06, |
|
"loss": 0.4257, |
|
"step": 4920 |
|
}, |
|
{ |
|
"epoch": 68.47, |
|
"learning_rate": 1.3588059701492536e-06, |
|
"loss": 0.4182, |
|
"step": 4930 |
|
}, |
|
{ |
|
"epoch": 68.61, |
|
"learning_rate": 1.3528358208955223e-06, |
|
"loss": 0.4199, |
|
"step": 4940 |
|
}, |
|
{ |
|
"epoch": 68.75, |
|
"learning_rate": 1.346865671641791e-06, |
|
"loss": 0.4121, |
|
"step": 4950 |
|
}, |
|
{ |
|
"epoch": 68.89, |
|
"learning_rate": 1.3408955223880597e-06, |
|
"loss": 0.4075, |
|
"step": 4960 |
|
}, |
|
{ |
|
"epoch": 69.0, |
|
"eval_loss": 0.22422996163368225, |
|
"eval_runtime": 125.3571, |
|
"eval_samples_per_second": 4.244, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09776949283280838, |
|
"step": 4968 |
|
}, |
|
{ |
|
"epoch": 69.03, |
|
"learning_rate": 1.3349253731343284e-06, |
|
"loss": 0.4332, |
|
"step": 4970 |
|
}, |
|
{ |
|
"epoch": 69.17, |
|
"learning_rate": 1.328955223880597e-06, |
|
"loss": 0.4177, |
|
"step": 4980 |
|
}, |
|
{ |
|
"epoch": 69.3, |
|
"learning_rate": 1.3229850746268655e-06, |
|
"loss": 0.4106, |
|
"step": 4990 |
|
}, |
|
{ |
|
"epoch": 69.44, |
|
"learning_rate": 1.3170149253731342e-06, |
|
"loss": 0.4016, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 69.58, |
|
"learning_rate": 1.311044776119403e-06, |
|
"loss": 0.4155, |
|
"step": 5010 |
|
}, |
|
{ |
|
"epoch": 69.72, |
|
"learning_rate": 1.3050746268656716e-06, |
|
"loss": 0.4201, |
|
"step": 5020 |
|
}, |
|
{ |
|
"epoch": 69.86, |
|
"learning_rate": 1.2991044776119402e-06, |
|
"loss": 0.4156, |
|
"step": 5030 |
|
}, |
|
{ |
|
"epoch": 70.0, |
|
"learning_rate": 1.2931343283582087e-06, |
|
"loss": 0.4167, |
|
"step": 5040 |
|
}, |
|
{ |
|
"epoch": 70.0, |
|
"eval_loss": 0.22484691441059113, |
|
"eval_runtime": 125.3698, |
|
"eval_samples_per_second": 4.243, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09892652825094812, |
|
"step": 5040 |
|
}, |
|
{ |
|
"epoch": 70.14, |
|
"learning_rate": 1.2871641791044776e-06, |
|
"loss": 0.4207, |
|
"step": 5050 |
|
}, |
|
{ |
|
"epoch": 70.28, |
|
"learning_rate": 1.2811940298507463e-06, |
|
"loss": 0.416, |
|
"step": 5060 |
|
}, |
|
{ |
|
"epoch": 70.42, |
|
"learning_rate": 1.2752238805970148e-06, |
|
"loss": 0.4038, |
|
"step": 5070 |
|
}, |
|
{ |
|
"epoch": 70.55, |
|
"learning_rate": 1.2692537313432837e-06, |
|
"loss": 0.4246, |
|
"step": 5080 |
|
}, |
|
{ |
|
"epoch": 70.69, |
|
"learning_rate": 1.2632835820895521e-06, |
|
"loss": 0.4291, |
|
"step": 5090 |
|
}, |
|
{ |
|
"epoch": 70.83, |
|
"learning_rate": 1.2573134328358208e-06, |
|
"loss": 0.4151, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 70.97, |
|
"learning_rate": 1.2513432835820895e-06, |
|
"loss": 0.4026, |
|
"step": 5110 |
|
}, |
|
{ |
|
"epoch": 71.0, |
|
"eval_loss": 0.2241600751876831, |
|
"eval_runtime": 124.9558, |
|
"eval_samples_per_second": 4.258, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09847657003278266, |
|
"step": 5112 |
|
}, |
|
{ |
|
"epoch": 71.11, |
|
"learning_rate": 1.2453731343283582e-06, |
|
"loss": 0.4355, |
|
"step": 5120 |
|
}, |
|
{ |
|
"epoch": 71.25, |
|
"learning_rate": 1.2394029850746269e-06, |
|
"loss": 0.416, |
|
"step": 5130 |
|
}, |
|
{ |
|
"epoch": 71.39, |
|
"learning_rate": 1.2334328358208953e-06, |
|
"loss": 0.4108, |
|
"step": 5140 |
|
}, |
|
{ |
|
"epoch": 71.53, |
|
"learning_rate": 1.2274626865671642e-06, |
|
"loss": 0.4108, |
|
"step": 5150 |
|
}, |
|
{ |
|
"epoch": 71.66, |
|
"learning_rate": 1.221492537313433e-06, |
|
"loss": 0.4215, |
|
"step": 5160 |
|
}, |
|
{ |
|
"epoch": 71.8, |
|
"learning_rate": 1.2155223880597014e-06, |
|
"loss": 0.4252, |
|
"step": 5170 |
|
}, |
|
{ |
|
"epoch": 71.94, |
|
"learning_rate": 1.20955223880597e-06, |
|
"loss": 0.404, |
|
"step": 5180 |
|
}, |
|
{ |
|
"epoch": 72.0, |
|
"eval_loss": 0.22358117997646332, |
|
"eval_runtime": 125.3804, |
|
"eval_samples_per_second": 4.243, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09886224850549592, |
|
"step": 5184 |
|
}, |
|
{ |
|
"epoch": 72.08, |
|
"learning_rate": 1.2035820895522387e-06, |
|
"loss": 0.425, |
|
"step": 5190 |
|
}, |
|
{ |
|
"epoch": 72.22, |
|
"learning_rate": 1.1976119402985074e-06, |
|
"loss": 0.4107, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 72.36, |
|
"learning_rate": 1.191641791044776e-06, |
|
"loss": 0.4141, |
|
"step": 5210 |
|
}, |
|
{ |
|
"epoch": 72.5, |
|
"learning_rate": 1.1856716417910446e-06, |
|
"loss": 0.4141, |
|
"step": 5220 |
|
}, |
|
{ |
|
"epoch": 72.64, |
|
"learning_rate": 1.1797014925373135e-06, |
|
"loss": 0.4156, |
|
"step": 5230 |
|
}, |
|
{ |
|
"epoch": 72.78, |
|
"learning_rate": 1.173731343283582e-06, |
|
"loss": 0.4386, |
|
"step": 5240 |
|
}, |
|
{ |
|
"epoch": 72.91, |
|
"learning_rate": 1.1677611940298506e-06, |
|
"loss": 0.4162, |
|
"step": 5250 |
|
}, |
|
{ |
|
"epoch": 73.0, |
|
"eval_loss": 0.22407032549381256, |
|
"eval_runtime": 125.1954, |
|
"eval_samples_per_second": 4.249, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09860512952368708, |
|
"step": 5256 |
|
}, |
|
{ |
|
"epoch": 73.06, |
|
"learning_rate": 1.1617910447761195e-06, |
|
"loss": 0.4415, |
|
"step": 5260 |
|
}, |
|
{ |
|
"epoch": 73.19, |
|
"learning_rate": 1.155820895522388e-06, |
|
"loss": 0.3949, |
|
"step": 5270 |
|
}, |
|
{ |
|
"epoch": 73.33, |
|
"learning_rate": 1.1498507462686567e-06, |
|
"loss": 0.4348, |
|
"step": 5280 |
|
}, |
|
{ |
|
"epoch": 73.47, |
|
"learning_rate": 1.1438805970149251e-06, |
|
"loss": 0.4097, |
|
"step": 5290 |
|
}, |
|
{ |
|
"epoch": 73.61, |
|
"learning_rate": 1.137910447761194e-06, |
|
"loss": 0.416, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 73.75, |
|
"learning_rate": 1.1319402985074627e-06, |
|
"loss": 0.4222, |
|
"step": 5310 |
|
}, |
|
{ |
|
"epoch": 73.89, |
|
"learning_rate": 1.1259701492537312e-06, |
|
"loss": 0.4094, |
|
"step": 5320 |
|
}, |
|
{ |
|
"epoch": 74.0, |
|
"eval_loss": 0.22439990937709808, |
|
"eval_runtime": 125.4587, |
|
"eval_samples_per_second": 4.24, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09905508774185254, |
|
"step": 5328 |
|
}, |
|
{ |
|
"epoch": 74.03, |
|
"learning_rate": 1.12e-06, |
|
"loss": 0.4523, |
|
"step": 5330 |
|
}, |
|
{ |
|
"epoch": 74.17, |
|
"learning_rate": 1.1140298507462685e-06, |
|
"loss": 0.4009, |
|
"step": 5340 |
|
}, |
|
{ |
|
"epoch": 74.3, |
|
"learning_rate": 1.1080597014925372e-06, |
|
"loss": 0.4297, |
|
"step": 5350 |
|
}, |
|
{ |
|
"epoch": 74.44, |
|
"learning_rate": 1.102089552238806e-06, |
|
"loss": 0.3987, |
|
"step": 5360 |
|
}, |
|
{ |
|
"epoch": 74.58, |
|
"learning_rate": 1.0961194029850746e-06, |
|
"loss": 0.431, |
|
"step": 5370 |
|
}, |
|
{ |
|
"epoch": 74.72, |
|
"learning_rate": 1.0901492537313433e-06, |
|
"loss": 0.4287, |
|
"step": 5380 |
|
}, |
|
{ |
|
"epoch": 74.86, |
|
"learning_rate": 1.0841791044776117e-06, |
|
"loss": 0.4254, |
|
"step": 5390 |
|
}, |
|
{ |
|
"epoch": 75.0, |
|
"learning_rate": 1.0782089552238804e-06, |
|
"loss": 0.4147, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 75.0, |
|
"eval_loss": 0.2246961146593094, |
|
"eval_runtime": 125.3134, |
|
"eval_samples_per_second": 4.245, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09886224850549592, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 75.14, |
|
"learning_rate": 1.0722388059701493e-06, |
|
"loss": 0.4198, |
|
"step": 5410 |
|
}, |
|
{ |
|
"epoch": 75.28, |
|
"learning_rate": 1.0662686567164178e-06, |
|
"loss": 0.4259, |
|
"step": 5420 |
|
}, |
|
{ |
|
"epoch": 75.42, |
|
"learning_rate": 1.0602985074626865e-06, |
|
"loss": 0.4051, |
|
"step": 5430 |
|
}, |
|
{ |
|
"epoch": 75.55, |
|
"learning_rate": 1.0543283582089554e-06, |
|
"loss": 0.4169, |
|
"step": 5440 |
|
}, |
|
{ |
|
"epoch": 75.69, |
|
"learning_rate": 1.0483582089552238e-06, |
|
"loss": 0.4143, |
|
"step": 5450 |
|
}, |
|
{ |
|
"epoch": 75.83, |
|
"learning_rate": 1.0423880597014925e-06, |
|
"loss": 0.4163, |
|
"step": 5460 |
|
}, |
|
{ |
|
"epoch": 75.97, |
|
"learning_rate": 1.036417910447761e-06, |
|
"loss": 0.4096, |
|
"step": 5470 |
|
}, |
|
{ |
|
"epoch": 76.0, |
|
"eval_loss": 0.22438716888427734, |
|
"eval_runtime": 125.0559, |
|
"eval_samples_per_second": 4.254, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09834801054187825, |
|
"step": 5472 |
|
}, |
|
{ |
|
"epoch": 76.11, |
|
"learning_rate": 1.0304477611940299e-06, |
|
"loss": 0.4215, |
|
"step": 5480 |
|
}, |
|
{ |
|
"epoch": 76.25, |
|
"learning_rate": 1.0244776119402986e-06, |
|
"loss": 0.4364, |
|
"step": 5490 |
|
}, |
|
{ |
|
"epoch": 76.39, |
|
"learning_rate": 1.018507462686567e-06, |
|
"loss": 0.4055, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 76.53, |
|
"learning_rate": 1.012537313432836e-06, |
|
"loss": 0.4264, |
|
"step": 5510 |
|
}, |
|
{ |
|
"epoch": 76.66, |
|
"learning_rate": 1.0065671641791044e-06, |
|
"loss": 0.4109, |
|
"step": 5520 |
|
}, |
|
{ |
|
"epoch": 76.8, |
|
"learning_rate": 1.000597014925373e-06, |
|
"loss": 0.4232, |
|
"step": 5530 |
|
}, |
|
{ |
|
"epoch": 76.94, |
|
"learning_rate": 9.946268656716418e-07, |
|
"loss": 0.4112, |
|
"step": 5540 |
|
}, |
|
{ |
|
"epoch": 77.0, |
|
"eval_loss": 0.223554790019989, |
|
"eval_runtime": 125.0537, |
|
"eval_samples_per_second": 4.254, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09809089156006942, |
|
"step": 5544 |
|
}, |
|
{ |
|
"epoch": 77.08, |
|
"learning_rate": 9.886567164179105e-07, |
|
"loss": 0.4247, |
|
"step": 5550 |
|
}, |
|
{ |
|
"epoch": 77.22, |
|
"learning_rate": 9.826865671641791e-07, |
|
"loss": 0.418, |
|
"step": 5560 |
|
}, |
|
{ |
|
"epoch": 77.36, |
|
"learning_rate": 9.767164179104476e-07, |
|
"loss": 0.4292, |
|
"step": 5570 |
|
}, |
|
{ |
|
"epoch": 77.5, |
|
"learning_rate": 9.707462686567163e-07, |
|
"loss": 0.4222, |
|
"step": 5580 |
|
}, |
|
{ |
|
"epoch": 77.64, |
|
"learning_rate": 9.64776119402985e-07, |
|
"loss": 0.4019, |
|
"step": 5590 |
|
}, |
|
{ |
|
"epoch": 77.78, |
|
"learning_rate": 9.588059701492537e-07, |
|
"loss": 0.429, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 77.91, |
|
"learning_rate": 9.528358208955224e-07, |
|
"loss": 0.3987, |
|
"step": 5610 |
|
}, |
|
{ |
|
"epoch": 78.0, |
|
"eval_loss": 0.22421398758888245, |
|
"eval_runtime": 125.3563, |
|
"eval_samples_per_second": 4.244, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09815517130552164, |
|
"step": 5616 |
|
}, |
|
{ |
|
"epoch": 78.06, |
|
"learning_rate": 9.46865671641791e-07, |
|
"loss": 0.4405, |
|
"step": 5620 |
|
}, |
|
{ |
|
"epoch": 78.19, |
|
"learning_rate": 9.408955223880597e-07, |
|
"loss": 0.397, |
|
"step": 5630 |
|
}, |
|
{ |
|
"epoch": 78.33, |
|
"learning_rate": 9.349253731343283e-07, |
|
"loss": 0.4311, |
|
"step": 5640 |
|
}, |
|
{ |
|
"epoch": 78.47, |
|
"learning_rate": 9.28955223880597e-07, |
|
"loss": 0.4229, |
|
"step": 5650 |
|
}, |
|
{ |
|
"epoch": 78.61, |
|
"learning_rate": 9.229850746268656e-07, |
|
"loss": 0.4181, |
|
"step": 5660 |
|
}, |
|
{ |
|
"epoch": 78.75, |
|
"learning_rate": 9.170149253731343e-07, |
|
"loss": 0.4098, |
|
"step": 5670 |
|
}, |
|
{ |
|
"epoch": 78.89, |
|
"learning_rate": 9.110447761194029e-07, |
|
"loss": 0.3953, |
|
"step": 5680 |
|
}, |
|
{ |
|
"epoch": 79.0, |
|
"eval_loss": 0.22594541311264038, |
|
"eval_runtime": 125.534, |
|
"eval_samples_per_second": 4.238, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09834801054187825, |
|
"step": 5688 |
|
}, |
|
{ |
|
"epoch": 79.03, |
|
"learning_rate": 9.050746268656716e-07, |
|
"loss": 0.4253, |
|
"step": 5690 |
|
}, |
|
{ |
|
"epoch": 79.17, |
|
"learning_rate": 8.991044776119403e-07, |
|
"loss": 0.4078, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 79.3, |
|
"learning_rate": 8.931343283582089e-07, |
|
"loss": 0.4296, |
|
"step": 5710 |
|
}, |
|
{ |
|
"epoch": 79.44, |
|
"learning_rate": 8.871641791044776e-07, |
|
"loss": 0.4045, |
|
"step": 5720 |
|
}, |
|
{ |
|
"epoch": 79.58, |
|
"learning_rate": 8.811940298507462e-07, |
|
"loss": 0.431, |
|
"step": 5730 |
|
}, |
|
{ |
|
"epoch": 79.72, |
|
"learning_rate": 8.752238805970149e-07, |
|
"loss": 0.4179, |
|
"step": 5740 |
|
}, |
|
{ |
|
"epoch": 79.86, |
|
"learning_rate": 8.692537313432835e-07, |
|
"loss": 0.4253, |
|
"step": 5750 |
|
}, |
|
{ |
|
"epoch": 80.0, |
|
"learning_rate": 8.632835820895522e-07, |
|
"loss": 0.4093, |
|
"step": 5760 |
|
}, |
|
{ |
|
"epoch": 80.0, |
|
"eval_loss": 0.22387731075286865, |
|
"eval_runtime": 125.4924, |
|
"eval_samples_per_second": 4.239, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09905508774185254, |
|
"step": 5760 |
|
}, |
|
{ |
|
"epoch": 80.14, |
|
"learning_rate": 8.573134328358208e-07, |
|
"loss": 0.4283, |
|
"step": 5770 |
|
}, |
|
{ |
|
"epoch": 80.28, |
|
"learning_rate": 8.513432835820895e-07, |
|
"loss": 0.4202, |
|
"step": 5780 |
|
}, |
|
{ |
|
"epoch": 80.42, |
|
"learning_rate": 8.453731343283582e-07, |
|
"loss": 0.4022, |
|
"step": 5790 |
|
}, |
|
{ |
|
"epoch": 80.55, |
|
"learning_rate": 8.394029850746268e-07, |
|
"loss": 0.4185, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 80.69, |
|
"learning_rate": 8.334328358208956e-07, |
|
"loss": 0.4139, |
|
"step": 5810 |
|
}, |
|
{ |
|
"epoch": 80.83, |
|
"learning_rate": 8.274626865671641e-07, |
|
"loss": 0.4199, |
|
"step": 5820 |
|
}, |
|
{ |
|
"epoch": 80.97, |
|
"learning_rate": 8.214925373134328e-07, |
|
"loss": 0.406, |
|
"step": 5830 |
|
}, |
|
{ |
|
"epoch": 81.0, |
|
"eval_loss": 0.22382712364196777, |
|
"eval_runtime": 125.0152, |
|
"eval_samples_per_second": 4.255, |
|
"eval_steps_per_second": 0.536, |
|
"eval_wer": 0.09802661181461722, |
|
"step": 5832 |
|
}, |
|
{ |
|
"epoch": 81.11, |
|
"learning_rate": 8.155223880597014e-07, |
|
"loss": 0.4209, |
|
"step": 5840 |
|
}, |
|
{ |
|
"epoch": 81.25, |
|
"learning_rate": 8.095522388059701e-07, |
|
"loss": 0.4123, |
|
"step": 5850 |
|
}, |
|
{ |
|
"epoch": 81.39, |
|
"learning_rate": 8.035820895522388e-07, |
|
"loss": 0.4118, |
|
"step": 5860 |
|
}, |
|
{ |
|
"epoch": 81.53, |
|
"learning_rate": 7.976119402985074e-07, |
|
"loss": 0.4332, |
|
"step": 5870 |
|
}, |
|
{ |
|
"epoch": 81.66, |
|
"learning_rate": 7.916417910447761e-07, |
|
"loss": 0.4112, |
|
"step": 5880 |
|
}, |
|
{ |
|
"epoch": 81.8, |
|
"learning_rate": 7.856716417910447e-07, |
|
"loss": 0.4147, |
|
"step": 5890 |
|
}, |
|
{ |
|
"epoch": 81.94, |
|
"learning_rate": 7.797014925373135e-07, |
|
"loss": 0.4149, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 82.0, |
|
"eval_loss": 0.22396345436573029, |
|
"eval_runtime": 125.2602, |
|
"eval_samples_per_second": 4.247, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.099505045960018, |
|
"step": 5904 |
|
}, |
|
{ |
|
"epoch": 82.08, |
|
"learning_rate": 7.737313432835821e-07, |
|
"loss": 0.4406, |
|
"step": 5910 |
|
}, |
|
{ |
|
"epoch": 82.22, |
|
"learning_rate": 7.677611940298507e-07, |
|
"loss": 0.4132, |
|
"step": 5920 |
|
}, |
|
{ |
|
"epoch": 82.36, |
|
"learning_rate": 7.617910447761193e-07, |
|
"loss": 0.4313, |
|
"step": 5930 |
|
}, |
|
{ |
|
"epoch": 82.5, |
|
"learning_rate": 7.55820895522388e-07, |
|
"loss": 0.4303, |
|
"step": 5940 |
|
}, |
|
{ |
|
"epoch": 82.64, |
|
"learning_rate": 7.498507462686567e-07, |
|
"loss": 0.4102, |
|
"step": 5950 |
|
}, |
|
{ |
|
"epoch": 82.78, |
|
"learning_rate": 7.438805970149254e-07, |
|
"loss": 0.4299, |
|
"step": 5960 |
|
}, |
|
{ |
|
"epoch": 82.91, |
|
"learning_rate": 7.37910447761194e-07, |
|
"loss": 0.4017, |
|
"step": 5970 |
|
}, |
|
{ |
|
"epoch": 83.0, |
|
"eval_loss": 0.22398056089878082, |
|
"eval_runtime": 125.384, |
|
"eval_samples_per_second": 4.243, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09873368901459151, |
|
"step": 5976 |
|
}, |
|
{ |
|
"epoch": 83.06, |
|
"learning_rate": 7.319402985074626e-07, |
|
"loss": 0.4342, |
|
"step": 5980 |
|
}, |
|
{ |
|
"epoch": 83.19, |
|
"learning_rate": 7.259701492537313e-07, |
|
"loss": 0.4093, |
|
"step": 5990 |
|
}, |
|
{ |
|
"epoch": 83.33, |
|
"learning_rate": 7.2e-07, |
|
"loss": 0.4185, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 83.47, |
|
"learning_rate": 7.140298507462687e-07, |
|
"loss": 0.4069, |
|
"step": 6010 |
|
}, |
|
{ |
|
"epoch": 83.61, |
|
"learning_rate": 7.080597014925372e-07, |
|
"loss": 0.4128, |
|
"step": 6020 |
|
}, |
|
{ |
|
"epoch": 83.75, |
|
"learning_rate": 7.020895522388059e-07, |
|
"loss": 0.4249, |
|
"step": 6030 |
|
}, |
|
{ |
|
"epoch": 83.89, |
|
"learning_rate": 6.961194029850745e-07, |
|
"loss": 0.4065, |
|
"step": 6040 |
|
}, |
|
{ |
|
"epoch": 84.0, |
|
"eval_loss": 0.2244831919670105, |
|
"eval_runtime": 125.4981, |
|
"eval_samples_per_second": 4.239, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09789805232371279, |
|
"step": 6048 |
|
}, |
|
{ |
|
"epoch": 84.03, |
|
"learning_rate": 6.901492537313433e-07, |
|
"loss": 0.4279, |
|
"step": 6050 |
|
}, |
|
{ |
|
"epoch": 84.17, |
|
"learning_rate": 6.84179104477612e-07, |
|
"loss": 0.4015, |
|
"step": 6060 |
|
}, |
|
{ |
|
"epoch": 84.3, |
|
"learning_rate": 6.782089552238806e-07, |
|
"loss": 0.4032, |
|
"step": 6070 |
|
}, |
|
{ |
|
"epoch": 84.44, |
|
"learning_rate": 6.722388059701492e-07, |
|
"loss": 0.3993, |
|
"step": 6080 |
|
}, |
|
{ |
|
"epoch": 84.58, |
|
"learning_rate": 6.662686567164178e-07, |
|
"loss": 0.4321, |
|
"step": 6090 |
|
}, |
|
{ |
|
"epoch": 84.72, |
|
"learning_rate": 6.602985074626866e-07, |
|
"loss": 0.4098, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 84.86, |
|
"learning_rate": 6.543283582089552e-07, |
|
"loss": 0.4063, |
|
"step": 6110 |
|
}, |
|
{ |
|
"epoch": 85.0, |
|
"learning_rate": 6.483582089552239e-07, |
|
"loss": 0.4315, |
|
"step": 6120 |
|
}, |
|
{ |
|
"epoch": 85.0, |
|
"eval_loss": 0.22491712868213654, |
|
"eval_runtime": 125.405, |
|
"eval_samples_per_second": 4.242, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09776949283280838, |
|
"step": 6120 |
|
}, |
|
{ |
|
"epoch": 85.14, |
|
"learning_rate": 6.423880597014924e-07, |
|
"loss": 0.4178, |
|
"step": 6130 |
|
}, |
|
{ |
|
"epoch": 85.28, |
|
"learning_rate": 6.364179104477611e-07, |
|
"loss": 0.4266, |
|
"step": 6140 |
|
}, |
|
{ |
|
"epoch": 85.42, |
|
"learning_rate": 6.304477611940299e-07, |
|
"loss": 0.4006, |
|
"step": 6150 |
|
}, |
|
{ |
|
"epoch": 85.55, |
|
"learning_rate": 6.244776119402985e-07, |
|
"loss": 0.4203, |
|
"step": 6160 |
|
}, |
|
{ |
|
"epoch": 85.69, |
|
"learning_rate": 6.185074626865672e-07, |
|
"loss": 0.4072, |
|
"step": 6170 |
|
}, |
|
{ |
|
"epoch": 85.83, |
|
"learning_rate": 6.125373134328357e-07, |
|
"loss": 0.415, |
|
"step": 6180 |
|
}, |
|
{ |
|
"epoch": 85.97, |
|
"learning_rate": 6.065671641791044e-07, |
|
"loss": 0.421, |
|
"step": 6190 |
|
}, |
|
{ |
|
"epoch": 86.0, |
|
"eval_loss": 0.223923921585083, |
|
"eval_runtime": 125.2942, |
|
"eval_samples_per_second": 4.246, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09770521308735618, |
|
"step": 6192 |
|
}, |
|
{ |
|
"epoch": 86.11, |
|
"learning_rate": 6.005970149253731e-07, |
|
"loss": 0.4201, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 86.25, |
|
"learning_rate": 5.946268656716418e-07, |
|
"loss": 0.4278, |
|
"step": 6210 |
|
}, |
|
{ |
|
"epoch": 86.39, |
|
"learning_rate": 5.886567164179104e-07, |
|
"loss": 0.3922, |
|
"step": 6220 |
|
}, |
|
{ |
|
"epoch": 86.53, |
|
"learning_rate": 5.82686567164179e-07, |
|
"loss": 0.4327, |
|
"step": 6230 |
|
}, |
|
{ |
|
"epoch": 86.66, |
|
"learning_rate": 5.767164179104478e-07, |
|
"loss": 0.4016, |
|
"step": 6240 |
|
}, |
|
{ |
|
"epoch": 86.8, |
|
"learning_rate": 5.707462686567164e-07, |
|
"loss": 0.4131, |
|
"step": 6250 |
|
}, |
|
{ |
|
"epoch": 86.94, |
|
"learning_rate": 5.647761194029851e-07, |
|
"loss": 0.4061, |
|
"step": 6260 |
|
}, |
|
{ |
|
"epoch": 87.0, |
|
"eval_loss": 0.22433649003505707, |
|
"eval_runtime": 125.2628, |
|
"eval_samples_per_second": 4.247, |
|
"eval_steps_per_second": 0.535, |
|
"eval_wer": 0.09744809410554735, |
|
"step": 6264 |
|
}, |
|
{ |
|
"epoch": 87.08, |
|
"learning_rate": 5.588059701492537e-07, |
|
"loss": 0.4244, |
|
"step": 6270 |
|
}, |
|
{ |
|
"epoch": 87.22, |
|
"learning_rate": 5.528358208955224e-07, |
|
"loss": 0.3966, |
|
"step": 6280 |
|
}, |
|
{ |
|
"epoch": 87.36, |
|
"learning_rate": 5.46865671641791e-07, |
|
"loss": 0.4151, |
|
"step": 6290 |
|
}, |
|
{ |
|
"epoch": 87.5, |
|
"learning_rate": 5.408955223880597e-07, |
|
"loss": 0.4137, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 87.64, |
|
"learning_rate": 5.349253731343283e-07, |
|
"loss": 0.4028, |
|
"step": 6310 |
|
}, |
|
{ |
|
"epoch": 87.78, |
|
"learning_rate": 5.28955223880597e-07, |
|
"loss": 0.4202, |
|
"step": 6320 |
|
}, |
|
{ |
|
"epoch": 87.91, |
|
"learning_rate": 5.229850746268657e-07, |
|
"loss": 0.4096, |
|
"step": 6330 |
|
}, |
|
{ |
|
"epoch": 88.0, |
|
"eval_loss": 0.22435232996940613, |
|
"eval_runtime": 125.981, |
|
"eval_samples_per_second": 4.223, |
|
"eval_steps_per_second": 0.532, |
|
"eval_wer": 0.09815517130552164, |
|
"step": 6336 |
|
}, |
|
{ |
|
"epoch": 88.06, |
|
"learning_rate": 5.170149253731343e-07, |
|
"loss": 0.427, |
|
"step": 6340 |
|
}, |
|
{ |
|
"epoch": 88.19, |
|
"learning_rate": 5.11044776119403e-07, |
|
"loss": 0.4153, |
|
"step": 6350 |
|
}, |
|
{ |
|
"epoch": 88.33, |
|
"learning_rate": 5.050746268656716e-07, |
|
"loss": 0.4118, |
|
"step": 6360 |
|
}, |
|
{ |
|
"epoch": 88.47, |
|
"learning_rate": 4.991044776119403e-07, |
|
"loss": 0.4019, |
|
"step": 6370 |
|
}, |
|
{ |
|
"epoch": 88.61, |
|
"learning_rate": 4.93134328358209e-07, |
|
"loss": 0.425, |
|
"step": 6380 |
|
}, |
|
{ |
|
"epoch": 88.75, |
|
"learning_rate": 4.871641791044776e-07, |
|
"loss": 0.414, |
|
"step": 6390 |
|
}, |
|
{ |
|
"epoch": 88.89, |
|
"learning_rate": 4.811940298507462e-07, |
|
"loss": 0.4171, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 89.0, |
|
"eval_loss": 0.22459125518798828, |
|
"eval_runtime": 127.3897, |
|
"eval_samples_per_second": 4.176, |
|
"eval_steps_per_second": 0.526, |
|
"eval_wer": 0.09744809410554735, |
|
"step": 6408 |
|
}, |
|
{ |
|
"epoch": 89.03, |
|
"learning_rate": 4.752238805970149e-07, |
|
"loss": 0.4365, |
|
"step": 6410 |
|
}, |
|
{ |
|
"epoch": 89.17, |
|
"learning_rate": 4.6925373134328353e-07, |
|
"loss": 0.4088, |
|
"step": 6420 |
|
}, |
|
{ |
|
"epoch": 89.3, |
|
"learning_rate": 4.632835820895522e-07, |
|
"loss": 0.4325, |
|
"step": 6430 |
|
}, |
|
{ |
|
"epoch": 89.44, |
|
"learning_rate": 4.5731343283582084e-07, |
|
"loss": 0.4199, |
|
"step": 6440 |
|
}, |
|
{ |
|
"epoch": 89.58, |
|
"learning_rate": 4.513432835820895e-07, |
|
"loss": 0.423, |
|
"step": 6450 |
|
}, |
|
{ |
|
"epoch": 89.72, |
|
"learning_rate": 4.453731343283582e-07, |
|
"loss": 0.3992, |
|
"step": 6460 |
|
}, |
|
{ |
|
"epoch": 89.86, |
|
"learning_rate": 4.3940298507462684e-07, |
|
"loss": 0.4168, |
|
"step": 6470 |
|
}, |
|
{ |
|
"epoch": 90.0, |
|
"learning_rate": 4.334328358208955e-07, |
|
"loss": 0.4189, |
|
"step": 6480 |
|
}, |
|
{ |
|
"epoch": 90.0, |
|
"eval_loss": 0.22403044998645782, |
|
"eval_runtime": 125.3957, |
|
"eval_samples_per_second": 4.243, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09802661181461722, |
|
"step": 6480 |
|
}, |
|
{ |
|
"epoch": 90.14, |
|
"learning_rate": 4.2746268656716415e-07, |
|
"loss": 0.4052, |
|
"step": 6490 |
|
}, |
|
{ |
|
"epoch": 90.28, |
|
"learning_rate": 4.2149253731343283e-07, |
|
"loss": 0.4133, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 90.42, |
|
"learning_rate": 4.1552238805970146e-07, |
|
"loss": 0.4123, |
|
"step": 6510 |
|
}, |
|
{ |
|
"epoch": 90.55, |
|
"learning_rate": 4.0955223880597014e-07, |
|
"loss": 0.4276, |
|
"step": 6520 |
|
}, |
|
{ |
|
"epoch": 90.69, |
|
"learning_rate": 4.0358208955223877e-07, |
|
"loss": 0.4255, |
|
"step": 6530 |
|
}, |
|
{ |
|
"epoch": 90.83, |
|
"learning_rate": 3.976119402985074e-07, |
|
"loss": 0.4321, |
|
"step": 6540 |
|
}, |
|
{ |
|
"epoch": 90.97, |
|
"learning_rate": 3.9164179104477614e-07, |
|
"loss": 0.4106, |
|
"step": 6550 |
|
}, |
|
{ |
|
"epoch": 91.0, |
|
"eval_loss": 0.22358761727809906, |
|
"eval_runtime": 125.8141, |
|
"eval_samples_per_second": 4.228, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09783377257826059, |
|
"step": 6552 |
|
}, |
|
{ |
|
"epoch": 91.11, |
|
"learning_rate": 3.8567164179104477e-07, |
|
"loss": 0.4308, |
|
"step": 6560 |
|
}, |
|
{ |
|
"epoch": 91.25, |
|
"learning_rate": 3.7970149253731345e-07, |
|
"loss": 0.4134, |
|
"step": 6570 |
|
}, |
|
{ |
|
"epoch": 91.39, |
|
"learning_rate": 3.737313432835821e-07, |
|
"loss": 0.3925, |
|
"step": 6580 |
|
}, |
|
{ |
|
"epoch": 91.53, |
|
"learning_rate": 3.677611940298507e-07, |
|
"loss": 0.4281, |
|
"step": 6590 |
|
}, |
|
{ |
|
"epoch": 91.66, |
|
"learning_rate": 3.617910447761194e-07, |
|
"loss": 0.4126, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 91.8, |
|
"learning_rate": 3.55820895522388e-07, |
|
"loss": 0.4165, |
|
"step": 6610 |
|
}, |
|
{ |
|
"epoch": 91.94, |
|
"learning_rate": 3.498507462686567e-07, |
|
"loss": 0.408, |
|
"step": 6620 |
|
}, |
|
{ |
|
"epoch": 92.0, |
|
"eval_loss": 0.2234458327293396, |
|
"eval_runtime": 126.0268, |
|
"eval_samples_per_second": 4.221, |
|
"eval_steps_per_second": 0.532, |
|
"eval_wer": 0.09828373079642605, |
|
"step": 6624 |
|
}, |
|
{ |
|
"epoch": 92.08, |
|
"learning_rate": 3.4388059701492533e-07, |
|
"loss": 0.4238, |
|
"step": 6630 |
|
}, |
|
{ |
|
"epoch": 92.22, |
|
"learning_rate": 3.3791044776119407e-07, |
|
"loss": 0.4042, |
|
"step": 6640 |
|
}, |
|
{ |
|
"epoch": 92.36, |
|
"learning_rate": 3.3253731343283583e-07, |
|
"loss": 0.409, |
|
"step": 6650 |
|
}, |
|
{ |
|
"epoch": 92.5, |
|
"learning_rate": 3.2656716417910446e-07, |
|
"loss": 0.4259, |
|
"step": 6660 |
|
}, |
|
{ |
|
"epoch": 92.64, |
|
"learning_rate": 3.205970149253731e-07, |
|
"loss": 0.4099, |
|
"step": 6670 |
|
}, |
|
{ |
|
"epoch": 92.78, |
|
"learning_rate": 3.1462686567164177e-07, |
|
"loss": 0.4041, |
|
"step": 6680 |
|
}, |
|
{ |
|
"epoch": 92.91, |
|
"learning_rate": 3.086567164179104e-07, |
|
"loss": 0.4218, |
|
"step": 6690 |
|
}, |
|
{ |
|
"epoch": 93.0, |
|
"eval_loss": 0.22388821840286255, |
|
"eval_runtime": 126.5555, |
|
"eval_samples_per_second": 4.204, |
|
"eval_steps_per_second": 0.529, |
|
"eval_wer": 0.09847657003278266, |
|
"step": 6696 |
|
}, |
|
{ |
|
"epoch": 93.06, |
|
"learning_rate": 3.0268656716417913e-07, |
|
"loss": 0.434, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 93.19, |
|
"learning_rate": 2.9671641791044776e-07, |
|
"loss": 0.389, |
|
"step": 6710 |
|
}, |
|
{ |
|
"epoch": 93.33, |
|
"learning_rate": 2.9074626865671644e-07, |
|
"loss": 0.4336, |
|
"step": 6720 |
|
}, |
|
{ |
|
"epoch": 93.47, |
|
"learning_rate": 2.8477611940298507e-07, |
|
"loss": 0.4085, |
|
"step": 6730 |
|
}, |
|
{ |
|
"epoch": 93.61, |
|
"learning_rate": 2.788059701492537e-07, |
|
"loss": 0.4192, |
|
"step": 6740 |
|
}, |
|
{ |
|
"epoch": 93.75, |
|
"learning_rate": 2.728358208955224e-07, |
|
"loss": 0.4147, |
|
"step": 6750 |
|
}, |
|
{ |
|
"epoch": 93.89, |
|
"learning_rate": 2.66865671641791e-07, |
|
"loss": 0.3997, |
|
"step": 6760 |
|
}, |
|
{ |
|
"epoch": 94.0, |
|
"eval_loss": 0.22373326122760773, |
|
"eval_runtime": 125.7889, |
|
"eval_samples_per_second": 4.229, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09828373079642605, |
|
"step": 6768 |
|
}, |
|
{ |
|
"epoch": 94.03, |
|
"learning_rate": 2.608955223880597e-07, |
|
"loss": 0.4271, |
|
"step": 6770 |
|
}, |
|
{ |
|
"epoch": 94.17, |
|
"learning_rate": 2.549253731343283e-07, |
|
"loss": 0.3954, |
|
"step": 6780 |
|
}, |
|
{ |
|
"epoch": 94.3, |
|
"learning_rate": 2.48955223880597e-07, |
|
"loss": 0.4211, |
|
"step": 6790 |
|
}, |
|
{ |
|
"epoch": 94.44, |
|
"learning_rate": 2.4298507462686564e-07, |
|
"loss": 0.3873, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 94.58, |
|
"learning_rate": 2.370149253731343e-07, |
|
"loss": 0.4161, |
|
"step": 6810 |
|
}, |
|
{ |
|
"epoch": 94.72, |
|
"learning_rate": 2.3104477611940298e-07, |
|
"loss": 0.4285, |
|
"step": 6820 |
|
}, |
|
{ |
|
"epoch": 94.86, |
|
"learning_rate": 2.2507462686567163e-07, |
|
"loss": 0.4227, |
|
"step": 6830 |
|
}, |
|
{ |
|
"epoch": 95.0, |
|
"learning_rate": 2.191044776119403e-07, |
|
"loss": 0.4173, |
|
"step": 6840 |
|
}, |
|
{ |
|
"epoch": 95.0, |
|
"eval_loss": 0.22381591796875, |
|
"eval_runtime": 127.1644, |
|
"eval_samples_per_second": 4.184, |
|
"eval_steps_per_second": 0.527, |
|
"eval_wer": 0.09802661181461722, |
|
"step": 6840 |
|
}, |
|
{ |
|
"epoch": 95.14, |
|
"learning_rate": 2.1313432835820894e-07, |
|
"loss": 0.4196, |
|
"step": 6850 |
|
}, |
|
{ |
|
"epoch": 95.28, |
|
"learning_rate": 2.0716417910447763e-07, |
|
"loss": 0.43, |
|
"step": 6860 |
|
}, |
|
{ |
|
"epoch": 95.42, |
|
"learning_rate": 2.0119402985074625e-07, |
|
"loss": 0.4102, |
|
"step": 6870 |
|
}, |
|
{ |
|
"epoch": 95.55, |
|
"learning_rate": 1.952238805970149e-07, |
|
"loss": 0.4332, |
|
"step": 6880 |
|
}, |
|
{ |
|
"epoch": 95.69, |
|
"learning_rate": 1.8925373134328357e-07, |
|
"loss": 0.3953, |
|
"step": 6890 |
|
}, |
|
{ |
|
"epoch": 95.83, |
|
"learning_rate": 1.8328358208955222e-07, |
|
"loss": 0.4254, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 95.97, |
|
"learning_rate": 1.773134328358209e-07, |
|
"loss": 0.4134, |
|
"step": 6910 |
|
}, |
|
{ |
|
"epoch": 96.0, |
|
"eval_loss": 0.22350211441516876, |
|
"eval_runtime": 125.8445, |
|
"eval_samples_per_second": 4.227, |
|
"eval_steps_per_second": 0.532, |
|
"eval_wer": 0.09821945105097384, |
|
"step": 6912 |
|
}, |
|
{ |
|
"epoch": 96.11, |
|
"learning_rate": 1.7134328358208956e-07, |
|
"loss": 0.4253, |
|
"step": 6920 |
|
}, |
|
{ |
|
"epoch": 96.25, |
|
"learning_rate": 1.653731343283582e-07, |
|
"loss": 0.4149, |
|
"step": 6930 |
|
}, |
|
{ |
|
"epoch": 96.39, |
|
"learning_rate": 1.5940298507462685e-07, |
|
"loss": 0.4107, |
|
"step": 6940 |
|
}, |
|
{ |
|
"epoch": 96.53, |
|
"learning_rate": 1.5343283582089553e-07, |
|
"loss": 0.4191, |
|
"step": 6950 |
|
}, |
|
{ |
|
"epoch": 96.66, |
|
"learning_rate": 1.4746268656716418e-07, |
|
"loss": 0.4086, |
|
"step": 6960 |
|
}, |
|
{ |
|
"epoch": 96.8, |
|
"learning_rate": 1.4149253731343284e-07, |
|
"loss": 0.4165, |
|
"step": 6970 |
|
}, |
|
{ |
|
"epoch": 96.94, |
|
"learning_rate": 1.3552238805970147e-07, |
|
"loss": 0.3959, |
|
"step": 6980 |
|
}, |
|
{ |
|
"epoch": 97.0, |
|
"eval_loss": 0.22365529835224152, |
|
"eval_runtime": 125.471, |
|
"eval_samples_per_second": 4.24, |
|
"eval_steps_per_second": 0.534, |
|
"eval_wer": 0.09789805232371279, |
|
"step": 6984 |
|
}, |
|
{ |
|
"epoch": 97.08, |
|
"learning_rate": 1.2955223880597012e-07, |
|
"loss": 0.4332, |
|
"step": 6990 |
|
}, |
|
{ |
|
"epoch": 97.22, |
|
"learning_rate": 1.235820895522388e-07, |
|
"loss": 0.42, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 97.36, |
|
"learning_rate": 1.1761194029850746e-07, |
|
"loss": 0.4226, |
|
"step": 7010 |
|
}, |
|
{ |
|
"epoch": 97.5, |
|
"learning_rate": 1.1164179104477612e-07, |
|
"loss": 0.4085, |
|
"step": 7020 |
|
}, |
|
{ |
|
"epoch": 97.64, |
|
"learning_rate": 1.0567164179104477e-07, |
|
"loss": 0.3979, |
|
"step": 7030 |
|
}, |
|
{ |
|
"epoch": 97.78, |
|
"learning_rate": 9.970149253731343e-08, |
|
"loss": 0.4226, |
|
"step": 7040 |
|
}, |
|
{ |
|
"epoch": 97.91, |
|
"learning_rate": 9.373134328358209e-08, |
|
"loss": 0.4149, |
|
"step": 7050 |
|
}, |
|
{ |
|
"epoch": 98.0, |
|
"eval_loss": 0.22375571727752686, |
|
"eval_runtime": 125.7958, |
|
"eval_samples_per_second": 4.229, |
|
"eval_steps_per_second": 0.533, |
|
"eval_wer": 0.09815517130552164, |
|
"step": 7056 |
|
}, |
|
{ |
|
"epoch": 98.06, |
|
"learning_rate": 8.776119402985074e-08, |
|
"loss": 0.4358, |
|
"step": 7060 |
|
}, |
|
{ |
|
"epoch": 98.19, |
|
"learning_rate": 8.17910447761194e-08, |
|
"loss": 0.4027, |
|
"step": 7070 |
|
}, |
|
{ |
|
"epoch": 98.33, |
|
"learning_rate": 7.582089552238805e-08, |
|
"loss": 0.4191, |
|
"step": 7080 |
|
}, |
|
{ |
|
"epoch": 98.47, |
|
"learning_rate": 6.985074626865671e-08, |
|
"loss": 0.409, |
|
"step": 7090 |
|
}, |
|
{ |
|
"epoch": 98.61, |
|
"learning_rate": 6.388059701492538e-08, |
|
"loss": 0.419, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 98.75, |
|
"learning_rate": 5.791044776119403e-08, |
|
"loss": 0.4202, |
|
"step": 7110 |
|
}, |
|
{ |
|
"epoch": 98.89, |
|
"learning_rate": 5.194029850746268e-08, |
|
"loss": 0.4125, |
|
"step": 7120 |
|
}, |
|
{ |
|
"epoch": 99.0, |
|
"eval_loss": 0.22379297018051147, |
|
"eval_runtime": 128.8043, |
|
"eval_samples_per_second": 4.13, |
|
"eval_steps_per_second": 0.52, |
|
"eval_wer": 0.09834801054187825, |
|
"step": 7128 |
|
}, |
|
{ |
|
"epoch": 99.03, |
|
"learning_rate": 4.597014925373134e-08, |
|
"loss": 0.4244, |
|
"step": 7130 |
|
}, |
|
{ |
|
"epoch": 99.17, |
|
"learning_rate": 4e-08, |
|
"loss": 0.407, |
|
"step": 7140 |
|
}, |
|
{ |
|
"epoch": 99.3, |
|
"learning_rate": 3.4029850746268657e-08, |
|
"loss": 0.4252, |
|
"step": 7150 |
|
}, |
|
{ |
|
"epoch": 99.44, |
|
"learning_rate": 2.8059701492537312e-08, |
|
"loss": 0.413, |
|
"step": 7160 |
|
}, |
|
{ |
|
"epoch": 99.58, |
|
"learning_rate": 2.2089552238805968e-08, |
|
"loss": 0.416, |
|
"step": 7170 |
|
}, |
|
{ |
|
"epoch": 99.72, |
|
"learning_rate": 1.6119402985074627e-08, |
|
"loss": 0.393, |
|
"step": 7180 |
|
}, |
|
{ |
|
"epoch": 99.86, |
|
"learning_rate": 1.0149253731343283e-08, |
|
"loss": 0.4266, |
|
"step": 7190 |
|
}, |
|
{ |
|
"epoch": 100.0, |
|
"learning_rate": 4.17910447761194e-09, |
|
"loss": 0.4111, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 100.0, |
|
"eval_loss": 0.22352680563926697, |
|
"eval_runtime": 127.8588, |
|
"eval_samples_per_second": 4.161, |
|
"eval_steps_per_second": 0.524, |
|
"eval_wer": 0.09821945105097384, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 100.0, |
|
"step": 7200, |
|
"total_flos": 2.7207912943242897e+20, |
|
"train_loss": 0.4237175911333826, |
|
"train_runtime": 188884.487, |
|
"train_samples_per_second": 2.445, |
|
"train_steps_per_second": 0.038 |
|
} |
|
], |
|
"max_steps": 7200, |
|
"num_train_epochs": 100, |
|
"total_flos": 2.7207912943242897e+20, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|